Command that produces this log: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-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])
>>> trigger_label_ffn.layers.0.weight: torch.Size([450, 1024])
>>> trigger_label_ffn.layers.0.bias: torch.Size([450])
>>> trigger_label_ffn.layers.1.weight: torch.Size([233, 450])
>>> trigger_label_ffn.layers.1.bias: torch.Size([233])
>>> trigger_crf.transition: torch.Size([235, 235])
n_trainable_params: 560511990, n_nontrainable_params: 0
----------------------------------------------------------------------------------------------------
******************************
Epoch: 0
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-22 23:22:31.644303: step: 4/526, loss: 3.6318392753601074
2023-01-22 23:22:32.812393: step: 8/526, loss: 28.890989303588867
2023-01-22 23:22:33.936767: step: 12/526, loss: 18.407047271728516
2023-01-22 23:22:35.079891: step: 16/526, loss: 25.845109939575195
2023-01-22 23:22:36.195272: step: 20/526, loss: 9.149889945983887
2023-01-22 23:22:37.330649: step: 24/526, loss: 3.810722827911377
2023-01-22 23:22:38.507591: step: 28/526, loss: 11.724077224731445
2023-01-22 23:22:39.657699: step: 32/526, loss: 14.911371231079102
2023-01-22 23:22:40.785404: step: 36/526, loss: 8.573379516601562
2023-01-22 23:22:41.914426: step: 40/526, loss: 4.186492919921875
2023-01-22 23:22:43.083215: step: 44/526, loss: 14.293676376342773
2023-01-22 23:22:44.202638: step: 48/526, loss: 3.38279128074646
2023-01-22 23:22:45.336238: step: 52/526, loss: 20.770090103149414
2023-01-22 23:22:46.478973: step: 56/526, loss: 11.954267501831055
2023-01-22 23:22:47.601503: step: 60/526, loss: 3.2696142196655273
2023-01-22 23:22:48.763072: step: 64/526, loss: 3.5716280937194824
2023-01-22 23:22:49.908952: step: 68/526, loss: 3.261629581451416
2023-01-22 23:22:51.076622: step: 72/526, loss: 13.102941513061523
2023-01-22 23:22:52.227587: step: 76/526, loss: 33.936065673828125
2023-01-22 23:22:53.388631: step: 80/526, loss: 3.9718658924102783
2023-01-22 23:22:54.534020: step: 84/526, loss: 9.024330139160156
2023-01-22 23:22:55.653620: step: 88/526, loss: 3.0318570137023926
2023-01-22 23:22:56.806804: step: 92/526, loss: 9.598344802856445
2023-01-22 23:22:57.946870: step: 96/526, loss: 7.868564605712891
2023-01-22 23:22:59.068308: step: 100/526, loss: 20.54723358154297
2023-01-22 23:23:00.206934: step: 104/526, loss: 7.756442070007324
2023-01-22 23:23:01.329310: step: 108/526, loss: 3.0901856422424316
2023-01-22 23:23:02.467768: step: 112/526, loss: 3.561924934387207
2023-01-22 23:23:03.578153: step: 116/526, loss: 7.165226936340332
2023-01-22 23:23:04.736652: step: 120/526, loss: 23.627790451049805
2023-01-22 23:23:05.859492: step: 124/526, loss: 4.433967113494873
2023-01-22 23:23:06.975344: step: 128/526, loss: 13.168096542358398
2023-01-22 23:23:08.116327: step: 132/526, loss: 15.751042366027832
2023-01-22 23:23:09.235404: step: 136/526, loss: 23.246429443359375
2023-01-22 23:23:10.380353: step: 140/526, loss: 16.421527862548828
2023-01-22 23:23:11.496291: step: 144/526, loss: 3.2233738899230957
2023-01-22 23:23:12.645913: step: 148/526, loss: 16.15756607055664
2023-01-22 23:23:13.756963: step: 152/526, loss: 3.4238474369049072
2023-01-22 23:23:14.869353: step: 156/526, loss: 10.485424041748047
2023-01-22 23:23:15.987708: step: 160/526, loss: 9.064422607421875
2023-01-22 23:23:17.148518: step: 164/526, loss: 4.762728214263916
2023-01-22 23:23:18.288906: step: 168/526, loss: 30.001049041748047
2023-01-22 23:23:19.426207: step: 172/526, loss: 4.155209541320801
2023-01-22 23:23:20.545883: step: 176/526, loss: 2.397127151489258
2023-01-22 23:23:21.680422: step: 180/526, loss: 2.4548416137695312
2023-01-22 23:23:22.860659: step: 184/526, loss: 3.7789855003356934
2023-01-22 23:23:23.994997: step: 188/526, loss: 14.679725646972656
2023-01-22 23:23:25.139624: step: 192/526, loss: 11.192453384399414
2023-01-22 23:23:26.259332: step: 196/526, loss: 2.4589171409606934
2023-01-22 23:23:27.385067: step: 200/526, loss: 22.41259765625
2023-01-22 23:23:28.508917: step: 204/526, loss: 7.1796698570251465
2023-01-22 23:23:29.627180: step: 208/526, loss: 3.5711936950683594
2023-01-22 23:23:30.771310: step: 212/526, loss: 20.40176773071289
2023-01-22 23:23:31.912869: step: 216/526, loss: 28.562137603759766
2023-01-22 23:23:33.112608: step: 220/526, loss: 9.086514472961426
2023-01-22 23:23:34.229865: step: 224/526, loss: 9.796311378479004
2023-01-22 23:23:35.353358: step: 228/526, loss: 7.405766487121582
2023-01-22 23:23:36.488036: step: 232/526, loss: 17.26175308227539
2023-01-22 23:23:37.588784: step: 236/526, loss: 2.8710148334503174
2023-01-22 23:23:38.737265: step: 240/526, loss: 4.286104679107666
2023-01-22 23:23:39.851240: step: 244/526, loss: 9.266624450683594
2023-01-22 23:23:40.978668: step: 248/526, loss: 2.771188259124756
2023-01-22 23:23:42.112089: step: 252/526, loss: 3.888857126235962
2023-01-22 23:23:43.225437: step: 256/526, loss: 13.929132461547852
2023-01-22 23:23:44.356064: step: 260/526, loss: 4.139479160308838
2023-01-22 23:23:45.474275: step: 264/526, loss: 13.014013290405273
2023-01-22 23:23:46.610539: step: 268/526, loss: 3.2820091247558594
2023-01-22 23:23:47.785667: step: 272/526, loss: 12.483892440795898
2023-01-22 23:23:48.913234: step: 276/526, loss: 3.6978845596313477
2023-01-22 23:23:50.035475: step: 280/526, loss: 17.864959716796875
2023-01-22 23:23:51.175113: step: 284/526, loss: 1.820019245147705
2023-01-22 23:23:52.321353: step: 288/526, loss: 26.590755462646484
2023-01-22 23:23:53.442588: step: 292/526, loss: 4.36468505859375
2023-01-22 23:23:54.598392: step: 296/526, loss: 25.427658081054688
2023-01-22 23:23:55.757701: step: 300/526, loss: 7.74377965927124
2023-01-22 23:23:56.888453: step: 304/526, loss: 10.137595176696777
2023-01-22 23:23:58.015055: step: 308/526, loss: 9.967369079589844
2023-01-22 23:23:59.185713: step: 312/526, loss: 15.322711944580078
2023-01-22 23:24:00.336573: step: 316/526, loss: 3.326475143432617
2023-01-22 23:24:01.475522: step: 320/526, loss: 20.173986434936523
2023-01-22 23:24:02.629187: step: 324/526, loss: 7.19556999206543
2023-01-22 23:24:03.753985: step: 328/526, loss: 3.106248378753662
2023-01-22 23:24:04.908052: step: 332/526, loss: 14.252914428710938
2023-01-22 23:24:06.049048: step: 336/526, loss: 15.54052448272705
2023-01-22 23:24:07.187238: step: 340/526, loss: 10.941143989562988
2023-01-22 23:24:08.310757: step: 344/526, loss: 3.1308562755584717
2023-01-22 23:24:09.438296: step: 348/526, loss: 12.181527137756348
2023-01-22 23:24:10.585196: step: 352/526, loss: 21.351825714111328
2023-01-22 23:24:11.726670: step: 356/526, loss: 3.507929801940918
2023-01-22 23:24:12.904045: step: 360/526, loss: 3.4611740112304688
2023-01-22 23:24:14.031174: step: 364/526, loss: 8.646406173706055
2023-01-22 23:24:15.160274: step: 368/526, loss: 2.7202072143554688
2023-01-22 23:24:16.311781: step: 372/526, loss: 11.316137313842773
2023-01-22 23:24:17.450187: step: 376/526, loss: 6.047792434692383
2023-01-22 23:24:18.574747: step: 380/526, loss: 9.796491622924805
2023-01-22 23:24:19.735208: step: 384/526, loss: 8.999422073364258
2023-01-22 23:24:20.841891: step: 388/526, loss: 3.275467872619629
2023-01-22 23:24:21.994104: step: 392/526, loss: 2.560004949569702
2023-01-22 23:24:23.144114: step: 396/526, loss: 14.490044593811035
2023-01-22 23:24:24.332667: step: 400/526, loss: 3.7974331378936768
2023-01-22 23:24:25.454213: step: 404/526, loss: 8.72499942779541
2023-01-22 23:24:26.608515: step: 408/526, loss: 8.436064720153809
2023-01-22 23:24:27.727182: step: 412/526, loss: 2.135772705078125
2023-01-22 23:24:28.842383: step: 416/526, loss: 2.2120108604431152
2023-01-22 23:24:29.988152: step: 420/526, loss: 11.856246948242188
2023-01-22 23:24:31.142611: step: 424/526, loss: 3.0674328804016113
2023-01-22 23:24:32.291265: step: 428/526, loss: 10.840810775756836
2023-01-22 23:24:33.448103: step: 432/526, loss: 4.878076553344727
2023-01-22 23:24:34.575026: step: 436/526, loss: 3.2610654830932617
2023-01-22 23:24:35.718588: step: 440/526, loss: 6.676850318908691
2023-01-22 23:24:36.848707: step: 444/526, loss: 2.6051454544067383
2023-01-22 23:24:37.964790: step: 448/526, loss: 1.9870959520339966
2023-01-22 23:24:39.084475: step: 452/526, loss: 1.5810116529464722
2023-01-22 23:24:40.214514: step: 456/526, loss: 12.493521690368652
2023-01-22 23:24:41.359274: step: 460/526, loss: 10.646100997924805
2023-01-22 23:24:42.519526: step: 464/526, loss: 13.667482376098633
2023-01-22 23:24:43.666920: step: 468/526, loss: 1.5309419631958008
2023-01-22 23:24:44.789381: step: 472/526, loss: 15.322973251342773
2023-01-22 23:24:45.901267: step: 476/526, loss: 1.8751522302627563
2023-01-22 23:24:47.022891: step: 480/526, loss: 4.105733871459961
2023-01-22 23:24:48.168440: step: 484/526, loss: 8.971606254577637
2023-01-22 23:24:49.285525: step: 488/526, loss: 5.2371320724487305
2023-01-22 23:24:50.404690: step: 492/526, loss: 1.2573308944702148
2023-01-22 23:24:51.524237: step: 496/526, loss: 6.7426252365112305
2023-01-22 23:24:52.633528: step: 500/526, loss: 7.719080924987793
2023-01-22 23:24:53.759066: step: 504/526, loss: 1.5554404258728027
2023-01-22 23:24:54.889361: step: 508/526, loss: 1.9200359582901
2023-01-22 23:24:56.025514: step: 512/526, loss: 8.222696304321289
2023-01-22 23:24:57.141695: step: 516/526, loss: 1.8079607486724854
2023-01-22 23:24:58.262906: step: 520/526, loss: 1.5630905628204346
2023-01-22 23:24:59.393753: step: 524/526, loss: 3.2997095584869385
2023-01-22 23:25:00.547179: step: 528/526, loss: 1.4388279914855957
2023-01-22 23:25:01.686254: step: 532/526, loss: 1.338409662246704
2023-01-22 23:25:02.823618: step: 536/526, loss: 1.5269181728363037
2023-01-22 23:25:03.970914: step: 540/526, loss: 2.7201998233795166
2023-01-22 23:25:05.111878: step: 544/526, loss: 3.768095016479492
2023-01-22 23:25:06.230930: step: 548/526, loss: 3.130605936050415
2023-01-22 23:25:07.368212: step: 552/526, loss: 2.2645978927612305
2023-01-22 23:25:08.481227: step: 556/526, loss: 1.4041845798492432
2023-01-22 23:25:09.640237: step: 560/526, loss: 9.178227424621582
2023-01-22 23:25:10.787550: step: 564/526, loss: 1.1238369941711426
2023-01-22 23:25:11.956325: step: 568/526, loss: 1.3538631200790405
2023-01-22 23:25:13.101038: step: 572/526, loss: 1.1342747211456299
2023-01-22 23:25:14.259469: step: 576/526, loss: 0.610762894153595
2023-01-22 23:25:15.408655: step: 580/526, loss: 0.8239659667015076
2023-01-22 23:25:16.554200: step: 584/526, loss: 2.9253759384155273
2023-01-22 23:25:17.699255: step: 588/526, loss: 2.825378894805908
2023-01-22 23:25:18.823686: step: 592/526, loss: 3.6761865615844727
2023-01-22 23:25:19.976937: step: 596/526, loss: 2.2604973316192627
2023-01-22 23:25:21.116680: step: 600/526, loss: 1.8053219318389893
2023-01-22 23:25:22.247222: step: 604/526, loss: 1.5901368856430054
2023-01-22 23:25:23.377619: step: 608/526, loss: 0.6941806674003601
2023-01-22 23:25:24.513493: step: 612/526, loss: 0.5261372923851013
2023-01-22 23:25:25.640277: step: 616/526, loss: 0.7327295541763306
2023-01-22 23:25:26.802650: step: 620/526, loss: 0.6329482793807983
2023-01-22 23:25:27.929476: step: 624/526, loss: 2.6085376739501953
2023-01-22 23:25:29.067976: step: 628/526, loss: 1.348832130432129
2023-01-22 23:25:30.206906: step: 632/526, loss: 0.6164334416389465
2023-01-22 23:25:31.341021: step: 636/526, loss: 0.8436727523803711
2023-01-22 23:25:32.444264: step: 640/526, loss: 1.7077959775924683
2023-01-22 23:25:33.585534: step: 644/526, loss: 0.9112004637718201
2023-01-22 23:25:34.718315: step: 648/526, loss: 0.9629526138305664
2023-01-22 23:25:35.857518: step: 652/526, loss: 3.245166778564453
2023-01-22 23:25:36.984314: step: 656/526, loss: 0.32384079694747925
2023-01-22 23:25:38.115100: step: 660/526, loss: 1.9293735027313232
2023-01-22 23:25:39.220974: step: 664/526, loss: 0.3393259048461914
2023-01-22 23:25:40.343073: step: 668/526, loss: 1.1617307662963867
2023-01-22 23:25:41.501686: step: 672/526, loss: 8.011707305908203
2023-01-22 23:25:42.628595: step: 676/526, loss: 2.6159844398498535
2023-01-22 23:25:43.750783: step: 680/526, loss: 1.7561559677124023
2023-01-22 23:25:44.862752: step: 684/526, loss: 0.5061033964157104
2023-01-22 23:25:46.013258: step: 688/526, loss: 1.9517956972122192
2023-01-22 23:25:47.119045: step: 692/526, loss: 2.0456690788269043
2023-01-22 23:25:48.277115: step: 696/526, loss: 1.0951050519943237
2023-01-22 23:25:49.393317: step: 700/526, loss: 1.2494298219680786
2023-01-22 23:25:50.505209: step: 704/526, loss: 0.6463273167610168
2023-01-22 23:25:51.634495: step: 708/526, loss: 0.38262584805488586
2023-01-22 23:25:52.768500: step: 712/526, loss: 3.2256932258605957
2023-01-22 23:25:53.878803: step: 716/526, loss: 4.036816596984863
2023-01-22 23:25:55.053740: step: 720/526, loss: 0.7773375511169434
2023-01-22 23:25:56.167244: step: 724/526, loss: 0.984978973865509
2023-01-22 23:25:57.293941: step: 728/526, loss: 2.834669589996338
2023-01-22 23:25:58.451056: step: 732/526, loss: 1.0841844081878662
2023-01-22 23:25:59.578553: step: 736/526, loss: 1.4302542209625244
2023-01-22 23:26:00.717147: step: 740/526, loss: 2.4996962547302246
2023-01-22 23:26:01.868125: step: 744/526, loss: 1.054992914199829
2023-01-22 23:26:03.006596: step: 748/526, loss: 0.9370424747467041
2023-01-22 23:26:04.130503: step: 752/526, loss: 2.3080639839172363
2023-01-22 23:26:05.291473: step: 756/526, loss: 6.626799583435059
2023-01-22 23:26:06.409988: step: 760/526, loss: 0.841479480266571
2023-01-22 23:26:07.546586: step: 764/526, loss: 9.992548942565918
2023-01-22 23:26:08.664150: step: 768/526, loss: 1.978711485862732
2023-01-22 23:26:09.804110: step: 772/526, loss: 0.7774362564086914
2023-01-22 23:26:10.942163: step: 776/526, loss: 1.2682746648788452
2023-01-22 23:26:12.089655: step: 780/526, loss: 2.283411979675293
2023-01-22 23:26:13.212973: step: 784/526, loss: 2.58374285697937
2023-01-22 23:26:14.338127: step: 788/526, loss: 0.33996516466140747
2023-01-22 23:26:15.482429: step: 792/526, loss: 0.7127280235290527
2023-01-22 23:26:16.605601: step: 796/526, loss: 2.485874652862549
2023-01-22 23:26:17.722489: step: 800/526, loss: 0.5513519048690796
2023-01-22 23:26:18.823000: step: 804/526, loss: 0.2581776976585388
2023-01-22 23:26:19.976383: step: 808/526, loss: 0.9015848636627197
2023-01-22 23:26:21.064598: step: 812/526, loss: 1.814470887184143
2023-01-22 23:26:22.191428: step: 816/526, loss: 0.8109980821609497
2023-01-22 23:26:23.308467: step: 820/526, loss: 0.8053920269012451
2023-01-22 23:26:24.424186: step: 824/526, loss: 0.6061736345291138
2023-01-22 23:26:25.548454: step: 828/526, loss: 0.5200212597846985
2023-01-22 23:26:26.671598: step: 832/526, loss: 0.5605607032775879
2023-01-22 23:26:27.798555: step: 836/526, loss: 2.9807093143463135
2023-01-22 23:26:28.950486: step: 840/526, loss: 3.461522340774536
2023-01-22 23:26:30.067321: step: 844/526, loss: 2.4613826274871826
2023-01-22 23:26:31.238771: step: 848/526, loss: 0.5394300222396851
2023-01-22 23:26:32.381758: step: 852/526, loss: 2.1785902976989746
2023-01-22 23:26:33.507571: step: 856/526, loss: 1.9200830459594727
2023-01-22 23:26:34.638070: step: 860/526, loss: 0.44600868225097656
2023-01-22 23:26:35.772391: step: 864/526, loss: 5.11099910736084
2023-01-22 23:26:36.870837: step: 868/526, loss: 0.9174662828445435
2023-01-22 23:26:37.991799: step: 872/526, loss: 0.5322202444076538
2023-01-22 23:26:39.106259: step: 876/526, loss: 0.2971850037574768
2023-01-22 23:26:40.230582: step: 880/526, loss: 3.78743314743042
2023-01-22 23:26:41.366388: step: 884/526, loss: 4.316065788269043
2023-01-22 23:26:42.491786: step: 888/526, loss: 3.725107192993164
2023-01-22 23:26:43.669236: step: 892/526, loss: 1.078489899635315
2023-01-22 23:26:44.823154: step: 896/526, loss: 1.4396113157272339
2023-01-22 23:26:45.966487: step: 900/526, loss: 1.194507360458374
2023-01-22 23:26:47.085555: step: 904/526, loss: 0.6034525632858276
2023-01-22 23:26:48.248023: step: 908/526, loss: 0.8795521259307861
2023-01-22 23:26:49.403079: step: 912/526, loss: 1.3526854515075684
2023-01-22 23:26:50.535432: step: 916/526, loss: 1.0072823762893677
2023-01-22 23:26:51.658541: step: 920/526, loss: 0.21270331740379333
2023-01-22 23:26:52.813268: step: 924/526, loss: 0.41289713978767395
2023-01-22 23:26:53.943514: step: 928/526, loss: 4.0356292724609375
2023-01-22 23:26:55.055733: step: 932/526, loss: 2.0324747562408447
2023-01-22 23:26:56.183355: step: 936/526, loss: 0.6113661527633667
2023-01-22 23:26:57.310961: step: 940/526, loss: 2.455641984939575
2023-01-22 23:26:58.431256: step: 944/526, loss: 0.4836846888065338
2023-01-22 23:26:59.542886: step: 948/526, loss: 0.7143409252166748
2023-01-22 23:27:00.733519: step: 952/526, loss: 0.5144330859184265
2023-01-22 23:27:01.857588: step: 956/526, loss: 0.7575192451477051
2023-01-22 23:27:03.005506: step: 960/526, loss: 1.4706535339355469
2023-01-22 23:27:04.154680: step: 964/526, loss: 3.752131700515747
2023-01-22 23:27:05.273654: step: 968/526, loss: 1.010324478149414
2023-01-22 23:27:06.391212: step: 972/526, loss: 1.2312567234039307
2023-01-22 23:27:07.519291: step: 976/526, loss: 2.3406429290771484
2023-01-22 23:27:08.657289: step: 980/526, loss: 0.9074604511260986
2023-01-22 23:27:09.776014: step: 984/526, loss: 0.6529759168624878
2023-01-22 23:27:10.915852: step: 988/526, loss: 0.2764093577861786
2023-01-22 23:27:12.043140: step: 992/526, loss: 0.3429710865020752
2023-01-22 23:27:13.162770: step: 996/526, loss: 0.3740905821323395
2023-01-22 23:27:14.281778: step: 1000/526, loss: 0.5420551896095276
2023-01-22 23:27:15.417314: step: 1004/526, loss: 0.45901262760162354
2023-01-22 23:27:16.556477: step: 1008/526, loss: 0.890532374382019
2023-01-22 23:27:17.663582: step: 1012/526, loss: 0.3833976089954376
2023-01-22 23:27:18.785566: step: 1016/526, loss: 0.4700547456741333
2023-01-22 23:27:19.905945: step: 1020/526, loss: 0.4177636206150055
2023-01-22 23:27:21.026994: step: 1024/526, loss: 1.8971961736679077
2023-01-22 23:27:22.159227: step: 1028/526, loss: 2.336444139480591
2023-01-22 23:27:23.276383: step: 1032/526, loss: 0.19568252563476562
2023-01-22 23:27:24.380294: step: 1036/526, loss: 0.4682191014289856
2023-01-22 23:27:25.510841: step: 1040/526, loss: 1.6938953399658203
2023-01-22 23:27:26.660063: step: 1044/526, loss: 0.4424464702606201
2023-01-22 23:27:27.769250: step: 1048/526, loss: 0.5344431400299072
2023-01-22 23:27:28.902666: step: 1052/526, loss: 1.361646056175232
2023-01-22 23:27:30.039896: step: 1056/526, loss: 0.36036643385887146
2023-01-22 23:27:31.167223: step: 1060/526, loss: 0.8183083534240723
2023-01-22 23:27:32.316876: step: 1064/526, loss: 0.3149799704551697
2023-01-22 23:27:33.458827: step: 1068/526, loss: 0.4732183516025543
2023-01-22 23:27:34.566536: step: 1072/526, loss: 0.19402772188186646
2023-01-22 23:27:35.694482: step: 1076/526, loss: 0.9440011978149414
2023-01-22 23:27:36.799306: step: 1080/526, loss: 1.884748101234436
2023-01-22 23:27:37.910789: step: 1084/526, loss: 1.3135898113250732
2023-01-22 23:27:39.023630: step: 1088/526, loss: 0.36445218324661255
2023-01-22 23:27:40.133083: step: 1092/526, loss: 0.5245578289031982
2023-01-22 23:27:41.291356: step: 1096/526, loss: 0.5936914682388306
2023-01-22 23:27:42.423808: step: 1100/526, loss: 0.8939400911331177
2023-01-22 23:27:43.543871: step: 1104/526, loss: 1.305603265762329
2023-01-22 23:27:44.678091: step: 1108/526, loss: 2.9500813484191895
2023-01-22 23:27:45.785753: step: 1112/526, loss: 0.7107867002487183
2023-01-22 23:27:46.908612: step: 1116/526, loss: 0.07613463699817657
2023-01-22 23:27:48.026131: step: 1120/526, loss: 0.30348050594329834
2023-01-22 23:27:49.153870: step: 1124/526, loss: 1.5272237062454224
2023-01-22 23:27:50.285364: step: 1128/526, loss: 1.7898383140563965
2023-01-22 23:27:51.424725: step: 1132/526, loss: 0.47858771681785583
2023-01-22 23:27:52.560232: step: 1136/526, loss: 0.3667069971561432
2023-01-22 23:27:53.691126: step: 1140/526, loss: 0.5482919812202454
2023-01-22 23:27:54.810312: step: 1144/526, loss: 0.37970858812332153
2023-01-22 23:27:55.934102: step: 1148/526, loss: 0.9039019346237183
2023-01-22 23:27:57.057711: step: 1152/526, loss: 4.6626691818237305
2023-01-22 23:27:58.201467: step: 1156/526, loss: 0.8359564542770386
2023-01-22 23:27:59.331299: step: 1160/526, loss: 4.585060119628906
2023-01-22 23:28:00.462190: step: 1164/526, loss: 1.1588298082351685
2023-01-22 23:28:01.583362: step: 1168/526, loss: 1.0112495422363281
2023-01-22 23:28:02.713353: step: 1172/526, loss: 0.4761594235897064
2023-01-22 23:28:03.820334: step: 1176/526, loss: 0.31148630380630493
2023-01-22 23:28:04.983631: step: 1180/526, loss: 0.5811941027641296
2023-01-22 23:28:06.149687: step: 1184/526, loss: 0.33053335547447205
2023-01-22 23:28:07.308949: step: 1188/526, loss: 0.4351780414581299
2023-01-22 23:28:08.426532: step: 1192/526, loss: 1.6941075325012207
2023-01-22 23:28:09.570776: step: 1196/526, loss: 0.2341902256011963
2023-01-22 23:28:10.721246: step: 1200/526, loss: 0.772669792175293
2023-01-22 23:28:11.868205: step: 1204/526, loss: 0.9370273947715759
2023-01-22 23:28:13.012568: step: 1208/526, loss: 0.5496181845664978
2023-01-22 23:28:14.124956: step: 1212/526, loss: 0.28019237518310547
2023-01-22 23:28:15.285341: step: 1216/526, loss: 0.5980945825576782
2023-01-22 23:28:16.435510: step: 1220/526, loss: 0.33800241351127625
2023-01-22 23:28:17.575951: step: 1224/526, loss: 0.5343923568725586
2023-01-22 23:28:18.727463: step: 1228/526, loss: 0.3986811339855194
2023-01-22 23:28:19.879791: step: 1232/526, loss: 0.6579622030258179
2023-01-22 23:28:21.016274: step: 1236/526, loss: 1.0317293405532837
2023-01-22 23:28:22.186226: step: 1240/526, loss: 1.3522977828979492
2023-01-22 23:28:23.289488: step: 1244/526, loss: 0.8583003282546997
2023-01-22 23:28:24.430393: step: 1248/526, loss: 0.3571805953979492
2023-01-22 23:28:25.560670: step: 1252/526, loss: 0.5468298196792603
2023-01-22 23:28:26.714089: step: 1256/526, loss: 0.5932650566101074
2023-01-22 23:28:27.833831: step: 1260/526, loss: 0.5215433835983276
2023-01-22 23:28:29.000849: step: 1264/526, loss: 1.1786279678344727
2023-01-22 23:28:30.150842: step: 1268/526, loss: 3.7608094215393066
2023-01-22 23:28:31.311514: step: 1272/526, loss: 1.6436172723770142
2023-01-22 23:28:32.433742: step: 1276/526, loss: 0.4854907989501953
2023-01-22 23:28:33.554269: step: 1280/526, loss: 0.728380024433136
2023-01-22 23:28:34.727897: step: 1284/526, loss: 0.3912392556667328
2023-01-22 23:28:35.848871: step: 1288/526, loss: 1.0520737171173096
2023-01-22 23:28:36.978111: step: 1292/526, loss: 0.3631967604160309
2023-01-22 23:28:38.102087: step: 1296/526, loss: 0.8719676733016968
2023-01-22 23:28:39.225318: step: 1300/526, loss: 0.7937418222427368
2023-01-22 23:28:40.368168: step: 1304/526, loss: 0.5097143650054932
2023-01-22 23:28:41.488048: step: 1308/526, loss: 1.2263057231903076
2023-01-22 23:28:42.612429: step: 1312/526, loss: 0.2847522795200348
2023-01-22 23:28:43.736142: step: 1316/526, loss: 0.31432899832725525
2023-01-22 23:28:44.884394: step: 1320/526, loss: 3.461671829223633
2023-01-22 23:28:46.027289: step: 1324/526, loss: 0.6790217161178589
2023-01-22 23:28:47.176250: step: 1328/526, loss: 0.9770418405532837
2023-01-22 23:28:48.300547: step: 1332/526, loss: 0.4239872097969055
2023-01-22 23:28:49.421099: step: 1336/526, loss: 0.6387863159179688
2023-01-22 23:28:50.538835: step: 1340/526, loss: 0.45950907468795776
2023-01-22 23:28:51.703396: step: 1344/526, loss: 0.6816931366920471
2023-01-22 23:28:52.817804: step: 1348/526, loss: 0.9068479537963867
2023-01-22 23:28:53.937563: step: 1352/526, loss: 0.4446907043457031
2023-01-22 23:28:55.076101: step: 1356/526, loss: 0.4947296977043152
2023-01-22 23:28:56.220385: step: 1360/526, loss: 1.7559940814971924
2023-01-22 23:28:57.362304: step: 1364/526, loss: 2.938032388687134
2023-01-22 23:28:58.529896: step: 1368/526, loss: 0.8173549175262451
2023-01-22 23:28:59.641405: step: 1372/526, loss: 0.510219395160675
2023-01-22 23:29:00.772285: step: 1376/526, loss: 1.6447769403457642
2023-01-22 23:29:01.955020: step: 1380/526, loss: 0.4797564446926117
2023-01-22 23:29:03.099656: step: 1384/526, loss: 0.532613217830658
2023-01-22 23:29:04.230234: step: 1388/526, loss: 0.7305388450622559
2023-01-22 23:29:05.390994: step: 1392/526, loss: 0.8144544363021851
2023-01-22 23:29:06.537339: step: 1396/526, loss: 1.5057934522628784
2023-01-22 23:29:07.641713: step: 1400/526, loss: 1.0043981075286865
2023-01-22 23:29:08.786832: step: 1404/526, loss: 4.387916564941406
2023-01-22 23:29:09.911000: step: 1408/526, loss: 0.29746735095977783
2023-01-22 23:29:11.041964: step: 1412/526, loss: 0.5198326110839844
2023-01-22 23:29:12.168217: step: 1416/526, loss: 0.27850157022476196
2023-01-22 23:29:13.342165: step: 1420/526, loss: 2.4872961044311523
2023-01-22 23:29:14.477692: step: 1424/526, loss: 2.2086496353149414
2023-01-22 23:29:15.600394: step: 1428/526, loss: 1.7859861850738525
2023-01-22 23:29:16.742963: step: 1432/526, loss: 0.4378030598163605
2023-01-22 23:29:17.863535: step: 1436/526, loss: 0.4930229187011719
2023-01-22 23:29:19.011168: step: 1440/526, loss: 0.6065353155136108
2023-01-22 23:29:20.143616: step: 1444/526, loss: 0.47361889481544495
2023-01-22 23:29:21.262332: step: 1448/526, loss: 0.37605801224708557
2023-01-22 23:29:22.410863: step: 1452/526, loss: 1.4961729049682617
2023-01-22 23:29:23.561484: step: 1456/526, loss: 1.583017349243164
2023-01-22 23:29:24.667836: step: 1460/526, loss: 0.2598903179168701
2023-01-22 23:29:25.802848: step: 1464/526, loss: 0.45981264114379883
2023-01-22 23:29:26.954567: step: 1468/526, loss: 0.44727057218551636
2023-01-22 23:29:28.082460: step: 1472/526, loss: 0.404015451669693
2023-01-22 23:29:29.213123: step: 1476/526, loss: 2.0474090576171875
2023-01-22 23:29:30.341099: step: 1480/526, loss: 1.4260640144348145
2023-01-22 23:29:31.499208: step: 1484/526, loss: 1.044939637184143
2023-01-22 23:29:32.621230: step: 1488/526, loss: 3.0949370861053467
2023-01-22 23:29:33.773616: step: 1492/526, loss: 0.4306080937385559
2023-01-22 23:29:34.960899: step: 1496/526, loss: 0.46039143204689026
2023-01-22 23:29:36.097020: step: 1500/526, loss: 0.3191283941268921
2023-01-22 23:29:37.213784: step: 1504/526, loss: 0.2647761404514313
2023-01-22 23:29:38.358547: step: 1508/526, loss: 2.128882646560669
2023-01-22 23:29:39.496650: step: 1512/526, loss: 0.4349292516708374
2023-01-22 23:29:40.636803: step: 1516/526, loss: 1.600499153137207
2023-01-22 23:29:41.780889: step: 1520/526, loss: 1.4844815731048584
2023-01-22 23:29:42.915543: step: 1524/526, loss: 2.144289970397949
2023-01-22 23:29:44.071632: step: 1528/526, loss: 0.36953020095825195
2023-01-22 23:29:45.205024: step: 1532/526, loss: 0.37135472893714905
2023-01-22 23:29:46.337960: step: 1536/526, loss: 0.39337289333343506
2023-01-22 23:29:47.458853: step: 1540/526, loss: 0.500944972038269
2023-01-22 23:29:48.595862: step: 1544/526, loss: 2.1210741996765137
2023-01-22 23:29:49.739466: step: 1548/526, loss: 0.3153996765613556
2023-01-22 23:29:50.890946: step: 1552/526, loss: 1.2591428756713867
2023-01-22 23:29:52.001962: step: 1556/526, loss: 2.7339954376220703
2023-01-22 23:29:53.113883: step: 1560/526, loss: 0.3999224603176117
2023-01-22 23:29:54.223497: step: 1564/526, loss: 2.504122257232666
2023-01-22 23:29:55.383657: step: 1568/526, loss: 1.0817643404006958
2023-01-22 23:29:56.531225: step: 1572/526, loss: 0.7084323763847351
2023-01-22 23:29:57.690950: step: 1576/526, loss: 0.23036609590053558
2023-01-22 23:29:58.821990: step: 1580/526, loss: 7.019631385803223
2023-01-22 23:29:59.956421: step: 1584/526, loss: 0.628699779510498
2023-01-22 23:30:01.078534: step: 1588/526, loss: 0.6608818769454956
2023-01-22 23:30:02.194211: step: 1592/526, loss: 0.3139715790748596
2023-01-22 23:30:03.366910: step: 1596/526, loss: 5.062445640563965
2023-01-22 23:30:04.527458: step: 1600/526, loss: 2.2490780353546143
2023-01-22 23:30:05.688545: step: 1604/526, loss: 0.4725354313850403
2023-01-22 23:30:06.841105: step: 1608/526, loss: 1.6625943183898926
2023-01-22 23:30:07.954952: step: 1612/526, loss: 7.107010364532471
2023-01-22 23:30:09.081055: step: 1616/526, loss: 1.544629454612732
2023-01-22 23:30:10.231380: step: 1620/526, loss: 0.4934345483779907
2023-01-22 23:30:11.384075: step: 1624/526, loss: 2.2757115364074707
2023-01-22 23:30:12.484902: step: 1628/526, loss: 2.29428768157959
2023-01-22 23:30:13.590396: step: 1632/526, loss: 2.0969605445861816
2023-01-22 23:30:14.746942: step: 1636/526, loss: 0.96044921875
2023-01-22 23:30:15.873217: step: 1640/526, loss: 0.9435324668884277
2023-01-22 23:30:16.989432: step: 1644/526, loss: 2.538663387298584
2023-01-22 23:30:18.144075: step: 1648/526, loss: 0.36689937114715576
2023-01-22 23:30:19.303281: step: 1652/526, loss: 0.7993355989456177
2023-01-22 23:30:20.421177: step: 1656/526, loss: 0.2025838941335678
2023-01-22 23:30:21.535800: step: 1660/526, loss: 1.9917449951171875
2023-01-22 23:30:22.688449: step: 1664/526, loss: 1.9251827001571655
2023-01-22 23:30:23.812898: step: 1668/526, loss: 0.31708812713623047
2023-01-22 23:30:24.956274: step: 1672/526, loss: 1.0962234735488892
2023-01-22 23:30:26.102424: step: 1676/526, loss: 0.4059239625930786
2023-01-22 23:30:27.248350: step: 1680/526, loss: 2.2722420692443848
2023-01-22 23:30:28.384037: step: 1684/526, loss: 0.312305748462677
2023-01-22 23:30:29.526580: step: 1688/526, loss: 0.444745808839798
2023-01-22 23:30:30.672798: step: 1692/526, loss: 0.24685117602348328
2023-01-22 23:30:31.802599: step: 1696/526, loss: 0.2933158874511719
2023-01-22 23:30:32.940555: step: 1700/526, loss: 1.0083562135696411
2023-01-22 23:30:34.073105: step: 1704/526, loss: 0.9939299821853638
2023-01-22 23:30:35.227718: step: 1708/526, loss: 2.3145675659179688
2023-01-22 23:30:36.340014: step: 1712/526, loss: 0.7160344123840332
2023-01-22 23:30:37.472947: step: 1716/526, loss: 0.3281521797180176
2023-01-22 23:30:38.659891: step: 1720/526, loss: 4.843984127044678
2023-01-22 23:30:39.789281: step: 1724/526, loss: 3.154914617538452
2023-01-22 23:30:40.906104: step: 1728/526, loss: 0.23179420828819275
2023-01-22 23:30:42.035717: step: 1732/526, loss: 0.7848429679870605
2023-01-22 23:30:43.170885: step: 1736/526, loss: 0.5189828276634216
2023-01-22 23:30:44.320232: step: 1740/526, loss: 0.5119626522064209
2023-01-22 23:30:45.424612: step: 1744/526, loss: 2.896693706512451
2023-01-22 23:30:46.587354: step: 1748/526, loss: 0.4422931671142578
2023-01-22 23:30:47.736056: step: 1752/526, loss: 0.3722724914550781
2023-01-22 23:30:48.898041: step: 1756/526, loss: 0.8425112962722778
2023-01-22 23:30:50.020555: step: 1760/526, loss: 2.4931066036224365
2023-01-22 23:30:51.141920: step: 1764/526, loss: 1.1446192264556885
2023-01-22 23:30:52.287354: step: 1768/526, loss: 0.49720528721809387
2023-01-22 23:30:53.406155: step: 1772/526, loss: 0.12635165452957153
2023-01-22 23:30:54.533460: step: 1776/526, loss: 2.4786667823791504
2023-01-22 23:30:55.680784: step: 1780/526, loss: 0.29175227880477905
2023-01-22 23:30:56.793725: step: 1784/526, loss: 1.8485543727874756
2023-01-22 23:30:57.942024: step: 1788/526, loss: 0.2906613051891327
2023-01-22 23:30:59.065448: step: 1792/526, loss: 0.3093242645263672
2023-01-22 23:31:00.165289: step: 1796/526, loss: 0.31108731031417847
2023-01-22 23:31:01.290142: step: 1800/526, loss: 0.3179604411125183
2023-01-22 23:31:02.425639: step: 1804/526, loss: 1.2491549253463745
2023-01-22 23:31:03.559353: step: 1808/526, loss: 1.4476888179779053
2023-01-22 23:31:04.679327: step: 1812/526, loss: 0.44461360573768616
2023-01-22 23:31:05.809684: step: 1816/526, loss: 1.6376667022705078
2023-01-22 23:31:06.936336: step: 1820/526, loss: 0.47399258613586426
2023-01-22 23:31:08.065313: step: 1824/526, loss: 0.8550583720207214
2023-01-22 23:31:09.185815: step: 1828/526, loss: 1.1353684663772583
2023-01-22 23:31:10.307045: step: 1832/526, loss: 0.15098491311073303
2023-01-22 23:31:11.402006: step: 1836/526, loss: 0.7288172245025635
2023-01-22 23:31:12.519024: step: 1840/526, loss: 1.0133200883865356
2023-01-22 23:31:13.696572: step: 1844/526, loss: 0.1850666105747223
2023-01-22 23:31:14.869340: step: 1848/526, loss: 0.9694145321846008
2023-01-22 23:31:15.999984: step: 1852/526, loss: 1.2353425025939941
2023-01-22 23:31:17.120266: step: 1856/526, loss: 0.2507871687412262
2023-01-22 23:31:18.220843: step: 1860/526, loss: 0.31660011410713196
2023-01-22 23:31:19.351427: step: 1864/526, loss: 0.23736849427223206
2023-01-22 23:31:20.481421: step: 1868/526, loss: 0.5693188309669495
2023-01-22 23:31:21.610960: step: 1872/526, loss: 0.8955358862876892
2023-01-22 23:31:22.746651: step: 1876/526, loss: 1.1898239850997925
2023-01-22 23:31:23.875371: step: 1880/526, loss: 0.28685086965560913
2023-01-22 23:31:25.017232: step: 1884/526, loss: 0.8071651458740234
2023-01-22 23:31:26.134839: step: 1888/526, loss: 3.286255359649658
2023-01-22 23:31:27.277981: step: 1892/526, loss: 0.22234492003917694
2023-01-22 23:31:28.412051: step: 1896/526, loss: 0.23985934257507324
2023-01-22 23:31:29.533063: step: 1900/526, loss: 2.318176031112671
2023-01-22 23:31:30.658223: step: 1904/526, loss: 1.1696834564208984
2023-01-22 23:31:31.773878: step: 1908/526, loss: 2.8154244422912598
2023-01-22 23:31:32.900051: step: 1912/526, loss: 0.9494587182998657
2023-01-22 23:31:34.102481: step: 1916/526, loss: 3.0047805309295654
2023-01-22 23:31:35.255177: step: 1920/526, loss: 2.5172293186187744
2023-01-22 23:31:36.410718: step: 1924/526, loss: 0.3164713978767395
2023-01-22 23:31:37.549040: step: 1928/526, loss: 1.2114191055297852
2023-01-22 23:31:38.687881: step: 1932/526, loss: 1.6604071855545044
2023-01-22 23:31:39.821572: step: 1936/526, loss: 2.9787697792053223
2023-01-22 23:31:40.955553: step: 1940/526, loss: 0.4908496141433716
2023-01-22 23:31:42.114060: step: 1944/526, loss: 1.097630262374878
2023-01-22 23:31:43.231983: step: 1948/526, loss: 2.469313859939575
2023-01-22 23:31:44.348275: step: 1952/526, loss: 2.3053290843963623
2023-01-22 23:31:45.472567: step: 1956/526, loss: 0.5947933197021484
2023-01-22 23:31:46.635938: step: 1960/526, loss: 0.5297248959541321
2023-01-22 23:31:47.742598: step: 1964/526, loss: 0.5264659523963928
2023-01-22 23:31:48.866819: step: 1968/526, loss: 0.4361874759197235
2023-01-22 23:31:49.977794: step: 1972/526, loss: 0.23376017808914185
2023-01-22 23:31:51.108258: step: 1976/526, loss: 1.3044383525848389
2023-01-22 23:31:52.255524: step: 1980/526, loss: 0.31719255447387695
2023-01-22 23:31:53.386268: step: 1984/526, loss: 0.5426143407821655
2023-01-22 23:31:54.521080: step: 1988/526, loss: 0.7885656356811523
2023-01-22 23:31:55.636588: step: 1992/526, loss: 2.0058581829071045
2023-01-22 23:31:56.762434: step: 1996/526, loss: 0.5770419836044312
2023-01-22 23:31:57.864724: step: 2000/526, loss: 1.8433730602264404
2023-01-22 23:31:59.002941: step: 2004/526, loss: 1.8296287059783936
2023-01-22 23:32:00.119483: step: 2008/526, loss: 0.6065354943275452
2023-01-22 23:32:01.257972: step: 2012/526, loss: 0.9866287708282471
2023-01-22 23:32:02.395809: step: 2016/526, loss: 0.9422327280044556
2023-01-22 23:32:03.524159: step: 2020/526, loss: 0.593647837638855
2023-01-22 23:32:04.667824: step: 2024/526, loss: 0.3329729437828064
2023-01-22 23:32:05.833073: step: 2028/526, loss: 0.49724704027175903
2023-01-22 23:32:06.971019: step: 2032/526, loss: 0.6353542804718018
2023-01-22 23:32:08.095711: step: 2036/526, loss: 0.20455598831176758
2023-01-22 23:32:09.232106: step: 2040/526, loss: 0.7911707162857056
2023-01-22 23:32:10.361389: step: 2044/526, loss: 0.6074792742729187
2023-01-22 23:32:11.490515: step: 2048/526, loss: 0.3341962695121765
2023-01-22 23:32:12.617725: step: 2052/526, loss: 0.5979087948799133
2023-01-22 23:32:13.746247: step: 2056/526, loss: 0.28880637884140015
2023-01-22 23:32:14.884431: step: 2060/526, loss: 0.8539525866508484
2023-01-22 23:32:16.036262: step: 2064/526, loss: 0.5040515661239624
2023-01-22 23:32:17.174116: step: 2068/526, loss: 0.37739840149879456
2023-01-22 23:32:18.280618: step: 2072/526, loss: 2.66009783744812
2023-01-22 23:32:19.418293: step: 2076/526, loss: 1.1328926086425781
2023-01-22 23:32:20.555956: step: 2080/526, loss: 0.32803452014923096
2023-01-22 23:32:21.715707: step: 2084/526, loss: 0.8675100803375244
2023-01-22 23:32:22.830805: step: 2088/526, loss: 1.6779357194900513
2023-01-22 23:32:23.973315: step: 2092/526, loss: 0.5400898456573486
2023-01-22 23:32:25.117177: step: 2096/526, loss: 0.5662949681282043
2023-01-22 23:32:26.260067: step: 2100/526, loss: 0.6584249138832092
2023-01-22 23:32:27.424345: step: 2104/526, loss: 1.1076157093048096
==================================================
Loss: 3.266
--------------------
Dev: {'event': {'p': 0.5421994884910486, 'r': 0.5645805592543276, 'f1': 0.553163731245923}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Test: {'event': {'p': 0.4775, 'r': 0.3987473903966597, 'f1': 0.43458475540386804}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Chinese: {'event': {'p': 0.5319148936170213, 'r': 0.46296296296296297, 'f1': 0.495049504950495}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Korean: {'event': {'p': 0.8421052631578947, 'r': 0.25396825396825395, 'f1': 0.3902439024390244}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Russian: {'event': {'p': 0.5, 'r': 0.16666666666666666, 'f1': 0.25}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
New best chinese model...
New best korean model...
New best russian model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.5421994884910486, 'r': 0.5645805592543276, 'f1': 0.553163731245923}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Eng Test for Chinese: {'event': {'p': 0.4775, 'r': 0.3987473903966597, 'f1': 0.43458475540386804}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Sample Chinese: {'event': {'p': 0.5319148936170213, 'r': 0.46296296296296297, 'f1': 0.495049504950495}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5421994884910486, 'r': 0.5645805592543276, 'f1': 0.553163731245923}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Eng Test for Korean: {'event': {'p': 0.4775, 'r': 0.3987473903966597, 'f1': 0.43458475540386804}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Sample Korean: {'event': {'p': 0.8421052631578947, 'r': 0.25396825396825395, 'f1': 0.3902439024390244}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5421994884910486, 'r': 0.5645805592543276, 'f1': 0.553163731245923}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Eng Test for Russian: {'event': {'p': 0.4775, 'r': 0.3987473903966597, 'f1': 0.43458475540386804}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Sample Russian: {'event': {'p': 0.5, 'r': 0.16666666666666666, 'f1': 0.25}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
******************************
Epoch: 1
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-22 23:33:30.876253: step: 4/526, loss: 2.083930015563965
2023-01-22 23:33:32.039060: step: 8/526, loss: 0.8274605870246887
2023-01-22 23:33:33.191368: step: 12/526, loss: 0.3782390356063843
2023-01-22 23:33:34.346079: step: 16/526, loss: 0.7598814964294434
2023-01-22 23:33:35.465116: step: 20/526, loss: 0.1971059888601303
2023-01-22 23:33:36.603835: step: 24/526, loss: 0.23529118299484253
2023-01-22 23:33:37.735198: step: 28/526, loss: 0.26415252685546875
2023-01-22 23:33:38.882841: step: 32/526, loss: 0.12952308356761932
2023-01-22 23:33:40.014981: step: 36/526, loss: 0.1944410502910614
2023-01-22 23:33:41.168109: step: 40/526, loss: 0.1660228818655014
2023-01-22 23:33:42.314083: step: 44/526, loss: 1.4282119274139404
2023-01-22 23:33:43.442977: step: 48/526, loss: 0.7807324528694153
2023-01-22 23:33:44.551870: step: 52/526, loss: 0.0864735096693039
2023-01-22 23:33:45.689992: step: 56/526, loss: 0.8017598986625671
2023-01-22 23:33:46.830407: step: 60/526, loss: 0.28034257888793945
2023-01-22 23:33:47.951881: step: 64/526, loss: 1.1089951992034912
2023-01-22 23:33:49.071291: step: 68/526, loss: 0.3048839569091797
2023-01-22 23:33:50.197339: step: 72/526, loss: 1.0833467245101929
2023-01-22 23:33:51.324972: step: 76/526, loss: 1.0029594898223877
2023-01-22 23:33:52.466768: step: 80/526, loss: 0.09686202555894852
2023-01-22 23:33:53.591951: step: 84/526, loss: 0.5943330526351929
2023-01-22 23:33:54.729115: step: 88/526, loss: 0.5998398065567017
2023-01-22 23:33:55.866827: step: 92/526, loss: 0.5607078671455383
2023-01-22 23:33:56.984820: step: 96/526, loss: 0.7707836627960205
2023-01-22 23:33:58.112867: step: 100/526, loss: 0.23311491310596466
2023-01-22 23:33:59.259136: step: 104/526, loss: 0.2576221227645874
2023-01-22 23:34:00.408671: step: 108/526, loss: 0.6494616866111755
2023-01-22 23:34:01.551021: step: 112/526, loss: 0.4253585934638977
2023-01-22 23:34:02.675618: step: 116/526, loss: 0.23099356889724731
2023-01-22 23:34:03.824352: step: 120/526, loss: 0.7637468576431274
2023-01-22 23:34:04.979217: step: 124/526, loss: 0.2622276842594147
2023-01-22 23:34:06.118148: step: 128/526, loss: 2.7345898151397705
2023-01-22 23:34:07.223585: step: 132/526, loss: 0.3178275227546692
2023-01-22 23:34:08.359474: step: 136/526, loss: 0.5001682043075562
2023-01-22 23:34:09.526741: step: 140/526, loss: 7.056186676025391
2023-01-22 23:34:10.662796: step: 144/526, loss: 0.9011992812156677
2023-01-22 23:34:11.804380: step: 148/526, loss: 1.5721018314361572
2023-01-22 23:34:12.942785: step: 152/526, loss: 0.16192373633384705
2023-01-22 23:34:14.129319: step: 156/526, loss: 0.26265040040016174
2023-01-22 23:34:15.261493: step: 160/526, loss: 0.46940135955810547
2023-01-22 23:34:16.393260: step: 164/526, loss: 0.4644995927810669
2023-01-22 23:34:17.510294: step: 168/526, loss: 0.3633946478366852
2023-01-22 23:34:18.640384: step: 172/526, loss: 0.9035346508026123
2023-01-22 23:34:19.777812: step: 176/526, loss: 1.9735026359558105
2023-01-22 23:34:20.900979: step: 180/526, loss: 2.5919289588928223
2023-01-22 23:34:22.018476: step: 184/526, loss: 0.6723855137825012
2023-01-22 23:34:23.163111: step: 188/526, loss: 0.24602484703063965
2023-01-22 23:34:24.273456: step: 192/526, loss: 1.0357261896133423
2023-01-22 23:34:25.398297: step: 196/526, loss: 0.9602370262145996
2023-01-22 23:34:26.529546: step: 200/526, loss: 0.9325742721557617
2023-01-22 23:34:27.705595: step: 204/526, loss: 3.030963182449341
2023-01-22 23:34:28.896493: step: 208/526, loss: 0.4387546181678772
2023-01-22 23:34:30.083582: step: 212/526, loss: 0.6036388278007507
2023-01-22 23:34:31.205345: step: 216/526, loss: 0.33836671710014343
2023-01-22 23:34:32.362612: step: 220/526, loss: 0.7502118945121765
2023-01-22 23:34:33.516030: step: 224/526, loss: 2.5615463256835938
2023-01-22 23:34:34.651809: step: 228/526, loss: 0.8718830943107605
2023-01-22 23:34:35.776823: step: 232/526, loss: 0.7705024480819702
2023-01-22 23:34:36.924597: step: 236/526, loss: 0.9986544251441956
2023-01-22 23:34:38.056093: step: 240/526, loss: 0.3948686718940735
2023-01-22 23:34:39.194603: step: 244/526, loss: 1.4745467901229858
2023-01-22 23:34:40.303517: step: 248/526, loss: 0.3927941620349884
2023-01-22 23:34:41.430527: step: 252/526, loss: 0.1897200047969818
2023-01-22 23:34:42.577504: step: 256/526, loss: 3.3282723426818848
2023-01-22 23:34:43.698548: step: 260/526, loss: 0.5444931983947754
2023-01-22 23:34:44.838307: step: 264/526, loss: 0.22589468955993652
2023-01-22 23:34:46.005424: step: 268/526, loss: 0.6399433016777039
2023-01-22 23:34:47.121101: step: 272/526, loss: 1.3531510829925537
2023-01-22 23:34:48.259207: step: 276/526, loss: 0.9859811067581177
2023-01-22 23:34:49.414904: step: 280/526, loss: 0.3848627209663391
2023-01-22 23:34:50.572613: step: 284/526, loss: 1.6057392358779907
2023-01-22 23:34:51.743987: step: 288/526, loss: 1.0108039379119873
2023-01-22 23:34:52.880409: step: 292/526, loss: 0.26069778203964233
2023-01-22 23:34:54.019161: step: 296/526, loss: 0.41763579845428467
2023-01-22 23:34:55.175800: step: 300/526, loss: 0.3531990051269531
2023-01-22 23:34:56.292826: step: 304/526, loss: 0.4743443727493286
2023-01-22 23:34:57.447456: step: 308/526, loss: 0.9863955974578857
2023-01-22 23:34:58.599908: step: 312/526, loss: 0.6807553768157959
2023-01-22 23:34:59.725142: step: 316/526, loss: 1.6670469045639038
2023-01-22 23:35:00.900176: step: 320/526, loss: 0.17421141266822815
2023-01-22 23:35:02.048978: step: 324/526, loss: 0.8518913388252258
2023-01-22 23:35:03.171416: step: 328/526, loss: 0.651017963886261
2023-01-22 23:35:04.334005: step: 332/526, loss: 0.48933982849121094
2023-01-22 23:35:05.491794: step: 336/526, loss: 0.18417192995548248
2023-01-22 23:35:06.647871: step: 340/526, loss: 0.6215408444404602
2023-01-22 23:35:07.778888: step: 344/526, loss: 0.36384862661361694
2023-01-22 23:35:08.929597: step: 348/526, loss: 0.5557636618614197
2023-01-22 23:35:10.065922: step: 352/526, loss: 2.640521287918091
2023-01-22 23:35:11.204741: step: 356/526, loss: 0.5376696586608887
2023-01-22 23:35:12.340907: step: 360/526, loss: 0.9676294922828674
2023-01-22 23:35:13.487640: step: 364/526, loss: 0.44783440232276917
2023-01-22 23:35:14.655713: step: 368/526, loss: 0.3965347111225128
2023-01-22 23:35:15.798358: step: 372/526, loss: 0.5311633944511414
2023-01-22 23:35:16.941882: step: 376/526, loss: 0.22307558357715607
2023-01-22 23:35:18.078815: step: 380/526, loss: 0.2216019332408905
2023-01-22 23:35:19.222974: step: 384/526, loss: 0.38986721634864807
2023-01-22 23:35:20.338652: step: 388/526, loss: 0.30713891983032227
2023-01-22 23:35:21.468226: step: 392/526, loss: 0.19910621643066406
2023-01-22 23:35:22.615621: step: 396/526, loss: 1.0961734056472778
2023-01-22 23:35:23.752726: step: 400/526, loss: 0.8917814493179321
2023-01-22 23:35:24.888307: step: 404/526, loss: 0.2355732023715973
2023-01-22 23:35:26.024479: step: 408/526, loss: 0.793698787689209
2023-01-22 23:35:27.140354: step: 412/526, loss: 1.4421148300170898
2023-01-22 23:35:28.272514: step: 416/526, loss: 0.25117313861846924
2023-01-22 23:35:29.400931: step: 420/526, loss: 0.2528945207595825
2023-01-22 23:35:30.547997: step: 424/526, loss: 2.6126599311828613
2023-01-22 23:35:31.676573: step: 428/526, loss: 0.25804147124290466
2023-01-22 23:35:32.800253: step: 432/526, loss: 0.22289638221263885
2023-01-22 23:35:33.922133: step: 436/526, loss: 1.0976557731628418
2023-01-22 23:35:35.103273: step: 440/526, loss: 0.22537703812122345
2023-01-22 23:35:36.236682: step: 444/526, loss: 0.5675263404846191
2023-01-22 23:35:37.404852: step: 448/526, loss: 0.8727865219116211
2023-01-22 23:35:38.553232: step: 452/526, loss: 0.32158422470092773
2023-01-22 23:35:39.705488: step: 456/526, loss: 0.526586651802063
2023-01-22 23:35:40.831136: step: 460/526, loss: 0.8260121941566467
2023-01-22 23:35:41.976429: step: 464/526, loss: 7.516510009765625
2023-01-22 23:35:43.144676: step: 468/526, loss: 1.013238549232483
2023-01-22 23:35:44.309249: step: 472/526, loss: 0.19077129662036896
2023-01-22 23:35:45.468593: step: 476/526, loss: 0.595874011516571
2023-01-22 23:35:46.600115: step: 480/526, loss: 0.7450437545776367
2023-01-22 23:35:47.770162: step: 484/526, loss: 1.3177281618118286
2023-01-22 23:35:48.924597: step: 488/526, loss: 0.6919177174568176
2023-01-22 23:35:50.042800: step: 492/526, loss: 0.8793939352035522
2023-01-22 23:35:51.167100: step: 496/526, loss: 0.770618200302124
2023-01-22 23:35:52.351099: step: 500/526, loss: 0.8184714913368225
2023-01-22 23:35:53.467175: step: 504/526, loss: 0.20872879028320312
2023-01-22 23:35:54.600817: step: 508/526, loss: 0.13976740837097168
2023-01-22 23:35:55.734050: step: 512/526, loss: 0.3190687298774719
2023-01-22 23:35:56.897852: step: 516/526, loss: 0.29576951265335083
2023-01-22 23:35:58.064137: step: 520/526, loss: 0.3784988820552826
2023-01-22 23:35:59.233571: step: 524/526, loss: 1.279805064201355
2023-01-22 23:36:00.357566: step: 528/526, loss: 0.514992892742157
2023-01-22 23:36:01.505961: step: 532/526, loss: 0.4659263789653778
2023-01-22 23:36:02.648457: step: 536/526, loss: 0.3378411531448364
2023-01-22 23:36:03.801160: step: 540/526, loss: 0.27676069736480713
2023-01-22 23:36:04.935641: step: 544/526, loss: 0.37308037281036377
2023-01-22 23:36:06.057878: step: 548/526, loss: 0.16481605172157288
2023-01-22 23:36:07.193111: step: 552/526, loss: 0.30347806215286255
2023-01-22 23:36:08.363326: step: 556/526, loss: 0.2569205164909363
2023-01-22 23:36:09.495526: step: 560/526, loss: 0.4747818112373352
2023-01-22 23:36:10.620484: step: 564/526, loss: 0.5102481245994568
2023-01-22 23:36:11.741182: step: 568/526, loss: 0.41791316866874695
2023-01-22 23:36:12.903548: step: 572/526, loss: 2.084381580352783
2023-01-22 23:36:14.029707: step: 576/526, loss: 0.9264667630195618
2023-01-22 23:36:15.144708: step: 580/526, loss: 0.6340084075927734
2023-01-22 23:36:16.271362: step: 584/526, loss: 0.9388248920440674
2023-01-22 23:36:17.392076: step: 588/526, loss: 0.4145932197570801
2023-01-22 23:36:18.526324: step: 592/526, loss: 0.5316857099533081
2023-01-22 23:36:19.659448: step: 596/526, loss: 1.4013551473617554
2023-01-22 23:36:20.808028: step: 600/526, loss: 0.5107519626617432
2023-01-22 23:36:21.930821: step: 604/526, loss: 0.26548969745635986
2023-01-22 23:36:23.081349: step: 608/526, loss: 0.8689706921577454
2023-01-22 23:36:24.242902: step: 612/526, loss: 0.7169291973114014
2023-01-22 23:36:25.406536: step: 616/526, loss: 1.7207502126693726
2023-01-22 23:36:26.555707: step: 620/526, loss: 0.5860875248908997
2023-01-22 23:36:27.680906: step: 624/526, loss: 1.6433438062667847
2023-01-22 23:36:28.829088: step: 628/526, loss: 5.409465789794922
2023-01-22 23:36:29.958208: step: 632/526, loss: 0.296293169260025
2023-01-22 23:36:31.114395: step: 636/526, loss: 0.6234157681465149
2023-01-22 23:36:32.232501: step: 640/526, loss: 0.7712377309799194
2023-01-22 23:36:33.412383: step: 644/526, loss: 0.36940136551856995
2023-01-22 23:36:34.534186: step: 648/526, loss: 0.26981449127197266
2023-01-22 23:36:35.647525: step: 652/526, loss: 0.4232860207557678
2023-01-22 23:36:36.766826: step: 656/526, loss: 0.6999709606170654
2023-01-22 23:36:37.903779: step: 660/526, loss: 0.19666405022144318
2023-01-22 23:36:39.008895: step: 664/526, loss: 0.8148563504219055
2023-01-22 23:36:40.117421: step: 668/526, loss: 0.47100716829299927
2023-01-22 23:36:41.242047: step: 672/526, loss: 0.23274736106395721
2023-01-22 23:36:42.376681: step: 676/526, loss: 2.2901201248168945
2023-01-22 23:36:43.497039: step: 680/526, loss: 0.46401405334472656
2023-01-22 23:36:44.627402: step: 684/526, loss: 2.6145966053009033
2023-01-22 23:36:45.766066: step: 688/526, loss: 0.777539849281311
2023-01-22 23:36:46.879301: step: 692/526, loss: 1.050235629081726
2023-01-22 23:36:48.011205: step: 696/526, loss: 0.1734866201877594
2023-01-22 23:36:49.121900: step: 700/526, loss: 0.07925238460302353
2023-01-22 23:36:50.254866: step: 704/526, loss: 0.6025959849357605
2023-01-22 23:36:51.405872: step: 708/526, loss: 7.720644474029541
2023-01-22 23:36:52.526391: step: 712/526, loss: 0.1756322681903839
2023-01-22 23:36:53.634989: step: 716/526, loss: 0.1689709722995758
2023-01-22 23:36:54.794616: step: 720/526, loss: 0.1403297483921051
2023-01-22 23:36:55.951052: step: 724/526, loss: 1.9489986896514893
2023-01-22 23:36:57.090256: step: 728/526, loss: 0.5420126914978027
2023-01-22 23:36:58.216314: step: 732/526, loss: 0.4235738515853882
2023-01-22 23:36:59.358746: step: 736/526, loss: 0.7603631019592285
2023-01-22 23:37:00.518432: step: 740/526, loss: 0.30566656589508057
2023-01-22 23:37:01.646069: step: 744/526, loss: 1.6442592144012451
2023-01-22 23:37:02.775171: step: 748/526, loss: 1.2697744369506836
2023-01-22 23:37:03.922199: step: 752/526, loss: 0.14380040764808655
2023-01-22 23:37:05.036758: step: 756/526, loss: 0.1881619393825531
2023-01-22 23:37:06.181005: step: 760/526, loss: 0.17431902885437012
2023-01-22 23:37:07.299649: step: 764/526, loss: 0.4401032328605652
2023-01-22 23:37:08.411635: step: 768/526, loss: 0.45035457611083984
2023-01-22 23:37:09.519773: step: 772/526, loss: 0.12683796882629395
2023-01-22 23:37:10.669945: step: 776/526, loss: 6.887025356292725
2023-01-22 23:37:11.765200: step: 780/526, loss: 1.1555850505828857
2023-01-22 23:37:12.910604: step: 784/526, loss: 1.0256932973861694
2023-01-22 23:37:14.054152: step: 788/526, loss: 1.7286767959594727
2023-01-22 23:37:15.198916: step: 792/526, loss: 0.2834101617336273
2023-01-22 23:37:16.339185: step: 796/526, loss: 0.6657474637031555
2023-01-22 23:37:17.480984: step: 800/526, loss: 0.39743462204933167
2023-01-22 23:37:18.596420: step: 804/526, loss: 1.0026803016662598
2023-01-22 23:37:19.728074: step: 808/526, loss: 0.8649067878723145
2023-01-22 23:37:20.855248: step: 812/526, loss: 0.756666362285614
2023-01-22 23:37:21.958641: step: 816/526, loss: 0.13735933601856232
2023-01-22 23:37:23.076015: step: 820/526, loss: 0.2243185043334961
2023-01-22 23:37:24.214549: step: 824/526, loss: 0.6144806146621704
2023-01-22 23:37:25.353847: step: 828/526, loss: 0.36953428387641907
2023-01-22 23:37:26.444841: step: 832/526, loss: 0.112358957529068
2023-01-22 23:37:27.548990: step: 836/526, loss: 7.910516262054443
2023-01-22 23:37:28.677052: step: 840/526, loss: 0.6389080286026001
2023-01-22 23:37:29.835359: step: 844/526, loss: 0.47347506880760193
2023-01-22 23:37:30.947302: step: 848/526, loss: 0.23369541764259338
2023-01-22 23:37:32.079927: step: 852/526, loss: 0.15017472207546234
2023-01-22 23:37:33.212020: step: 856/526, loss: 1.034529685974121
2023-01-22 23:37:34.309774: step: 860/526, loss: 0.768824577331543
2023-01-22 23:37:35.444669: step: 864/526, loss: 0.7620635628700256
2023-01-22 23:37:36.592424: step: 868/526, loss: 0.26703566312789917
2023-01-22 23:37:37.744347: step: 872/526, loss: 1.6306886672973633
2023-01-22 23:37:38.848199: step: 876/526, loss: 0.20424380898475647
2023-01-22 23:37:39.993250: step: 880/526, loss: 0.2717951834201813
2023-01-22 23:37:41.155932: step: 884/526, loss: 0.3805252015590668
2023-01-22 23:37:42.281028: step: 888/526, loss: 0.46414369344711304
2023-01-22 23:37:43.460232: step: 892/526, loss: 0.18890619277954102
2023-01-22 23:37:44.594946: step: 896/526, loss: 0.826716959476471
2023-01-22 23:37:45.753034: step: 900/526, loss: 0.6143976449966431
2023-01-22 23:37:46.891119: step: 904/526, loss: 0.17708587646484375
2023-01-22 23:37:48.008885: step: 908/526, loss: 1.067354440689087
2023-01-22 23:37:49.157153: step: 912/526, loss: 0.1992177963256836
2023-01-22 23:37:50.272292: step: 916/526, loss: 0.08626718819141388
2023-01-22 23:37:51.400278: step: 920/526, loss: 0.601593017578125
2023-01-22 23:37:52.525496: step: 924/526, loss: 0.3136301636695862
2023-01-22 23:37:53.631009: step: 928/526, loss: 0.3361783027648926
2023-01-22 23:37:54.811365: step: 932/526, loss: 1.8437751531600952
2023-01-22 23:37:55.957548: step: 936/526, loss: 0.5151111483573914
2023-01-22 23:37:57.113923: step: 940/526, loss: 0.49617502093315125
2023-01-22 23:37:58.278747: step: 944/526, loss: 1.0481302738189697
2023-01-22 23:37:59.403071: step: 948/526, loss: 0.24285149574279785
2023-01-22 23:38:00.511688: step: 952/526, loss: 0.16453714668750763
2023-01-22 23:38:01.654450: step: 956/526, loss: 0.5571976900100708
2023-01-22 23:38:02.772732: step: 960/526, loss: 1.0675063133239746
2023-01-22 23:38:03.920760: step: 964/526, loss: 0.31882303953170776
2023-01-22 23:38:05.040205: step: 968/526, loss: 0.16361112892627716
2023-01-22 23:38:06.197260: step: 972/526, loss: 0.3353150486946106
2023-01-22 23:38:07.350148: step: 976/526, loss: 0.37121570110321045
2023-01-22 23:38:08.482367: step: 980/526, loss: 0.18925437331199646
2023-01-22 23:38:09.583379: step: 984/526, loss: 1.0003020763397217
2023-01-22 23:38:10.699512: step: 988/526, loss: 2.0658602714538574
2023-01-22 23:38:11.847498: step: 992/526, loss: 0.2758404016494751
2023-01-22 23:38:13.005900: step: 996/526, loss: 0.784070611000061
2023-01-22 23:38:14.120123: step: 1000/526, loss: 0.3153071999549866
2023-01-22 23:38:15.212068: step: 1004/526, loss: 1.74001944065094
2023-01-22 23:38:16.327495: step: 1008/526, loss: 0.6710470914840698
2023-01-22 23:38:17.471090: step: 1012/526, loss: 0.17495279014110565
2023-01-22 23:38:18.619026: step: 1016/526, loss: 0.6081430315971375
2023-01-22 23:38:19.773460: step: 1020/526, loss: 0.3611958622932434
2023-01-22 23:38:20.908485: step: 1024/526, loss: 0.2290334403514862
2023-01-22 23:38:22.031940: step: 1028/526, loss: 0.16033358871936798
2023-01-22 23:38:23.155665: step: 1032/526, loss: 0.07119403034448624
2023-01-22 23:38:24.304789: step: 1036/526, loss: 0.3850610554218292
2023-01-22 23:38:25.438969: step: 1040/526, loss: 0.7330614924430847
2023-01-22 23:38:26.569587: step: 1044/526, loss: 0.9605895280838013
2023-01-22 23:38:27.680511: step: 1048/526, loss: 0.5487978458404541
2023-01-22 23:38:28.828743: step: 1052/526, loss: 0.20520305633544922
2023-01-22 23:38:29.946575: step: 1056/526, loss: 0.17443647980690002
2023-01-22 23:38:31.063770: step: 1060/526, loss: 0.32667216658592224
2023-01-22 23:38:32.179210: step: 1064/526, loss: 0.7762643694877625
2023-01-22 23:38:33.328365: step: 1068/526, loss: 0.45331984758377075
2023-01-22 23:38:34.467871: step: 1072/526, loss: 0.22069521248340607
2023-01-22 23:38:35.597075: step: 1076/526, loss: 0.29446014761924744
2023-01-22 23:38:36.745010: step: 1080/526, loss: 0.305077463388443
2023-01-22 23:38:37.870196: step: 1084/526, loss: 0.12300291657447815
2023-01-22 23:38:39.011412: step: 1088/526, loss: 0.8958039283752441
2023-01-22 23:38:40.158461: step: 1092/526, loss: 2.183286428451538
2023-01-22 23:38:41.303608: step: 1096/526, loss: 0.5702366232872009
2023-01-22 23:38:42.415432: step: 1100/526, loss: 0.36265257000923157
2023-01-22 23:38:43.520334: step: 1104/526, loss: 0.7502535581588745
2023-01-22 23:38:44.617437: step: 1108/526, loss: 1.2186193466186523
2023-01-22 23:38:45.746662: step: 1112/526, loss: 0.20356245338916779
2023-01-22 23:38:46.881018: step: 1116/526, loss: 0.33965975046157837
2023-01-22 23:38:48.020585: step: 1120/526, loss: 0.5156302452087402
2023-01-22 23:38:49.144495: step: 1124/526, loss: 0.14819243550300598
2023-01-22 23:38:50.307053: step: 1128/526, loss: 2.252439498901367
2023-01-22 23:38:51.433168: step: 1132/526, loss: 0.35062360763549805
2023-01-22 23:38:52.572466: step: 1136/526, loss: 1.8226397037506104
2023-01-22 23:38:53.708637: step: 1140/526, loss: 0.3080207407474518
2023-01-22 23:38:54.812371: step: 1144/526, loss: 1.0768003463745117
2023-01-22 23:38:55.941427: step: 1148/526, loss: 0.012936020269989967
2023-01-22 23:38:57.065165: step: 1152/526, loss: 1.0421228408813477
2023-01-22 23:38:58.194690: step: 1156/526, loss: 0.14714708924293518
2023-01-22 23:38:59.310859: step: 1160/526, loss: 1.5155606269836426
2023-01-22 23:39:00.409227: step: 1164/526, loss: 0.13709335029125214
2023-01-22 23:39:01.520796: step: 1168/526, loss: 0.20482495427131653
2023-01-22 23:39:02.622537: step: 1172/526, loss: 0.476881206035614
2023-01-22 23:39:03.753085: step: 1176/526, loss: 0.28138744831085205
2023-01-22 23:39:04.880594: step: 1180/526, loss: 0.6077210903167725
2023-01-22 23:39:06.037314: step: 1184/526, loss: 0.29387348890304565
2023-01-22 23:39:07.162732: step: 1188/526, loss: 0.12247458100318909
2023-01-22 23:39:08.280479: step: 1192/526, loss: 0.8134750127792358
2023-01-22 23:39:09.391424: step: 1196/526, loss: 3.0776665210723877
2023-01-22 23:39:10.565016: step: 1200/526, loss: 0.644314706325531
2023-01-22 23:39:11.696000: step: 1204/526, loss: 0.9402607679367065
2023-01-22 23:39:12.858116: step: 1208/526, loss: 0.9494227766990662
2023-01-22 23:39:14.001224: step: 1212/526, loss: 1.0180188417434692
2023-01-22 23:39:15.135238: step: 1216/526, loss: 0.3018779456615448
2023-01-22 23:39:16.243029: step: 1220/526, loss: 0.1744004786014557
2023-01-22 23:39:17.371753: step: 1224/526, loss: 1.2292245626449585
2023-01-22 23:39:18.481748: step: 1228/526, loss: 0.2391524314880371
2023-01-22 23:39:19.593185: step: 1232/526, loss: 0.6449756622314453
2023-01-22 23:39:20.686986: step: 1236/526, loss: 0.1707058846950531
2023-01-22 23:39:21.851026: step: 1240/526, loss: 0.2891367971897125
2023-01-22 23:39:22.960781: step: 1244/526, loss: 0.16197548806667328
2023-01-22 23:39:24.087324: step: 1248/526, loss: 0.08786487579345703
2023-01-22 23:39:25.234653: step: 1252/526, loss: 0.2576826214790344
2023-01-22 23:39:26.374490: step: 1256/526, loss: 1.7650480270385742
2023-01-22 23:39:27.551148: step: 1260/526, loss: 0.38966912031173706
2023-01-22 23:39:28.727364: step: 1264/526, loss: 1.028980016708374
2023-01-22 23:39:29.891517: step: 1268/526, loss: 0.2723108232021332
2023-01-22 23:39:31.002719: step: 1272/526, loss: 0.33362141251564026
2023-01-22 23:39:32.121351: step: 1276/526, loss: 0.28495320677757263
2023-01-22 23:39:33.228979: step: 1280/526, loss: 0.6047466397285461
2023-01-22 23:39:34.342603: step: 1284/526, loss: 0.24461022019386292
2023-01-22 23:39:35.464892: step: 1288/526, loss: 0.7112138867378235
2023-01-22 23:39:36.610985: step: 1292/526, loss: 0.9876381754875183
2023-01-22 23:39:37.769095: step: 1296/526, loss: 0.3674299120903015
2023-01-22 23:39:38.911566: step: 1300/526, loss: 0.2671385407447815
2023-01-22 23:39:40.038203: step: 1304/526, loss: 0.4772930145263672
2023-01-22 23:39:41.203198: step: 1308/526, loss: 0.40917739272117615
2023-01-22 23:39:42.313324: step: 1312/526, loss: 0.09050621837377548
2023-01-22 23:39:43.438833: step: 1316/526, loss: 0.2704673409461975
2023-01-22 23:39:44.547974: step: 1320/526, loss: 0.5377576351165771
2023-01-22 23:39:45.678652: step: 1324/526, loss: 1.5563396215438843
2023-01-22 23:39:46.815216: step: 1328/526, loss: 0.11209554970264435
2023-01-22 23:39:47.940913: step: 1332/526, loss: 0.15192189812660217
2023-01-22 23:39:49.076150: step: 1336/526, loss: 0.1536126732826233
2023-01-22 23:39:50.169172: step: 1340/526, loss: 1.1947139501571655
2023-01-22 23:39:51.308262: step: 1344/526, loss: 0.10649147629737854
2023-01-22 23:39:52.455086: step: 1348/526, loss: 0.24128800630569458
2023-01-22 23:39:53.580260: step: 1352/526, loss: 0.2277817726135254
2023-01-22 23:39:54.724124: step: 1356/526, loss: 2.7785356044769287
2023-01-22 23:39:55.845766: step: 1360/526, loss: 0.1620945930480957
2023-01-22 23:39:56.991669: step: 1364/526, loss: 0.8325731754302979
2023-01-22 23:39:58.126281: step: 1368/526, loss: 0.7937656044960022
2023-01-22 23:39:59.234663: step: 1372/526, loss: 1.5738050937652588
2023-01-22 23:40:00.391609: step: 1376/526, loss: 0.0945199504494667
2023-01-22 23:40:01.542998: step: 1380/526, loss: 1.0409876108169556
2023-01-22 23:40:02.666255: step: 1384/526, loss: 0.9487485289573669
2023-01-22 23:40:03.787936: step: 1388/526, loss: 0.26488518714904785
2023-01-22 23:40:04.919880: step: 1392/526, loss: 0.27072596549987793
2023-01-22 23:40:06.027279: step: 1396/526, loss: 0.3947053551673889
2023-01-22 23:40:07.121895: step: 1400/526, loss: 1.791111707687378
2023-01-22 23:40:08.280404: step: 1404/526, loss: 1.0617741346359253
2023-01-22 23:40:09.405181: step: 1408/526, loss: 0.37687110900878906
2023-01-22 23:40:10.556835: step: 1412/526, loss: 0.19886387884616852
2023-01-22 23:40:11.692710: step: 1416/526, loss: 0.5679737329483032
2023-01-22 23:40:12.852808: step: 1420/526, loss: 0.5390400290489197
2023-01-22 23:40:13.981315: step: 1424/526, loss: 0.8597105145454407
2023-01-22 23:40:15.100890: step: 1428/526, loss: 0.8764166831970215
2023-01-22 23:40:16.230462: step: 1432/526, loss: 0.39880692958831787
2023-01-22 23:40:17.356577: step: 1436/526, loss: 0.8203771710395813
2023-01-22 23:40:18.526408: step: 1440/526, loss: 2.040961265563965
2023-01-22 23:40:19.635763: step: 1444/526, loss: 0.22099782526493073
2023-01-22 23:40:20.782691: step: 1448/526, loss: 0.4093784689903259
2023-01-22 23:40:21.918031: step: 1452/526, loss: 0.3832346796989441
2023-01-22 23:40:23.061843: step: 1456/526, loss: 0.34543895721435547
2023-01-22 23:40:24.225256: step: 1460/526, loss: 0.4288085699081421
2023-01-22 23:40:25.370150: step: 1464/526, loss: 0.49686431884765625
2023-01-22 23:40:26.489782: step: 1468/526, loss: 0.8526090383529663
2023-01-22 23:40:27.607350: step: 1472/526, loss: 1.317407488822937
2023-01-22 23:40:28.736791: step: 1476/526, loss: 1.2262513637542725
2023-01-22 23:40:29.849638: step: 1480/526, loss: 1.0341687202453613
2023-01-22 23:40:30.971754: step: 1484/526, loss: 1.428326964378357
2023-01-22 23:40:32.074272: step: 1488/526, loss: 0.1320885717868805
2023-01-22 23:40:33.197131: step: 1492/526, loss: 0.16648346185684204
2023-01-22 23:40:34.301469: step: 1496/526, loss: 1.1512404680252075
2023-01-22 23:40:35.429521: step: 1500/526, loss: 0.13755732774734497
2023-01-22 23:40:36.539553: step: 1504/526, loss: 0.16974076628684998
2023-01-22 23:40:37.673428: step: 1508/526, loss: 0.45059338212013245
2023-01-22 23:40:38.855055: step: 1512/526, loss: 1.5823800563812256
2023-01-22 23:40:39.995431: step: 1516/526, loss: 0.364286333322525
2023-01-22 23:40:41.124300: step: 1520/526, loss: 1.3566417694091797
2023-01-22 23:40:42.281365: step: 1524/526, loss: 1.0856091976165771
2023-01-22 23:40:43.419010: step: 1528/526, loss: 0.5379573702812195
2023-01-22 23:40:44.520899: step: 1532/526, loss: 0.05152153968811035
2023-01-22 23:40:45.650988: step: 1536/526, loss: 0.2345394790172577
2023-01-22 23:40:46.775544: step: 1540/526, loss: 0.11498479545116425
2023-01-22 23:40:47.897260: step: 1544/526, loss: 1.08973228931427
2023-01-22 23:40:49.035505: step: 1548/526, loss: 0.12101593613624573
2023-01-22 23:40:50.188711: step: 1552/526, loss: 0.251290500164032
2023-01-22 23:40:51.324550: step: 1556/526, loss: 1.249951720237732
2023-01-22 23:40:52.460315: step: 1560/526, loss: 0.5401656031608582
2023-01-22 23:40:53.584183: step: 1564/526, loss: 0.5475764274597168
2023-01-22 23:40:54.699866: step: 1568/526, loss: 0.27133098244667053
2023-01-22 23:40:55.844214: step: 1572/526, loss: 1.6317224502563477
2023-01-22 23:40:56.975259: step: 1576/526, loss: 0.3935227394104004
2023-01-22 23:40:58.115840: step: 1580/526, loss: 0.5932140350341797
2023-01-22 23:40:59.272544: step: 1584/526, loss: 0.8116245865821838
2023-01-22 23:41:00.391302: step: 1588/526, loss: 0.17813152074813843
2023-01-22 23:41:01.529698: step: 1592/526, loss: 1.099025845527649
2023-01-22 23:41:02.643975: step: 1596/526, loss: 0.3425900638103485
2023-01-22 23:41:03.759891: step: 1600/526, loss: 1.39274263381958
2023-01-22 23:41:04.936486: step: 1604/526, loss: 0.9731160402297974
2023-01-22 23:41:06.070585: step: 1608/526, loss: 0.0604243278503418
2023-01-22 23:41:07.190146: step: 1612/526, loss: 0.6072297692298889
2023-01-22 23:41:08.354401: step: 1616/526, loss: 0.7625547647476196
2023-01-22 23:41:09.483990: step: 1620/526, loss: 2.1663389205932617
2023-01-22 23:41:10.603017: step: 1624/526, loss: 0.12372012436389923
2023-01-22 23:41:11.740309: step: 1628/526, loss: 0.10592193901538849
2023-01-22 23:41:12.862566: step: 1632/526, loss: 0.13152508437633514
2023-01-22 23:41:14.018333: step: 1636/526, loss: 0.44631558656692505
2023-01-22 23:41:15.162594: step: 1640/526, loss: 0.27061766386032104
2023-01-22 23:41:16.289281: step: 1644/526, loss: 8.072844505310059
2023-01-22 23:41:17.412018: step: 1648/526, loss: 0.2594289481639862
2023-01-22 23:41:18.544783: step: 1652/526, loss: 0.33607929944992065
2023-01-22 23:41:19.700387: step: 1656/526, loss: 0.4192092716693878
2023-01-22 23:41:20.855101: step: 1660/526, loss: 1.0942312479019165
2023-01-22 23:41:21.957678: step: 1664/526, loss: 0.3006388247013092
2023-01-22 23:41:23.102352: step: 1668/526, loss: 0.5258996486663818
2023-01-22 23:41:24.253176: step: 1672/526, loss: 0.2088792324066162
2023-01-22 23:41:25.411546: step: 1676/526, loss: 0.16801539063453674
2023-01-22 23:41:26.567247: step: 1680/526, loss: 0.8115229606628418
2023-01-22 23:41:27.714514: step: 1684/526, loss: 0.27260667085647583
2023-01-22 23:41:28.842735: step: 1688/526, loss: 2.6050796508789062
2023-01-22 23:41:29.997876: step: 1692/526, loss: 0.2026577889919281
2023-01-22 23:41:31.125733: step: 1696/526, loss: 0.3631228506565094
2023-01-22 23:41:32.239496: step: 1700/526, loss: 0.42658910155296326
2023-01-22 23:41:33.356565: step: 1704/526, loss: 0.20788437128067017
2023-01-22 23:41:34.488948: step: 1708/526, loss: 0.20939479768276215
2023-01-22 23:41:35.611633: step: 1712/526, loss: 0.23475365340709686
2023-01-22 23:41:36.729370: step: 1716/526, loss: 0.6525284647941589
2023-01-22 23:41:37.867996: step: 1720/526, loss: 0.8020996451377869
2023-01-22 23:41:38.996161: step: 1724/526, loss: 0.9109253883361816
2023-01-22 23:41:40.120898: step: 1728/526, loss: 0.13469500839710236
2023-01-22 23:41:41.266256: step: 1732/526, loss: 0.3011285364627838
2023-01-22 23:41:42.434556: step: 1736/526, loss: 0.4028759002685547
2023-01-22 23:41:43.544953: step: 1740/526, loss: 0.8307867050170898
2023-01-22 23:41:44.646119: step: 1744/526, loss: 0.7511939406394958
2023-01-22 23:41:45.789385: step: 1748/526, loss: 1.1502940654754639
2023-01-22 23:41:46.932400: step: 1752/526, loss: 0.7582845091819763
2023-01-22 23:41:48.048089: step: 1756/526, loss: 1.912783145904541
2023-01-22 23:41:49.186395: step: 1760/526, loss: 0.090985968708992
2023-01-22 23:41:50.298964: step: 1764/526, loss: 0.15521731972694397
2023-01-22 23:41:51.446178: step: 1768/526, loss: 0.4850344657897949
2023-01-22 23:41:52.576498: step: 1772/526, loss: 0.08559072017669678
2023-01-22 23:41:53.702806: step: 1776/526, loss: 0.17542386054992676
2023-01-22 23:41:54.856348: step: 1780/526, loss: 0.7627726793289185
2023-01-22 23:41:55.979821: step: 1784/526, loss: 0.09132376313209534
2023-01-22 23:41:57.105815: step: 1788/526, loss: 0.09789452701807022
2023-01-22 23:41:58.237551: step: 1792/526, loss: 0.15408021211624146
2023-01-22 23:41:59.383377: step: 1796/526, loss: 1.2216967344284058
2023-01-22 23:42:00.511570: step: 1800/526, loss: 0.15602655708789825
2023-01-22 23:42:01.642656: step: 1804/526, loss: 0.6172432899475098
2023-01-22 23:42:02.762787: step: 1808/526, loss: 0.48861628770828247
2023-01-22 23:42:03.925054: step: 1812/526, loss: 0.3700433075428009
2023-01-22 23:42:05.094231: step: 1816/526, loss: 0.5947478413581848
2023-01-22 23:42:06.197522: step: 1820/526, loss: 0.16661682724952698
2023-01-22 23:42:07.320977: step: 1824/526, loss: 0.7500246167182922
2023-01-22 23:42:08.457872: step: 1828/526, loss: 0.33961400389671326
2023-01-22 23:42:09.595390: step: 1832/526, loss: 0.2885696589946747
2023-01-22 23:42:10.719266: step: 1836/526, loss: 0.5720929503440857
2023-01-22 23:42:11.840209: step: 1840/526, loss: 0.4878579080104828
2023-01-22 23:42:12.982592: step: 1844/526, loss: 0.5794669985771179
2023-01-22 23:42:14.094629: step: 1848/526, loss: 0.26986151933670044
2023-01-22 23:42:15.206348: step: 1852/526, loss: 0.7763718962669373
2023-01-22 23:42:16.344231: step: 1856/526, loss: 1.6587055921554565
2023-01-22 23:42:17.451973: step: 1860/526, loss: 1.0288796424865723
2023-01-22 23:42:18.607577: step: 1864/526, loss: 0.21489034593105316
2023-01-22 23:42:19.738354: step: 1868/526, loss: 2.1826789379119873
2023-01-22 23:42:20.877956: step: 1872/526, loss: 1.1303766965866089
2023-01-22 23:42:22.042203: step: 1876/526, loss: 0.4038127362728119
2023-01-22 23:42:23.189540: step: 1880/526, loss: 0.40224477648735046
2023-01-22 23:42:24.334890: step: 1884/526, loss: 0.1496295928955078
2023-01-22 23:42:25.482123: step: 1888/526, loss: 0.12028808891773224
2023-01-22 23:42:26.643669: step: 1892/526, loss: 0.43746626377105713
2023-01-22 23:42:27.768540: step: 1896/526, loss: 0.1351669430732727
2023-01-22 23:42:28.942590: step: 1900/526, loss: 0.5046834945678711
2023-01-22 23:42:30.099741: step: 1904/526, loss: 0.6530091762542725
2023-01-22 23:42:31.231264: step: 1908/526, loss: 0.37235116958618164
2023-01-22 23:42:32.351905: step: 1912/526, loss: 0.07220964133739471
2023-01-22 23:42:33.464396: step: 1916/526, loss: 1.303880214691162
2023-01-22 23:42:34.596004: step: 1920/526, loss: 0.1236216127872467
2023-01-22 23:42:35.707567: step: 1924/526, loss: 0.597282886505127
2023-01-22 23:42:36.819753: step: 1928/526, loss: 0.9237990975379944
2023-01-22 23:42:37.966991: step: 1932/526, loss: 0.6608754396438599
2023-01-22 23:42:39.098860: step: 1936/526, loss: 0.45004063844680786
2023-01-22 23:42:40.250041: step: 1940/526, loss: 0.23730525374412537
2023-01-22 23:42:41.402365: step: 1944/526, loss: 0.2515888214111328
2023-01-22 23:42:42.517663: step: 1948/526, loss: 0.19622564315795898
2023-01-22 23:42:43.628452: step: 1952/526, loss: 0.8251916170120239
2023-01-22 23:42:44.762896: step: 1956/526, loss: 0.19301262497901917
2023-01-22 23:42:45.899657: step: 1960/526, loss: 0.11155568063259125
2023-01-22 23:42:47.056302: step: 1964/526, loss: 0.10877638310194016
2023-01-22 23:42:48.207777: step: 1968/526, loss: 1.6936662197113037
2023-01-22 23:42:49.356337: step: 1972/526, loss: 1.429900884628296
2023-01-22 23:42:50.497274: step: 1976/526, loss: 1.3313575983047485
2023-01-22 23:42:51.658981: step: 1980/526, loss: 0.16067099571228027
2023-01-22 23:42:52.770229: step: 1984/526, loss: 0.18011170625686646
2023-01-22 23:42:53.890697: step: 1988/526, loss: 0.5535411238670349
2023-01-22 23:42:55.013239: step: 1992/526, loss: 0.4083411991596222
2023-01-22 23:42:56.144271: step: 1996/526, loss: 1.4199025630950928
2023-01-22 23:42:57.272097: step: 2000/526, loss: 2.347923517227173
2023-01-22 23:42:58.378149: step: 2004/526, loss: 0.16935959458351135
2023-01-22 23:42:59.495544: step: 2008/526, loss: 0.6884486675262451
2023-01-22 23:43:00.635818: step: 2012/526, loss: 0.12982749938964844
2023-01-22 23:43:01.770708: step: 2016/526, loss: 6.484982967376709
2023-01-22 23:43:02.909098: step: 2020/526, loss: 0.7090138792991638
2023-01-22 23:43:04.089451: step: 2024/526, loss: 0.8112053871154785
2023-01-22 23:43:05.209887: step: 2028/526, loss: 0.2834510803222656
2023-01-22 23:43:06.360787: step: 2032/526, loss: 0.16633328795433044
2023-01-22 23:43:07.479378: step: 2036/526, loss: 0.35938215255737305
2023-01-22 23:43:08.609126: step: 2040/526, loss: 0.2283536046743393
2023-01-22 23:43:09.717528: step: 2044/526, loss: 0.07451625168323517
2023-01-22 23:43:10.837864: step: 2048/526, loss: 0.08642594516277313
2023-01-22 23:43:11.987985: step: 2052/526, loss: 0.7784126400947571
2023-01-22 23:43:13.115619: step: 2056/526, loss: 0.8092414140701294
2023-01-22 23:43:14.283718: step: 2060/526, loss: 0.40342777967453003
2023-01-22 23:43:15.395252: step: 2064/526, loss: 0.14191943407058716
2023-01-22 23:43:16.524520: step: 2068/526, loss: 0.278459370136261
2023-01-22 23:43:17.663033: step: 2072/526, loss: 0.5136095285415649
2023-01-22 23:43:18.786420: step: 2076/526, loss: 0.27368029952049255
2023-01-22 23:43:19.947569: step: 2080/526, loss: 1.7214633226394653
2023-01-22 23:43:21.040500: step: 2084/526, loss: 0.5242714881896973
2023-01-22 23:43:22.150285: step: 2088/526, loss: 0.3880229592323303
2023-01-22 23:43:23.311334: step: 2092/526, loss: 0.2507127821445465
2023-01-22 23:43:24.412081: step: 2096/526, loss: 0.2552480399608612
2023-01-22 23:43:25.510343: step: 2100/526, loss: 0.44141992926597595
2023-01-22 23:43:26.646802: step: 2104/526, loss: 6.530412673950195
==================================================
Loss: 0.751
--------------------
Dev: {'event': {'p': 0.6193853427895981, 'r': 0.6977363515312917, 'f1': 0.6562304320601127}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Test: {'event': {'p': 0.5890142226581657, 'r': 0.6268267223382046, 'f1': 0.6073324905183313}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Chinese: {'event': {'p': 0.6376811594202898, 'r': 0.8148148148148148, 'f1': 0.7154471544715448}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Korean: {'event': {'p': 0.7, 'r': 0.3333333333333333, 'f1': 0.45161290322580644}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Russian: {'event': {'p': 0.5, 'r': 0.3611111111111111, 'f1': 0.4193548387096774}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
New best chinese model...
New best korean model...
New best russian model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6193853427895981, 'r': 0.6977363515312917, 'f1': 0.6562304320601127}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Eng Test for Chinese: {'event': {'p': 0.5890142226581657, 'r': 0.6268267223382046, 'f1': 0.6073324905183313}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Sample Chinese: {'event': {'p': 0.6376811594202898, 'r': 0.8148148148148148, 'f1': 0.7154471544715448}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6193853427895981, 'r': 0.6977363515312917, 'f1': 0.6562304320601127}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Eng Test for Korean: {'event': {'p': 0.5890142226581657, 'r': 0.6268267223382046, 'f1': 0.6073324905183313}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Sample Korean: {'event': {'p': 0.7, 'r': 0.3333333333333333, 'f1': 0.45161290322580644}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6193853427895981, 'r': 0.6977363515312917, 'f1': 0.6562304320601127}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Eng Test for Russian: {'event': {'p': 0.5890142226581657, 'r': 0.6268267223382046, 'f1': 0.6073324905183313}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Sample Russian: {'event': {'p': 0.5, 'r': 0.3611111111111111, 'f1': 0.4193548387096774}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
******************************
Epoch: 2
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-22 23:44:30.814286: step: 4/526, loss: 0.7371686697006226
2023-01-22 23:44:31.981081: step: 8/526, loss: 0.14277620613574982
2023-01-22 23:44:33.134101: step: 12/526, loss: 0.22620564699172974
2023-01-22 23:44:34.267500: step: 16/526, loss: 6.459168910980225
2023-01-22 23:44:35.410133: step: 20/526, loss: 2.7405848503112793
2023-01-22 23:44:36.533321: step: 24/526, loss: 0.4026455879211426
2023-01-22 23:44:37.663533: step: 28/526, loss: 0.19612395763397217
2023-01-22 23:44:38.757355: step: 32/526, loss: 0.0955914556980133
2023-01-22 23:44:39.865238: step: 36/526, loss: 0.849429190158844
2023-01-22 23:44:40.984568: step: 40/526, loss: 0.28417879343032837
2023-01-22 23:44:42.089131: step: 44/526, loss: 0.18784980475902557
2023-01-22 23:44:43.227406: step: 48/526, loss: 0.6011751890182495
2023-01-22 23:44:44.383918: step: 52/526, loss: 1.947126865386963
2023-01-22 23:44:45.487661: step: 56/526, loss: 0.05753608047962189
2023-01-22 23:44:46.609888: step: 60/526, loss: 0.8347592353820801
2023-01-22 23:44:47.739250: step: 64/526, loss: 0.8283432126045227
2023-01-22 23:44:48.886232: step: 68/526, loss: 0.192641019821167
2023-01-22 23:44:50.021492: step: 72/526, loss: 1.207589030265808
2023-01-22 23:44:51.151756: step: 76/526, loss: 0.28988510370254517
2023-01-22 23:44:52.305584: step: 80/526, loss: 0.2214467078447342
2023-01-22 23:44:53.439130: step: 84/526, loss: 0.054837897419929504
2023-01-22 23:44:54.566233: step: 88/526, loss: 0.17066727578639984
2023-01-22 23:44:55.710400: step: 92/526, loss: 0.26862430572509766
2023-01-22 23:44:56.830930: step: 96/526, loss: 0.1193912997841835
2023-01-22 23:44:57.970265: step: 100/526, loss: 0.1942417174577713
2023-01-22 23:44:59.111530: step: 104/526, loss: 0.7256829738616943
2023-01-22 23:45:00.241833: step: 108/526, loss: 0.34531232714653015
2023-01-22 23:45:01.354955: step: 112/526, loss: 0.3780747354030609
2023-01-22 23:45:02.489612: step: 116/526, loss: 0.14871588349342346
2023-01-22 23:45:03.642063: step: 120/526, loss: 1.8272624015808105
2023-01-22 23:45:04.775059: step: 124/526, loss: 2.5648231506347656
2023-01-22 23:45:05.899357: step: 128/526, loss: 0.2851431369781494
2023-01-22 23:45:07.021450: step: 132/526, loss: 0.4197579622268677
2023-01-22 23:45:08.133840: step: 136/526, loss: 0.3052535057067871
2023-01-22 23:45:09.240531: step: 140/526, loss: 0.5125947594642639
2023-01-22 23:45:10.382873: step: 144/526, loss: 0.7838599681854248
2023-01-22 23:45:11.529039: step: 148/526, loss: 0.3850439786911011
2023-01-22 23:45:12.667104: step: 152/526, loss: 0.8700082898139954
2023-01-22 23:45:13.780209: step: 156/526, loss: 0.1666758954524994
2023-01-22 23:45:14.930585: step: 160/526, loss: 0.18689113855361938
2023-01-22 23:45:16.060569: step: 164/526, loss: 0.14302244782447815
2023-01-22 23:45:17.193826: step: 168/526, loss: 0.158074289560318
2023-01-22 23:45:18.306602: step: 172/526, loss: 1.471127986907959
2023-01-22 23:45:19.429815: step: 176/526, loss: 0.5885858535766602
2023-01-22 23:45:20.557675: step: 180/526, loss: 0.30178844928741455
2023-01-22 23:45:21.671750: step: 184/526, loss: 0.1546308994293213
2023-01-22 23:45:22.800042: step: 188/526, loss: 0.5008574724197388
2023-01-22 23:45:23.928385: step: 192/526, loss: 0.12119532376527786
2023-01-22 23:45:25.031780: step: 196/526, loss: 0.14665204286575317
2023-01-22 23:45:26.177007: step: 200/526, loss: 0.2566226124763489
2023-01-22 23:45:27.297164: step: 204/526, loss: 6.856566905975342
2023-01-22 23:45:28.441985: step: 208/526, loss: 0.8183758854866028
2023-01-22 23:45:29.551704: step: 212/526, loss: 0.7002421021461487
2023-01-22 23:45:30.702842: step: 216/526, loss: 1.0828109979629517
2023-01-22 23:45:31.818739: step: 220/526, loss: 0.2938995957374573
2023-01-22 23:45:32.953222: step: 224/526, loss: 0.2463708519935608
2023-01-22 23:45:34.091905: step: 228/526, loss: 0.7030066251754761
2023-01-22 23:45:35.312969: step: 232/526, loss: 0.27724459767341614
2023-01-22 23:45:36.440169: step: 236/526, loss: 0.8027188777923584
2023-01-22 23:45:37.561059: step: 240/526, loss: 0.16752897202968597
2023-01-22 23:45:38.674885: step: 244/526, loss: 6.357608795166016
2023-01-22 23:45:39.824294: step: 248/526, loss: 0.22123274207115173
2023-01-22 23:45:40.971584: step: 252/526, loss: 0.13078276813030243
2023-01-22 23:45:42.170580: step: 256/526, loss: 0.4018796980381012
2023-01-22 23:45:43.338423: step: 260/526, loss: 0.5865241885185242
2023-01-22 23:45:44.501290: step: 264/526, loss: 0.8238250017166138
2023-01-22 23:45:45.663938: step: 268/526, loss: 1.88313889503479
2023-01-22 23:45:46.793949: step: 272/526, loss: 0.9527637362480164
2023-01-22 23:45:47.910796: step: 276/526, loss: 0.9735413789749146
2023-01-22 23:45:49.063283: step: 280/526, loss: 0.21730008721351624
2023-01-22 23:45:50.204495: step: 284/526, loss: 0.6474210619926453
2023-01-22 23:45:51.343782: step: 288/526, loss: 0.2266136258840561
2023-01-22 23:45:52.475396: step: 292/526, loss: 0.5801045894622803
2023-01-22 23:45:53.608196: step: 296/526, loss: 6.723257541656494
2023-01-22 23:45:54.733969: step: 300/526, loss: 0.19547128677368164
2023-01-22 23:45:55.895303: step: 304/526, loss: 0.2741946280002594
2023-01-22 23:45:57.004521: step: 308/526, loss: 0.25209468603134155
2023-01-22 23:45:58.148665: step: 312/526, loss: 0.7836558222770691
2023-01-22 23:45:59.261779: step: 316/526, loss: 0.08856067806482315
2023-01-22 23:46:00.374115: step: 320/526, loss: 0.13040843605995178
2023-01-22 23:46:01.536685: step: 324/526, loss: 0.6577426195144653
2023-01-22 23:46:02.645215: step: 328/526, loss: 0.3646667003631592
2023-01-22 23:46:03.796558: step: 332/526, loss: 0.7247281074523926
2023-01-22 23:46:04.946254: step: 336/526, loss: 0.17073917388916016
2023-01-22 23:46:06.074024: step: 340/526, loss: 0.21138477325439453
2023-01-22 23:46:07.201368: step: 344/526, loss: 0.095563605427742
2023-01-22 23:46:08.358711: step: 348/526, loss: 0.9368394017219543
2023-01-22 23:46:09.471995: step: 352/526, loss: 0.28148743510246277
2023-01-22 23:46:10.590808: step: 356/526, loss: 0.3404358923435211
2023-01-22 23:46:11.761305: step: 360/526, loss: 0.3894495964050293
2023-01-22 23:46:12.886103: step: 364/526, loss: 0.21750307083129883
2023-01-22 23:46:14.012291: step: 368/526, loss: 0.10416451096534729
2023-01-22 23:46:15.119264: step: 372/526, loss: 0.07759085297584534
2023-01-22 23:46:16.226138: step: 376/526, loss: 0.3454691469669342
2023-01-22 23:46:17.363436: step: 380/526, loss: 0.8341060876846313
2023-01-22 23:46:18.487256: step: 384/526, loss: 0.3944700360298157
2023-01-22 23:46:19.608107: step: 388/526, loss: 0.7250019311904907
2023-01-22 23:46:20.726943: step: 392/526, loss: 0.20458531379699707
2023-01-22 23:46:21.882239: step: 396/526, loss: 0.826136589050293
2023-01-22 23:46:23.028070: step: 400/526, loss: 0.685352623462677
2023-01-22 23:46:24.165710: step: 404/526, loss: 0.27412986755371094
2023-01-22 23:46:25.331101: step: 408/526, loss: 0.10080757737159729
2023-01-22 23:46:26.481890: step: 412/526, loss: 0.17872238159179688
2023-01-22 23:46:27.633082: step: 416/526, loss: 1.8121154308319092
2023-01-22 23:46:28.762445: step: 420/526, loss: 0.2770763337612152
2023-01-22 23:46:29.864122: step: 424/526, loss: 0.3830799460411072
2023-01-22 23:46:30.995560: step: 428/526, loss: 0.34010785818099976
2023-01-22 23:46:32.137103: step: 432/526, loss: 0.16602563858032227
2023-01-22 23:46:33.293047: step: 436/526, loss: 1.202040195465088
2023-01-22 23:46:34.427913: step: 440/526, loss: 0.21638837456703186
2023-01-22 23:46:35.561499: step: 444/526, loss: 0.08371257781982422
2023-01-22 23:46:36.721609: step: 448/526, loss: 1.234601378440857
2023-01-22 23:46:37.873482: step: 452/526, loss: 0.8448450565338135
2023-01-22 23:46:39.042507: step: 456/526, loss: 0.15782856941223145
2023-01-22 23:46:40.195536: step: 460/526, loss: 2.00057315826416
2023-01-22 23:46:41.331838: step: 464/526, loss: 0.1114925891160965
2023-01-22 23:46:42.459106: step: 468/526, loss: 0.2380194216966629
2023-01-22 23:46:43.625782: step: 472/526, loss: 0.8867142796516418
2023-01-22 23:46:44.792804: step: 476/526, loss: 3.263335704803467
2023-01-22 23:46:45.930430: step: 480/526, loss: 0.6447303891181946
2023-01-22 23:46:47.054693: step: 484/526, loss: 0.4122544825077057
2023-01-22 23:46:48.202442: step: 488/526, loss: 0.3632197380065918
2023-01-22 23:46:49.344151: step: 492/526, loss: 0.17861899733543396
2023-01-22 23:46:50.493497: step: 496/526, loss: 0.9973654747009277
2023-01-22 23:46:51.615645: step: 500/526, loss: 0.3834887742996216
2023-01-22 23:46:52.749225: step: 504/526, loss: 0.6213089227676392
2023-01-22 23:46:53.887892: step: 508/526, loss: 0.5560882091522217
2023-01-22 23:46:55.020398: step: 512/526, loss: 0.5832465291023254
2023-01-22 23:46:56.149443: step: 516/526, loss: 0.08488158881664276
2023-01-22 23:46:57.289783: step: 520/526, loss: 0.6259737610816956
2023-01-22 23:46:58.450385: step: 524/526, loss: 0.24635343253612518
2023-01-22 23:46:59.588187: step: 528/526, loss: 0.2052966207265854
2023-01-22 23:47:00.707747: step: 532/526, loss: 0.14800778031349182
2023-01-22 23:47:01.850517: step: 536/526, loss: 0.34591084718704224
2023-01-22 23:47:02.975130: step: 540/526, loss: 0.21279869973659515
2023-01-22 23:47:04.099868: step: 544/526, loss: 0.2472452074289322
2023-01-22 23:47:05.254472: step: 548/526, loss: 9.263084411621094
2023-01-22 23:47:06.383592: step: 552/526, loss: 0.1365702748298645
2023-01-22 23:47:07.520713: step: 556/526, loss: 1.2602787017822266
2023-01-22 23:47:08.691765: step: 560/526, loss: 0.9019102454185486
2023-01-22 23:47:09.849770: step: 564/526, loss: 0.05515509098768234
2023-01-22 23:47:10.988857: step: 568/526, loss: 1.2054473161697388
2023-01-22 23:47:12.115338: step: 572/526, loss: 0.20976220071315765
2023-01-22 23:47:13.262703: step: 576/526, loss: 1.3283308744430542
2023-01-22 23:47:14.384133: step: 580/526, loss: 0.9090974926948547
2023-01-22 23:47:15.513453: step: 584/526, loss: 1.6399478912353516
2023-01-22 23:47:16.618218: step: 588/526, loss: 0.17284272611141205
2023-01-22 23:47:17.746939: step: 592/526, loss: 0.17959660291671753
2023-01-22 23:47:18.899211: step: 596/526, loss: 0.0896090567111969
2023-01-22 23:47:20.053409: step: 600/526, loss: 0.13831454515457153
2023-01-22 23:47:21.216802: step: 604/526, loss: 0.9562665224075317
2023-01-22 23:47:22.331441: step: 608/526, loss: 0.17174744606018066
2023-01-22 23:47:23.527860: step: 612/526, loss: 0.10748949646949768
2023-01-22 23:47:24.633778: step: 616/526, loss: 0.6629589796066284
2023-01-22 23:47:25.779944: step: 620/526, loss: 0.21342550218105316
2023-01-22 23:47:26.977195: step: 624/526, loss: 0.204206183552742
2023-01-22 23:47:28.111707: step: 628/526, loss: 0.08018426597118378
2023-01-22 23:47:29.287027: step: 632/526, loss: 0.10665550082921982
2023-01-22 23:47:30.429797: step: 636/526, loss: 0.2275547981262207
2023-01-22 23:47:31.574056: step: 640/526, loss: 0.6749961376190186
2023-01-22 23:47:32.712246: step: 644/526, loss: 0.06434555351734161
2023-01-22 23:47:33.807793: step: 648/526, loss: 0.2734025716781616
2023-01-22 23:47:34.939008: step: 652/526, loss: 0.13301712274551392
2023-01-22 23:47:36.064533: step: 656/526, loss: 0.2600051164627075
2023-01-22 23:47:37.211812: step: 660/526, loss: 0.08476734161376953
2023-01-22 23:47:38.352956: step: 664/526, loss: 1.7141621112823486
2023-01-22 23:47:39.499425: step: 668/526, loss: 0.474673330783844
2023-01-22 23:47:40.607461: step: 672/526, loss: 0.4861367642879486
2023-01-22 23:47:41.725999: step: 676/526, loss: 0.6617634892463684
2023-01-22 23:47:42.911246: step: 680/526, loss: 0.08454294502735138
2023-01-22 23:47:44.070892: step: 684/526, loss: 0.13664832711219788
2023-01-22 23:47:45.176895: step: 688/526, loss: 0.7994793653488159
2023-01-22 23:47:46.358220: step: 692/526, loss: 0.7563218474388123
2023-01-22 23:47:47.509833: step: 696/526, loss: 0.12473689019680023
2023-01-22 23:47:48.626643: step: 700/526, loss: 0.1568729430437088
2023-01-22 23:47:49.763559: step: 704/526, loss: 0.520408034324646
2023-01-22 23:47:50.898288: step: 708/526, loss: 0.10370621830224991
2023-01-22 23:47:51.995398: step: 712/526, loss: 0.3513716757297516
2023-01-22 23:47:53.134413: step: 716/526, loss: 0.18958741426467896
2023-01-22 23:47:54.301287: step: 720/526, loss: 0.4684511125087738
2023-01-22 23:47:55.443765: step: 724/526, loss: 0.07368616759777069
2023-01-22 23:47:56.559811: step: 728/526, loss: 0.8527272939682007
2023-01-22 23:47:57.701433: step: 732/526, loss: 0.2130545675754547
2023-01-22 23:47:58.817898: step: 736/526, loss: 0.2087687999010086
2023-01-22 23:47:59.952464: step: 740/526, loss: 0.270187646150589
2023-01-22 23:48:01.070682: step: 744/526, loss: 0.36126840114593506
2023-01-22 23:48:02.202914: step: 748/526, loss: 0.19674549996852875
2023-01-22 23:48:03.330119: step: 752/526, loss: 0.8210179805755615
2023-01-22 23:48:04.469524: step: 756/526, loss: 1.8814308643341064
2023-01-22 23:48:05.615919: step: 760/526, loss: 0.1634916365146637
2023-01-22 23:48:06.734287: step: 764/526, loss: 0.08084812760353088
2023-01-22 23:48:07.877041: step: 768/526, loss: 0.0727061778306961
2023-01-22 23:48:09.027834: step: 772/526, loss: 0.16369609534740448
2023-01-22 23:48:10.163391: step: 776/526, loss: 1.20604407787323
2023-01-22 23:48:11.273225: step: 780/526, loss: 0.1588907241821289
2023-01-22 23:48:12.427587: step: 784/526, loss: 0.03581704944372177
2023-01-22 23:48:13.581818: step: 788/526, loss: 0.19073882699012756
2023-01-22 23:48:14.697979: step: 792/526, loss: 0.1830032467842102
2023-01-22 23:48:15.868875: step: 796/526, loss: 1.1516741514205933
2023-01-22 23:48:16.998117: step: 800/526, loss: 6.965559959411621
2023-01-22 23:48:18.122136: step: 804/526, loss: 0.18981438875198364
2023-01-22 23:48:19.259037: step: 808/526, loss: 0.21846535801887512
2023-01-22 23:48:20.394604: step: 812/526, loss: 0.09237129986286163
2023-01-22 23:48:21.555892: step: 816/526, loss: 0.27701517939567566
2023-01-22 23:48:22.662349: step: 820/526, loss: 0.7196527719497681
2023-01-22 23:48:23.795032: step: 824/526, loss: 0.19946356117725372
2023-01-22 23:48:24.908706: step: 828/526, loss: 0.15538763999938965
2023-01-22 23:48:26.041337: step: 832/526, loss: 0.15155087411403656
2023-01-22 23:48:27.207787: step: 836/526, loss: 1.4473398923873901
2023-01-22 23:48:28.356564: step: 840/526, loss: 0.7193412184715271
2023-01-22 23:48:29.460948: step: 844/526, loss: 0.14692479372024536
2023-01-22 23:48:30.591065: step: 848/526, loss: 0.19061346352100372
2023-01-22 23:48:31.691550: step: 852/526, loss: 0.33641982078552246
2023-01-22 23:48:32.849146: step: 856/526, loss: 0.34093427658081055
2023-01-22 23:48:33.981442: step: 860/526, loss: 0.7681768536567688
2023-01-22 23:48:35.120892: step: 864/526, loss: 0.18542137742042542
2023-01-22 23:48:36.246900: step: 868/526, loss: 0.037743210792541504
2023-01-22 23:48:37.360343: step: 872/526, loss: 0.9006453156471252
2023-01-22 23:48:38.495910: step: 876/526, loss: 0.11338487267494202
2023-01-22 23:48:39.643544: step: 880/526, loss: 0.4533006548881531
2023-01-22 23:48:40.767094: step: 884/526, loss: 0.8425458669662476
2023-01-22 23:48:41.882514: step: 888/526, loss: 0.7941291332244873
2023-01-22 23:48:43.018130: step: 892/526, loss: 1.0038068294525146
2023-01-22 23:48:44.132161: step: 896/526, loss: 0.20018891990184784
2023-01-22 23:48:45.242096: step: 900/526, loss: 0.6852834224700928
2023-01-22 23:48:46.356458: step: 904/526, loss: 1.060499906539917
2023-01-22 23:48:47.495540: step: 908/526, loss: 0.1644587516784668
2023-01-22 23:48:48.604718: step: 912/526, loss: 0.2475832998752594
2023-01-22 23:48:49.734923: step: 916/526, loss: 4.642247676849365
2023-01-22 23:48:50.859423: step: 920/526, loss: 1.515236735343933
2023-01-22 23:48:51.963189: step: 924/526, loss: 0.2769314646720886
2023-01-22 23:48:53.103941: step: 928/526, loss: 0.8623466491699219
2023-01-22 23:48:54.245845: step: 932/526, loss: 0.3963509798049927
2023-01-22 23:48:55.373202: step: 936/526, loss: 0.19093409180641174
2023-01-22 23:48:56.552918: step: 940/526, loss: 0.4518064558506012
2023-01-22 23:48:57.671021: step: 944/526, loss: 0.1292782723903656
2023-01-22 23:48:58.804254: step: 948/526, loss: 7.877197742462158
2023-01-22 23:48:59.936562: step: 952/526, loss: 0.12697263062000275
2023-01-22 23:49:01.074371: step: 956/526, loss: 0.17100726068019867
2023-01-22 23:49:02.209183: step: 960/526, loss: 0.21051812171936035
2023-01-22 23:49:03.344679: step: 964/526, loss: 0.9328678250312805
2023-01-22 23:49:04.498488: step: 968/526, loss: 1.9260833263397217
2023-01-22 23:49:05.655532: step: 972/526, loss: 0.11043057590723038
2023-01-22 23:49:06.821453: step: 976/526, loss: 0.3045993745326996
2023-01-22 23:49:07.942144: step: 980/526, loss: 0.15302905440330505
2023-01-22 23:49:09.089021: step: 984/526, loss: 0.5110117197036743
2023-01-22 23:49:10.227855: step: 988/526, loss: 0.06770721077919006
2023-01-22 23:49:11.384426: step: 992/526, loss: 0.13780584931373596
2023-01-22 23:49:12.518902: step: 996/526, loss: 0.2611147463321686
2023-01-22 23:49:13.653893: step: 1000/526, loss: 0.060150954872369766
2023-01-22 23:49:14.791212: step: 1004/526, loss: 1.1544982194900513
2023-01-22 23:49:15.923671: step: 1008/526, loss: 0.20008069276809692
2023-01-22 23:49:17.054528: step: 1012/526, loss: 0.7357773780822754
2023-01-22 23:49:18.197731: step: 1016/526, loss: 0.07235307991504669
2023-01-22 23:49:19.333467: step: 1020/526, loss: 0.3647525906562805
2023-01-22 23:49:20.494211: step: 1024/526, loss: 0.40268927812576294
2023-01-22 23:49:21.619382: step: 1028/526, loss: 0.7556501626968384
2023-01-22 23:49:22.766409: step: 1032/526, loss: 0.6995542645454407
2023-01-22 23:49:23.890206: step: 1036/526, loss: 0.124393992125988
2023-01-22 23:49:25.026275: step: 1040/526, loss: 0.35593196749687195
2023-01-22 23:49:26.160176: step: 1044/526, loss: 0.13892945647239685
2023-01-22 23:49:27.278247: step: 1048/526, loss: 0.989820122718811
2023-01-22 23:49:28.411523: step: 1052/526, loss: 0.09860043227672577
2023-01-22 23:49:29.542938: step: 1056/526, loss: 0.5358060598373413
2023-01-22 23:49:30.633225: step: 1060/526, loss: 0.21409329771995544
2023-01-22 23:49:31.752815: step: 1064/526, loss: 0.6925015449523926
2023-01-22 23:49:32.922428: step: 1068/526, loss: 0.4330235421657562
2023-01-22 23:49:34.073223: step: 1072/526, loss: 6.833107948303223
2023-01-22 23:49:35.213537: step: 1076/526, loss: 0.1685158610343933
2023-01-22 23:49:36.325144: step: 1080/526, loss: 0.17064112424850464
2023-01-22 23:49:37.470288: step: 1084/526, loss: 1.2955894470214844
2023-01-22 23:49:38.579606: step: 1088/526, loss: 0.029970981180667877
2023-01-22 23:49:39.680127: step: 1092/526, loss: 0.7043238282203674
2023-01-22 23:49:40.806621: step: 1096/526, loss: 0.09527397155761719
2023-01-22 23:49:41.931933: step: 1100/526, loss: 0.12092152237892151
2023-01-22 23:49:43.082423: step: 1104/526, loss: 0.06790585815906525
2023-01-22 23:49:44.213532: step: 1108/526, loss: 0.10850711166858673
2023-01-22 23:49:45.390382: step: 1112/526, loss: 0.20133551955223083
2023-01-22 23:49:46.508037: step: 1116/526, loss: 0.15107566118240356
2023-01-22 23:49:47.612868: step: 1120/526, loss: 0.21529769897460938
2023-01-22 23:49:48.749508: step: 1124/526, loss: 0.4878457188606262
2023-01-22 23:49:49.886041: step: 1128/526, loss: 0.241888627409935
2023-01-22 23:49:51.012549: step: 1132/526, loss: 1.7180202007293701
2023-01-22 23:49:52.136323: step: 1136/526, loss: 0.7908123135566711
2023-01-22 23:49:53.267313: step: 1140/526, loss: 0.2929447293281555
2023-01-22 23:49:54.416170: step: 1144/526, loss: 0.5712848901748657
2023-01-22 23:49:55.526757: step: 1148/526, loss: 1.495749831199646
2023-01-22 23:49:56.675558: step: 1152/526, loss: 0.6782424449920654
2023-01-22 23:49:57.800361: step: 1156/526, loss: 0.052136801183223724
2023-01-22 23:49:58.959985: step: 1160/526, loss: 0.1865929216146469
2023-01-22 23:50:00.076369: step: 1164/526, loss: 0.18351951241493225
2023-01-22 23:50:01.198930: step: 1168/526, loss: 0.7199469804763794
2023-01-22 23:50:02.350868: step: 1172/526, loss: 0.6309493780136108
2023-01-22 23:50:03.472783: step: 1176/526, loss: 0.179520845413208
2023-01-22 23:50:04.600013: step: 1180/526, loss: 0.4822305738925934
2023-01-22 23:50:05.703042: step: 1184/526, loss: 0.3642409145832062
2023-01-22 23:50:06.835303: step: 1188/526, loss: 0.8015809655189514
2023-01-22 23:50:08.008122: step: 1192/526, loss: 0.14055633544921875
2023-01-22 23:50:09.141482: step: 1196/526, loss: 0.13793951272964478
2023-01-22 23:50:10.268589: step: 1200/526, loss: 0.06664423644542694
2023-01-22 23:50:11.391351: step: 1204/526, loss: 0.07401466369628906
2023-01-22 23:50:12.517602: step: 1208/526, loss: 0.2749904692173004
2023-01-22 23:50:13.678898: step: 1212/526, loss: 0.5550336241722107
2023-01-22 23:50:14.822145: step: 1216/526, loss: 0.3880097270011902
2023-01-22 23:50:15.982604: step: 1220/526, loss: 0.49445676803588867
2023-01-22 23:50:17.109002: step: 1224/526, loss: 0.06755051761865616
2023-01-22 23:50:18.229222: step: 1228/526, loss: 1.6481280326843262
2023-01-22 23:50:19.377465: step: 1232/526, loss: 0.12867221236228943
2023-01-22 23:50:20.525629: step: 1236/526, loss: 0.13796454668045044
2023-01-22 23:50:21.653383: step: 1240/526, loss: 0.11804446578025818
2023-01-22 23:50:22.801103: step: 1244/526, loss: 0.6119052171707153
2023-01-22 23:50:23.948129: step: 1248/526, loss: 0.4132540822029114
2023-01-22 23:50:25.090798: step: 1252/526, loss: 0.1319485306739807
2023-01-22 23:50:26.213058: step: 1256/526, loss: 0.1947527825832367
2023-01-22 23:50:27.369709: step: 1260/526, loss: 0.13552546501159668
2023-01-22 23:50:28.479185: step: 1264/526, loss: 0.5897731781005859
2023-01-22 23:50:29.586042: step: 1268/526, loss: 1.033892035484314
2023-01-22 23:50:30.714519: step: 1272/526, loss: 0.7521183490753174
2023-01-22 23:50:31.876909: step: 1276/526, loss: 0.16722755134105682
2023-01-22 23:50:33.043045: step: 1280/526, loss: 0.15022316575050354
2023-01-22 23:50:34.167859: step: 1284/526, loss: 6.773693561553955
2023-01-22 23:50:35.314476: step: 1288/526, loss: 0.12554121017456055
2023-01-22 23:50:36.474288: step: 1292/526, loss: 0.8333118557929993
2023-01-22 23:50:37.615938: step: 1296/526, loss: 0.23240791261196136
2023-01-22 23:50:38.735665: step: 1300/526, loss: 0.13540272414684296
2023-01-22 23:50:39.883362: step: 1304/526, loss: 0.09288950264453888
2023-01-22 23:50:41.032477: step: 1308/526, loss: 0.5963178277015686
2023-01-22 23:50:42.160750: step: 1312/526, loss: 0.39611929655075073
2023-01-22 23:50:43.294437: step: 1316/526, loss: 0.09164667129516602
2023-01-22 23:50:44.452405: step: 1320/526, loss: 0.5031039118766785
2023-01-22 23:50:45.577516: step: 1324/526, loss: 0.20707297325134277
2023-01-22 23:50:46.703595: step: 1328/526, loss: 0.2976667284965515
2023-01-22 23:50:47.819558: step: 1332/526, loss: 0.13202795386314392
2023-01-22 23:50:48.942610: step: 1336/526, loss: 0.3469514846801758
2023-01-22 23:50:50.081739: step: 1340/526, loss: 2.144334554672241
2023-01-22 23:50:51.215612: step: 1344/526, loss: 0.26964569091796875
2023-01-22 23:50:52.329051: step: 1348/526, loss: 0.27661553025245667
2023-01-22 23:50:53.494434: step: 1352/526, loss: 0.4165247082710266
2023-01-22 23:50:54.617563: step: 1356/526, loss: 0.3352002501487732
2023-01-22 23:50:55.722458: step: 1360/526, loss: 0.25387871265411377
2023-01-22 23:50:56.849949: step: 1364/526, loss: 0.7760627865791321
2023-01-22 23:50:57.978499: step: 1368/526, loss: 0.9163665771484375
2023-01-22 23:50:59.105877: step: 1372/526, loss: 0.09707331657409668
2023-01-22 23:51:00.290232: step: 1376/526, loss: 0.0896996483206749
2023-01-22 23:51:01.414109: step: 1380/526, loss: 0.1081552505493164
2023-01-22 23:51:02.593740: step: 1384/526, loss: 0.40700292587280273
2023-01-22 23:51:03.731475: step: 1388/526, loss: 0.04897632449865341
2023-01-22 23:51:04.892813: step: 1392/526, loss: 1.671891450881958
2023-01-22 23:51:06.015362: step: 1396/526, loss: 0.25511035323143005
2023-01-22 23:51:07.184997: step: 1400/526, loss: 0.4179447293281555
2023-01-22 23:51:08.321239: step: 1404/526, loss: 0.22246304154396057
2023-01-22 23:51:09.499572: step: 1408/526, loss: 0.7529239654541016
2023-01-22 23:51:10.637672: step: 1412/526, loss: 0.19054308533668518
2023-01-22 23:51:11.782616: step: 1416/526, loss: 0.22854405641555786
2023-01-22 23:51:12.920915: step: 1420/526, loss: 0.3220301568508148
2023-01-22 23:51:14.050935: step: 1424/526, loss: 1.4963210821151733
2023-01-22 23:51:15.184378: step: 1428/526, loss: 0.0571308359503746
2023-01-22 23:51:16.292621: step: 1432/526, loss: 0.12312392890453339
2023-01-22 23:51:17.402047: step: 1436/526, loss: 0.08499126136302948
2023-01-22 23:51:18.525308: step: 1440/526, loss: 0.33305859565734863
2023-01-22 23:51:19.686019: step: 1444/526, loss: 0.7659327387809753
2023-01-22 23:51:20.822307: step: 1448/526, loss: 0.11860928684473038
2023-01-22 23:51:21.923177: step: 1452/526, loss: 0.09401998668909073
2023-01-22 23:51:23.004123: step: 1456/526, loss: 0.20078416168689728
2023-01-22 23:51:24.121278: step: 1460/526, loss: 0.7208659648895264
2023-01-22 23:51:25.298537: step: 1464/526, loss: 0.5318990349769592
2023-01-22 23:51:26.423245: step: 1468/526, loss: 1.0348161458969116
2023-01-22 23:51:27.555959: step: 1472/526, loss: 0.19070421159267426
2023-01-22 23:51:28.665238: step: 1476/526, loss: 0.8465617895126343
2023-01-22 23:51:29.816043: step: 1480/526, loss: 0.10943231731653214
2023-01-22 23:51:30.988469: step: 1484/526, loss: 0.7222205996513367
2023-01-22 23:51:32.116295: step: 1488/526, loss: 0.33950796723365784
2023-01-22 23:51:33.281004: step: 1492/526, loss: 0.14517097175121307
2023-01-22 23:51:34.388704: step: 1496/526, loss: 0.2597583830356598
2023-01-22 23:51:35.499302: step: 1500/526, loss: 0.13723182678222656
2023-01-22 23:51:36.645660: step: 1504/526, loss: 0.7158119678497314
2023-01-22 23:51:37.783460: step: 1508/526, loss: 0.9934319257736206
2023-01-22 23:51:38.922976: step: 1512/526, loss: 0.2308272421360016
2023-01-22 23:51:40.047296: step: 1516/526, loss: 0.1680740863084793
2023-01-22 23:51:41.177705: step: 1520/526, loss: 0.404039204120636
2023-01-22 23:51:42.289557: step: 1524/526, loss: 0.04582517221570015
2023-01-22 23:51:43.430552: step: 1528/526, loss: 0.14079482853412628
2023-01-22 23:51:44.535651: step: 1532/526, loss: 0.20451106131076813
2023-01-22 23:51:45.686278: step: 1536/526, loss: 0.23486891388893127
2023-01-22 23:51:46.837980: step: 1540/526, loss: 1.179813265800476
2023-01-22 23:51:47.955684: step: 1544/526, loss: 0.12898799777030945
2023-01-22 23:51:49.101961: step: 1548/526, loss: 1.0655649900436401
2023-01-22 23:51:50.248654: step: 1552/526, loss: 0.11519122123718262
2023-01-22 23:51:51.374000: step: 1556/526, loss: 0.961085319519043
2023-01-22 23:51:52.490002: step: 1560/526, loss: 0.8817575573921204
2023-01-22 23:51:53.646152: step: 1564/526, loss: 0.6503612399101257
2023-01-22 23:51:54.776737: step: 1568/526, loss: 0.7036305665969849
2023-01-22 23:51:55.894557: step: 1572/526, loss: 0.14672155678272247
2023-01-22 23:51:57.044568: step: 1576/526, loss: 0.05438194423913956
2023-01-22 23:51:58.182951: step: 1580/526, loss: 0.162797212600708
2023-01-22 23:51:59.307116: step: 1584/526, loss: 1.4852162599563599
2023-01-22 23:52:00.440051: step: 1588/526, loss: 0.9209295511245728
2023-01-22 23:52:01.557045: step: 1592/526, loss: 0.16470471024513245
2023-01-22 23:52:02.684797: step: 1596/526, loss: 0.1885172724723816
2023-01-22 23:52:03.792275: step: 1600/526, loss: 0.13555240631103516
2023-01-22 23:52:04.930822: step: 1604/526, loss: 1.318207025527954
2023-01-22 23:52:06.071883: step: 1608/526, loss: 0.604112982749939
2023-01-22 23:52:07.214175: step: 1612/526, loss: 1.2439247369766235
2023-01-22 23:52:08.341407: step: 1616/526, loss: 0.14844894409179688
2023-01-22 23:52:09.483176: step: 1620/526, loss: 0.114264577627182
2023-01-22 23:52:10.633694: step: 1624/526, loss: 0.7023523449897766
2023-01-22 23:52:11.786322: step: 1628/526, loss: 0.1391819268465042
2023-01-22 23:52:12.931510: step: 1632/526, loss: 0.41977816820144653
2023-01-22 23:52:14.065812: step: 1636/526, loss: 0.019954919815063477
2023-01-22 23:52:15.232414: step: 1640/526, loss: 0.17443951964378357
2023-01-22 23:52:16.360267: step: 1644/526, loss: 0.08527708053588867
2023-01-22 23:52:17.490954: step: 1648/526, loss: 0.16211938858032227
2023-01-22 23:52:18.637444: step: 1652/526, loss: 0.6825048923492432
2023-01-22 23:52:19.774554: step: 1656/526, loss: 0.2446775883436203
2023-01-22 23:52:20.903733: step: 1660/526, loss: 0.13465556502342224
2023-01-22 23:52:22.037531: step: 1664/526, loss: 0.2758150100708008
2023-01-22 23:52:23.185735: step: 1668/526, loss: 0.16842412948608398
2023-01-22 23:52:24.331660: step: 1672/526, loss: 0.5834553837776184
2023-01-22 23:52:25.471138: step: 1676/526, loss: 0.5031963586807251
2023-01-22 23:52:26.643662: step: 1680/526, loss: 0.7752524614334106
2023-01-22 23:52:27.781423: step: 1684/526, loss: 0.4572591781616211
2023-01-22 23:52:28.926303: step: 1688/526, loss: 0.20999452471733093
2023-01-22 23:52:30.058150: step: 1692/526, loss: 0.12950201332569122
2023-01-22 23:52:31.159757: step: 1696/526, loss: 0.12381734699010849
2023-01-22 23:52:32.290606: step: 1700/526, loss: 1.1109201908111572
2023-01-22 23:52:33.405569: step: 1704/526, loss: 0.23636063933372498
2023-01-22 23:52:34.560918: step: 1708/526, loss: 0.1920696347951889
2023-01-22 23:52:35.678783: step: 1712/526, loss: 0.2930752635002136
2023-01-22 23:52:36.804330: step: 1716/526, loss: 0.2131677269935608
2023-01-22 23:52:37.932604: step: 1720/526, loss: 0.2644510269165039
2023-01-22 23:52:39.075223: step: 1724/526, loss: 0.08906535804271698
2023-01-22 23:52:40.194310: step: 1728/526, loss: 1.166796326637268
2023-01-22 23:52:41.320766: step: 1732/526, loss: 1.7660728693008423
2023-01-22 23:52:42.459577: step: 1736/526, loss: 0.13750696182250977
2023-01-22 23:52:43.620402: step: 1740/526, loss: 1.9681421518325806
2023-01-22 23:52:44.739872: step: 1744/526, loss: 0.08952713012695312
2023-01-22 23:52:45.839900: step: 1748/526, loss: 0.7064719200134277
2023-01-22 23:52:47.000413: step: 1752/526, loss: 1.5497710704803467
2023-01-22 23:52:48.154932: step: 1756/526, loss: 0.2173960655927658
2023-01-22 23:52:49.312207: step: 1760/526, loss: 0.4258689880371094
2023-01-22 23:52:50.445044: step: 1764/526, loss: 8.201467514038086
2023-01-22 23:52:51.570093: step: 1768/526, loss: 0.2752320170402527
2023-01-22 23:52:52.722130: step: 1772/526, loss: 0.1689353585243225
2023-01-22 23:52:53.867584: step: 1776/526, loss: 0.09599890559911728
2023-01-22 23:52:54.996121: step: 1780/526, loss: 0.06656942516565323
2023-01-22 23:52:56.094448: step: 1784/526, loss: 0.37990808486938477
2023-01-22 23:52:57.247958: step: 1788/526, loss: 0.6800745129585266
2023-01-22 23:52:58.351634: step: 1792/526, loss: 0.12408037483692169
2023-01-22 23:52:59.464202: step: 1796/526, loss: 0.4488007128238678
2023-01-22 23:53:00.621820: step: 1800/526, loss: 0.1357475221157074
2023-01-22 23:53:01.744396: step: 1804/526, loss: 0.582709014415741
2023-01-22 23:53:02.863525: step: 1808/526, loss: 0.057540036737918854
2023-01-22 23:53:04.021218: step: 1812/526, loss: 1.0467431545257568
2023-01-22 23:53:05.150150: step: 1816/526, loss: 0.08513914048671722
2023-01-22 23:53:06.308688: step: 1820/526, loss: 1.3753395080566406
2023-01-22 23:53:07.421068: step: 1824/526, loss: 0.10260339081287384
2023-01-22 23:53:08.513023: step: 1828/526, loss: 0.21843966841697693
2023-01-22 23:53:09.640137: step: 1832/526, loss: 0.18705901503562927
2023-01-22 23:53:10.781671: step: 1836/526, loss: 0.0969705581665039
2023-01-22 23:53:11.914218: step: 1840/526, loss: 0.19723044335842133
2023-01-22 23:53:13.005806: step: 1844/526, loss: 0.6745023131370544
2023-01-22 23:53:14.129666: step: 1848/526, loss: 0.6798454523086548
2023-01-22 23:53:15.275982: step: 1852/526, loss: 0.33070430159568787
2023-01-22 23:53:16.409124: step: 1856/526, loss: 0.0542755126953125
2023-01-22 23:53:17.545045: step: 1860/526, loss: 0.12937946617603302
2023-01-22 23:53:18.685842: step: 1864/526, loss: 0.6542806029319763
2023-01-22 23:53:19.811186: step: 1868/526, loss: 0.11233168095350266
2023-01-22 23:53:20.939806: step: 1872/526, loss: 0.22717523574829102
2023-01-22 23:53:22.045463: step: 1876/526, loss: 0.8232075572013855
2023-01-22 23:53:23.164531: step: 1880/526, loss: 0.11775856465101242
2023-01-22 23:53:24.327741: step: 1884/526, loss: 7.02653169631958
2023-01-22 23:53:25.468245: step: 1888/526, loss: 0.0841517448425293
2023-01-22 23:53:26.709553: step: 1892/526, loss: 0.241241455078125
2023-01-22 23:53:27.812035: step: 1896/526, loss: 0.8380448818206787
2023-01-22 23:53:28.963382: step: 1900/526, loss: 0.5783689618110657
2023-01-22 23:53:30.083693: step: 1904/526, loss: 0.09035640209913254
2023-01-22 23:53:31.214923: step: 1908/526, loss: 0.26674729585647583
2023-01-22 23:53:32.373963: step: 1912/526, loss: 0.15535469353199005
2023-01-22 23:53:33.513685: step: 1916/526, loss: 0.90913987159729
2023-01-22 23:53:34.637484: step: 1920/526, loss: 0.24711419641971588
2023-01-22 23:53:35.765900: step: 1924/526, loss: 0.6851876378059387
2023-01-22 23:53:36.916073: step: 1928/526, loss: 0.7727624773979187
2023-01-22 23:53:38.064522: step: 1932/526, loss: 0.15901513397693634
2023-01-22 23:53:39.234369: step: 1936/526, loss: 0.2840121388435364
2023-01-22 23:53:40.381439: step: 1940/526, loss: 0.23126983642578125
2023-01-22 23:53:41.514854: step: 1944/526, loss: 1.0606579780578613
2023-01-22 23:53:42.647867: step: 1948/526, loss: 0.12540951371192932
2023-01-22 23:53:43.780480: step: 1952/526, loss: 0.12876950204372406
2023-01-22 23:53:44.912152: step: 1956/526, loss: 0.7682791948318481
2023-01-22 23:53:46.071574: step: 1960/526, loss: 0.4332424998283386
2023-01-22 23:53:47.193614: step: 1964/526, loss: 0.16579023003578186
2023-01-22 23:53:48.328930: step: 1968/526, loss: 0.32374557852745056
2023-01-22 23:53:49.468615: step: 1972/526, loss: 0.2833237648010254
2023-01-22 23:53:50.604007: step: 1976/526, loss: 0.14649434387683868
2023-01-22 23:53:51.748298: step: 1980/526, loss: 0.4473107159137726
2023-01-22 23:53:52.881998: step: 1984/526, loss: 0.04439125210046768
2023-01-22 23:53:53.996468: step: 1988/526, loss: 0.07865715026855469
2023-01-22 23:53:55.122579: step: 1992/526, loss: 0.1248352974653244
2023-01-22 23:53:56.249959: step: 1996/526, loss: 0.24855881929397583
2023-01-22 23:53:57.386584: step: 2000/526, loss: 0.20954833924770355
2023-01-22 23:53:58.513441: step: 2004/526, loss: 0.07233085483312607
2023-01-22 23:53:59.675427: step: 2008/526, loss: 0.12671375274658203
2023-01-22 23:54:00.798858: step: 2012/526, loss: 0.16479754447937012
2023-01-22 23:54:01.906542: step: 2016/526, loss: 0.0788472592830658
2023-01-22 23:54:03.018231: step: 2020/526, loss: 0.25870028138160706
2023-01-22 23:54:04.158040: step: 2024/526, loss: 0.15761509537696838
2023-01-22 23:54:05.282837: step: 2028/526, loss: 0.12140502780675888
2023-01-22 23:54:06.437090: step: 2032/526, loss: 0.1563182920217514
2023-01-22 23:54:07.602091: step: 2036/526, loss: 0.2727026045322418
2023-01-22 23:54:08.756548: step: 2040/526, loss: 0.48599594831466675
2023-01-22 23:54:09.893447: step: 2044/526, loss: 0.21796751022338867
2023-01-22 23:54:11.014599: step: 2048/526, loss: 0.17315025627613068
2023-01-22 23:54:12.186443: step: 2052/526, loss: 1.8426520824432373
2023-01-22 23:54:13.340234: step: 2056/526, loss: 0.175628662109375
2023-01-22 23:54:14.494209: step: 2060/526, loss: 0.27656039595603943
2023-01-22 23:54:15.622200: step: 2064/526, loss: 0.1536390781402588
2023-01-22 23:54:16.749013: step: 2068/526, loss: 0.10318709164857864
2023-01-22 23:54:17.888544: step: 2072/526, loss: 0.38626405596733093
2023-01-22 23:54:19.035190: step: 2076/526, loss: 0.14542122185230255
2023-01-22 23:54:20.187033: step: 2080/526, loss: 0.21770288050174713
2023-01-22 23:54:21.269294: step: 2084/526, loss: 0.6639150977134705
2023-01-22 23:54:22.418999: step: 2088/526, loss: 0.668742835521698
2023-01-22 23:54:23.543518: step: 2092/526, loss: 0.12401580810546875
2023-01-22 23:54:24.681777: step: 2096/526, loss: 0.14313897490501404
2023-01-22 23:54:25.825356: step: 2100/526, loss: 0.46609991788864136
2023-01-22 23:54:27.004823: step: 2104/526, loss: 1.8064841032028198
==================================================
Loss: 0.603
--------------------
Dev: {'event': {'p': 0.6604010025062657, 'r': 0.7017310252996005, 'f1': 0.6804389928986443}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Test: {'event': {'p': 0.6480836236933798, 'r': 0.6795407098121086, 'f1': 0.6634394904458599}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Chinese: {'event': {'p': 0.6323529411764706, 'r': 0.7962962962962963, 'f1': 0.7049180327868853}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Korean: {'event': {'p': 0.7575757575757576, 'r': 0.3968253968253968, 'f1': 0.5208333333333334}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Russian: {'event': {'p': 0.44, 'r': 0.3055555555555556, 'f1': 0.36065573770491804}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
New best chinese model...
New best korean model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6604010025062657, 'r': 0.7017310252996005, 'f1': 0.6804389928986443}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Eng Test for Chinese: {'event': {'p': 0.6480836236933798, 'r': 0.6795407098121086, 'f1': 0.6634394904458599}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Sample Chinese: {'event': {'p': 0.6323529411764706, 'r': 0.7962962962962963, 'f1': 0.7049180327868853}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6604010025062657, 'r': 0.7017310252996005, 'f1': 0.6804389928986443}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Eng Test for Korean: {'event': {'p': 0.6480836236933798, 'r': 0.6795407098121086, 'f1': 0.6634394904458599}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Sample Korean: {'event': {'p': 0.7575757575757576, 'r': 0.3968253968253968, 'f1': 0.5208333333333334}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6193853427895981, 'r': 0.6977363515312917, 'f1': 0.6562304320601127}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Eng Test for Russian: {'event': {'p': 0.5890142226581657, 'r': 0.6268267223382046, 'f1': 0.6073324905183313}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Sample Russian: {'event': {'p': 0.5, 'r': 0.3611111111111111, 'f1': 0.4193548387096774}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
******************************
Epoch: 3
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-22 23:55:23.667031: step: 4/526, loss: 0.09815549850463867
2023-01-22 23:55:24.799985: step: 8/526, loss: 0.778786301612854
2023-01-22 23:55:25.921509: step: 12/526, loss: 0.26237422227859497
2023-01-22 23:55:27.068224: step: 16/526, loss: 1.166905164718628
2023-01-22 23:55:28.194268: step: 20/526, loss: 0.48532190918922424
2023-01-22 23:55:29.322837: step: 24/526, loss: 0.1599363535642624
2023-01-22 23:55:30.456525: step: 28/526, loss: 0.7683050036430359
2023-01-22 23:55:31.589327: step: 32/526, loss: 0.24998140335083008
2023-01-22 23:55:32.754428: step: 36/526, loss: 0.16066434979438782
2023-01-22 23:55:33.887771: step: 40/526, loss: 0.40726643800735474
2023-01-22 23:55:35.033101: step: 44/526, loss: 0.39912334084510803
2023-01-22 23:55:36.205528: step: 48/526, loss: 0.7967689037322998
2023-01-22 23:55:37.350219: step: 52/526, loss: 0.15700674057006836
2023-01-22 23:55:38.483637: step: 56/526, loss: 0.052364349365234375
2023-01-22 23:55:39.606339: step: 60/526, loss: 0.017160989344120026
2023-01-22 23:55:40.759274: step: 64/526, loss: 0.15097865462303162
2023-01-22 23:55:41.867642: step: 68/526, loss: 5.9862589836120605
2023-01-22 23:55:42.985123: step: 72/526, loss: 0.2158377766609192
2023-01-22 23:55:44.124584: step: 76/526, loss: 0.24023528397083282
2023-01-22 23:55:45.305634: step: 80/526, loss: 0.5475010871887207
2023-01-22 23:55:46.454860: step: 84/526, loss: 0.7246114015579224
2023-01-22 23:55:47.599480: step: 88/526, loss: 0.16104355454444885
2023-01-22 23:55:48.711275: step: 92/526, loss: 1.012978434562683
2023-01-22 23:55:49.838617: step: 96/526, loss: 0.12779411673545837
2023-01-22 23:55:50.976427: step: 100/526, loss: 0.055496931076049805
2023-01-22 23:55:52.138868: step: 104/526, loss: 0.7779055833816528
2023-01-22 23:55:53.258930: step: 108/526, loss: 0.5048141479492188
2023-01-22 23:55:54.429742: step: 112/526, loss: 0.9158059358596802
2023-01-22 23:55:55.534399: step: 116/526, loss: 0.39264994859695435
2023-01-22 23:55:56.651933: step: 120/526, loss: 0.11361436545848846
2023-01-22 23:55:57.762342: step: 124/526, loss: 0.7745078802108765
2023-01-22 23:55:58.871757: step: 128/526, loss: 0.05784139782190323
2023-01-22 23:55:59.999826: step: 132/526, loss: 0.1789465993642807
2023-01-22 23:56:01.149835: step: 136/526, loss: 0.466744989156723
2023-01-22 23:56:02.296208: step: 140/526, loss: 0.32892686128616333
2023-01-22 23:56:03.433759: step: 144/526, loss: 6.197875022888184
2023-01-22 23:56:04.584689: step: 148/526, loss: 0.18039646744728088
2023-01-22 23:56:05.753346: step: 152/526, loss: 1.033241629600525
2023-01-22 23:56:06.876141: step: 156/526, loss: 0.41054707765579224
2023-01-22 23:56:07.983783: step: 160/526, loss: 0.0938936248421669
2023-01-22 23:56:09.110022: step: 164/526, loss: 0.661960780620575
2023-01-22 23:56:10.271684: step: 168/526, loss: 0.5396683812141418
2023-01-22 23:56:11.395112: step: 172/526, loss: 0.23382607102394104
2023-01-22 23:56:12.521484: step: 176/526, loss: 0.7011641263961792
2023-01-22 23:56:13.663916: step: 180/526, loss: 0.6363601684570312
2023-01-22 23:56:14.784442: step: 184/526, loss: 0.10609379410743713
2023-01-22 23:56:15.932447: step: 188/526, loss: 0.7307679653167725
2023-01-22 23:56:17.064736: step: 192/526, loss: 0.873341977596283
2023-01-22 23:56:18.212213: step: 196/526, loss: 0.15034499764442444
2023-01-22 23:56:19.330520: step: 200/526, loss: 0.18926949799060822
2023-01-22 23:56:20.464218: step: 204/526, loss: 0.2140326052904129
2023-01-22 23:56:21.575413: step: 208/526, loss: 0.13158798217773438
2023-01-22 23:56:22.703545: step: 212/526, loss: 0.14059486985206604
2023-01-22 23:56:23.852458: step: 216/526, loss: 0.3620586395263672
2023-01-22 23:56:24.977772: step: 220/526, loss: 0.09814868122339249
2023-01-22 23:56:26.092490: step: 224/526, loss: 0.14739857614040375
2023-01-22 23:56:27.236337: step: 228/526, loss: 0.8174866437911987
2023-01-22 23:56:28.393874: step: 232/526, loss: 0.6810035705566406
2023-01-22 23:56:29.522088: step: 236/526, loss: 0.729864776134491
2023-01-22 23:56:30.649392: step: 240/526, loss: 0.05735397711396217
2023-01-22 23:56:31.827186: step: 244/526, loss: 0.6320679783821106
2023-01-22 23:56:32.939852: step: 248/526, loss: 0.026183797046542168
2023-01-22 23:56:34.093942: step: 252/526, loss: 0.18542452156543732
2023-01-22 23:56:35.264817: step: 256/526, loss: 0.15911169350147247
2023-01-22 23:56:36.452929: step: 260/526, loss: 0.16515932977199554
2023-01-22 23:56:37.620449: step: 264/526, loss: 0.10121984034776688
2023-01-22 23:56:38.819426: step: 268/526, loss: 0.15083780884742737
2023-01-22 23:56:39.946889: step: 272/526, loss: 0.149017333984375
2023-01-22 23:56:41.112515: step: 276/526, loss: 1.0262253284454346
2023-01-22 23:56:42.235058: step: 280/526, loss: 0.3056522309780121
2023-01-22 23:56:43.361840: step: 284/526, loss: 0.7167744040489197
2023-01-22 23:56:44.487659: step: 288/526, loss: 0.06786961853504181
2023-01-22 23:56:45.592120: step: 292/526, loss: 0.12627820670604706
2023-01-22 23:56:46.729661: step: 296/526, loss: 0.16959428787231445
2023-01-22 23:56:47.886011: step: 300/526, loss: 0.5408000946044922
2023-01-22 23:56:49.027630: step: 304/526, loss: 0.748309850692749
2023-01-22 23:56:50.159461: step: 308/526, loss: 0.1924075037240982
2023-01-22 23:56:51.295216: step: 312/526, loss: 0.18067866563796997
2023-01-22 23:56:52.449779: step: 316/526, loss: 0.06243553012609482
2023-01-22 23:56:53.610897: step: 320/526, loss: 0.12429027259349823
2023-01-22 23:56:54.748037: step: 324/526, loss: 0.10332375019788742
2023-01-22 23:56:55.894828: step: 328/526, loss: 0.2423768937587738
2023-01-22 23:56:57.029586: step: 332/526, loss: 0.6232358813285828
2023-01-22 23:56:58.152110: step: 336/526, loss: 0.2174820601940155
2023-01-22 23:56:59.281857: step: 340/526, loss: 1.1696345806121826
2023-01-22 23:57:00.407051: step: 344/526, loss: 0.6681364178657532
2023-01-22 23:57:01.546516: step: 348/526, loss: 0.761664867401123
2023-01-22 23:57:02.687144: step: 352/526, loss: 0.6626855731010437
2023-01-22 23:57:03.809826: step: 356/526, loss: 0.2573251724243164
2023-01-22 23:57:04.931370: step: 360/526, loss: 0.12913647294044495
2023-01-22 23:57:06.058165: step: 364/526, loss: 0.6908438205718994
2023-01-22 23:57:07.207253: step: 368/526, loss: 6.724062442779541
2023-01-22 23:57:08.360421: step: 372/526, loss: 0.1610884666442871
2023-01-22 23:57:09.495037: step: 376/526, loss: 0.13350383937358856
2023-01-22 23:57:10.630948: step: 380/526, loss: 0.315802663564682
2023-01-22 23:57:11.745839: step: 384/526, loss: 0.09661498665809631
2023-01-22 23:57:12.911842: step: 388/526, loss: 0.283730149269104
2023-01-22 23:57:14.029398: step: 392/526, loss: 0.2510172724723816
2023-01-22 23:57:15.169602: step: 396/526, loss: 0.21686744689941406
2023-01-22 23:57:16.339785: step: 400/526, loss: 0.8394155502319336
2023-01-22 23:57:17.513061: step: 404/526, loss: 0.19308948516845703
2023-01-22 23:57:18.642200: step: 408/526, loss: 0.5364732146263123
2023-01-22 23:57:19.756622: step: 412/526, loss: 0.13504552841186523
2023-01-22 23:57:20.892378: step: 416/526, loss: 0.05910434573888779
2023-01-22 23:57:22.006518: step: 420/526, loss: 0.09674377739429474
2023-01-22 23:57:23.136864: step: 424/526, loss: 0.2659017741680145
2023-01-22 23:57:24.279890: step: 428/526, loss: 0.10842514038085938
2023-01-22 23:57:25.405719: step: 432/526, loss: 0.6830092072486877
2023-01-22 23:57:26.537041: step: 436/526, loss: 0.11732621490955353
2023-01-22 23:57:27.663461: step: 440/526, loss: 0.06782722473144531
2023-01-22 23:57:28.809893: step: 444/526, loss: 1.1526572704315186
2023-01-22 23:57:29.944405: step: 448/526, loss: 0.8452734351158142
2023-01-22 23:57:31.085544: step: 452/526, loss: 0.0719631165266037
2023-01-22 23:57:32.225417: step: 456/526, loss: 0.11287655681371689
2023-01-22 23:57:33.395077: step: 460/526, loss: 0.08829379081726074
2023-01-22 23:57:34.503758: step: 464/526, loss: 0.24529676139354706
2023-01-22 23:57:35.687537: step: 468/526, loss: 0.2507755160331726
2023-01-22 23:57:36.850832: step: 472/526, loss: 0.1434486359357834
2023-01-22 23:57:38.014037: step: 476/526, loss: 1.9669455289840698
2023-01-22 23:57:39.176540: step: 480/526, loss: 0.03885490819811821
2023-01-22 23:57:40.327330: step: 484/526, loss: 0.333885133266449
2023-01-22 23:57:41.438552: step: 488/526, loss: 0.24597254395484924
2023-01-22 23:57:42.589334: step: 492/526, loss: 0.15722675621509552
2023-01-22 23:57:43.758570: step: 496/526, loss: 0.2573823630809784
2023-01-22 23:57:44.912905: step: 500/526, loss: 0.05392961576581001
2023-01-22 23:57:46.103593: step: 504/526, loss: 0.06517043709754944
2023-01-22 23:57:47.230775: step: 508/526, loss: 0.15791350603103638
2023-01-22 23:57:48.337414: step: 512/526, loss: 0.1807699203491211
2023-01-22 23:57:49.455887: step: 516/526, loss: 0.14367209374904633
2023-01-22 23:57:50.598643: step: 520/526, loss: 0.2890182435512543
2023-01-22 23:57:51.733066: step: 524/526, loss: 0.2728877663612366
2023-01-22 23:57:52.863355: step: 528/526, loss: 0.15734797716140747
2023-01-22 23:57:53.983691: step: 532/526, loss: 0.0902770459651947
2023-01-22 23:57:55.133993: step: 536/526, loss: 0.042649269104003906
2023-01-22 23:57:56.273250: step: 540/526, loss: 0.7358492612838745
2023-01-22 23:57:57.421510: step: 544/526, loss: 0.19873514771461487
2023-01-22 23:57:58.564448: step: 548/526, loss: 0.14755135774612427
2023-01-22 23:57:59.730211: step: 552/526, loss: 0.2229456901550293
2023-01-22 23:58:00.890326: step: 556/526, loss: 0.9254617691040039
2023-01-22 23:58:02.026054: step: 560/526, loss: 0.2923905551433563
2023-01-22 23:58:03.140423: step: 564/526, loss: 0.314846396446228
2023-01-22 23:58:04.257963: step: 568/526, loss: 0.3457811772823334
2023-01-22 23:58:05.402119: step: 572/526, loss: 0.15723343193531036
2023-01-22 23:58:06.590361: step: 576/526, loss: 1.830252766609192
2023-01-22 23:58:07.712471: step: 580/526, loss: 0.032427262514829636
2023-01-22 23:58:08.837562: step: 584/526, loss: 0.1188659742474556
2023-01-22 23:58:09.962071: step: 588/526, loss: 1.2814996242523193
2023-01-22 23:58:11.096478: step: 592/526, loss: 1.1448551416397095
2023-01-22 23:58:12.259270: step: 596/526, loss: 0.3831920623779297
2023-01-22 23:58:13.386490: step: 600/526, loss: 0.06013665348291397
2023-01-22 23:58:14.516805: step: 604/526, loss: 0.690144419670105
2023-01-22 23:58:15.652821: step: 608/526, loss: 0.20937128365039825
2023-01-22 23:58:16.814399: step: 612/526, loss: 0.06971664726734161
2023-01-22 23:58:17.952420: step: 616/526, loss: 0.19894886016845703
2023-01-22 23:58:19.100240: step: 620/526, loss: 0.07591447979211807
2023-01-22 23:58:20.206862: step: 624/526, loss: 5.988174915313721
2023-01-22 23:58:21.345440: step: 628/526, loss: 0.1725023239850998
2023-01-22 23:58:22.483705: step: 632/526, loss: 0.06016264110803604
2023-01-22 23:58:23.611048: step: 636/526, loss: 0.7884900569915771
2023-01-22 23:58:24.728342: step: 640/526, loss: 1.5777852535247803
2023-01-22 23:58:25.875116: step: 644/526, loss: 0.14996632933616638
2023-01-22 23:58:27.012470: step: 648/526, loss: 0.17883777618408203
2023-01-22 23:58:28.161301: step: 652/526, loss: 1.7639210224151611
2023-01-22 23:58:29.289029: step: 656/526, loss: 0.05362577736377716
2023-01-22 23:58:30.458213: step: 660/526, loss: 0.08198356628417969
2023-01-22 23:58:31.601269: step: 664/526, loss: 0.1766609251499176
2023-01-22 23:58:32.755489: step: 668/526, loss: 0.167727991938591
2023-01-22 23:58:33.883857: step: 672/526, loss: 0.17878219485282898
2023-01-22 23:58:35.019547: step: 676/526, loss: 0.051870059221982956
2023-01-22 23:58:36.200744: step: 680/526, loss: 0.13780784606933594
2023-01-22 23:58:37.331758: step: 684/526, loss: 0.1823573112487793
2023-01-22 23:58:38.444627: step: 688/526, loss: 0.10534921288490295
2023-01-22 23:58:39.614693: step: 692/526, loss: 0.3059524595737457
2023-01-22 23:58:40.749540: step: 696/526, loss: 0.30730992555618286
2023-01-22 23:58:41.899990: step: 700/526, loss: 0.33931687474250793
2023-01-22 23:58:43.018025: step: 704/526, loss: 0.9796249866485596
2023-01-22 23:58:44.165838: step: 708/526, loss: 0.31933584809303284
2023-01-22 23:58:45.306404: step: 712/526, loss: 0.4349270761013031
2023-01-22 23:58:46.433092: step: 716/526, loss: 0.9338370561599731
2023-01-22 23:58:47.574630: step: 720/526, loss: 0.0669802725315094
2023-01-22 23:58:48.706310: step: 724/526, loss: 0.1706235408782959
2023-01-22 23:58:49.845086: step: 728/526, loss: 0.7605264782905579
2023-01-22 23:58:50.977145: step: 732/526, loss: 0.7951940298080444
2023-01-22 23:58:52.127646: step: 736/526, loss: 0.0916227400302887
2023-01-22 23:58:53.250345: step: 740/526, loss: 0.5308011174201965
2023-01-22 23:58:54.378603: step: 744/526, loss: 0.12734170258045197
2023-01-22 23:58:55.512840: step: 748/526, loss: 0.4225795567035675
2023-01-22 23:58:56.651471: step: 752/526, loss: 0.9455537796020508
2023-01-22 23:58:57.823573: step: 756/526, loss: 0.11672095954418182
2023-01-22 23:58:58.964357: step: 760/526, loss: 0.4404076635837555
2023-01-22 23:59:00.100970: step: 764/526, loss: 0.36769819259643555
2023-01-22 23:59:01.234362: step: 768/526, loss: 0.1434079110622406
2023-01-22 23:59:02.360262: step: 772/526, loss: 0.23262205719947815
2023-01-22 23:59:03.461417: step: 776/526, loss: 0.0569973923265934
2023-01-22 23:59:04.582130: step: 780/526, loss: 0.09339595586061478
2023-01-22 23:59:05.715229: step: 784/526, loss: 0.12500867247581482
2023-01-22 23:59:06.868234: step: 788/526, loss: 2.8017613887786865
2023-01-22 23:59:08.042024: step: 792/526, loss: 0.2985422909259796
2023-01-22 23:59:09.169774: step: 796/526, loss: 0.6917413473129272
2023-01-22 23:59:10.280242: step: 800/526, loss: 1.242168664932251
2023-01-22 23:59:11.411004: step: 804/526, loss: 0.19024498760700226
2023-01-22 23:59:12.546597: step: 808/526, loss: 1.0680491924285889
2023-01-22 23:59:13.708375: step: 812/526, loss: 0.21203525364398956
2023-01-22 23:59:14.829548: step: 816/526, loss: 1.0118982791900635
2023-01-22 23:59:15.967816: step: 820/526, loss: 0.1602334976196289
2023-01-22 23:59:17.100266: step: 824/526, loss: 0.020087718963623047
2023-01-22 23:59:18.211218: step: 828/526, loss: 0.25196534395217896
2023-01-22 23:59:19.336162: step: 832/526, loss: 0.1407441645860672
2023-01-22 23:59:20.471455: step: 836/526, loss: 0.13415169715881348
2023-01-22 23:59:21.570394: step: 840/526, loss: 0.07295289635658264
2023-01-22 23:59:22.699717: step: 844/526, loss: 0.11090050637722015
2023-01-22 23:59:23.827872: step: 848/526, loss: 0.08863496780395508
2023-01-22 23:59:24.939262: step: 852/526, loss: 6.1598801612854
2023-01-22 23:59:26.106231: step: 856/526, loss: 0.21306943893432617
2023-01-22 23:59:27.269273: step: 860/526, loss: 0.3341161608695984
2023-01-22 23:59:28.407598: step: 864/526, loss: 0.8827815055847168
2023-01-22 23:59:29.543827: step: 868/526, loss: 0.24832621216773987
2023-01-22 23:59:30.680359: step: 872/526, loss: 0.748885452747345
2023-01-22 23:59:31.821850: step: 876/526, loss: 0.14316312968730927
2023-01-22 23:59:32.958941: step: 880/526, loss: 0.1617463082075119
2023-01-22 23:59:34.077267: step: 884/526, loss: 1.1235769987106323
2023-01-22 23:59:35.219206: step: 888/526, loss: 0.2687419354915619
2023-01-22 23:59:36.348836: step: 892/526, loss: 5.968334197998047
2023-01-22 23:59:37.480816: step: 896/526, loss: 0.1484842300415039
2023-01-22 23:59:38.636574: step: 900/526, loss: 0.15555091202259064
2023-01-22 23:59:39.745941: step: 904/526, loss: 0.184285968542099
2023-01-22 23:59:40.913530: step: 908/526, loss: 0.11641374230384827
2023-01-22 23:59:42.076949: step: 912/526, loss: 0.09140090644359589
2023-01-22 23:59:43.227474: step: 916/526, loss: 0.6824744343757629
2023-01-22 23:59:44.384133: step: 920/526, loss: 0.05462322384119034
2023-01-22 23:59:45.516223: step: 924/526, loss: 0.12663468718528748
2023-01-22 23:59:46.641378: step: 928/526, loss: 0.05434150993824005
2023-01-22 23:59:47.763558: step: 932/526, loss: 0.214741051197052
2023-01-22 23:59:48.861752: step: 936/526, loss: 0.07408924400806427
2023-01-22 23:59:50.004041: step: 940/526, loss: 0.5570886135101318
2023-01-22 23:59:51.143481: step: 944/526, loss: 1.0303354263305664
2023-01-22 23:59:52.270702: step: 948/526, loss: 0.1643667221069336
2023-01-22 23:59:53.377603: step: 952/526, loss: 0.23496118187904358
2023-01-22 23:59:54.526512: step: 956/526, loss: 0.19179022312164307
2023-01-22 23:59:55.670153: step: 960/526, loss: 1.0404634475708008
2023-01-22 23:59:56.790250: step: 964/526, loss: 0.05198941379785538
2023-01-22 23:59:57.946802: step: 968/526, loss: 0.5997173190116882
2023-01-22 23:59:59.081323: step: 972/526, loss: 6.237577438354492
2023-01-23 00:00:00.221676: step: 976/526, loss: 0.10701847076416016
2023-01-23 00:00:01.410588: step: 980/526, loss: 0.2570188641548157
2023-01-23 00:00:02.553509: step: 984/526, loss: 0.3070027232170105
2023-01-23 00:00:03.686909: step: 988/526, loss: 1.7618612051010132
2023-01-23 00:00:04.820428: step: 992/526, loss: 0.8996191024780273
2023-01-23 00:00:05.929711: step: 996/526, loss: 0.5811383128166199
2023-01-23 00:00:07.072682: step: 1000/526, loss: 0.664803147315979
2023-01-23 00:00:08.222439: step: 1004/526, loss: 0.3209201991558075
2023-01-23 00:00:09.360496: step: 1008/526, loss: 0.4834885597229004
2023-01-23 00:00:10.491748: step: 1012/526, loss: 0.2890813946723938
2023-01-23 00:00:11.603883: step: 1016/526, loss: 0.6176754236221313
2023-01-23 00:00:12.757976: step: 1020/526, loss: 0.08344468474388123
2023-01-23 00:00:13.872031: step: 1024/526, loss: 0.7532416582107544
2023-01-23 00:00:15.003850: step: 1028/526, loss: 0.4188307821750641
2023-01-23 00:00:16.136287: step: 1032/526, loss: 0.7252113223075867
2023-01-23 00:00:17.253573: step: 1036/526, loss: 0.17177867889404297
2023-01-23 00:00:18.370651: step: 1040/526, loss: 0.06400027126073837
2023-01-23 00:00:19.493880: step: 1044/526, loss: 0.10868249088525772
2023-01-23 00:00:20.678208: step: 1048/526, loss: 0.11496695876121521
2023-01-23 00:00:21.780023: step: 1052/526, loss: 0.1320648193359375
2023-01-23 00:00:22.903067: step: 1056/526, loss: 0.019594576209783554
2023-01-23 00:00:24.047808: step: 1060/526, loss: 0.04037170484662056
2023-01-23 00:00:25.196111: step: 1064/526, loss: 0.06519465148448944
2023-01-23 00:00:26.317607: step: 1068/526, loss: 0.19335699081420898
2023-01-23 00:00:27.439799: step: 1072/526, loss: 0.22089740633964539
2023-01-23 00:00:28.590081: step: 1076/526, loss: 0.02359180524945259
2023-01-23 00:00:29.720999: step: 1080/526, loss: 0.07745294272899628
2023-01-23 00:00:30.839472: step: 1084/526, loss: 0.10699639469385147
2023-01-23 00:00:31.976960: step: 1088/526, loss: 0.11986284703016281
2023-01-23 00:00:33.208483: step: 1092/526, loss: 0.09723816066980362
2023-01-23 00:00:34.345498: step: 1096/526, loss: 0.15060502290725708
2023-01-23 00:00:35.490739: step: 1100/526, loss: 0.25521835684776306
2023-01-23 00:00:36.619122: step: 1104/526, loss: 0.064361572265625
2023-01-23 00:00:37.742952: step: 1108/526, loss: 0.060060977935791016
2023-01-23 00:00:38.848209: step: 1112/526, loss: 0.04093647003173828
2023-01-23 00:00:39.962997: step: 1116/526, loss: 0.8150016069412231
2023-01-23 00:00:41.096284: step: 1120/526, loss: 1.2796907424926758
2023-01-23 00:00:42.229373: step: 1124/526, loss: 0.8485506772994995
2023-01-23 00:00:43.357095: step: 1128/526, loss: 0.745945155620575
2023-01-23 00:00:44.455773: step: 1132/526, loss: 0.30736014246940613
2023-01-23 00:00:45.590560: step: 1136/526, loss: 0.14030304551124573
2023-01-23 00:00:46.730819: step: 1140/526, loss: 0.06971073150634766
2023-01-23 00:00:47.870296: step: 1144/526, loss: 0.12525349855422974
2023-01-23 00:00:48.990209: step: 1148/526, loss: 6.075376033782959
2023-01-23 00:00:50.098613: step: 1152/526, loss: 0.09767132252454758
2023-01-23 00:00:51.232805: step: 1156/526, loss: 0.16151876747608185
2023-01-23 00:00:52.365218: step: 1160/526, loss: 0.03954639285802841
2023-01-23 00:00:53.476615: step: 1164/526, loss: 0.0148452278226614
2023-01-23 00:00:54.599530: step: 1168/526, loss: 0.46187302470207214
2023-01-23 00:00:55.735521: step: 1172/526, loss: 0.24328966438770294
2023-01-23 00:00:56.846045: step: 1176/526, loss: 0.05940687656402588
2023-01-23 00:00:58.021324: step: 1180/526, loss: 0.42158180475234985
2023-01-23 00:00:59.138889: step: 1184/526, loss: 0.29104599356651306
2023-01-23 00:01:00.250094: step: 1188/526, loss: 0.5036236047744751
2023-01-23 00:01:01.365526: step: 1192/526, loss: 0.04713907465338707
2023-01-23 00:01:02.522668: step: 1196/526, loss: 0.5283783078193665
2023-01-23 00:01:03.648124: step: 1200/526, loss: 0.10162925720214844
2023-01-23 00:01:04.791704: step: 1204/526, loss: 0.224803164601326
2023-01-23 00:01:05.909514: step: 1208/526, loss: 0.7440999150276184
2023-01-23 00:01:07.040189: step: 1212/526, loss: 0.08854293823242188
2023-01-23 00:01:08.166130: step: 1216/526, loss: 0.07764258235692978
2023-01-23 00:01:09.301463: step: 1220/526, loss: 1.003868579864502
2023-01-23 00:01:10.431211: step: 1224/526, loss: 0.14478349685668945
2023-01-23 00:01:11.555108: step: 1228/526, loss: 0.7403308153152466
2023-01-23 00:01:12.699152: step: 1232/526, loss: 0.08355551213026047
2023-01-23 00:01:13.864179: step: 1236/526, loss: 0.6245163083076477
2023-01-23 00:01:14.983505: step: 1240/526, loss: 0.580281138420105
2023-01-23 00:01:16.113793: step: 1244/526, loss: 0.7963274717330933
2023-01-23 00:01:17.237196: step: 1248/526, loss: 0.37675970792770386
2023-01-23 00:01:18.378621: step: 1252/526, loss: 0.8511053323745728
2023-01-23 00:01:19.517119: step: 1256/526, loss: 0.028861189261078835
2023-01-23 00:01:20.666376: step: 1260/526, loss: 0.05666828155517578
2023-01-23 00:01:21.795946: step: 1264/526, loss: 0.0780644416809082
2023-01-23 00:01:22.935471: step: 1268/526, loss: 1.047023057937622
2023-01-23 00:01:24.065405: step: 1272/526, loss: 0.09973640739917755
2023-01-23 00:01:25.202144: step: 1276/526, loss: 1.1144388914108276
2023-01-23 00:01:26.330562: step: 1280/526, loss: 0.9942584037780762
2023-01-23 00:01:27.451004: step: 1284/526, loss: 0.11726050823926926
2023-01-23 00:01:28.575916: step: 1288/526, loss: 0.24627934396266937
2023-01-23 00:01:29.709827: step: 1292/526, loss: 0.10007962584495544
2023-01-23 00:01:30.828811: step: 1296/526, loss: 0.04827446863055229
2023-01-23 00:01:31.943492: step: 1300/526, loss: 0.19467994570732117
2023-01-23 00:01:33.116136: step: 1304/526, loss: 0.25225162506103516
2023-01-23 00:01:34.268858: step: 1308/526, loss: 0.11150360107421875
2023-01-23 00:01:35.407352: step: 1312/526, loss: 1.4192262887954712
2023-01-23 00:01:36.541480: step: 1316/526, loss: 0.40786734223365784
2023-01-23 00:01:37.668573: step: 1320/526, loss: 0.06680698692798615
2023-01-23 00:01:38.801863: step: 1324/526, loss: 0.06681499630212784
2023-01-23 00:01:39.966940: step: 1328/526, loss: 0.22055187821388245
2023-01-23 00:01:41.080888: step: 1332/526, loss: 0.2694765031337738
2023-01-23 00:01:42.247777: step: 1336/526, loss: 0.9559891223907471
2023-01-23 00:01:43.450147: step: 1340/526, loss: 0.8912206292152405
2023-01-23 00:01:44.591463: step: 1344/526, loss: 0.7527163624763489
2023-01-23 00:01:45.739378: step: 1348/526, loss: 0.18553757667541504
2023-01-23 00:01:46.856788: step: 1352/526, loss: 0.23619085550308228
2023-01-23 00:01:48.004863: step: 1356/526, loss: 0.13935032486915588
2023-01-23 00:01:49.154399: step: 1360/526, loss: 0.06779885292053223
2023-01-23 00:01:50.282324: step: 1364/526, loss: 0.09334440529346466
2023-01-23 00:01:51.437259: step: 1368/526, loss: 0.20999857783317566
2023-01-23 00:01:52.567463: step: 1372/526, loss: 0.11324353516101837
2023-01-23 00:01:53.731498: step: 1376/526, loss: 0.13618770241737366
2023-01-23 00:01:54.855652: step: 1380/526, loss: 0.16702528297901154
2023-01-23 00:01:55.993335: step: 1384/526, loss: 0.5035191178321838
2023-01-23 00:01:57.118683: step: 1388/526, loss: 1.3180017471313477
2023-01-23 00:01:58.212696: step: 1392/526, loss: 0.2432619035243988
2023-01-23 00:01:59.308983: step: 1396/526, loss: 0.1816757172346115
2023-01-23 00:02:00.437877: step: 1400/526, loss: 0.2634263038635254
2023-01-23 00:02:01.535063: step: 1404/526, loss: 0.0674934983253479
2023-01-23 00:02:02.647432: step: 1408/526, loss: 0.25318947434425354
2023-01-23 00:02:03.783500: step: 1412/526, loss: 0.2854065001010895
2023-01-23 00:02:04.864357: step: 1416/526, loss: 0.3882119059562683
2023-01-23 00:02:05.987441: step: 1420/526, loss: 0.05792813375592232
2023-01-23 00:02:07.109270: step: 1424/526, loss: 0.38272157311439514
2023-01-23 00:02:08.218465: step: 1428/526, loss: 0.5331307649612427
2023-01-23 00:02:09.357352: step: 1432/526, loss: 0.13443392515182495
2023-01-23 00:02:10.488645: step: 1436/526, loss: 0.09153075516223907
2023-01-23 00:02:11.601841: step: 1440/526, loss: 0.07008647918701172
2023-01-23 00:02:12.767119: step: 1444/526, loss: 0.6439488530158997
2023-01-23 00:02:13.887962: step: 1448/526, loss: 1.077980875968933
2023-01-23 00:02:15.048775: step: 1452/526, loss: 0.44732579588890076
2023-01-23 00:02:16.195390: step: 1456/526, loss: 0.2313501387834549
2023-01-23 00:02:17.339942: step: 1460/526, loss: 0.11343111842870712
2023-01-23 00:02:18.483406: step: 1464/526, loss: 0.04825792461633682
2023-01-23 00:02:19.617409: step: 1468/526, loss: 0.3280300199985504
2023-01-23 00:02:20.755120: step: 1472/526, loss: 6.1980414390563965
2023-01-23 00:02:21.905383: step: 1476/526, loss: 0.7206302881240845
2023-01-23 00:02:23.038074: step: 1480/526, loss: 0.09934735298156738
2023-01-23 00:02:24.180939: step: 1484/526, loss: 0.3719167709350586
2023-01-23 00:02:25.319802: step: 1488/526, loss: 0.09125781804323196
2023-01-23 00:02:26.437586: step: 1492/526, loss: 0.10218754410743713
2023-01-23 00:02:27.576288: step: 1496/526, loss: 0.5845492482185364
2023-01-23 00:02:28.708508: step: 1500/526, loss: 0.7742104530334473
2023-01-23 00:02:29.866542: step: 1504/526, loss: 0.15945816040039062
2023-01-23 00:02:30.973624: step: 1508/526, loss: 0.11177407205104828
2023-01-23 00:02:32.092013: step: 1512/526, loss: 0.08908472210168839
2023-01-23 00:02:33.239906: step: 1516/526, loss: 0.20404338836669922
2023-01-23 00:02:34.396289: step: 1520/526, loss: 0.75209641456604
2023-01-23 00:02:35.531884: step: 1524/526, loss: 0.16547413170337677
2023-01-23 00:02:36.652516: step: 1528/526, loss: 0.10301017761230469
2023-01-23 00:02:37.764674: step: 1532/526, loss: 0.5217010378837585
2023-01-23 00:02:38.915345: step: 1536/526, loss: 0.12957553565502167
2023-01-23 00:02:40.027767: step: 1540/526, loss: 0.10902738571166992
2023-01-23 00:02:41.139956: step: 1544/526, loss: 0.05682273209095001
2023-01-23 00:02:42.274622: step: 1548/526, loss: 0.8489383459091187
2023-01-23 00:02:43.400184: step: 1552/526, loss: 0.8127043843269348
2023-01-23 00:02:44.520004: step: 1556/526, loss: 0.34159165620803833
2023-01-23 00:02:45.665754: step: 1560/526, loss: 0.1747705042362213
2023-01-23 00:02:46.808311: step: 1564/526, loss: 0.4296688139438629
2023-01-23 00:02:47.903457: step: 1568/526, loss: 0.1284904032945633
2023-01-23 00:02:49.060108: step: 1572/526, loss: 0.2206592559814453
2023-01-23 00:02:50.207458: step: 1576/526, loss: 0.12147083133459091
2023-01-23 00:02:51.328823: step: 1580/526, loss: 0.2198609858751297
2023-01-23 00:02:52.455110: step: 1584/526, loss: 0.2692309617996216
2023-01-23 00:02:53.632425: step: 1588/526, loss: 0.21258258819580078
2023-01-23 00:02:54.759496: step: 1592/526, loss: 0.07004199177026749
2023-01-23 00:02:55.920093: step: 1596/526, loss: 0.10684271156787872
2023-01-23 00:02:57.069112: step: 1600/526, loss: 0.08016996085643768
2023-01-23 00:02:58.210929: step: 1604/526, loss: 0.08632688969373703
2023-01-23 00:02:59.356719: step: 1608/526, loss: 0.28077125549316406
2023-01-23 00:03:00.523210: step: 1612/526, loss: 0.1809266209602356
2023-01-23 00:03:01.655869: step: 1616/526, loss: 0.1500811129808426
2023-01-23 00:03:02.807168: step: 1620/526, loss: 0.5783336758613586
2023-01-23 00:03:03.937012: step: 1624/526, loss: 0.46894150972366333
2023-01-23 00:03:05.068224: step: 1628/526, loss: 0.6204140186309814
2023-01-23 00:03:06.197577: step: 1632/526, loss: 0.17772865295410156
2023-01-23 00:03:07.317283: step: 1636/526, loss: 0.1586422324180603
2023-01-23 00:03:08.440866: step: 1640/526, loss: 0.048552703112363815
2023-01-23 00:03:09.583912: step: 1644/526, loss: 0.05477786436676979
2023-01-23 00:03:10.706542: step: 1648/526, loss: 0.15095233917236328
2023-01-23 00:03:11.832881: step: 1652/526, loss: 0.5051612854003906
2023-01-23 00:03:12.991511: step: 1656/526, loss: 0.1724916398525238
2023-01-23 00:03:14.134180: step: 1660/526, loss: 0.158155158162117
2023-01-23 00:03:15.290933: step: 1664/526, loss: 0.2265586405992508
2023-01-23 00:03:16.436252: step: 1668/526, loss: 0.4416227340698242
2023-01-23 00:03:17.557906: step: 1672/526, loss: 0.048676300793886185
2023-01-23 00:03:18.690353: step: 1676/526, loss: 0.18028397858142853
2023-01-23 00:03:19.840879: step: 1680/526, loss: 0.7623763680458069
2023-01-23 00:03:20.998674: step: 1684/526, loss: 0.3002418577671051
2023-01-23 00:03:22.146720: step: 1688/526, loss: 0.07221928238868713
2023-01-23 00:03:23.246701: step: 1692/526, loss: 0.1144382506608963
2023-01-23 00:03:24.373810: step: 1696/526, loss: 0.9417555928230286
2023-01-23 00:03:25.487323: step: 1700/526, loss: 0.7007885575294495
2023-01-23 00:03:26.632507: step: 1704/526, loss: 0.4379734694957733
2023-01-23 00:03:27.767067: step: 1708/526, loss: 0.27464112639427185
2023-01-23 00:03:28.902342: step: 1712/526, loss: 0.1818973571062088
2023-01-23 00:03:30.047472: step: 1716/526, loss: 0.15587759017944336
2023-01-23 00:03:31.179868: step: 1720/526, loss: 0.5782361030578613
2023-01-23 00:03:32.317978: step: 1724/526, loss: 0.3107401132583618
2023-01-23 00:03:33.431552: step: 1728/526, loss: 0.10782603919506073
2023-01-23 00:03:34.595514: step: 1732/526, loss: 0.18604522943496704
2023-01-23 00:03:35.722287: step: 1736/526, loss: 0.06759343296289444
2023-01-23 00:03:36.879004: step: 1740/526, loss: 0.13604554533958435
2023-01-23 00:03:37.997999: step: 1744/526, loss: 0.306617796421051
2023-01-23 00:03:39.133139: step: 1748/526, loss: 0.3607856035232544
2023-01-23 00:03:40.274417: step: 1752/526, loss: 0.1634874939918518
2023-01-23 00:03:41.420065: step: 1756/526, loss: 0.8868076801300049
2023-01-23 00:03:42.564873: step: 1760/526, loss: 0.3137521743774414
2023-01-23 00:03:43.740772: step: 1764/526, loss: 0.22938479483127594
2023-01-23 00:03:44.892571: step: 1768/526, loss: 0.6368406414985657
2023-01-23 00:03:46.022596: step: 1772/526, loss: 0.4434700012207031
2023-01-23 00:03:47.146006: step: 1776/526, loss: 0.20543384552001953
2023-01-23 00:03:48.263236: step: 1780/526, loss: 0.7326292991638184
2023-01-23 00:03:49.384477: step: 1784/526, loss: 0.13726906478405
2023-01-23 00:03:50.510273: step: 1788/526, loss: 0.14172545075416565
2023-01-23 00:03:51.647771: step: 1792/526, loss: 0.101201631128788
2023-01-23 00:03:52.768886: step: 1796/526, loss: 0.7137531042098999
2023-01-23 00:03:53.921630: step: 1800/526, loss: 0.5728021264076233
2023-01-23 00:03:55.049923: step: 1804/526, loss: 0.1522558331489563
2023-01-23 00:03:56.184893: step: 1808/526, loss: 0.3777618706226349
2023-01-23 00:03:57.323650: step: 1812/526, loss: 0.46837204694747925
2023-01-23 00:03:58.464010: step: 1816/526, loss: 0.40504521131515503
2023-01-23 00:03:59.579102: step: 1820/526, loss: 0.11311206221580505
2023-01-23 00:04:00.723585: step: 1824/526, loss: 0.8778169751167297
2023-01-23 00:04:01.854540: step: 1828/526, loss: 0.25798356533050537
2023-01-23 00:04:02.969262: step: 1832/526, loss: 0.20984306931495667
2023-01-23 00:04:04.109283: step: 1836/526, loss: 0.674612820148468
2023-01-23 00:04:05.206777: step: 1840/526, loss: 0.35536304116249084
2023-01-23 00:04:06.354938: step: 1844/526, loss: 0.6872149705886841
2023-01-23 00:04:07.509161: step: 1848/526, loss: 0.2538905143737793
2023-01-23 00:04:08.642465: step: 1852/526, loss: 0.7141143083572388
2023-01-23 00:04:09.773295: step: 1856/526, loss: 0.04651389271020889
2023-01-23 00:04:10.896604: step: 1860/526, loss: 0.13599276542663574
2023-01-23 00:04:12.003039: step: 1864/526, loss: 0.1452498883008957
2023-01-23 00:04:13.169584: step: 1868/526, loss: 0.17661356925964355
2023-01-23 00:04:14.293296: step: 1872/526, loss: 0.1657661348581314
2023-01-23 00:04:15.439717: step: 1876/526, loss: 0.10716857761144638
2023-01-23 00:04:16.608380: step: 1880/526, loss: 0.20729699730873108
2023-01-23 00:04:17.775907: step: 1884/526, loss: 1.8192706108093262
2023-01-23 00:04:18.929366: step: 1888/526, loss: 0.13287487626075745
2023-01-23 00:04:20.089332: step: 1892/526, loss: 0.1459612399339676
2023-01-23 00:04:21.215399: step: 1896/526, loss: 0.19155669212341309
2023-01-23 00:04:22.341787: step: 1900/526, loss: 0.03620195388793945
2023-01-23 00:04:23.467755: step: 1904/526, loss: 0.10412587970495224
2023-01-23 00:04:24.588260: step: 1908/526, loss: 0.12637433409690857
2023-01-23 00:04:25.726588: step: 1912/526, loss: 0.3685949444770813
2023-01-23 00:04:26.882575: step: 1916/526, loss: 0.43134477734565735
2023-01-23 00:04:28.003473: step: 1920/526, loss: 0.022488880902528763
2023-01-23 00:04:29.138470: step: 1924/526, loss: 0.6904934048652649
2023-01-23 00:04:30.312245: step: 1928/526, loss: 1.1879143714904785
2023-01-23 00:04:31.428550: step: 1932/526, loss: 0.13188600540161133
2023-01-23 00:04:32.568165: step: 1936/526, loss: 1.479654312133789
2023-01-23 00:04:33.689673: step: 1940/526, loss: 0.07299375534057617
2023-01-23 00:04:34.816235: step: 1944/526, loss: 0.23859329521656036
2023-01-23 00:04:35.941795: step: 1948/526, loss: 0.289031982421875
2023-01-23 00:04:37.102511: step: 1952/526, loss: 0.35942333936691284
2023-01-23 00:04:38.236145: step: 1956/526, loss: 0.5721483826637268
2023-01-23 00:04:39.349723: step: 1960/526, loss: 0.09510289132595062
2023-01-23 00:04:40.498819: step: 1964/526, loss: 0.19095487892627716
2023-01-23 00:04:41.634801: step: 1968/526, loss: 0.24901218712329865
2023-01-23 00:04:42.771518: step: 1972/526, loss: 0.6099697351455688
2023-01-23 00:04:43.911506: step: 1976/526, loss: 0.1544574797153473
2023-01-23 00:04:45.028062: step: 1980/526, loss: 0.25021684169769287
2023-01-23 00:04:46.174267: step: 1984/526, loss: 0.09940137714147568
2023-01-23 00:04:47.337544: step: 1988/526, loss: 0.11141081154346466
2023-01-23 00:04:48.472412: step: 1992/526, loss: 0.12098207324743271
2023-01-23 00:04:49.615388: step: 1996/526, loss: 0.037741970270872116
2023-01-23 00:04:50.774440: step: 2000/526, loss: 0.12642598152160645
2023-01-23 00:04:51.918584: step: 2004/526, loss: 0.14484553039073944
2023-01-23 00:04:53.037509: step: 2008/526, loss: 0.54514479637146
2023-01-23 00:04:54.140673: step: 2012/526, loss: 0.4738819897174835
2023-01-23 00:04:55.290870: step: 2016/526, loss: 0.10210972279310226
2023-01-23 00:04:56.431262: step: 2020/526, loss: 0.22374558448791504
2023-01-23 00:04:57.529494: step: 2024/526, loss: 0.13703079521656036
2023-01-23 00:04:58.676238: step: 2028/526, loss: 1.143784523010254
2023-01-23 00:04:59.790355: step: 2032/526, loss: 0.22043628990650177
2023-01-23 00:05:00.907326: step: 2036/526, loss: 0.7103164792060852
2023-01-23 00:05:02.074798: step: 2040/526, loss: 0.32267388701438904
2023-01-23 00:05:03.218447: step: 2044/526, loss: 2.1595511436462402
2023-01-23 00:05:04.343110: step: 2048/526, loss: 0.07906289398670197
2023-01-23 00:05:05.487096: step: 2052/526, loss: 0.4950440526008606
2023-01-23 00:05:06.604113: step: 2056/526, loss: 0.27676939964294434
2023-01-23 00:05:07.727708: step: 2060/526, loss: 0.8087915778160095
2023-01-23 00:05:08.858203: step: 2064/526, loss: 0.09626217186450958
2023-01-23 00:05:10.015646: step: 2068/526, loss: 0.15070191025733948
2023-01-23 00:05:11.170700: step: 2072/526, loss: 0.143851175904274
2023-01-23 00:05:12.292714: step: 2076/526, loss: 0.10410786420106888
2023-01-23 00:05:13.451974: step: 2080/526, loss: 0.02433171309530735
2023-01-23 00:05:14.623974: step: 2084/526, loss: 0.23612503707408905
2023-01-23 00:05:15.776934: step: 2088/526, loss: 0.188856840133667
2023-01-23 00:05:16.920193: step: 2092/526, loss: 0.18363535404205322
2023-01-23 00:05:18.058039: step: 2096/526, loss: 0.712185800075531
2023-01-23 00:05:19.192308: step: 2100/526, loss: 0.1364772915840149
2023-01-23 00:05:20.322708: step: 2104/526, loss: 0.19660745561122894
==================================================
Loss: 0.456
--------------------
Dev: {'event': {'p': 0.587251828631139, 'r': 0.748335552596538, 'f1': 0.6580796252927401}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Test: {'event': {'p': 0.5717155484130173, 'r': 0.7426931106471816, 'f1': 0.6460839954597049}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Chinese: {'event': {'p': 0.5529411764705883, 'r': 0.8703703703703703, 'f1': 0.6762589928057553}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Korean: {'event': {'p': 0.6590909090909091, 'r': 0.4603174603174603, 'f1': 0.5420560747663551}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Russian: {'event': {'p': 0.47368421052631576, 'r': 0.5, 'f1': 0.4864864864864865}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
New best russian model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6604010025062657, 'r': 0.7017310252996005, 'f1': 0.6804389928986443}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Eng Test for Chinese: {'event': {'p': 0.6480836236933798, 'r': 0.6795407098121086, 'f1': 0.6634394904458599}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Sample Chinese: {'event': {'p': 0.6323529411764706, 'r': 0.7962962962962963, 'f1': 0.7049180327868853}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6604010025062657, 'r': 0.7017310252996005, 'f1': 0.6804389928986443}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Eng Test for Korean: {'event': {'p': 0.6480836236933798, 'r': 0.6795407098121086, 'f1': 0.6634394904458599}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Sample Korean: {'event': {'p': 0.7575757575757576, 'r': 0.3968253968253968, 'f1': 0.5208333333333334}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
--------------------
Eng Dev for Russian: {'event': {'p': 0.587251828631139, 'r': 0.748335552596538, 'f1': 0.6580796252927401}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Russian: {'event': {'p': 0.5717155484130173, 'r': 0.7426931106471816, 'f1': 0.6460839954597049}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Russian: {'event': {'p': 0.47368421052631576, 'r': 0.5, 'f1': 0.4864864864864865}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
******************************
Epoch: 4
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 00:06:11.295741: step: 4/526, loss: 0.4162517488002777
2023-01-23 00:06:12.463200: step: 8/526, loss: 0.16281470656394958
2023-01-23 00:06:13.611449: step: 12/526, loss: 0.09604306519031525
2023-01-23 00:06:14.752720: step: 16/526, loss: 0.12089300155639648
2023-01-23 00:06:15.896593: step: 20/526, loss: 0.7449560165405273
2023-01-23 00:06:17.014660: step: 24/526, loss: 0.07508730888366699
2023-01-23 00:06:18.154956: step: 28/526, loss: 0.38911762833595276
2023-01-23 00:06:19.289146: step: 32/526, loss: 0.12695255875587463
2023-01-23 00:06:20.425196: step: 36/526, loss: 0.27916955947875977
2023-01-23 00:06:21.569423: step: 40/526, loss: 0.07797583937644958
2023-01-23 00:06:22.690329: step: 44/526, loss: 0.1345663070678711
2023-01-23 00:06:23.824189: step: 48/526, loss: 0.8785447478294373
2023-01-23 00:06:24.954809: step: 52/526, loss: 0.023710155859589577
2023-01-23 00:06:26.104747: step: 56/526, loss: 0.18689842522144318
2023-01-23 00:06:27.225256: step: 60/526, loss: 0.19478636980056763
2023-01-23 00:06:28.359763: step: 64/526, loss: 0.06995487213134766
2023-01-23 00:06:29.474783: step: 68/526, loss: 0.9890401363372803
2023-01-23 00:06:30.621753: step: 72/526, loss: 0.09284988045692444
2023-01-23 00:06:31.741005: step: 76/526, loss: 0.2822338938713074
2023-01-23 00:06:32.848458: step: 80/526, loss: 0.01050415076315403
2023-01-23 00:06:33.963776: step: 84/526, loss: 0.18396396934986115
2023-01-23 00:06:35.094362: step: 88/526, loss: 0.8235489130020142
2023-01-23 00:06:36.259222: step: 92/526, loss: 0.0786537230014801
2023-01-23 00:06:37.423170: step: 96/526, loss: 0.12528057396411896
2023-01-23 00:06:38.542084: step: 100/526, loss: 0.22777271270751953
2023-01-23 00:06:39.712190: step: 104/526, loss: 0.3339591920375824
2023-01-23 00:06:40.863178: step: 108/526, loss: 0.13051939010620117
2023-01-23 00:06:41.998640: step: 112/526, loss: 0.13963966071605682
2023-01-23 00:06:43.127277: step: 116/526, loss: 0.13987894356250763
2023-01-23 00:06:44.259659: step: 120/526, loss: 0.25016745924949646
2023-01-23 00:06:45.411277: step: 124/526, loss: 0.7342115640640259
2023-01-23 00:06:46.522080: step: 128/526, loss: 0.020869970321655273
2023-01-23 00:06:47.645485: step: 132/526, loss: 0.1124420166015625
2023-01-23 00:06:48.785901: step: 136/526, loss: 0.3675425350666046
2023-01-23 00:06:49.923834: step: 140/526, loss: 0.8147329092025757
2023-01-23 00:06:51.040560: step: 144/526, loss: 0.1429820954799652
2023-01-23 00:06:52.187162: step: 148/526, loss: 0.09115403145551682
2023-01-23 00:06:53.304068: step: 152/526, loss: 0.708909809589386
2023-01-23 00:06:54.451150: step: 156/526, loss: 0.05897693708539009
2023-01-23 00:06:55.589949: step: 160/526, loss: 0.2730226516723633
2023-01-23 00:06:56.693960: step: 164/526, loss: 0.12081471085548401
2023-01-23 00:06:57.850193: step: 168/526, loss: 0.04553051292896271
2023-01-23 00:06:59.008503: step: 172/526, loss: 0.5359403491020203
2023-01-23 00:07:00.125603: step: 176/526, loss: 0.5294515490531921
2023-01-23 00:07:01.286083: step: 180/526, loss: 0.28645047545433044
2023-01-23 00:07:02.426968: step: 184/526, loss: 0.4109261631965637
2023-01-23 00:07:03.579281: step: 188/526, loss: 0.08603839576244354
2023-01-23 00:07:04.727441: step: 192/526, loss: 0.1760941594839096
2023-01-23 00:07:05.889821: step: 196/526, loss: 0.29432833194732666
2023-01-23 00:07:07.022745: step: 200/526, loss: 0.14655523002147675
2023-01-23 00:07:08.178162: step: 204/526, loss: 0.048816584050655365
2023-01-23 00:07:09.319612: step: 208/526, loss: 0.1075296401977539
2023-01-23 00:07:10.469861: step: 212/526, loss: 0.6211971640586853
2023-01-23 00:07:11.611339: step: 216/526, loss: 0.430537611246109
2023-01-23 00:07:12.752426: step: 220/526, loss: 0.16335105895996094
2023-01-23 00:07:13.907753: step: 224/526, loss: 0.13757658004760742
2023-01-23 00:07:15.072196: step: 228/526, loss: 0.10219473391771317
2023-01-23 00:07:16.229186: step: 232/526, loss: 0.47321754693984985
2023-01-23 00:07:17.385873: step: 236/526, loss: 0.09550885856151581
2023-01-23 00:07:18.567751: step: 240/526, loss: 0.1250135451555252
2023-01-23 00:07:19.671790: step: 244/526, loss: 0.14286527037620544
2023-01-23 00:07:20.825993: step: 248/526, loss: 0.0886419266462326
2023-01-23 00:07:21.960644: step: 252/526, loss: 0.4233490228652954
2023-01-23 00:07:23.085942: step: 256/526, loss: 0.08562731742858887
2023-01-23 00:07:24.192666: step: 260/526, loss: 0.032315947115421295
2023-01-23 00:07:25.289436: step: 264/526, loss: 0.7196832299232483
2023-01-23 00:07:26.406133: step: 268/526, loss: 0.3318479359149933
2023-01-23 00:07:27.530663: step: 272/526, loss: 0.016775943338871002
2023-01-23 00:07:28.681955: step: 276/526, loss: 0.43076688051223755
2023-01-23 00:07:29.850192: step: 280/526, loss: 0.15205231308937073
2023-01-23 00:07:30.964897: step: 284/526, loss: 0.2976920008659363
2023-01-23 00:07:32.112837: step: 288/526, loss: 0.12062001973390579
2023-01-23 00:07:33.246844: step: 292/526, loss: 0.6778050065040588
2023-01-23 00:07:34.405378: step: 296/526, loss: 0.24091148376464844
2023-01-23 00:07:35.546069: step: 300/526, loss: 0.8197460174560547
2023-01-23 00:07:36.678684: step: 304/526, loss: 0.14999523758888245
2023-01-23 00:07:37.855717: step: 308/526, loss: 0.1704537719488144
2023-01-23 00:07:39.010777: step: 312/526, loss: 1.2849609851837158
2023-01-23 00:07:40.188012: step: 316/526, loss: 0.09026508033275604
2023-01-23 00:07:41.320193: step: 320/526, loss: 0.05670461431145668
2023-01-23 00:07:42.468950: step: 324/526, loss: 0.01755533181130886
2023-01-23 00:07:43.641339: step: 328/526, loss: 0.44096651673316956
2023-01-23 00:07:44.767403: step: 332/526, loss: 0.24535000324249268
2023-01-23 00:07:45.919434: step: 336/526, loss: 0.10419130325317383
2023-01-23 00:07:47.082977: step: 340/526, loss: 0.3023788630962372
2023-01-23 00:07:48.237778: step: 344/526, loss: 0.18359366059303284
2023-01-23 00:07:49.392519: step: 348/526, loss: 0.09482508152723312
2023-01-23 00:07:50.520987: step: 352/526, loss: 0.4031192660331726
2023-01-23 00:07:51.667629: step: 356/526, loss: 0.19881489872932434
2023-01-23 00:07:52.829490: step: 360/526, loss: 0.6746804714202881
2023-01-23 00:07:53.960965: step: 364/526, loss: 0.43863701820373535
2023-01-23 00:07:55.125917: step: 368/526, loss: 0.11959227919578552
2023-01-23 00:07:56.262649: step: 372/526, loss: 0.10329818725585938
2023-01-23 00:07:57.387068: step: 376/526, loss: 0.08187904208898544
2023-01-23 00:07:58.546778: step: 380/526, loss: 0.2239125370979309
2023-01-23 00:07:59.662375: step: 384/526, loss: 0.41037869453430176
2023-01-23 00:08:00.804307: step: 388/526, loss: 0.11743126064538956
2023-01-23 00:08:01.979009: step: 392/526, loss: 0.24530839920043945
2023-01-23 00:08:03.114295: step: 396/526, loss: 0.5493795275688171
2023-01-23 00:08:04.248447: step: 400/526, loss: 0.07184629142284393
2023-01-23 00:08:05.369908: step: 404/526, loss: 0.3614213466644287
2023-01-23 00:08:06.530787: step: 408/526, loss: 0.23081770539283752
2023-01-23 00:08:07.673938: step: 412/526, loss: 0.02835226058959961
2023-01-23 00:08:08.816994: step: 416/526, loss: 0.37867841124534607
2023-01-23 00:08:09.969677: step: 420/526, loss: 0.2118498831987381
2023-01-23 00:08:11.131577: step: 424/526, loss: 0.5382680892944336
2023-01-23 00:08:12.267081: step: 428/526, loss: 0.8340715169906616
2023-01-23 00:08:13.427655: step: 432/526, loss: 0.1693919599056244
2023-01-23 00:08:14.586049: step: 436/526, loss: 0.22669143974781036
2023-01-23 00:08:15.724926: step: 440/526, loss: 0.17380136251449585
2023-01-23 00:08:16.891301: step: 444/526, loss: 0.09809380024671555
2023-01-23 00:08:18.036027: step: 448/526, loss: 0.5440462231636047
2023-01-23 00:08:19.151760: step: 452/526, loss: 0.06541042029857635
2023-01-23 00:08:20.301047: step: 456/526, loss: 0.2109546661376953
2023-01-23 00:08:21.410022: step: 460/526, loss: 0.09080924838781357
2023-01-23 00:08:22.542898: step: 464/526, loss: 0.07684745639562607
2023-01-23 00:08:23.678704: step: 468/526, loss: 0.042144108563661575
2023-01-23 00:08:24.796070: step: 472/526, loss: 0.11273002624511719
2023-01-23 00:08:25.970812: step: 476/526, loss: 0.7454760074615479
2023-01-23 00:08:27.100621: step: 480/526, loss: 0.08959593623876572
2023-01-23 00:08:28.240192: step: 484/526, loss: 0.14918716251850128
2023-01-23 00:08:29.447794: step: 488/526, loss: 0.3742007613182068
2023-01-23 00:08:30.567784: step: 492/526, loss: 0.037870120257139206
2023-01-23 00:08:31.715715: step: 496/526, loss: 0.08254127204418182
2023-01-23 00:08:32.840741: step: 500/526, loss: 0.1438557207584381
2023-01-23 00:08:34.001383: step: 504/526, loss: 0.1511041224002838
2023-01-23 00:08:35.168460: step: 508/526, loss: 0.06995344161987305
2023-01-23 00:08:36.275621: step: 512/526, loss: 0.06293439865112305
2023-01-23 00:08:37.435813: step: 516/526, loss: 0.1041233092546463
2023-01-23 00:08:38.603742: step: 520/526, loss: 0.3784911036491394
2023-01-23 00:08:39.746065: step: 524/526, loss: 0.03926382213830948
2023-01-23 00:08:40.869911: step: 528/526, loss: 0.019102763384580612
2023-01-23 00:08:42.008913: step: 532/526, loss: 0.09351787716150284
2023-01-23 00:08:43.162736: step: 536/526, loss: 0.5679179430007935
2023-01-23 00:08:44.277770: step: 540/526, loss: 0.14807163178920746
2023-01-23 00:08:45.402335: step: 544/526, loss: 0.24053727090358734
2023-01-23 00:08:46.499063: step: 548/526, loss: 0.05138111114501953
2023-01-23 00:08:47.620849: step: 552/526, loss: 0.23480865359306335
2023-01-23 00:08:48.766460: step: 556/526, loss: 0.12402839958667755
2023-01-23 00:08:49.900301: step: 560/526, loss: 0.07263145595788956
2023-01-23 00:08:51.040265: step: 564/526, loss: 0.13666324317455292
2023-01-23 00:08:52.167179: step: 568/526, loss: 0.2843009829521179
2023-01-23 00:08:53.327869: step: 572/526, loss: 0.18428076803684235
2023-01-23 00:08:54.456780: step: 576/526, loss: 0.09730225056409836
2023-01-23 00:08:55.620630: step: 580/526, loss: 0.04092860221862793
2023-01-23 00:08:56.765836: step: 584/526, loss: 0.11186066269874573
2023-01-23 00:08:57.938012: step: 588/526, loss: 0.9921743869781494
2023-01-23 00:08:59.101177: step: 592/526, loss: 0.056658077985048294
2023-01-23 00:09:00.235274: step: 596/526, loss: 0.17836570739746094
2023-01-23 00:09:01.371707: step: 600/526, loss: 0.033994387835264206
2023-01-23 00:09:02.489764: step: 604/526, loss: 1.318795084953308
2023-01-23 00:09:03.614602: step: 608/526, loss: 0.20577049255371094
2023-01-23 00:09:04.747842: step: 612/526, loss: 0.10561619699001312
2023-01-23 00:09:05.868797: step: 616/526, loss: 0.10459490120410919
2023-01-23 00:09:07.008909: step: 620/526, loss: 0.076439768075943
2023-01-23 00:09:08.166915: step: 624/526, loss: 0.10842490196228027
2023-01-23 00:09:09.302297: step: 628/526, loss: 0.10341091454029083
2023-01-23 00:09:10.436574: step: 632/526, loss: 0.1505311131477356
2023-01-23 00:09:11.578244: step: 636/526, loss: 0.08439254760742188
2023-01-23 00:09:12.720603: step: 640/526, loss: 0.1255919337272644
2023-01-23 00:09:13.876964: step: 644/526, loss: 0.4810018539428711
2023-01-23 00:09:15.001854: step: 648/526, loss: 0.09029150009155273
2023-01-23 00:09:16.127828: step: 652/526, loss: 1.07391357421875
2023-01-23 00:09:17.280321: step: 656/526, loss: 0.11303277313709259
2023-01-23 00:09:18.395590: step: 660/526, loss: 0.10102319717407227
2023-01-23 00:09:19.525861: step: 664/526, loss: 0.03169383853673935
2023-01-23 00:09:20.647408: step: 668/526, loss: 0.12495499104261398
2023-01-23 00:09:21.792425: step: 672/526, loss: 0.722877562046051
2023-01-23 00:09:22.916304: step: 676/526, loss: 0.057461075484752655
2023-01-23 00:09:24.059935: step: 680/526, loss: 0.6774193048477173
2023-01-23 00:09:25.216577: step: 684/526, loss: 0.130553737282753
2023-01-23 00:09:26.349924: step: 688/526, loss: 0.5497356057167053
2023-01-23 00:09:27.531145: step: 692/526, loss: 0.34561729431152344
2023-01-23 00:09:28.693033: step: 696/526, loss: 0.8197286128997803
2023-01-23 00:09:29.850162: step: 700/526, loss: 0.07111091911792755
2023-01-23 00:09:30.995037: step: 704/526, loss: 0.23404255509376526
2023-01-23 00:09:32.095888: step: 708/526, loss: 0.17759867012500763
2023-01-23 00:09:33.250206: step: 712/526, loss: 0.2189093679189682
2023-01-23 00:09:34.398829: step: 716/526, loss: 0.17411461472511292
2023-01-23 00:09:35.534038: step: 720/526, loss: 0.1080346405506134
2023-01-23 00:09:36.667723: step: 724/526, loss: 0.08979358524084091
2023-01-23 00:09:37.809720: step: 728/526, loss: 0.09780425578355789
2023-01-23 00:09:38.929378: step: 732/526, loss: 0.12218132615089417
2023-01-23 00:09:40.047926: step: 736/526, loss: 0.08891335129737854
2023-01-23 00:09:41.210450: step: 740/526, loss: 0.1156400665640831
2023-01-23 00:09:42.359391: step: 744/526, loss: 0.1883530616760254
2023-01-23 00:09:43.482941: step: 748/526, loss: 1.6280313730239868
2023-01-23 00:09:44.614321: step: 752/526, loss: 0.17897024750709534
2023-01-23 00:09:45.751601: step: 756/526, loss: 0.3709869384765625
2023-01-23 00:09:46.894425: step: 760/526, loss: 0.06960678100585938
2023-01-23 00:09:48.048516: step: 764/526, loss: 0.22618350386619568
2023-01-23 00:09:49.216328: step: 768/526, loss: 1.4186476469039917
2023-01-23 00:09:50.334253: step: 772/526, loss: 0.1943950653076172
2023-01-23 00:09:51.460903: step: 776/526, loss: 0.11608649045228958
2023-01-23 00:09:52.611626: step: 780/526, loss: 0.1909475326538086
2023-01-23 00:09:53.744557: step: 784/526, loss: 0.19988222420215607
2023-01-23 00:09:54.855384: step: 788/526, loss: 0.11071443557739258
2023-01-23 00:09:55.987606: step: 792/526, loss: 0.5383886694908142
2023-01-23 00:09:57.138511: step: 796/526, loss: 0.16698570549488068
2023-01-23 00:09:58.289213: step: 800/526, loss: 0.009955167770385742
2023-01-23 00:09:59.405022: step: 804/526, loss: 0.08415904641151428
2023-01-23 00:10:00.551878: step: 808/526, loss: 0.48933279514312744
2023-01-23 00:10:01.686260: step: 812/526, loss: 0.9976007342338562
2023-01-23 00:10:02.824592: step: 816/526, loss: 0.18563146889209747
2023-01-23 00:10:03.941278: step: 820/526, loss: 6.025500774383545
2023-01-23 00:10:05.097682: step: 824/526, loss: 0.28811654448509216
2023-01-23 00:10:06.231098: step: 828/526, loss: 0.11262817680835724
2023-01-23 00:10:07.353463: step: 832/526, loss: 0.08733835071325302
2023-01-23 00:10:08.477187: step: 836/526, loss: 0.500493586063385
2023-01-23 00:10:09.581717: step: 840/526, loss: 0.15617340803146362
2023-01-23 00:10:10.711459: step: 844/526, loss: 0.16936083137989044
2023-01-23 00:10:11.851322: step: 848/526, loss: 0.09375190734863281
2023-01-23 00:10:12.948288: step: 852/526, loss: 0.7823423743247986
2023-01-23 00:10:14.062140: step: 856/526, loss: 0.14134198427200317
2023-01-23 00:10:15.192742: step: 860/526, loss: 0.24290743470191956
2023-01-23 00:10:16.331288: step: 864/526, loss: 0.18269950151443481
2023-01-23 00:10:17.447342: step: 868/526, loss: 0.11488529294729233
2023-01-23 00:10:18.568021: step: 872/526, loss: 0.6648132801055908
2023-01-23 00:10:19.702546: step: 876/526, loss: 0.1677156388759613
2023-01-23 00:10:20.853815: step: 880/526, loss: 0.27670565247535706
2023-01-23 00:10:21.969304: step: 884/526, loss: 0.7141363620758057
2023-01-23 00:10:23.107910: step: 888/526, loss: 5.9438157081604
2023-01-23 00:10:24.246497: step: 892/526, loss: 0.2637576460838318
2023-01-23 00:10:25.399461: step: 896/526, loss: 0.15523844957351685
2023-01-23 00:10:26.555502: step: 900/526, loss: 0.6245636343955994
2023-01-23 00:10:27.673660: step: 904/526, loss: 0.12494106590747833
2023-01-23 00:10:28.808044: step: 908/526, loss: 0.21034583449363708
2023-01-23 00:10:29.963586: step: 912/526, loss: 0.9144895672798157
2023-01-23 00:10:31.115656: step: 916/526, loss: 0.6842329502105713
2023-01-23 00:10:32.233265: step: 920/526, loss: 0.18424977362155914
2023-01-23 00:10:33.385575: step: 924/526, loss: 2.065530300140381
2023-01-23 00:10:34.569258: step: 928/526, loss: 0.09701290726661682
2023-01-23 00:10:35.711860: step: 932/526, loss: 0.125346377491951
2023-01-23 00:10:36.815278: step: 936/526, loss: 0.11811709403991699
2023-01-23 00:10:37.943126: step: 940/526, loss: 0.26700520515441895
2023-01-23 00:10:39.066703: step: 944/526, loss: 0.14254026114940643
2023-01-23 00:10:40.198651: step: 948/526, loss: 0.06474772095680237
2023-01-23 00:10:41.335060: step: 952/526, loss: 0.18564969301223755
2023-01-23 00:10:42.441748: step: 956/526, loss: 0.15506859123706818
2023-01-23 00:10:43.610653: step: 960/526, loss: 0.22779254615306854
2023-01-23 00:10:44.745319: step: 964/526, loss: 0.26531124114990234
2023-01-23 00:10:45.856702: step: 968/526, loss: 0.22185811400413513
2023-01-23 00:10:46.999331: step: 972/526, loss: 0.05372581630945206
2023-01-23 00:10:48.101199: step: 976/526, loss: 0.22016258537769318
2023-01-23 00:10:49.228251: step: 980/526, loss: 0.7096502780914307
2023-01-23 00:10:50.377086: step: 984/526, loss: 0.9157988429069519
2023-01-23 00:10:51.554220: step: 988/526, loss: 0.27391892671585083
2023-01-23 00:10:52.679730: step: 992/526, loss: 0.6831054091453552
2023-01-23 00:10:53.806061: step: 996/526, loss: 0.22025933861732483
2023-01-23 00:10:54.957838: step: 1000/526, loss: 0.2376731038093567
2023-01-23 00:10:56.078826: step: 1004/526, loss: 0.21200771629810333
2023-01-23 00:10:57.196205: step: 1008/526, loss: 0.16856956481933594
2023-01-23 00:10:58.347209: step: 1012/526, loss: 0.15849237143993378
2023-01-23 00:10:59.494011: step: 1016/526, loss: 6.842772006988525
2023-01-23 00:11:00.616418: step: 1020/526, loss: 0.09412240982055664
2023-01-23 00:11:01.762925: step: 1024/526, loss: 0.20343151688575745
2023-01-23 00:11:02.920127: step: 1028/526, loss: 0.5002622604370117
2023-01-23 00:11:04.057804: step: 1032/526, loss: 0.18950414657592773
2023-01-23 00:11:05.189993: step: 1036/526, loss: 0.20053061842918396
2023-01-23 00:11:06.295872: step: 1040/526, loss: 0.13936929404735565
2023-01-23 00:11:07.434054: step: 1044/526, loss: 0.18831472098827362
2023-01-23 00:11:08.592959: step: 1048/526, loss: 0.19123177230358124
2023-01-23 00:11:09.703277: step: 1052/526, loss: 0.05880117416381836
2023-01-23 00:11:10.843735: step: 1056/526, loss: 0.6875283122062683
2023-01-23 00:11:11.976813: step: 1060/526, loss: 0.456093966960907
2023-01-23 00:11:13.102773: step: 1064/526, loss: 0.685244083404541
2023-01-23 00:11:14.244045: step: 1068/526, loss: 0.5029582381248474
2023-01-23 00:11:15.431320: step: 1072/526, loss: 0.0618559867143631
2023-01-23 00:11:16.574405: step: 1076/526, loss: 0.15304584801197052
2023-01-23 00:11:17.724011: step: 1080/526, loss: 0.0708322525024414
2023-01-23 00:11:18.872329: step: 1084/526, loss: 0.8185214996337891
2023-01-23 00:11:20.009526: step: 1088/526, loss: 0.0909125804901123
2023-01-23 00:11:21.151697: step: 1092/526, loss: 0.7081989645957947
2023-01-23 00:11:22.294888: step: 1096/526, loss: 0.32577913999557495
2023-01-23 00:11:23.394007: step: 1100/526, loss: 0.13986030220985413
2023-01-23 00:11:24.558671: step: 1104/526, loss: 0.39668768644332886
2023-01-23 00:11:25.687300: step: 1108/526, loss: 0.3519403338432312
2023-01-23 00:11:26.818764: step: 1112/526, loss: 0.5454993844032288
2023-01-23 00:11:27.948355: step: 1116/526, loss: 0.12598438560962677
2023-01-23 00:11:29.066017: step: 1120/526, loss: 0.08856096118688583
2023-01-23 00:11:30.195597: step: 1124/526, loss: 0.12020225822925568
2023-01-23 00:11:31.355300: step: 1128/526, loss: 0.13518276810646057
2023-01-23 00:11:32.476989: step: 1132/526, loss: 0.12709268927574158
2023-01-23 00:11:33.593161: step: 1136/526, loss: 0.02418675646185875
2023-01-23 00:11:34.714209: step: 1140/526, loss: 0.4214306175708771
2023-01-23 00:11:35.835570: step: 1144/526, loss: 0.3428903818130493
2023-01-23 00:11:36.995790: step: 1148/526, loss: 0.17736349999904633
2023-01-23 00:11:38.104370: step: 1152/526, loss: 0.32006072998046875
2023-01-23 00:11:39.240413: step: 1156/526, loss: 0.717534601688385
2023-01-23 00:11:40.384317: step: 1160/526, loss: 0.43570470809936523
2023-01-23 00:11:41.515576: step: 1164/526, loss: 1.1295288801193237
2023-01-23 00:11:42.639890: step: 1168/526, loss: 0.07961931824684143
2023-01-23 00:11:43.779892: step: 1172/526, loss: 0.43556660413742065
2023-01-23 00:11:44.920466: step: 1176/526, loss: 0.26903438568115234
2023-01-23 00:11:46.051207: step: 1180/526, loss: 0.05784440040588379
2023-01-23 00:11:47.184392: step: 1184/526, loss: 0.28725466132164
2023-01-23 00:11:48.320394: step: 1188/526, loss: 0.07860822975635529
2023-01-23 00:11:49.442148: step: 1192/526, loss: 1.069618582725525
2023-01-23 00:11:50.589163: step: 1196/526, loss: 0.09319524466991425
2023-01-23 00:11:51.742534: step: 1200/526, loss: 0.9479278922080994
2023-01-23 00:11:52.880114: step: 1204/526, loss: 0.7471533417701721
2023-01-23 00:11:54.032152: step: 1208/526, loss: 0.5247141122817993
2023-01-23 00:11:55.131000: step: 1212/526, loss: 0.0443631187081337
2023-01-23 00:11:56.275014: step: 1216/526, loss: 0.053660012781620026
2023-01-23 00:11:57.373213: step: 1220/526, loss: 0.7454779148101807
2023-01-23 00:11:58.525882: step: 1224/526, loss: 0.13610154390335083
2023-01-23 00:11:59.649330: step: 1228/526, loss: 0.2525690197944641
2023-01-23 00:12:00.764369: step: 1232/526, loss: 0.8536794185638428
2023-01-23 00:12:01.906883: step: 1236/526, loss: 0.06363983452320099
2023-01-23 00:12:03.043419: step: 1240/526, loss: 0.29542914032936096
2023-01-23 00:12:04.200354: step: 1244/526, loss: 0.4992457926273346
2023-01-23 00:12:05.340751: step: 1248/526, loss: 0.44941824674606323
2023-01-23 00:12:06.468972: step: 1252/526, loss: 0.20342311263084412
2023-01-23 00:12:07.612412: step: 1256/526, loss: 0.0764416754245758
2023-01-23 00:12:08.750771: step: 1260/526, loss: 0.03515281900763512
2023-01-23 00:12:09.877427: step: 1264/526, loss: 0.1457241028547287
2023-01-23 00:12:10.979191: step: 1268/526, loss: 0.07068701088428497
2023-01-23 00:12:12.104930: step: 1272/526, loss: 0.7477499842643738
2023-01-23 00:12:13.234652: step: 1276/526, loss: 0.23456035554409027
2023-01-23 00:12:14.330504: step: 1280/526, loss: 0.19361944496631622
2023-01-23 00:12:15.450389: step: 1284/526, loss: 0.11824379116296768
2023-01-23 00:12:16.574593: step: 1288/526, loss: 0.2297314703464508
2023-01-23 00:12:17.697829: step: 1292/526, loss: 0.6895031929016113
2023-01-23 00:12:18.814906: step: 1296/526, loss: 0.05504312366247177
2023-01-23 00:12:19.943168: step: 1300/526, loss: 0.6723909974098206
2023-01-23 00:12:21.051900: step: 1304/526, loss: 0.2251339852809906
2023-01-23 00:12:22.179123: step: 1308/526, loss: 0.2795290946960449
2023-01-23 00:12:23.326008: step: 1312/526, loss: 0.023305200040340424
2023-01-23 00:12:24.453344: step: 1316/526, loss: 0.032586004585027695
2023-01-23 00:12:25.538649: step: 1320/526, loss: 0.6801646947860718
2023-01-23 00:12:26.670299: step: 1324/526, loss: 0.05224008858203888
2023-01-23 00:12:27.825934: step: 1328/526, loss: 0.1410684585571289
2023-01-23 00:12:28.941314: step: 1332/526, loss: 0.19551940262317657
2023-01-23 00:12:30.076106: step: 1336/526, loss: 0.1493641436100006
2023-01-23 00:12:31.240005: step: 1340/526, loss: 0.1305527687072754
2023-01-23 00:12:32.352739: step: 1344/526, loss: 0.19192147254943848
2023-01-23 00:12:33.465406: step: 1348/526, loss: 0.056697942316532135
2023-01-23 00:12:34.605394: step: 1352/526, loss: 0.23513685166835785
2023-01-23 00:12:35.736832: step: 1356/526, loss: 0.15572190284729004
2023-01-23 00:12:36.870314: step: 1360/526, loss: 0.09732604026794434
2023-01-23 00:12:38.015031: step: 1364/526, loss: 0.30835264921188354
2023-01-23 00:12:39.147653: step: 1368/526, loss: 0.1821792721748352
2023-01-23 00:12:40.292404: step: 1372/526, loss: 0.15931901335716248
2023-01-23 00:12:41.442353: step: 1376/526, loss: 0.2861195504665375
2023-01-23 00:12:42.605396: step: 1380/526, loss: 0.9929283857345581
2023-01-23 00:12:43.735796: step: 1384/526, loss: 0.1610986739397049
2023-01-23 00:12:44.875143: step: 1388/526, loss: 0.47864967584609985
2023-01-23 00:12:46.007560: step: 1392/526, loss: 0.2566388249397278
2023-01-23 00:12:47.108300: step: 1396/526, loss: 0.07148456573486328
2023-01-23 00:12:48.253960: step: 1400/526, loss: 0.1619223654270172
2023-01-23 00:12:49.372962: step: 1404/526, loss: 0.06925344467163086
2023-01-23 00:12:50.491317: step: 1408/526, loss: 0.47106000781059265
2023-01-23 00:12:51.602993: step: 1412/526, loss: 1.3208248615264893
2023-01-23 00:12:52.757927: step: 1416/526, loss: 0.042852021753787994
2023-01-23 00:12:53.863396: step: 1420/526, loss: 1.056248664855957
2023-01-23 00:12:55.025486: step: 1424/526, loss: 0.7417402267456055
2023-01-23 00:12:56.165677: step: 1428/526, loss: 0.07049369812011719
2023-01-23 00:12:57.326217: step: 1432/526, loss: 0.3194744288921356
2023-01-23 00:12:58.453972: step: 1436/526, loss: 0.5398289561271667
2023-01-23 00:12:59.598681: step: 1440/526, loss: 0.2468746155500412
2023-01-23 00:13:00.766113: step: 1444/526, loss: 0.24635668098926544
2023-01-23 00:13:01.947678: step: 1448/526, loss: 2.023756265640259
2023-01-23 00:13:03.108976: step: 1452/526, loss: 0.4297069311141968
2023-01-23 00:13:04.233112: step: 1456/526, loss: 0.10008516162633896
2023-01-23 00:13:05.387463: step: 1460/526, loss: 0.35322466492652893
2023-01-23 00:13:06.507781: step: 1464/526, loss: 0.06808061897754669
2023-01-23 00:13:07.665102: step: 1468/526, loss: 0.05945263057947159
2023-01-23 00:13:08.819903: step: 1472/526, loss: 0.24721908569335938
2023-01-23 00:13:09.956577: step: 1476/526, loss: 0.7393164038658142
2023-01-23 00:13:11.092808: step: 1480/526, loss: 0.28931379318237305
2023-01-23 00:13:12.207437: step: 1484/526, loss: 0.2223377227783203
2023-01-23 00:13:13.381005: step: 1488/526, loss: 0.23443478345870972
2023-01-23 00:13:14.503401: step: 1492/526, loss: 0.15631341934204102
2023-01-23 00:13:15.638775: step: 1496/526, loss: 2.540395736694336
2023-01-23 00:13:16.741735: step: 1500/526, loss: 0.1442979872226715
2023-01-23 00:13:17.924529: step: 1504/526, loss: 0.12117157131433487
2023-01-23 00:13:19.057512: step: 1508/526, loss: 0.11972665786743164
2023-01-23 00:13:20.173360: step: 1512/526, loss: 0.10798332095146179
2023-01-23 00:13:21.295595: step: 1516/526, loss: 0.1232258751988411
2023-01-23 00:13:22.405920: step: 1520/526, loss: 0.10492291301488876
2023-01-23 00:13:23.558414: step: 1524/526, loss: 0.12372155487537384
2023-01-23 00:13:24.704558: step: 1528/526, loss: 0.7846032977104187
2023-01-23 00:13:25.852433: step: 1532/526, loss: 1.361919641494751
2023-01-23 00:13:27.006647: step: 1536/526, loss: 0.144123837351799
2023-01-23 00:13:28.135445: step: 1540/526, loss: 0.4321043789386749
2023-01-23 00:13:29.270266: step: 1544/526, loss: 0.062157824635505676
2023-01-23 00:13:30.366226: step: 1548/526, loss: 0.135029137134552
2023-01-23 00:13:31.512252: step: 1552/526, loss: 0.02161407470703125
2023-01-23 00:13:32.652663: step: 1556/526, loss: 0.16113395988941193
2023-01-23 00:13:33.817229: step: 1560/526, loss: 0.5720523595809937
2023-01-23 00:13:34.947865: step: 1564/526, loss: 0.5385809540748596
2023-01-23 00:13:36.104336: step: 1568/526, loss: 0.07579260319471359
2023-01-23 00:13:37.253375: step: 1572/526, loss: 0.09935131669044495
2023-01-23 00:13:38.384074: step: 1576/526, loss: 0.09231805801391602
2023-01-23 00:13:39.519136: step: 1580/526, loss: 0.11738023161888123
2023-01-23 00:13:40.646629: step: 1584/526, loss: 0.37796393036842346
2023-01-23 00:13:41.767171: step: 1588/526, loss: 0.5186008214950562
2023-01-23 00:13:42.910973: step: 1592/526, loss: 0.4013316035270691
2023-01-23 00:13:44.048610: step: 1596/526, loss: 0.09492354094982147
2023-01-23 00:13:45.201950: step: 1600/526, loss: 0.2895212173461914
2023-01-23 00:13:46.342494: step: 1604/526, loss: 0.11452098190784454
2023-01-23 00:13:47.514760: step: 1608/526, loss: 0.17952455580234528
2023-01-23 00:13:48.649444: step: 1612/526, loss: 0.020197726786136627
2023-01-23 00:13:49.787384: step: 1616/526, loss: 0.20291881263256073
2023-01-23 00:13:50.933550: step: 1620/526, loss: 0.19766837358474731
2023-01-23 00:13:52.041918: step: 1624/526, loss: 0.11001381278038025
2023-01-23 00:13:53.161360: step: 1628/526, loss: 0.5903832316398621
2023-01-23 00:13:54.296170: step: 1632/526, loss: 0.5519746541976929
2023-01-23 00:13:55.423273: step: 1636/526, loss: 0.34842386841773987
2023-01-23 00:13:56.574968: step: 1640/526, loss: 0.09857045114040375
2023-01-23 00:13:57.721446: step: 1644/526, loss: 0.8871277570724487
2023-01-23 00:13:58.840820: step: 1648/526, loss: 0.2080329954624176
2023-01-23 00:13:59.984069: step: 1652/526, loss: 0.3938787579536438
2023-01-23 00:14:01.130332: step: 1656/526, loss: 0.7692900896072388
2023-01-23 00:14:02.322238: step: 1660/526, loss: 0.0781501829624176
2023-01-23 00:14:03.502285: step: 1664/526, loss: 0.04093952476978302
2023-01-23 00:14:04.612065: step: 1668/526, loss: 0.045726679265499115
2023-01-23 00:14:05.749172: step: 1672/526, loss: 0.8742673397064209
2023-01-23 00:14:06.890191: step: 1676/526, loss: 1.3643262386322021
2023-01-23 00:14:08.059214: step: 1680/526, loss: 0.1408170759677887
2023-01-23 00:14:09.233651: step: 1684/526, loss: 0.4666202664375305
2023-01-23 00:14:10.364778: step: 1688/526, loss: 0.41231030225753784
2023-01-23 00:14:11.532113: step: 1692/526, loss: 0.8471347093582153
2023-01-23 00:14:12.690920: step: 1696/526, loss: 0.3264133930206299
2023-01-23 00:14:13.856667: step: 1700/526, loss: 0.47895461320877075
2023-01-23 00:14:14.969998: step: 1704/526, loss: 0.13776779174804688
2023-01-23 00:14:16.128647: step: 1708/526, loss: 0.3295432925224304
2023-01-23 00:14:17.286888: step: 1712/526, loss: 0.11990585178136826
2023-01-23 00:14:18.427783: step: 1716/526, loss: 0.6645368933677673
2023-01-23 00:14:19.543743: step: 1720/526, loss: 1.2137835025787354
2023-01-23 00:14:20.707780: step: 1724/526, loss: 0.28978538513183594
2023-01-23 00:14:21.838452: step: 1728/526, loss: 0.0360596664249897
2023-01-23 00:14:22.958198: step: 1732/526, loss: 0.05216164514422417
2023-01-23 00:14:24.076128: step: 1736/526, loss: 0.22510471940040588
2023-01-23 00:14:25.192550: step: 1740/526, loss: 0.5259994864463806
2023-01-23 00:14:26.331964: step: 1744/526, loss: 0.1807439923286438
2023-01-23 00:14:27.477433: step: 1748/526, loss: 0.08307859301567078
2023-01-23 00:14:28.616126: step: 1752/526, loss: 0.20417433977127075
2023-01-23 00:14:29.757141: step: 1756/526, loss: 0.7567815780639648
2023-01-23 00:14:30.908438: step: 1760/526, loss: 0.9521654844284058
2023-01-23 00:14:32.029293: step: 1764/526, loss: 0.17875318229198456
2023-01-23 00:14:33.159240: step: 1768/526, loss: 0.06773886829614639
2023-01-23 00:14:34.290446: step: 1772/526, loss: 0.33285924792289734
2023-01-23 00:14:35.436215: step: 1776/526, loss: 0.10147294402122498
2023-01-23 00:14:36.570592: step: 1780/526, loss: 0.960585355758667
2023-01-23 00:14:37.714968: step: 1784/526, loss: 0.10967588424682617
2023-01-23 00:14:38.852801: step: 1788/526, loss: 0.6423585414886475
2023-01-23 00:14:39.989691: step: 1792/526, loss: 0.6108390688896179
2023-01-23 00:14:41.118518: step: 1796/526, loss: 0.5428126454353333
2023-01-23 00:14:42.240433: step: 1800/526, loss: 0.015728093683719635
2023-01-23 00:14:43.360866: step: 1804/526, loss: 0.17113475501537323
2023-01-23 00:14:44.478076: step: 1808/526, loss: 0.23737744987010956
2023-01-23 00:14:45.603842: step: 1812/526, loss: 0.4769209027290344
2023-01-23 00:14:46.746979: step: 1816/526, loss: 0.08623366057872772
2023-01-23 00:14:47.897950: step: 1820/526, loss: 0.11496620625257492
2023-01-23 00:14:49.026861: step: 1824/526, loss: 0.30621927976608276
2023-01-23 00:14:50.168653: step: 1828/526, loss: 0.7393184900283813
2023-01-23 00:14:51.281099: step: 1832/526, loss: 0.0417332649230957
2023-01-23 00:14:52.406831: step: 1836/526, loss: 0.7059459686279297
2023-01-23 00:14:53.505380: step: 1840/526, loss: 0.6556960344314575
2023-01-23 00:14:54.685482: step: 1844/526, loss: 0.03392457962036133
2023-01-23 00:14:55.855509: step: 1848/526, loss: 0.06405811756849289
2023-01-23 00:14:56.980474: step: 1852/526, loss: 0.30063286423683167
2023-01-23 00:14:58.119698: step: 1856/526, loss: 0.31495171785354614
2023-01-23 00:14:59.238766: step: 1860/526, loss: 0.33719176054000854
2023-01-23 00:15:00.378890: step: 1864/526, loss: 0.6194790005683899
2023-01-23 00:15:01.520345: step: 1868/526, loss: 0.15346379578113556
2023-01-23 00:15:02.691070: step: 1872/526, loss: 0.3342325687408447
2023-01-23 00:15:03.834383: step: 1876/526, loss: 0.06054558977484703
2023-01-23 00:15:04.948888: step: 1880/526, loss: 0.1685403436422348
2023-01-23 00:15:06.092298: step: 1884/526, loss: 0.054334595799446106
2023-01-23 00:15:07.254061: step: 1888/526, loss: 0.06665010750293732
2023-01-23 00:15:08.406876: step: 1892/526, loss: 0.3820188641548157
2023-01-23 00:15:09.573716: step: 1896/526, loss: 0.14128609001636505
2023-01-23 00:15:10.701611: step: 1900/526, loss: 0.04584827274084091
2023-01-23 00:15:11.801294: step: 1904/526, loss: 0.08219747245311737
2023-01-23 00:15:12.939404: step: 1908/526, loss: 0.028188802301883698
2023-01-23 00:15:14.063718: step: 1912/526, loss: 0.04881878197193146
2023-01-23 00:15:15.186165: step: 1916/526, loss: 0.1517138034105301
2023-01-23 00:15:16.353361: step: 1920/526, loss: 1.1820714473724365
2023-01-23 00:15:17.482964: step: 1924/526, loss: 0.32395753264427185
2023-01-23 00:15:18.591455: step: 1928/526, loss: 1.1668269634246826
2023-01-23 00:15:19.719541: step: 1932/526, loss: 0.127878338098526
2023-01-23 00:15:20.833313: step: 1936/526, loss: 0.8874449729919434
2023-01-23 00:15:21.986904: step: 1940/526, loss: 0.744866132736206
2023-01-23 00:15:23.095302: step: 1944/526, loss: 0.08502760529518127
2023-01-23 00:15:24.240456: step: 1948/526, loss: 0.08729524910449982
2023-01-23 00:15:25.359721: step: 1952/526, loss: 0.08264384418725967
2023-01-23 00:15:26.499896: step: 1956/526, loss: 0.08795285224914551
2023-01-23 00:15:27.624567: step: 1960/526, loss: 0.19313374161720276
2023-01-23 00:15:28.755529: step: 1964/526, loss: 5.26082181930542
2023-01-23 00:15:29.910976: step: 1968/526, loss: 0.09294624626636505
2023-01-23 00:15:31.029947: step: 1972/526, loss: 0.10113152861595154
2023-01-23 00:15:32.150912: step: 1976/526, loss: 0.2049887776374817
2023-01-23 00:15:33.299106: step: 1980/526, loss: 0.19875651597976685
2023-01-23 00:15:34.436843: step: 1984/526, loss: 0.2498459815979004
2023-01-23 00:15:35.555322: step: 1988/526, loss: 0.10887555778026581
2023-01-23 00:15:36.688675: step: 1992/526, loss: 0.05493581295013428
2023-01-23 00:15:37.830615: step: 1996/526, loss: 0.15251369774341583
2023-01-23 00:15:38.946336: step: 2000/526, loss: 0.01222152728587389
2023-01-23 00:15:40.078937: step: 2004/526, loss: 0.7983397245407104
2023-01-23 00:15:41.193394: step: 2008/526, loss: 0.22303137183189392
2023-01-23 00:15:42.316564: step: 2012/526, loss: 0.6977473497390747
2023-01-23 00:15:43.483591: step: 2016/526, loss: 0.3306276202201843
2023-01-23 00:15:44.648543: step: 2020/526, loss: 0.40909910202026367
2023-01-23 00:15:45.817359: step: 2024/526, loss: 0.10456257313489914
2023-01-23 00:15:46.951348: step: 2028/526, loss: 0.23742122948169708
2023-01-23 00:15:48.114254: step: 2032/526, loss: 0.16777239739894867
2023-01-23 00:15:49.258630: step: 2036/526, loss: 0.02179795503616333
2023-01-23 00:15:50.420883: step: 2040/526, loss: 0.3406356871128082
2023-01-23 00:15:51.553237: step: 2044/526, loss: 0.7128070592880249
2023-01-23 00:15:52.713924: step: 2048/526, loss: 0.10555877536535263
2023-01-23 00:15:53.811376: step: 2052/526, loss: 0.06222992390394211
2023-01-23 00:15:54.942559: step: 2056/526, loss: 0.7264218330383301
2023-01-23 00:15:56.085198: step: 2060/526, loss: 0.04870662838220596
2023-01-23 00:15:57.230260: step: 2064/526, loss: 1.328598976135254
2023-01-23 00:15:58.344815: step: 2068/526, loss: 0.09405260533094406
2023-01-23 00:15:59.517315: step: 2072/526, loss: 0.12173452228307724
2023-01-23 00:16:00.668104: step: 2076/526, loss: 0.15678229928016663
2023-01-23 00:16:01.793406: step: 2080/526, loss: 1.41208815574646
2023-01-23 00:16:02.930848: step: 2084/526, loss: 0.6326181888580322
2023-01-23 00:16:04.102272: step: 2088/526, loss: 0.1623951941728592
2023-01-23 00:16:05.233813: step: 2092/526, loss: 0.15030059218406677
2023-01-23 00:16:06.400997: step: 2096/526, loss: 0.39091941714286804
2023-01-23 00:16:07.551521: step: 2100/526, loss: 0.8702443242073059
2023-01-23 00:16:08.694155: step: 2104/526, loss: 0.07611255347728729
==================================================
Loss: 0.353
--------------------
Dev: {'event': {'p': 0.5563041385948027, 'r': 0.7696404793608522, 'f1': 0.6458100558659218}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Test: {'event': {'p': 0.5336806847785635, 'r': 0.7484342379958246, 'f1': 0.6230719096241583}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Chinese: {'event': {'p': 0.5434782608695652, 'r': 0.9259259259259259, 'f1': 0.6849315068493151}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Korean: {'event': {'p': 0.5932203389830508, 'r': 0.5555555555555556, 'f1': 0.5737704918032787}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Russian: {'event': {'p': 0.5116279069767442, 'r': 0.6111111111111112, 'f1': 0.5569620253164557}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
New best korean model...
New best russian model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6604010025062657, 'r': 0.7017310252996005, 'f1': 0.6804389928986443}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Eng Test for Chinese: {'event': {'p': 0.6480836236933798, 'r': 0.6795407098121086, 'f1': 0.6634394904458599}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Sample Chinese: {'event': {'p': 0.6323529411764706, 'r': 0.7962962962962963, 'f1': 0.7049180327868853}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5563041385948027, 'r': 0.7696404793608522, 'f1': 0.6458100558659218}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Eng Test for Korean: {'event': {'p': 0.5336806847785635, 'r': 0.7484342379958246, 'f1': 0.6230719096241583}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Sample Korean: {'event': {'p': 0.5932203389830508, 'r': 0.5555555555555556, 'f1': 0.5737704918032787}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5563041385948027, 'r': 0.7696404793608522, 'f1': 0.6458100558659218}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Eng Test for Russian: {'event': {'p': 0.5336806847785635, 'r': 0.7484342379958246, 'f1': 0.6230719096241583}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Sample Russian: {'event': {'p': 0.5116279069767442, 'r': 0.6111111111111112, 'f1': 0.5569620253164557}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
******************************
Epoch: 5
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 00:17:03.940248: step: 4/526, loss: 0.07552170753479004
2023-01-23 00:17:05.063075: step: 8/526, loss: 0.1778736114501953
2023-01-23 00:17:06.229866: step: 12/526, loss: 0.47908085584640503
2023-01-23 00:17:07.353336: step: 16/526, loss: 0.41332149505615234
2023-01-23 00:17:08.486553: step: 20/526, loss: 0.22914238274097443
2023-01-23 00:17:09.612867: step: 24/526, loss: 0.49168384075164795
2023-01-23 00:17:10.748569: step: 28/526, loss: 0.7054325342178345
2023-01-23 00:17:11.876046: step: 32/526, loss: 0.22354355454444885
2023-01-23 00:17:13.062671: step: 36/526, loss: 0.2816998362541199
2023-01-23 00:17:14.176587: step: 40/526, loss: 0.15015316009521484
2023-01-23 00:17:15.323804: step: 44/526, loss: 0.3128385543823242
2023-01-23 00:17:16.458105: step: 48/526, loss: 0.1136753112077713
2023-01-23 00:17:17.601542: step: 52/526, loss: 0.3024848699569702
2023-01-23 00:17:18.738339: step: 56/526, loss: 0.2961660325527191
2023-01-23 00:17:19.860825: step: 60/526, loss: 0.16076450049877167
2023-01-23 00:17:21.018219: step: 64/526, loss: 0.70372474193573
2023-01-23 00:17:22.130313: step: 68/526, loss: 0.05580272898077965
2023-01-23 00:17:23.248245: step: 72/526, loss: 0.33491912484169006
2023-01-23 00:17:24.371471: step: 76/526, loss: 0.08502702414989471
2023-01-23 00:17:25.493317: step: 80/526, loss: 0.6640203595161438
2023-01-23 00:17:26.621787: step: 84/526, loss: 0.06171112135052681
2023-01-23 00:17:27.765927: step: 88/526, loss: 0.2955389618873596
2023-01-23 00:17:28.914900: step: 92/526, loss: 0.07607822120189667
2023-01-23 00:17:30.022473: step: 96/526, loss: 0.15505895018577576
2023-01-23 00:17:31.144976: step: 100/526, loss: 1.0233112573623657
2023-01-23 00:17:32.271674: step: 104/526, loss: 0.13770484924316406
2023-01-23 00:17:33.415653: step: 108/526, loss: 0.4573703706264496
2023-01-23 00:17:34.571273: step: 112/526, loss: 0.3016144931316376
2023-01-23 00:17:35.714301: step: 116/526, loss: 0.6969193816184998
2023-01-23 00:17:36.842875: step: 120/526, loss: 0.20527324080467224
2023-01-23 00:17:37.967078: step: 124/526, loss: 1.2636239528656006
2023-01-23 00:17:39.115436: step: 128/526, loss: 0.5671699047088623
2023-01-23 00:17:40.257909: step: 132/526, loss: 0.10811157524585724
2023-01-23 00:17:41.380223: step: 136/526, loss: 0.12215442955493927
2023-01-23 00:17:42.511747: step: 140/526, loss: 0.21227779984474182
2023-01-23 00:17:43.616897: step: 144/526, loss: 0.030367136001586914
2023-01-23 00:17:44.740885: step: 148/526, loss: 0.4781329333782196
2023-01-23 00:17:45.871725: step: 152/526, loss: 0.06072940677404404
2023-01-23 00:17:46.999903: step: 156/526, loss: 0.05557294189929962
2023-01-23 00:17:48.124722: step: 160/526, loss: 0.4160362482070923
2023-01-23 00:17:49.254968: step: 164/526, loss: 0.051721859723329544
2023-01-23 00:17:50.384750: step: 168/526, loss: 0.0803864449262619
2023-01-23 00:17:51.517549: step: 172/526, loss: 0.08706312626600266
2023-01-23 00:17:52.620794: step: 176/526, loss: 0.12174461781978607
2023-01-23 00:17:53.771768: step: 180/526, loss: 0.14703483879566193
2023-01-23 00:17:54.916827: step: 184/526, loss: 0.19677190482616425
2023-01-23 00:17:56.076192: step: 188/526, loss: 0.5028398036956787
2023-01-23 00:17:57.193086: step: 192/526, loss: 0.03458528593182564
2023-01-23 00:17:58.305022: step: 196/526, loss: 0.08830176293849945
2023-01-23 00:17:59.423358: step: 200/526, loss: 0.05585050582885742
2023-01-23 00:18:00.581866: step: 204/526, loss: 0.19362641870975494
2023-01-23 00:18:01.696960: step: 208/526, loss: 0.08621148765087128
2023-01-23 00:18:02.851093: step: 212/526, loss: 0.5853188633918762
2023-01-23 00:18:03.993184: step: 216/526, loss: 0.4329465925693512
2023-01-23 00:18:05.127246: step: 220/526, loss: 0.4039674699306488
2023-01-23 00:18:06.242462: step: 224/526, loss: 0.026792338117957115
2023-01-23 00:18:07.403861: step: 228/526, loss: 0.1944846212863922
2023-01-23 00:18:08.524435: step: 232/526, loss: 0.10644569993019104
2023-01-23 00:18:09.631886: step: 236/526, loss: 3.594597101211548
2023-01-23 00:18:10.760656: step: 240/526, loss: 0.23088054358959198
2023-01-23 00:18:11.884248: step: 244/526, loss: 0.060803867876529694
2023-01-23 00:18:13.054322: step: 248/526, loss: 0.07625265419483185
2023-01-23 00:18:14.177394: step: 252/526, loss: 0.3246402144432068
2023-01-23 00:18:15.286795: step: 256/526, loss: 0.222834974527359
2023-01-23 00:18:16.454490: step: 260/526, loss: 0.15671049058437347
2023-01-23 00:18:17.567275: step: 264/526, loss: 0.2793780565261841
2023-01-23 00:18:18.695151: step: 268/526, loss: 0.3518807291984558
2023-01-23 00:18:19.839178: step: 272/526, loss: 0.16502493619918823
2023-01-23 00:18:20.981299: step: 276/526, loss: 0.13538670539855957
2023-01-23 00:18:22.130263: step: 280/526, loss: 0.33921700716018677
2023-01-23 00:18:23.271418: step: 284/526, loss: 0.09293756633996964
2023-01-23 00:18:24.407780: step: 288/526, loss: 0.12042374908924103
2023-01-23 00:18:25.529228: step: 292/526, loss: 0.10213012993335724
2023-01-23 00:18:26.635096: step: 296/526, loss: 0.14765429496765137
2023-01-23 00:18:27.755085: step: 300/526, loss: 0.11585512012243271
2023-01-23 00:18:28.900876: step: 304/526, loss: 0.2017158567905426
2023-01-23 00:18:30.027003: step: 308/526, loss: 0.4023115336894989
2023-01-23 00:18:31.150254: step: 312/526, loss: 0.051944926381111145
2023-01-23 00:18:32.305231: step: 316/526, loss: 0.03483166918158531
2023-01-23 00:18:33.474013: step: 320/526, loss: 0.1493522673845291
2023-01-23 00:18:34.599343: step: 324/526, loss: 0.436555951833725
2023-01-23 00:18:35.717373: step: 328/526, loss: 0.09910402446985245
2023-01-23 00:18:36.851483: step: 332/526, loss: 0.10703545063734055
2023-01-23 00:18:37.963107: step: 336/526, loss: 0.01687011681497097
2023-01-23 00:18:39.111533: step: 340/526, loss: 0.6482803821563721
2023-01-23 00:18:40.282641: step: 344/526, loss: 0.3501931428909302
2023-01-23 00:18:41.413484: step: 348/526, loss: 0.5176986455917358
2023-01-23 00:18:42.540854: step: 352/526, loss: 0.41397643089294434
2023-01-23 00:18:43.697743: step: 356/526, loss: 0.11719612777233124
2023-01-23 00:18:44.851658: step: 360/526, loss: 0.14571914076805115
2023-01-23 00:18:45.976662: step: 364/526, loss: 0.1404467523097992
2023-01-23 00:18:47.120772: step: 368/526, loss: 0.04848051071166992
2023-01-23 00:18:48.262237: step: 372/526, loss: 0.029836654663085938
2023-01-23 00:18:49.369701: step: 376/526, loss: 0.049016378819942474
2023-01-23 00:18:50.530992: step: 380/526, loss: 0.4558943212032318
2023-01-23 00:18:51.669702: step: 384/526, loss: 0.07975959777832031
2023-01-23 00:18:52.831377: step: 388/526, loss: 0.24870933592319489
2023-01-23 00:18:53.975685: step: 392/526, loss: 0.07261504977941513
2023-01-23 00:18:55.098320: step: 396/526, loss: 0.2094138115644455
2023-01-23 00:18:56.224791: step: 400/526, loss: 0.06749296188354492
2023-01-23 00:18:57.347348: step: 404/526, loss: 0.6789333820343018
2023-01-23 00:18:58.491601: step: 408/526, loss: 0.14371486008167267
2023-01-23 00:18:59.598317: step: 412/526, loss: 0.11847849190235138
2023-01-23 00:19:00.714997: step: 416/526, loss: 0.14260311424732208
2023-01-23 00:19:01.869701: step: 420/526, loss: 0.6579089164733887
2023-01-23 00:19:03.003422: step: 424/526, loss: 0.13759641349315643
2023-01-23 00:19:04.161577: step: 428/526, loss: 0.1361497938632965
2023-01-23 00:19:05.281900: step: 432/526, loss: 0.11495156586170197
2023-01-23 00:19:06.421190: step: 436/526, loss: 0.10495725274085999
2023-01-23 00:19:07.531280: step: 440/526, loss: 0.2477591633796692
2023-01-23 00:19:08.701184: step: 444/526, loss: 0.3187906742095947
2023-01-23 00:19:09.828111: step: 448/526, loss: 0.11388960480690002
2023-01-23 00:19:10.942089: step: 452/526, loss: 0.1595078557729721
2023-01-23 00:19:12.084448: step: 456/526, loss: 0.4562973082065582
2023-01-23 00:19:13.238402: step: 460/526, loss: 0.2635514736175537
2023-01-23 00:19:14.358205: step: 464/526, loss: 0.1092710942029953
2023-01-23 00:19:15.484795: step: 468/526, loss: 0.030313827097415924
2023-01-23 00:19:16.580984: step: 472/526, loss: 0.4443342983722687
2023-01-23 00:19:17.714636: step: 476/526, loss: 0.0713747963309288
2023-01-23 00:19:18.868224: step: 480/526, loss: 0.084652379155159
2023-01-23 00:19:19.985574: step: 484/526, loss: 0.08752064406871796
2023-01-23 00:19:21.126071: step: 488/526, loss: 0.03136329725384712
2023-01-23 00:19:22.244773: step: 492/526, loss: 0.03622160106897354
2023-01-23 00:19:23.366576: step: 496/526, loss: 0.05147838592529297
2023-01-23 00:19:24.481752: step: 500/526, loss: 0.08350391685962677
2023-01-23 00:19:25.633666: step: 504/526, loss: 0.15375709533691406
2023-01-23 00:19:26.775236: step: 508/526, loss: 0.6762579083442688
2023-01-23 00:19:27.922840: step: 512/526, loss: 0.6304488182067871
2023-01-23 00:19:29.043883: step: 516/526, loss: 0.2314133644104004
2023-01-23 00:19:30.163944: step: 520/526, loss: 0.10436764359474182
2023-01-23 00:19:31.301460: step: 524/526, loss: 0.5557795763015747
2023-01-23 00:19:32.453338: step: 528/526, loss: 0.15001335740089417
2023-01-23 00:19:33.575440: step: 532/526, loss: 0.6348365545272827
2023-01-23 00:19:34.686002: step: 536/526, loss: 0.08023472130298615
2023-01-23 00:19:35.786700: step: 540/526, loss: 0.287660151720047
2023-01-23 00:19:36.929642: step: 544/526, loss: 0.08438985794782639
2023-01-23 00:19:38.068982: step: 548/526, loss: 0.14376278221607208
2023-01-23 00:19:39.224746: step: 552/526, loss: 0.057227421551942825
2023-01-23 00:19:40.340923: step: 556/526, loss: 0.06003871187567711
2023-01-23 00:19:41.469346: step: 560/526, loss: 0.08796177059412003
2023-01-23 00:19:42.603712: step: 564/526, loss: 0.44969606399536133
2023-01-23 00:19:43.751031: step: 568/526, loss: 0.5560224652290344
2023-01-23 00:19:44.901406: step: 572/526, loss: 0.19575929641723633
2023-01-23 00:19:46.041842: step: 576/526, loss: 0.10686217248439789
2023-01-23 00:19:47.199389: step: 580/526, loss: 0.27057409286499023
2023-01-23 00:19:48.318526: step: 584/526, loss: 0.6121435165405273
2023-01-23 00:19:49.447930: step: 588/526, loss: 0.0969381332397461
2023-01-23 00:19:50.555868: step: 592/526, loss: 0.09959135949611664
2023-01-23 00:19:51.707155: step: 596/526, loss: 0.0922972708940506
2023-01-23 00:19:52.823833: step: 600/526, loss: 0.10342487692832947
2023-01-23 00:19:53.962889: step: 604/526, loss: 0.019901657477021217
2023-01-23 00:19:55.106982: step: 608/526, loss: 0.19516621530056
2023-01-23 00:19:56.222926: step: 612/526, loss: 0.3263491094112396
2023-01-23 00:19:57.347974: step: 616/526, loss: 0.1799975484609604
2023-01-23 00:19:58.503360: step: 620/526, loss: 0.06523466110229492
2023-01-23 00:19:59.639764: step: 624/526, loss: 0.4737827181816101
2023-01-23 00:20:00.766307: step: 628/526, loss: 0.05707339942455292
2023-01-23 00:20:01.900935: step: 632/526, loss: 0.1440323442220688
2023-01-23 00:20:03.030677: step: 636/526, loss: 0.10384152084589005
2023-01-23 00:20:04.186752: step: 640/526, loss: 0.39088764786720276
2023-01-23 00:20:05.326676: step: 644/526, loss: 0.21252554655075073
2023-01-23 00:20:06.472426: step: 648/526, loss: 0.23186130821704865
2023-01-23 00:20:07.625287: step: 652/526, loss: 0.14491558074951172
2023-01-23 00:20:08.735753: step: 656/526, loss: 0.0809914618730545
2023-01-23 00:20:09.901407: step: 660/526, loss: 0.581156849861145
2023-01-23 00:20:11.028674: step: 664/526, loss: 0.11716137081384659
2023-01-23 00:20:12.139849: step: 668/526, loss: 0.42929807305336
2023-01-23 00:20:13.239989: step: 672/526, loss: 0.06738128513097763
2023-01-23 00:20:14.369134: step: 676/526, loss: 0.03126473352313042
2023-01-23 00:20:15.493277: step: 680/526, loss: 0.5546294450759888
2023-01-23 00:20:16.647394: step: 684/526, loss: 0.40436506271362305
2023-01-23 00:20:17.789436: step: 688/526, loss: 0.1566580832004547
2023-01-23 00:20:18.907957: step: 692/526, loss: 0.17345371842384338
2023-01-23 00:20:20.010357: step: 696/526, loss: 0.05924072116613388
2023-01-23 00:20:21.136188: step: 700/526, loss: 0.3746162950992584
2023-01-23 00:20:22.274126: step: 704/526, loss: 0.1387009620666504
2023-01-23 00:20:23.420330: step: 708/526, loss: 0.1399168074131012
2023-01-23 00:20:24.532390: step: 712/526, loss: 0.05567455291748047
2023-01-23 00:20:25.696016: step: 716/526, loss: 0.3600977659225464
2023-01-23 00:20:26.866184: step: 720/526, loss: 0.33110275864601135
2023-01-23 00:20:28.040551: step: 724/526, loss: 0.2367338240146637
2023-01-23 00:20:29.170490: step: 728/526, loss: 0.049689389765262604
2023-01-23 00:20:30.357033: step: 732/526, loss: 0.06639156490564346
2023-01-23 00:20:31.518795: step: 736/526, loss: 0.10460825264453888
2023-01-23 00:20:32.670799: step: 740/526, loss: 0.2921673059463501
2023-01-23 00:20:33.805102: step: 744/526, loss: 0.082593634724617
2023-01-23 00:20:34.950668: step: 748/526, loss: 0.22028112411499023
2023-01-23 00:20:36.078281: step: 752/526, loss: 0.20759665966033936
2023-01-23 00:20:37.212017: step: 756/526, loss: 0.04025144502520561
2023-01-23 00:20:38.337575: step: 760/526, loss: 0.06561832129955292
2023-01-23 00:20:39.463877: step: 764/526, loss: 0.10911436378955841
2023-01-23 00:20:40.610884: step: 768/526, loss: 0.07309374958276749
2023-01-23 00:20:41.742990: step: 772/526, loss: 0.13165739178657532
2023-01-23 00:20:42.886624: step: 776/526, loss: 0.3502717614173889
2023-01-23 00:20:44.014496: step: 780/526, loss: 0.08526067435741425
2023-01-23 00:20:45.153764: step: 784/526, loss: 0.30387717485427856
2023-01-23 00:20:46.285122: step: 788/526, loss: 0.4214094281196594
2023-01-23 00:20:47.454777: step: 792/526, loss: 0.677837610244751
2023-01-23 00:20:48.603522: step: 796/526, loss: 0.11714563518762589
2023-01-23 00:20:49.728023: step: 800/526, loss: 0.5716214179992676
2023-01-23 00:20:50.849203: step: 804/526, loss: 0.0568116195499897
2023-01-23 00:20:51.981296: step: 808/526, loss: 0.632706880569458
2023-01-23 00:20:53.074187: step: 812/526, loss: 0.31289201974868774
2023-01-23 00:20:54.190037: step: 816/526, loss: 0.5513056516647339
2023-01-23 00:20:55.345260: step: 820/526, loss: 0.12334317713975906
2023-01-23 00:20:56.494134: step: 824/526, loss: 0.056501008570194244
2023-01-23 00:20:57.642875: step: 828/526, loss: 0.16306714713573456
2023-01-23 00:20:58.781035: step: 832/526, loss: 0.12435455620288849
2023-01-23 00:20:59.918369: step: 836/526, loss: 0.07763805985450745
2023-01-23 00:21:01.039535: step: 840/526, loss: 0.2870665490627289
2023-01-23 00:21:02.198172: step: 844/526, loss: 0.4671330451965332
2023-01-23 00:21:03.323253: step: 848/526, loss: 0.016177939251065254
2023-01-23 00:21:04.466363: step: 852/526, loss: 0.025417424738407135
2023-01-23 00:21:05.588523: step: 856/526, loss: 0.043744660913944244
2023-01-23 00:21:06.730481: step: 860/526, loss: 0.581939697265625
2023-01-23 00:21:07.859890: step: 864/526, loss: 0.061492159962654114
2023-01-23 00:21:08.981787: step: 868/526, loss: 0.6203882098197937
2023-01-23 00:21:10.137288: step: 872/526, loss: 0.055752232670784
2023-01-23 00:21:11.253094: step: 876/526, loss: 0.024624967947602272
2023-01-23 00:21:12.378045: step: 880/526, loss: 0.16453096270561218
2023-01-23 00:21:13.513723: step: 884/526, loss: 0.10548434406518936
2023-01-23 00:21:14.612049: step: 888/526, loss: 0.20627892017364502
2023-01-23 00:21:15.760958: step: 892/526, loss: 0.07390408962965012
2023-01-23 00:21:16.912733: step: 896/526, loss: 0.12392453849315643
2023-01-23 00:21:18.038354: step: 900/526, loss: 0.622948944568634
2023-01-23 00:21:19.183527: step: 904/526, loss: 0.1790519654750824
2023-01-23 00:21:20.325588: step: 908/526, loss: 0.8041629195213318
2023-01-23 00:21:21.499670: step: 912/526, loss: 0.29022684693336487
2023-01-23 00:21:22.649269: step: 916/526, loss: 0.35412710905075073
2023-01-23 00:21:23.820052: step: 920/526, loss: 0.1469673216342926
2023-01-23 00:21:24.985352: step: 924/526, loss: 0.18353509902954102
2023-01-23 00:21:26.124430: step: 928/526, loss: 0.3620956242084503
2023-01-23 00:21:27.270410: step: 932/526, loss: 0.12959997355937958
2023-01-23 00:21:28.393468: step: 936/526, loss: 0.27869871258735657
2023-01-23 00:21:29.531068: step: 940/526, loss: 0.25083011388778687
2023-01-23 00:21:30.656341: step: 944/526, loss: 0.1387719213962555
2023-01-23 00:21:31.793306: step: 948/526, loss: 0.18806734681129456
2023-01-23 00:21:32.933511: step: 952/526, loss: 0.37217214703559875
2023-01-23 00:21:34.054147: step: 956/526, loss: 0.17451295256614685
2023-01-23 00:21:35.172011: step: 960/526, loss: 0.12138272076845169
2023-01-23 00:21:36.308261: step: 964/526, loss: 0.987384021282196
2023-01-23 00:21:37.471218: step: 968/526, loss: 0.08471079170703888
2023-01-23 00:21:38.598284: step: 972/526, loss: 0.16412298381328583
2023-01-23 00:21:39.762337: step: 976/526, loss: 0.09780779480934143
2023-01-23 00:21:40.889306: step: 980/526, loss: 0.07905187457799911
2023-01-23 00:21:42.031787: step: 984/526, loss: 0.030390549451112747
2023-01-23 00:21:43.181702: step: 988/526, loss: 0.0787535235285759
2023-01-23 00:21:44.294019: step: 992/526, loss: 0.17775791883468628
2023-01-23 00:21:45.412110: step: 996/526, loss: 0.059416815638542175
2023-01-23 00:21:46.547608: step: 1000/526, loss: 0.09653346240520477
2023-01-23 00:21:47.650463: step: 1004/526, loss: 0.13981446623802185
2023-01-23 00:21:48.802484: step: 1008/526, loss: 1.0894023180007935
2023-01-23 00:21:49.926471: step: 1012/526, loss: 0.0881490707397461
2023-01-23 00:21:51.077026: step: 1016/526, loss: 0.0698762908577919
2023-01-23 00:21:52.210185: step: 1020/526, loss: 0.16481313109397888
2023-01-23 00:21:53.363898: step: 1024/526, loss: 0.07063284516334534
2023-01-23 00:21:54.533317: step: 1028/526, loss: 0.09497375786304474
2023-01-23 00:21:55.663073: step: 1032/526, loss: 0.122956283390522
2023-01-23 00:21:56.778035: step: 1036/526, loss: 0.1150793582201004
2023-01-23 00:21:57.902607: step: 1040/526, loss: 0.10032553970813751
2023-01-23 00:21:59.038827: step: 1044/526, loss: 0.0470617301762104
2023-01-23 00:22:00.193476: step: 1048/526, loss: 0.3499331474304199
2023-01-23 00:22:01.366398: step: 1052/526, loss: 0.30687639117240906
2023-01-23 00:22:02.516903: step: 1056/526, loss: 0.37629234790802
2023-01-23 00:22:03.636431: step: 1060/526, loss: 0.06239809840917587
2023-01-23 00:22:04.758650: step: 1064/526, loss: 0.004215431399643421
2023-01-23 00:22:05.884200: step: 1068/526, loss: 0.05564947426319122
2023-01-23 00:22:07.043523: step: 1072/526, loss: 0.11828222870826721
2023-01-23 00:22:08.151040: step: 1076/526, loss: 0.048153355717659
2023-01-23 00:22:09.286518: step: 1080/526, loss: 0.07006406784057617
2023-01-23 00:22:10.435954: step: 1084/526, loss: 0.2897661328315735
2023-01-23 00:22:11.620088: step: 1088/526, loss: 0.02233278751373291
2023-01-23 00:22:12.761715: step: 1092/526, loss: 0.20013219118118286
2023-01-23 00:22:13.910763: step: 1096/526, loss: 0.07541098445653915
2023-01-23 00:22:15.039737: step: 1100/526, loss: 0.18152180314064026
2023-01-23 00:22:16.189857: step: 1104/526, loss: 0.09701547026634216
2023-01-23 00:22:17.302049: step: 1108/526, loss: 0.007830810733139515
2023-01-23 00:22:18.451535: step: 1112/526, loss: 0.20827673375606537
2023-01-23 00:22:19.564838: step: 1116/526, loss: 0.07904062420129776
2023-01-23 00:22:20.693374: step: 1120/526, loss: 0.06303844600915909
2023-01-23 00:22:21.895447: step: 1124/526, loss: 0.27868205308914185
2023-01-23 00:22:23.052172: step: 1128/526, loss: 0.4336077570915222
2023-01-23 00:22:24.216674: step: 1132/526, loss: 0.0917481929063797
2023-01-23 00:22:25.352524: step: 1136/526, loss: 0.5258356928825378
2023-01-23 00:22:26.484408: step: 1140/526, loss: 0.17753896117210388
2023-01-23 00:22:27.608962: step: 1144/526, loss: 0.23496904969215393
2023-01-23 00:22:28.737248: step: 1148/526, loss: 0.06634197384119034
2023-01-23 00:22:29.874450: step: 1152/526, loss: 0.26711511611938477
2023-01-23 00:22:31.017120: step: 1156/526, loss: 0.13119515776634216
2023-01-23 00:22:32.205336: step: 1160/526, loss: 0.07149533927440643
2023-01-23 00:22:33.350611: step: 1164/526, loss: 0.47180628776550293
2023-01-23 00:22:34.496312: step: 1168/526, loss: 0.13471731543540955
2023-01-23 00:22:35.628951: step: 1172/526, loss: 0.28347986936569214
2023-01-23 00:22:36.738235: step: 1176/526, loss: 0.01544198952615261
2023-01-23 00:22:37.875418: step: 1180/526, loss: 0.1351659893989563
2023-01-23 00:22:39.002830: step: 1184/526, loss: 0.16764900088310242
2023-01-23 00:22:40.123675: step: 1188/526, loss: 5.7529215812683105
2023-01-23 00:22:41.247449: step: 1192/526, loss: 0.6821755170822144
2023-01-23 00:22:42.375455: step: 1196/526, loss: 1.002524971961975
2023-01-23 00:22:43.501030: step: 1200/526, loss: 0.21645474433898926
2023-01-23 00:22:44.637020: step: 1204/526, loss: 0.15088805556297302
2023-01-23 00:22:45.752764: step: 1208/526, loss: 0.5905170440673828
2023-01-23 00:22:46.885628: step: 1212/526, loss: 0.046729087829589844
2023-01-23 00:22:48.039578: step: 1216/526, loss: 0.1753438413143158
2023-01-23 00:22:49.184047: step: 1220/526, loss: 0.08497485518455505
2023-01-23 00:22:50.310106: step: 1224/526, loss: 0.1213504746556282
2023-01-23 00:22:51.405182: step: 1228/526, loss: 0.4379407465457916
2023-01-23 00:22:52.539371: step: 1232/526, loss: 0.12683840095996857
2023-01-23 00:22:53.700032: step: 1236/526, loss: 0.4335874617099762
2023-01-23 00:22:54.836479: step: 1240/526, loss: 0.11594896018505096
2023-01-23 00:22:55.989759: step: 1244/526, loss: 0.09811754524707794
2023-01-23 00:22:57.127079: step: 1248/526, loss: 0.9354307651519775
2023-01-23 00:22:58.266025: step: 1252/526, loss: 0.136609748005867
2023-01-23 00:22:59.416562: step: 1256/526, loss: 0.14618225395679474
2023-01-23 00:23:00.569828: step: 1260/526, loss: 0.049700167030096054
2023-01-23 00:23:01.699240: step: 1264/526, loss: 0.026849079877138138
2023-01-23 00:23:02.829115: step: 1268/526, loss: 0.030932903289794922
2023-01-23 00:23:03.985955: step: 1272/526, loss: 0.12946195900440216
2023-01-23 00:23:05.109488: step: 1276/526, loss: 0.3413374125957489
2023-01-23 00:23:06.252835: step: 1280/526, loss: 0.5484434962272644
2023-01-23 00:23:07.397454: step: 1284/526, loss: 0.09699907153844833
2023-01-23 00:23:08.517700: step: 1288/526, loss: 0.10249491035938263
2023-01-23 00:23:09.654146: step: 1292/526, loss: 0.528791606426239
2023-01-23 00:23:10.795990: step: 1296/526, loss: 0.08172684162855148
2023-01-23 00:23:11.924310: step: 1300/526, loss: 0.15835723280906677
2023-01-23 00:23:13.115009: step: 1304/526, loss: 3.7234480381011963
2023-01-23 00:23:14.249959: step: 1308/526, loss: 0.15857048332691193
2023-01-23 00:23:15.382341: step: 1312/526, loss: 0.15546664595603943
2023-01-23 00:23:16.519894: step: 1316/526, loss: 0.013378048315644264
2023-01-23 00:23:17.689678: step: 1320/526, loss: 0.31611576676368713
2023-01-23 00:23:18.832049: step: 1324/526, loss: 0.056382276117801666
2023-01-23 00:23:19.940632: step: 1328/526, loss: 0.1151147335767746
2023-01-23 00:23:21.053867: step: 1332/526, loss: 0.19945715367794037
2023-01-23 00:23:22.180418: step: 1336/526, loss: 0.10670605301856995
2023-01-23 00:23:23.343490: step: 1340/526, loss: 0.06457419693470001
2023-01-23 00:23:24.511618: step: 1344/526, loss: 0.1427433043718338
2023-01-23 00:23:25.626136: step: 1348/526, loss: 0.07333040237426758
2023-01-23 00:23:26.773660: step: 1352/526, loss: 0.28943243622779846
2023-01-23 00:23:27.861963: step: 1356/526, loss: 0.04551959037780762
2023-01-23 00:23:29.016972: step: 1360/526, loss: 0.03165636211633682
2023-01-23 00:23:30.140113: step: 1364/526, loss: 0.110833540558815
2023-01-23 00:23:31.262302: step: 1368/526, loss: 0.18557500839233398
2023-01-23 00:23:32.423185: step: 1372/526, loss: 0.7316573858261108
2023-01-23 00:23:33.567512: step: 1376/526, loss: 0.6557825803756714
2023-01-23 00:23:34.711182: step: 1380/526, loss: 0.0473148375749588
2023-01-23 00:23:35.841231: step: 1384/526, loss: 0.19366998970508575
2023-01-23 00:23:36.985369: step: 1388/526, loss: 0.07655983418226242
2023-01-23 00:23:38.107715: step: 1392/526, loss: 0.08151821792125702
2023-01-23 00:23:39.232439: step: 1396/526, loss: 0.14024314284324646
2023-01-23 00:23:40.387451: step: 1400/526, loss: 0.12762165069580078
2023-01-23 00:23:41.511581: step: 1404/526, loss: 0.29477283358573914
2023-01-23 00:23:42.657905: step: 1408/526, loss: 0.1507505476474762
2023-01-23 00:23:43.777375: step: 1412/526, loss: 0.055031586438417435
2023-01-23 00:23:44.912490: step: 1416/526, loss: 0.19547760486602783
2023-01-23 00:23:46.071186: step: 1420/526, loss: 0.08987510204315186
2023-01-23 00:23:47.194865: step: 1424/526, loss: 0.17260035872459412
2023-01-23 00:23:48.331635: step: 1428/526, loss: 0.4401676654815674
2023-01-23 00:23:49.465659: step: 1432/526, loss: 0.10761260986328125
2023-01-23 00:23:50.602668: step: 1436/526, loss: 0.17115606367588043
2023-01-23 00:23:51.726326: step: 1440/526, loss: 0.12303884327411652
2023-01-23 00:23:52.892226: step: 1444/526, loss: 0.3938596844673157
2023-01-23 00:23:54.021428: step: 1448/526, loss: 0.13859958946704865
2023-01-23 00:23:55.175494: step: 1452/526, loss: 0.991059422492981
2023-01-23 00:23:56.314684: step: 1456/526, loss: 0.11598372459411621
2023-01-23 00:23:57.436840: step: 1460/526, loss: 0.06403837352991104
2023-01-23 00:23:58.559498: step: 1464/526, loss: 0.04212365299463272
2023-01-23 00:23:59.669303: step: 1468/526, loss: 0.045427776873111725
2023-01-23 00:24:00.806700: step: 1472/526, loss: 0.1310184895992279
2023-01-23 00:24:01.952898: step: 1476/526, loss: 0.20100879669189453
2023-01-23 00:24:03.100128: step: 1480/526, loss: 0.230610653758049
2023-01-23 00:24:04.236526: step: 1484/526, loss: 0.9139903783798218
2023-01-23 00:24:05.366994: step: 1488/526, loss: 0.2325393706560135
2023-01-23 00:24:06.507024: step: 1492/526, loss: 0.1776561737060547
2023-01-23 00:24:07.654929: step: 1496/526, loss: 0.09078922867774963
2023-01-23 00:24:08.808327: step: 1500/526, loss: 0.5354470014572144
2023-01-23 00:24:09.919950: step: 1504/526, loss: 0.040494538843631744
2023-01-23 00:24:11.054890: step: 1508/526, loss: 0.18460139632225037
2023-01-23 00:24:12.190250: step: 1512/526, loss: 0.21998730301856995
2023-01-23 00:24:13.369500: step: 1516/526, loss: 0.23641423881053925
2023-01-23 00:24:14.504293: step: 1520/526, loss: 0.05305318534374237
2023-01-23 00:24:15.638334: step: 1524/526, loss: 0.14219188690185547
2023-01-23 00:24:16.770886: step: 1528/526, loss: 0.192413330078125
2023-01-23 00:24:17.911937: step: 1532/526, loss: 0.19365087151527405
2023-01-23 00:24:19.043876: step: 1536/526, loss: 0.007358169183135033
2023-01-23 00:24:20.150967: step: 1540/526, loss: 0.06071644276380539
2023-01-23 00:24:21.287476: step: 1544/526, loss: 0.3244949281215668
2023-01-23 00:24:22.435990: step: 1548/526, loss: 0.9575450420379639
2023-01-23 00:24:23.604373: step: 1552/526, loss: 0.06787557899951935
2023-01-23 00:24:24.756016: step: 1556/526, loss: 0.04984130710363388
2023-01-23 00:24:25.864234: step: 1560/526, loss: 0.05042486637830734
2023-01-23 00:24:26.986139: step: 1564/526, loss: 0.7666254043579102
2023-01-23 00:24:28.129266: step: 1568/526, loss: 0.09522084891796112
2023-01-23 00:24:29.288533: step: 1572/526, loss: 0.21847449243068695
2023-01-23 00:24:30.452326: step: 1576/526, loss: 0.14648428559303284
2023-01-23 00:24:31.573570: step: 1580/526, loss: 0.2526691257953644
2023-01-23 00:24:32.712979: step: 1584/526, loss: 0.2150009274482727
2023-01-23 00:24:33.837307: step: 1588/526, loss: 0.10367265343666077
2023-01-23 00:24:34.970271: step: 1592/526, loss: 0.07769985496997833
2023-01-23 00:24:36.119234: step: 1596/526, loss: 0.08559217303991318
2023-01-23 00:24:37.243858: step: 1600/526, loss: 0.66338711977005
2023-01-23 00:24:38.361971: step: 1604/526, loss: 0.04394664987921715
2023-01-23 00:24:39.506938: step: 1608/526, loss: 0.2186059057712555
2023-01-23 00:24:40.638387: step: 1612/526, loss: 0.14132104814052582
2023-01-23 00:24:41.764295: step: 1616/526, loss: 0.013515759259462357
2023-01-23 00:24:42.915531: step: 1620/526, loss: 2.7745673656463623
2023-01-23 00:24:44.041402: step: 1624/526, loss: 0.35903164744377136
2023-01-23 00:24:45.179629: step: 1628/526, loss: 0.06225328892469406
2023-01-23 00:24:46.316854: step: 1632/526, loss: 0.09368248283863068
2023-01-23 00:24:47.460616: step: 1636/526, loss: 0.11353512108325958
2023-01-23 00:24:48.628789: step: 1640/526, loss: 0.4567698538303375
2023-01-23 00:24:49.797097: step: 1644/526, loss: 0.34618473052978516
2023-01-23 00:24:50.943265: step: 1648/526, loss: 0.5828515291213989
2023-01-23 00:24:52.078592: step: 1652/526, loss: 0.4022310972213745
2023-01-23 00:24:53.240815: step: 1656/526, loss: 0.18383732438087463
2023-01-23 00:24:54.360204: step: 1660/526, loss: 0.02237219735980034
2023-01-23 00:24:55.468241: step: 1664/526, loss: 0.028775788843631744
2023-01-23 00:24:56.603736: step: 1668/526, loss: 0.5737066268920898
2023-01-23 00:24:57.729859: step: 1672/526, loss: 5.0599565505981445
2023-01-23 00:24:58.848632: step: 1676/526, loss: 0.12092189490795135
2023-01-23 00:24:59.993251: step: 1680/526, loss: 0.0936523973941803
2023-01-23 00:25:01.130530: step: 1684/526, loss: 0.6087787747383118
2023-01-23 00:25:02.275284: step: 1688/526, loss: 0.5766590237617493
2023-01-23 00:25:03.395004: step: 1692/526, loss: 0.07612409442663193
2023-01-23 00:25:04.521816: step: 1696/526, loss: 0.1062956377863884
2023-01-23 00:25:05.655868: step: 1700/526, loss: 0.13765287399291992
2023-01-23 00:25:06.804854: step: 1704/526, loss: 2.2298364639282227
2023-01-23 00:25:07.951016: step: 1708/526, loss: 0.1256028264760971
2023-01-23 00:25:09.100128: step: 1712/526, loss: 0.12371645867824554
2023-01-23 00:25:10.221019: step: 1716/526, loss: 0.12302427738904953
2023-01-23 00:25:11.372812: step: 1720/526, loss: 0.13936057686805725
2023-01-23 00:25:12.498819: step: 1724/526, loss: 0.2171371579170227
2023-01-23 00:25:13.630307: step: 1728/526, loss: 0.07089905440807343
2023-01-23 00:25:14.768601: step: 1732/526, loss: 0.12172970920801163
2023-01-23 00:25:15.937012: step: 1736/526, loss: 0.1670808494091034
2023-01-23 00:25:17.069054: step: 1740/526, loss: 0.23992501199245453
2023-01-23 00:25:18.184555: step: 1744/526, loss: 0.1299276351928711
2023-01-23 00:25:19.377143: step: 1748/526, loss: 0.0321536548435688
2023-01-23 00:25:20.494593: step: 1752/526, loss: 0.0880836546421051
2023-01-23 00:25:21.630942: step: 1756/526, loss: 0.17066097259521484
2023-01-23 00:25:22.791542: step: 1760/526, loss: 0.21126055717468262
2023-01-23 00:25:23.920783: step: 1764/526, loss: 0.19855758547782898
2023-01-23 00:25:25.030870: step: 1768/526, loss: 0.4041768014431
2023-01-23 00:25:26.180267: step: 1772/526, loss: 0.08282260596752167
2023-01-23 00:25:27.298620: step: 1776/526, loss: 0.17709942162036896
2023-01-23 00:25:28.428991: step: 1780/526, loss: 0.9613229036331177
2023-01-23 00:25:29.567546: step: 1784/526, loss: 0.05794067680835724
2023-01-23 00:25:30.712916: step: 1788/526, loss: 0.08860006183385849
2023-01-23 00:25:31.843128: step: 1792/526, loss: 1.0366246700286865
2023-01-23 00:25:32.999347: step: 1796/526, loss: 0.26304614543914795
2023-01-23 00:25:34.158335: step: 1800/526, loss: 0.2124791443347931
2023-01-23 00:25:35.298672: step: 1804/526, loss: 0.23847246170043945
2023-01-23 00:25:36.444412: step: 1808/526, loss: 0.06172237545251846
2023-01-23 00:25:37.579779: step: 1812/526, loss: 0.3944447338581085
2023-01-23 00:25:38.693306: step: 1816/526, loss: 0.059876300394535065
2023-01-23 00:25:39.852263: step: 1820/526, loss: 0.08906774967908859
2023-01-23 00:25:40.976890: step: 1824/526, loss: 0.033185675740242004
2023-01-23 00:25:42.135035: step: 1828/526, loss: 0.15181049704551697
2023-01-23 00:25:43.315749: step: 1832/526, loss: 0.04933585971593857
2023-01-23 00:25:44.450133: step: 1836/526, loss: 0.14813023805618286
2023-01-23 00:25:45.577657: step: 1840/526, loss: 0.17138242721557617
2023-01-23 00:25:46.760855: step: 1844/526, loss: 0.23095454275608063
2023-01-23 00:25:47.900324: step: 1848/526, loss: 0.1301533728837967
2023-01-23 00:25:49.021020: step: 1852/526, loss: 0.10752621293067932
2023-01-23 00:25:50.152522: step: 1856/526, loss: 0.15956458449363708
2023-01-23 00:25:51.305963: step: 1860/526, loss: 0.20112381875514984
2023-01-23 00:25:52.437908: step: 1864/526, loss: 0.11384125053882599
2023-01-23 00:25:53.577054: step: 1868/526, loss: 0.18870334327220917
2023-01-23 00:25:54.716579: step: 1872/526, loss: 0.186344712972641
2023-01-23 00:25:55.863157: step: 1876/526, loss: 0.120759516954422
2023-01-23 00:25:56.995755: step: 1880/526, loss: 1.128904104232788
2023-01-23 00:25:58.141877: step: 1884/526, loss: 0.05447559431195259
2023-01-23 00:25:59.262648: step: 1888/526, loss: 0.2696797549724579
2023-01-23 00:26:00.391239: step: 1892/526, loss: 0.07769393920898438
2023-01-23 00:26:01.518317: step: 1896/526, loss: 0.1314132809638977
2023-01-23 00:26:02.652998: step: 1900/526, loss: 0.613822340965271
2023-01-23 00:26:03.793072: step: 1904/526, loss: 0.04486870765686035
2023-01-23 00:26:04.945126: step: 1908/526, loss: 1.2491724491119385
2023-01-23 00:26:06.084700: step: 1912/526, loss: 0.535128116607666
2023-01-23 00:26:07.248405: step: 1916/526, loss: 0.37151986360549927
2023-01-23 00:26:08.388652: step: 1920/526, loss: 0.7147814035415649
2023-01-23 00:26:09.542306: step: 1924/526, loss: 0.306810200214386
2023-01-23 00:26:10.687236: step: 1928/526, loss: 0.019554901868104935
2023-01-23 00:26:11.805786: step: 1932/526, loss: 0.32457178831100464
2023-01-23 00:26:12.924349: step: 1936/526, loss: 0.17129212617874146
2023-01-23 00:26:14.059503: step: 1940/526, loss: 0.08126652240753174
2023-01-23 00:26:15.193639: step: 1944/526, loss: 0.10410746186971664
2023-01-23 00:26:16.323831: step: 1948/526, loss: 0.18546819686889648
2023-01-23 00:26:17.456190: step: 1952/526, loss: 0.10252432525157928
2023-01-23 00:26:18.588631: step: 1956/526, loss: 0.501430094242096
2023-01-23 00:26:19.718703: step: 1960/526, loss: 0.17966899275779724
2023-01-23 00:26:20.859762: step: 1964/526, loss: 0.09827251732349396
2023-01-23 00:26:21.993999: step: 1968/526, loss: 0.06325512379407883
2023-01-23 00:26:23.152546: step: 1972/526, loss: 0.04881734773516655
2023-01-23 00:26:24.295146: step: 1976/526, loss: 0.30985507369041443
2023-01-23 00:26:25.450380: step: 1980/526, loss: 0.16137337684631348
2023-01-23 00:26:26.575530: step: 1984/526, loss: 0.6488516926765442
2023-01-23 00:26:27.709883: step: 1988/526, loss: 0.1319808065891266
2023-01-23 00:26:28.845095: step: 1992/526, loss: 0.09083929657936096
2023-01-23 00:26:30.006483: step: 1996/526, loss: 0.10225944966077805
2023-01-23 00:26:31.148004: step: 2000/526, loss: 0.041106320917606354
2023-01-23 00:26:32.268260: step: 2004/526, loss: 0.1926548033952713
2023-01-23 00:26:33.412909: step: 2008/526, loss: 0.1910114288330078
2023-01-23 00:26:34.542871: step: 2012/526, loss: 0.12288536876440048
2023-01-23 00:26:35.702733: step: 2016/526, loss: 0.02734251134097576
2023-01-23 00:26:36.850166: step: 2020/526, loss: 2.473437547683716
2023-01-23 00:26:38.018173: step: 2024/526, loss: 0.04134635999798775
2023-01-23 00:26:39.150427: step: 2028/526, loss: 0.2366454154253006
2023-01-23 00:26:40.290715: step: 2032/526, loss: 0.06661701202392578
2023-01-23 00:26:41.448577: step: 2036/526, loss: 0.148019939661026
2023-01-23 00:26:42.582842: step: 2040/526, loss: 0.030071640387177467
2023-01-23 00:26:43.730423: step: 2044/526, loss: 0.1777830272912979
2023-01-23 00:26:44.874436: step: 2048/526, loss: 0.21318073570728302
2023-01-23 00:26:45.994413: step: 2052/526, loss: 0.06619720160961151
2023-01-23 00:26:47.146418: step: 2056/526, loss: 0.07484984397888184
2023-01-23 00:26:48.284008: step: 2060/526, loss: 0.02998533472418785
2023-01-23 00:26:49.404931: step: 2064/526, loss: 0.03785824775695801
2023-01-23 00:26:50.551707: step: 2068/526, loss: 0.08734522014856339
2023-01-23 00:26:51.679391: step: 2072/526, loss: 0.13103142380714417
2023-01-23 00:26:52.815553: step: 2076/526, loss: 0.1434842050075531
2023-01-23 00:26:53.933387: step: 2080/526, loss: 0.03428039699792862
2023-01-23 00:26:55.079832: step: 2084/526, loss: 0.03596749156713486
2023-01-23 00:26:56.218746: step: 2088/526, loss: 1.0822758674621582
2023-01-23 00:26:57.345200: step: 2092/526, loss: 0.0823885053396225
2023-01-23 00:26:58.447252: step: 2096/526, loss: 0.06300631165504456
2023-01-23 00:26:59.617481: step: 2100/526, loss: 0.11963353306055069
2023-01-23 00:27:00.738530: step: 2104/526, loss: 0.05372738838195801
==================================================
Loss: 0.268
--------------------
Dev: {'event': {'p': 0.5482954545454546, 'r': 0.7709720372836218, 'f1': 0.6408411732152739}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Test: {'event': {'p': 0.584652862362972, 'r': 0.7515657620041754, 'f1': 0.6576844028316966}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Chinese: {'event': {'p': 0.5595238095238095, 'r': 0.8703703703703703, 'f1': 0.6811594202898551}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Korean: {'event': {'p': 0.5689655172413793, 'r': 0.5238095238095238, 'f1': 0.5454545454545455}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Russian: {'event': {'p': 0.3902439024390244, 'r': 0.4444444444444444, 'f1': 0.4155844155844156}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6604010025062657, 'r': 0.7017310252996005, 'f1': 0.6804389928986443}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Eng Test for Chinese: {'event': {'p': 0.6480836236933798, 'r': 0.6795407098121086, 'f1': 0.6634394904458599}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Sample Chinese: {'event': {'p': 0.6323529411764706, 'r': 0.7962962962962963, 'f1': 0.7049180327868853}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5563041385948027, 'r': 0.7696404793608522, 'f1': 0.6458100558659218}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Eng Test for Korean: {'event': {'p': 0.5336806847785635, 'r': 0.7484342379958246, 'f1': 0.6230719096241583}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Sample Korean: {'event': {'p': 0.5932203389830508, 'r': 0.5555555555555556, 'f1': 0.5737704918032787}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5563041385948027, 'r': 0.7696404793608522, 'f1': 0.6458100558659218}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Eng Test for Russian: {'event': {'p': 0.5336806847785635, 'r': 0.7484342379958246, 'f1': 0.6230719096241583}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Sample Russian: {'event': {'p': 0.5116279069767442, 'r': 0.6111111111111112, 'f1': 0.5569620253164557}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
******************************
Epoch: 6
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 00:27:44.143633: step: 4/526, loss: 0.1935199648141861
2023-01-23 00:27:45.264442: step: 8/526, loss: 0.053366661071777344
2023-01-23 00:27:46.413485: step: 12/526, loss: 0.09214058518409729
2023-01-23 00:27:47.552429: step: 16/526, loss: 0.05108308792114258
2023-01-23 00:27:48.686264: step: 20/526, loss: 0.16564340889453888
2023-01-23 00:27:49.819046: step: 24/526, loss: 0.12585657835006714
2023-01-23 00:27:50.971614: step: 28/526, loss: 0.0700259655714035
2023-01-23 00:27:52.098241: step: 32/526, loss: 0.04057908058166504
2023-01-23 00:27:53.258656: step: 36/526, loss: 0.27317723631858826
2023-01-23 00:27:54.441347: step: 40/526, loss: 0.10032758116722107
2023-01-23 00:27:55.578055: step: 44/526, loss: 0.1474703848361969
2023-01-23 00:27:56.707525: step: 48/526, loss: 0.10151688009500504
2023-01-23 00:27:57.841640: step: 52/526, loss: 0.06741821765899658
2023-01-23 00:27:58.982090: step: 56/526, loss: 0.08254604786634445
2023-01-23 00:28:00.111458: step: 60/526, loss: 0.09099225699901581
2023-01-23 00:28:01.224615: step: 64/526, loss: 0.13013902306556702
2023-01-23 00:28:02.354790: step: 68/526, loss: 0.1279090940952301
2023-01-23 00:28:03.510092: step: 72/526, loss: 0.3624299168586731
2023-01-23 00:28:04.627452: step: 76/526, loss: 1.7218503952026367
2023-01-23 00:28:05.787214: step: 80/526, loss: 0.17056140303611755
2023-01-23 00:28:06.979704: step: 84/526, loss: 0.10572975873947144
2023-01-23 00:28:08.113907: step: 88/526, loss: 0.10263185948133469
2023-01-23 00:28:09.264464: step: 92/526, loss: 0.09498701244592667
2023-01-23 00:28:10.381577: step: 96/526, loss: 0.14327764511108398
2023-01-23 00:28:11.519545: step: 100/526, loss: 0.2205335646867752
2023-01-23 00:28:12.652220: step: 104/526, loss: 0.43257367610931396
2023-01-23 00:28:13.781919: step: 108/526, loss: 0.23544475436210632
2023-01-23 00:28:14.948288: step: 112/526, loss: 0.06714353710412979
2023-01-23 00:28:16.142194: step: 116/526, loss: 0.20405682921409607
2023-01-23 00:28:17.272775: step: 120/526, loss: 0.12117824703454971
2023-01-23 00:28:18.429276: step: 124/526, loss: 0.23634929955005646
2023-01-23 00:28:19.568900: step: 128/526, loss: 0.11167869716882706
2023-01-23 00:28:20.712156: step: 132/526, loss: 0.7614037990570068
2023-01-23 00:28:21.858178: step: 136/526, loss: 0.0993494987487793
2023-01-23 00:28:23.018236: step: 140/526, loss: 0.04996833950281143
2023-01-23 00:28:24.168012: step: 144/526, loss: 0.14071054756641388
2023-01-23 00:28:25.281049: step: 148/526, loss: 0.04061935096979141
2023-01-23 00:28:26.431502: step: 152/526, loss: 0.4921053647994995
2023-01-23 00:28:27.555316: step: 156/526, loss: 0.3915863037109375
2023-01-23 00:28:28.717422: step: 160/526, loss: 0.047487977892160416
2023-01-23 00:28:29.851326: step: 164/526, loss: 0.12497777491807938
2023-01-23 00:28:30.982059: step: 168/526, loss: 0.031023599207401276
2023-01-23 00:28:32.135174: step: 172/526, loss: 0.061802055686712265
2023-01-23 00:28:33.311782: step: 176/526, loss: 0.12532693147659302
2023-01-23 00:28:34.464992: step: 180/526, loss: 0.08658051490783691
2023-01-23 00:28:35.618439: step: 184/526, loss: 0.08162536472082138
2023-01-23 00:28:36.730409: step: 188/526, loss: 0.12107090651988983
2023-01-23 00:28:37.924573: step: 192/526, loss: 0.33039236068725586
2023-01-23 00:28:39.054910: step: 196/526, loss: 0.4681624174118042
2023-01-23 00:28:40.208046: step: 200/526, loss: 0.19839076697826385
2023-01-23 00:28:41.328541: step: 204/526, loss: 0.13721294701099396
2023-01-23 00:28:42.472052: step: 208/526, loss: 0.1353965401649475
2023-01-23 00:28:43.628163: step: 212/526, loss: 0.05025773122906685
2023-01-23 00:28:44.779900: step: 216/526, loss: 0.8137813806533813
2023-01-23 00:28:45.905562: step: 220/526, loss: 0.05085926130414009
2023-01-23 00:28:47.038747: step: 224/526, loss: 0.08609800785779953
2023-01-23 00:28:48.192692: step: 228/526, loss: 0.041141461580991745
2023-01-23 00:28:49.316627: step: 232/526, loss: 0.13425445556640625
2023-01-23 00:28:50.469795: step: 236/526, loss: 0.17219281196594238
2023-01-23 00:28:51.587166: step: 240/526, loss: 0.28969812393188477
2023-01-23 00:28:52.720530: step: 244/526, loss: 0.12828321754932404
2023-01-23 00:28:53.829437: step: 248/526, loss: 0.21680259704589844
2023-01-23 00:28:54.943064: step: 252/526, loss: 0.5963222980499268
2023-01-23 00:28:56.071710: step: 256/526, loss: 0.14127665758132935
2023-01-23 00:28:57.206347: step: 260/526, loss: 0.40478143095970154
2023-01-23 00:28:58.313952: step: 264/526, loss: 0.022491455078125
2023-01-23 00:28:59.780192: step: 268/526, loss: 0.14795736968517303
2023-01-23 00:29:00.898821: step: 272/526, loss: 0.2272837609052658
2023-01-23 00:29:02.055331: step: 276/526, loss: 0.14946284890174866
2023-01-23 00:29:03.218700: step: 280/526, loss: 0.09964227676391602
2023-01-23 00:29:04.348307: step: 284/526, loss: 0.14771641790866852
2023-01-23 00:29:05.506652: step: 288/526, loss: 0.03897056728601456
2023-01-23 00:29:06.639356: step: 292/526, loss: 0.29770296812057495
2023-01-23 00:29:07.752441: step: 296/526, loss: 0.21242466568946838
2023-01-23 00:29:08.893064: step: 300/526, loss: 0.041317179799079895
2023-01-23 00:29:10.022170: step: 304/526, loss: 0.0701996311545372
2023-01-23 00:29:11.154440: step: 308/526, loss: 0.29508471488952637
2023-01-23 00:29:12.276877: step: 312/526, loss: 0.29923582077026367
2023-01-23 00:29:13.391987: step: 316/526, loss: 0.04200158268213272
2023-01-23 00:29:14.502400: step: 320/526, loss: 0.3863620162010193
2023-01-23 00:29:15.617164: step: 324/526, loss: 0.0825316458940506
2023-01-23 00:29:16.740500: step: 328/526, loss: 0.21170654892921448
2023-01-23 00:29:17.899761: step: 332/526, loss: 0.13917456567287445
2023-01-23 00:29:19.047114: step: 336/526, loss: 0.28148922324180603
2023-01-23 00:29:20.181716: step: 340/526, loss: 0.10612602531909943
2023-01-23 00:29:21.296059: step: 344/526, loss: 0.03621101379394531
2023-01-23 00:29:22.410089: step: 348/526, loss: 0.04159374162554741
2023-01-23 00:29:23.551366: step: 352/526, loss: 0.09239482879638672
2023-01-23 00:29:24.708216: step: 356/526, loss: 0.2786267399787903
2023-01-23 00:29:25.843582: step: 360/526, loss: 0.019766712561249733
2023-01-23 00:29:27.000459: step: 364/526, loss: 0.08411598205566406
2023-01-23 00:29:28.126361: step: 368/526, loss: 0.12203660607337952
2023-01-23 00:29:29.278147: step: 372/526, loss: 0.2746692895889282
2023-01-23 00:29:30.436645: step: 376/526, loss: 0.030750369653105736
2023-01-23 00:29:31.555243: step: 380/526, loss: 0.08497676998376846
2023-01-23 00:29:32.693329: step: 384/526, loss: 0.04459733888506889
2023-01-23 00:29:33.808619: step: 388/526, loss: 0.06859102100133896
2023-01-23 00:29:34.941185: step: 392/526, loss: 0.08576574921607971
2023-01-23 00:29:36.084558: step: 396/526, loss: 0.2812884449958801
2023-01-23 00:29:37.219901: step: 400/526, loss: 0.39120596647262573
2023-01-23 00:29:38.334532: step: 404/526, loss: 0.03319845348596573
2023-01-23 00:29:39.463718: step: 408/526, loss: 0.31789249181747437
2023-01-23 00:29:40.599139: step: 412/526, loss: 0.16425448656082153
2023-01-23 00:29:41.736319: step: 416/526, loss: 0.07633178681135178
2023-01-23 00:29:42.915958: step: 420/526, loss: 0.1328599900007248
2023-01-23 00:29:44.043177: step: 424/526, loss: 0.17225494980812073
2023-01-23 00:29:45.174321: step: 428/526, loss: 0.024799346923828125
2023-01-23 00:29:46.319336: step: 432/526, loss: 0.0743323341012001
2023-01-23 00:29:47.440427: step: 436/526, loss: 0.048112429678440094
2023-01-23 00:29:48.593926: step: 440/526, loss: 0.10075311362743378
2023-01-23 00:29:49.751157: step: 444/526, loss: 0.06957521289587021
2023-01-23 00:29:50.891079: step: 448/526, loss: 0.05378551781177521
2023-01-23 00:29:52.010384: step: 452/526, loss: 0.01987457275390625
2023-01-23 00:29:53.129132: step: 456/526, loss: 0.34529200196266174
2023-01-23 00:29:54.223809: step: 460/526, loss: 0.1810527890920639
2023-01-23 00:29:55.333776: step: 464/526, loss: 0.18962498009204865
2023-01-23 00:29:56.441769: step: 468/526, loss: 0.27324995398521423
2023-01-23 00:29:57.584436: step: 472/526, loss: 0.1481439620256424
2023-01-23 00:29:58.738486: step: 476/526, loss: 0.0918925330042839
2023-01-23 00:29:59.881254: step: 480/526, loss: 0.0877266451716423
2023-01-23 00:30:01.034686: step: 484/526, loss: 0.06493854522705078
2023-01-23 00:30:02.182786: step: 488/526, loss: 0.03394820913672447
2023-01-23 00:30:03.316330: step: 492/526, loss: 0.08866987377405167
2023-01-23 00:30:04.449005: step: 496/526, loss: 0.14991122484207153
2023-01-23 00:30:05.589111: step: 500/526, loss: 0.20004349946975708
2023-01-23 00:30:06.818006: step: 504/526, loss: 0.0679527297616005
2023-01-23 00:30:07.960198: step: 508/526, loss: 0.10013322532176971
2023-01-23 00:30:09.077016: step: 512/526, loss: 0.21924495697021484
2023-01-23 00:30:10.191500: step: 516/526, loss: 0.060643672943115234
2023-01-23 00:30:11.307319: step: 520/526, loss: 0.01569042168557644
2023-01-23 00:30:12.500858: step: 524/526, loss: 0.16761493682861328
2023-01-23 00:30:13.677299: step: 528/526, loss: 0.02835388109087944
2023-01-23 00:30:14.816953: step: 532/526, loss: 0.19586822390556335
2023-01-23 00:30:15.957529: step: 536/526, loss: 0.03471088409423828
2023-01-23 00:30:17.122901: step: 540/526, loss: 0.20807743072509766
2023-01-23 00:30:18.278066: step: 544/526, loss: 0.028271447867155075
2023-01-23 00:30:19.418957: step: 548/526, loss: 0.08852767944335938
2023-01-23 00:30:20.537364: step: 552/526, loss: 0.11253197491168976
2023-01-23 00:30:21.660647: step: 556/526, loss: 0.13039885461330414
2023-01-23 00:30:22.793698: step: 560/526, loss: 0.23515664041042328
2023-01-23 00:30:23.924177: step: 564/526, loss: 0.1011715903878212
2023-01-23 00:30:25.086567: step: 568/526, loss: 0.14560852944850922
2023-01-23 00:30:26.218827: step: 572/526, loss: 0.5282018184661865
2023-01-23 00:30:27.352303: step: 576/526, loss: 0.0902009904384613
2023-01-23 00:30:28.476645: step: 580/526, loss: 0.008965587243437767
2023-01-23 00:30:29.567033: step: 584/526, loss: 0.08957748860120773
2023-01-23 00:30:30.708056: step: 588/526, loss: 0.3128474950790405
2023-01-23 00:30:31.831933: step: 592/526, loss: 0.027715492993593216
2023-01-23 00:30:32.968730: step: 596/526, loss: 0.05699920654296875
2023-01-23 00:30:34.109957: step: 600/526, loss: 0.04225330427289009
2023-01-23 00:30:35.240592: step: 604/526, loss: 0.06309624016284943
2023-01-23 00:30:36.379132: step: 608/526, loss: 0.15198016166687012
2023-01-23 00:30:37.518987: step: 612/526, loss: 0.30850622057914734
2023-01-23 00:30:38.645944: step: 616/526, loss: 0.03823041915893555
2023-01-23 00:30:39.765471: step: 620/526, loss: 0.45894908905029297
2023-01-23 00:30:40.884890: step: 624/526, loss: 0.16934317350387573
2023-01-23 00:30:42.032110: step: 628/526, loss: 0.23666810989379883
2023-01-23 00:30:43.175592: step: 632/526, loss: 0.02895507961511612
2023-01-23 00:30:44.293244: step: 636/526, loss: 0.10448131710290909
2023-01-23 00:30:45.439116: step: 640/526, loss: 0.14572878181934357
2023-01-23 00:30:46.553984: step: 644/526, loss: 0.3547572195529938
2023-01-23 00:30:47.712145: step: 648/526, loss: 0.010396289639174938
2023-01-23 00:30:48.847012: step: 652/526, loss: 0.12235183268785477
2023-01-23 00:30:50.000633: step: 656/526, loss: 0.03808736801147461
2023-01-23 00:30:51.125717: step: 660/526, loss: 0.10837996006011963
2023-01-23 00:30:52.267506: step: 664/526, loss: 0.10509152710437775
2023-01-23 00:30:53.391935: step: 668/526, loss: 0.37106457352638245
2023-01-23 00:30:54.543882: step: 672/526, loss: 0.08305959403514862
2023-01-23 00:30:55.687906: step: 676/526, loss: 0.3925187289714813
2023-01-23 00:30:56.856396: step: 680/526, loss: 0.2616066336631775
2023-01-23 00:30:58.005760: step: 684/526, loss: 0.0772009864449501
2023-01-23 00:30:59.154316: step: 688/526, loss: 1.1067917346954346
2023-01-23 00:31:00.294701: step: 692/526, loss: 0.03790278360247612
2023-01-23 00:31:01.453462: step: 696/526, loss: 0.04826851189136505
2023-01-23 00:31:02.582799: step: 700/526, loss: 0.21131621301174164
2023-01-23 00:31:03.714685: step: 704/526, loss: 0.3306438624858856
2023-01-23 00:31:04.836829: step: 708/526, loss: 0.398441880941391
2023-01-23 00:31:06.006469: step: 712/526, loss: 0.12625399231910706
2023-01-23 00:31:07.134523: step: 716/526, loss: 0.06526875495910645
2023-01-23 00:31:08.261406: step: 720/526, loss: 0.09623154997825623
2023-01-23 00:31:09.396723: step: 724/526, loss: 0.05037336423993111
2023-01-23 00:31:10.550862: step: 728/526, loss: 0.0637001097202301
2023-01-23 00:31:11.691459: step: 732/526, loss: 1.1518621444702148
2023-01-23 00:31:12.853577: step: 736/526, loss: 0.1728355586528778
2023-01-23 00:31:14.037553: step: 740/526, loss: 0.039498139172792435
2023-01-23 00:31:15.170485: step: 744/526, loss: 0.14737872779369354
2023-01-23 00:31:16.288989: step: 748/526, loss: 0.3067273199558258
2023-01-23 00:31:17.409391: step: 752/526, loss: 0.17174334824085236
2023-01-23 00:31:18.563611: step: 756/526, loss: 0.06000871583819389
2023-01-23 00:31:19.689866: step: 760/526, loss: 0.22411632537841797
2023-01-23 00:31:20.812620: step: 764/526, loss: 0.08788815140724182
2023-01-23 00:31:21.929239: step: 768/526, loss: 0.15324965119361877
2023-01-23 00:31:23.055184: step: 772/526, loss: 0.08564749360084534
2023-01-23 00:31:24.193376: step: 776/526, loss: 0.08029551804065704
2023-01-23 00:31:25.357394: step: 780/526, loss: 0.22256916761398315
2023-01-23 00:31:26.486076: step: 784/526, loss: 0.04142565652728081
2023-01-23 00:31:27.612048: step: 788/526, loss: 0.013770533725619316
2023-01-23 00:31:28.710021: step: 792/526, loss: 0.1091160774230957
2023-01-23 00:31:29.824369: step: 796/526, loss: 0.17877742648124695
2023-01-23 00:31:30.969140: step: 800/526, loss: 0.23655076324939728
2023-01-23 00:31:32.101250: step: 804/526, loss: 0.151583731174469
2023-01-23 00:31:33.240464: step: 808/526, loss: 0.0842476338148117
2023-01-23 00:31:34.379335: step: 812/526, loss: 0.12497062981128693
2023-01-23 00:31:35.486829: step: 816/526, loss: 0.04380984231829643
2023-01-23 00:31:36.630643: step: 820/526, loss: 0.16521388292312622
2023-01-23 00:31:37.787768: step: 824/526, loss: 0.08629884570837021
2023-01-23 00:31:38.949455: step: 828/526, loss: 0.08899412304162979
2023-01-23 00:31:40.083245: step: 832/526, loss: 0.25268885493278503
2023-01-23 00:31:41.214772: step: 836/526, loss: 0.04107518121600151
2023-01-23 00:31:42.351360: step: 840/526, loss: 0.17141857743263245
2023-01-23 00:31:43.474396: step: 844/526, loss: 0.056225232779979706
2023-01-23 00:31:44.604224: step: 848/526, loss: 0.21195407211780548
2023-01-23 00:31:45.759537: step: 852/526, loss: 0.13661302626132965
2023-01-23 00:31:46.891378: step: 856/526, loss: 0.11779718101024628
2023-01-23 00:31:48.020158: step: 860/526, loss: 0.10724586993455887
2023-01-23 00:31:49.160988: step: 864/526, loss: 0.17789001762866974
2023-01-23 00:31:50.280139: step: 868/526, loss: 0.07723245769739151
2023-01-23 00:31:51.435801: step: 872/526, loss: 0.12877464294433594
2023-01-23 00:31:52.583181: step: 876/526, loss: 0.1516997516155243
2023-01-23 00:31:53.725015: step: 880/526, loss: 0.08661232143640518
2023-01-23 00:31:54.866961: step: 884/526, loss: 0.20451012253761292
2023-01-23 00:31:55.994421: step: 888/526, loss: 0.031790636479854584
2023-01-23 00:31:57.165895: step: 892/526, loss: 0.2826294004917145
2023-01-23 00:31:58.311093: step: 896/526, loss: 0.3116837739944458
2023-01-23 00:31:59.447709: step: 900/526, loss: 0.020956754684448242
2023-01-23 00:32:00.577147: step: 904/526, loss: 0.15053005516529083
2023-01-23 00:32:01.701991: step: 908/526, loss: 0.044760704040527344
2023-01-23 00:32:02.857080: step: 912/526, loss: 0.4009353518486023
2023-01-23 00:32:04.008990: step: 916/526, loss: 0.4486294686794281
2023-01-23 00:32:05.120349: step: 920/526, loss: 0.06704731285572052
2023-01-23 00:32:06.240108: step: 924/526, loss: 0.08138275146484375
2023-01-23 00:32:07.349080: step: 928/526, loss: 0.060701943933963776
2023-01-23 00:32:08.448722: step: 932/526, loss: 0.17838707566261292
2023-01-23 00:32:09.593432: step: 936/526, loss: 0.1150943711400032
2023-01-23 00:32:10.701363: step: 940/526, loss: 0.08999890834093094
2023-01-23 00:32:11.808186: step: 944/526, loss: 0.07424888759851456
2023-01-23 00:32:12.940142: step: 948/526, loss: 0.10326433181762695
2023-01-23 00:32:14.089318: step: 952/526, loss: 0.1869238018989563
2023-01-23 00:32:15.209038: step: 956/526, loss: 0.13016529381275177
2023-01-23 00:32:16.368662: step: 960/526, loss: 0.0988527312874794
2023-01-23 00:32:17.504554: step: 964/526, loss: 0.23519906401634216
2023-01-23 00:32:18.615914: step: 968/526, loss: 0.08537960052490234
2023-01-23 00:32:19.763829: step: 972/526, loss: 0.1011384055018425
2023-01-23 00:32:20.910491: step: 976/526, loss: 0.04553098976612091
2023-01-23 00:32:22.069609: step: 980/526, loss: 0.0717797800898552
2023-01-23 00:32:23.219262: step: 984/526, loss: 0.18373413383960724
2023-01-23 00:32:24.344574: step: 988/526, loss: 0.11869249492883682
2023-01-23 00:32:25.465198: step: 992/526, loss: 0.07695799320936203
2023-01-23 00:32:26.642345: step: 996/526, loss: 0.034386828541755676
2023-01-23 00:32:27.769059: step: 1000/526, loss: 0.17930403351783752
2023-01-23 00:32:28.930101: step: 1004/526, loss: 1.1596510410308838
2023-01-23 00:32:30.055298: step: 1008/526, loss: 0.06212444230914116
2023-01-23 00:32:31.169271: step: 1012/526, loss: 0.06146228685975075
2023-01-23 00:32:32.301261: step: 1016/526, loss: 0.029346086084842682
2023-01-23 00:32:33.430722: step: 1020/526, loss: 0.27891793847084045
2023-01-23 00:32:34.562739: step: 1024/526, loss: 0.8286097049713135
2023-01-23 00:32:35.700116: step: 1028/526, loss: 0.1077735424041748
2023-01-23 00:32:36.845342: step: 1032/526, loss: 0.3889457583427429
2023-01-23 00:32:37.989484: step: 1036/526, loss: 0.10716943442821503
2023-01-23 00:32:39.127587: step: 1040/526, loss: 0.05354709550738335
2023-01-23 00:32:40.284747: step: 1044/526, loss: 0.0801825076341629
2023-01-23 00:32:41.402779: step: 1048/526, loss: 0.24855437874794006
2023-01-23 00:32:42.513389: step: 1052/526, loss: 0.15052232146263123
2023-01-23 00:32:43.638191: step: 1056/526, loss: 0.26865842938423157
2023-01-23 00:32:44.749148: step: 1060/526, loss: 0.10129585862159729
2023-01-23 00:32:45.898423: step: 1064/526, loss: 0.2093355655670166
2023-01-23 00:32:47.053000: step: 1068/526, loss: 0.19879885017871857
2023-01-23 00:32:48.206411: step: 1072/526, loss: 0.2345268428325653
2023-01-23 00:32:49.337436: step: 1076/526, loss: 0.23189297318458557
2023-01-23 00:32:50.466282: step: 1080/526, loss: 0.2789713442325592
2023-01-23 00:32:51.610008: step: 1084/526, loss: 0.09879694133996964
2023-01-23 00:32:52.744881: step: 1088/526, loss: 0.1386704444885254
2023-01-23 00:32:53.874160: step: 1092/526, loss: 0.1418129950761795
2023-01-23 00:32:55.028373: step: 1096/526, loss: 0.19827881455421448
2023-01-23 00:32:56.155182: step: 1100/526, loss: 0.03734779357910156
2023-01-23 00:32:57.260799: step: 1104/526, loss: 0.16050490736961365
2023-01-23 00:32:58.406531: step: 1108/526, loss: 0.06221742555499077
2023-01-23 00:32:59.541001: step: 1112/526, loss: 0.11807861179113388
2023-01-23 00:33:00.693744: step: 1116/526, loss: 0.1265970766544342
2023-01-23 00:33:01.812284: step: 1120/526, loss: 0.05973844602704048
2023-01-23 00:33:02.939214: step: 1124/526, loss: 0.04374570772051811
2023-01-23 00:33:04.060718: step: 1128/526, loss: 0.40221673250198364
2023-01-23 00:33:05.193321: step: 1132/526, loss: 0.057587288320064545
2023-01-23 00:33:06.345720: step: 1136/526, loss: 0.07253055274486542
2023-01-23 00:33:07.510846: step: 1140/526, loss: 0.5135291814804077
2023-01-23 00:33:08.647539: step: 1144/526, loss: 0.0750647485256195
2023-01-23 00:33:09.771749: step: 1148/526, loss: 0.23290835320949554
2023-01-23 00:33:10.884072: step: 1152/526, loss: 0.030810022726655006
2023-01-23 00:33:12.007577: step: 1156/526, loss: 0.24512425065040588
2023-01-23 00:33:13.176244: step: 1160/526, loss: 0.09919628500938416
2023-01-23 00:33:14.291644: step: 1164/526, loss: 0.09027914702892303
2023-01-23 00:33:15.452959: step: 1168/526, loss: 0.04261169582605362
2023-01-23 00:33:16.639083: step: 1172/526, loss: 0.09574628621339798
2023-01-23 00:33:17.746087: step: 1176/526, loss: 0.13626104593276978
2023-01-23 00:33:18.915599: step: 1180/526, loss: 0.5341628193855286
2023-01-23 00:33:20.064100: step: 1184/526, loss: 0.7170593738555908
2023-01-23 00:33:21.182519: step: 1188/526, loss: 0.11014915257692337
2023-01-23 00:33:22.344244: step: 1192/526, loss: 0.2766742408275604
2023-01-23 00:33:23.527772: step: 1196/526, loss: 0.046143628656864166
2023-01-23 00:33:24.680875: step: 1200/526, loss: 0.07663488388061523
2023-01-23 00:33:25.810529: step: 1204/526, loss: 0.04668016731739044
2023-01-23 00:33:26.949631: step: 1208/526, loss: 0.07996115833520889
2023-01-23 00:33:28.091089: step: 1212/526, loss: 0.033505868166685104
2023-01-23 00:33:29.270425: step: 1216/526, loss: 0.3432506322860718
2023-01-23 00:33:30.417134: step: 1220/526, loss: 0.05837153270840645
2023-01-23 00:33:31.543392: step: 1224/526, loss: 0.04403328895568848
2023-01-23 00:33:32.675783: step: 1228/526, loss: 0.39112210273742676
2023-01-23 00:33:33.822162: step: 1232/526, loss: 0.13740229606628418
2023-01-23 00:33:34.979218: step: 1236/526, loss: 0.8640855550765991
2023-01-23 00:33:36.135293: step: 1240/526, loss: 0.11695460975170135
2023-01-23 00:33:37.332208: step: 1244/526, loss: 0.04489259794354439
2023-01-23 00:33:38.479365: step: 1248/526, loss: 0.09422874450683594
2023-01-23 00:33:39.597568: step: 1252/526, loss: 0.06230144202709198
2023-01-23 00:33:40.758956: step: 1256/526, loss: 1.684261679649353
2023-01-23 00:33:41.872071: step: 1260/526, loss: 0.05754508823156357
2023-01-23 00:33:42.985412: step: 1264/526, loss: 0.12799835205078125
2023-01-23 00:33:44.139089: step: 1268/526, loss: 0.04727745056152344
2023-01-23 00:33:45.286416: step: 1272/526, loss: 0.12582802772521973
2023-01-23 00:33:46.456425: step: 1276/526, loss: 0.23694530129432678
2023-01-23 00:33:47.587806: step: 1280/526, loss: 0.7765634059906006
2023-01-23 00:33:48.706473: step: 1284/526, loss: 0.07010293006896973
2023-01-23 00:33:49.849971: step: 1288/526, loss: 0.12948857247829437
2023-01-23 00:33:51.005880: step: 1292/526, loss: 1.0716722011566162
2023-01-23 00:33:52.124434: step: 1296/526, loss: 0.3529067933559418
2023-01-23 00:33:53.270879: step: 1300/526, loss: 0.08829350769519806
2023-01-23 00:33:54.367222: step: 1304/526, loss: 0.14155983924865723
2023-01-23 00:33:55.491479: step: 1308/526, loss: 0.05764905363321304
2023-01-23 00:33:56.645237: step: 1312/526, loss: 0.18648245930671692
2023-01-23 00:33:57.768954: step: 1316/526, loss: 0.16608795523643494
2023-01-23 00:33:58.894353: step: 1320/526, loss: 0.058429718017578125
2023-01-23 00:34:00.023750: step: 1324/526, loss: 1.1081345081329346
2023-01-23 00:34:01.181986: step: 1328/526, loss: 0.05601778253912926
2023-01-23 00:34:02.310431: step: 1332/526, loss: 0.1123056411743164
2023-01-23 00:34:03.484502: step: 1336/526, loss: 0.21761107444763184
2023-01-23 00:34:04.618251: step: 1340/526, loss: 0.12184090912342072
2023-01-23 00:34:05.754521: step: 1344/526, loss: 0.05934043228626251
2023-01-23 00:34:06.873156: step: 1348/526, loss: 0.3498401641845703
2023-01-23 00:34:08.016475: step: 1352/526, loss: 0.057191941887140274
2023-01-23 00:34:09.163053: step: 1356/526, loss: 0.1820422112941742
2023-01-23 00:34:10.306634: step: 1360/526, loss: 0.2146422266960144
2023-01-23 00:34:11.429664: step: 1364/526, loss: 0.06824059784412384
2023-01-23 00:34:12.531344: step: 1368/526, loss: 0.3996272087097168
2023-01-23 00:34:13.680582: step: 1372/526, loss: 0.13198700547218323
2023-01-23 00:34:14.840328: step: 1376/526, loss: 0.08759908378124237
2023-01-23 00:34:15.969666: step: 1380/526, loss: 0.09477319568395615
2023-01-23 00:34:17.083297: step: 1384/526, loss: 0.03702554851770401
2023-01-23 00:34:18.221008: step: 1388/526, loss: 0.040091514587402344
2023-01-23 00:34:19.368212: step: 1392/526, loss: 0.0537782683968544
2023-01-23 00:34:20.496894: step: 1396/526, loss: 0.30851611495018005
2023-01-23 00:34:21.632052: step: 1400/526, loss: 0.077253058552742
2023-01-23 00:34:22.735317: step: 1404/526, loss: 0.12993822991847992
2023-01-23 00:34:23.885855: step: 1408/526, loss: 0.027674105018377304
2023-01-23 00:34:25.014008: step: 1412/526, loss: 0.458151638507843
2023-01-23 00:34:26.154181: step: 1416/526, loss: 0.20200443267822266
2023-01-23 00:34:27.316803: step: 1420/526, loss: 0.08398628234863281
2023-01-23 00:34:28.462195: step: 1424/526, loss: 0.1619892120361328
2023-01-23 00:34:29.587213: step: 1428/526, loss: 0.18240490555763245
2023-01-23 00:34:30.711895: step: 1432/526, loss: 0.09315434098243713
2023-01-23 00:34:31.840685: step: 1436/526, loss: 0.14366689324378967
2023-01-23 00:34:33.010506: step: 1440/526, loss: 0.027073001489043236
2023-01-23 00:34:34.127542: step: 1444/526, loss: 0.03297267109155655
2023-01-23 00:34:35.239717: step: 1448/526, loss: 0.05766334757208824
2023-01-23 00:34:36.414346: step: 1452/526, loss: 0.11763410270214081
2023-01-23 00:34:37.578557: step: 1456/526, loss: 0.1841091513633728
2023-01-23 00:34:38.685230: step: 1460/526, loss: 0.09012174606323242
2023-01-23 00:34:39.810542: step: 1464/526, loss: 0.1229579895734787
2023-01-23 00:34:40.939092: step: 1468/526, loss: 0.22106781601905823
2023-01-23 00:34:42.098838: step: 1472/526, loss: 0.03912201151251793
2023-01-23 00:34:43.248094: step: 1476/526, loss: 0.08545112609863281
2023-01-23 00:34:44.363664: step: 1480/526, loss: 0.29759687185287476
2023-01-23 00:34:45.480786: step: 1484/526, loss: 0.22104902565479279
2023-01-23 00:34:46.610364: step: 1488/526, loss: 0.1259743571281433
2023-01-23 00:34:47.727723: step: 1492/526, loss: 0.01933879964053631
2023-01-23 00:34:48.852150: step: 1496/526, loss: 0.4715174436569214
2023-01-23 00:34:49.981155: step: 1500/526, loss: 0.7592087984085083
2023-01-23 00:34:51.108425: step: 1504/526, loss: 0.24064360558986664
2023-01-23 00:34:52.236248: step: 1508/526, loss: 0.22151318192481995
2023-01-23 00:34:53.348769: step: 1512/526, loss: 0.21759772300720215
2023-01-23 00:34:54.490122: step: 1516/526, loss: 0.689658522605896
2023-01-23 00:34:55.618474: step: 1520/526, loss: 0.1900985836982727
2023-01-23 00:34:56.793914: step: 1524/526, loss: 0.2347254753112793
2023-01-23 00:34:57.927512: step: 1528/526, loss: 0.027950286865234375
2023-01-23 00:34:59.070668: step: 1532/526, loss: 0.049568794667720795
2023-01-23 00:35:00.226176: step: 1536/526, loss: 0.20738163590431213
2023-01-23 00:35:01.383625: step: 1540/526, loss: 0.13126210868358612
2023-01-23 00:35:02.555600: step: 1544/526, loss: 0.04920470714569092
2023-01-23 00:35:03.722555: step: 1548/526, loss: 0.0811530128121376
2023-01-23 00:35:04.841796: step: 1552/526, loss: 0.13413038849830627
2023-01-23 00:35:06.003980: step: 1556/526, loss: 0.2211053967475891
2023-01-23 00:35:07.135301: step: 1560/526, loss: 0.11402948200702667
2023-01-23 00:35:08.242542: step: 1564/526, loss: 0.052236318588256836
2023-01-23 00:35:09.405827: step: 1568/526, loss: 0.18630047142505646
2023-01-23 00:35:10.539186: step: 1572/526, loss: 0.0687480941414833
2023-01-23 00:35:11.660502: step: 1576/526, loss: 0.03628816828131676
2023-01-23 00:35:12.777827: step: 1580/526, loss: 0.052163124084472656
2023-01-23 00:35:13.900470: step: 1584/526, loss: 0.015277600847184658
2023-01-23 00:35:15.031234: step: 1588/526, loss: 0.08992882072925568
2023-01-23 00:35:16.201870: step: 1592/526, loss: 0.7267881631851196
2023-01-23 00:35:17.342777: step: 1596/526, loss: 0.028608275577425957
2023-01-23 00:35:18.475468: step: 1600/526, loss: 0.07127423584461212
2023-01-23 00:35:19.628138: step: 1604/526, loss: 0.07827906310558319
2023-01-23 00:35:20.771021: step: 1608/526, loss: 0.09033241868019104
2023-01-23 00:35:21.919050: step: 1612/526, loss: 0.19561472535133362
2023-01-23 00:35:23.063449: step: 1616/526, loss: 0.10225506126880646
2023-01-23 00:35:24.186994: step: 1620/526, loss: 0.15876071155071259
2023-01-23 00:35:25.339259: step: 1624/526, loss: 0.1647598296403885
2023-01-23 00:35:26.544428: step: 1628/526, loss: 1.0362557172775269
2023-01-23 00:35:27.681511: step: 1632/526, loss: 0.08430089801549911
2023-01-23 00:35:28.799756: step: 1636/526, loss: 0.06773605942726135
2023-01-23 00:35:29.939391: step: 1640/526, loss: 0.12646789848804474
2023-01-23 00:35:31.077501: step: 1644/526, loss: 0.13007886707782745
2023-01-23 00:35:32.227217: step: 1648/526, loss: 0.08169527351856232
2023-01-23 00:35:33.359819: step: 1652/526, loss: 0.013237333856523037
2023-01-23 00:35:34.469721: step: 1656/526, loss: 0.044371794909238815
2023-01-23 00:35:35.658614: step: 1660/526, loss: 0.08450069278478622
2023-01-23 00:35:36.784095: step: 1664/526, loss: 0.16088305413722992
2023-01-23 00:35:37.905942: step: 1668/526, loss: 0.23504170775413513
2023-01-23 00:35:39.019882: step: 1672/526, loss: 0.059360697865486145
2023-01-23 00:35:40.144559: step: 1676/526, loss: 0.13032637536525726
2023-01-23 00:35:41.295214: step: 1680/526, loss: 0.12923890352249146
2023-01-23 00:35:42.432009: step: 1684/526, loss: 0.15137061476707458
2023-01-23 00:35:43.557775: step: 1688/526, loss: 0.10355682671070099
2023-01-23 00:35:44.695904: step: 1692/526, loss: 0.20478634536266327
2023-01-23 00:35:45.813291: step: 1696/526, loss: 0.026871968060731888
2023-01-23 00:35:46.931500: step: 1700/526, loss: 0.22027406096458435
2023-01-23 00:35:48.058949: step: 1704/526, loss: 0.20819568634033203
2023-01-23 00:35:49.211203: step: 1708/526, loss: 0.07477288693189621
2023-01-23 00:35:50.351432: step: 1712/526, loss: 0.1203809306025505
2023-01-23 00:35:51.499296: step: 1716/526, loss: 0.12176313996315002
2023-01-23 00:35:52.652014: step: 1720/526, loss: 0.11805567890405655
2023-01-23 00:35:53.781680: step: 1724/526, loss: 0.12193985283374786
2023-01-23 00:35:54.911691: step: 1728/526, loss: 0.13236084580421448
2023-01-23 00:35:56.054433: step: 1732/526, loss: 0.14280566573143005
2023-01-23 00:35:57.185627: step: 1736/526, loss: 0.13417492806911469
2023-01-23 00:35:58.324720: step: 1740/526, loss: 0.02441840060055256
2023-01-23 00:35:59.437401: step: 1744/526, loss: 0.0666445717215538
2023-01-23 00:36:00.560919: step: 1748/526, loss: 0.32476407289505005
2023-01-23 00:36:01.701477: step: 1752/526, loss: 0.18137098848819733
2023-01-23 00:36:02.835666: step: 1756/526, loss: 0.022738946601748466
2023-01-23 00:36:03.986101: step: 1760/526, loss: 0.16420021653175354
2023-01-23 00:36:05.128697: step: 1764/526, loss: 0.20444834232330322
2023-01-23 00:36:06.264412: step: 1768/526, loss: 0.175619974732399
2023-01-23 00:36:07.392098: step: 1772/526, loss: 0.10529603809118271
2023-01-23 00:36:08.527988: step: 1776/526, loss: 0.29934147000312805
2023-01-23 00:36:09.656801: step: 1780/526, loss: 0.03155786916613579
2023-01-23 00:36:10.778591: step: 1784/526, loss: 0.1482965052127838
2023-01-23 00:36:11.903246: step: 1788/526, loss: 0.05663476139307022
2023-01-23 00:36:13.075403: step: 1792/526, loss: 0.147626131772995
2023-01-23 00:36:14.187355: step: 1796/526, loss: 0.32595062255859375
2023-01-23 00:36:15.310827: step: 1800/526, loss: 0.1381494253873825
2023-01-23 00:36:16.461035: step: 1804/526, loss: 0.0920679122209549
2023-01-23 00:36:17.557103: step: 1808/526, loss: 0.02328047715127468
2023-01-23 00:36:18.710851: step: 1812/526, loss: 0.09933920204639435
2023-01-23 00:36:19.836821: step: 1816/526, loss: 0.1050751656293869
2023-01-23 00:36:20.960459: step: 1820/526, loss: 0.028495408594608307
2023-01-23 00:36:22.093832: step: 1824/526, loss: 0.20693102478981018
2023-01-23 00:36:23.217604: step: 1828/526, loss: 0.2184181958436966
2023-01-23 00:36:24.351460: step: 1832/526, loss: 0.13041381537914276
2023-01-23 00:36:25.480134: step: 1836/526, loss: 0.16703061759471893
2023-01-23 00:36:26.591664: step: 1840/526, loss: 1.2478207349777222
2023-01-23 00:36:27.713895: step: 1844/526, loss: 0.05235252529382706
2023-01-23 00:36:28.850916: step: 1848/526, loss: 0.08937931060791016
2023-01-23 00:36:29.981536: step: 1852/526, loss: 0.1811787486076355
2023-01-23 00:36:31.103622: step: 1856/526, loss: 0.23315058648586273
2023-01-23 00:36:32.237166: step: 1860/526, loss: 0.09772854298353195
2023-01-23 00:36:33.406718: step: 1864/526, loss: 0.24598237872123718
2023-01-23 00:36:34.587203: step: 1868/526, loss: 0.08545856177806854
2023-01-23 00:36:35.738101: step: 1872/526, loss: 0.01973877102136612
2023-01-23 00:36:36.895619: step: 1876/526, loss: 0.19826316833496094
2023-01-23 00:36:38.007650: step: 1880/526, loss: 0.03031148947775364
2023-01-23 00:36:39.128976: step: 1884/526, loss: 0.12070666253566742
2023-01-23 00:36:40.231894: step: 1888/526, loss: 0.05679841339588165
2023-01-23 00:36:41.357972: step: 1892/526, loss: 0.1682707816362381
2023-01-23 00:36:42.488957: step: 1896/526, loss: 0.04011411592364311
2023-01-23 00:36:43.641606: step: 1900/526, loss: 0.06990289688110352
2023-01-23 00:36:44.782363: step: 1904/526, loss: 0.2473526895046234
2023-01-23 00:36:45.932010: step: 1908/526, loss: 0.028064489364624023
2023-01-23 00:36:47.093709: step: 1912/526, loss: 0.04668784141540527
2023-01-23 00:36:48.247571: step: 1916/526, loss: 0.10080371052026749
2023-01-23 00:36:49.386450: step: 1920/526, loss: 0.07001761347055435
2023-01-23 00:36:50.517601: step: 1924/526, loss: 0.823540210723877
2023-01-23 00:36:51.647171: step: 1928/526, loss: 0.03893604502081871
2023-01-23 00:36:52.791953: step: 1932/526, loss: 0.11929807811975479
2023-01-23 00:36:53.945336: step: 1936/526, loss: 0.08397804200649261
2023-01-23 00:36:55.062680: step: 1940/526, loss: 0.034690700471401215
2023-01-23 00:36:56.202329: step: 1944/526, loss: 0.30808085203170776
2023-01-23 00:36:57.310454: step: 1948/526, loss: 0.06326466053724289
2023-01-23 00:36:58.461237: step: 1952/526, loss: 0.021103668957948685
2023-01-23 00:36:59.584708: step: 1956/526, loss: 0.06706027686595917
2023-01-23 00:37:00.727413: step: 1960/526, loss: 0.11220850795507431
2023-01-23 00:37:01.873581: step: 1964/526, loss: 0.14683294296264648
2023-01-23 00:37:03.027593: step: 1968/526, loss: 0.1673121452331543
2023-01-23 00:37:04.168671: step: 1972/526, loss: 0.017523478716611862
2023-01-23 00:37:05.291878: step: 1976/526, loss: 0.10771122574806213
2023-01-23 00:37:06.450397: step: 1980/526, loss: 0.11405238509178162
2023-01-23 00:37:07.593213: step: 1984/526, loss: 0.8534290194511414
2023-01-23 00:37:08.731859: step: 1988/526, loss: 0.16459941864013672
2023-01-23 00:37:09.872221: step: 1992/526, loss: 0.07454963028430939
2023-01-23 00:37:11.023037: step: 1996/526, loss: 0.19767847657203674
2023-01-23 00:37:12.141664: step: 2000/526, loss: 0.22813721001148224
2023-01-23 00:37:13.307868: step: 2004/526, loss: 0.05680818855762482
2023-01-23 00:37:14.431512: step: 2008/526, loss: 0.15537257492542267
2023-01-23 00:37:15.559485: step: 2012/526, loss: 0.15140561759471893
2023-01-23 00:37:16.672299: step: 2016/526, loss: 0.12234115600585938
2023-01-23 00:37:17.784540: step: 2020/526, loss: 0.05316825211048126
2023-01-23 00:37:18.910437: step: 2024/526, loss: 0.0906367301940918
2023-01-23 00:37:20.047713: step: 2028/526, loss: 0.26286783814430237
2023-01-23 00:37:21.184315: step: 2032/526, loss: 0.35145533084869385
2023-01-23 00:37:22.317341: step: 2036/526, loss: 0.2321152687072754
2023-01-23 00:37:23.468443: step: 2040/526, loss: 0.13255424797534943
2023-01-23 00:37:24.605584: step: 2044/526, loss: 0.0745459571480751
2023-01-23 00:37:25.737572: step: 2048/526, loss: 0.154963880777359
2023-01-23 00:37:26.834297: step: 2052/526, loss: 0.10433606803417206
2023-01-23 00:37:27.941451: step: 2056/526, loss: 0.0325261615216732
2023-01-23 00:37:29.091586: step: 2060/526, loss: 0.27381545305252075
2023-01-23 00:37:30.240918: step: 2064/526, loss: 0.16113099455833435
2023-01-23 00:37:31.364428: step: 2068/526, loss: 0.0280564334243536
2023-01-23 00:37:32.519800: step: 2072/526, loss: 0.08778181672096252
2023-01-23 00:37:33.675153: step: 2076/526, loss: 0.13478480279445648
2023-01-23 00:37:34.788375: step: 2080/526, loss: 0.1894073486328125
2023-01-23 00:37:35.908713: step: 2084/526, loss: 0.01869783364236355
2023-01-23 00:37:37.030774: step: 2088/526, loss: 0.11841030418872833
2023-01-23 00:37:38.164552: step: 2092/526, loss: 0.04905872046947479
2023-01-23 00:37:39.283698: step: 2096/526, loss: 0.12393054366111755
2023-01-23 00:37:40.445369: step: 2100/526, loss: 0.241658017039299
2023-01-23 00:37:41.587048: step: 2104/526, loss: 0.17300310730934143
==================================================
Loss: 0.172
--------------------
Dev: {'event': {'p': 0.5892494929006086, 'r': 0.7736351531291611, 'f1': 0.6689694876223374}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Test: {'event': {'p': 0.6005770816158286, 'r': 0.7604384133611691, 'f1': 0.6711192998618148}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Chinese: {'event': {'p': 0.5308641975308642, 'r': 0.7962962962962963, 'f1': 0.637037037037037}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Korean: {'event': {'p': 0.7073170731707317, 'r': 0.4603174603174603, 'f1': 0.5576923076923077}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Russian: {'event': {'p': 0.4772727272727273, 'r': 0.5833333333333334, 'f1': 0.5250000000000001}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
New best korean model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6604010025062657, 'r': 0.7017310252996005, 'f1': 0.6804389928986443}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Eng Test for Chinese: {'event': {'p': 0.6480836236933798, 'r': 0.6795407098121086, 'f1': 0.6634394904458599}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Sample Chinese: {'event': {'p': 0.6323529411764706, 'r': 0.7962962962962963, 'f1': 0.7049180327868853}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5892494929006086, 'r': 0.7736351531291611, 'f1': 0.6689694876223374}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Korean: {'event': {'p': 0.6005770816158286, 'r': 0.7604384133611691, 'f1': 0.6711192998618148}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Korean: {'event': {'p': 0.7073170731707317, 'r': 0.4603174603174603, 'f1': 0.5576923076923077}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5563041385948027, 'r': 0.7696404793608522, 'f1': 0.6458100558659218}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Eng Test for Russian: {'event': {'p': 0.5336806847785635, 'r': 0.7484342379958246, 'f1': 0.6230719096241583}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Sample Russian: {'event': {'p': 0.5116279069767442, 'r': 0.6111111111111112, 'f1': 0.5569620253164557}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
******************************
Epoch: 7
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 00:38:30.177521: step: 4/526, loss: 0.08167391270399094
2023-01-23 00:38:31.304237: step: 8/526, loss: 0.07296915352344513
2023-01-23 00:38:32.492120: step: 12/526, loss: 0.10415878891944885
2023-01-23 00:38:33.656054: step: 16/526, loss: 0.339252769947052
2023-01-23 00:38:34.776491: step: 20/526, loss: 0.11001763492822647
2023-01-23 00:38:35.928716: step: 24/526, loss: 0.12424440681934357
2023-01-23 00:38:37.084173: step: 28/526, loss: 0.13503007590770721
2023-01-23 00:38:38.231611: step: 32/526, loss: 0.04702162742614746
2023-01-23 00:38:39.360178: step: 36/526, loss: 0.18683910369873047
2023-01-23 00:38:40.478210: step: 40/526, loss: 0.13439694046974182
2023-01-23 00:38:41.585361: step: 44/526, loss: 0.10474987328052521
2023-01-23 00:38:42.719160: step: 48/526, loss: 0.07858066260814667
2023-01-23 00:38:43.875325: step: 52/526, loss: 0.31191468238830566
2023-01-23 00:38:44.994097: step: 56/526, loss: 0.07207565009593964
2023-01-23 00:38:46.133533: step: 60/526, loss: 0.013375366106629372
2023-01-23 00:38:47.253324: step: 64/526, loss: 0.19718004763126373
2023-01-23 00:38:48.361413: step: 68/526, loss: 0.05647735670208931
2023-01-23 00:38:49.505254: step: 72/526, loss: 0.15307402610778809
2023-01-23 00:38:50.652857: step: 76/526, loss: 0.18623638153076172
2023-01-23 00:38:51.763436: step: 80/526, loss: 0.13776616752147675
2023-01-23 00:38:52.895489: step: 84/526, loss: 0.6230600476264954
2023-01-23 00:38:54.025101: step: 88/526, loss: 0.023225117474794388
2023-01-23 00:38:55.151827: step: 92/526, loss: 0.05773868411779404
2023-01-23 00:38:56.282409: step: 96/526, loss: 0.08946572244167328
2023-01-23 00:38:57.399173: step: 100/526, loss: 0.20988251268863678
2023-01-23 00:38:58.541128: step: 104/526, loss: 0.5690016150474548
2023-01-23 00:38:59.675521: step: 108/526, loss: 0.18187038600444794
2023-01-23 00:39:00.822521: step: 112/526, loss: 0.08731038868427277
2023-01-23 00:39:01.938272: step: 116/526, loss: 0.07598146796226501
2023-01-23 00:39:03.111711: step: 120/526, loss: 0.13496838510036469
2023-01-23 00:39:04.254733: step: 124/526, loss: 0.2077789306640625
2023-01-23 00:39:05.398181: step: 128/526, loss: 0.013856267556548119
2023-01-23 00:39:06.538788: step: 132/526, loss: 0.09541435539722443
2023-01-23 00:39:07.680283: step: 136/526, loss: 0.05809245631098747
2023-01-23 00:39:08.813532: step: 140/526, loss: 0.3651152551174164
2023-01-23 00:39:09.946623: step: 144/526, loss: 0.018068598583340645
2023-01-23 00:39:11.064748: step: 148/526, loss: 0.24460040032863617
2023-01-23 00:39:12.196067: step: 152/526, loss: 0.04399614408612251
2023-01-23 00:39:13.348968: step: 156/526, loss: 0.22436374425888062
2023-01-23 00:39:14.484439: step: 160/526, loss: 0.0024582864716649055
2023-01-23 00:39:15.632589: step: 164/526, loss: 0.021137237548828125
2023-01-23 00:39:16.742994: step: 168/526, loss: 0.06161389499902725
2023-01-23 00:39:17.883118: step: 172/526, loss: 0.15993185341358185
2023-01-23 00:39:19.037545: step: 176/526, loss: 0.9113231897354126
2023-01-23 00:39:20.166398: step: 180/526, loss: 0.060880571603775024
2023-01-23 00:39:21.272860: step: 184/526, loss: 0.050478171557188034
2023-01-23 00:39:22.372655: step: 188/526, loss: 0.015278911218047142
2023-01-23 00:39:23.545299: step: 192/526, loss: 0.07800436019897461
2023-01-23 00:39:24.695037: step: 196/526, loss: 0.5849026441574097
2023-01-23 00:39:25.824019: step: 200/526, loss: 0.042290449142456055
2023-01-23 00:39:26.942601: step: 204/526, loss: 0.0784408301115036
2023-01-23 00:39:28.078531: step: 208/526, loss: 0.02679157257080078
2023-01-23 00:39:29.247836: step: 212/526, loss: 0.09209270775318146
2023-01-23 00:39:30.370226: step: 216/526, loss: 0.047389887273311615
2023-01-23 00:39:31.507974: step: 220/526, loss: 0.5147913098335266
2023-01-23 00:39:32.649895: step: 224/526, loss: 0.05951347574591637
2023-01-23 00:39:33.782517: step: 228/526, loss: 0.06431560218334198
2023-01-23 00:39:34.875407: step: 232/526, loss: 0.06869430840015411
2023-01-23 00:39:36.036175: step: 236/526, loss: 0.07268104702234268
2023-01-23 00:39:37.154421: step: 240/526, loss: 0.18074187636375427
2023-01-23 00:39:38.296991: step: 244/526, loss: 0.038242436945438385
2023-01-23 00:39:39.445967: step: 248/526, loss: 0.037408068776130676
2023-01-23 00:39:40.589469: step: 252/526, loss: 0.015559673309326172
2023-01-23 00:39:41.745132: step: 256/526, loss: 0.07357215881347656
2023-01-23 00:39:42.858692: step: 260/526, loss: 0.06849727034568787
2023-01-23 00:39:44.001049: step: 264/526, loss: 0.46111923456192017
2023-01-23 00:39:45.170563: step: 268/526, loss: 0.20764578878879547
2023-01-23 00:39:46.290872: step: 272/526, loss: 0.1614522486925125
2023-01-23 00:39:47.440216: step: 276/526, loss: 0.22258442640304565
2023-01-23 00:39:48.582193: step: 280/526, loss: 0.08382568508386612
2023-01-23 00:39:49.747111: step: 284/526, loss: 0.06825542449951172
2023-01-23 00:39:50.866217: step: 288/526, loss: 0.13082657754421234
2023-01-23 00:39:52.014108: step: 292/526, loss: 0.48294275999069214
2023-01-23 00:39:53.169716: step: 296/526, loss: 0.03033742867410183
2023-01-23 00:39:54.304856: step: 300/526, loss: 0.42863520979881287
2023-01-23 00:39:55.437217: step: 304/526, loss: 0.05352230370044708
2023-01-23 00:39:56.559065: step: 308/526, loss: 0.10876922309398651
2023-01-23 00:39:57.716566: step: 312/526, loss: 0.028925180435180664
2023-01-23 00:39:58.851770: step: 316/526, loss: 0.0429142490029335
2023-01-23 00:39:59.944645: step: 320/526, loss: 0.005161619279533625
2023-01-23 00:40:01.048430: step: 324/526, loss: 0.016247272491455078
2023-01-23 00:40:02.215526: step: 328/526, loss: 0.05932874232530594
2023-01-23 00:40:03.352684: step: 332/526, loss: 0.03951101377606392
2023-01-23 00:40:04.499141: step: 336/526, loss: 0.04240245744585991
2023-01-23 00:40:05.655697: step: 340/526, loss: 0.02077507972717285
2023-01-23 00:40:06.812638: step: 344/526, loss: 0.0703771561384201
2023-01-23 00:40:07.948351: step: 348/526, loss: 0.041604042053222656
2023-01-23 00:40:09.090468: step: 352/526, loss: 0.1324130892753601
2023-01-23 00:40:10.233673: step: 356/526, loss: 0.10725397616624832
2023-01-23 00:40:11.373558: step: 360/526, loss: 0.038194939494132996
2023-01-23 00:40:12.514194: step: 364/526, loss: 0.7604475617408752
2023-01-23 00:40:13.660378: step: 368/526, loss: 0.10343198478221893
2023-01-23 00:40:14.812937: step: 372/526, loss: 0.30154791474342346
2023-01-23 00:40:15.918511: step: 376/526, loss: 0.7934285402297974
2023-01-23 00:40:17.038573: step: 380/526, loss: 0.10674865543842316
2023-01-23 00:40:18.193116: step: 384/526, loss: 0.07076716423034668
2023-01-23 00:40:19.327207: step: 388/526, loss: 0.22519856691360474
2023-01-23 00:40:20.444025: step: 392/526, loss: 0.03980549797415733
2023-01-23 00:40:21.599218: step: 396/526, loss: 0.03682880476117134
2023-01-23 00:40:22.730805: step: 400/526, loss: 0.005124473944306374
2023-01-23 00:40:23.849888: step: 404/526, loss: 0.19035053253173828
2023-01-23 00:40:24.977350: step: 408/526, loss: 0.04564166069030762
2023-01-23 00:40:26.138730: step: 412/526, loss: 0.16892023384571075
2023-01-23 00:40:27.305117: step: 416/526, loss: 0.0794258564710617
2023-01-23 00:40:28.444360: step: 420/526, loss: 0.5449943542480469
2023-01-23 00:40:29.563408: step: 424/526, loss: 0.09458093345165253
2023-01-23 00:40:30.689650: step: 428/526, loss: 0.04249515384435654
2023-01-23 00:40:31.802552: step: 432/526, loss: 0.14795684814453125
2023-01-23 00:40:32.951964: step: 436/526, loss: 0.11780376732349396
2023-01-23 00:40:34.080984: step: 440/526, loss: 0.11471491307020187
2023-01-23 00:40:35.218357: step: 444/526, loss: 0.04942111670970917
2023-01-23 00:40:36.351968: step: 448/526, loss: 0.055294036865234375
2023-01-23 00:40:37.515805: step: 452/526, loss: 0.07405147701501846
2023-01-23 00:40:38.667236: step: 456/526, loss: 0.07961221039295197
2023-01-23 00:40:39.800494: step: 460/526, loss: 0.026602745056152344
2023-01-23 00:40:40.928010: step: 464/526, loss: 0.292308509349823
2023-01-23 00:40:42.079220: step: 468/526, loss: 0.07435820251703262
2023-01-23 00:40:43.217491: step: 472/526, loss: 0.046309471130371094
2023-01-23 00:40:44.360376: step: 476/526, loss: 0.15707239508628845
2023-01-23 00:40:45.494684: step: 480/526, loss: 0.047875214368104935
2023-01-23 00:40:46.630499: step: 484/526, loss: 0.07487936317920685
2023-01-23 00:40:47.761184: step: 488/526, loss: 0.0793735533952713
2023-01-23 00:40:48.887695: step: 492/526, loss: 0.13200893998146057
2023-01-23 00:40:50.030002: step: 496/526, loss: 0.11926007270812988
2023-01-23 00:40:51.191051: step: 500/526, loss: 0.1535160094499588
2023-01-23 00:40:52.307791: step: 504/526, loss: 0.18116417527198792
2023-01-23 00:40:53.431700: step: 508/526, loss: 0.580575168132782
2023-01-23 00:40:54.548663: step: 512/526, loss: 0.04906139522790909
2023-01-23 00:40:55.664184: step: 516/526, loss: 0.0695432648062706
2023-01-23 00:40:56.804541: step: 520/526, loss: 0.17038078606128693
2023-01-23 00:40:57.924191: step: 524/526, loss: 0.10769033432006836
2023-01-23 00:40:59.048931: step: 528/526, loss: 0.49971145391464233
2023-01-23 00:41:00.183914: step: 532/526, loss: 0.25485116243362427
2023-01-23 00:41:01.315308: step: 536/526, loss: 0.05196123570203781
2023-01-23 00:41:02.447960: step: 540/526, loss: 0.005896282382309437
2023-01-23 00:41:03.578688: step: 544/526, loss: 0.09783181548118591
2023-01-23 00:41:04.704715: step: 548/526, loss: 0.10216712951660156
2023-01-23 00:41:05.829938: step: 552/526, loss: 0.03494014963507652
2023-01-23 00:41:06.950285: step: 556/526, loss: 0.020683670416474342
2023-01-23 00:41:08.101331: step: 560/526, loss: 0.03055420145392418
2023-01-23 00:41:09.239007: step: 564/526, loss: 0.12073612958192825
2023-01-23 00:41:10.387149: step: 568/526, loss: 0.2799626290798187
2023-01-23 00:41:11.529183: step: 572/526, loss: 0.08815017342567444
2023-01-23 00:41:12.656477: step: 576/526, loss: 0.05846752971410751
2023-01-23 00:41:13.801668: step: 580/526, loss: 0.12896637618541718
2023-01-23 00:41:14.934151: step: 584/526, loss: 0.43202272057533264
2023-01-23 00:41:16.076646: step: 588/526, loss: 0.034606173634529114
2023-01-23 00:41:17.217322: step: 592/526, loss: 0.31149905920028687
2023-01-23 00:41:18.364196: step: 596/526, loss: 0.11661787331104279
2023-01-23 00:41:19.510018: step: 600/526, loss: 0.6148589849472046
2023-01-23 00:41:20.630104: step: 604/526, loss: 1.1019624471664429
2023-01-23 00:41:21.753410: step: 608/526, loss: 0.0805574506521225
2023-01-23 00:41:22.885613: step: 612/526, loss: 0.05362563207745552
2023-01-23 00:41:24.040489: step: 616/526, loss: 0.08867712318897247
2023-01-23 00:41:25.163166: step: 620/526, loss: 0.07213282585144043
2023-01-23 00:41:26.276074: step: 624/526, loss: 0.03709716722369194
2023-01-23 00:41:27.423642: step: 628/526, loss: 0.1803010106086731
2023-01-23 00:41:28.575006: step: 632/526, loss: 0.0391879566013813
2023-01-23 00:41:29.710395: step: 636/526, loss: 0.10424366593360901
2023-01-23 00:41:30.837642: step: 640/526, loss: 0.009069728665053844
2023-01-23 00:41:31.973927: step: 644/526, loss: 0.5905860662460327
2023-01-23 00:41:33.081311: step: 648/526, loss: 0.023659229278564453
2023-01-23 00:41:34.195462: step: 652/526, loss: 0.0717647597193718
2023-01-23 00:41:35.362596: step: 656/526, loss: 0.01780710183084011
2023-01-23 00:41:36.494555: step: 660/526, loss: 0.10806316882371902
2023-01-23 00:41:37.653606: step: 664/526, loss: 0.11200366169214249
2023-01-23 00:41:38.783497: step: 668/526, loss: 0.0597173236310482
2023-01-23 00:41:39.933029: step: 672/526, loss: 0.07035350799560547
2023-01-23 00:41:41.108687: step: 676/526, loss: 0.274576872587204
2023-01-23 00:41:42.240394: step: 680/526, loss: 0.042966749519109726
2023-01-23 00:41:43.414035: step: 684/526, loss: 0.2340126931667328
2023-01-23 00:41:44.528690: step: 688/526, loss: 0.061487678438425064
2023-01-23 00:41:45.669389: step: 692/526, loss: 0.11537900567054749
2023-01-23 00:41:46.800174: step: 696/526, loss: 0.04064655303955078
2023-01-23 00:41:47.936065: step: 700/526, loss: 0.008150959387421608
2023-01-23 00:41:49.042930: step: 704/526, loss: 0.08518867194652557
2023-01-23 00:41:50.167391: step: 708/526, loss: 0.08306531608104706
2023-01-23 00:41:51.306891: step: 712/526, loss: 0.03696250915527344
2023-01-23 00:41:52.464586: step: 716/526, loss: 0.1326136291027069
2023-01-23 00:41:53.571185: step: 720/526, loss: 0.27834969758987427
2023-01-23 00:41:54.714792: step: 724/526, loss: 0.08183804154396057
2023-01-23 00:41:55.855337: step: 728/526, loss: 0.15969830751419067
2023-01-23 00:41:56.960658: step: 732/526, loss: 0.014976215548813343
2023-01-23 00:41:58.109356: step: 736/526, loss: 0.1051931381225586
2023-01-23 00:41:59.224185: step: 740/526, loss: 0.025025749579072
2023-01-23 00:42:00.375509: step: 744/526, loss: 0.014679431915283203
2023-01-23 00:42:01.534914: step: 748/526, loss: 0.3080042004585266
2023-01-23 00:42:02.623757: step: 752/526, loss: 0.15704306960105896
2023-01-23 00:42:03.754225: step: 756/526, loss: 0.06792859733104706
2023-01-23 00:42:04.880574: step: 760/526, loss: 0.05796823650598526
2023-01-23 00:42:06.020945: step: 764/526, loss: 0.37051573395729065
2023-01-23 00:42:07.143487: step: 768/526, loss: 0.0008899688837118447
2023-01-23 00:42:08.282407: step: 772/526, loss: 0.4569458067417145
2023-01-23 00:42:09.395798: step: 776/526, loss: 0.10436372458934784
2023-01-23 00:42:10.551453: step: 780/526, loss: 0.005532217212021351
2023-01-23 00:42:11.690534: step: 784/526, loss: 0.1366383582353592
2023-01-23 00:42:12.831059: step: 788/526, loss: 0.03198595345020294
2023-01-23 00:42:13.940505: step: 792/526, loss: 0.1335197389125824
2023-01-23 00:42:15.097205: step: 796/526, loss: 0.40154755115509033
2023-01-23 00:42:16.259538: step: 800/526, loss: 0.19560456275939941
2023-01-23 00:42:17.415672: step: 804/526, loss: 0.10589656978845596
2023-01-23 00:42:18.558068: step: 808/526, loss: 0.10243845731019974
2023-01-23 00:42:19.690706: step: 812/526, loss: 0.09133201092481613
2023-01-23 00:42:20.835331: step: 816/526, loss: 0.17204904556274414
2023-01-23 00:42:22.003930: step: 820/526, loss: 0.06681585311889648
2023-01-23 00:42:23.161827: step: 824/526, loss: 0.33932629227638245
2023-01-23 00:42:24.291541: step: 828/526, loss: 0.07811050862073898
2023-01-23 00:42:25.419532: step: 832/526, loss: 0.15597376227378845
2023-01-23 00:42:26.558426: step: 836/526, loss: 0.07745952904224396
2023-01-23 00:42:27.709993: step: 840/526, loss: 0.07306583225727081
2023-01-23 00:42:28.849285: step: 844/526, loss: 0.054602622985839844
2023-01-23 00:42:30.001320: step: 848/526, loss: 0.2932031750679016
2023-01-23 00:42:31.108759: step: 852/526, loss: 0.06582732498645782
2023-01-23 00:42:32.230080: step: 856/526, loss: 0.03746090084314346
2023-01-23 00:42:33.359326: step: 860/526, loss: 0.11692628264427185
2023-01-23 00:42:34.484682: step: 864/526, loss: 0.4945685565471649
2023-01-23 00:42:35.606820: step: 868/526, loss: 0.1825283020734787
2023-01-23 00:42:36.739132: step: 872/526, loss: 0.03533501550555229
2023-01-23 00:42:37.863548: step: 876/526, loss: 0.037752602249383926
2023-01-23 00:42:38.995610: step: 880/526, loss: 0.10571518540382385
2023-01-23 00:42:40.143909: step: 884/526, loss: 0.33125782012939453
2023-01-23 00:42:41.279414: step: 888/526, loss: 0.03770214319229126
2023-01-23 00:42:42.401439: step: 892/526, loss: 0.1424632966518402
2023-01-23 00:42:43.557562: step: 896/526, loss: 0.3080737292766571
2023-01-23 00:42:44.710693: step: 900/526, loss: 0.35783377289772034
2023-01-23 00:42:45.840529: step: 904/526, loss: 0.029872512444853783
2023-01-23 00:42:46.997376: step: 908/526, loss: 0.16637524962425232
2023-01-23 00:42:48.113467: step: 912/526, loss: 0.020266462117433548
2023-01-23 00:42:49.292940: step: 916/526, loss: 0.26609399914741516
2023-01-23 00:42:50.419379: step: 920/526, loss: 0.0461542122066021
2023-01-23 00:42:51.579661: step: 924/526, loss: 0.017359159886837006
2023-01-23 00:42:52.704504: step: 928/526, loss: 0.07158572971820831
2023-01-23 00:42:53.808983: step: 932/526, loss: 0.05541105195879936
2023-01-23 00:42:54.946987: step: 936/526, loss: 0.05066251754760742
2023-01-23 00:42:56.049630: step: 940/526, loss: 0.04320118948817253
2023-01-23 00:42:57.187920: step: 944/526, loss: 0.0726872906088829
2023-01-23 00:42:58.307313: step: 948/526, loss: 1.1193865537643433
2023-01-23 00:42:59.448385: step: 952/526, loss: 0.009647369384765625
2023-01-23 00:43:00.609074: step: 956/526, loss: 0.07161865383386612
2023-01-23 00:43:01.763167: step: 960/526, loss: 0.21820850670337677
2023-01-23 00:43:02.891004: step: 964/526, loss: 0.11262059211730957
2023-01-23 00:43:04.044703: step: 968/526, loss: 0.052465248852968216
2023-01-23 00:43:05.183286: step: 972/526, loss: 0.0840580016374588
2023-01-23 00:43:06.339576: step: 976/526, loss: 0.08422450721263885
2023-01-23 00:43:07.454043: step: 980/526, loss: 0.05547799915075302
2023-01-23 00:43:08.593949: step: 984/526, loss: 0.3026929497718811
2023-01-23 00:43:09.711764: step: 988/526, loss: 0.05694770812988281
2023-01-23 00:43:10.829924: step: 992/526, loss: 0.04771725833415985
2023-01-23 00:43:11.931597: step: 996/526, loss: 0.0326298251748085
2023-01-23 00:43:13.097542: step: 1000/526, loss: 0.1268974244594574
2023-01-23 00:43:14.220115: step: 1004/526, loss: 0.09495782852172852
2023-01-23 00:43:15.342366: step: 1008/526, loss: 0.05754394456744194
2023-01-23 00:43:16.471511: step: 1012/526, loss: 0.07991227507591248
2023-01-23 00:43:17.595495: step: 1016/526, loss: 0.06967845559120178
2023-01-23 00:43:18.717492: step: 1020/526, loss: 0.18973246216773987
2023-01-23 00:43:19.865155: step: 1024/526, loss: 0.07780519127845764
2023-01-23 00:43:21.029196: step: 1028/526, loss: 0.15296021103858948
2023-01-23 00:43:22.185189: step: 1032/526, loss: 0.10831265151500702
2023-01-23 00:43:23.334198: step: 1036/526, loss: 0.15890845656394958
2023-01-23 00:43:24.480927: step: 1040/526, loss: 0.06265049427747726
2023-01-23 00:43:25.625228: step: 1044/526, loss: 0.11585778743028641
2023-01-23 00:43:26.775848: step: 1048/526, loss: 0.024000167846679688
2023-01-23 00:43:27.918393: step: 1052/526, loss: 0.007708740420639515
2023-01-23 00:43:29.067353: step: 1056/526, loss: 0.17126807570457458
2023-01-23 00:43:30.212528: step: 1060/526, loss: 0.6998818516731262
2023-01-23 00:43:31.334781: step: 1064/526, loss: 0.0391172394156456
2023-01-23 00:43:32.455361: step: 1068/526, loss: 0.25107860565185547
2023-01-23 00:43:33.577842: step: 1072/526, loss: 0.10010509938001633
2023-01-23 00:43:34.699520: step: 1076/526, loss: 0.0942656546831131
2023-01-23 00:43:35.792215: step: 1080/526, loss: 0.05831451714038849
2023-01-23 00:43:36.943708: step: 1084/526, loss: 0.10765514522790909
2023-01-23 00:43:38.074357: step: 1088/526, loss: 0.04110097885131836
2023-01-23 00:43:39.202042: step: 1092/526, loss: 0.1538499891757965
2023-01-23 00:43:40.327766: step: 1096/526, loss: 0.09977855533361435
2023-01-23 00:43:41.464076: step: 1100/526, loss: 0.3947006165981293
2023-01-23 00:43:42.612196: step: 1104/526, loss: 0.021377945318818092
2023-01-23 00:43:43.731969: step: 1108/526, loss: 0.18397732079029083
2023-01-23 00:43:44.840889: step: 1112/526, loss: 0.18016815185546875
2023-01-23 00:43:46.003907: step: 1116/526, loss: 0.5049295425415039
2023-01-23 00:43:47.138401: step: 1120/526, loss: 0.46759310364723206
2023-01-23 00:43:48.288234: step: 1124/526, loss: 0.11646925657987595
2023-01-23 00:43:49.404849: step: 1128/526, loss: 0.10861194133758545
2023-01-23 00:43:50.533601: step: 1132/526, loss: 0.19022607803344727
2023-01-23 00:43:51.656302: step: 1136/526, loss: 0.1617298126220703
2023-01-23 00:43:52.811203: step: 1140/526, loss: 0.11830015480518341
2023-01-23 00:43:53.976772: step: 1144/526, loss: 0.8109237551689148
2023-01-23 00:43:55.109143: step: 1148/526, loss: 0.03343292325735092
2023-01-23 00:43:56.241283: step: 1152/526, loss: 0.09109906852245331
2023-01-23 00:43:57.388492: step: 1156/526, loss: 0.06347141414880753
2023-01-23 00:43:58.508627: step: 1160/526, loss: 0.024823855608701706
2023-01-23 00:43:59.660261: step: 1164/526, loss: 0.08118382096290588
2023-01-23 00:44:00.780585: step: 1168/526, loss: 0.1971965879201889
2023-01-23 00:44:01.934881: step: 1172/526, loss: 0.05900769308209419
2023-01-23 00:44:03.058651: step: 1176/526, loss: 0.043454360216856
2023-01-23 00:44:04.180892: step: 1180/526, loss: 0.019617462530732155
2023-01-23 00:44:05.304221: step: 1184/526, loss: 0.10672197490930557
2023-01-23 00:44:06.440311: step: 1188/526, loss: 0.23176135122776031
2023-01-23 00:44:07.558167: step: 1192/526, loss: 0.07296357303857803
2023-01-23 00:44:08.715289: step: 1196/526, loss: 0.09023533016443253
2023-01-23 00:44:09.820909: step: 1200/526, loss: 0.14960722625255585
2023-01-23 00:44:10.956539: step: 1204/526, loss: 0.708601176738739
2023-01-23 00:44:12.099062: step: 1208/526, loss: 0.07830296456813812
2023-01-23 00:44:13.235299: step: 1212/526, loss: 0.0588352233171463
2023-01-23 00:44:14.381257: step: 1216/526, loss: 0.09022102504968643
2023-01-23 00:44:15.505154: step: 1220/526, loss: 0.5049480199813843
2023-01-23 00:44:16.647269: step: 1224/526, loss: 0.10298814624547958
2023-01-23 00:44:17.813092: step: 1228/526, loss: 0.030216598883271217
2023-01-23 00:44:18.942931: step: 1232/526, loss: 0.02164621278643608
2023-01-23 00:44:20.110419: step: 1236/526, loss: 0.03098478354513645
2023-01-23 00:44:21.267012: step: 1240/526, loss: 0.07389402389526367
2023-01-23 00:44:22.421399: step: 1244/526, loss: 0.14863519370555878
2023-01-23 00:44:23.554923: step: 1248/526, loss: 0.032288551330566406
2023-01-23 00:44:24.680712: step: 1252/526, loss: 0.5651698112487793
2023-01-23 00:44:25.828094: step: 1256/526, loss: 0.0921720489859581
2023-01-23 00:44:26.950927: step: 1260/526, loss: 0.20742206275463104
2023-01-23 00:44:28.112966: step: 1264/526, loss: 0.1320362091064453
2023-01-23 00:44:29.244038: step: 1268/526, loss: 0.10012664645910263
2023-01-23 00:44:30.391309: step: 1272/526, loss: 0.09101162105798721
2023-01-23 00:44:31.543906: step: 1276/526, loss: 0.2577333450317383
2023-01-23 00:44:32.687890: step: 1280/526, loss: 0.7802594900131226
2023-01-23 00:44:33.813427: step: 1284/526, loss: 0.35978859663009644
2023-01-23 00:44:34.978058: step: 1288/526, loss: 0.05459742620587349
2023-01-23 00:44:36.127164: step: 1292/526, loss: 0.04782591015100479
2023-01-23 00:44:37.222871: step: 1296/526, loss: 0.06419219821691513
2023-01-23 00:44:38.379360: step: 1300/526, loss: 0.03440551832318306
2023-01-23 00:44:39.519065: step: 1304/526, loss: 0.15025176107883453
2023-01-23 00:44:40.689637: step: 1308/526, loss: 0.06674442440271378
2023-01-23 00:44:41.875845: step: 1312/526, loss: 0.3306504189968109
2023-01-23 00:44:43.020758: step: 1316/526, loss: 0.23197859525680542
2023-01-23 00:44:44.125769: step: 1320/526, loss: 0.22558268904685974
2023-01-23 00:44:45.271454: step: 1324/526, loss: 0.015024662017822266
2023-01-23 00:44:46.401614: step: 1328/526, loss: 0.2526015341281891
2023-01-23 00:44:47.567353: step: 1332/526, loss: 0.1268499344587326
2023-01-23 00:44:48.699585: step: 1336/526, loss: 0.21193313598632812
2023-01-23 00:44:49.829524: step: 1340/526, loss: 0.028816748410463333
2023-01-23 00:44:50.983654: step: 1344/526, loss: 0.10718526691198349
2023-01-23 00:44:52.125835: step: 1348/526, loss: 0.13887767493724823
2023-01-23 00:44:53.243544: step: 1352/526, loss: 0.07422390580177307
2023-01-23 00:44:54.373133: step: 1356/526, loss: 0.028196675702929497
2023-01-23 00:44:55.521545: step: 1360/526, loss: 0.03765721619129181
2023-01-23 00:44:56.648752: step: 1364/526, loss: 0.5351154804229736
2023-01-23 00:44:57.753358: step: 1368/526, loss: 0.28474217653274536
2023-01-23 00:44:58.867666: step: 1372/526, loss: 0.34652385115623474
2023-01-23 00:45:00.000568: step: 1376/526, loss: 0.03533210977911949
2023-01-23 00:45:01.152957: step: 1380/526, loss: 0.06955623626708984
2023-01-23 00:45:02.319459: step: 1384/526, loss: 0.222881019115448
2023-01-23 00:45:03.456432: step: 1388/526, loss: 0.06616034358739853
2023-01-23 00:45:04.608141: step: 1392/526, loss: 0.08102045208215714
2023-01-23 00:45:05.797370: step: 1396/526, loss: 0.04788055270910263
2023-01-23 00:45:06.934217: step: 1400/526, loss: 0.6647990942001343
2023-01-23 00:45:08.058422: step: 1404/526, loss: 0.06681656837463379
2023-01-23 00:45:09.188439: step: 1408/526, loss: 0.010775423608720303
2023-01-23 00:45:10.327501: step: 1412/526, loss: 0.12645049393177032
2023-01-23 00:45:11.459124: step: 1416/526, loss: 0.05009651184082031
2023-01-23 00:45:12.614745: step: 1420/526, loss: 0.0318637490272522
2023-01-23 00:45:13.738646: step: 1424/526, loss: 0.12748508155345917
2023-01-23 00:45:14.887020: step: 1428/526, loss: 0.028865624219179153
2023-01-23 00:45:16.060164: step: 1432/526, loss: 0.16792979836463928
2023-01-23 00:45:17.193521: step: 1436/526, loss: 0.06971435993909836
2023-01-23 00:45:18.323930: step: 1440/526, loss: 0.14157867431640625
2023-01-23 00:45:19.470175: step: 1444/526, loss: 0.06895770877599716
2023-01-23 00:45:20.607644: step: 1448/526, loss: 0.04891672357916832
2023-01-23 00:45:21.724746: step: 1452/526, loss: 0.26673200726509094
2023-01-23 00:45:22.853950: step: 1456/526, loss: 0.003355693770572543
2023-01-23 00:45:23.984077: step: 1460/526, loss: 0.06873917579650879
2023-01-23 00:45:25.147598: step: 1464/526, loss: 0.12451129406690598
2023-01-23 00:45:26.295938: step: 1468/526, loss: 0.079241082072258
2023-01-23 00:45:27.442444: step: 1472/526, loss: 0.05995222553610802
2023-01-23 00:45:28.582372: step: 1476/526, loss: 0.16911935806274414
2023-01-23 00:45:29.710472: step: 1480/526, loss: 0.13927793502807617
2023-01-23 00:45:30.824319: step: 1484/526, loss: 0.05743388831615448
2023-01-23 00:45:31.935711: step: 1488/526, loss: 0.07564163208007812
2023-01-23 00:45:33.040583: step: 1492/526, loss: 0.18532094359397888
2023-01-23 00:45:34.217046: step: 1496/526, loss: 0.028899766504764557
2023-01-23 00:45:35.317085: step: 1500/526, loss: 0.01598033867776394
2023-01-23 00:45:36.439723: step: 1504/526, loss: 0.04201669618487358
2023-01-23 00:45:37.578391: step: 1508/526, loss: 0.0795467421412468
2023-01-23 00:45:38.714804: step: 1512/526, loss: 0.09611830860376358
2023-01-23 00:45:39.881835: step: 1516/526, loss: 0.16045865416526794
2023-01-23 00:45:41.063126: step: 1520/526, loss: 0.8075896501541138
2023-01-23 00:45:42.208567: step: 1524/526, loss: 0.07167863845825195
2023-01-23 00:45:43.374554: step: 1528/526, loss: 0.052689362317323685
2023-01-23 00:45:44.501112: step: 1532/526, loss: 0.23393507301807404
2023-01-23 00:45:45.647929: step: 1536/526, loss: 0.2833879590034485
2023-01-23 00:45:46.773845: step: 1540/526, loss: 0.07227067649364471
2023-01-23 00:45:47.904453: step: 1544/526, loss: 0.002843809314072132
2023-01-23 00:45:49.032124: step: 1548/526, loss: 0.11440396308898926
2023-01-23 00:45:50.178654: step: 1552/526, loss: 0.09573821723461151
2023-01-23 00:45:51.337427: step: 1556/526, loss: 0.12741537392139435
2023-01-23 00:45:52.455024: step: 1560/526, loss: 0.09237485378980637
2023-01-23 00:45:53.614991: step: 1564/526, loss: 0.09336452931165695
2023-01-23 00:45:54.743268: step: 1568/526, loss: 0.07695751637220383
2023-01-23 00:45:55.888005: step: 1572/526, loss: 0.21299171447753906
2023-01-23 00:45:57.063258: step: 1576/526, loss: 0.05524163320660591
2023-01-23 00:45:58.206354: step: 1580/526, loss: 0.09359641373157501
2023-01-23 00:45:59.364836: step: 1584/526, loss: 0.2421269416809082
2023-01-23 00:46:00.488604: step: 1588/526, loss: 0.21581211686134338
2023-01-23 00:46:01.609144: step: 1592/526, loss: 0.21436166763305664
2023-01-23 00:46:02.732482: step: 1596/526, loss: 0.06375961750745773
2023-01-23 00:46:03.854243: step: 1600/526, loss: 0.2839374542236328
2023-01-23 00:46:04.986188: step: 1604/526, loss: 0.12226247787475586
2023-01-23 00:46:06.120451: step: 1608/526, loss: 0.10494418442249298
2023-01-23 00:46:07.247891: step: 1612/526, loss: 0.024761630222201347
2023-01-23 00:46:08.375236: step: 1616/526, loss: 0.17037610709667206
2023-01-23 00:46:09.537320: step: 1620/526, loss: 0.07723579555749893
2023-01-23 00:46:10.670743: step: 1624/526, loss: 0.2092466801404953
2023-01-23 00:46:11.819831: step: 1628/526, loss: 0.05044609308242798
2023-01-23 00:46:12.946060: step: 1632/526, loss: 0.029678424820303917
2023-01-23 00:46:14.098824: step: 1636/526, loss: 0.40183210372924805
2023-01-23 00:46:15.225765: step: 1640/526, loss: 0.08136948943138123
2023-01-23 00:46:16.353863: step: 1644/526, loss: 0.027004718780517578
2023-01-23 00:46:17.468306: step: 1648/526, loss: 0.01864652708172798
2023-01-23 00:46:18.632058: step: 1652/526, loss: 0.21829204261302948
2023-01-23 00:46:19.799844: step: 1656/526, loss: 0.2569066882133484
2023-01-23 00:46:20.941304: step: 1660/526, loss: 0.026708031073212624
2023-01-23 00:46:22.065235: step: 1664/526, loss: 0.06775055080652237
2023-01-23 00:46:23.205684: step: 1668/526, loss: 0.44076114892959595
2023-01-23 00:46:24.326191: step: 1672/526, loss: 0.054117538034915924
2023-01-23 00:46:25.462787: step: 1676/526, loss: 0.13281765580177307
2023-01-23 00:46:26.605794: step: 1680/526, loss: 0.365447998046875
2023-01-23 00:46:27.763398: step: 1684/526, loss: 0.12681007385253906
2023-01-23 00:46:28.906852: step: 1688/526, loss: 0.16925403475761414
2023-01-23 00:46:30.040762: step: 1692/526, loss: 0.06788118183612823
2023-01-23 00:46:31.173283: step: 1696/526, loss: 0.1189342513680458
2023-01-23 00:46:32.334519: step: 1700/526, loss: 1.2117369174957275
2023-01-23 00:46:33.455003: step: 1704/526, loss: 0.01751413382589817
2023-01-23 00:46:34.589971: step: 1708/526, loss: 0.11873197555541992
2023-01-23 00:46:35.706797: step: 1712/526, loss: 0.03187905251979828
2023-01-23 00:46:36.853010: step: 1716/526, loss: 0.12629947066307068
2023-01-23 00:46:37.991963: step: 1720/526, loss: 0.11023445427417755
2023-01-23 00:46:39.173369: step: 1724/526, loss: 0.11636095494031906
2023-01-23 00:46:40.311996: step: 1728/526, loss: 0.1528707593679428
2023-01-23 00:46:41.440538: step: 1732/526, loss: 0.1430281698703766
2023-01-23 00:46:42.577758: step: 1736/526, loss: 0.17953424155712128
2023-01-23 00:46:43.709966: step: 1740/526, loss: 0.04234180599451065
2023-01-23 00:46:44.854634: step: 1744/526, loss: 0.046218253672122955
2023-01-23 00:46:45.982107: step: 1748/526, loss: 0.29042285680770874
2023-01-23 00:46:47.104040: step: 1752/526, loss: 0.3707937002182007
2023-01-23 00:46:48.220855: step: 1756/526, loss: 0.419533908367157
2023-01-23 00:46:49.360093: step: 1760/526, loss: 0.6809808015823364
2023-01-23 00:46:50.485407: step: 1764/526, loss: 0.17096862196922302
2023-01-23 00:46:51.624050: step: 1768/526, loss: 0.1278887391090393
2023-01-23 00:46:52.788781: step: 1772/526, loss: 0.15587787330150604
2023-01-23 00:46:53.923477: step: 1776/526, loss: 0.06174030527472496
2023-01-23 00:46:55.062815: step: 1780/526, loss: 0.15425196290016174
2023-01-23 00:46:56.208157: step: 1784/526, loss: 0.12806811928749084
2023-01-23 00:46:57.350872: step: 1788/526, loss: 0.03488569334149361
2023-01-23 00:46:58.466819: step: 1792/526, loss: 0.15859737992286682
2023-01-23 00:46:59.574971: step: 1796/526, loss: 0.03506731986999512
2023-01-23 00:47:00.688770: step: 1800/526, loss: 0.11343927681446075
2023-01-23 00:47:01.828821: step: 1804/526, loss: 0.1599036157131195
2023-01-23 00:47:02.988793: step: 1808/526, loss: 0.07686062157154083
2023-01-23 00:47:04.138357: step: 1812/526, loss: 0.17101605236530304
2023-01-23 00:47:05.296359: step: 1816/526, loss: 0.10806016623973846
2023-01-23 00:47:06.435376: step: 1820/526, loss: 0.21551105380058289
2023-01-23 00:47:07.561358: step: 1824/526, loss: 0.1386154741048813
2023-01-23 00:47:08.689062: step: 1828/526, loss: 0.04928422346711159
2023-01-23 00:47:09.838711: step: 1832/526, loss: 0.02080964669585228
2023-01-23 00:47:10.977660: step: 1836/526, loss: 0.08711685985326767
2023-01-23 00:47:12.108172: step: 1840/526, loss: 0.1628192961215973
2023-01-23 00:47:13.240780: step: 1844/526, loss: 0.7590702772140503
2023-01-23 00:47:14.375262: step: 1848/526, loss: 0.09123792499303818
2023-01-23 00:47:15.501563: step: 1852/526, loss: 0.01990513876080513
2023-01-23 00:47:16.649678: step: 1856/526, loss: 0.14835429191589355
2023-01-23 00:47:17.774590: step: 1860/526, loss: 0.05281124264001846
2023-01-23 00:47:18.933679: step: 1864/526, loss: 0.05277001112699509
2023-01-23 00:47:20.050172: step: 1868/526, loss: 0.8418101072311401
2023-01-23 00:47:21.211779: step: 1872/526, loss: 0.055646900087594986
2023-01-23 00:47:22.354254: step: 1876/526, loss: 0.10546045005321503
2023-01-23 00:47:23.498095: step: 1880/526, loss: 0.11477122455835342
2023-01-23 00:47:24.606689: step: 1884/526, loss: 0.15601015090942383
2023-01-23 00:47:25.758779: step: 1888/526, loss: 0.022717859596014023
2023-01-23 00:47:26.891348: step: 1892/526, loss: 0.11235609650611877
2023-01-23 00:47:28.029881: step: 1896/526, loss: 0.22358913719654083
2023-01-23 00:47:29.161468: step: 1900/526, loss: 0.03359527513384819
2023-01-23 00:47:30.303505: step: 1904/526, loss: 0.0324854850769043
2023-01-23 00:47:31.430425: step: 1908/526, loss: 0.06537675857543945
2023-01-23 00:47:32.567797: step: 1912/526, loss: 0.20563125610351562
2023-01-23 00:47:33.719305: step: 1916/526, loss: 0.06448874622583389
2023-01-23 00:47:34.826326: step: 1920/526, loss: 0.37325984239578247
2023-01-23 00:47:35.935498: step: 1924/526, loss: 0.05528712272644043
2023-01-23 00:47:37.086621: step: 1928/526, loss: 0.0896279364824295
2023-01-23 00:47:38.247395: step: 1932/526, loss: 0.27288904786109924
2023-01-23 00:47:39.407269: step: 1936/526, loss: 0.14644156396389008
2023-01-23 00:47:40.566154: step: 1940/526, loss: 0.3932479918003082
2023-01-23 00:47:41.693183: step: 1944/526, loss: 0.0750247985124588
2023-01-23 00:47:42.858667: step: 1948/526, loss: 0.1488696038722992
2023-01-23 00:47:43.981197: step: 1952/526, loss: 0.01288747787475586
2023-01-23 00:47:45.109682: step: 1956/526, loss: 0.30777817964553833
2023-01-23 00:47:46.228396: step: 1960/526, loss: 0.013335800729691982
2023-01-23 00:47:47.352722: step: 1964/526, loss: 0.09965267032384872
2023-01-23 00:47:48.490180: step: 1968/526, loss: 0.033304404467344284
2023-01-23 00:47:49.620754: step: 1972/526, loss: 0.10899333655834198
2023-01-23 00:47:50.758510: step: 1976/526, loss: 1.0351192951202393
2023-01-23 00:47:51.875937: step: 1980/526, loss: 0.02187070995569229
2023-01-23 00:47:53.018640: step: 1984/526, loss: 0.11713247001171112
2023-01-23 00:47:54.148186: step: 1988/526, loss: 0.06531868129968643
2023-01-23 00:47:55.300828: step: 1992/526, loss: 0.3635888993740082
2023-01-23 00:47:56.449470: step: 1996/526, loss: 0.049531079828739166
2023-01-23 00:47:57.608972: step: 2000/526, loss: 0.022366192191839218
2023-01-23 00:47:58.766998: step: 2004/526, loss: 0.19946500658988953
2023-01-23 00:47:59.909571: step: 2008/526, loss: 0.36543503403663635
2023-01-23 00:48:01.081622: step: 2012/526, loss: 0.13704414665699005
2023-01-23 00:48:02.230213: step: 2016/526, loss: 0.1697574108839035
2023-01-23 00:48:03.362315: step: 2020/526, loss: 0.029215335845947266
2023-01-23 00:48:04.503642: step: 2024/526, loss: 0.02939128875732422
2023-01-23 00:48:05.616042: step: 2028/526, loss: 0.159742534160614
2023-01-23 00:48:06.776008: step: 2032/526, loss: 0.7922096252441406
2023-01-23 00:48:07.921666: step: 2036/526, loss: 0.04607725143432617
2023-01-23 00:48:09.050457: step: 2040/526, loss: 0.07328657805919647
2023-01-23 00:48:10.210298: step: 2044/526, loss: 0.050852395594120026
2023-01-23 00:48:11.370906: step: 2048/526, loss: 0.020374394953250885
2023-01-23 00:48:12.517395: step: 2052/526, loss: 0.06905481219291687
2023-01-23 00:48:13.661574: step: 2056/526, loss: 0.023433685302734375
2023-01-23 00:48:14.820784: step: 2060/526, loss: 0.07002801448106766
2023-01-23 00:48:15.990586: step: 2064/526, loss: 1.9444684982299805
2023-01-23 00:48:17.135056: step: 2068/526, loss: 0.061034154146909714
2023-01-23 00:48:18.260707: step: 2072/526, loss: 0.052844252437353134
2023-01-23 00:48:19.398961: step: 2076/526, loss: 0.0982128232717514
2023-01-23 00:48:20.536585: step: 2080/526, loss: 0.12395502626895905
2023-01-23 00:48:21.688857: step: 2084/526, loss: 0.08458928763866425
2023-01-23 00:48:22.799832: step: 2088/526, loss: 0.05322227627038956
2023-01-23 00:48:23.922730: step: 2092/526, loss: 0.021163761615753174
2023-01-23 00:48:25.057228: step: 2096/526, loss: 0.7529973983764648
2023-01-23 00:48:26.203571: step: 2100/526, loss: 0.06707258522510529
2023-01-23 00:48:27.341068: step: 2104/526, loss: 0.2566892206668854
==================================================
Loss: 0.155
--------------------
Dev: {'event': {'p': 0.6257995735607675, 'r': 0.7816245006657789, 'f1': 0.6950858496151568}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Test: {'event': {'p': 0.623113410952997, 'r': 0.7541753653444676, 'f1': 0.6824085005903188}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Chinese: {'event': {'p': 0.5569620253164557, 'r': 0.8148148148148148, 'f1': 0.6616541353383458}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Korean: {'event': {'p': 0.7446808510638298, 'r': 0.5555555555555556, 'f1': 0.6363636363636364}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Russian: {'event': {'p': 0.37777777777777777, 'r': 0.4722222222222222, 'f1': 0.4197530864197531}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
New best korean model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6604010025062657, 'r': 0.7017310252996005, 'f1': 0.6804389928986443}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Eng Test for Chinese: {'event': {'p': 0.6480836236933798, 'r': 0.6795407098121086, 'f1': 0.6634394904458599}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Sample Chinese: {'event': {'p': 0.6323529411764706, 'r': 0.7962962962962963, 'f1': 0.7049180327868853}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6257995735607675, 'r': 0.7816245006657789, 'f1': 0.6950858496151568}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Eng Test for Korean: {'event': {'p': 0.623113410952997, 'r': 0.7541753653444676, 'f1': 0.6824085005903188}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Sample Korean: {'event': {'p': 0.7446808510638298, 'r': 0.5555555555555556, 'f1': 0.6363636363636364}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5563041385948027, 'r': 0.7696404793608522, 'f1': 0.6458100558659218}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Eng Test for Russian: {'event': {'p': 0.5336806847785635, 'r': 0.7484342379958246, 'f1': 0.6230719096241583}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Sample Russian: {'event': {'p': 0.5116279069767442, 'r': 0.6111111111111112, 'f1': 0.5569620253164557}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
******************************
Epoch: 8
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 00:49:14.930107: step: 4/526, loss: 0.4509592652320862
2023-01-23 00:49:16.091876: step: 8/526, loss: 0.009682273492217064
2023-01-23 00:49:17.223496: step: 12/526, loss: 0.20073539018630981
2023-01-23 00:49:18.379313: step: 16/526, loss: 0.04364137724041939
2023-01-23 00:49:19.514848: step: 20/526, loss: 0.12309151142835617
2023-01-23 00:49:20.651289: step: 24/526, loss: 0.05186261981725693
2023-01-23 00:49:21.818689: step: 28/526, loss: 0.03564329445362091
2023-01-23 00:49:22.916571: step: 32/526, loss: 0.11937236785888672
2023-01-23 00:49:24.015673: step: 36/526, loss: 0.13100528717041016
2023-01-23 00:49:25.156469: step: 40/526, loss: 0.12632770836353302
2023-01-23 00:49:26.318061: step: 44/526, loss: 0.08592571318149567
2023-01-23 00:49:27.485259: step: 48/526, loss: 0.07140274345874786
2023-01-23 00:49:28.630021: step: 52/526, loss: 0.17488251626491547
2023-01-23 00:49:29.774826: step: 56/526, loss: 0.1383393406867981
2023-01-23 00:49:30.925193: step: 60/526, loss: 0.027023887261748314
2023-01-23 00:49:32.036224: step: 64/526, loss: 0.02628622017800808
2023-01-23 00:49:33.163047: step: 68/526, loss: 0.010891628451645374
2023-01-23 00:49:34.301661: step: 72/526, loss: 0.07957735657691956
2023-01-23 00:49:35.424802: step: 76/526, loss: 0.18381062150001526
2023-01-23 00:49:36.569386: step: 80/526, loss: 0.13099898397922516
2023-01-23 00:49:37.700898: step: 84/526, loss: 0.11448946595191956
2023-01-23 00:49:38.828165: step: 88/526, loss: 0.07045440375804901
2023-01-23 00:49:39.938772: step: 92/526, loss: 0.014455914497375488
2023-01-23 00:49:41.024275: step: 96/526, loss: 0.8065840601921082
2023-01-23 00:49:42.127215: step: 100/526, loss: 0.04395761340856552
2023-01-23 00:49:43.270364: step: 104/526, loss: 0.09363555908203125
2023-01-23 00:49:44.389248: step: 108/526, loss: 0.12660837173461914
2023-01-23 00:49:45.534013: step: 112/526, loss: 0.018051816150546074
2023-01-23 00:49:46.668609: step: 116/526, loss: 0.06137971952557564
2023-01-23 00:49:47.829602: step: 120/526, loss: 0.07128267735242844
2023-01-23 00:49:48.956011: step: 124/526, loss: 0.16976423561573029
2023-01-23 00:49:50.075665: step: 128/526, loss: 0.05111045762896538
2023-01-23 00:49:51.175586: step: 132/526, loss: 0.07206392288208008
2023-01-23 00:49:52.280223: step: 136/526, loss: 0.049035023897886276
2023-01-23 00:49:53.410867: step: 140/526, loss: 0.062110044062137604
2023-01-23 00:49:54.531160: step: 144/526, loss: 0.07096338272094727
2023-01-23 00:49:55.721839: step: 148/526, loss: 0.4366329312324524
2023-01-23 00:49:56.860753: step: 152/526, loss: 0.060074903070926666
2023-01-23 00:49:58.020142: step: 156/526, loss: 0.08557100594043732
2023-01-23 00:49:59.182669: step: 160/526, loss: 0.08230438083410263
2023-01-23 00:50:00.318963: step: 164/526, loss: 0.03566126897931099
2023-01-23 00:50:01.446769: step: 168/526, loss: 0.09695682674646378
2023-01-23 00:50:02.592492: step: 172/526, loss: 0.05592308193445206
2023-01-23 00:50:03.734242: step: 176/526, loss: 0.019489290192723274
2023-01-23 00:50:04.882515: step: 180/526, loss: 0.07788868248462677
2023-01-23 00:50:06.053186: step: 184/526, loss: 0.06774282455444336
2023-01-23 00:50:07.206159: step: 188/526, loss: 0.10261721909046173
2023-01-23 00:50:08.348997: step: 192/526, loss: 0.05845542252063751
2023-01-23 00:50:09.472826: step: 196/526, loss: 0.05750560760498047
2023-01-23 00:50:10.587015: step: 200/526, loss: 0.02927863597869873
2023-01-23 00:50:11.695216: step: 204/526, loss: 0.08807583153247833
2023-01-23 00:50:12.859337: step: 208/526, loss: 0.047608375549316406
2023-01-23 00:50:13.973213: step: 212/526, loss: 0.099675752222538
2023-01-23 00:50:15.120414: step: 216/526, loss: 0.11963607370853424
2023-01-23 00:50:16.248817: step: 220/526, loss: 0.11921291798353195
2023-01-23 00:50:17.384673: step: 224/526, loss: 0.2667018175125122
2023-01-23 00:50:18.537168: step: 228/526, loss: 0.1565166860818863
2023-01-23 00:50:19.666379: step: 232/526, loss: 0.459891140460968
2023-01-23 00:50:20.808050: step: 236/526, loss: 0.023046493530273438
2023-01-23 00:50:21.925453: step: 240/526, loss: 2.904085636138916
2023-01-23 00:50:23.024431: step: 244/526, loss: 0.021080588921904564
2023-01-23 00:50:24.163373: step: 248/526, loss: 0.014219284057617188
2023-01-23 00:50:25.294373: step: 252/526, loss: 0.025008201599121094
2023-01-23 00:50:26.412297: step: 256/526, loss: 0.05641651153564453
2023-01-23 00:50:27.565725: step: 260/526, loss: 0.0062920572236180305
2023-01-23 00:50:28.721501: step: 264/526, loss: 0.12470598518848419
2023-01-23 00:50:29.872655: step: 268/526, loss: 0.08369922637939453
2023-01-23 00:50:31.006471: step: 272/526, loss: 0.07556037604808807
2023-01-23 00:50:32.119118: step: 276/526, loss: 0.08341007679700851
2023-01-23 00:50:33.257955: step: 280/526, loss: 0.11428480595350266
2023-01-23 00:50:34.434139: step: 284/526, loss: 0.9325697422027588
2023-01-23 00:50:35.583145: step: 288/526, loss: 0.18574738502502441
2023-01-23 00:50:36.738682: step: 292/526, loss: 0.02388610877096653
2023-01-23 00:50:37.900027: step: 296/526, loss: 0.04833984375
2023-01-23 00:50:39.062767: step: 300/526, loss: 0.020642375573515892
2023-01-23 00:50:40.192955: step: 304/526, loss: 0.1163792610168457
2023-01-23 00:50:41.346883: step: 308/526, loss: 0.02852320671081543
2023-01-23 00:50:42.481838: step: 312/526, loss: 0.0456182025372982
2023-01-23 00:50:43.606288: step: 316/526, loss: 0.12594766914844513
2023-01-23 00:50:44.735966: step: 320/526, loss: 0.17843884229660034
2023-01-23 00:50:45.872393: step: 324/526, loss: 0.020578479394316673
2023-01-23 00:50:47.035129: step: 328/526, loss: 0.04206524044275284
2023-01-23 00:50:48.174475: step: 332/526, loss: 0.10274887084960938
2023-01-23 00:50:49.300615: step: 336/526, loss: 0.4566787779331207
2023-01-23 00:50:50.438631: step: 340/526, loss: 0.09298267215490341
2023-01-23 00:50:51.558151: step: 344/526, loss: 0.08521173894405365
2023-01-23 00:50:52.689475: step: 348/526, loss: 0.16558514535427094
2023-01-23 00:50:53.827854: step: 352/526, loss: 0.01702265813946724
2023-01-23 00:50:54.943265: step: 356/526, loss: 0.32536476850509644
2023-01-23 00:50:56.090072: step: 360/526, loss: 0.11419686675071716
2023-01-23 00:50:57.207038: step: 364/526, loss: 0.18552808463573456
2023-01-23 00:50:58.342358: step: 368/526, loss: 0.7736044526100159
2023-01-23 00:50:59.491194: step: 372/526, loss: 0.05100994184613228
2023-01-23 00:51:00.607739: step: 376/526, loss: 0.039560794830322266
2023-01-23 00:51:01.762626: step: 380/526, loss: 0.06244611740112305
2023-01-23 00:51:02.901779: step: 384/526, loss: 0.01614541932940483
2023-01-23 00:51:04.042149: step: 388/526, loss: 0.05539894104003906
2023-01-23 00:51:05.140761: step: 392/526, loss: 0.07028555870056152
2023-01-23 00:51:06.285222: step: 396/526, loss: 0.027847956866025925
2023-01-23 00:51:07.419312: step: 400/526, loss: 0.09425429999828339
2023-01-23 00:51:08.532999: step: 404/526, loss: 0.05379796028137207
2023-01-23 00:51:09.663180: step: 408/526, loss: 0.36586126685142517
2023-01-23 00:51:10.816321: step: 412/526, loss: 0.13255101442337036
2023-01-23 00:51:11.978464: step: 416/526, loss: 0.011668015271425247
2023-01-23 00:51:13.127722: step: 420/526, loss: 0.0749419704079628
2023-01-23 00:51:14.244614: step: 424/526, loss: 0.01673254929482937
2023-01-23 00:51:15.348357: step: 428/526, loss: 1.02268385887146
2023-01-23 00:51:16.493437: step: 432/526, loss: 0.21064051985740662
2023-01-23 00:51:17.629064: step: 436/526, loss: 0.25405243039131165
2023-01-23 00:51:18.779022: step: 440/526, loss: 0.0852547436952591
2023-01-23 00:51:19.921961: step: 444/526, loss: 0.006771135609596968
2023-01-23 00:51:21.042732: step: 448/526, loss: 0.02016305923461914
2023-01-23 00:51:22.183009: step: 452/526, loss: 0.01931324042379856
2023-01-23 00:51:23.328860: step: 456/526, loss: 0.046138957142829895
2023-01-23 00:51:24.456896: step: 460/526, loss: 0.01810484007000923
2023-01-23 00:51:25.588686: step: 464/526, loss: 0.2569112777709961
2023-01-23 00:51:26.747577: step: 468/526, loss: 0.0521366149187088
2023-01-23 00:51:27.875627: step: 472/526, loss: 0.21542473137378693
2023-01-23 00:51:28.995803: step: 476/526, loss: 0.10165233910083771
2023-01-23 00:51:30.139826: step: 480/526, loss: 0.1466052085161209
2023-01-23 00:51:31.307087: step: 484/526, loss: 0.06927242130041122
2023-01-23 00:51:32.461801: step: 488/526, loss: 0.1103677749633789
2023-01-23 00:51:33.572985: step: 492/526, loss: 0.02180485799908638
2023-01-23 00:51:34.700480: step: 496/526, loss: 0.13236021995544434
2023-01-23 00:51:35.843733: step: 500/526, loss: 0.008610916323959827
2023-01-23 00:51:36.986674: step: 504/526, loss: 0.05118846893310547
2023-01-23 00:51:38.110536: step: 508/526, loss: 0.02141270600259304
2023-01-23 00:51:39.296813: step: 512/526, loss: 0.0804070457816124
2023-01-23 00:51:40.424886: step: 516/526, loss: 0.11349506676197052
2023-01-23 00:51:41.556410: step: 520/526, loss: 0.36216410994529724
2023-01-23 00:51:42.688779: step: 524/526, loss: 0.033472299575805664
2023-01-23 00:51:43.875400: step: 528/526, loss: 0.024210095405578613
2023-01-23 00:51:45.001334: step: 532/526, loss: 0.0711517333984375
2023-01-23 00:51:46.111538: step: 536/526, loss: 0.1883375197649002
2023-01-23 00:51:47.236015: step: 540/526, loss: 0.03312330320477486
2023-01-23 00:51:48.380958: step: 544/526, loss: 0.16953782737255096
2023-01-23 00:51:49.496266: step: 548/526, loss: 0.07899179309606552
2023-01-23 00:51:50.630805: step: 552/526, loss: 0.0881553664803505
2023-01-23 00:51:51.829678: step: 556/526, loss: 0.05763111263513565
2023-01-23 00:51:52.992289: step: 560/526, loss: 0.10114964842796326
2023-01-23 00:51:54.127735: step: 564/526, loss: 0.07979154586791992
2023-01-23 00:51:55.291870: step: 568/526, loss: 0.21123342216014862
2023-01-23 00:51:56.419683: step: 572/526, loss: 0.049878671765327454
2023-01-23 00:51:57.553331: step: 576/526, loss: 0.057035066187381744
2023-01-23 00:51:58.704449: step: 580/526, loss: 0.13447979092597961
2023-01-23 00:51:59.804475: step: 584/526, loss: 0.16881036758422852
2023-01-23 00:52:00.947161: step: 588/526, loss: 0.08310695737600327
2023-01-23 00:52:02.090624: step: 592/526, loss: 0.14080849289894104
2023-01-23 00:52:03.224449: step: 596/526, loss: 0.12084797024726868
2023-01-23 00:52:04.364196: step: 600/526, loss: 0.03946685791015625
2023-01-23 00:52:05.507668: step: 604/526, loss: 0.11840762943029404
2023-01-23 00:52:06.632393: step: 608/526, loss: 0.38136404752731323
2023-01-23 00:52:07.728714: step: 612/526, loss: 0.0014248609077185392
2023-01-23 00:52:08.842130: step: 616/526, loss: 0.03033771552145481
2023-01-23 00:52:10.001282: step: 620/526, loss: 0.030315257608890533
2023-01-23 00:52:11.159512: step: 624/526, loss: 0.08245439827442169
2023-01-23 00:52:12.286724: step: 628/526, loss: 0.017532777041196823
2023-01-23 00:52:13.464151: step: 632/526, loss: 0.2039492428302765
2023-01-23 00:52:14.616144: step: 636/526, loss: 0.027325155213475227
2023-01-23 00:52:15.739660: step: 640/526, loss: 0.07786641269922256
2023-01-23 00:52:16.870284: step: 644/526, loss: 0.009795594029128551
2023-01-23 00:52:18.014302: step: 648/526, loss: 0.14057111740112305
2023-01-23 00:52:19.165314: step: 652/526, loss: 0.08568086475133896
2023-01-23 00:52:20.297932: step: 656/526, loss: 0.12078313529491425
2023-01-23 00:52:21.469011: step: 660/526, loss: 0.07834787666797638
2023-01-23 00:52:22.599559: step: 664/526, loss: 0.10383033752441406
2023-01-23 00:52:23.776056: step: 668/526, loss: 0.05333023518323898
2023-01-23 00:52:24.918109: step: 672/526, loss: 0.08539829403162003
2023-01-23 00:52:26.071676: step: 676/526, loss: 0.04530048370361328
2023-01-23 00:52:27.211813: step: 680/526, loss: 0.019302750006318092
2023-01-23 00:52:28.358599: step: 684/526, loss: 0.44927406311035156
2023-01-23 00:52:29.508253: step: 688/526, loss: 0.07670411467552185
2023-01-23 00:52:30.685402: step: 692/526, loss: 0.03258876875042915
2023-01-23 00:52:31.824590: step: 696/526, loss: 0.11091528087854385
2023-01-23 00:52:32.940250: step: 700/526, loss: 0.01544036902487278
2023-01-23 00:52:34.068394: step: 704/526, loss: 0.036835383623838425
2023-01-23 00:52:35.214349: step: 708/526, loss: 0.031983375549316406
2023-01-23 00:52:36.351553: step: 712/526, loss: 0.026570988819003105
2023-01-23 00:52:37.482412: step: 716/526, loss: 0.013112116605043411
2023-01-23 00:52:38.616515: step: 720/526, loss: 0.06713657081127167
2023-01-23 00:52:39.777950: step: 724/526, loss: 0.18842096626758575
2023-01-23 00:52:40.914776: step: 728/526, loss: 0.3138576149940491
2023-01-23 00:52:42.055317: step: 732/526, loss: 0.030364610254764557
2023-01-23 00:52:43.177435: step: 736/526, loss: 0.01774129830300808
2023-01-23 00:52:44.337514: step: 740/526, loss: 0.02115321159362793
2023-01-23 00:52:45.452642: step: 744/526, loss: 0.10952109843492508
2023-01-23 00:52:46.578361: step: 748/526, loss: 0.1439904272556305
2023-01-23 00:52:47.721281: step: 752/526, loss: 0.015142631717026234
2023-01-23 00:52:48.849693: step: 756/526, loss: 0.09855957329273224
2023-01-23 00:52:49.999238: step: 760/526, loss: 0.04211006313562393
2023-01-23 00:52:51.154168: step: 764/526, loss: 0.2005455195903778
2023-01-23 00:52:52.299813: step: 768/526, loss: 0.6141564846038818
2023-01-23 00:52:53.418141: step: 772/526, loss: 0.09879302978515625
2023-01-23 00:52:54.532914: step: 776/526, loss: 0.4876483976840973
2023-01-23 00:52:55.662630: step: 780/526, loss: 0.11870536208152771
2023-01-23 00:52:56.803510: step: 784/526, loss: 0.03438301011919975
2023-01-23 00:52:57.954048: step: 788/526, loss: 0.07214164733886719
2023-01-23 00:52:59.098036: step: 792/526, loss: 0.04700946807861328
2023-01-23 00:53:00.245869: step: 796/526, loss: 0.005422401241958141
2023-01-23 00:53:01.382166: step: 800/526, loss: 0.07056216895580292
2023-01-23 00:53:02.507122: step: 804/526, loss: 0.11131231486797333
2023-01-23 00:53:03.618903: step: 808/526, loss: 0.15480156242847443
2023-01-23 00:53:04.750652: step: 812/526, loss: 0.026541804894804955
2023-01-23 00:53:05.867597: step: 816/526, loss: 0.06710920482873917
2023-01-23 00:53:06.972831: step: 820/526, loss: 0.11994200199842453
2023-01-23 00:53:08.122600: step: 824/526, loss: 0.01672639697790146
2023-01-23 00:53:09.254477: step: 828/526, loss: 0.0629308670759201
2023-01-23 00:53:10.381062: step: 832/526, loss: 0.14385686814785004
2023-01-23 00:53:11.481042: step: 836/526, loss: 0.010058593936264515
2023-01-23 00:53:12.641918: step: 840/526, loss: 0.07296065986156464
2023-01-23 00:53:13.774575: step: 844/526, loss: 0.2944096624851227
2023-01-23 00:53:14.910028: step: 848/526, loss: 0.022469425573945045
2023-01-23 00:53:16.051669: step: 852/526, loss: 0.46562662720680237
2023-01-23 00:53:17.175760: step: 856/526, loss: 0.029773712158203125
2023-01-23 00:53:18.314266: step: 860/526, loss: 0.13548488914966583
2023-01-23 00:53:19.469440: step: 864/526, loss: 0.09199275821447372
2023-01-23 00:53:20.613849: step: 868/526, loss: 0.1318870633840561
2023-01-23 00:53:21.773005: step: 872/526, loss: 0.2812376022338867
2023-01-23 00:53:22.933824: step: 876/526, loss: 0.040105536580085754
2023-01-23 00:53:24.076540: step: 880/526, loss: 0.18516980111598969
2023-01-23 00:53:25.229317: step: 884/526, loss: 0.5230588316917419
2023-01-23 00:53:26.387561: step: 888/526, loss: 0.08030033111572266
2023-01-23 00:53:27.485521: step: 892/526, loss: 0.06456517428159714
2023-01-23 00:53:28.610975: step: 896/526, loss: 0.11795501410961151
2023-01-23 00:53:29.726109: step: 900/526, loss: 0.02095651626586914
2023-01-23 00:53:30.876412: step: 904/526, loss: 0.023101331666111946
2023-01-23 00:53:32.009615: step: 908/526, loss: 0.04510049894452095
2023-01-23 00:53:33.145707: step: 912/526, loss: 0.01420135423541069
2023-01-23 00:53:34.297591: step: 916/526, loss: 0.014659309759736061
2023-01-23 00:53:35.458867: step: 920/526, loss: 0.2086995393037796
2023-01-23 00:53:36.589795: step: 924/526, loss: 0.12090644985437393
2023-01-23 00:53:37.701830: step: 928/526, loss: 0.12550897896289825
2023-01-23 00:53:38.842782: step: 932/526, loss: 0.10923528671264648
2023-01-23 00:53:39.982547: step: 936/526, loss: 0.13390541076660156
2023-01-23 00:53:41.122746: step: 940/526, loss: 0.31669092178344727
2023-01-23 00:53:42.242970: step: 944/526, loss: 0.08669109642505646
2023-01-23 00:53:43.350284: step: 948/526, loss: 0.004893970675766468
2023-01-23 00:53:44.486525: step: 952/526, loss: 0.07659421116113663
2023-01-23 00:53:45.620326: step: 956/526, loss: 0.04791421815752983
2023-01-23 00:53:46.763495: step: 960/526, loss: 0.0898553803563118
2023-01-23 00:53:47.926775: step: 964/526, loss: 0.1253407597541809
2023-01-23 00:53:49.079147: step: 968/526, loss: 0.09322299808263779
2023-01-23 00:53:50.207192: step: 972/526, loss: 0.032363034784793854
2023-01-23 00:53:51.355874: step: 976/526, loss: 0.12266630679368973
2023-01-23 00:53:52.524372: step: 980/526, loss: 0.12242374569177628
2023-01-23 00:53:53.666647: step: 984/526, loss: 0.0991489440202713
2023-01-23 00:53:54.796540: step: 988/526, loss: 0.35024648904800415
2023-01-23 00:53:55.906180: step: 992/526, loss: 0.03630800172686577
2023-01-23 00:53:57.058570: step: 996/526, loss: 0.07523689419031143
2023-01-23 00:53:58.179075: step: 1000/526, loss: 0.03704657778143883
2023-01-23 00:53:59.328267: step: 1004/526, loss: 0.265733927488327
2023-01-23 00:54:00.454945: step: 1008/526, loss: 0.06460990756750107
2023-01-23 00:54:01.616002: step: 1012/526, loss: 0.08989782631397247
2023-01-23 00:54:02.737554: step: 1016/526, loss: 0.07344035804271698
2023-01-23 00:54:03.888866: step: 1020/526, loss: 0.23651272058486938
2023-01-23 00:54:05.015576: step: 1024/526, loss: 0.014575100503861904
2023-01-23 00:54:06.134137: step: 1028/526, loss: 1.0429644584655762
2023-01-23 00:54:07.282123: step: 1032/526, loss: 0.1339537650346756
2023-01-23 00:54:08.411223: step: 1036/526, loss: 0.12161803245544434
2023-01-23 00:54:09.530747: step: 1040/526, loss: 0.082611083984375
2023-01-23 00:54:10.625229: step: 1044/526, loss: 0.036517977714538574
2023-01-23 00:54:11.725929: step: 1048/526, loss: 0.05288155376911163
2023-01-23 00:54:12.903382: step: 1052/526, loss: 0.0292205810546875
2023-01-23 00:54:14.018531: step: 1056/526, loss: 0.09984450787305832
2023-01-23 00:54:15.129793: step: 1060/526, loss: 0.03174543380737305
2023-01-23 00:54:16.218018: step: 1064/526, loss: 0.14022216200828552
2023-01-23 00:54:17.345812: step: 1068/526, loss: 0.06268835067749023
2023-01-23 00:54:18.456292: step: 1072/526, loss: 0.26589494943618774
2023-01-23 00:54:19.628382: step: 1076/526, loss: 0.11476574093103409
2023-01-23 00:54:20.780670: step: 1080/526, loss: 0.3752923905849457
2023-01-23 00:54:21.891019: step: 1084/526, loss: 0.02142627164721489
2023-01-23 00:54:23.073050: step: 1088/526, loss: 0.5172773599624634
2023-01-23 00:54:24.199960: step: 1092/526, loss: 0.044009022414684296
2023-01-23 00:54:25.345953: step: 1096/526, loss: 0.08822555840015411
2023-01-23 00:54:26.478465: step: 1100/526, loss: 0.019056033343076706
2023-01-23 00:54:27.622132: step: 1104/526, loss: 0.03240513801574707
2023-01-23 00:54:28.756798: step: 1108/526, loss: 0.08362092822790146
2023-01-23 00:54:29.911473: step: 1112/526, loss: 0.02197418175637722
2023-01-23 00:54:31.051572: step: 1116/526, loss: 0.05853843688964844
2023-01-23 00:54:32.183536: step: 1120/526, loss: 0.030892515555024147
2023-01-23 00:54:33.338171: step: 1124/526, loss: 0.02810525894165039
2023-01-23 00:54:34.510307: step: 1128/526, loss: 0.19932176172733307
2023-01-23 00:54:35.672526: step: 1132/526, loss: 0.13839474320411682
2023-01-23 00:54:36.796824: step: 1136/526, loss: 0.05189061537384987
2023-01-23 00:54:37.901193: step: 1140/526, loss: 0.058396339416503906
2023-01-23 00:54:39.028027: step: 1144/526, loss: 0.05872382968664169
2023-01-23 00:54:40.148457: step: 1148/526, loss: 0.7279013395309448
2023-01-23 00:54:41.271100: step: 1152/526, loss: 0.03947272524237633
2023-01-23 00:54:42.407159: step: 1156/526, loss: 0.00186672224663198
2023-01-23 00:54:43.523795: step: 1160/526, loss: 0.06262989342212677
2023-01-23 00:54:44.655047: step: 1164/526, loss: 0.06388092786073685
2023-01-23 00:54:45.768961: step: 1168/526, loss: 0.018650412559509277
2023-01-23 00:54:46.917655: step: 1172/526, loss: 0.12528343498706818
2023-01-23 00:54:48.047915: step: 1176/526, loss: 0.1625482589006424
2023-01-23 00:54:49.148458: step: 1180/526, loss: 0.025317644700407982
2023-01-23 00:54:50.283850: step: 1184/526, loss: 0.03203906863927841
2023-01-23 00:54:51.435110: step: 1188/526, loss: 0.03545050695538521
2023-01-23 00:54:52.563357: step: 1192/526, loss: 0.04661398008465767
2023-01-23 00:54:53.690936: step: 1196/526, loss: 0.08548067510128021
2023-01-23 00:54:54.825515: step: 1200/526, loss: 0.3050301671028137
2023-01-23 00:54:55.944934: step: 1204/526, loss: 0.010405827313661575
2023-01-23 00:54:57.071013: step: 1208/526, loss: 0.09387321770191193
2023-01-23 00:54:58.171163: step: 1212/526, loss: 0.02991638332605362
2023-01-23 00:54:59.284879: step: 1216/526, loss: 0.20187081396579742
2023-01-23 00:55:00.398360: step: 1220/526, loss: 0.0730188861489296
2023-01-23 00:55:01.549773: step: 1224/526, loss: 0.05721969157457352
2023-01-23 00:55:02.684411: step: 1228/526, loss: 0.044106196612119675
2023-01-23 00:55:03.862297: step: 1232/526, loss: 0.035642530769109726
2023-01-23 00:55:05.020136: step: 1236/526, loss: 0.05703568831086159
2023-01-23 00:55:06.167383: step: 1240/526, loss: 0.016860295087099075
2023-01-23 00:55:07.352219: step: 1244/526, loss: 0.06117277592420578
2023-01-23 00:55:08.503372: step: 1248/526, loss: 0.027732277289032936
2023-01-23 00:55:09.627444: step: 1252/526, loss: 0.04078684002161026
2023-01-23 00:55:10.778410: step: 1256/526, loss: 0.03658314049243927
2023-01-23 00:55:11.927171: step: 1260/526, loss: 0.5496713519096375
2023-01-23 00:55:13.085376: step: 1264/526, loss: 0.05313711240887642
2023-01-23 00:55:14.240676: step: 1268/526, loss: 0.08549108356237411
2023-01-23 00:55:15.385017: step: 1272/526, loss: 0.06908149272203445
2023-01-23 00:55:16.485647: step: 1276/526, loss: 0.014507818035781384
2023-01-23 00:55:17.607992: step: 1280/526, loss: 0.10577650368213654
2023-01-23 00:55:18.733254: step: 1284/526, loss: 0.29365384578704834
2023-01-23 00:55:19.888308: step: 1288/526, loss: 0.04140627384185791
2023-01-23 00:55:21.042016: step: 1292/526, loss: 0.2889742851257324
2023-01-23 00:55:22.179170: step: 1296/526, loss: 0.5034885406494141
2023-01-23 00:55:23.316625: step: 1300/526, loss: 0.13891348242759705
2023-01-23 00:55:24.463800: step: 1304/526, loss: 0.111005499958992
2023-01-23 00:55:25.615863: step: 1308/526, loss: 0.11884107440710068
2023-01-23 00:55:26.765354: step: 1312/526, loss: 0.008743476122617722
2023-01-23 00:55:27.923703: step: 1316/526, loss: 0.10264606773853302
2023-01-23 00:55:29.052045: step: 1320/526, loss: 0.07501468807458878
2023-01-23 00:55:30.203704: step: 1324/526, loss: 0.16715145111083984
2023-01-23 00:55:31.358708: step: 1328/526, loss: 0.09068889915943146
2023-01-23 00:55:32.490342: step: 1332/526, loss: 0.9852508306503296
2023-01-23 00:55:33.621679: step: 1336/526, loss: 0.11147145926952362
2023-01-23 00:55:34.739994: step: 1340/526, loss: 0.08434734493494034
2023-01-23 00:55:35.850147: step: 1344/526, loss: 0.08265219628810883
2023-01-23 00:55:36.983636: step: 1348/526, loss: 0.01094741839915514
2023-01-23 00:55:38.128066: step: 1352/526, loss: 0.07162294536828995
2023-01-23 00:55:39.284595: step: 1356/526, loss: 0.02768879011273384
2023-01-23 00:55:40.395271: step: 1360/526, loss: 0.06671638786792755
2023-01-23 00:55:41.525620: step: 1364/526, loss: 0.46332302689552307
2023-01-23 00:55:42.643103: step: 1368/526, loss: 0.09154520183801651
2023-01-23 00:55:43.739162: step: 1372/526, loss: 0.09058380126953125
2023-01-23 00:55:44.847796: step: 1376/526, loss: 0.11177539825439453
2023-01-23 00:55:46.000063: step: 1380/526, loss: 0.405598908662796
2023-01-23 00:55:47.153617: step: 1384/526, loss: 0.0658111572265625
2023-01-23 00:55:48.283438: step: 1388/526, loss: 0.0830145925283432
2023-01-23 00:55:49.430915: step: 1392/526, loss: 0.025028228759765625
2023-01-23 00:55:50.553460: step: 1396/526, loss: 0.04585247114300728
2023-01-23 00:55:51.678649: step: 1400/526, loss: 0.046415187418460846
2023-01-23 00:55:52.793199: step: 1404/526, loss: 0.08061465620994568
2023-01-23 00:55:53.953420: step: 1408/526, loss: 0.1907079815864563
2023-01-23 00:55:55.075994: step: 1412/526, loss: 0.117953822016716
2023-01-23 00:55:56.203251: step: 1416/526, loss: 0.6954421997070312
2023-01-23 00:55:57.318662: step: 1420/526, loss: 0.06044788658618927
2023-01-23 00:55:58.457282: step: 1424/526, loss: 0.2675694525241852
2023-01-23 00:55:59.587601: step: 1428/526, loss: 0.042508531361818314
2023-01-23 00:56:00.698595: step: 1432/526, loss: 0.013435173779726028
2023-01-23 00:56:01.827694: step: 1436/526, loss: 0.0046634674072265625
2023-01-23 00:56:02.969343: step: 1440/526, loss: 0.14389826357364655
2023-01-23 00:56:04.084082: step: 1444/526, loss: 0.13436804711818695
2023-01-23 00:56:05.242408: step: 1448/526, loss: 1.344647765159607
2023-01-23 00:56:06.374947: step: 1452/526, loss: 0.20523148775100708
2023-01-23 00:56:07.501499: step: 1456/526, loss: 0.09275570511817932
2023-01-23 00:56:08.617438: step: 1460/526, loss: 0.058936458081007004
2023-01-23 00:56:09.741620: step: 1464/526, loss: 0.1774713695049286
2023-01-23 00:56:10.855515: step: 1468/526, loss: 0.18755581974983215
2023-01-23 00:56:11.976947: step: 1472/526, loss: 0.06118784099817276
2023-01-23 00:56:13.101752: step: 1476/526, loss: 0.0021563530899584293
2023-01-23 00:56:14.246393: step: 1480/526, loss: 0.21430516242980957
2023-01-23 00:56:15.377746: step: 1484/526, loss: 0.14232167601585388
2023-01-23 00:56:16.510948: step: 1488/526, loss: 0.09897498786449432
2023-01-23 00:56:17.637269: step: 1492/526, loss: 0.1261250078678131
2023-01-23 00:56:18.775162: step: 1496/526, loss: 0.13158316910266876
2023-01-23 00:56:19.910458: step: 1500/526, loss: 0.04002013057470322
2023-01-23 00:56:21.050319: step: 1504/526, loss: 0.14873509109020233
2023-01-23 00:56:22.193991: step: 1508/526, loss: 0.14446449279785156
2023-01-23 00:56:23.321946: step: 1512/526, loss: 0.08695831894874573
2023-01-23 00:56:24.448307: step: 1516/526, loss: 0.24661703407764435
2023-01-23 00:56:25.559201: step: 1520/526, loss: 0.14397135376930237
2023-01-23 00:56:26.705933: step: 1524/526, loss: 0.1595521867275238
2023-01-23 00:56:27.848886: step: 1528/526, loss: 0.04168272018432617
2023-01-23 00:56:28.977294: step: 1532/526, loss: 0.11637590080499649
2023-01-23 00:56:30.095607: step: 1536/526, loss: 0.20395943522453308
2023-01-23 00:56:31.245905: step: 1540/526, loss: 0.30232658982276917
2023-01-23 00:56:32.393130: step: 1544/526, loss: 0.11829891800880432
2023-01-23 00:56:33.545785: step: 1548/526, loss: 0.06865549087524414
2023-01-23 00:56:34.706053: step: 1552/526, loss: 0.2947154939174652
2023-01-23 00:56:35.832185: step: 1556/526, loss: 0.005326509475708008
2023-01-23 00:56:36.961962: step: 1560/526, loss: 0.04194007068872452
2023-01-23 00:56:38.103579: step: 1564/526, loss: 0.1535348892211914
2023-01-23 00:56:39.246259: step: 1568/526, loss: 0.1386076956987381
2023-01-23 00:56:40.392186: step: 1572/526, loss: 0.1179957389831543
2023-01-23 00:56:41.506419: step: 1576/526, loss: 0.09382247924804688
2023-01-23 00:56:42.616220: step: 1580/526, loss: 0.07488055527210236
2023-01-23 00:56:43.741517: step: 1584/526, loss: 0.03157339245080948
2023-01-23 00:56:44.875092: step: 1588/526, loss: 0.05361314117908478
2023-01-23 00:56:46.009561: step: 1592/526, loss: 0.06537432968616486
2023-01-23 00:56:47.129681: step: 1596/526, loss: 0.02526872232556343
2023-01-23 00:56:48.290144: step: 1600/526, loss: 0.13180875778198242
2023-01-23 00:56:49.418628: step: 1604/526, loss: 0.012719536200165749
2023-01-23 00:56:50.545785: step: 1608/526, loss: 0.015569686889648438
2023-01-23 00:56:51.667502: step: 1612/526, loss: 0.2748333513736725
2023-01-23 00:56:52.802969: step: 1616/526, loss: 0.11798276752233505
2023-01-23 00:56:53.912824: step: 1620/526, loss: 0.059235960245132446
2023-01-23 00:56:55.061997: step: 1624/526, loss: 0.054703906178474426
2023-01-23 00:56:56.176435: step: 1628/526, loss: 0.08646111190319061
2023-01-23 00:56:57.324548: step: 1632/526, loss: 0.13414783775806427
2023-01-23 00:56:58.463686: step: 1636/526, loss: 0.15013009309768677
2023-01-23 00:56:59.601174: step: 1640/526, loss: 0.06078920513391495
2023-01-23 00:57:00.742279: step: 1644/526, loss: 0.05789661407470703
2023-01-23 00:57:01.847146: step: 1648/526, loss: 0.009781932458281517
2023-01-23 00:57:03.008549: step: 1652/526, loss: 0.088352732360363
2023-01-23 00:57:04.160332: step: 1656/526, loss: 0.11192426830530167
2023-01-23 00:57:05.292976: step: 1660/526, loss: 0.1688070297241211
2023-01-23 00:57:06.420485: step: 1664/526, loss: 0.05373840406537056
2023-01-23 00:57:07.576183: step: 1668/526, loss: 0.15043525397777557
2023-01-23 00:57:08.715741: step: 1672/526, loss: 0.293840616941452
2023-01-23 00:57:09.842837: step: 1676/526, loss: 0.0830683708190918
2023-01-23 00:57:10.994209: step: 1680/526, loss: 0.21626701951026917
2023-01-23 00:57:12.123885: step: 1684/526, loss: 0.4208146631717682
2023-01-23 00:57:13.324764: step: 1688/526, loss: 0.09813422709703445
2023-01-23 00:57:14.471180: step: 1692/526, loss: 0.2739488184452057
2023-01-23 00:57:15.581413: step: 1696/526, loss: 0.018120765686035156
2023-01-23 00:57:16.716576: step: 1700/526, loss: 0.27012139558792114
2023-01-23 00:57:17.856482: step: 1704/526, loss: 0.3360114097595215
2023-01-23 00:57:18.959597: step: 1708/526, loss: 0.17406173050403595
2023-01-23 00:57:20.095701: step: 1712/526, loss: 0.015485573559999466
2023-01-23 00:57:21.223499: step: 1716/526, loss: 0.09435214847326279
2023-01-23 00:57:22.375360: step: 1720/526, loss: 0.7589371204376221
2023-01-23 00:57:23.533359: step: 1724/526, loss: 0.05659975856542587
2023-01-23 00:57:24.684381: step: 1728/526, loss: 0.1485244780778885
2023-01-23 00:57:25.857015: step: 1732/526, loss: 0.09022854268550873
2023-01-23 00:57:26.966695: step: 1736/526, loss: 0.02278771437704563
2023-01-23 00:57:28.086294: step: 1740/526, loss: 0.11888370662927628
2023-01-23 00:57:29.204263: step: 1744/526, loss: 0.1495838165283203
2023-01-23 00:57:30.336661: step: 1748/526, loss: 0.08892793953418732
2023-01-23 00:57:31.473299: step: 1752/526, loss: 0.2684028744697571
2023-01-23 00:57:32.614382: step: 1756/526, loss: 0.06688585132360458
2023-01-23 00:57:33.731102: step: 1760/526, loss: 0.015359879471361637
2023-01-23 00:57:34.848296: step: 1764/526, loss: 0.24693012237548828
2023-01-23 00:57:36.010978: step: 1768/526, loss: 0.08525620400905609
2023-01-23 00:57:37.150608: step: 1772/526, loss: 0.22598764300346375
2023-01-23 00:57:38.261378: step: 1776/526, loss: 0.06120362505316734
2023-01-23 00:57:39.409001: step: 1780/526, loss: 0.0734894722700119
2023-01-23 00:57:40.561737: step: 1784/526, loss: 0.011290360242128372
2023-01-23 00:57:41.687270: step: 1788/526, loss: 0.07968025654554367
2023-01-23 00:57:42.796481: step: 1792/526, loss: 0.05257873609662056
2023-01-23 00:57:43.935878: step: 1796/526, loss: 0.11113350093364716
2023-01-23 00:57:45.066428: step: 1800/526, loss: 0.07039546966552734
2023-01-23 00:57:46.186141: step: 1804/526, loss: 0.20111922919750214
2023-01-23 00:57:47.300103: step: 1808/526, loss: 0.017680644989013672
2023-01-23 00:57:48.415448: step: 1812/526, loss: 0.026076506823301315
2023-01-23 00:57:49.557974: step: 1816/526, loss: 0.08258219063282013
2023-01-23 00:57:50.710985: step: 1820/526, loss: 0.08950748294591904
2023-01-23 00:57:51.810641: step: 1824/526, loss: 0.031737376004457474
2023-01-23 00:57:52.961475: step: 1828/526, loss: 0.27701932191848755
2023-01-23 00:57:54.106401: step: 1832/526, loss: 0.013955689035356045
2023-01-23 00:57:55.255193: step: 1836/526, loss: 0.45228147506713867
2023-01-23 00:57:56.407388: step: 1840/526, loss: 0.02460331842303276
2023-01-23 00:57:57.519810: step: 1844/526, loss: 0.0606042854487896
2023-01-23 00:57:58.655995: step: 1848/526, loss: 0.3637872636318207
2023-01-23 00:57:59.782475: step: 1852/526, loss: 0.09964275360107422
2023-01-23 00:58:00.911824: step: 1856/526, loss: 0.032918740063905716
2023-01-23 00:58:02.031308: step: 1860/526, loss: 0.21822606027126312
2023-01-23 00:58:03.167427: step: 1864/526, loss: 0.029240990057587624
2023-01-23 00:58:04.307049: step: 1868/526, loss: 0.11280885338783264
2023-01-23 00:58:05.437958: step: 1872/526, loss: 0.08848877251148224
2023-01-23 00:58:06.564217: step: 1876/526, loss: 0.11782693862915039
2023-01-23 00:58:07.702812: step: 1880/526, loss: 0.10418033599853516
2023-01-23 00:58:08.840670: step: 1884/526, loss: 0.03960847854614258
2023-01-23 00:58:09.974699: step: 1888/526, loss: 0.029823780059814453
2023-01-23 00:58:11.107558: step: 1892/526, loss: 0.04397788271307945
2023-01-23 00:58:12.222055: step: 1896/526, loss: 0.11380930989980698
2023-01-23 00:58:13.350328: step: 1900/526, loss: 0.06160225719213486
2023-01-23 00:58:14.485193: step: 1904/526, loss: 0.2855139374732971
2023-01-23 00:58:15.605508: step: 1908/526, loss: 0.7506707906723022
2023-01-23 00:58:16.755039: step: 1912/526, loss: 0.0538908950984478
2023-01-23 00:58:17.876808: step: 1916/526, loss: 0.22454842925071716
2023-01-23 00:58:18.998446: step: 1920/526, loss: 0.003399467561393976
2023-01-23 00:58:20.116333: step: 1924/526, loss: 0.026694048196077347
2023-01-23 00:58:21.246077: step: 1928/526, loss: 0.5568329095840454
2023-01-23 00:58:22.405454: step: 1932/526, loss: 0.0950227826833725
2023-01-23 00:58:23.542445: step: 1936/526, loss: 0.08688707649707794
2023-01-23 00:58:24.678453: step: 1940/526, loss: 0.12432795017957687
2023-01-23 00:58:25.803076: step: 1944/526, loss: 0.09275256097316742
2023-01-23 00:58:26.927369: step: 1948/526, loss: 0.02868051640689373
2023-01-23 00:58:28.076837: step: 1952/526, loss: 0.0698302760720253
2023-01-23 00:58:29.222229: step: 1956/526, loss: 0.07321586459875107
2023-01-23 00:58:30.343350: step: 1960/526, loss: 0.040228843688964844
2023-01-23 00:58:31.484217: step: 1964/526, loss: 0.17586413025856018
2023-01-23 00:58:32.599033: step: 1968/526, loss: 0.07969598472118378
2023-01-23 00:58:33.709320: step: 1972/526, loss: 0.11393904685974121
2023-01-23 00:58:34.858412: step: 1976/526, loss: 0.036074426025152206
2023-01-23 00:58:35.974127: step: 1980/526, loss: 0.39023932814598083
2023-01-23 00:58:37.111768: step: 1984/526, loss: 0.02489762380719185
2023-01-23 00:58:38.254519: step: 1988/526, loss: 0.039016008377075195
2023-01-23 00:58:39.409569: step: 1992/526, loss: 0.21317899227142334
2023-01-23 00:58:40.544440: step: 1996/526, loss: 0.037840940058231354
2023-01-23 00:58:41.685830: step: 2000/526, loss: 0.17182107269763947
2023-01-23 00:58:42.849816: step: 2004/526, loss: 0.032541655004024506
2023-01-23 00:58:43.979409: step: 2008/526, loss: 0.060860924422740936
2023-01-23 00:58:45.108980: step: 2012/526, loss: 0.04920406639575958
2023-01-23 00:58:46.227947: step: 2016/526, loss: 0.08759719878435135
2023-01-23 00:58:47.354091: step: 2020/526, loss: 0.07130040973424911
2023-01-23 00:58:48.483607: step: 2024/526, loss: 0.06774139404296875
2023-01-23 00:58:49.619650: step: 2028/526, loss: 0.15149059891700745
2023-01-23 00:58:50.767723: step: 2032/526, loss: 0.03901328891515732
2023-01-23 00:58:51.963860: step: 2036/526, loss: 0.04768018424510956
2023-01-23 00:58:53.117633: step: 2040/526, loss: 0.13834437727928162
2023-01-23 00:58:54.244935: step: 2044/526, loss: 0.13579322397708893
2023-01-23 00:58:55.419428: step: 2048/526, loss: 0.11051268875598907
2023-01-23 00:58:56.552618: step: 2052/526, loss: 0.05337200313806534
2023-01-23 00:58:57.699722: step: 2056/526, loss: 0.02866397053003311
2023-01-23 00:58:58.858893: step: 2060/526, loss: 0.12159357219934464
2023-01-23 00:58:59.986359: step: 2064/526, loss: 0.046639252454042435
2023-01-23 00:59:01.105862: step: 2068/526, loss: 0.3356172740459442
2023-01-23 00:59:02.259833: step: 2072/526, loss: 0.1432534158229828
2023-01-23 00:59:03.383452: step: 2076/526, loss: 0.2417449951171875
2023-01-23 00:59:04.538818: step: 2080/526, loss: 0.07272524386644363
2023-01-23 00:59:05.675970: step: 2084/526, loss: 0.05484972149133682
2023-01-23 00:59:06.796249: step: 2088/526, loss: 0.12363357841968536
2023-01-23 00:59:07.927054: step: 2092/526, loss: 0.025763511657714844
2023-01-23 00:59:09.058014: step: 2096/526, loss: 0.0769733414053917
2023-01-23 00:59:10.187966: step: 2100/526, loss: 0.11375121772289276
2023-01-23 00:59:11.343939: step: 2104/526, loss: 0.049809932708740234
==================================================
Loss: 0.130
--------------------
Dev: {'event': {'p': 0.60687432867884, 'r': 0.7523302263648469, 'f1': 0.6718192627824019}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Test: {'event': {'p': 0.6179966044142614, 'r': 0.7599164926931107, 'f1': 0.6816479400749064}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Chinese: {'event': {'p': 0.5844155844155844, 'r': 0.8333333333333334, 'f1': 0.6870229007633588}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Korean: {'event': {'p': 0.7714285714285715, 'r': 0.42857142857142855, 'f1': 0.5510204081632654}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Russian: {'event': {'p': 0.5263157894736842, 'r': 0.5555555555555556, 'f1': 0.5405405405405405}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
New best russian model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6604010025062657, 'r': 0.7017310252996005, 'f1': 0.6804389928986443}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Eng Test for Chinese: {'event': {'p': 0.6480836236933798, 'r': 0.6795407098121086, 'f1': 0.6634394904458599}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Sample Chinese: {'event': {'p': 0.6323529411764706, 'r': 0.7962962962962963, 'f1': 0.7049180327868853}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6257995735607675, 'r': 0.7816245006657789, 'f1': 0.6950858496151568}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Eng Test for Korean: {'event': {'p': 0.623113410952997, 'r': 0.7541753653444676, 'f1': 0.6824085005903188}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Sample Korean: {'event': {'p': 0.7446808510638298, 'r': 0.5555555555555556, 'f1': 0.6363636363636364}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
--------------------
Eng Dev for Russian: {'event': {'p': 0.60687432867884, 'r': 0.7523302263648469, 'f1': 0.6718192627824019}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Russian: {'event': {'p': 0.6179966044142614, 'r': 0.7599164926931107, 'f1': 0.6816479400749064}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Russian: {'event': {'p': 0.5263157894736842, 'r': 0.5555555555555556, 'f1': 0.5405405405405405}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
******************************
Epoch: 9
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 01:00:02.068854: step: 4/526, loss: 0.06273460388183594
2023-01-23 01:00:03.181478: step: 8/526, loss: 0.04972662776708603
2023-01-23 01:00:04.312873: step: 12/526, loss: 0.02827734872698784
2023-01-23 01:00:05.447243: step: 16/526, loss: 0.052943114191293716
2023-01-23 01:00:06.587772: step: 20/526, loss: 0.008646011352539062
2023-01-23 01:00:07.711264: step: 24/526, loss: 0.06134873628616333
2023-01-23 01:00:08.814983: step: 28/526, loss: 0.2242942452430725
2023-01-23 01:00:09.920048: step: 32/526, loss: 0.29536008834838867
2023-01-23 01:00:11.062141: step: 36/526, loss: 0.055123090744018555
2023-01-23 01:00:12.184202: step: 40/526, loss: 0.05992274358868599
2023-01-23 01:00:13.376087: step: 44/526, loss: 0.024144649505615234
2023-01-23 01:00:14.483001: step: 48/526, loss: 0.08518228679895401
2023-01-23 01:00:15.611710: step: 52/526, loss: 0.018128395080566406
2023-01-23 01:00:16.777804: step: 56/526, loss: 0.12564639747142792
2023-01-23 01:00:17.993428: step: 60/526, loss: 0.07249632477760315
2023-01-23 01:00:19.150864: step: 64/526, loss: 0.2735300064086914
2023-01-23 01:00:20.260713: step: 68/526, loss: 0.024007225409150124
2023-01-23 01:00:21.400500: step: 72/526, loss: 0.05489225313067436
2023-01-23 01:00:22.529440: step: 76/526, loss: 0.045737460255622864
2023-01-23 01:00:23.661242: step: 80/526, loss: 0.13226623833179474
2023-01-23 01:00:24.799237: step: 84/526, loss: 0.1825447678565979
2023-01-23 01:00:25.996329: step: 88/526, loss: 0.06590290367603302
2023-01-23 01:00:27.151133: step: 92/526, loss: 0.16964063048362732
2023-01-23 01:00:28.282714: step: 96/526, loss: 0.2701391577720642
2023-01-23 01:00:29.380196: step: 100/526, loss: 0.002492809435352683
2023-01-23 01:00:30.523079: step: 104/526, loss: 0.00204639439471066
2023-01-23 01:00:31.665848: step: 108/526, loss: 0.226235494017601
2023-01-23 01:00:32.795404: step: 112/526, loss: 0.0693480521440506
2023-01-23 01:00:33.938847: step: 116/526, loss: 0.02584218978881836
2023-01-23 01:00:35.058545: step: 120/526, loss: 0.07365093380212784
2023-01-23 01:00:36.177899: step: 124/526, loss: 0.018468167632818222
2023-01-23 01:00:37.334849: step: 128/526, loss: 3.8758349418640137
2023-01-23 01:00:38.467765: step: 132/526, loss: 0.052092649042606354
2023-01-23 01:00:39.602481: step: 136/526, loss: 0.08069362491369247
2023-01-23 01:00:40.722819: step: 140/526, loss: 0.03643073886632919
2023-01-23 01:00:41.857759: step: 144/526, loss: 0.008904552087187767
2023-01-23 01:00:42.989920: step: 148/526, loss: 0.061319828033447266
2023-01-23 01:00:44.105101: step: 152/526, loss: 0.10991770774126053
2023-01-23 01:00:45.228695: step: 156/526, loss: 0.12624579668045044
2023-01-23 01:00:46.365143: step: 160/526, loss: 0.004436207003891468
2023-01-23 01:00:47.499536: step: 164/526, loss: 0.12727917730808258
2023-01-23 01:00:48.620075: step: 168/526, loss: 0.05051498860120773
2023-01-23 01:00:49.758447: step: 172/526, loss: 0.018753433600068092
2023-01-23 01:00:50.898938: step: 176/526, loss: 0.09445858001708984
2023-01-23 01:00:52.042990: step: 180/526, loss: 0.03955969959497452
2023-01-23 01:00:53.177463: step: 184/526, loss: 0.01619882509112358
2023-01-23 01:00:54.269337: step: 188/526, loss: 0.004410171881318092
2023-01-23 01:00:55.397511: step: 192/526, loss: 0.10134325921535492
2023-01-23 01:00:56.527092: step: 196/526, loss: 0.03623542934656143
2023-01-23 01:00:57.650624: step: 200/526, loss: 0.025229329243302345
2023-01-23 01:00:58.794942: step: 204/526, loss: 0.046385716646909714
2023-01-23 01:00:59.934659: step: 208/526, loss: 0.14255085587501526
2023-01-23 01:01:01.052299: step: 212/526, loss: 0.009249973110854626
2023-01-23 01:01:02.215908: step: 216/526, loss: 0.029299069195985794
2023-01-23 01:01:03.372598: step: 220/526, loss: 0.09028711169958115
2023-01-23 01:01:04.505740: step: 224/526, loss: 0.05342698097229004
2023-01-23 01:01:05.659277: step: 228/526, loss: 0.03964881971478462
2023-01-23 01:01:06.819770: step: 232/526, loss: 0.05981273576617241
2023-01-23 01:01:07.988443: step: 236/526, loss: 0.12419013679027557
2023-01-23 01:01:09.123766: step: 240/526, loss: 0.026497889310121536
2023-01-23 01:01:10.257487: step: 244/526, loss: 0.02921009063720703
2023-01-23 01:01:11.402064: step: 248/526, loss: 0.07892656326293945
2023-01-23 01:01:12.553711: step: 252/526, loss: 0.4995053708553314
2023-01-23 01:01:13.690090: step: 256/526, loss: 0.03964080661535263
2023-01-23 01:01:14.835344: step: 260/526, loss: 0.09100300818681717
2023-01-23 01:01:15.978776: step: 264/526, loss: 0.23894843459129333
2023-01-23 01:01:17.111000: step: 268/526, loss: 0.0653919205069542
2023-01-23 01:01:18.295170: step: 272/526, loss: 0.11007685959339142
2023-01-23 01:01:19.446703: step: 276/526, loss: 0.04790840297937393
2023-01-23 01:01:20.569682: step: 280/526, loss: 0.010727310553193092
2023-01-23 01:01:21.708659: step: 284/526, loss: 0.08917751908302307
2023-01-23 01:01:22.836031: step: 288/526, loss: 0.04526824876666069
2023-01-23 01:01:23.995166: step: 292/526, loss: 0.023631764575839043
2023-01-23 01:01:25.158677: step: 296/526, loss: 0.10619097948074341
2023-01-23 01:01:26.281963: step: 300/526, loss: 0.07016344368457794
2023-01-23 01:01:27.425521: step: 304/526, loss: 0.06495552510023117
2023-01-23 01:01:28.586298: step: 308/526, loss: 0.20252735912799835
2023-01-23 01:01:29.692130: step: 312/526, loss: 0.06283549964427948
2023-01-23 01:01:30.822986: step: 316/526, loss: 0.07670155167579651
2023-01-23 01:01:31.974677: step: 320/526, loss: 0.02313871495425701
2023-01-23 01:01:33.086019: step: 324/526, loss: 0.01654043234884739
2023-01-23 01:01:34.218120: step: 328/526, loss: 0.03600268438458443
2023-01-23 01:01:35.360535: step: 332/526, loss: 0.051339223980903625
2023-01-23 01:01:36.507117: step: 336/526, loss: 0.012384273111820221
2023-01-23 01:01:37.646032: step: 340/526, loss: 0.06428880989551544
2023-01-23 01:01:38.806576: step: 344/526, loss: 0.2045794576406479
2023-01-23 01:01:39.937146: step: 348/526, loss: 0.01100549753755331
2023-01-23 01:01:41.109853: step: 352/526, loss: 0.09947919845581055
2023-01-23 01:01:42.260971: step: 356/526, loss: 0.5032371282577515
2023-01-23 01:01:43.386716: step: 360/526, loss: 0.03166599199175835
2023-01-23 01:01:44.514623: step: 364/526, loss: 0.02063298225402832
2023-01-23 01:01:45.619803: step: 368/526, loss: 0.04896404966711998
2023-01-23 01:01:46.747303: step: 372/526, loss: 0.06352724879980087
2023-01-23 01:01:47.899052: step: 376/526, loss: 0.09708347916603088
2023-01-23 01:01:49.038404: step: 380/526, loss: 0.09912853688001633
2023-01-23 01:01:50.147938: step: 384/526, loss: 0.02930302731692791
2023-01-23 01:01:51.304583: step: 388/526, loss: 0.23564453423023224
2023-01-23 01:01:52.433045: step: 392/526, loss: 0.10602133721113205
2023-01-23 01:01:53.598892: step: 396/526, loss: 0.1418243646621704
2023-01-23 01:01:54.726821: step: 400/526, loss: 0.06861257553100586
2023-01-23 01:01:55.859443: step: 404/526, loss: 0.3773897886276245
2023-01-23 01:01:56.987210: step: 408/526, loss: 0.008510899730026722
2023-01-23 01:01:58.112031: step: 412/526, loss: 0.012688159942626953
2023-01-23 01:01:59.236558: step: 416/526, loss: 0.0464058443903923
2023-01-23 01:02:00.380317: step: 420/526, loss: 0.07371998578310013
2023-01-23 01:02:01.531241: step: 424/526, loss: 0.7404410243034363
2023-01-23 01:02:02.685157: step: 428/526, loss: 0.01785125769674778
2023-01-23 01:02:03.808897: step: 432/526, loss: 0.12167225033044815
2023-01-23 01:02:04.956393: step: 436/526, loss: 0.04297056049108505
2023-01-23 01:02:06.095032: step: 440/526, loss: 0.10440711677074432
2023-01-23 01:02:07.244206: step: 444/526, loss: 0.06877918541431427
2023-01-23 01:02:08.402976: step: 448/526, loss: 0.029997684061527252
2023-01-23 01:02:09.556172: step: 452/526, loss: 0.15336699783802032
2023-01-23 01:02:10.713622: step: 456/526, loss: 0.03872213512659073
2023-01-23 01:02:11.846677: step: 460/526, loss: 0.10762529075145721
2023-01-23 01:02:12.976402: step: 464/526, loss: 0.05059080198407173
2023-01-23 01:02:14.109371: step: 468/526, loss: 0.04152107238769531
2023-01-23 01:02:15.245772: step: 472/526, loss: 0.03788471221923828
2023-01-23 01:02:16.387514: step: 476/526, loss: 0.0924578607082367
2023-01-23 01:02:17.515686: step: 480/526, loss: 0.04869556799530983
2023-01-23 01:02:18.665132: step: 484/526, loss: 0.03446640446782112
2023-01-23 01:02:19.780434: step: 488/526, loss: 0.030467605218291283
2023-01-23 01:02:20.906379: step: 492/526, loss: 0.04888105392456055
2023-01-23 01:02:22.046780: step: 496/526, loss: 0.10127200931310654
2023-01-23 01:02:23.175063: step: 500/526, loss: 0.49693623185157776
2023-01-23 01:02:24.275913: step: 504/526, loss: 0.06561170518398285
2023-01-23 01:02:25.392098: step: 508/526, loss: 0.03338127210736275
2023-01-23 01:02:26.544555: step: 512/526, loss: 0.053220320492982864
2023-01-23 01:02:27.683173: step: 516/526, loss: 0.26733750104904175
2023-01-23 01:02:28.820763: step: 520/526, loss: 0.022270098328590393
2023-01-23 01:02:29.938020: step: 524/526, loss: 0.017182255163788795
2023-01-23 01:02:31.065154: step: 528/526, loss: 0.08973188698291779
2023-01-23 01:02:32.240502: step: 532/526, loss: 0.16665706038475037
2023-01-23 01:02:33.421177: step: 536/526, loss: 0.0938805565237999
2023-01-23 01:02:34.585674: step: 540/526, loss: 0.01415166910737753
2023-01-23 01:02:35.750070: step: 544/526, loss: 0.22182941436767578
2023-01-23 01:02:36.881455: step: 548/526, loss: 0.018256567418575287
2023-01-23 01:02:38.000472: step: 552/526, loss: 0.013985920697450638
2023-01-23 01:02:39.133908: step: 556/526, loss: 0.05294542759656906
2023-01-23 01:02:40.249085: step: 560/526, loss: 0.026349354535341263
2023-01-23 01:02:41.391346: step: 564/526, loss: 0.027312468737363815
2023-01-23 01:02:42.538667: step: 568/526, loss: 0.05296573415398598
2023-01-23 01:02:43.725414: step: 572/526, loss: 0.029798317700624466
2023-01-23 01:02:44.850545: step: 576/526, loss: 0.03664436563849449
2023-01-23 01:02:45.991873: step: 580/526, loss: 0.11082687973976135
2023-01-23 01:02:47.132339: step: 584/526, loss: 0.0678778663277626
2023-01-23 01:02:48.263415: step: 588/526, loss: 0.056672096252441406
2023-01-23 01:02:49.380420: step: 592/526, loss: 0.14632777869701385
2023-01-23 01:02:50.528670: step: 596/526, loss: 0.14618340134620667
2023-01-23 01:02:51.643702: step: 600/526, loss: 0.1745828539133072
2023-01-23 01:02:52.776382: step: 604/526, loss: 0.0998816043138504
2023-01-23 01:02:53.919244: step: 608/526, loss: 0.08128509670495987
2023-01-23 01:02:55.071305: step: 612/526, loss: 0.034986067563295364
2023-01-23 01:02:56.195397: step: 616/526, loss: 0.06140480190515518
2023-01-23 01:02:57.330706: step: 620/526, loss: 0.10063949972391129
2023-01-23 01:02:58.455005: step: 624/526, loss: 0.08500318229198456
2023-01-23 01:02:59.598696: step: 628/526, loss: 0.04294443503022194
2023-01-23 01:03:00.739855: step: 632/526, loss: 0.115880087018013
2023-01-23 01:03:01.907026: step: 636/526, loss: 0.007815957069396973
2023-01-23 01:03:03.030642: step: 640/526, loss: 0.007673311047255993
2023-01-23 01:03:04.182310: step: 644/526, loss: 0.07724981009960175
2023-01-23 01:03:05.305396: step: 648/526, loss: 0.09962892532348633
2023-01-23 01:03:06.441731: step: 652/526, loss: 0.06111174076795578
2023-01-23 01:03:07.571249: step: 656/526, loss: 0.0499509796500206
2023-01-23 01:03:08.675815: step: 660/526, loss: 0.019877910614013672
2023-01-23 01:03:09.833426: step: 664/526, loss: 0.1742444932460785
2023-01-23 01:03:10.982937: step: 668/526, loss: 0.07345151901245117
2023-01-23 01:03:12.114493: step: 672/526, loss: 0.05171380192041397
2023-01-23 01:03:13.268627: step: 676/526, loss: 0.06844054162502289
2023-01-23 01:03:14.388826: step: 680/526, loss: 0.19001130759716034
2023-01-23 01:03:15.524781: step: 684/526, loss: 0.0820087417960167
2023-01-23 01:03:16.649323: step: 688/526, loss: 0.04524059221148491
2023-01-23 01:03:17.778213: step: 692/526, loss: 0.02237701416015625
2023-01-23 01:03:18.913077: step: 696/526, loss: 0.013925934210419655
2023-01-23 01:03:20.029433: step: 700/526, loss: 0.13059782981872559
2023-01-23 01:03:21.172413: step: 704/526, loss: 0.005258369259536266
2023-01-23 01:03:22.308759: step: 708/526, loss: 0.1428043395280838
2023-01-23 01:03:23.431648: step: 712/526, loss: 0.13605232536792755
2023-01-23 01:03:24.573316: step: 716/526, loss: 0.05469207838177681
2023-01-23 01:03:25.729714: step: 720/526, loss: 0.029755020514130592
2023-01-23 01:03:26.849318: step: 724/526, loss: 0.019161224365234375
2023-01-23 01:03:27.999090: step: 728/526, loss: 0.15146532654762268
2023-01-23 01:03:29.134907: step: 732/526, loss: 0.12099442631006241
2023-01-23 01:03:30.287864: step: 736/526, loss: 0.11903706192970276
2023-01-23 01:03:31.429767: step: 740/526, loss: 0.035573769360780716
2023-01-23 01:03:32.546994: step: 744/526, loss: 0.023453522473573685
2023-01-23 01:03:33.674330: step: 748/526, loss: 0.06212405860424042
2023-01-23 01:03:34.837988: step: 752/526, loss: 0.041171833872795105
2023-01-23 01:03:35.973094: step: 756/526, loss: 0.0913642942905426
2023-01-23 01:03:37.114929: step: 760/526, loss: 0.060819149017333984
2023-01-23 01:03:38.242494: step: 764/526, loss: 0.005241966340690851
2023-01-23 01:03:39.358241: step: 768/526, loss: 0.04731016606092453
2023-01-23 01:03:40.483298: step: 772/526, loss: 0.0874660536646843
2023-01-23 01:03:41.617795: step: 776/526, loss: 0.0473664253950119
2023-01-23 01:03:42.727373: step: 780/526, loss: 0.04849643632769585
2023-01-23 01:03:43.868198: step: 784/526, loss: 0.021467208862304688
2023-01-23 01:03:45.020267: step: 788/526, loss: 0.02276330068707466
2023-01-23 01:03:46.146649: step: 792/526, loss: 0.7945021390914917
2023-01-23 01:03:47.272572: step: 796/526, loss: 0.07966355979442596
2023-01-23 01:03:48.392421: step: 800/526, loss: 0.10666169971227646
2023-01-23 01:03:49.537075: step: 804/526, loss: 0.12571974098682404
2023-01-23 01:03:50.660014: step: 808/526, loss: 0.030166054144501686
2023-01-23 01:03:51.811283: step: 812/526, loss: 0.0077298167161643505
2023-01-23 01:03:52.933534: step: 816/526, loss: 0.09210185706615448
2023-01-23 01:03:54.065392: step: 820/526, loss: 0.04695863649249077
2023-01-23 01:03:55.209315: step: 824/526, loss: 0.11744165420532227
2023-01-23 01:03:56.327899: step: 828/526, loss: 0.038575079292058945
2023-01-23 01:03:57.488165: step: 832/526, loss: 0.027442552149295807
2023-01-23 01:03:58.634956: step: 836/526, loss: 0.04608777165412903
2023-01-23 01:03:59.767116: step: 840/526, loss: 0.06978344917297363
2023-01-23 01:04:00.909623: step: 844/526, loss: 0.01463708933442831
2023-01-23 01:04:02.047641: step: 848/526, loss: 0.05460663139820099
2023-01-23 01:04:03.187581: step: 852/526, loss: 0.03759412840008736
2023-01-23 01:04:04.354526: step: 856/526, loss: 0.049581434577703476
2023-01-23 01:04:05.496883: step: 860/526, loss: 0.028264619410037994
2023-01-23 01:04:06.628432: step: 864/526, loss: 0.06847391277551651
2023-01-23 01:04:07.764591: step: 868/526, loss: 0.05833626165986061
2023-01-23 01:04:08.906591: step: 872/526, loss: 0.04056265950202942
2023-01-23 01:04:10.002917: step: 876/526, loss: 0.06393267959356308
2023-01-23 01:04:11.159195: step: 880/526, loss: 0.07144995033740997
2023-01-23 01:04:12.278560: step: 884/526, loss: 0.1611798256635666
2023-01-23 01:04:13.420223: step: 888/526, loss: 0.061147596687078476
2023-01-23 01:04:14.569127: step: 892/526, loss: 0.04013872146606445
2023-01-23 01:04:15.720194: step: 896/526, loss: 0.07072458416223526
2023-01-23 01:04:16.845335: step: 900/526, loss: 0.4843043386936188
2023-01-23 01:04:17.969253: step: 904/526, loss: 0.13908196985721588
2023-01-23 01:04:19.098114: step: 908/526, loss: 0.04387928545475006
2023-01-23 01:04:20.226024: step: 912/526, loss: 0.07040281593799591
2023-01-23 01:04:21.367655: step: 916/526, loss: 0.04282999038696289
2023-01-23 01:04:22.494812: step: 920/526, loss: 0.07336115837097168
2023-01-23 01:04:23.625013: step: 924/526, loss: 0.10548292100429535
2023-01-23 01:04:24.772426: step: 928/526, loss: 0.15576358139514923
2023-01-23 01:04:25.936714: step: 932/526, loss: 0.10637989640235901
2023-01-23 01:04:27.063833: step: 936/526, loss: 0.09210458397865295
2023-01-23 01:04:28.211474: step: 940/526, loss: 0.046960845589637756
2023-01-23 01:04:29.328317: step: 944/526, loss: 0.030419539660215378
2023-01-23 01:04:30.436657: step: 948/526, loss: 0.06506214290857315
2023-01-23 01:04:31.559138: step: 952/526, loss: 0.09902973473072052
2023-01-23 01:04:32.678561: step: 956/526, loss: 0.06627140194177628
2023-01-23 01:04:33.816346: step: 960/526, loss: 0.10831494629383087
2023-01-23 01:04:34.939297: step: 964/526, loss: 0.13443775475025177
2023-01-23 01:04:36.094056: step: 968/526, loss: 0.012888241559267044
2023-01-23 01:04:37.220973: step: 972/526, loss: 0.18446750938892365
2023-01-23 01:04:38.354004: step: 976/526, loss: 0.339281290769577
2023-01-23 01:04:39.532319: step: 980/526, loss: 0.05691647529602051
2023-01-23 01:04:40.678609: step: 984/526, loss: 0.07747035473585129
2023-01-23 01:04:41.797121: step: 988/526, loss: 0.08023052662611008
2023-01-23 01:04:42.964039: step: 992/526, loss: 0.7032496333122253
2023-01-23 01:04:44.115431: step: 996/526, loss: 0.06381640583276749
2023-01-23 01:04:45.238856: step: 1000/526, loss: 0.056778714060783386
2023-01-23 01:04:46.340516: step: 1004/526, loss: 0.33411872386932373
2023-01-23 01:04:47.470062: step: 1008/526, loss: 0.1968100517988205
2023-01-23 01:04:48.600551: step: 1012/526, loss: 0.06786146014928818
2023-01-23 01:04:49.735451: step: 1016/526, loss: 0.034000590443611145
2023-01-23 01:04:50.845274: step: 1020/526, loss: 0.004477500915527344
2023-01-23 01:04:51.975277: step: 1024/526, loss: 0.19066371023654938
2023-01-23 01:04:53.092342: step: 1028/526, loss: 0.10681009292602539
2023-01-23 01:04:54.223402: step: 1032/526, loss: 0.03215327113866806
2023-01-23 01:04:55.355504: step: 1036/526, loss: 0.1189613863825798
2023-01-23 01:04:56.517353: step: 1040/526, loss: 0.016580868512392044
2023-01-23 01:04:57.634061: step: 1044/526, loss: 0.040842246264219284
2023-01-23 01:04:58.793466: step: 1048/526, loss: 0.07049208134412766
2023-01-23 01:04:59.950533: step: 1052/526, loss: 0.2909330427646637
2023-01-23 01:05:01.068470: step: 1056/526, loss: 0.07620034366846085
2023-01-23 01:05:02.214246: step: 1060/526, loss: 0.0831860601902008
2023-01-23 01:05:03.341276: step: 1064/526, loss: 0.08039799332618713
2023-01-23 01:05:04.468690: step: 1068/526, loss: 0.0762978121638298
2023-01-23 01:05:05.583637: step: 1072/526, loss: 0.005699443630874157
2023-01-23 01:05:06.715907: step: 1076/526, loss: 0.06466083228588104
2023-01-23 01:05:07.839328: step: 1080/526, loss: 0.20280568301677704
2023-01-23 01:05:08.955800: step: 1084/526, loss: 0.08602876216173172
2023-01-23 01:05:10.070698: step: 1088/526, loss: 0.03445424884557724
2023-01-23 01:05:11.204042: step: 1092/526, loss: 0.03289613872766495
2023-01-23 01:05:12.325403: step: 1096/526, loss: 0.03306560590863228
2023-01-23 01:05:13.471135: step: 1100/526, loss: 0.12068119645118713
2023-01-23 01:05:14.593091: step: 1104/526, loss: 0.05690737068653107
2023-01-23 01:05:15.734685: step: 1108/526, loss: 0.0273881908506155
2023-01-23 01:05:16.867412: step: 1112/526, loss: 0.23444966971874237
2023-01-23 01:05:18.018389: step: 1116/526, loss: 0.04446830600500107
2023-01-23 01:05:19.192232: step: 1120/526, loss: 0.025336647406220436
2023-01-23 01:05:20.312181: step: 1124/526, loss: 0.05155191570520401
2023-01-23 01:05:21.464108: step: 1128/526, loss: 0.10651607811450958
2023-01-23 01:05:22.597597: step: 1132/526, loss: 0.114251047372818
2023-01-23 01:05:23.722770: step: 1136/526, loss: 0.5184873342514038
2023-01-23 01:05:24.837359: step: 1140/526, loss: 0.09276838600635529
2023-01-23 01:05:25.995661: step: 1144/526, loss: 0.024493694305419922
2023-01-23 01:05:27.107594: step: 1148/526, loss: 0.842566192150116
2023-01-23 01:05:28.232198: step: 1152/526, loss: 0.008257674984633923
2023-01-23 01:05:29.376973: step: 1156/526, loss: 0.08722105622291565
2023-01-23 01:05:30.491909: step: 1160/526, loss: 0.09716796875
2023-01-23 01:05:31.594572: step: 1164/526, loss: 0.007197761442512274
2023-01-23 01:05:32.712227: step: 1168/526, loss: 0.08151836693286896
2023-01-23 01:05:33.870602: step: 1172/526, loss: 0.0497395284473896
2023-01-23 01:05:34.992654: step: 1176/526, loss: 0.06084489822387695
2023-01-23 01:05:36.146898: step: 1180/526, loss: 0.07828722149133682
2023-01-23 01:05:37.275348: step: 1184/526, loss: 0.042025040835142136
2023-01-23 01:05:38.429884: step: 1188/526, loss: 0.09930925071239471
2023-01-23 01:05:39.624593: step: 1192/526, loss: 0.07812199741601944
2023-01-23 01:05:40.738503: step: 1196/526, loss: 0.041902828961610794
2023-01-23 01:05:41.866008: step: 1200/526, loss: 0.22845545411109924
2023-01-23 01:05:43.000874: step: 1204/526, loss: 0.05532092973589897
2023-01-23 01:05:44.159860: step: 1208/526, loss: 0.06245307996869087
2023-01-23 01:05:45.288412: step: 1212/526, loss: 0.02949414774775505
2023-01-23 01:05:46.437173: step: 1216/526, loss: 0.02378559112548828
2023-01-23 01:05:47.561802: step: 1220/526, loss: 0.006373787298798561
2023-01-23 01:05:48.699129: step: 1224/526, loss: 0.08481474220752716
2023-01-23 01:05:49.823244: step: 1228/526, loss: 0.03761797025799751
2023-01-23 01:05:50.924545: step: 1232/526, loss: 0.0032770633697509766
2023-01-23 01:05:52.060612: step: 1236/526, loss: 0.05032806470990181
2023-01-23 01:05:53.184668: step: 1240/526, loss: 0.07737484574317932
2023-01-23 01:05:54.304867: step: 1244/526, loss: 0.026522256433963776
2023-01-23 01:05:55.435238: step: 1248/526, loss: 0.027126504108309746
2023-01-23 01:05:56.573473: step: 1252/526, loss: 0.07468719780445099
2023-01-23 01:05:57.723273: step: 1256/526, loss: 0.28271007537841797
2023-01-23 01:05:58.836271: step: 1260/526, loss: 0.28559890389442444
2023-01-23 01:06:00.017435: step: 1264/526, loss: 0.022942161187529564
2023-01-23 01:06:01.129705: step: 1268/526, loss: 0.018129730597138405
2023-01-23 01:06:02.237272: step: 1272/526, loss: 0.3420391082763672
2023-01-23 01:06:03.378764: step: 1276/526, loss: 0.0206514373421669
2023-01-23 01:06:04.496852: step: 1280/526, loss: 0.6973414421081543
2023-01-23 01:06:05.604401: step: 1284/526, loss: 0.09004630893468857
2023-01-23 01:06:06.713898: step: 1288/526, loss: 0.012910605408251286
2023-01-23 01:06:07.848485: step: 1292/526, loss: 0.052889443933963776
2023-01-23 01:06:08.998213: step: 1296/526, loss: 0.00937356986105442
2023-01-23 01:06:10.125126: step: 1300/526, loss: 0.009701442904770374
2023-01-23 01:06:11.252938: step: 1304/526, loss: 0.08429671078920364
2023-01-23 01:06:12.372436: step: 1308/526, loss: 0.05223708599805832
2023-01-23 01:06:13.478103: step: 1312/526, loss: 0.1049903929233551
2023-01-23 01:06:14.603682: step: 1316/526, loss: 0.15975895524024963
2023-01-23 01:06:15.730800: step: 1320/526, loss: 0.06687908619642258
2023-01-23 01:06:16.859548: step: 1324/526, loss: 0.0996524840593338
2023-01-23 01:06:17.962462: step: 1328/526, loss: 0.007422924041748047
2023-01-23 01:06:19.093713: step: 1332/526, loss: 0.1732240617275238
2023-01-23 01:06:20.231825: step: 1336/526, loss: 0.03923340141773224
2023-01-23 01:06:21.381065: step: 1340/526, loss: 0.007705879397690296
2023-01-23 01:06:22.542051: step: 1344/526, loss: 1.9873721599578857
2023-01-23 01:06:23.668326: step: 1348/526, loss: 0.06160922348499298
2023-01-23 01:06:24.793949: step: 1352/526, loss: 0.05101480334997177
2023-01-23 01:06:25.921718: step: 1356/526, loss: 0.04123516008257866
2023-01-23 01:06:27.036805: step: 1360/526, loss: 0.12192918360233307
2023-01-23 01:06:28.172574: step: 1364/526, loss: 0.14946289360523224
2023-01-23 01:06:29.303612: step: 1368/526, loss: 0.04394255951046944
2023-01-23 01:06:30.403521: step: 1372/526, loss: 0.09714050590991974
2023-01-23 01:06:31.556808: step: 1376/526, loss: 0.04991569742560387
2023-01-23 01:06:32.700666: step: 1380/526, loss: 0.07330255955457687
2023-01-23 01:06:33.833802: step: 1384/526, loss: 0.10196466743946075
2023-01-23 01:06:35.003102: step: 1388/526, loss: 0.11431503295898438
2023-01-23 01:06:36.145064: step: 1392/526, loss: 0.24093666672706604
2023-01-23 01:06:37.266304: step: 1396/526, loss: 0.016542624682188034
2023-01-23 01:06:38.396759: step: 1400/526, loss: 0.6701074838638306
2023-01-23 01:06:39.557453: step: 1404/526, loss: 0.0032260892912745476
2023-01-23 01:06:40.678272: step: 1408/526, loss: 0.03952236473560333
2023-01-23 01:06:41.818165: step: 1412/526, loss: 0.053475573658943176
2023-01-23 01:06:42.935496: step: 1416/526, loss: 0.10574407875537872
2023-01-23 01:06:44.077700: step: 1420/526, loss: 0.02206139639019966
2023-01-23 01:06:45.218460: step: 1424/526, loss: 0.23898696899414062
2023-01-23 01:06:46.323368: step: 1428/526, loss: 0.0604923740029335
2023-01-23 01:06:47.463969: step: 1432/526, loss: 0.22128941118717194
2023-01-23 01:06:48.601404: step: 1436/526, loss: 0.03140106052160263
2023-01-23 01:06:49.743281: step: 1440/526, loss: 0.07476844638586044
2023-01-23 01:06:50.831182: step: 1444/526, loss: 0.05649605020880699
2023-01-23 01:06:51.948145: step: 1448/526, loss: 0.04432068020105362
2023-01-23 01:06:53.050505: step: 1452/526, loss: 0.01875171810388565
2023-01-23 01:06:54.171763: step: 1456/526, loss: 0.10838525742292404
2023-01-23 01:06:55.294212: step: 1460/526, loss: 0.014918709173798561
2023-01-23 01:06:56.461556: step: 1464/526, loss: 0.05639658123254776
2023-01-23 01:06:57.594984: step: 1468/526, loss: 0.04339020326733589
2023-01-23 01:06:58.703209: step: 1472/526, loss: 0.024857616052031517
2023-01-23 01:06:59.859942: step: 1476/526, loss: 0.007811450865119696
2023-01-23 01:07:00.978263: step: 1480/526, loss: 0.01029291097074747
2023-01-23 01:07:02.115425: step: 1484/526, loss: 0.11069220304489136
2023-01-23 01:07:03.217927: step: 1488/526, loss: 0.009436321444809437
2023-01-23 01:07:04.347081: step: 1492/526, loss: 0.005244255065917969
2023-01-23 01:07:05.464483: step: 1496/526, loss: 0.05494390055537224
2023-01-23 01:07:06.602763: step: 1500/526, loss: 0.01738009601831436
2023-01-23 01:07:07.733948: step: 1504/526, loss: 0.041535090655088425
2023-01-23 01:07:08.862087: step: 1508/526, loss: 0.07702608406543732
2023-01-23 01:07:09.990547: step: 1512/526, loss: 0.08296613395214081
2023-01-23 01:07:11.121489: step: 1516/526, loss: 0.1479577124118805
2023-01-23 01:07:12.242266: step: 1520/526, loss: 0.06086378172039986
2023-01-23 01:07:13.411559: step: 1524/526, loss: 0.1092875525355339
2023-01-23 01:07:14.561217: step: 1528/526, loss: 0.0897495299577713
2023-01-23 01:07:15.718090: step: 1532/526, loss: 0.07425608485937119
2023-01-23 01:07:16.862707: step: 1536/526, loss: 0.027304459363222122
2023-01-23 01:07:17.997539: step: 1540/526, loss: 0.09604702144861221
2023-01-23 01:07:19.136062: step: 1544/526, loss: 0.10754013061523438
2023-01-23 01:07:20.258111: step: 1548/526, loss: 0.10374736785888672
2023-01-23 01:07:21.380284: step: 1552/526, loss: 0.037551261484622955
2023-01-23 01:07:22.503456: step: 1556/526, loss: 0.31077396869659424
2023-01-23 01:07:23.644897: step: 1560/526, loss: 0.08327203243970871
2023-01-23 01:07:24.794093: step: 1564/526, loss: 0.020313359797000885
2023-01-23 01:07:25.933718: step: 1568/526, loss: 0.08904695510864258
2023-01-23 01:07:27.084695: step: 1572/526, loss: 0.034650661051273346
2023-01-23 01:07:28.183959: step: 1576/526, loss: 0.04883251339197159
2023-01-23 01:07:29.312740: step: 1580/526, loss: 0.08138800412416458
2023-01-23 01:07:30.435716: step: 1584/526, loss: 0.03640337288379669
2023-01-23 01:07:31.553069: step: 1588/526, loss: 0.09982023388147354
2023-01-23 01:07:32.708589: step: 1592/526, loss: 0.10655536502599716
2023-01-23 01:07:33.845201: step: 1596/526, loss: 0.09950906783342361
2023-01-23 01:07:34.952629: step: 1600/526, loss: 0.0488312765955925
2023-01-23 01:07:36.064712: step: 1604/526, loss: 0.13597726821899414
2023-01-23 01:07:37.201279: step: 1608/526, loss: 0.03615992143750191
2023-01-23 01:07:38.337829: step: 1612/526, loss: 0.24791431427001953
2023-01-23 01:07:39.481904: step: 1616/526, loss: 0.1749028116464615
2023-01-23 01:07:40.634560: step: 1620/526, loss: 0.08051913231611252
2023-01-23 01:07:41.764268: step: 1624/526, loss: 0.151081845164299
2023-01-23 01:07:42.915568: step: 1628/526, loss: 0.09550247341394424
2023-01-23 01:07:44.051552: step: 1632/526, loss: 0.005854606628417969
2023-01-23 01:07:45.198559: step: 1636/526, loss: 0.08622942119836807
2023-01-23 01:07:46.309039: step: 1640/526, loss: 0.026195144280791283
2023-01-23 01:07:47.431378: step: 1644/526, loss: 0.006679725367575884
2023-01-23 01:07:48.603021: step: 1648/526, loss: 0.14648056030273438
2023-01-23 01:07:49.755146: step: 1652/526, loss: 0.12668178975582123
2023-01-23 01:07:50.895030: step: 1656/526, loss: 0.06289100646972656
2023-01-23 01:07:52.018655: step: 1660/526, loss: 0.1046912893652916
2023-01-23 01:07:53.158784: step: 1664/526, loss: 0.016279984265565872
2023-01-23 01:07:54.302892: step: 1668/526, loss: 0.09579434245824814
2023-01-23 01:07:55.415795: step: 1672/526, loss: 0.04399166256189346
2023-01-23 01:07:56.556735: step: 1676/526, loss: 0.024792686104774475
2023-01-23 01:07:57.709529: step: 1680/526, loss: 0.08130040764808655
2023-01-23 01:07:58.841800: step: 1684/526, loss: 0.025147533044219017
2023-01-23 01:07:59.992043: step: 1688/526, loss: 0.0655585303902626
2023-01-23 01:08:01.121347: step: 1692/526, loss: 0.0028779031708836555
2023-01-23 01:08:02.265741: step: 1696/526, loss: 0.03996109962463379
2023-01-23 01:08:03.400433: step: 1700/526, loss: 0.12408313155174255
2023-01-23 01:08:04.558734: step: 1704/526, loss: 0.011883596889674664
2023-01-23 01:08:05.682800: step: 1708/526, loss: 0.10415688157081604
2023-01-23 01:08:06.832404: step: 1712/526, loss: 0.01332016009837389
2023-01-23 01:08:07.957144: step: 1716/526, loss: 0.07270117104053497
2023-01-23 01:08:09.124215: step: 1720/526, loss: 0.08891163021326065
2023-01-23 01:08:10.258089: step: 1724/526, loss: 0.01740737073123455
2023-01-23 01:08:11.397606: step: 1728/526, loss: 0.023345567286014557
2023-01-23 01:08:12.554948: step: 1732/526, loss: 0.012402153573930264
2023-01-23 01:08:13.743127: step: 1736/526, loss: 0.3003942370414734
2023-01-23 01:08:14.856617: step: 1740/526, loss: 0.0820653960108757
2023-01-23 01:08:15.977709: step: 1744/526, loss: 0.03697824478149414
2023-01-23 01:08:17.096037: step: 1748/526, loss: 0.1366405040025711
2023-01-23 01:08:18.207832: step: 1752/526, loss: 0.13540410995483398
2023-01-23 01:08:19.365237: step: 1756/526, loss: 0.06986103951931
2023-01-23 01:08:20.513824: step: 1760/526, loss: 0.04328117519617081
2023-01-23 01:08:21.614487: step: 1764/526, loss: 0.005517005920410156
2023-01-23 01:08:22.737819: step: 1768/526, loss: 0.9555491805076599
2023-01-23 01:08:23.879049: step: 1772/526, loss: 0.38103771209716797
2023-01-23 01:08:25.013553: step: 1776/526, loss: 0.08931179344654083
2023-01-23 01:08:26.169957: step: 1780/526, loss: 0.14278793334960938
2023-01-23 01:08:27.287972: step: 1784/526, loss: 0.05463924631476402
2023-01-23 01:08:28.433170: step: 1788/526, loss: 0.17228588461875916
2023-01-23 01:08:29.559419: step: 1792/526, loss: 0.0715034008026123
2023-01-23 01:08:30.714343: step: 1796/526, loss: 0.08065047860145569
2023-01-23 01:08:31.833801: step: 1800/526, loss: 0.14247922599315643
2023-01-23 01:08:32.964243: step: 1804/526, loss: 0.2524127960205078
2023-01-23 01:08:34.112917: step: 1808/526, loss: 0.08272905647754669
2023-01-23 01:08:35.230442: step: 1812/526, loss: 0.014359379187226295
2023-01-23 01:08:36.344754: step: 1816/526, loss: 0.04249287024140358
2023-01-23 01:08:37.463652: step: 1820/526, loss: 0.6068402528762817
2023-01-23 01:08:38.599704: step: 1824/526, loss: 0.04011697694659233
2023-01-23 01:08:39.756674: step: 1828/526, loss: 0.04723620414733887
2023-01-23 01:08:40.913661: step: 1832/526, loss: 0.17213377356529236
2023-01-23 01:08:42.022076: step: 1836/526, loss: 0.4181341528892517
2023-01-23 01:08:43.199709: step: 1840/526, loss: 0.156813383102417
2023-01-23 01:08:44.342357: step: 1844/526, loss: 0.3373374044895172
2023-01-23 01:08:45.499693: step: 1848/526, loss: 0.1378398984670639
2023-01-23 01:08:46.645346: step: 1852/526, loss: 0.022688819095492363
2023-01-23 01:08:47.736984: step: 1856/526, loss: 0.0207995418459177
2023-01-23 01:08:48.907618: step: 1860/526, loss: 0.01760849915444851
2023-01-23 01:08:50.078573: step: 1864/526, loss: 0.06021890416741371
2023-01-23 01:08:51.213813: step: 1868/526, loss: 0.03155479580163956
2023-01-23 01:08:52.333568: step: 1872/526, loss: 0.03675680235028267
2023-01-23 01:08:53.445908: step: 1876/526, loss: 0.06314067542552948
2023-01-23 01:08:54.592420: step: 1880/526, loss: 0.03274441137909889
2023-01-23 01:08:55.722762: step: 1884/526, loss: 0.0290724765509367
2023-01-23 01:08:56.842708: step: 1888/526, loss: 0.0348079688847065
2023-01-23 01:08:58.002473: step: 1892/526, loss: 0.25051993131637573
2023-01-23 01:08:59.167602: step: 1896/526, loss: 0.08215999603271484
2023-01-23 01:09:00.297177: step: 1900/526, loss: 0.10269089043140411
2023-01-23 01:09:01.449105: step: 1904/526, loss: 0.01501312293112278
2023-01-23 01:09:02.598207: step: 1908/526, loss: 0.01247868500649929
2023-01-23 01:09:03.751225: step: 1912/526, loss: 0.05762819945812225
2023-01-23 01:09:04.885778: step: 1916/526, loss: 0.059395406395196915
2023-01-23 01:09:06.028500: step: 1920/526, loss: 0.04089965671300888
2023-01-23 01:09:07.160554: step: 1924/526, loss: 0.08226414024829865
2023-01-23 01:09:08.322112: step: 1928/526, loss: 0.027237892150878906
2023-01-23 01:09:09.444859: step: 1932/526, loss: 0.029527664184570312
2023-01-23 01:09:10.564179: step: 1936/526, loss: 0.22997260093688965
2023-01-23 01:09:11.686546: step: 1940/526, loss: 0.030162526294589043
2023-01-23 01:09:12.845848: step: 1944/526, loss: 0.3136647343635559
2023-01-23 01:09:13.961054: step: 1948/526, loss: 0.49713554978370667
2023-01-23 01:09:15.120903: step: 1952/526, loss: 0.004202508833259344
2023-01-23 01:09:16.275555: step: 1956/526, loss: 0.1447422057390213
2023-01-23 01:09:17.396914: step: 1960/526, loss: 0.017315387725830078
2023-01-23 01:09:18.521556: step: 1964/526, loss: 0.04121146351099014
2023-01-23 01:09:19.621858: step: 1968/526, loss: 0.053319741040468216
2023-01-23 01:09:20.737264: step: 1972/526, loss: 0.09213316440582275
2023-01-23 01:09:21.872573: step: 1976/526, loss: 0.09824752807617188
2023-01-23 01:09:23.004213: step: 1980/526, loss: 0.09497824311256409
2023-01-23 01:09:24.122467: step: 1984/526, loss: 0.14240819215774536
2023-01-23 01:09:25.219181: step: 1988/526, loss: 0.042424917221069336
2023-01-23 01:09:26.343419: step: 1992/526, loss: 0.048325732350349426
2023-01-23 01:09:27.463578: step: 1996/526, loss: 0.07114067673683167
2023-01-23 01:09:28.617248: step: 2000/526, loss: 0.06646886467933655
2023-01-23 01:09:29.723872: step: 2004/526, loss: 0.2667744755744934
2023-01-23 01:09:30.890095: step: 2008/526, loss: 0.011460686102509499
2023-01-23 01:09:32.021092: step: 2012/526, loss: 0.0881836861371994
2023-01-23 01:09:33.139039: step: 2016/526, loss: 0.03329572454094887
2023-01-23 01:09:34.292071: step: 2020/526, loss: 0.5911588072776794
2023-01-23 01:09:35.421421: step: 2024/526, loss: 0.05148658901453018
2023-01-23 01:09:36.542189: step: 2028/526, loss: 0.0896640345454216
2023-01-23 01:09:37.664070: step: 2032/526, loss: 0.08779249340295792
2023-01-23 01:09:38.783745: step: 2036/526, loss: 0.04977541044354439
2023-01-23 01:09:39.917618: step: 2040/526, loss: 0.06893427670001984
2023-01-23 01:09:41.042420: step: 2044/526, loss: 0.5643278956413269
2023-01-23 01:09:42.187637: step: 2048/526, loss: 0.18750472366809845
2023-01-23 01:09:43.346487: step: 2052/526, loss: 0.058579444885253906
2023-01-23 01:09:44.487676: step: 2056/526, loss: 0.06687898933887482
2023-01-23 01:09:45.644315: step: 2060/526, loss: 0.05959515646100044
2023-01-23 01:09:46.797599: step: 2064/526, loss: 0.04958000034093857
2023-01-23 01:09:47.923834: step: 2068/526, loss: 0.04323253780603409
2023-01-23 01:09:49.080572: step: 2072/526, loss: 0.05554013326764107
2023-01-23 01:09:50.225020: step: 2076/526, loss: 0.08727961033582687
2023-01-23 01:09:51.350009: step: 2080/526, loss: 1.0955184698104858
2023-01-23 01:09:52.520251: step: 2084/526, loss: 0.11226553469896317
2023-01-23 01:09:53.644554: step: 2088/526, loss: 0.06319661438465118
2023-01-23 01:09:54.804784: step: 2092/526, loss: 0.08107885718345642
2023-01-23 01:09:55.939065: step: 2096/526, loss: 0.04995689168572426
2023-01-23 01:09:57.088169: step: 2100/526, loss: 0.14095425605773926
2023-01-23 01:09:58.187667: step: 2104/526, loss: 0.03281044960021973
==================================================
Loss: 0.108
--------------------
Dev: {'event': {'p': 0.5503802281368821, 'r': 0.7709720372836218, 'f1': 0.6422628951747089}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Test: {'event': {'p': 0.5799212598425196, 'r': 0.7687891440501043, 'f1': 0.6611310592459605}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Chinese: {'event': {'p': 0.6, 'r': 0.9444444444444444, 'f1': 0.7338129496402879}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Korean: {'event': {'p': 0.717391304347826, 'r': 0.5238095238095238, 'f1': 0.6055045871559633}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Russian: {'event': {'p': 0.4583333333333333, 'r': 0.6111111111111112, 'f1': 0.5238095238095238}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6604010025062657, 'r': 0.7017310252996005, 'f1': 0.6804389928986443}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Eng Test for Chinese: {'event': {'p': 0.6480836236933798, 'r': 0.6795407098121086, 'f1': 0.6634394904458599}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Sample Chinese: {'event': {'p': 0.6323529411764706, 'r': 0.7962962962962963, 'f1': 0.7049180327868853}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6257995735607675, 'r': 0.7816245006657789, 'f1': 0.6950858496151568}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Eng Test for Korean: {'event': {'p': 0.623113410952997, 'r': 0.7541753653444676, 'f1': 0.6824085005903188}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Sample Korean: {'event': {'p': 0.7446808510638298, 'r': 0.5555555555555556, 'f1': 0.6363636363636364}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
--------------------
Eng Dev for Russian: {'event': {'p': 0.60687432867884, 'r': 0.7523302263648469, 'f1': 0.6718192627824019}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Russian: {'event': {'p': 0.6179966044142614, 'r': 0.7599164926931107, 'f1': 0.6816479400749064}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Russian: {'event': {'p': 0.5263157894736842, 'r': 0.5555555555555556, 'f1': 0.5405405405405405}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
******************************
Epoch: 10
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 01:10:41.757686: step: 4/526, loss: 0.028320984914898872
2023-01-23 01:10:42.916117: step: 8/526, loss: 0.028383541852235794
2023-01-23 01:10:44.064720: step: 12/526, loss: 0.06290411949157715
2023-01-23 01:10:45.212043: step: 16/526, loss: 0.04937257617712021
2023-01-23 01:10:46.353491: step: 20/526, loss: 0.16861124336719513
2023-01-23 01:10:47.460406: step: 24/526, loss: 0.06576375663280487
2023-01-23 01:10:48.623711: step: 28/526, loss: 0.024859048426151276
2023-01-23 01:10:49.768749: step: 32/526, loss: 0.003791332244873047
2023-01-23 01:10:50.867267: step: 36/526, loss: 0.009054708294570446
2023-01-23 01:10:51.987368: step: 40/526, loss: 0.06260533630847931
2023-01-23 01:10:53.111967: step: 44/526, loss: 0.004513883963227272
2023-01-23 01:10:54.270036: step: 48/526, loss: 0.04992947727441788
2023-01-23 01:10:55.411512: step: 52/526, loss: 0.12240581214427948
2023-01-23 01:10:56.528982: step: 56/526, loss: 0.12667998671531677
2023-01-23 01:10:57.646283: step: 60/526, loss: 0.12655992805957794
2023-01-23 01:10:58.794472: step: 64/526, loss: 0.023884296417236328
2023-01-23 01:10:59.900240: step: 68/526, loss: 0.10118045657873154
2023-01-23 01:11:01.030124: step: 72/526, loss: 0.032205771654844284
2023-01-23 01:11:02.132255: step: 76/526, loss: 0.06212451681494713
2023-01-23 01:11:03.277212: step: 80/526, loss: 0.09330043941736221
2023-01-23 01:11:04.410673: step: 84/526, loss: 0.019300175830721855
2023-01-23 01:11:05.524805: step: 88/526, loss: 0.0037672044709324837
2023-01-23 01:11:06.644258: step: 92/526, loss: 0.0006354331853799522
2023-01-23 01:11:07.755472: step: 96/526, loss: 0.03278150409460068
2023-01-23 01:11:08.918437: step: 100/526, loss: 0.013471794314682484
2023-01-23 01:11:10.054355: step: 104/526, loss: 0.010409379377961159
2023-01-23 01:11:11.142908: step: 108/526, loss: 0.003136539366096258
2023-01-23 01:11:12.276997: step: 112/526, loss: 0.2667730450630188
2023-01-23 01:11:13.440245: step: 116/526, loss: 0.02319650538265705
2023-01-23 01:11:14.545031: step: 120/526, loss: 0.038399938493967056
2023-01-23 01:11:15.669906: step: 124/526, loss: 0.04065141826868057
2023-01-23 01:11:16.789269: step: 128/526, loss: 0.07226391136646271
2023-01-23 01:11:17.912315: step: 132/526, loss: 0.0392330177128315
2023-01-23 01:11:19.046762: step: 136/526, loss: 0.08125477284193039
2023-01-23 01:11:20.175355: step: 140/526, loss: 0.01510238740593195
2023-01-23 01:11:21.325174: step: 144/526, loss: 0.22804327309131622
2023-01-23 01:11:22.486974: step: 148/526, loss: 0.05395030975341797
2023-01-23 01:11:23.623366: step: 152/526, loss: 0.011246491223573685
2023-01-23 01:11:24.776933: step: 156/526, loss: 0.06688646972179413
2023-01-23 01:11:25.923424: step: 160/526, loss: 0.15941017866134644
2023-01-23 01:11:27.075328: step: 164/526, loss: 0.03614625707268715
2023-01-23 01:11:28.190711: step: 168/526, loss: 0.04990587383508682
2023-01-23 01:11:29.332075: step: 172/526, loss: 0.010376430116593838
2023-01-23 01:11:30.466474: step: 176/526, loss: 0.047675516456365585
2023-01-23 01:11:31.602883: step: 180/526, loss: 0.34093916416168213
2023-01-23 01:11:32.727884: step: 184/526, loss: 0.014830781146883965
2023-01-23 01:11:33.848286: step: 188/526, loss: 0.04991798475384712
2023-01-23 01:11:35.011881: step: 192/526, loss: 0.023826980963349342
2023-01-23 01:11:36.163442: step: 196/526, loss: 0.0010565996635705233
2023-01-23 01:11:37.309021: step: 200/526, loss: 0.04137573391199112
2023-01-23 01:11:38.456012: step: 204/526, loss: 0.07580319046974182
2023-01-23 01:11:39.596907: step: 208/526, loss: 0.030399512499570847
2023-01-23 01:11:40.721669: step: 212/526, loss: 0.06335706263780594
2023-01-23 01:11:41.863334: step: 216/526, loss: 0.0020377160981297493
2023-01-23 01:11:43.017215: step: 220/526, loss: 0.023698806762695312
2023-01-23 01:11:44.197869: step: 224/526, loss: 0.032497502863407135
2023-01-23 01:11:45.341897: step: 228/526, loss: 0.01242523267865181
2023-01-23 01:11:46.515905: step: 232/526, loss: 0.04625234752893448
2023-01-23 01:11:47.658267: step: 236/526, loss: 0.07313938438892365
2023-01-23 01:11:48.804239: step: 240/526, loss: 0.08535385131835938
2023-01-23 01:11:49.956667: step: 244/526, loss: 0.4234287738800049
2023-01-23 01:11:51.109254: step: 248/526, loss: 0.06997833400964737
2023-01-23 01:11:52.255799: step: 252/526, loss: 0.16430386900901794
2023-01-23 01:11:53.392618: step: 256/526, loss: 0.023958731442689896
2023-01-23 01:11:54.524637: step: 260/526, loss: 0.022513866424560547
2023-01-23 01:11:55.625807: step: 264/526, loss: 0.030522825196385384
2023-01-23 01:11:56.749742: step: 268/526, loss: 0.10798521339893341
2023-01-23 01:11:57.871518: step: 272/526, loss: 0.01524047926068306
2023-01-23 01:11:58.989545: step: 276/526, loss: 0.037169747054576874
2023-01-23 01:12:00.146285: step: 280/526, loss: 0.20213204622268677
2023-01-23 01:12:01.263044: step: 284/526, loss: 0.10551920533180237
2023-01-23 01:12:02.376667: step: 288/526, loss: 0.026165615767240524
2023-01-23 01:12:03.495893: step: 292/526, loss: 0.34799259901046753
2023-01-23 01:12:04.622103: step: 296/526, loss: 0.03233833611011505
2023-01-23 01:12:05.752402: step: 300/526, loss: 0.02612781524658203
2023-01-23 01:12:06.865096: step: 304/526, loss: 0.0483766570687294
2023-01-23 01:12:08.029733: step: 308/526, loss: 0.010968636721372604
2023-01-23 01:12:09.208117: step: 312/526, loss: 0.11256222426891327
2023-01-23 01:12:10.374257: step: 316/526, loss: 0.026598358526825905
2023-01-23 01:12:11.500879: step: 320/526, loss: 0.25557535886764526
2023-01-23 01:12:12.659473: step: 324/526, loss: 0.04780564457178116
2023-01-23 01:12:13.813700: step: 328/526, loss: 0.0025281906127929688
2023-01-23 01:12:14.937190: step: 332/526, loss: 0.0003452778037171811
2023-01-23 01:12:16.102437: step: 336/526, loss: 0.07560577243566513
2023-01-23 01:12:17.235187: step: 340/526, loss: 0.020679473876953125
2023-01-23 01:12:18.354976: step: 344/526, loss: 0.08357725292444229
2023-01-23 01:12:19.454182: step: 348/526, loss: 0.022170402109622955
2023-01-23 01:12:20.575904: step: 352/526, loss: 0.0702851265668869
2023-01-23 01:12:21.699283: step: 356/526, loss: 0.1083984375
2023-01-23 01:12:22.853295: step: 360/526, loss: 0.15933114290237427
2023-01-23 01:12:23.993779: step: 364/526, loss: 0.08095331490039825
2023-01-23 01:12:25.113850: step: 368/526, loss: 0.07179813832044601
2023-01-23 01:12:26.247735: step: 372/526, loss: 0.06184377521276474
2023-01-23 01:12:27.378151: step: 376/526, loss: 0.011195373721420765
2023-01-23 01:12:28.524561: step: 380/526, loss: 0.01475071907043457
2023-01-23 01:12:29.645692: step: 384/526, loss: 0.03557606041431427
2023-01-23 01:12:30.780121: step: 388/526, loss: 0.03391990810632706
2023-01-23 01:12:31.893241: step: 392/526, loss: 0.04469270631670952
2023-01-23 01:12:33.025643: step: 396/526, loss: 0.23098793625831604
2023-01-23 01:12:34.142643: step: 400/526, loss: 0.02031850814819336
2023-01-23 01:12:35.302855: step: 404/526, loss: 0.09688778221607208
2023-01-23 01:12:36.457961: step: 408/526, loss: 0.06264915317296982
2023-01-23 01:12:37.573787: step: 412/526, loss: 0.07998549938201904
2023-01-23 01:12:38.719011: step: 416/526, loss: 0.115503691136837
2023-01-23 01:12:39.845735: step: 420/526, loss: 0.025243043899536133
2023-01-23 01:12:40.962131: step: 424/526, loss: 0.017613792791962624
2023-01-23 01:12:42.099654: step: 428/526, loss: 0.1176474541425705
2023-01-23 01:12:43.261643: step: 432/526, loss: 0.043384552001953125
2023-01-23 01:12:44.399132: step: 436/526, loss: 0.007562064565718174
2023-01-23 01:12:45.570239: step: 440/526, loss: 0.09554615616798401
2023-01-23 01:12:46.695899: step: 444/526, loss: 0.0011378289200365543
2023-01-23 01:12:47.870224: step: 448/526, loss: 0.08882226794958115
2023-01-23 01:12:49.016489: step: 452/526, loss: 0.03608202934265137
2023-01-23 01:12:50.141827: step: 456/526, loss: 0.011974668130278587
2023-01-23 01:12:51.272990: step: 460/526, loss: 0.0049231527373194695
2023-01-23 01:12:52.396460: step: 464/526, loss: 0.14429016411304474
2023-01-23 01:12:53.538252: step: 468/526, loss: 0.09686315059661865
2023-01-23 01:12:54.694911: step: 472/526, loss: 0.02040109783411026
2023-01-23 01:12:55.826939: step: 476/526, loss: 0.01570301130414009
2023-01-23 01:12:56.967294: step: 480/526, loss: 0.024383926764130592
2023-01-23 01:12:58.102063: step: 484/526, loss: 0.18245373666286469
2023-01-23 01:12:59.219887: step: 488/526, loss: 0.052815936505794525
2023-01-23 01:13:00.338867: step: 492/526, loss: 0.03601484000682831
2023-01-23 01:13:01.474760: step: 496/526, loss: 0.02328806184232235
2023-01-23 01:13:02.612789: step: 500/526, loss: 0.06231861189007759
2023-01-23 01:13:03.738179: step: 504/526, loss: 0.038298606872558594
2023-01-23 01:13:04.880212: step: 508/526, loss: 0.09702196717262268
2023-01-23 01:13:06.032822: step: 512/526, loss: 0.04379863664507866
2023-01-23 01:13:07.152444: step: 516/526, loss: 0.055422186851501465
2023-01-23 01:13:08.268181: step: 520/526, loss: 0.017874527722597122
2023-01-23 01:13:09.395346: step: 524/526, loss: 0.02707233466207981
2023-01-23 01:13:10.544652: step: 528/526, loss: 0.053722333163022995
2023-01-23 01:13:11.686994: step: 532/526, loss: 0.11697397381067276
2023-01-23 01:13:12.858678: step: 536/526, loss: 0.06402167677879333
2023-01-23 01:13:13.998859: step: 540/526, loss: 0.04290056228637695
2023-01-23 01:13:15.122899: step: 544/526, loss: 0.029560375958681107
2023-01-23 01:13:16.268822: step: 548/526, loss: 0.0044727325439453125
2023-01-23 01:13:17.394572: step: 552/526, loss: 0.02180004119873047
2023-01-23 01:13:18.586146: step: 556/526, loss: 0.03216296434402466
2023-01-23 01:13:19.767613: step: 560/526, loss: 0.07602892071008682
2023-01-23 01:13:20.927646: step: 564/526, loss: 0.01582932472229004
2023-01-23 01:13:22.037922: step: 568/526, loss: 0.03550272062420845
2023-01-23 01:13:23.169063: step: 572/526, loss: 0.06587543338537216
2023-01-23 01:13:24.300735: step: 576/526, loss: 0.09434433281421661
2023-01-23 01:13:25.436974: step: 580/526, loss: 0.05430154874920845
2023-01-23 01:13:26.561354: step: 584/526, loss: 0.29151880741119385
2023-01-23 01:13:27.693352: step: 588/526, loss: 0.014581013470888138
2023-01-23 01:13:28.830766: step: 592/526, loss: 0.03231649473309517
2023-01-23 01:13:29.991659: step: 596/526, loss: 0.1652783304452896
2023-01-23 01:13:31.106256: step: 600/526, loss: 0.0006856441032141447
2023-01-23 01:13:32.270740: step: 604/526, loss: 0.10957708209753036
2023-01-23 01:13:33.387938: step: 608/526, loss: 0.0373167023062706
2023-01-23 01:13:34.514651: step: 612/526, loss: 0.0268572811037302
2023-01-23 01:13:35.651123: step: 616/526, loss: 0.043706513941287994
2023-01-23 01:13:36.785460: step: 620/526, loss: 0.1443004608154297
2023-01-23 01:13:37.923332: step: 624/526, loss: 0.032207682728767395
2023-01-23 01:13:39.056888: step: 628/526, loss: 0.14608363807201385
2023-01-23 01:13:40.199273: step: 632/526, loss: 1.1984728574752808
2023-01-23 01:13:41.341432: step: 636/526, loss: 0.04691801220178604
2023-01-23 01:13:42.474769: step: 640/526, loss: 0.13143710792064667
2023-01-23 01:13:43.622747: step: 644/526, loss: 0.04209737852215767
2023-01-23 01:13:44.740129: step: 648/526, loss: 0.07995434105396271
2023-01-23 01:13:45.893772: step: 652/526, loss: 0.005539512727409601
2023-01-23 01:13:47.043179: step: 656/526, loss: 0.032628726214170456
2023-01-23 01:13:48.160514: step: 660/526, loss: 0.030490685254335403
2023-01-23 01:13:49.313366: step: 664/526, loss: 0.073316290974617
2023-01-23 01:13:50.450441: step: 668/526, loss: 0.496309757232666
2023-01-23 01:13:51.589594: step: 672/526, loss: 0.1407543122768402
2023-01-23 01:13:52.745085: step: 676/526, loss: 0.004931735806167126
2023-01-23 01:13:53.897949: step: 680/526, loss: 0.011069202795624733
2023-01-23 01:13:55.041119: step: 684/526, loss: 0.011652231216430664
2023-01-23 01:13:56.178190: step: 688/526, loss: 0.05863799899816513
2023-01-23 01:13:57.292868: step: 692/526, loss: 0.12837858498096466
2023-01-23 01:13:58.440151: step: 696/526, loss: 0.010602951049804688
2023-01-23 01:13:59.546910: step: 700/526, loss: 0.0979333445429802
2023-01-23 01:14:00.669652: step: 704/526, loss: 0.014994812197983265
2023-01-23 01:14:01.788489: step: 708/526, loss: 0.00142078404314816
2023-01-23 01:14:02.924046: step: 712/526, loss: 0.01856342703104019
2023-01-23 01:14:04.041547: step: 716/526, loss: 0.06520041823387146
2023-01-23 01:14:05.157643: step: 720/526, loss: 0.01949338987469673
2023-01-23 01:14:06.277128: step: 724/526, loss: 0.011514759622514248
2023-01-23 01:14:07.415391: step: 728/526, loss: 0.22837772965431213
2023-01-23 01:14:08.521372: step: 732/526, loss: 0.08065585792064667
2023-01-23 01:14:09.649267: step: 736/526, loss: 0.10996055603027344
2023-01-23 01:14:10.800082: step: 740/526, loss: 0.042223989963531494
2023-01-23 01:14:11.920287: step: 744/526, loss: 0.0754416435956955
2023-01-23 01:14:13.073937: step: 748/526, loss: 0.05606689676642418
2023-01-23 01:14:14.204365: step: 752/526, loss: 0.00275592808611691
2023-01-23 01:14:15.335673: step: 756/526, loss: 0.10385185480117798
2023-01-23 01:14:16.521794: step: 760/526, loss: 0.09406185150146484
2023-01-23 01:14:17.658009: step: 764/526, loss: 0.04433479160070419
2023-01-23 01:14:18.827908: step: 768/526, loss: 0.03898601606488228
2023-01-23 01:14:19.932491: step: 772/526, loss: 0.047724343836307526
2023-01-23 01:14:21.052688: step: 776/526, loss: 0.014749574474990368
2023-01-23 01:14:22.194573: step: 780/526, loss: 0.009395027533173561
2023-01-23 01:14:23.336822: step: 784/526, loss: 0.132147878408432
2023-01-23 01:14:24.456836: step: 788/526, loss: 0.014745360240340233
2023-01-23 01:14:25.588633: step: 792/526, loss: 0.0352899543941021
2023-01-23 01:14:26.725878: step: 796/526, loss: 0.05112161859869957
2023-01-23 01:14:27.873998: step: 800/526, loss: 0.05016679689288139
2023-01-23 01:14:29.015291: step: 804/526, loss: 0.04091458395123482
2023-01-23 01:14:30.153970: step: 808/526, loss: 0.03102698363363743
2023-01-23 01:14:31.306587: step: 812/526, loss: 0.07510252296924591
2023-01-23 01:14:32.420724: step: 816/526, loss: 0.009077358059585094
2023-01-23 01:14:33.559134: step: 820/526, loss: 0.0262330062687397
2023-01-23 01:14:34.659343: step: 824/526, loss: 0.02296009100973606
2023-01-23 01:14:35.788601: step: 828/526, loss: 0.047461796551942825
2023-01-23 01:14:36.931958: step: 832/526, loss: 0.021651649847626686
2023-01-23 01:14:38.069427: step: 836/526, loss: 0.041078757494688034
2023-01-23 01:14:39.190606: step: 840/526, loss: 0.37376919388771057
2023-01-23 01:14:40.344434: step: 844/526, loss: 0.1277790069580078
2023-01-23 01:14:41.501973: step: 848/526, loss: 0.08828449249267578
2023-01-23 01:14:42.675357: step: 852/526, loss: 0.15048810839653015
2023-01-23 01:14:43.802325: step: 856/526, loss: 0.20188234746456146
2023-01-23 01:14:44.929373: step: 860/526, loss: 0.0610136054456234
2023-01-23 01:14:46.062823: step: 864/526, loss: 0.1468985676765442
2023-01-23 01:14:47.186514: step: 868/526, loss: 0.13093385100364685
2023-01-23 01:14:48.331375: step: 872/526, loss: 0.34043940901756287
2023-01-23 01:14:49.481693: step: 876/526, loss: 0.046022605150938034
2023-01-23 01:14:50.646758: step: 880/526, loss: 0.057181455194950104
2023-01-23 01:14:51.808701: step: 884/526, loss: 0.06816444545984268
2023-01-23 01:14:52.974407: step: 888/526, loss: 0.06227097287774086
2023-01-23 01:14:54.132456: step: 892/526, loss: 0.030421830713748932
2023-01-23 01:14:55.276562: step: 896/526, loss: 0.19506484270095825
2023-01-23 01:14:56.406652: step: 900/526, loss: 0.020766019821166992
2023-01-23 01:14:57.533733: step: 904/526, loss: 0.14779242873191833
2023-01-23 01:14:58.673966: step: 908/526, loss: 0.007510280702263117
2023-01-23 01:14:59.837693: step: 912/526, loss: 0.09319205582141876
2023-01-23 01:15:00.986105: step: 916/526, loss: 0.06066341698169708
2023-01-23 01:15:02.132880: step: 920/526, loss: 0.032367803156375885
2023-01-23 01:15:03.275480: step: 924/526, loss: 0.19828377664089203
2023-01-23 01:15:04.381200: step: 928/526, loss: 0.0059191701002418995
2023-01-23 01:15:05.505311: step: 932/526, loss: 0.00969848595559597
2023-01-23 01:15:06.656567: step: 936/526, loss: 0.019677067175507545
2023-01-23 01:15:07.771180: step: 940/526, loss: 0.06122016906738281
2023-01-23 01:15:08.885601: step: 944/526, loss: 0.011370975524187088
2023-01-23 01:15:10.006525: step: 948/526, loss: 0.013803817331790924
2023-01-23 01:15:11.124612: step: 952/526, loss: 0.02003936655819416
2023-01-23 01:15:12.247907: step: 956/526, loss: 0.02453165128827095
2023-01-23 01:15:13.374870: step: 960/526, loss: 0.007159424014389515
2023-01-23 01:15:14.523208: step: 964/526, loss: 0.027132224291563034
2023-01-23 01:15:15.658217: step: 968/526, loss: 0.06755886226892471
2023-01-23 01:15:16.790371: step: 972/526, loss: 0.08049201965332031
2023-01-23 01:15:17.952422: step: 976/526, loss: 0.16731682419776917
2023-01-23 01:15:19.107616: step: 980/526, loss: 0.08363030105829239
2023-01-23 01:15:20.247097: step: 984/526, loss: 0.01293573435395956
2023-01-23 01:15:21.377753: step: 988/526, loss: 0.044126223772764206
2023-01-23 01:15:22.522009: step: 992/526, loss: 0.23999693989753723
2023-01-23 01:15:23.656261: step: 996/526, loss: 0.03117094188928604
2023-01-23 01:15:24.779806: step: 1000/526, loss: 0.04149474948644638
2023-01-23 01:15:25.916465: step: 1004/526, loss: 0.030040835961699486
2023-01-23 01:15:27.021586: step: 1008/526, loss: 0.05211935192346573
2023-01-23 01:15:28.150419: step: 1012/526, loss: 0.07298517227172852
2023-01-23 01:15:29.318371: step: 1016/526, loss: 0.004798555746674538
2023-01-23 01:15:30.469149: step: 1020/526, loss: 0.07155527919530869
2023-01-23 01:15:31.587840: step: 1024/526, loss: 0.009870529174804688
2023-01-23 01:15:32.751530: step: 1028/526, loss: 0.06878840923309326
2023-01-23 01:15:33.902744: step: 1032/526, loss: 0.054642342031002045
2023-01-23 01:15:35.030267: step: 1036/526, loss: 0.059169963002204895
2023-01-23 01:15:36.156104: step: 1040/526, loss: 0.12754793465137482
2023-01-23 01:15:37.280910: step: 1044/526, loss: 0.030283259227871895
2023-01-23 01:15:38.397019: step: 1048/526, loss: 0.025376440957188606
2023-01-23 01:15:39.521208: step: 1052/526, loss: 0.01849508285522461
2023-01-23 01:15:40.634411: step: 1056/526, loss: 0.007206773851066828
2023-01-23 01:15:41.806889: step: 1060/526, loss: 0.022374916821718216
2023-01-23 01:15:42.954028: step: 1064/526, loss: 0.05935974046587944
2023-01-23 01:15:44.084050: step: 1068/526, loss: 0.02503185346722603
2023-01-23 01:15:45.251856: step: 1072/526, loss: 0.05175476148724556
2023-01-23 01:15:46.400093: step: 1076/526, loss: 0.05761241912841797
2023-01-23 01:15:47.567627: step: 1080/526, loss: 0.03208618238568306
2023-01-23 01:15:48.686522: step: 1084/526, loss: 0.013869166374206543
2023-01-23 01:15:49.806029: step: 1088/526, loss: 0.3287279009819031
2023-01-23 01:15:50.912913: step: 1092/526, loss: 0.12407165765762329
2023-01-23 01:15:52.019334: step: 1096/526, loss: 0.07733113318681717
2023-01-23 01:15:53.199795: step: 1100/526, loss: 0.02474966086447239
2023-01-23 01:15:54.346671: step: 1104/526, loss: 0.05765619874000549
2023-01-23 01:15:55.495917: step: 1108/526, loss: 0.055417634546756744
2023-01-23 01:15:56.638566: step: 1112/526, loss: 0.07246103137731552
2023-01-23 01:15:57.761412: step: 1116/526, loss: 0.05764341354370117
2023-01-23 01:15:58.881041: step: 1120/526, loss: 0.08796558529138565
2023-01-23 01:16:00.021736: step: 1124/526, loss: 0.11782994121313095
2023-01-23 01:16:01.162837: step: 1128/526, loss: 0.6517559289932251
2023-01-23 01:16:02.312910: step: 1132/526, loss: 0.03792142868041992
2023-01-23 01:16:03.437550: step: 1136/526, loss: 0.012488747015595436
2023-01-23 01:16:04.579518: step: 1140/526, loss: 0.003528594970703125
2023-01-23 01:16:05.727592: step: 1144/526, loss: 0.09680843353271484
2023-01-23 01:16:06.852238: step: 1148/526, loss: 0.023140262812376022
2023-01-23 01:16:08.015015: step: 1152/526, loss: 0.025685502216219902
2023-01-23 01:16:09.153489: step: 1156/526, loss: 0.00809102039784193
2023-01-23 01:16:10.315559: step: 1160/526, loss: 0.11041207611560822
2023-01-23 01:16:11.464063: step: 1164/526, loss: 0.06896954029798508
2023-01-23 01:16:12.591151: step: 1168/526, loss: 0.1656995713710785
2023-01-23 01:16:13.743823: step: 1172/526, loss: 0.08468323200941086
2023-01-23 01:16:14.875517: step: 1176/526, loss: 0.06340312957763672
2023-01-23 01:16:15.990302: step: 1180/526, loss: 0.054660990834236145
2023-01-23 01:16:17.122978: step: 1184/526, loss: 0.009999657049775124
2023-01-23 01:16:18.286805: step: 1188/526, loss: 0.19355127215385437
2023-01-23 01:16:19.401152: step: 1192/526, loss: 0.08167479187250137
2023-01-23 01:16:20.541820: step: 1196/526, loss: 0.04205026850104332
2023-01-23 01:16:21.702509: step: 1200/526, loss: 0.10201139748096466
2023-01-23 01:16:22.838092: step: 1204/526, loss: 0.08033923804759979
2023-01-23 01:16:23.955112: step: 1208/526, loss: 0.10385928303003311
2023-01-23 01:16:25.118130: step: 1212/526, loss: 0.08103971183300018
2023-01-23 01:16:26.289213: step: 1216/526, loss: 0.0748133659362793
2023-01-23 01:16:27.422475: step: 1220/526, loss: 0.022324658930301666
2023-01-23 01:16:28.560864: step: 1224/526, loss: 0.04760704189538956
2023-01-23 01:16:29.705606: step: 1228/526, loss: 0.014558887109160423
2023-01-23 01:16:30.856620: step: 1232/526, loss: 0.031389132142066956
2023-01-23 01:16:32.005270: step: 1236/526, loss: 0.02243518829345703
2023-01-23 01:16:33.123044: step: 1240/526, loss: 0.02817354165017605
2023-01-23 01:16:34.256101: step: 1244/526, loss: 0.04374952241778374
2023-01-23 01:16:35.387117: step: 1248/526, loss: 0.050734326243400574
2023-01-23 01:16:36.534805: step: 1252/526, loss: 0.09195242077112198
2023-01-23 01:16:37.675591: step: 1256/526, loss: 0.03470778465270996
2023-01-23 01:16:38.830615: step: 1260/526, loss: 0.0790136381983757
2023-01-23 01:16:39.992736: step: 1264/526, loss: 0.1336391419172287
2023-01-23 01:16:41.122373: step: 1268/526, loss: 0.03554688021540642
2023-01-23 01:16:42.242360: step: 1272/526, loss: 0.02658400498330593
2023-01-23 01:16:43.400531: step: 1276/526, loss: 0.06641463935375214
2023-01-23 01:16:44.531301: step: 1280/526, loss: 0.0794897973537445
2023-01-23 01:16:45.694574: step: 1284/526, loss: 0.05838785320520401
2023-01-23 01:16:46.821768: step: 1288/526, loss: 0.01993265189230442
2023-01-23 01:16:47.951847: step: 1292/526, loss: 0.2914840579032898
2023-01-23 01:16:49.088664: step: 1296/526, loss: 0.026393413543701172
2023-01-23 01:16:50.217409: step: 1300/526, loss: 0.051714133471250534
2023-01-23 01:16:51.345890: step: 1304/526, loss: 0.033529095351696014
2023-01-23 01:16:52.478794: step: 1308/526, loss: 0.15825581550598145
2023-01-23 01:16:53.611537: step: 1312/526, loss: 0.010504817590117455
2023-01-23 01:16:54.745951: step: 1316/526, loss: 0.1150369644165039
2023-01-23 01:16:55.916576: step: 1320/526, loss: 0.10432469844818115
2023-01-23 01:16:57.042566: step: 1324/526, loss: 0.023850345984101295
2023-01-23 01:16:58.189961: step: 1328/526, loss: 0.3994367718696594
2023-01-23 01:16:59.298465: step: 1332/526, loss: 0.003780448343604803
2023-01-23 01:17:00.460816: step: 1336/526, loss: 0.05550122261047363
2023-01-23 01:17:01.622188: step: 1340/526, loss: 0.05399675294756889
2023-01-23 01:17:02.729281: step: 1344/526, loss: 0.008647250942885876
2023-01-23 01:17:03.829422: step: 1348/526, loss: 0.03377723693847656
2023-01-23 01:17:04.955628: step: 1352/526, loss: 0.08250083774328232
2023-01-23 01:17:06.086403: step: 1356/526, loss: 0.09580240398645401
2023-01-23 01:17:07.219953: step: 1360/526, loss: 0.017348527908325195
2023-01-23 01:17:08.358034: step: 1364/526, loss: 0.0042724609375
2023-01-23 01:17:09.501417: step: 1368/526, loss: 0.017301440238952637
2023-01-23 01:17:10.665346: step: 1372/526, loss: 0.004537248983979225
2023-01-23 01:17:11.852887: step: 1376/526, loss: 0.14740857481956482
2023-01-23 01:17:13.011928: step: 1380/526, loss: 0.03909559175372124
2023-01-23 01:17:14.156809: step: 1384/526, loss: 0.16381597518920898
2023-01-23 01:17:15.284743: step: 1388/526, loss: 0.03183326870203018
2023-01-23 01:17:16.392587: step: 1392/526, loss: 0.0280427448451519
2023-01-23 01:17:17.543609: step: 1396/526, loss: 0.1238887831568718
2023-01-23 01:17:18.700317: step: 1400/526, loss: 0.07164116203784943
2023-01-23 01:17:19.858287: step: 1404/526, loss: 0.03279304504394531
2023-01-23 01:17:20.996708: step: 1408/526, loss: 0.05606594309210777
2023-01-23 01:17:22.144862: step: 1412/526, loss: 0.014059877023100853
2023-01-23 01:17:23.262024: step: 1416/526, loss: 0.004166269209235907
2023-01-23 01:17:24.391610: step: 1420/526, loss: 0.2109052687883377
2023-01-23 01:17:25.508337: step: 1424/526, loss: 0.0957794189453125
2023-01-23 01:17:26.661798: step: 1428/526, loss: 0.028122520074248314
2023-01-23 01:17:27.773801: step: 1432/526, loss: 0.0031442642211914062
2023-01-23 01:17:28.894668: step: 1436/526, loss: 0.2259502410888672
2023-01-23 01:17:30.032769: step: 1440/526, loss: 0.05520162731409073
2023-01-23 01:17:31.175762: step: 1444/526, loss: 0.09885750710964203
2023-01-23 01:17:32.302876: step: 1448/526, loss: 0.017478371039032936
2023-01-23 01:17:33.438201: step: 1452/526, loss: 0.055128954350948334
2023-01-23 01:17:34.561263: step: 1456/526, loss: 0.0517701655626297
2023-01-23 01:17:35.701265: step: 1460/526, loss: 0.011632347479462624
2023-01-23 01:17:36.851046: step: 1464/526, loss: 0.03318033367395401
2023-01-23 01:17:38.010791: step: 1468/526, loss: 0.11411857604980469
2023-01-23 01:17:39.130356: step: 1472/526, loss: 0.19330093264579773
2023-01-23 01:17:40.288287: step: 1476/526, loss: 0.06672678142786026
2023-01-23 01:17:41.454963: step: 1480/526, loss: 0.08597736805677414
2023-01-23 01:17:42.559992: step: 1484/526, loss: 0.10448607057332993
2023-01-23 01:17:43.724361: step: 1488/526, loss: 0.01931598410010338
2023-01-23 01:17:44.882175: step: 1492/526, loss: 0.013746977783739567
2023-01-23 01:17:45.997496: step: 1496/526, loss: 0.004908561706542969
2023-01-23 01:17:47.187133: step: 1500/526, loss: 0.03815726935863495
2023-01-23 01:17:48.308373: step: 1504/526, loss: 0.028313064947724342
2023-01-23 01:17:49.447875: step: 1508/526, loss: 0.06979440897703171
2023-01-23 01:17:50.616590: step: 1512/526, loss: 0.07203473895788193
2023-01-23 01:17:51.714724: step: 1516/526, loss: 0.05343141779303551
2023-01-23 01:17:52.877142: step: 1520/526, loss: 0.027323532849550247
2023-01-23 01:17:54.019794: step: 1524/526, loss: 0.07754402607679367
2023-01-23 01:17:55.146670: step: 1528/526, loss: 0.06882844120264053
2023-01-23 01:17:56.270294: step: 1532/526, loss: 0.01407613791525364
2023-01-23 01:17:57.427721: step: 1536/526, loss: 0.02982468530535698
2023-01-23 01:17:58.575276: step: 1540/526, loss: 0.19618263840675354
2023-01-23 01:17:59.687369: step: 1544/526, loss: 0.30988186597824097
2023-01-23 01:18:00.814305: step: 1548/526, loss: 0.03654642030596733
2023-01-23 01:18:01.920540: step: 1552/526, loss: 0.007747936062514782
2023-01-23 01:18:03.071136: step: 1556/526, loss: 0.10610080510377884
2023-01-23 01:18:04.213896: step: 1560/526, loss: 0.10457658767700195
2023-01-23 01:18:05.346462: step: 1564/526, loss: 0.35605552792549133
2023-01-23 01:18:06.506248: step: 1568/526, loss: 0.0793820396065712
2023-01-23 01:18:07.609071: step: 1572/526, loss: 0.13206414878368378
2023-01-23 01:18:08.746558: step: 1576/526, loss: 0.12931156158447266
2023-01-23 01:18:09.890069: step: 1580/526, loss: 0.052256204187870026
2023-01-23 01:18:11.030992: step: 1584/526, loss: 0.07471618801355362
2023-01-23 01:18:12.148615: step: 1588/526, loss: 0.14208492636680603
2023-01-23 01:18:13.272799: step: 1592/526, loss: 0.45212239027023315
2023-01-23 01:18:14.400754: step: 1596/526, loss: 0.019907426089048386
2023-01-23 01:18:15.560264: step: 1600/526, loss: 0.03246612846851349
2023-01-23 01:18:16.685827: step: 1604/526, loss: 0.05747561901807785
2023-01-23 01:18:17.805308: step: 1608/526, loss: 0.02671222761273384
2023-01-23 01:18:18.929045: step: 1612/526, loss: 0.03648632764816284
2023-01-23 01:18:20.054063: step: 1616/526, loss: 0.03674755245447159
2023-01-23 01:18:21.208313: step: 1620/526, loss: 0.008162951096892357
2023-01-23 01:18:22.349001: step: 1624/526, loss: 0.03517938032746315
2023-01-23 01:18:23.453405: step: 1628/526, loss: 0.08168144524097443
2023-01-23 01:18:24.562034: step: 1632/526, loss: 0.16347496211528778
2023-01-23 01:18:25.674362: step: 1636/526, loss: 0.04364819452166557
2023-01-23 01:18:26.803593: step: 1640/526, loss: 0.014599466696381569
2023-01-23 01:18:27.917224: step: 1644/526, loss: 0.026294518262147903
2023-01-23 01:18:29.089167: step: 1648/526, loss: 0.047118380665779114
2023-01-23 01:18:30.243306: step: 1652/526, loss: 0.07855091243982315
2023-01-23 01:18:31.409983: step: 1656/526, loss: 0.21931058168411255
2023-01-23 01:18:32.554667: step: 1660/526, loss: 0.08486151695251465
2023-01-23 01:18:33.673249: step: 1664/526, loss: 0.027772333472967148
2023-01-23 01:18:34.798712: step: 1668/526, loss: 0.04638214409351349
2023-01-23 01:18:35.939348: step: 1672/526, loss: 0.020376110449433327
2023-01-23 01:18:37.102921: step: 1676/526, loss: 0.12195605784654617
2023-01-23 01:18:38.243507: step: 1680/526, loss: 0.11245956271886826
2023-01-23 01:18:39.365797: step: 1684/526, loss: 0.18732263147830963
2023-01-23 01:18:40.503036: step: 1688/526, loss: 0.42811423540115356
2023-01-23 01:18:41.637944: step: 1692/526, loss: 0.033809103071689606
2023-01-23 01:18:42.765964: step: 1696/526, loss: 0.02467980608344078
2023-01-23 01:18:43.937684: step: 1700/526, loss: 0.07565413415431976
2023-01-23 01:18:45.064204: step: 1704/526, loss: 0.06971245259046555
2023-01-23 01:18:46.183912: step: 1708/526, loss: 0.02219533920288086
2023-01-23 01:18:47.303120: step: 1712/526, loss: 0.035179756581783295
2023-01-23 01:18:48.445279: step: 1716/526, loss: 0.024142790585756302
2023-01-23 01:18:49.580825: step: 1720/526, loss: 0.045146238058805466
2023-01-23 01:18:50.711315: step: 1724/526, loss: 0.008876467123627663
2023-01-23 01:18:51.867650: step: 1728/526, loss: 0.07120724022388458
2023-01-23 01:18:52.973310: step: 1732/526, loss: 0.004645633976906538
2023-01-23 01:18:54.112069: step: 1736/526, loss: 0.04314884915947914
2023-01-23 01:18:55.200897: step: 1740/526, loss: 0.12078976631164551
2023-01-23 01:18:56.340308: step: 1744/526, loss: 0.023958493024110794
2023-01-23 01:18:57.483619: step: 1748/526, loss: 0.08768635243177414
2023-01-23 01:18:58.620638: step: 1752/526, loss: 0.01675243303179741
2023-01-23 01:18:59.771354: step: 1756/526, loss: 0.028470231220126152
2023-01-23 01:19:00.894558: step: 1760/526, loss: 0.004552984144538641
2023-01-23 01:19:02.047197: step: 1764/526, loss: 0.10632573068141937
2023-01-23 01:19:03.222493: step: 1768/526, loss: 0.11652755737304688
2023-01-23 01:19:04.344508: step: 1772/526, loss: 0.13604259490966797
2023-01-23 01:19:05.467826: step: 1776/526, loss: 0.28422442078590393
2023-01-23 01:19:06.594526: step: 1780/526, loss: 0.048311520367860794
2023-01-23 01:19:07.713164: step: 1784/526, loss: 0.03549493849277496
2023-01-23 01:19:08.843341: step: 1788/526, loss: 0.01968097686767578
2023-01-23 01:19:09.986725: step: 1792/526, loss: 0.02958536148071289
2023-01-23 01:19:11.121359: step: 1796/526, loss: 0.007223033811897039
2023-01-23 01:19:12.278469: step: 1800/526, loss: 0.17660921812057495
2023-01-23 01:19:13.441224: step: 1804/526, loss: 0.010737895965576172
2023-01-23 01:19:14.598673: step: 1808/526, loss: 0.03359851986169815
2023-01-23 01:19:15.750970: step: 1812/526, loss: 0.0781548023223877
2023-01-23 01:19:16.903452: step: 1816/526, loss: 0.1672716736793518
2023-01-23 01:19:18.021823: step: 1820/526, loss: 0.009849358350038528
2023-01-23 01:19:19.160621: step: 1824/526, loss: 0.11711722612380981
2023-01-23 01:19:20.290081: step: 1828/526, loss: 0.019664956256747246
2023-01-23 01:19:21.413252: step: 1832/526, loss: 0.016196250915527344
2023-01-23 01:19:22.562910: step: 1836/526, loss: 0.12970009446144104
2023-01-23 01:19:23.689314: step: 1840/526, loss: 0.041359614580869675
2023-01-23 01:19:24.823949: step: 1844/526, loss: 0.02796030230820179
2023-01-23 01:19:25.941254: step: 1848/526, loss: 0.10098437964916229
2023-01-23 01:19:27.121388: step: 1852/526, loss: 0.0474674254655838
2023-01-23 01:19:28.271201: step: 1856/526, loss: 0.02993020974099636
2023-01-23 01:19:29.406720: step: 1860/526, loss: 0.08916177600622177
2023-01-23 01:19:30.548031: step: 1864/526, loss: 0.05043373256921768
2023-01-23 01:19:31.669599: step: 1868/526, loss: 0.13478927314281464
2023-01-23 01:19:32.813872: step: 1872/526, loss: 0.003322315402328968
2023-01-23 01:19:33.915385: step: 1876/526, loss: 0.048246145248413086
2023-01-23 01:19:35.040134: step: 1880/526, loss: 0.0334840789437294
2023-01-23 01:19:36.178364: step: 1884/526, loss: 0.0033965588081628084
2023-01-23 01:19:37.303552: step: 1888/526, loss: 0.018155859783291817
2023-01-23 01:19:38.428635: step: 1892/526, loss: 0.005624675657600164
2023-01-23 01:19:39.560248: step: 1896/526, loss: 0.027116205543279648
2023-01-23 01:19:40.674497: step: 1900/526, loss: 0.08187694847583771
2023-01-23 01:19:41.778341: step: 1904/526, loss: 0.0037211417220532894
2023-01-23 01:19:42.933370: step: 1908/526, loss: 0.04520740360021591
2023-01-23 01:19:44.059178: step: 1912/526, loss: 0.515699565410614
2023-01-23 01:19:45.170754: step: 1916/526, loss: 0.039029501378536224
2023-01-23 01:19:46.298559: step: 1920/526, loss: 0.06831901520490646
2023-01-23 01:19:47.415792: step: 1924/526, loss: 0.035895347595214844
2023-01-23 01:19:48.574145: step: 1928/526, loss: 0.024035751819610596
2023-01-23 01:19:49.714138: step: 1932/526, loss: 0.043511394411325455
2023-01-23 01:19:50.839362: step: 1936/526, loss: 0.023209620267152786
2023-01-23 01:19:51.999176: step: 1940/526, loss: 0.08647099137306213
2023-01-23 01:19:53.115498: step: 1944/526, loss: 0.08339639008045197
2023-01-23 01:19:54.284542: step: 1948/526, loss: 0.08672972023487091
2023-01-23 01:19:55.411149: step: 1952/526, loss: 0.1704721450805664
2023-01-23 01:19:56.547016: step: 1956/526, loss: 0.13986149430274963
2023-01-23 01:19:57.695540: step: 1960/526, loss: 0.10825100541114807
2023-01-23 01:19:58.828304: step: 1964/526, loss: 1.1889848709106445
2023-01-23 01:19:59.979027: step: 1968/526, loss: 0.027541637420654297
2023-01-23 01:20:01.122529: step: 1972/526, loss: 0.0064182281494140625
2023-01-23 01:20:02.278051: step: 1976/526, loss: 0.03887768089771271
2023-01-23 01:20:03.414387: step: 1980/526, loss: 0.07199759781360626
2023-01-23 01:20:04.575148: step: 1984/526, loss: 0.03553476184606552
2023-01-23 01:20:05.697935: step: 1988/526, loss: 0.04219427332282066
2023-01-23 01:20:06.872896: step: 1992/526, loss: 0.22363309562206268
2023-01-23 01:20:08.052789: step: 1996/526, loss: 0.04667210578918457
2023-01-23 01:20:09.151283: step: 2000/526, loss: 0.0815645232796669
2023-01-23 01:20:10.311117: step: 2004/526, loss: 0.0011970996856689453
2023-01-23 01:20:11.434060: step: 2008/526, loss: 0.05406847223639488
2023-01-23 01:20:12.546945: step: 2012/526, loss: 0.15167349576950073
2023-01-23 01:20:13.725666: step: 2016/526, loss: 0.08149395138025284
2023-01-23 01:20:14.861193: step: 2020/526, loss: 0.1271902173757553
2023-01-23 01:20:16.088985: step: 2024/526, loss: 0.035814858973026276
2023-01-23 01:20:17.264751: step: 2028/526, loss: 0.2741064131259918
2023-01-23 01:20:18.399719: step: 2032/526, loss: 0.19340907037258148
2023-01-23 01:20:19.520781: step: 2036/526, loss: 0.05843010172247887
2023-01-23 01:20:20.656472: step: 2040/526, loss: 0.0958930030465126
2023-01-23 01:20:21.793702: step: 2044/526, loss: 0.07399062812328339
2023-01-23 01:20:22.920656: step: 2048/526, loss: 0.08161049336194992
2023-01-23 01:20:24.083951: step: 2052/526, loss: 0.18087102472782135
2023-01-23 01:20:25.225736: step: 2056/526, loss: 0.09563814103603363
2023-01-23 01:20:26.351091: step: 2060/526, loss: 0.050290297716856
2023-01-23 01:20:27.488674: step: 2064/526, loss: 0.10206671059131622
2023-01-23 01:20:28.663350: step: 2068/526, loss: 0.07828088104724884
2023-01-23 01:20:29.786628: step: 2072/526, loss: 0.03274235874414444
2023-01-23 01:20:30.937484: step: 2076/526, loss: 0.012637329287827015
2023-01-23 01:20:32.085786: step: 2080/526, loss: 0.09160013496875763
2023-01-23 01:20:33.263263: step: 2084/526, loss: 0.02294163778424263
2023-01-23 01:20:34.383722: step: 2088/526, loss: 0.006971931550651789
2023-01-23 01:20:35.539787: step: 2092/526, loss: 0.0292356014251709
2023-01-23 01:20:36.671579: step: 2096/526, loss: 0.14679566025733948
2023-01-23 01:20:37.793272: step: 2100/526, loss: 0.5074905157089233
2023-01-23 01:20:38.898590: step: 2104/526, loss: 0.5970926284790039
==================================================
Loss: 0.078
--------------------
Dev: {'event': {'p': 0.6217672413793104, 'r': 0.7683089214380826, 'f1': 0.6873138773079214}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Test: {'event': {'p': 0.6300302899177845, 'r': 0.7599164926931107, 'f1': 0.6889046605157322}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Chinese: {'event': {'p': 0.5595238095238095, 'r': 0.8703703703703703, 'f1': 0.6811594202898551}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Korean: {'event': {'p': 0.6530612244897959, 'r': 0.5079365079365079, 'f1': 0.5714285714285714}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Russian: {'event': {'p': 0.5, 'r': 0.5833333333333334, 'f1': 0.5384615384615384}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
New best russian model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6604010025062657, 'r': 0.7017310252996005, 'f1': 0.6804389928986443}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Eng Test for Chinese: {'event': {'p': 0.6480836236933798, 'r': 0.6795407098121086, 'f1': 0.6634394904458599}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Sample Chinese: {'event': {'p': 0.6323529411764706, 'r': 0.7962962962962963, 'f1': 0.7049180327868853}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6257995735607675, 'r': 0.7816245006657789, 'f1': 0.6950858496151568}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Eng Test for Korean: {'event': {'p': 0.623113410952997, 'r': 0.7541753653444676, 'f1': 0.6824085005903188}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Sample Korean: {'event': {'p': 0.7446808510638298, 'r': 0.5555555555555556, 'f1': 0.6363636363636364}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6217672413793104, 'r': 0.7683089214380826, 'f1': 0.6873138773079214}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Eng Test for Russian: {'event': {'p': 0.6300302899177845, 'r': 0.7599164926931107, 'f1': 0.6889046605157322}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Sample Russian: {'event': {'p': 0.5, 'r': 0.5833333333333334, 'f1': 0.5384615384615384}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
******************************
Epoch: 11
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 01:21:29.475237: step: 4/526, loss: 0.7875440716743469
2023-01-23 01:21:30.608028: step: 8/526, loss: 0.02249932289123535
2023-01-23 01:21:31.765484: step: 12/526, loss: 0.004925346467643976
2023-01-23 01:21:32.872595: step: 16/526, loss: 0.02322368696331978
2023-01-23 01:21:33.995572: step: 20/526, loss: 0.05778513103723526
2023-01-23 01:21:35.145703: step: 24/526, loss: 0.027384568005800247
2023-01-23 01:21:36.282030: step: 28/526, loss: 0.04867757484316826
2023-01-23 01:21:37.381896: step: 32/526, loss: 0.03923201560974121
2023-01-23 01:21:38.524260: step: 36/526, loss: 0.05661306530237198
2023-01-23 01:21:39.659735: step: 40/526, loss: 0.04953975975513458
2023-01-23 01:21:40.791795: step: 44/526, loss: 0.03000359609723091
2023-01-23 01:21:41.932940: step: 48/526, loss: 0.03891410678625107
2023-01-23 01:21:43.113175: step: 52/526, loss: 0.033743537962436676
2023-01-23 01:21:44.238039: step: 56/526, loss: 0.007989120669662952
2023-01-23 01:21:45.387163: step: 60/526, loss: 0.010918332263827324
2023-01-23 01:21:46.495482: step: 64/526, loss: 0.09751138836145401
2023-01-23 01:21:47.617102: step: 68/526, loss: 0.02198515087366104
2023-01-23 01:21:48.761006: step: 72/526, loss: 0.01547012384980917
2023-01-23 01:21:49.882781: step: 76/526, loss: 0.08279826492071152
2023-01-23 01:21:51.013176: step: 80/526, loss: 0.16883696615695953
2023-01-23 01:21:52.131175: step: 84/526, loss: 0.0665230080485344
2023-01-23 01:21:53.260185: step: 88/526, loss: 0.023172665387392044
2023-01-23 01:21:54.422519: step: 92/526, loss: 0.003418541047722101
2023-01-23 01:21:55.540523: step: 96/526, loss: 0.03295326232910156
2023-01-23 01:21:56.668944: step: 100/526, loss: 0.15467782318592072
2023-01-23 01:21:57.801247: step: 104/526, loss: 0.04071483761072159
2023-01-23 01:21:58.922619: step: 108/526, loss: 0.023386195302009583
2023-01-23 01:22:00.055446: step: 112/526, loss: 0.07622185349464417
2023-01-23 01:22:01.159012: step: 116/526, loss: 0.04514904320240021
2023-01-23 01:22:02.277869: step: 120/526, loss: 0.013074207119643688
2023-01-23 01:22:03.410941: step: 124/526, loss: 0.0023229599464684725
2023-01-23 01:22:04.588447: step: 128/526, loss: 0.015420341864228249
2023-01-23 01:22:05.727567: step: 132/526, loss: 0.041366007179021835
2023-01-23 01:22:06.856761: step: 136/526, loss: 0.06983594596385956
2023-01-23 01:22:07.974978: step: 140/526, loss: 0.06665734946727753
2023-01-23 01:22:09.102855: step: 144/526, loss: 0.0364743210375309
2023-01-23 01:22:10.235448: step: 148/526, loss: 0.07817334681749344
2023-01-23 01:22:11.368591: step: 152/526, loss: 0.06048621982336044
2023-01-23 01:22:12.501750: step: 156/526, loss: 0.008032036013901234
2023-01-23 01:22:13.636181: step: 160/526, loss: 0.10645437985658646
2023-01-23 01:22:14.793064: step: 164/526, loss: 0.017642784863710403
2023-01-23 01:22:15.906953: step: 168/526, loss: 0.010627923533320427
2023-01-23 01:22:17.044735: step: 172/526, loss: 0.015745734795928
2023-01-23 01:22:18.173312: step: 176/526, loss: 0.4386845529079437
2023-01-23 01:22:19.310958: step: 180/526, loss: 0.02267928048968315
2023-01-23 01:22:20.447492: step: 184/526, loss: 0.05037736892700195
2023-01-23 01:22:21.565411: step: 188/526, loss: 0.01201620139181614
2023-01-23 01:22:22.722853: step: 192/526, loss: 0.06117381900548935
2023-01-23 01:22:23.863575: step: 196/526, loss: 0.022325992584228516
2023-01-23 01:22:25.022389: step: 200/526, loss: 0.07804547250270844
2023-01-23 01:22:26.163744: step: 204/526, loss: 0.05018806457519531
2023-01-23 01:22:27.289207: step: 208/526, loss: 0.0376712828874588
2023-01-23 01:22:28.461156: step: 212/526, loss: 0.08962497860193253
2023-01-23 01:22:29.570209: step: 216/526, loss: 0.0306883342564106
2023-01-23 01:22:30.706746: step: 220/526, loss: 0.13745450973510742
2023-01-23 01:22:31.839386: step: 224/526, loss: 0.016959190368652344
2023-01-23 01:22:32.955386: step: 228/526, loss: 0.04527008533477783
2023-01-23 01:22:34.156476: step: 232/526, loss: 0.1183050125837326
2023-01-23 01:22:35.324151: step: 236/526, loss: 0.10537528991699219
2023-01-23 01:22:36.485839: step: 240/526, loss: 0.023282814770936966
2023-01-23 01:22:37.626680: step: 244/526, loss: 0.0017177105182781816
2023-01-23 01:22:38.755895: step: 248/526, loss: 0.07080788165330887
2023-01-23 01:22:39.877957: step: 252/526, loss: 0.006410121917724609
2023-01-23 01:22:41.017841: step: 256/526, loss: 0.07890644669532776
2023-01-23 01:22:42.121962: step: 260/526, loss: 0.0656648650765419
2023-01-23 01:22:43.275929: step: 264/526, loss: 0.014365863986313343
2023-01-23 01:22:44.483549: step: 268/526, loss: 0.4121030867099762
2023-01-23 01:22:45.616341: step: 272/526, loss: 0.011065102182328701
2023-01-23 01:22:46.772371: step: 276/526, loss: 0.07069685310125351
2023-01-23 01:22:47.909037: step: 280/526, loss: 2.1570065021514893
2023-01-23 01:22:49.037266: step: 284/526, loss: 0.08994360268115997
2023-01-23 01:22:50.158716: step: 288/526, loss: 0.05215740203857422
2023-01-23 01:22:51.254866: step: 292/526, loss: 0.00024046898761298507
2023-01-23 01:22:52.390947: step: 296/526, loss: 0.09027834236621857
2023-01-23 01:22:53.562874: step: 300/526, loss: 0.08672408759593964
2023-01-23 01:22:54.686369: step: 304/526, loss: 0.09557781368494034
2023-01-23 01:22:55.828159: step: 308/526, loss: 0.03354682773351669
2023-01-23 01:22:56.955418: step: 312/526, loss: 0.006915283389389515
2023-01-23 01:22:58.102284: step: 316/526, loss: 0.050173282623291016
2023-01-23 01:22:59.228173: step: 320/526, loss: 0.022202301770448685
2023-01-23 01:23:00.367832: step: 324/526, loss: 0.027315808460116386
2023-01-23 01:23:01.494529: step: 328/526, loss: 0.04655585438013077
2023-01-23 01:23:02.622017: step: 332/526, loss: 0.003204727079719305
2023-01-23 01:23:03.779976: step: 336/526, loss: 0.05240964889526367
2023-01-23 01:23:04.902498: step: 340/526, loss: 0.027200888842344284
2023-01-23 01:23:06.046621: step: 344/526, loss: 0.04323005676269531
2023-01-23 01:23:07.159799: step: 348/526, loss: 0.011305427178740501
2023-01-23 01:23:08.278605: step: 352/526, loss: 0.0011354446178302169
2023-01-23 01:23:09.440019: step: 356/526, loss: 0.03729061037302017
2023-01-23 01:23:10.579786: step: 360/526, loss: 0.0022614479530602694
2023-01-23 01:23:11.705101: step: 364/526, loss: 0.04951276630163193
2023-01-23 01:23:12.866056: step: 368/526, loss: 0.005857181269675493
2023-01-23 01:23:13.996436: step: 372/526, loss: 0.028737831860780716
2023-01-23 01:23:15.116159: step: 376/526, loss: 0.12956352531909943
2023-01-23 01:23:16.262440: step: 380/526, loss: 0.2627403140068054
2023-01-23 01:23:17.403827: step: 384/526, loss: 0.05890006944537163
2023-01-23 01:23:18.533214: step: 388/526, loss: 0.001965141389518976
2023-01-23 01:23:19.651442: step: 392/526, loss: 0.14423684775829315
2023-01-23 01:23:20.762307: step: 396/526, loss: 0.038520436733961105
2023-01-23 01:23:21.913849: step: 400/526, loss: 0.14634761214256287
2023-01-23 01:23:23.049511: step: 404/526, loss: 0.060933783650398254
2023-01-23 01:23:24.225233: step: 408/526, loss: 0.12302875518798828
2023-01-23 01:23:25.352368: step: 412/526, loss: 0.01497945748269558
2023-01-23 01:23:26.544595: step: 416/526, loss: 0.06960439682006836
2023-01-23 01:23:27.672204: step: 420/526, loss: 0.16288337111473083
2023-01-23 01:23:28.811539: step: 424/526, loss: 0.0877465307712555
2023-01-23 01:23:29.976258: step: 428/526, loss: 0.0016601562965661287
2023-01-23 01:23:31.132853: step: 432/526, loss: 0.02856769599020481
2023-01-23 01:23:32.278995: step: 436/526, loss: 0.45875853300094604
2023-01-23 01:23:33.409212: step: 440/526, loss: 0.04623117670416832
2023-01-23 01:23:34.562356: step: 444/526, loss: 0.08636818081140518
2023-01-23 01:23:35.682237: step: 448/526, loss: 0.17690840363502502
2023-01-23 01:23:36.818318: step: 452/526, loss: 0.04018135368824005
2023-01-23 01:23:37.945626: step: 456/526, loss: 0.0006117820739746094
2023-01-23 01:23:39.114904: step: 460/526, loss: 0.044963836669921875
2023-01-23 01:23:40.268022: step: 464/526, loss: 0.04150800779461861
2023-01-23 01:23:41.384131: step: 468/526, loss: 0.029713820666074753
2023-01-23 01:23:42.524183: step: 472/526, loss: 0.08301468193531036
2023-01-23 01:23:43.622234: step: 476/526, loss: 0.06878957897424698
2023-01-23 01:23:44.759331: step: 480/526, loss: 0.002543926239013672
2023-01-23 01:23:45.880670: step: 484/526, loss: 0.020890522748231888
2023-01-23 01:23:47.031978: step: 488/526, loss: 0.006577491760253906
2023-01-23 01:23:48.247508: step: 492/526, loss: 0.028504230082035065
2023-01-23 01:23:49.401575: step: 496/526, loss: 0.11988388001918793
2023-01-23 01:23:50.556961: step: 500/526, loss: 0.04588508605957031
2023-01-23 01:23:51.695642: step: 504/526, loss: 0.06446514278650284
2023-01-23 01:23:52.841557: step: 508/526, loss: 0.20085124671459198
2023-01-23 01:23:53.987114: step: 512/526, loss: 0.14871521294116974
2023-01-23 01:23:55.101076: step: 516/526, loss: 0.016603756695985794
2023-01-23 01:23:56.253789: step: 520/526, loss: 0.017780590802431107
2023-01-23 01:23:57.356140: step: 524/526, loss: 0.029329968616366386
2023-01-23 01:23:58.465651: step: 528/526, loss: 0.06928665935993195
2023-01-23 01:23:59.585315: step: 532/526, loss: 0.1715715527534485
2023-01-23 01:24:00.701775: step: 536/526, loss: 0.012115097604691982
2023-01-23 01:24:01.824362: step: 540/526, loss: 0.021280813962221146
2023-01-23 01:24:02.928894: step: 544/526, loss: 0.4144185185432434
2023-01-23 01:24:04.050634: step: 548/526, loss: 0.1649942547082901
2023-01-23 01:24:05.186277: step: 552/526, loss: 0.040679000318050385
2023-01-23 01:24:06.336641: step: 556/526, loss: 0.01966571807861328
2023-01-23 01:24:07.462313: step: 560/526, loss: 0.0019033432472497225
2023-01-23 01:24:08.613014: step: 564/526, loss: 0.2586946487426758
2023-01-23 01:24:09.765065: step: 568/526, loss: 0.07293100655078888
2023-01-23 01:24:10.901779: step: 572/526, loss: 0.09041118621826172
2023-01-23 01:24:12.055205: step: 576/526, loss: 0.0097503662109375
2023-01-23 01:24:13.187630: step: 580/526, loss: 0.05258836969733238
2023-01-23 01:24:14.348887: step: 584/526, loss: 0.02617006190121174
2023-01-23 01:24:15.493247: step: 588/526, loss: 0.0029286383651196957
2023-01-23 01:24:16.644411: step: 592/526, loss: 0.1657407581806183
2023-01-23 01:24:17.766047: step: 596/526, loss: 0.022541143000125885
2023-01-23 01:24:18.906894: step: 600/526, loss: 0.16706332564353943
2023-01-23 01:24:20.001435: step: 604/526, loss: 0.004824066534638405
2023-01-23 01:24:21.108285: step: 608/526, loss: 0.9176253080368042
2023-01-23 01:24:22.285648: step: 612/526, loss: 0.008787775412201881
2023-01-23 01:24:23.419516: step: 616/526, loss: 0.02135448530316353
2023-01-23 01:24:24.561141: step: 620/526, loss: 0.037813473492860794
2023-01-23 01:24:25.692391: step: 624/526, loss: 0.019387150183320045
2023-01-23 01:24:26.828466: step: 628/526, loss: 0.011272287927567959
2023-01-23 01:24:27.988767: step: 632/526, loss: 0.026995087042450905
2023-01-23 01:24:29.137194: step: 636/526, loss: 0.014538098126649857
2023-01-23 01:24:30.293268: step: 640/526, loss: 0.07078027725219727
2023-01-23 01:24:31.429196: step: 644/526, loss: 0.09060049057006836
2023-01-23 01:24:32.578555: step: 648/526, loss: 0.0013401031028479338
2023-01-23 01:24:33.726971: step: 652/526, loss: 0.06468410789966583
2023-01-23 01:24:34.879778: step: 656/526, loss: 0.09370870888233185
2023-01-23 01:24:36.024113: step: 660/526, loss: 0.09635104984045029
2023-01-23 01:24:37.146442: step: 664/526, loss: 0.15643177926540375
2023-01-23 01:24:38.287058: step: 668/526, loss: 0.07567481696605682
2023-01-23 01:24:39.432815: step: 672/526, loss: 0.0414765365421772
2023-01-23 01:24:40.553498: step: 676/526, loss: 0.06897668540477753
2023-01-23 01:24:41.667813: step: 680/526, loss: 0.13982850313186646
2023-01-23 01:24:42.802702: step: 684/526, loss: 0.0678325816988945
2023-01-23 01:24:43.951716: step: 688/526, loss: 0.1256331503391266
2023-01-23 01:24:45.083652: step: 692/526, loss: 0.09280691295862198
2023-01-23 01:24:46.226653: step: 696/526, loss: 0.08952607959508896
2023-01-23 01:24:47.388213: step: 700/526, loss: 0.04745883867144585
2023-01-23 01:24:48.548426: step: 704/526, loss: 0.02794818766415119
2023-01-23 01:24:49.686504: step: 708/526, loss: 0.01044159010052681
2023-01-23 01:24:50.829715: step: 712/526, loss: 0.024486351758241653
2023-01-23 01:24:51.978658: step: 716/526, loss: 0.04224910959601402
2023-01-23 01:24:53.129188: step: 720/526, loss: 0.01577301137149334
2023-01-23 01:24:54.293947: step: 724/526, loss: 0.030944060534238815
2023-01-23 01:24:55.386257: step: 728/526, loss: 0.04078331217169762
2023-01-23 01:24:56.550745: step: 732/526, loss: 0.06733899563550949
2023-01-23 01:24:57.693892: step: 736/526, loss: 0.03284921869635582
2023-01-23 01:24:58.832637: step: 740/526, loss: 0.011911321431398392
2023-01-23 01:24:59.957514: step: 744/526, loss: 0.03274650499224663
2023-01-23 01:25:01.121822: step: 748/526, loss: 0.05940263345837593
2023-01-23 01:25:02.273131: step: 752/526, loss: 0.12280355393886566
2023-01-23 01:25:03.411233: step: 756/526, loss: 0.0732354149222374
2023-01-23 01:25:04.555767: step: 760/526, loss: 0.022115040570497513
2023-01-23 01:25:05.691550: step: 764/526, loss: 0.014854812994599342
2023-01-23 01:25:06.811232: step: 768/526, loss: 0.006291211117058992
2023-01-23 01:25:07.939890: step: 772/526, loss: 0.033112525939941406
2023-01-23 01:25:09.059634: step: 776/526, loss: 0.06358539313077927
2023-01-23 01:25:10.201888: step: 780/526, loss: 0.0706118568778038
2023-01-23 01:25:11.365705: step: 784/526, loss: 0.06204243004322052
2023-01-23 01:25:12.502926: step: 788/526, loss: 0.054195500910282135
2023-01-23 01:25:13.622681: step: 792/526, loss: 0.01781935803592205
2023-01-23 01:25:14.724288: step: 796/526, loss: 0.007649135310202837
2023-01-23 01:25:15.892295: step: 800/526, loss: 0.02671995386481285
2023-01-23 01:25:17.019265: step: 804/526, loss: 0.06302700191736221
2023-01-23 01:25:18.140476: step: 808/526, loss: 0.05171575769782066
2023-01-23 01:25:19.286075: step: 812/526, loss: 0.07220802456140518
2023-01-23 01:25:20.438501: step: 816/526, loss: 0.058527376502752304
2023-01-23 01:25:21.575914: step: 820/526, loss: 0.021082116290926933
2023-01-23 01:25:22.722191: step: 824/526, loss: 0.1577732115983963
2023-01-23 01:25:23.879641: step: 828/526, loss: 0.04468078911304474
2023-01-23 01:25:24.990573: step: 832/526, loss: 0.10990381240844727
2023-01-23 01:25:26.101593: step: 836/526, loss: 0.01732635498046875
2023-01-23 01:25:27.275374: step: 840/526, loss: 0.032190799713134766
2023-01-23 01:25:28.415530: step: 844/526, loss: 0.03010735660791397
2023-01-23 01:25:29.534469: step: 848/526, loss: 0.061919644474983215
2023-01-23 01:25:30.666629: step: 852/526, loss: 0.009528684429824352
2023-01-23 01:25:31.821326: step: 856/526, loss: 0.013329267501831055
2023-01-23 01:25:32.943300: step: 860/526, loss: 0.08001852035522461
2023-01-23 01:25:34.074215: step: 864/526, loss: 0.0638311430811882
2023-01-23 01:25:35.217254: step: 868/526, loss: 0.018859058618545532
2023-01-23 01:25:36.368118: step: 872/526, loss: 0.08367881178855896
2023-01-23 01:25:37.510047: step: 876/526, loss: 0.0007014751899987459
2023-01-23 01:25:38.679732: step: 880/526, loss: 0.06270580738782883
2023-01-23 01:25:39.809573: step: 884/526, loss: 0.028011512011289597
2023-01-23 01:25:40.963984: step: 888/526, loss: 0.0805811882019043
2023-01-23 01:25:42.089555: step: 892/526, loss: 0.12155047059059143
2023-01-23 01:25:43.211117: step: 896/526, loss: 0.14108867943286896
2023-01-23 01:25:44.384923: step: 900/526, loss: 0.01929459534585476
2023-01-23 01:25:45.520264: step: 904/526, loss: 0.01830129697918892
2023-01-23 01:25:46.694210: step: 908/526, loss: 0.05306129530072212
2023-01-23 01:25:47.828761: step: 912/526, loss: 0.09303779155015945
2023-01-23 01:25:48.979612: step: 916/526, loss: 0.10501112788915634
2023-01-23 01:25:50.134191: step: 920/526, loss: 0.04940962791442871
2023-01-23 01:25:51.307688: step: 924/526, loss: 0.3828137218952179
2023-01-23 01:25:52.440339: step: 928/526, loss: 0.0023636340629309416
2023-01-23 01:25:53.563883: step: 932/526, loss: 0.02647123485803604
2023-01-23 01:25:54.718793: step: 936/526, loss: 0.09867896884679794
2023-01-23 01:25:55.834170: step: 940/526, loss: 0.046065427362918854
2023-01-23 01:25:57.059796: step: 944/526, loss: 0.03982894495129585
2023-01-23 01:25:58.200684: step: 948/526, loss: 0.045298196375370026
2023-01-23 01:25:59.319220: step: 952/526, loss: 0.03884153068065643
2023-01-23 01:26:00.462592: step: 956/526, loss: 0.03743448108434677
2023-01-23 01:26:01.569436: step: 960/526, loss: 0.046800754964351654
2023-01-23 01:26:02.701181: step: 964/526, loss: 0.005704021546989679
2023-01-23 01:26:03.821137: step: 968/526, loss: 0.01610422134399414
2023-01-23 01:26:04.951981: step: 972/526, loss: 0.06591711193323135
2023-01-23 01:26:06.104346: step: 976/526, loss: 0.026584720239043236
2023-01-23 01:26:07.261192: step: 980/526, loss: 0.103411965072155
2023-01-23 01:26:08.392081: step: 984/526, loss: 0.1741001158952713
2023-01-23 01:26:09.548764: step: 988/526, loss: 0.0450650230050087
2023-01-23 01:26:10.716085: step: 992/526, loss: 0.005143642891198397
2023-01-23 01:26:11.859139: step: 996/526, loss: 0.015406466089189053
2023-01-23 01:26:13.001570: step: 1000/526, loss: 0.012519837357103825
2023-01-23 01:26:14.114805: step: 1004/526, loss: 0.035891368985176086
2023-01-23 01:26:15.255518: step: 1008/526, loss: 0.08953256905078888
2023-01-23 01:26:16.405077: step: 1012/526, loss: 0.03525133058428764
2023-01-23 01:26:17.540372: step: 1016/526, loss: 0.0743812620639801
2023-01-23 01:26:18.702211: step: 1020/526, loss: 0.26910096406936646
2023-01-23 01:26:19.836520: step: 1024/526, loss: 0.0531248115003109
2023-01-23 01:26:20.983345: step: 1028/526, loss: 0.042627908289432526
2023-01-23 01:26:22.114854: step: 1032/526, loss: 0.08183574676513672
2023-01-23 01:26:23.268932: step: 1036/526, loss: 0.01733860932290554
2023-01-23 01:26:24.424777: step: 1040/526, loss: 0.05517435073852539
2023-01-23 01:26:25.577652: step: 1044/526, loss: 0.12523861229419708
2023-01-23 01:26:26.758687: step: 1048/526, loss: 0.16399379074573517
2023-01-23 01:26:27.861578: step: 1052/526, loss: 0.01727323606610298
2023-01-23 01:26:28.984861: step: 1056/526, loss: 0.40482062101364136
2023-01-23 01:26:30.122248: step: 1060/526, loss: 0.03465118259191513
2023-01-23 01:26:31.278099: step: 1064/526, loss: 0.09335631877183914
2023-01-23 01:26:32.407933: step: 1068/526, loss: 0.009600735269486904
2023-01-23 01:26:33.566730: step: 1072/526, loss: 0.03583049774169922
2023-01-23 01:26:34.740789: step: 1076/526, loss: 0.02284879796206951
2023-01-23 01:26:35.868698: step: 1080/526, loss: 0.01699678972363472
2023-01-23 01:26:37.012859: step: 1084/526, loss: 0.07446169853210449
2023-01-23 01:26:38.151076: step: 1088/526, loss: 0.04209384694695473
2023-01-23 01:26:39.266657: step: 1092/526, loss: 0.026517678052186966
2023-01-23 01:26:40.384736: step: 1096/526, loss: 0.006968879606574774
2023-01-23 01:26:41.505521: step: 1100/526, loss: 0.04068265110254288
2023-01-23 01:26:42.640272: step: 1104/526, loss: 0.22661571204662323
2023-01-23 01:26:43.779942: step: 1108/526, loss: 0.025042343884706497
2023-01-23 01:26:44.926816: step: 1112/526, loss: 0.011298942379653454
2023-01-23 01:26:46.087984: step: 1116/526, loss: 0.0077888015657663345
2023-01-23 01:26:47.251923: step: 1120/526, loss: 0.05329904705286026
2023-01-23 01:26:48.374482: step: 1124/526, loss: 0.029503442347049713
2023-01-23 01:26:49.512984: step: 1128/526, loss: 0.022494984790682793
2023-01-23 01:26:50.662087: step: 1132/526, loss: 0.11945438385009766
2023-01-23 01:26:51.826087: step: 1136/526, loss: 0.027576161548495293
2023-01-23 01:26:52.945947: step: 1140/526, loss: 0.012827587313950062
2023-01-23 01:26:54.065264: step: 1144/526, loss: 0.03182496875524521
2023-01-23 01:26:55.200743: step: 1148/526, loss: 0.05577068775892258
2023-01-23 01:26:56.352524: step: 1152/526, loss: 0.010259103029966354
2023-01-23 01:26:57.513992: step: 1156/526, loss: 0.05718441307544708
2023-01-23 01:26:58.668236: step: 1160/526, loss: 0.14575956761837006
2023-01-23 01:26:59.786470: step: 1164/526, loss: 0.014760971069335938
2023-01-23 01:27:00.926639: step: 1168/526, loss: 0.1333659142255783
2023-01-23 01:27:02.082545: step: 1172/526, loss: 0.006091308780014515
2023-01-23 01:27:03.218457: step: 1176/526, loss: 0.07075687497854233
2023-01-23 01:27:04.346964: step: 1180/526, loss: 0.029253197833895683
2023-01-23 01:27:05.490112: step: 1184/526, loss: 0.02695169672369957
2023-01-23 01:27:06.617130: step: 1188/526, loss: 0.023044109344482422
2023-01-23 01:27:07.765524: step: 1192/526, loss: 0.08442975580692291
2023-01-23 01:27:08.890516: step: 1196/526, loss: 0.02315702475607395
2023-01-23 01:27:10.073401: step: 1200/526, loss: 0.3992482125759125
2023-01-23 01:27:11.230082: step: 1204/526, loss: 0.06844520568847656
2023-01-23 01:27:12.366552: step: 1208/526, loss: 0.017757605761289597
2023-01-23 01:27:13.521101: step: 1212/526, loss: 0.016434574499726295
2023-01-23 01:27:14.670314: step: 1216/526, loss: 0.05191526561975479
2023-01-23 01:27:15.802712: step: 1220/526, loss: 0.040917206555604935
2023-01-23 01:27:16.951406: step: 1224/526, loss: 0.04365057870745659
2023-01-23 01:27:18.080903: step: 1228/526, loss: 0.03348054736852646
2023-01-23 01:27:19.215668: step: 1232/526, loss: 0.003781127743422985
2023-01-23 01:27:20.352134: step: 1236/526, loss: 0.022966481745243073
2023-01-23 01:27:21.506229: step: 1240/526, loss: 0.23435230553150177
2023-01-23 01:27:22.658156: step: 1244/526, loss: 0.07387170940637589
2023-01-23 01:27:23.783257: step: 1248/526, loss: 0.04220600426197052
2023-01-23 01:27:24.922354: step: 1252/526, loss: 0.22918277978897095
2023-01-23 01:27:26.064910: step: 1256/526, loss: 0.2728847563266754
2023-01-23 01:27:27.204425: step: 1260/526, loss: 0.1085447371006012
2023-01-23 01:27:28.384274: step: 1264/526, loss: 0.27389073371887207
2023-01-23 01:27:29.548271: step: 1268/526, loss: 0.0417238250374794
2023-01-23 01:27:30.716516: step: 1272/526, loss: 0.05303382873535156
2023-01-23 01:27:31.852991: step: 1276/526, loss: 0.030916860327124596
2023-01-23 01:27:32.960561: step: 1280/526, loss: 0.029001297429203987
2023-01-23 01:27:34.097532: step: 1284/526, loss: 0.07766552269458771
2023-01-23 01:27:35.265380: step: 1288/526, loss: 0.09346818923950195
2023-01-23 01:27:36.406945: step: 1292/526, loss: 0.0011556625831872225
2023-01-23 01:27:37.540575: step: 1296/526, loss: 0.08032999187707901
2023-01-23 01:27:38.657745: step: 1300/526, loss: 0.03483548015356064
2023-01-23 01:27:39.842496: step: 1304/526, loss: 0.04926605522632599
2023-01-23 01:27:40.981838: step: 1308/526, loss: 0.04237718507647514
2023-01-23 01:27:42.079365: step: 1312/526, loss: 0.015924930572509766
2023-01-23 01:27:43.202271: step: 1316/526, loss: 0.0515320785343647
2023-01-23 01:27:44.338988: step: 1320/526, loss: 0.017804985865950584
2023-01-23 01:27:45.466215: step: 1324/526, loss: 0.0012434959644451737
2023-01-23 01:27:46.597622: step: 1328/526, loss: 0.02672438696026802
2023-01-23 01:27:47.733141: step: 1332/526, loss: 0.05814165994524956
2023-01-23 01:27:48.843942: step: 1336/526, loss: 0.001913738320581615
2023-01-23 01:27:49.977229: step: 1340/526, loss: 0.008213615976274014
2023-01-23 01:27:51.095904: step: 1344/526, loss: 0.042535971850156784
2023-01-23 01:27:52.239423: step: 1348/526, loss: 0.3972126841545105
2023-01-23 01:27:53.378124: step: 1352/526, loss: 0.007982779294252396
2023-01-23 01:27:54.502036: step: 1356/526, loss: 0.023943137377500534
2023-01-23 01:27:55.629956: step: 1360/526, loss: 0.04347553476691246
2023-01-23 01:27:56.772570: step: 1364/526, loss: 0.0876404345035553
2023-01-23 01:27:57.943216: step: 1368/526, loss: 0.09897013008594513
2023-01-23 01:27:59.073374: step: 1372/526, loss: 0.03507370874285698
2023-01-23 01:28:00.210440: step: 1376/526, loss: 0.021694118157029152
2023-01-23 01:28:01.389938: step: 1380/526, loss: 0.008884811773896217
2023-01-23 01:28:02.513447: step: 1384/526, loss: 0.009718275628983974
2023-01-23 01:28:03.641603: step: 1388/526, loss: 0.033117104321718216
2023-01-23 01:28:04.796287: step: 1392/526, loss: 0.23833851516246796
2023-01-23 01:28:05.917143: step: 1396/526, loss: 0.022200584411621094
2023-01-23 01:28:07.100240: step: 1400/526, loss: 0.07133479416370392
2023-01-23 01:28:08.244118: step: 1404/526, loss: 0.021805191412568092
2023-01-23 01:28:09.361037: step: 1408/526, loss: 0.10773412883281708
2023-01-23 01:28:10.488218: step: 1412/526, loss: 0.020034123212099075
2023-01-23 01:28:11.623467: step: 1416/526, loss: 0.06970882415771484
2023-01-23 01:28:12.773011: step: 1420/526, loss: 0.012594223953783512
2023-01-23 01:28:13.894210: step: 1424/526, loss: 0.07655420899391174
2023-01-23 01:28:15.040168: step: 1428/526, loss: 0.01114511489868164
2023-01-23 01:28:16.179688: step: 1432/526, loss: 0.1356087177991867
2023-01-23 01:28:17.300964: step: 1436/526, loss: 0.004479885101318359
2023-01-23 01:28:18.443371: step: 1440/526, loss: 0.1724068820476532
2023-01-23 01:28:19.574572: step: 1444/526, loss: 0.061400797218084335
2023-01-23 01:28:20.697567: step: 1448/526, loss: 0.05605662986636162
2023-01-23 01:28:21.840211: step: 1452/526, loss: 0.003729534102603793
2023-01-23 01:28:23.011101: step: 1456/526, loss: 0.16875191032886505
2023-01-23 01:28:24.175107: step: 1460/526, loss: 0.04922027885913849
2023-01-23 01:28:25.326988: step: 1464/526, loss: 0.07462406903505325
2023-01-23 01:28:26.469054: step: 1468/526, loss: 0.026093482971191406
2023-01-23 01:28:27.603056: step: 1472/526, loss: 0.04679737240076065
2023-01-23 01:28:28.773363: step: 1476/526, loss: 0.05691566318273544
2023-01-23 01:28:29.907457: step: 1480/526, loss: 0.04170060157775879
2023-01-23 01:28:31.042556: step: 1484/526, loss: 0.03397498279809952
2023-01-23 01:28:32.142808: step: 1488/526, loss: 0.031627655029296875
2023-01-23 01:28:33.256842: step: 1492/526, loss: 0.020652294158935547
2023-01-23 01:28:34.388659: step: 1496/526, loss: 0.04655003547668457
2023-01-23 01:28:35.538545: step: 1500/526, loss: 0.09661178290843964
2023-01-23 01:28:36.665414: step: 1504/526, loss: 0.7788635492324829
2023-01-23 01:28:37.809388: step: 1508/526, loss: 0.054302215576171875
2023-01-23 01:28:38.965607: step: 1512/526, loss: 0.03610391542315483
2023-01-23 01:28:40.104087: step: 1516/526, loss: 0.04607558250427246
2023-01-23 01:28:41.271082: step: 1520/526, loss: 0.016023922711610794
2023-01-23 01:28:42.401090: step: 1524/526, loss: 0.005801391787827015
2023-01-23 01:28:43.531531: step: 1528/526, loss: 0.06605930626392365
2023-01-23 01:28:44.669427: step: 1532/526, loss: 0.015055418945848942
2023-01-23 01:28:45.809534: step: 1536/526, loss: 0.023659851402044296
2023-01-23 01:28:46.959691: step: 1540/526, loss: 0.023528099060058594
2023-01-23 01:28:48.078947: step: 1544/526, loss: 0.03215980902314186
2023-01-23 01:28:49.194128: step: 1548/526, loss: 0.02749185636639595
2023-01-23 01:28:50.328956: step: 1552/526, loss: 0.13465410470962524
2023-01-23 01:28:51.450037: step: 1556/526, loss: 0.05170431360602379
2023-01-23 01:28:52.615766: step: 1560/526, loss: 0.1625603288412094
2023-01-23 01:28:53.747085: step: 1564/526, loss: 0.045168355107307434
2023-01-23 01:28:54.884511: step: 1568/526, loss: 0.008575725369155407
2023-01-23 01:28:56.030270: step: 1572/526, loss: 0.0715770274400711
2023-01-23 01:28:57.147869: step: 1576/526, loss: 0.1396162509918213
2023-01-23 01:28:58.287768: step: 1580/526, loss: 0.05045466870069504
2023-01-23 01:28:59.402073: step: 1584/526, loss: 0.03575272485613823
2023-01-23 01:29:00.526575: step: 1588/526, loss: 0.01935606077313423
2023-01-23 01:29:01.652439: step: 1592/526, loss: 0.019881058484315872
2023-01-23 01:29:02.805223: step: 1596/526, loss: 0.042699433863162994
2023-01-23 01:29:03.943898: step: 1600/526, loss: 0.02517561987042427
2023-01-23 01:29:05.062114: step: 1604/526, loss: 0.010599327273666859
2023-01-23 01:29:06.228654: step: 1608/526, loss: 0.05540146678686142
2023-01-23 01:29:07.376797: step: 1612/526, loss: 0.09423694014549255
2023-01-23 01:29:08.492985: step: 1616/526, loss: 0.46620291471481323
2023-01-23 01:29:09.630109: step: 1620/526, loss: 0.035639550536870956
2023-01-23 01:29:10.761537: step: 1624/526, loss: 0.07630367577075958
2023-01-23 01:29:11.910736: step: 1628/526, loss: 0.14377766847610474
2023-01-23 01:29:13.051351: step: 1632/526, loss: 0.01673140563070774
2023-01-23 01:29:14.200521: step: 1636/526, loss: 0.029838846996426582
2023-01-23 01:29:15.344147: step: 1640/526, loss: 0.01385793648660183
2023-01-23 01:29:16.459419: step: 1644/526, loss: 0.027337361127138138
2023-01-23 01:29:17.613194: step: 1648/526, loss: 0.008957100100815296
2023-01-23 01:29:18.733027: step: 1652/526, loss: 0.027769137173891068
2023-01-23 01:29:19.893962: step: 1656/526, loss: 0.020801641047000885
2023-01-23 01:29:21.014793: step: 1660/526, loss: 0.0037563801743090153
2023-01-23 01:29:22.150342: step: 1664/526, loss: 0.10962390899658203
2023-01-23 01:29:23.315936: step: 1668/526, loss: 0.018858812749385834
2023-01-23 01:29:24.434466: step: 1672/526, loss: 0.04797947406768799
2023-01-23 01:29:25.571306: step: 1676/526, loss: 0.10421662032604218
2023-01-23 01:29:26.694781: step: 1680/526, loss: 0.02319207228720188
2023-01-23 01:29:27.813810: step: 1684/526, loss: 0.0046520233154296875
2023-01-23 01:29:28.950764: step: 1688/526, loss: 0.015748977661132812
2023-01-23 01:29:30.095349: step: 1692/526, loss: 0.0009660244104452431
2023-01-23 01:29:31.240703: step: 1696/526, loss: 0.46494781970977783
2023-01-23 01:29:32.373248: step: 1700/526, loss: 0.038410186767578125
2023-01-23 01:29:33.461153: step: 1704/526, loss: 0.0030962468590587378
2023-01-23 01:29:34.578443: step: 1708/526, loss: 0.13460254669189453
2023-01-23 01:29:35.676785: step: 1712/526, loss: 0.29013940691947937
2023-01-23 01:29:36.787736: step: 1716/526, loss: 0.0002465248107910156
2023-01-23 01:29:37.878631: step: 1720/526, loss: 0.00477290153503418
2023-01-23 01:29:39.061978: step: 1724/526, loss: 0.11452846229076385
2023-01-23 01:29:40.187007: step: 1728/526, loss: 0.18054704368114471
2023-01-23 01:29:41.338154: step: 1732/526, loss: 0.028684616088867188
2023-01-23 01:29:42.452515: step: 1736/526, loss: 0.08340243995189667
2023-01-23 01:29:43.619181: step: 1740/526, loss: 0.0382143035531044
2023-01-23 01:29:44.779038: step: 1744/526, loss: 0.03238735347986221
2023-01-23 01:29:45.930246: step: 1748/526, loss: 0.06665096431970596
2023-01-23 01:29:47.065832: step: 1752/526, loss: 0.08878107368946075
2023-01-23 01:29:48.211095: step: 1756/526, loss: 0.07616205513477325
2023-01-23 01:29:49.325605: step: 1760/526, loss: 0.07322315871715546
2023-01-23 01:29:50.450724: step: 1764/526, loss: 0.33517712354660034
2023-01-23 01:29:51.606244: step: 1768/526, loss: 0.018207263201475143
2023-01-23 01:29:52.715757: step: 1772/526, loss: 0.048223115503787994
2023-01-23 01:29:53.863363: step: 1776/526, loss: 0.007552933879196644
2023-01-23 01:29:55.010847: step: 1780/526, loss: 0.03580122068524361
2023-01-23 01:29:56.134731: step: 1784/526, loss: 0.08817722648382187
2023-01-23 01:29:57.234677: step: 1788/526, loss: 0.007825946435332298
2023-01-23 01:29:58.368933: step: 1792/526, loss: 0.6622940897941589
2023-01-23 01:29:59.518400: step: 1796/526, loss: 0.11396083980798721
2023-01-23 01:30:00.675213: step: 1800/526, loss: 0.0024312972091138363
2023-01-23 01:30:01.807337: step: 1804/526, loss: 0.03350124508142471
2023-01-23 01:30:02.928095: step: 1808/526, loss: 0.013551807031035423
2023-01-23 01:30:04.063866: step: 1812/526, loss: 0.058525752276182175
2023-01-23 01:30:05.178433: step: 1816/526, loss: 0.0364532470703125
2023-01-23 01:30:06.363869: step: 1820/526, loss: 0.013156699016690254
2023-01-23 01:30:07.483232: step: 1824/526, loss: 0.039473772048950195
2023-01-23 01:30:08.626006: step: 1828/526, loss: 0.030416011810302734
2023-01-23 01:30:09.755126: step: 1832/526, loss: 0.011693526059389114
2023-01-23 01:30:10.890859: step: 1836/526, loss: 0.057546332478523254
2023-01-23 01:30:12.044216: step: 1840/526, loss: 0.09516707062721252
2023-01-23 01:30:13.177237: step: 1844/526, loss: 0.04046466201543808
2023-01-23 01:30:14.301374: step: 1848/526, loss: 0.02912139892578125
2023-01-23 01:30:15.423410: step: 1852/526, loss: 0.0180098544806242
2023-01-23 01:30:16.568219: step: 1856/526, loss: 0.029911089688539505
2023-01-23 01:30:17.715189: step: 1860/526, loss: 0.0234573595225811
2023-01-23 01:30:18.844593: step: 1864/526, loss: 0.008993816561996937
2023-01-23 01:30:19.968298: step: 1868/526, loss: 0.027631284669041634
2023-01-23 01:30:21.104383: step: 1872/526, loss: 0.023629046976566315
2023-01-23 01:30:22.301307: step: 1876/526, loss: 0.02846803516149521
2023-01-23 01:30:23.446488: step: 1880/526, loss: 0.04903569445014
2023-01-23 01:30:24.586446: step: 1884/526, loss: 0.06552944332361221
2023-01-23 01:30:25.728169: step: 1888/526, loss: 0.013401031494140625
2023-01-23 01:30:26.853473: step: 1892/526, loss: 0.05478954315185547
2023-01-23 01:30:27.972325: step: 1896/526, loss: 0.11679296940565109
2023-01-23 01:30:29.132069: step: 1900/526, loss: 0.04600093513727188
2023-01-23 01:30:30.304673: step: 1904/526, loss: 0.007589483633637428
2023-01-23 01:30:31.441815: step: 1908/526, loss: 0.41737622022628784
2023-01-23 01:30:32.571050: step: 1912/526, loss: 0.031861305236816406
2023-01-23 01:30:33.702210: step: 1916/526, loss: 0.05798816680908203
2023-01-23 01:30:34.860361: step: 1920/526, loss: 0.07336101680994034
2023-01-23 01:30:36.036932: step: 1924/526, loss: 0.15314950048923492
2023-01-23 01:30:37.185418: step: 1928/526, loss: 0.002681732177734375
2023-01-23 01:30:38.345521: step: 1932/526, loss: 0.4707014262676239
2023-01-23 01:30:39.474455: step: 1936/526, loss: 0.03202028200030327
2023-01-23 01:30:40.583296: step: 1940/526, loss: 0.004622364416718483
2023-01-23 01:30:41.714878: step: 1944/526, loss: 0.0360906608402729
2023-01-23 01:30:42.859254: step: 1948/526, loss: 0.017039014026522636
2023-01-23 01:30:43.974552: step: 1952/526, loss: 0.003299760865047574
2023-01-23 01:30:45.102630: step: 1956/526, loss: 0.0649019256234169
2023-01-23 01:30:46.230261: step: 1960/526, loss: 0.11012105643749237
2023-01-23 01:30:47.350556: step: 1964/526, loss: 0.11162881553173065
2023-01-23 01:30:48.484246: step: 1968/526, loss: 0.0005999326822347939
2023-01-23 01:30:49.625990: step: 1972/526, loss: 0.009122943505644798
2023-01-23 01:30:50.744170: step: 1976/526, loss: 0.11528149247169495
2023-01-23 01:30:51.861747: step: 1980/526, loss: 0.09085922688245773
2023-01-23 01:30:53.027642: step: 1984/526, loss: 0.006344890221953392
2023-01-23 01:30:54.163241: step: 1988/526, loss: 0.04867715761065483
2023-01-23 01:30:55.306564: step: 1992/526, loss: 0.0987405776977539
2023-01-23 01:30:56.453218: step: 1996/526, loss: 0.05556058883666992
2023-01-23 01:30:57.579348: step: 2000/526, loss: 0.01620776578783989
2023-01-23 01:30:58.720277: step: 2004/526, loss: 0.03907070308923721
2023-01-23 01:30:59.882630: step: 2008/526, loss: 0.014750957489013672
2023-01-23 01:31:01.008537: step: 2012/526, loss: 0.07001190632581711
2023-01-23 01:31:02.115199: step: 2016/526, loss: 0.5143219232559204
2023-01-23 01:31:03.228459: step: 2020/526, loss: 0.010564994998276234
2023-01-23 01:31:04.354250: step: 2024/526, loss: 0.10760851204395294
2023-01-23 01:31:05.474420: step: 2028/526, loss: 0.07874422520399094
2023-01-23 01:31:06.609194: step: 2032/526, loss: 0.06146583706140518
2023-01-23 01:31:07.739448: step: 2036/526, loss: 0.05511474609375
2023-01-23 01:31:08.868345: step: 2040/526, loss: 0.09309883415699005
2023-01-23 01:31:09.994201: step: 2044/526, loss: 0.043385982513427734
2023-01-23 01:31:11.200029: step: 2048/526, loss: 0.06844620406627655
2023-01-23 01:31:12.365265: step: 2052/526, loss: 0.046548936516046524
2023-01-23 01:31:13.473037: step: 2056/526, loss: 0.016779804602265358
2023-01-23 01:31:14.579848: step: 2060/526, loss: 0.07168009132146835
2023-01-23 01:31:15.693461: step: 2064/526, loss: 0.029972266405820847
2023-01-23 01:31:16.806284: step: 2068/526, loss: 0.04488839954137802
2023-01-23 01:31:17.960830: step: 2072/526, loss: 0.16236476600170135
2023-01-23 01:31:19.092900: step: 2076/526, loss: 0.2640199661254883
2023-01-23 01:31:20.214247: step: 2080/526, loss: 0.014705944806337357
2023-01-23 01:31:21.368325: step: 2084/526, loss: 0.13029327988624573
2023-01-23 01:31:22.515132: step: 2088/526, loss: 0.41745373606681824
2023-01-23 01:31:23.654417: step: 2092/526, loss: 0.04197096824645996
2023-01-23 01:31:24.789431: step: 2096/526, loss: 0.007121086586266756
2023-01-23 01:31:25.934779: step: 2100/526, loss: 0.03950660303235054
2023-01-23 01:31:27.074945: step: 2104/526, loss: 0.27300509810447693
==================================================
Loss: 0.075
--------------------
Dev: {'event': {'p': 0.6263498920086393, 'r': 0.7723035952063915, 'f1': 0.6917113893858079}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 11}
Test: {'event': {'p': 0.6342208642514185, 'r': 0.7583507306889353, 'f1': 0.6907535060613264}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 11}
Chinese: {'event': {'p': 0.5714285714285714, 'r': 0.8888888888888888, 'f1': 0.6956521739130435}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 11}
Korean: {'event': {'p': 0.7380952380952381, 'r': 0.49206349206349204, 'f1': 0.5904761904761904}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 11}
Russian: {'event': {'p': 0.5, 'r': 0.5277777777777778, 'f1': 0.5135135135135136}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 11}
New best chinese model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6263498920086393, 'r': 0.7723035952063915, 'f1': 0.6917113893858079}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 11}
Eng Test for Chinese: {'event': {'p': 0.6342208642514185, 'r': 0.7583507306889353, 'f1': 0.6907535060613264}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 11}
Sample Chinese: {'event': {'p': 0.5714285714285714, 'r': 0.8888888888888888, 'f1': 0.6956521739130435}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 11}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6257995735607675, 'r': 0.7816245006657789, 'f1': 0.6950858496151568}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Eng Test for Korean: {'event': {'p': 0.623113410952997, 'r': 0.7541753653444676, 'f1': 0.6824085005903188}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Sample Korean: {'event': {'p': 0.7446808510638298, 'r': 0.5555555555555556, 'f1': 0.6363636363636364}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6217672413793104, 'r': 0.7683089214380826, 'f1': 0.6873138773079214}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Eng Test for Russian: {'event': {'p': 0.6300302899177845, 'r': 0.7599164926931107, 'f1': 0.6889046605157322}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Sample Russian: {'event': {'p': 0.5, 'r': 0.5833333333333334, 'f1': 0.5384615384615384}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
******************************
Epoch: 12
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 01:32:15.522141: step: 4/526, loss: 0.005014276597648859
2023-01-23 01:32:16.692412: step: 8/526, loss: 0.15837565064430237
2023-01-23 01:32:17.834163: step: 12/526, loss: 0.02331562340259552
2023-01-23 01:32:18.962536: step: 16/526, loss: 0.05583696439862251
2023-01-23 01:32:20.117566: step: 20/526, loss: 0.02319946326315403
2023-01-23 01:32:21.246591: step: 24/526, loss: 0.07766366004943848
2023-01-23 01:32:22.352343: step: 28/526, loss: 0.007442283909767866
2023-01-23 01:32:23.477181: step: 32/526, loss: 0.11003002524375916
2023-01-23 01:32:24.581928: step: 36/526, loss: 0.0012899399735033512
2023-01-23 01:32:25.714721: step: 40/526, loss: 0.05518393591046333
2023-01-23 01:32:26.841158: step: 44/526, loss: 0.2991431951522827
2023-01-23 01:32:27.984001: step: 48/526, loss: 0.006704807281494141
2023-01-23 01:32:29.119965: step: 52/526, loss: 0.035034749656915665
2023-01-23 01:32:30.237080: step: 56/526, loss: 0.05994434654712677
2023-01-23 01:32:31.374092: step: 60/526, loss: 0.33890390396118164
2023-01-23 01:32:32.569569: step: 64/526, loss: 0.03724546357989311
2023-01-23 01:32:33.695062: step: 68/526, loss: 0.005110550206154585
2023-01-23 01:32:34.853991: step: 72/526, loss: 0.0189864169806242
2023-01-23 01:32:36.038397: step: 76/526, loss: 0.051998041570186615
2023-01-23 01:32:37.188114: step: 80/526, loss: 0.010298728942871094
2023-01-23 01:32:38.308693: step: 84/526, loss: 0.04920339584350586
2023-01-23 01:32:39.421902: step: 88/526, loss: 0.09373245388269424
2023-01-23 01:32:40.543119: step: 92/526, loss: 0.197038933634758
2023-01-23 01:32:41.692474: step: 96/526, loss: 0.07460059970617294
2023-01-23 01:32:42.853326: step: 100/526, loss: 0.018487263470888138
2023-01-23 01:32:44.001427: step: 104/526, loss: 0.19398756325244904
2023-01-23 01:32:45.166992: step: 108/526, loss: 0.0467960387468338
2023-01-23 01:32:46.306668: step: 112/526, loss: 0.03556842729449272
2023-01-23 01:32:47.517868: step: 116/526, loss: 0.07704783976078033
2023-01-23 01:32:48.632625: step: 120/526, loss: 0.033930111676454544
2023-01-23 01:32:49.742235: step: 124/526, loss: 0.09686551988124847
2023-01-23 01:32:50.886001: step: 128/526, loss: 0.08251826465129852
2023-01-23 01:32:52.011068: step: 132/526, loss: 0.22340141236782074
2023-01-23 01:32:53.157658: step: 136/526, loss: 0.23547811806201935
2023-01-23 01:32:54.295390: step: 140/526, loss: 0.16128763556480408
2023-01-23 01:32:55.423573: step: 144/526, loss: 0.01851787604391575
2023-01-23 01:32:56.551461: step: 148/526, loss: 0.0385284423828125
2023-01-23 01:32:57.698775: step: 152/526, loss: 0.06302586197853088
2023-01-23 01:32:58.822783: step: 156/526, loss: 0.007805442903190851
2023-01-23 01:32:59.946862: step: 160/526, loss: 0.0001601219264557585
2023-01-23 01:33:01.082356: step: 164/526, loss: 0.004538869950920343
2023-01-23 01:33:02.198874: step: 168/526, loss: 0.006539535708725452
2023-01-23 01:33:03.335298: step: 172/526, loss: 0.013204623013734818
2023-01-23 01:33:04.508764: step: 176/526, loss: 0.07103576511144638
2023-01-23 01:33:05.645959: step: 180/526, loss: 0.026652049273252487
2023-01-23 01:33:06.799097: step: 184/526, loss: 0.02602977864444256
2023-01-23 01:33:07.916045: step: 188/526, loss: 0.0026180269196629524
2023-01-23 01:33:09.097972: step: 192/526, loss: 0.05306531488895416
2023-01-23 01:33:10.225774: step: 196/526, loss: 0.0069921016693115234
2023-01-23 01:33:11.389043: step: 200/526, loss: 0.011813545599579811
2023-01-23 01:33:12.503197: step: 204/526, loss: 0.024253463372588158
2023-01-23 01:33:13.675823: step: 208/526, loss: 0.008948802947998047
2023-01-23 01:33:14.802153: step: 212/526, loss: 0.015288067981600761
2023-01-23 01:33:15.912092: step: 216/526, loss: 0.002563786692917347
2023-01-23 01:33:17.056938: step: 220/526, loss: 0.04061717912554741
2023-01-23 01:33:18.181288: step: 224/526, loss: 0.11216068267822266
2023-01-23 01:33:19.347371: step: 228/526, loss: 0.04761169105768204
2023-01-23 01:33:20.477598: step: 232/526, loss: 0.01874055713415146
2023-01-23 01:33:21.592661: step: 236/526, loss: 0.009713363833725452
2023-01-23 01:33:22.774798: step: 240/526, loss: 0.017380524426698685
2023-01-23 01:33:23.938523: step: 244/526, loss: 0.050794124603271484
2023-01-23 01:33:25.085606: step: 248/526, loss: 0.013465499505400658
2023-01-23 01:33:26.210985: step: 252/526, loss: 0.02010054513812065
2023-01-23 01:33:27.351934: step: 256/526, loss: 0.013569450005888939
2023-01-23 01:33:28.529842: step: 260/526, loss: 0.006478500552475452
2023-01-23 01:33:29.685335: step: 264/526, loss: 0.04996204376220703
2023-01-23 01:33:30.819731: step: 268/526, loss: 0.035019125789403915
2023-01-23 01:33:31.944640: step: 272/526, loss: 0.01232242677360773
2023-01-23 01:33:33.079253: step: 276/526, loss: 0.038022611290216446
2023-01-23 01:33:34.207739: step: 280/526, loss: 0.0251601692289114
2023-01-23 01:33:35.373411: step: 284/526, loss: 0.03603691980242729
2023-01-23 01:33:36.481272: step: 288/526, loss: 0.027198027819395065
2023-01-23 01:33:37.670911: step: 292/526, loss: 0.030568504706025124
2023-01-23 01:33:38.795567: step: 296/526, loss: 0.004569435492157936
2023-01-23 01:33:39.935866: step: 300/526, loss: 0.19565612077713013
2023-01-23 01:33:41.057107: step: 304/526, loss: 0.07910709083080292
2023-01-23 01:33:42.199264: step: 308/526, loss: 0.001977908657863736
2023-01-23 01:33:43.358965: step: 312/526, loss: 0.013912105932831764
2023-01-23 01:33:44.533977: step: 316/526, loss: 0.004699897952377796
2023-01-23 01:33:45.689752: step: 320/526, loss: 0.75470370054245
2023-01-23 01:33:46.819497: step: 324/526, loss: 0.06167927011847496
2023-01-23 01:33:47.973685: step: 328/526, loss: 0.06235914304852486
2023-01-23 01:33:49.110688: step: 332/526, loss: 0.08310098946094513
2023-01-23 01:33:50.219594: step: 336/526, loss: 0.01947193220257759
2023-01-23 01:33:51.335765: step: 340/526, loss: 0.04777107387781143
2023-01-23 01:33:52.498517: step: 344/526, loss: 0.053322505205869675
2023-01-23 01:33:53.665324: step: 348/526, loss: 0.06441116333007812
2023-01-23 01:33:54.785999: step: 352/526, loss: 0.0547216422855854
2023-01-23 01:33:55.962214: step: 356/526, loss: 0.09208846837282181
2023-01-23 01:33:57.102596: step: 360/526, loss: 0.03144874423742294
2023-01-23 01:33:58.239303: step: 364/526, loss: 0.09040851145982742
2023-01-23 01:33:59.369427: step: 368/526, loss: 0.3013055920600891
2023-01-23 01:34:00.497827: step: 372/526, loss: 0.049841977655887604
2023-01-23 01:34:01.596514: step: 376/526, loss: 0.04145689308643341
2023-01-23 01:34:02.720715: step: 380/526, loss: 0.055289652198553085
2023-01-23 01:34:03.848198: step: 384/526, loss: 0.05458955839276314
2023-01-23 01:34:04.993358: step: 388/526, loss: 0.006760788150131702
2023-01-23 01:34:06.117243: step: 392/526, loss: 0.015175485983490944
2023-01-23 01:34:07.251570: step: 396/526, loss: 0.043103788048028946
2023-01-23 01:34:08.366615: step: 400/526, loss: 0.05019550397992134
2023-01-23 01:34:09.491204: step: 404/526, loss: 0.023662948980927467
2023-01-23 01:34:10.620942: step: 408/526, loss: 0.02124500274658203
2023-01-23 01:34:11.757687: step: 412/526, loss: 0.06670932471752167
2023-01-23 01:34:12.904039: step: 416/526, loss: 0.05777731165289879
2023-01-23 01:34:14.057699: step: 420/526, loss: 0.03680391237139702
2023-01-23 01:34:15.209218: step: 424/526, loss: 0.047613002359867096
2023-01-23 01:34:16.343833: step: 428/526, loss: 0.7896060943603516
2023-01-23 01:34:17.464929: step: 432/526, loss: 0.023007284849882126
2023-01-23 01:34:18.580782: step: 436/526, loss: 0.11981189250946045
2023-01-23 01:34:19.716954: step: 440/526, loss: 0.03748941794037819
2023-01-23 01:34:20.876804: step: 444/526, loss: 0.011210059747099876
2023-01-23 01:34:22.005944: step: 448/526, loss: 0.0694499984383583
2023-01-23 01:34:23.116915: step: 452/526, loss: 0.08625636249780655
2023-01-23 01:34:24.266080: step: 456/526, loss: 0.1802116334438324
2023-01-23 01:34:25.412313: step: 460/526, loss: 0.035994913429021835
2023-01-23 01:34:26.542555: step: 464/526, loss: 0.07664966583251953
2023-01-23 01:34:27.680303: step: 468/526, loss: 0.06726408004760742
2023-01-23 01:34:28.800221: step: 472/526, loss: 0.10308542102575302
2023-01-23 01:34:29.920502: step: 476/526, loss: 0.02859029732644558
2023-01-23 01:34:31.062768: step: 480/526, loss: 0.013994693756103516
2023-01-23 01:34:32.242969: step: 484/526, loss: 0.03370704501867294
2023-01-23 01:34:33.371174: step: 488/526, loss: 0.03453044965863228
2023-01-23 01:34:34.492482: step: 492/526, loss: 0.0007882118225097656
2023-01-23 01:34:35.619981: step: 496/526, loss: 0.3698081970214844
2023-01-23 01:34:36.739972: step: 500/526, loss: 0.8205415606498718
2023-01-23 01:34:37.861211: step: 504/526, loss: 0.09431672096252441
2023-01-23 01:34:38.996948: step: 508/526, loss: 0.039953041821718216
2023-01-23 01:34:40.121671: step: 512/526, loss: 0.03703467920422554
2023-01-23 01:34:41.264982: step: 516/526, loss: 0.1137368232011795
2023-01-23 01:34:42.383114: step: 520/526, loss: 0.005227852147072554
2023-01-23 01:34:43.521129: step: 524/526, loss: 0.025608062744140625
2023-01-23 01:34:44.684238: step: 528/526, loss: 0.10578260570764542
2023-01-23 01:34:45.812633: step: 532/526, loss: 0.020121192559599876
2023-01-23 01:34:46.956753: step: 536/526, loss: 0.0334138385951519
2023-01-23 01:34:48.062074: step: 540/526, loss: 0.021785831078886986
2023-01-23 01:34:49.222705: step: 544/526, loss: 0.05236692726612091
2023-01-23 01:34:50.353247: step: 548/526, loss: 0.1314988136291504
2023-01-23 01:34:51.497267: step: 552/526, loss: 0.02799406088888645
2023-01-23 01:34:52.646139: step: 556/526, loss: 0.1003204807639122
2023-01-23 01:34:53.750356: step: 560/526, loss: 0.012031269259750843
2023-01-23 01:34:54.891852: step: 564/526, loss: 0.021151352673768997
2023-01-23 01:34:56.028251: step: 568/526, loss: 0.0068832398392260075
2023-01-23 01:34:57.151597: step: 572/526, loss: 0.016821861267089844
2023-01-23 01:34:58.301359: step: 576/526, loss: 0.018536090850830078
2023-01-23 01:34:59.453476: step: 580/526, loss: 0.01825409010052681
2023-01-23 01:35:00.617897: step: 584/526, loss: 0.003875351045280695
2023-01-23 01:35:01.784961: step: 588/526, loss: 0.00866842269897461
2023-01-23 01:35:02.948381: step: 592/526, loss: 0.01886777952313423
2023-01-23 01:35:04.070441: step: 596/526, loss: 0.009160804562270641
2023-01-23 01:35:05.227497: step: 600/526, loss: 0.006759452633559704
2023-01-23 01:35:06.388156: step: 604/526, loss: 0.006973934359848499
2023-01-23 01:35:07.560258: step: 608/526, loss: 0.05599198490381241
2023-01-23 01:35:08.689387: step: 612/526, loss: 0.031445980072021484
2023-01-23 01:35:09.804984: step: 616/526, loss: 0.013846492394804955
2023-01-23 01:35:10.904686: step: 620/526, loss: 0.08624868094921112
2023-01-23 01:35:12.030070: step: 624/526, loss: 0.01663370244204998
2023-01-23 01:35:13.179187: step: 628/526, loss: 0.027376916259527206
2023-01-23 01:35:14.320019: step: 632/526, loss: 0.004254770465195179
2023-01-23 01:35:15.486319: step: 636/526, loss: 0.03201127052307129
2023-01-23 01:35:16.601783: step: 640/526, loss: 0.013113665394484997
2023-01-23 01:35:17.720248: step: 644/526, loss: 0.16804885864257812
2023-01-23 01:35:18.909664: step: 648/526, loss: 0.0326998233795166
2023-01-23 01:35:20.050618: step: 652/526, loss: 0.020496368408203125
2023-01-23 01:35:21.180196: step: 656/526, loss: 0.008899211883544922
2023-01-23 01:35:22.322670: step: 660/526, loss: 0.013555800542235374
2023-01-23 01:35:23.509537: step: 664/526, loss: 0.06982650607824326
2023-01-23 01:35:24.638442: step: 668/526, loss: 0.14360694587230682
2023-01-23 01:35:25.788694: step: 672/526, loss: 0.020160485059022903
2023-01-23 01:35:26.934834: step: 676/526, loss: 0.03500986471772194
2023-01-23 01:35:28.052128: step: 680/526, loss: 0.18179956078529358
2023-01-23 01:35:29.235469: step: 684/526, loss: 0.015084696002304554
2023-01-23 01:35:30.401961: step: 688/526, loss: 0.018367290496826172
2023-01-23 01:35:31.546586: step: 692/526, loss: 0.021160507574677467
2023-01-23 01:35:32.701633: step: 696/526, loss: 0.020832061767578125
2023-01-23 01:35:33.861441: step: 700/526, loss: 0.02121915854513645
2023-01-23 01:35:34.984957: step: 704/526, loss: 0.03353748470544815
2023-01-23 01:35:36.105627: step: 708/526, loss: 0.012795353308320045
2023-01-23 01:35:37.212980: step: 712/526, loss: 0.05167360603809357
2023-01-23 01:35:38.320669: step: 716/526, loss: 0.0785159170627594
2023-01-23 01:35:39.494209: step: 720/526, loss: 0.14270934462547302
2023-01-23 01:35:40.625453: step: 724/526, loss: 0.017456531524658203
2023-01-23 01:35:41.741756: step: 728/526, loss: 0.04156322404742241
2023-01-23 01:35:42.907821: step: 732/526, loss: 0.019110679626464844
2023-01-23 01:35:44.030996: step: 736/526, loss: 0.13657379150390625
2023-01-23 01:35:45.160167: step: 740/526, loss: 0.028533553704619408
2023-01-23 01:35:46.290183: step: 744/526, loss: 0.04280510172247887
2023-01-23 01:35:47.417708: step: 748/526, loss: 0.014842415228486061
2023-01-23 01:35:48.550856: step: 752/526, loss: 0.0020779133774340153
2023-01-23 01:35:49.664528: step: 756/526, loss: 0.007045364938676357
2023-01-23 01:35:50.848264: step: 760/526, loss: 0.04721980169415474
2023-01-23 01:35:52.019991: step: 764/526, loss: 0.02477102167904377
2023-01-23 01:35:53.151131: step: 768/526, loss: 0.0012703895336017013
2023-01-23 01:35:54.269958: step: 772/526, loss: 0.031102323904633522
2023-01-23 01:35:55.412744: step: 776/526, loss: 0.04388155788183212
2023-01-23 01:35:56.557973: step: 780/526, loss: 0.009329509921371937
2023-01-23 01:35:57.671758: step: 784/526, loss: 0.022286999970674515
2023-01-23 01:35:58.769568: step: 788/526, loss: 0.022002220153808594
2023-01-23 01:35:59.895366: step: 792/526, loss: 0.021439289674162865
2023-01-23 01:36:01.045899: step: 796/526, loss: 0.09964265674352646
2023-01-23 01:36:02.188368: step: 800/526, loss: 0.00927190762013197
2023-01-23 01:36:03.315368: step: 804/526, loss: 0.026840783655643463
2023-01-23 01:36:04.465333: step: 808/526, loss: 0.05136584863066673
2023-01-23 01:36:05.600377: step: 812/526, loss: 0.02593545988202095
2023-01-23 01:36:06.778461: step: 816/526, loss: 0.024433420971035957
2023-01-23 01:36:07.907280: step: 820/526, loss: 0.02726602554321289
2023-01-23 01:36:09.030897: step: 824/526, loss: 0.006706523708999157
2023-01-23 01:36:10.177394: step: 828/526, loss: 0.00850820541381836
2023-01-23 01:36:11.297764: step: 832/526, loss: 0.01353550050407648
2023-01-23 01:36:12.431788: step: 836/526, loss: 0.0828624740242958
2023-01-23 01:36:13.561209: step: 840/526, loss: 0.0027029276825487614
2023-01-23 01:36:14.708567: step: 844/526, loss: 0.02274780347943306
2023-01-23 01:36:15.868191: step: 848/526, loss: 0.03883986547589302
2023-01-23 01:36:16.983344: step: 852/526, loss: 0.020419906824827194
2023-01-23 01:36:18.110214: step: 856/526, loss: 0.007386303041130304
2023-01-23 01:36:19.247891: step: 860/526, loss: 0.3408277630805969
2023-01-23 01:36:20.344097: step: 864/526, loss: 0.0542634017765522
2023-01-23 01:36:21.465786: step: 868/526, loss: 0.0017309188842773438
2023-01-23 01:36:22.591665: step: 872/526, loss: 0.0013473511207848787
2023-01-23 01:36:23.738638: step: 876/526, loss: 0.054708484560251236
2023-01-23 01:36:24.858112: step: 880/526, loss: 0.04383111000061035
2023-01-23 01:36:26.003889: step: 884/526, loss: 0.03033285029232502
2023-01-23 01:36:27.150135: step: 888/526, loss: 0.0433807373046875
2023-01-23 01:36:28.311584: step: 892/526, loss: 0.034485530108213425
2023-01-23 01:36:29.442176: step: 896/526, loss: 0.043548014014959335
2023-01-23 01:36:30.591883: step: 900/526, loss: 0.06304372847080231
2023-01-23 01:36:31.732713: step: 904/526, loss: 0.04075632244348526
2023-01-23 01:36:32.884842: step: 908/526, loss: 0.16977018117904663
2023-01-23 01:36:34.015983: step: 912/526, loss: 0.011780452914536
2023-01-23 01:36:35.152503: step: 916/526, loss: 0.07580890506505966
2023-01-23 01:36:36.289818: step: 920/526, loss: 0.03230275958776474
2023-01-23 01:36:37.423702: step: 924/526, loss: 0.11890307068824768
2023-01-23 01:36:38.560184: step: 928/526, loss: 0.06739797443151474
2023-01-23 01:36:39.694197: step: 932/526, loss: 0.017836762592196465
2023-01-23 01:36:40.848264: step: 936/526, loss: 0.00805444736033678
2023-01-23 01:36:41.989111: step: 940/526, loss: 0.01569375954568386
2023-01-23 01:36:43.141889: step: 944/526, loss: 0.0011993409134447575
2023-01-23 01:36:44.276314: step: 948/526, loss: 0.019652558490633965
2023-01-23 01:36:45.421604: step: 952/526, loss: 0.06442413479089737
2023-01-23 01:36:46.565130: step: 956/526, loss: 0.18526040017604828
2023-01-23 01:36:47.700329: step: 960/526, loss: 0.009407520294189453
2023-01-23 01:36:48.830615: step: 964/526, loss: 0.025765608996152878
2023-01-23 01:36:49.936280: step: 968/526, loss: 0.06046156957745552
2023-01-23 01:36:51.051002: step: 972/526, loss: 0.04392719268798828
2023-01-23 01:36:52.172384: step: 976/526, loss: 0.015723418444395065
2023-01-23 01:36:53.318474: step: 980/526, loss: 0.06410686671733856
2023-01-23 01:36:54.461855: step: 984/526, loss: 0.07546329498291016
2023-01-23 01:36:55.568407: step: 988/526, loss: 0.0746615082025528
2023-01-23 01:36:56.710065: step: 992/526, loss: 0.04820432886481285
2023-01-23 01:36:57.875604: step: 996/526, loss: 0.00711593683809042
2023-01-23 01:36:59.011159: step: 1000/526, loss: 0.045021869242191315
2023-01-23 01:37:00.162762: step: 1004/526, loss: 0.032410621643066406
2023-01-23 01:37:01.283416: step: 1008/526, loss: 0.03292074054479599
2023-01-23 01:37:02.461121: step: 1012/526, loss: 0.009679603390395641
2023-01-23 01:37:03.606340: step: 1016/526, loss: 0.02282867208123207
2023-01-23 01:37:04.762827: step: 1020/526, loss: 0.06127443164587021
2023-01-23 01:37:05.922456: step: 1024/526, loss: 0.02827281877398491
2023-01-23 01:37:07.043426: step: 1028/526, loss: 0.003234005067497492
2023-01-23 01:37:08.194015: step: 1032/526, loss: 0.031190872192382812
2023-01-23 01:37:09.335018: step: 1036/526, loss: 0.04781933128833771
2023-01-23 01:37:10.461130: step: 1040/526, loss: 0.012742806226015091
2023-01-23 01:37:11.579485: step: 1044/526, loss: 0.0018214226001873612
2023-01-23 01:37:12.750676: step: 1048/526, loss: 0.136883944272995
2023-01-23 01:37:13.888677: step: 1052/526, loss: 0.027689361944794655
2023-01-23 01:37:15.002057: step: 1056/526, loss: 0.4107941687107086
2023-01-23 01:37:16.156061: step: 1060/526, loss: 0.03291730955243111
2023-01-23 01:37:17.315688: step: 1064/526, loss: 0.01733236387372017
2023-01-23 01:37:18.453622: step: 1068/526, loss: 0.006503724958747625
2023-01-23 01:37:19.595892: step: 1072/526, loss: 0.050051119178533554
2023-01-23 01:37:20.735637: step: 1076/526, loss: 0.021442700177431107
2023-01-23 01:37:21.841059: step: 1080/526, loss: 0.032674409449100494
2023-01-23 01:37:22.977444: step: 1084/526, loss: 0.03428492695093155
2023-01-23 01:37:24.106121: step: 1088/526, loss: 0.0006778120878152549
2023-01-23 01:37:25.236868: step: 1092/526, loss: 0.04425087198615074
2023-01-23 01:37:26.348527: step: 1096/526, loss: 0.012255668640136719
2023-01-23 01:37:27.473074: step: 1100/526, loss: 0.05667443573474884
2023-01-23 01:37:28.607488: step: 1104/526, loss: 0.010410880669951439
2023-01-23 01:37:29.733717: step: 1108/526, loss: 0.0020513534545898438
2023-01-23 01:37:30.880650: step: 1112/526, loss: 0.180999755859375
2023-01-23 01:37:32.015399: step: 1116/526, loss: 0.023761559277772903
2023-01-23 01:37:33.139098: step: 1120/526, loss: 0.0240662582218647
2023-01-23 01:37:34.263148: step: 1124/526, loss: 0.01329665258526802
2023-01-23 01:37:35.389504: step: 1128/526, loss: 0.006125736050307751
2023-01-23 01:37:36.518962: step: 1132/526, loss: 0.03783588483929634
2023-01-23 01:37:37.638131: step: 1136/526, loss: 0.04968605190515518
2023-01-23 01:37:38.769866: step: 1140/526, loss: 0.1593664288520813
2023-01-23 01:37:39.904300: step: 1144/526, loss: 0.09417963027954102
2023-01-23 01:37:41.068235: step: 1148/526, loss: 0.026500225067138672
2023-01-23 01:37:42.233644: step: 1152/526, loss: 0.0037673949263989925
2023-01-23 01:37:43.372025: step: 1156/526, loss: 0.0488039031624794
2023-01-23 01:37:44.507029: step: 1160/526, loss: 0.013555717654526234
2023-01-23 01:37:45.661020: step: 1164/526, loss: 0.002695274306461215
2023-01-23 01:37:46.806632: step: 1168/526, loss: 0.016222668811678886
2023-01-23 01:37:47.928463: step: 1172/526, loss: 0.026630688458681107
2023-01-23 01:37:49.090310: step: 1176/526, loss: 0.1773972362279892
2023-01-23 01:37:50.220203: step: 1180/526, loss: 0.021808242425322533
2023-01-23 01:37:51.369654: step: 1184/526, loss: 0.2964572012424469
2023-01-23 01:37:52.524806: step: 1188/526, loss: 0.04487719386816025
2023-01-23 01:37:53.697331: step: 1192/526, loss: 0.00749549875035882
2023-01-23 01:37:54.814739: step: 1196/526, loss: 0.021151162683963776
2023-01-23 01:37:55.968423: step: 1200/526, loss: 0.0334961861371994
2023-01-23 01:37:57.090379: step: 1204/526, loss: 0.03635196387767792
2023-01-23 01:37:58.187046: step: 1208/526, loss: 0.006293904967606068
2023-01-23 01:37:59.331803: step: 1212/526, loss: 0.0027557373978197575
2023-01-23 01:38:00.471891: step: 1216/526, loss: 0.04963350296020508
2023-01-23 01:38:01.594845: step: 1220/526, loss: 0.2429819107055664
2023-01-23 01:38:02.782181: step: 1224/526, loss: 0.2772899866104126
2023-01-23 01:38:03.928060: step: 1228/526, loss: 0.03223705291748047
2023-01-23 01:38:05.090079: step: 1232/526, loss: 0.06376257538795471
2023-01-23 01:38:06.228078: step: 1236/526, loss: 0.04116266965866089
2023-01-23 01:38:07.365936: step: 1240/526, loss: 0.014807652682065964
2023-01-23 01:38:08.506719: step: 1244/526, loss: 0.02443566359579563
2023-01-23 01:38:09.643523: step: 1248/526, loss: 0.005798244383186102
2023-01-23 01:38:10.762480: step: 1252/526, loss: 0.024842072278261185
2023-01-23 01:38:11.883809: step: 1256/526, loss: 0.03334350511431694
2023-01-23 01:38:13.100478: step: 1260/526, loss: 0.0090491296723485
2023-01-23 01:38:14.270665: step: 1264/526, loss: 0.014495945535600185
2023-01-23 01:38:15.382387: step: 1268/526, loss: 0.004066848661750555
2023-01-23 01:38:16.585290: step: 1272/526, loss: 0.08167324215173721
2023-01-23 01:38:17.753011: step: 1276/526, loss: 0.03427610546350479
2023-01-23 01:38:18.882379: step: 1280/526, loss: 0.027289772406220436
2023-01-23 01:38:20.027125: step: 1284/526, loss: 0.003236436750739813
2023-01-23 01:38:21.144568: step: 1288/526, loss: 0.038630008697509766
2023-01-23 01:38:22.297375: step: 1292/526, loss: 0.012416648678481579
2023-01-23 01:38:23.482732: step: 1296/526, loss: 0.07008008658885956
2023-01-23 01:38:24.616322: step: 1300/526, loss: 0.05007324367761612
2023-01-23 01:38:25.757101: step: 1304/526, loss: 0.0747290700674057
2023-01-23 01:38:26.890409: step: 1308/526, loss: 0.03546304628252983
2023-01-23 01:38:28.056010: step: 1312/526, loss: 0.044303130358457565
2023-01-23 01:38:29.209071: step: 1316/526, loss: 0.1232721358537674
2023-01-23 01:38:30.378987: step: 1320/526, loss: 0.027375031262636185
2023-01-23 01:38:31.499989: step: 1324/526, loss: 0.009673118591308594
2023-01-23 01:38:32.629257: step: 1328/526, loss: 0.02348911762237549
2023-01-23 01:38:33.768371: step: 1332/526, loss: 0.07153091579675674
2023-01-23 01:38:34.914984: step: 1336/526, loss: 0.030302954837679863
2023-01-23 01:38:36.064210: step: 1340/526, loss: 0.041434336453676224
2023-01-23 01:38:37.204848: step: 1344/526, loss: 0.020363997668027878
2023-01-23 01:38:38.370009: step: 1348/526, loss: 0.07390232384204865
2023-01-23 01:38:39.533511: step: 1352/526, loss: 0.07209186255931854
2023-01-23 01:38:40.666358: step: 1356/526, loss: 0.004238558001816273
2023-01-23 01:38:41.800752: step: 1360/526, loss: 0.025953199714422226
2023-01-23 01:38:42.927880: step: 1364/526, loss: 0.02716651000082493
2023-01-23 01:38:44.043315: step: 1368/526, loss: 0.05875494331121445
2023-01-23 01:38:45.149707: step: 1372/526, loss: 0.031439781188964844
2023-01-23 01:38:46.284734: step: 1376/526, loss: 0.017386246472597122
2023-01-23 01:38:47.413481: step: 1380/526, loss: 0.008271598257124424
2023-01-23 01:38:48.557635: step: 1384/526, loss: 0.06272315979003906
2023-01-23 01:38:49.696665: step: 1388/526, loss: 0.011740971356630325
2023-01-23 01:38:50.823461: step: 1392/526, loss: 0.034822940826416016
2023-01-23 01:38:51.979292: step: 1396/526, loss: 0.0436285026371479
2023-01-23 01:38:53.119109: step: 1400/526, loss: 0.004963874816894531
2023-01-23 01:38:54.245030: step: 1404/526, loss: 0.053969480097293854
2023-01-23 01:38:55.393871: step: 1408/526, loss: 0.03966865688562393
2023-01-23 01:38:56.509189: step: 1412/526, loss: 0.05612468719482422
2023-01-23 01:38:57.636077: step: 1416/526, loss: 0.011247635819017887
2023-01-23 01:38:58.778801: step: 1420/526, loss: 0.025371933355927467
2023-01-23 01:38:59.898341: step: 1424/526, loss: 0.0461546890437603
2023-01-23 01:39:01.036492: step: 1428/526, loss: 0.003895664354786277
2023-01-23 01:39:02.194146: step: 1432/526, loss: 0.8182815313339233
2023-01-23 01:39:03.307791: step: 1436/526, loss: 0.006576252169907093
2023-01-23 01:39:04.505048: step: 1440/526, loss: 0.023845817893743515
2023-01-23 01:39:05.656344: step: 1444/526, loss: 0.03608150780200958
2023-01-23 01:39:06.793666: step: 1448/526, loss: 0.016951465979218483
2023-01-23 01:39:07.935481: step: 1452/526, loss: 0.0018060803413391113
2023-01-23 01:39:09.082410: step: 1456/526, loss: 0.08336801081895828
2023-01-23 01:39:10.192046: step: 1460/526, loss: 0.02992877922952175
2023-01-23 01:39:11.323629: step: 1464/526, loss: 0.6871873140335083
2023-01-23 01:39:12.478580: step: 1468/526, loss: 0.03498063236474991
2023-01-23 01:39:13.620319: step: 1472/526, loss: 0.06262655556201935
2023-01-23 01:39:14.743227: step: 1476/526, loss: 0.02201104164123535
2023-01-23 01:39:15.846376: step: 1480/526, loss: 0.005126094911247492
2023-01-23 01:39:16.979590: step: 1484/526, loss: 0.02070169523358345
2023-01-23 01:39:18.105152: step: 1488/526, loss: 0.0006317138904705644
2023-01-23 01:39:19.218523: step: 1492/526, loss: 0.00042033198405988514
2023-01-23 01:39:20.360211: step: 1496/526, loss: 0.013733958825469017
2023-01-23 01:39:21.474462: step: 1500/526, loss: 0.01101963222026825
2023-01-23 01:39:22.621824: step: 1504/526, loss: 0.10884075611829758
2023-01-23 01:39:23.752097: step: 1508/526, loss: 0.0911344513297081
2023-01-23 01:39:24.886284: step: 1512/526, loss: 0.14299726486206055
2023-01-23 01:39:26.019242: step: 1516/526, loss: 0.010817051865160465
2023-01-23 01:39:27.155505: step: 1520/526, loss: 0.023146916180849075
2023-01-23 01:39:28.310191: step: 1524/526, loss: 0.02089667320251465
2023-01-23 01:39:29.429641: step: 1528/526, loss: 0.14809398353099823
2023-01-23 01:39:30.539418: step: 1532/526, loss: 0.026880264282226562
2023-01-23 01:39:31.669014: step: 1536/526, loss: 0.05155186727643013
2023-01-23 01:39:32.843474: step: 1540/526, loss: 0.000682830810546875
2023-01-23 01:39:33.969143: step: 1544/526, loss: 0.022702883929014206
2023-01-23 01:39:35.104434: step: 1548/526, loss: 0.047187235206365585
2023-01-23 01:39:36.249611: step: 1552/526, loss: 0.17317704856395721
2023-01-23 01:39:37.391849: step: 1556/526, loss: 0.02258272096514702
2023-01-23 01:39:38.585080: step: 1560/526, loss: 0.026255272328853607
2023-01-23 01:39:39.703765: step: 1564/526, loss: 0.00017632247181609273
2023-01-23 01:39:40.844979: step: 1568/526, loss: 0.23204460740089417
2023-01-23 01:39:42.022478: step: 1572/526, loss: 0.05755005031824112
2023-01-23 01:39:43.171761: step: 1576/526, loss: 0.045473624020814896
2023-01-23 01:39:44.299602: step: 1580/526, loss: 0.002887773560360074
2023-01-23 01:39:45.419980: step: 1584/526, loss: 0.07780475914478302
2023-01-23 01:39:46.545732: step: 1588/526, loss: 0.0057201385498046875
2023-01-23 01:39:47.669324: step: 1592/526, loss: 0.0072193145751953125
2023-01-23 01:39:48.794373: step: 1596/526, loss: 0.02798943594098091
2023-01-23 01:39:49.948551: step: 1600/526, loss: 0.01578812673687935
2023-01-23 01:39:51.110979: step: 1604/526, loss: 0.4075937271118164
2023-01-23 01:39:52.263192: step: 1608/526, loss: 0.04425077512860298
2023-01-23 01:39:53.378120: step: 1612/526, loss: 0.023885346949100494
2023-01-23 01:39:54.519235: step: 1616/526, loss: 0.023654939606785774
2023-01-23 01:39:55.652871: step: 1620/526, loss: 0.08473014831542969
2023-01-23 01:39:56.773250: step: 1624/526, loss: 0.07060708105564117
2023-01-23 01:39:57.930222: step: 1628/526, loss: 0.054797910153865814
2023-01-23 01:39:59.074299: step: 1632/526, loss: 0.2670868933200836
2023-01-23 01:40:00.235445: step: 1636/526, loss: 0.0017000199295580387
2023-01-23 01:40:01.377722: step: 1640/526, loss: 0.038254451006650925
2023-01-23 01:40:02.505682: step: 1644/526, loss: 0.012462044134736061
2023-01-23 01:40:03.644400: step: 1648/526, loss: 0.07951248437166214
2023-01-23 01:40:04.772512: step: 1652/526, loss: 0.5755947828292847
2023-01-23 01:40:05.898528: step: 1656/526, loss: 0.019350241869688034
2023-01-23 01:40:07.019096: step: 1660/526, loss: 0.01771240308880806
2023-01-23 01:40:08.142078: step: 1664/526, loss: 0.10567188262939453
2023-01-23 01:40:09.254697: step: 1668/526, loss: 0.07023916393518448
2023-01-23 01:40:10.384389: step: 1672/526, loss: 0.05703587830066681
2023-01-23 01:40:11.543362: step: 1676/526, loss: 0.027640677988529205
2023-01-23 01:40:12.689327: step: 1680/526, loss: 0.025768471881747246
2023-01-23 01:40:13.822865: step: 1684/526, loss: 0.04692802205681801
2023-01-23 01:40:14.993950: step: 1688/526, loss: 0.05409812927246094
2023-01-23 01:40:16.168860: step: 1692/526, loss: 0.4012279510498047
2023-01-23 01:40:17.300170: step: 1696/526, loss: 0.1030871644616127
2023-01-23 01:40:18.438544: step: 1700/526, loss: 0.04265942797064781
2023-01-23 01:40:19.556760: step: 1704/526, loss: 0.15849293768405914
2023-01-23 01:40:20.693521: step: 1708/526, loss: 0.03170964866876602
2023-01-23 01:40:21.825064: step: 1712/526, loss: 0.02606491930782795
2023-01-23 01:40:22.957514: step: 1716/526, loss: 0.053172290325164795
2023-01-23 01:40:24.090912: step: 1720/526, loss: 0.03164386749267578
2023-01-23 01:40:25.239778: step: 1724/526, loss: 0.04469861835241318
2023-01-23 01:40:26.368531: step: 1728/526, loss: 0.005818176083266735
2023-01-23 01:40:27.504552: step: 1732/526, loss: 0.04537258297204971
2023-01-23 01:40:28.663765: step: 1736/526, loss: 0.04201517254114151
2023-01-23 01:40:29.800143: step: 1740/526, loss: 0.029452133923768997
2023-01-23 01:40:30.925106: step: 1744/526, loss: 0.0060163503512740135
2023-01-23 01:40:32.013064: step: 1748/526, loss: 0.28751277923583984
2023-01-23 01:40:33.170329: step: 1752/526, loss: 0.01087264996021986
2023-01-23 01:40:34.300826: step: 1756/526, loss: 0.048621464520692825
2023-01-23 01:40:35.465030: step: 1760/526, loss: 0.04401111602783203
2023-01-23 01:40:36.588003: step: 1764/526, loss: 0.022840406745672226
2023-01-23 01:40:37.714720: step: 1768/526, loss: 0.01822199858725071
2023-01-23 01:40:38.854871: step: 1772/526, loss: 0.07354164123535156
2023-01-23 01:40:39.976073: step: 1776/526, loss: 0.02441110834479332
2023-01-23 01:40:41.135160: step: 1780/526, loss: 0.019890213385224342
2023-01-23 01:40:42.290851: step: 1784/526, loss: 0.06719360500574112
2023-01-23 01:40:43.429467: step: 1788/526, loss: 0.05928993225097656
2023-01-23 01:40:44.554591: step: 1792/526, loss: 0.4545758366584778
2023-01-23 01:40:45.707178: step: 1796/526, loss: 0.17160768806934357
2023-01-23 01:40:46.852793: step: 1800/526, loss: 0.05804738774895668
2023-01-23 01:40:48.001113: step: 1804/526, loss: 0.04509871453046799
2023-01-23 01:40:49.138303: step: 1808/526, loss: 0.04761238396167755
2023-01-23 01:40:50.249242: step: 1812/526, loss: 0.01605534553527832
2023-01-23 01:40:51.397003: step: 1816/526, loss: 0.01584453694522381
2023-01-23 01:40:52.545593: step: 1820/526, loss: 0.09592743217945099
2023-01-23 01:40:53.661823: step: 1824/526, loss: 0.193315327167511
2023-01-23 01:40:54.797415: step: 1828/526, loss: 0.01300439890474081
2023-01-23 01:40:55.930619: step: 1832/526, loss: 0.00048437720397487283
2023-01-23 01:40:57.079245: step: 1836/526, loss: 0.01170816458761692
2023-01-23 01:40:58.269246: step: 1840/526, loss: 0.028622150421142578
2023-01-23 01:40:59.417618: step: 1844/526, loss: 0.09107961505651474
2023-01-23 01:41:00.546533: step: 1848/526, loss: 0.0006039619911462069
2023-01-23 01:41:01.683787: step: 1852/526, loss: 0.0005326271057128906
2023-01-23 01:41:02.812802: step: 1856/526, loss: 0.0033239363692700863
2023-01-23 01:41:03.981388: step: 1860/526, loss: 0.059676554054021835
2023-01-23 01:41:05.120861: step: 1864/526, loss: 0.0428556427359581
2023-01-23 01:41:06.269458: step: 1868/526, loss: 0.018061447888612747
2023-01-23 01:41:07.394705: step: 1872/526, loss: 0.03526115417480469
2023-01-23 01:41:08.517377: step: 1876/526, loss: 0.06230955570936203
2023-01-23 01:41:09.636304: step: 1880/526, loss: 0.07876358181238174
2023-01-23 01:41:10.760391: step: 1884/526, loss: 0.019382977858185768
2023-01-23 01:41:11.919502: step: 1888/526, loss: 0.0564669631421566
2023-01-23 01:41:13.067032: step: 1892/526, loss: 0.038663100451231
2023-01-23 01:41:14.243390: step: 1896/526, loss: 0.0011962890857830644
2023-01-23 01:41:15.374330: step: 1900/526, loss: 0.005804920569062233
2023-01-23 01:41:16.521303: step: 1904/526, loss: 0.0636088103055954
2023-01-23 01:41:17.651487: step: 1908/526, loss: 0.0152749540284276
2023-01-23 01:41:18.778008: step: 1912/526, loss: 0.007731437683105469
2023-01-23 01:41:19.900905: step: 1916/526, loss: 0.026102924719452858
2023-01-23 01:41:21.043950: step: 1920/526, loss: 0.42654716968536377
2023-01-23 01:41:22.187462: step: 1924/526, loss: 0.041433051228523254
2023-01-23 01:41:23.322532: step: 1928/526, loss: 0.038018226623535156
2023-01-23 01:41:24.446382: step: 1932/526, loss: 0.031040668487548828
2023-01-23 01:41:25.590455: step: 1936/526, loss: 0.011744118295609951
2023-01-23 01:41:26.707332: step: 1940/526, loss: 0.026145363226532936
2023-01-23 01:41:27.841063: step: 1944/526, loss: 0.04430332034826279
2023-01-23 01:41:29.018204: step: 1948/526, loss: 0.03115851990878582
2023-01-23 01:41:30.161679: step: 1952/526, loss: 0.00018043517775367945
2023-01-23 01:41:31.293366: step: 1956/526, loss: 0.018588924780488014
2023-01-23 01:41:32.439115: step: 1960/526, loss: 0.11597137153148651
2023-01-23 01:41:33.564788: step: 1964/526, loss: 0.04968447610735893
2023-01-23 01:41:34.681514: step: 1968/526, loss: 0.01731748692691326
2023-01-23 01:41:35.825617: step: 1972/526, loss: 0.02411813661456108
2023-01-23 01:41:36.955940: step: 1976/526, loss: 0.027556326240301132
2023-01-23 01:41:38.100435: step: 1980/526, loss: 0.04701070860028267
2023-01-23 01:41:39.231441: step: 1984/526, loss: 0.08717431873083115
2023-01-23 01:41:40.388802: step: 1988/526, loss: 0.039710044860839844
2023-01-23 01:41:41.529640: step: 1992/526, loss: 0.08350543677806854
2023-01-23 01:41:42.639703: step: 1996/526, loss: 0.04892873764038086
2023-01-23 01:41:43.793746: step: 2000/526, loss: 0.45091360807418823
2023-01-23 01:41:44.914409: step: 2004/526, loss: 0.029063750058412552
2023-01-23 01:41:46.039826: step: 2008/526, loss: 0.024001501500606537
2023-01-23 01:41:47.194912: step: 2012/526, loss: 0.013182925991714
2023-01-23 01:41:48.321745: step: 2016/526, loss: 0.08830604702234268
2023-01-23 01:41:49.458731: step: 2020/526, loss: 0.052048493176698685
2023-01-23 01:41:50.639298: step: 2024/526, loss: 0.03321409225463867
2023-01-23 01:41:51.787556: step: 2028/526, loss: 0.11997724324464798
2023-01-23 01:41:52.933299: step: 2032/526, loss: 0.15167662501335144
2023-01-23 01:41:54.087678: step: 2036/526, loss: 0.12710018455982208
2023-01-23 01:41:55.227266: step: 2040/526, loss: 0.5929369926452637
2023-01-23 01:41:56.405106: step: 2044/526, loss: 0.04465284198522568
2023-01-23 01:41:57.562472: step: 2048/526, loss: 0.06522063910961151
2023-01-23 01:41:58.694201: step: 2052/526, loss: 0.06809630990028381
2023-01-23 01:41:59.847025: step: 2056/526, loss: 0.0362459197640419
2023-01-23 01:42:00.995972: step: 2060/526, loss: 0.02742924727499485
2023-01-23 01:42:02.142903: step: 2064/526, loss: 0.03204236179590225
2023-01-23 01:42:03.261481: step: 2068/526, loss: 0.11362352222204208
2023-01-23 01:42:04.394540: step: 2072/526, loss: 0.08075514435768127
2023-01-23 01:42:05.521094: step: 2076/526, loss: 0.12044267356395721
2023-01-23 01:42:06.670360: step: 2080/526, loss: 0.03281516954302788
2023-01-23 01:42:07.800452: step: 2084/526, loss: 0.06396923214197159
2023-01-23 01:42:08.930857: step: 2088/526, loss: 0.03920001909136772
2023-01-23 01:42:10.096630: step: 2092/526, loss: 0.14201021194458008
2023-01-23 01:42:11.238871: step: 2096/526, loss: 0.031968019902706146
2023-01-23 01:42:12.379314: step: 2100/526, loss: 0.23675537109375
2023-01-23 01:42:13.527925: step: 2104/526, loss: 0.13140617311000824
==================================================
Loss: 0.062
--------------------
Dev: {'event': {'p': 0.5905349794238683, 'r': 0.7643142476697736, 'f1': 0.6662797446314569}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Test: {'event': {'p': 0.6230870135548754, 'r': 0.7437369519832986, 'f1': 0.6780870806566739}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Chinese: {'event': {'p': 0.5853658536585366, 'r': 0.8888888888888888, 'f1': 0.7058823529411764}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Korean: {'event': {'p': 0.6136363636363636, 'r': 0.42857142857142855, 'f1': 0.5046728971962617}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Russian: {'event': {'p': 0.4418604651162791, 'r': 0.5277777777777778, 'f1': 0.4810126582278481}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6263498920086393, 'r': 0.7723035952063915, 'f1': 0.6917113893858079}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 11}
Eng Test for Chinese: {'event': {'p': 0.6342208642514185, 'r': 0.7583507306889353, 'f1': 0.6907535060613264}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 11}
Sample Chinese: {'event': {'p': 0.5714285714285714, 'r': 0.8888888888888888, 'f1': 0.6956521739130435}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 11}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6257995735607675, 'r': 0.7816245006657789, 'f1': 0.6950858496151568}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Eng Test for Korean: {'event': {'p': 0.623113410952997, 'r': 0.7541753653444676, 'f1': 0.6824085005903188}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Sample Korean: {'event': {'p': 0.7446808510638298, 'r': 0.5555555555555556, 'f1': 0.6363636363636364}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6217672413793104, 'r': 0.7683089214380826, 'f1': 0.6873138773079214}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Eng Test for Russian: {'event': {'p': 0.6300302899177845, 'r': 0.7599164926931107, 'f1': 0.6889046605157322}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Sample Russian: {'event': {'p': 0.5, 'r': 0.5833333333333334, 'f1': 0.5384615384615384}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
******************************
Epoch: 13
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 01:42:56.482216: step: 4/526, loss: 0.003343868302181363
2023-01-23 01:42:57.614967: step: 8/526, loss: 0.04936399683356285
2023-01-23 01:42:58.746823: step: 12/526, loss: 0.007564449217170477
2023-01-23 01:42:59.908184: step: 16/526, loss: 0.01380014419555664
2023-01-23 01:43:01.025943: step: 20/526, loss: 0.052228882908821106
2023-01-23 01:43:02.181523: step: 24/526, loss: 0.049744606018066406
2023-01-23 01:43:03.343591: step: 28/526, loss: 0.06352625042200089
2023-01-23 01:43:04.455799: step: 32/526, loss: 0.031080342829227448
2023-01-23 01:43:05.542169: step: 36/526, loss: 0.0637393444776535
2023-01-23 01:43:06.674567: step: 40/526, loss: 0.03955040127038956
2023-01-23 01:43:07.811702: step: 44/526, loss: 0.018660355359315872
2023-01-23 01:43:08.954104: step: 48/526, loss: 0.03791084140539169
2023-01-23 01:43:10.094011: step: 52/526, loss: 0.4659709930419922
2023-01-23 01:43:11.257487: step: 56/526, loss: 0.02841362915933132
2023-01-23 01:43:12.411932: step: 60/526, loss: 0.02750368043780327
2023-01-23 01:43:13.536539: step: 64/526, loss: 0.004151105880737305
2023-01-23 01:43:14.669951: step: 68/526, loss: 0.019626140594482422
2023-01-23 01:43:15.798291: step: 72/526, loss: 0.026484966278076172
2023-01-23 01:43:16.940624: step: 76/526, loss: 0.09473247826099396
2023-01-23 01:43:18.042211: step: 80/526, loss: 0.11876068264245987
2023-01-23 01:43:19.167219: step: 84/526, loss: 0.05898723751306534
2023-01-23 01:43:20.274883: step: 88/526, loss: 0.02245493046939373
2023-01-23 01:43:21.408599: step: 92/526, loss: 0.0012227654224261642
2023-01-23 01:43:22.528621: step: 96/526, loss: 0.030055999755859375
2023-01-23 01:43:23.658035: step: 100/526, loss: 0.53765869140625
2023-01-23 01:43:24.800468: step: 104/526, loss: 0.1193990707397461
2023-01-23 01:43:25.940818: step: 108/526, loss: 0.6213350296020508
2023-01-23 01:43:27.083495: step: 112/526, loss: 0.03964824602007866
2023-01-23 01:43:28.202659: step: 116/526, loss: 0.04657583311200142
2023-01-23 01:43:29.328121: step: 120/526, loss: 0.017995595932006836
2023-01-23 01:43:30.466898: step: 124/526, loss: 0.1778421401977539
2023-01-23 01:43:31.589511: step: 128/526, loss: 0.12723799049854279
2023-01-23 01:43:32.726491: step: 132/526, loss: 0.004783248994499445
2023-01-23 01:43:33.845495: step: 136/526, loss: 0.07159395515918732
2023-01-23 01:43:35.034345: step: 140/526, loss: 0.04679832607507706
2023-01-23 01:43:36.178690: step: 144/526, loss: 0.043010879307985306
2023-01-23 01:43:37.278561: step: 148/526, loss: 0.04448862001299858
2023-01-23 01:43:38.410396: step: 152/526, loss: 0.11926116794347763
2023-01-23 01:43:39.580916: step: 156/526, loss: 0.4576537609100342
2023-01-23 01:43:40.752510: step: 160/526, loss: 0.0801454484462738
2023-01-23 01:43:41.919418: step: 164/526, loss: 0.08440323173999786
2023-01-23 01:43:43.093350: step: 168/526, loss: 0.04520683363080025
2023-01-23 01:43:44.228276: step: 172/526, loss: 0.010570526123046875
2023-01-23 01:43:45.344087: step: 176/526, loss: 0.005318975541740656
2023-01-23 01:43:46.462593: step: 180/526, loss: 0.012668800540268421
2023-01-23 01:43:47.587433: step: 184/526, loss: 0.040294550359249115
2023-01-23 01:43:48.709362: step: 188/526, loss: 0.08683434128761292
2023-01-23 01:43:49.845723: step: 192/526, loss: 0.012177658267319202
2023-01-23 01:43:50.962284: step: 196/526, loss: 0.00578994769603014
2023-01-23 01:43:52.074838: step: 200/526, loss: 0.013469576835632324
2023-01-23 01:43:53.217628: step: 204/526, loss: 0.00961923599243164
2023-01-23 01:43:54.347420: step: 208/526, loss: 0.0031724930740892887
2023-01-23 01:43:55.469876: step: 212/526, loss: 0.008566808886826038
2023-01-23 01:43:56.618613: step: 216/526, loss: 0.05053577199578285
2023-01-23 01:43:57.721653: step: 220/526, loss: 0.019422434270381927
2023-01-23 01:43:58.861978: step: 224/526, loss: 0.11163187026977539
2023-01-23 01:43:59.983908: step: 228/526, loss: 0.6892479658126831
2023-01-23 01:44:01.092874: step: 232/526, loss: 0.004634285345673561
2023-01-23 01:44:02.219803: step: 236/526, loss: 0.028853796422481537
2023-01-23 01:44:03.335453: step: 240/526, loss: 0.030071640387177467
2023-01-23 01:44:04.473882: step: 244/526, loss: 0.10433006286621094
2023-01-23 01:44:05.604928: step: 248/526, loss: 0.06990686058998108
2023-01-23 01:44:06.763920: step: 252/526, loss: 0.10982856154441833
2023-01-23 01:44:07.915679: step: 256/526, loss: 0.0402885302901268
2023-01-23 01:44:09.034921: step: 260/526, loss: 0.03999929502606392
2023-01-23 01:44:10.172688: step: 264/526, loss: 0.013419246301054955
2023-01-23 01:44:11.304302: step: 268/526, loss: 0.11001081764698029
2023-01-23 01:44:12.461611: step: 272/526, loss: 0.015373516827821732
2023-01-23 01:44:13.612912: step: 276/526, loss: 0.03369751200079918
2023-01-23 01:44:14.719089: step: 280/526, loss: 0.00595436105504632
2023-01-23 01:44:15.846316: step: 284/526, loss: 0.05754728242754936
2023-01-23 01:44:16.985979: step: 288/526, loss: 0.05466146767139435
2023-01-23 01:44:18.142546: step: 292/526, loss: 0.00962753314524889
2023-01-23 01:44:19.273260: step: 296/526, loss: 0.028749655932188034
2023-01-23 01:44:20.385110: step: 300/526, loss: 0.017904235050082207
2023-01-23 01:44:21.514690: step: 304/526, loss: 0.01133575476706028
2023-01-23 01:44:22.651849: step: 308/526, loss: 0.0036680935882031918
2023-01-23 01:44:23.835551: step: 312/526, loss: 0.0059254649095237255
2023-01-23 01:44:24.990780: step: 316/526, loss: 0.0036606788635253906
2023-01-23 01:44:26.119159: step: 320/526, loss: 0.009058046154677868
2023-01-23 01:44:27.233781: step: 324/526, loss: 0.00353584298864007
2023-01-23 01:44:28.363510: step: 328/526, loss: 0.0011196136474609375
2023-01-23 01:44:29.481468: step: 332/526, loss: 0.00653076171875
2023-01-23 01:44:30.595577: step: 336/526, loss: 0.015506076626479626
2023-01-23 01:44:31.745651: step: 340/526, loss: 0.0452730655670166
2023-01-23 01:44:32.854122: step: 344/526, loss: 0.027920866385102272
2023-01-23 01:44:33.991629: step: 348/526, loss: 0.0018477441044524312
2023-01-23 01:44:35.136377: step: 352/526, loss: 0.005360317416489124
2023-01-23 01:44:36.277608: step: 356/526, loss: 0.018458843231201172
2023-01-23 01:44:37.414307: step: 360/526, loss: 0.099718376994133
2023-01-23 01:44:38.549657: step: 364/526, loss: 0.025664901360869408
2023-01-23 01:44:39.689674: step: 368/526, loss: 0.04473366588354111
2023-01-23 01:44:40.853154: step: 372/526, loss: 0.056041717529296875
2023-01-23 01:44:42.013749: step: 376/526, loss: 0.007688617799431086
2023-01-23 01:44:43.179406: step: 380/526, loss: 0.020863723009824753
2023-01-23 01:44:44.306358: step: 384/526, loss: 0.0014172076480463147
2023-01-23 01:44:45.441601: step: 388/526, loss: 0.015442085452377796
2023-01-23 01:44:46.612544: step: 392/526, loss: 0.018088817596435547
2023-01-23 01:44:47.725831: step: 396/526, loss: 0.02909700945019722
2023-01-23 01:44:48.862906: step: 400/526, loss: 0.011687946505844593
2023-01-23 01:44:50.023155: step: 404/526, loss: 0.00018882752920035273
2023-01-23 01:44:51.177851: step: 408/526, loss: 0.00488700857385993
2023-01-23 01:44:52.336486: step: 412/526, loss: 0.057968903332948685
2023-01-23 01:44:53.457057: step: 416/526, loss: 0.005549335852265358
2023-01-23 01:44:54.636326: step: 420/526, loss: 0.012666416354477406
2023-01-23 01:44:55.750084: step: 424/526, loss: 0.0160387996584177
2023-01-23 01:44:56.882638: step: 428/526, loss: 0.04160728678107262
2023-01-23 01:44:58.023128: step: 432/526, loss: 0.08094330132007599
2023-01-23 01:44:59.190569: step: 436/526, loss: 0.027771759778261185
2023-01-23 01:45:00.334195: step: 440/526, loss: 0.07526607811450958
2023-01-23 01:45:01.509680: step: 444/526, loss: 0.05303172767162323
2023-01-23 01:45:02.638464: step: 448/526, loss: 0.13842131197452545
2023-01-23 01:45:03.780339: step: 452/526, loss: 0.0013718606205657125
2023-01-23 01:45:04.903318: step: 456/526, loss: 0.0044023036025464535
2023-01-23 01:45:06.023094: step: 460/526, loss: 0.01291036605834961
2023-01-23 01:45:07.188056: step: 464/526, loss: 0.03337745741009712
2023-01-23 01:45:08.301586: step: 468/526, loss: 0.023488139733672142
2023-01-23 01:45:09.443055: step: 472/526, loss: 0.0369526743888855
2023-01-23 01:45:10.579918: step: 476/526, loss: 0.08896227180957794
2023-01-23 01:45:11.696825: step: 480/526, loss: 0.022980643436312675
2023-01-23 01:45:12.804868: step: 484/526, loss: 0.0011325955856591463
2023-01-23 01:45:13.946157: step: 488/526, loss: 0.24746552109718323
2023-01-23 01:45:15.095896: step: 492/526, loss: 0.03898783028125763
2023-01-23 01:45:16.207232: step: 496/526, loss: 0.04852492734789848
2023-01-23 01:45:17.351104: step: 500/526, loss: 0.027479028329253197
2023-01-23 01:45:18.482929: step: 504/526, loss: 0.02696561999619007
2023-01-23 01:45:19.607400: step: 508/526, loss: 0.05223055183887482
2023-01-23 01:45:20.759090: step: 512/526, loss: 0.08334140479564667
2023-01-23 01:45:21.908839: step: 516/526, loss: 0.05268239974975586
2023-01-23 01:45:23.032501: step: 520/526, loss: 0.11760444194078445
2023-01-23 01:45:24.173329: step: 524/526, loss: 0.13242359459400177
2023-01-23 01:45:25.304596: step: 528/526, loss: 0.008893584832549095
2023-01-23 01:45:26.428298: step: 532/526, loss: 0.027087021619081497
2023-01-23 01:45:27.570651: step: 536/526, loss: 0.02698230743408203
2023-01-23 01:45:28.692796: step: 540/526, loss: 0.04895520210266113
2023-01-23 01:45:29.850758: step: 544/526, loss: 0.09065943211317062
2023-01-23 01:45:31.019853: step: 548/526, loss: 0.03667950630187988
2023-01-23 01:45:32.186016: step: 552/526, loss: 0.4843130111694336
2023-01-23 01:45:33.302640: step: 556/526, loss: 0.010173416696488857
2023-01-23 01:45:34.460961: step: 560/526, loss: 0.009769439697265625
2023-01-23 01:45:35.593462: step: 564/526, loss: 0.009202862158417702
2023-01-23 01:45:36.701042: step: 568/526, loss: 0.06249351426959038
2023-01-23 01:45:37.825687: step: 572/526, loss: 0.049231961369514465
2023-01-23 01:45:38.960776: step: 576/526, loss: 0.08227720856666565
2023-01-23 01:45:40.087524: step: 580/526, loss: 0.022121144458651543
2023-01-23 01:45:41.232900: step: 584/526, loss: 0.07328915596008301
2023-01-23 01:45:42.343877: step: 588/526, loss: 0.02001342736184597
2023-01-23 01:45:43.483422: step: 592/526, loss: 0.040125273168087006
2023-01-23 01:45:44.595573: step: 596/526, loss: 0.0020106793381273746
2023-01-23 01:45:45.698249: step: 600/526, loss: 0.01310644205659628
2023-01-23 01:45:46.825974: step: 604/526, loss: 0.0038715361151844263
2023-01-23 01:45:47.987290: step: 608/526, loss: 0.04984588548541069
2023-01-23 01:45:49.148822: step: 612/526, loss: 0.033686257898807526
2023-01-23 01:45:50.311621: step: 616/526, loss: 0.7480446696281433
2023-01-23 01:45:51.430400: step: 620/526, loss: 0.04864707216620445
2023-01-23 01:45:52.565144: step: 624/526, loss: 0.009557723999023438
2023-01-23 01:45:53.711481: step: 628/526, loss: 0.0551937110722065
2023-01-23 01:45:54.827303: step: 632/526, loss: 0.03425464779138565
2023-01-23 01:45:55.971530: step: 636/526, loss: 0.025500871241092682
2023-01-23 01:45:57.107319: step: 640/526, loss: 0.03884430229663849
2023-01-23 01:45:58.261431: step: 644/526, loss: 0.8188632130622864
2023-01-23 01:45:59.372268: step: 648/526, loss: 0.06335659325122833
2023-01-23 01:46:00.470757: step: 652/526, loss: 0.03251013904809952
2023-01-23 01:46:01.612817: step: 656/526, loss: 0.01196746900677681
2023-01-23 01:46:02.762524: step: 660/526, loss: 0.05213518068194389
2023-01-23 01:46:03.885705: step: 664/526, loss: 0.009797478094696999
2023-01-23 01:46:05.041330: step: 668/526, loss: 0.04624948650598526
2023-01-23 01:46:06.166177: step: 672/526, loss: 0.0673513412475586
2023-01-23 01:46:07.284917: step: 676/526, loss: 0.012476349249482155
2023-01-23 01:46:08.404724: step: 680/526, loss: 0.025736570358276367
2023-01-23 01:46:09.564346: step: 684/526, loss: 0.013802719302475452
2023-01-23 01:46:10.737190: step: 688/526, loss: 0.01801929622888565
2023-01-23 01:46:11.863934: step: 692/526, loss: 0.04194164276123047
2023-01-23 01:46:13.095955: step: 696/526, loss: 0.06269092857837677
2023-01-23 01:46:14.279397: step: 700/526, loss: 0.042037203907966614
2023-01-23 01:46:15.435478: step: 704/526, loss: 0.019763469696044922
2023-01-23 01:46:16.594534: step: 708/526, loss: 0.049951933324337006
2023-01-23 01:46:17.722843: step: 712/526, loss: 0.2472720742225647
2023-01-23 01:46:18.865526: step: 716/526, loss: 0.04955577850341797
2023-01-23 01:46:19.994032: step: 720/526, loss: 0.019998932257294655
2023-01-23 01:46:21.124453: step: 724/526, loss: 0.3687778413295746
2023-01-23 01:46:22.276539: step: 728/526, loss: 0.01746220700442791
2023-01-23 01:46:23.416603: step: 732/526, loss: 0.08555164933204651
2023-01-23 01:46:24.556056: step: 736/526, loss: 0.028433572500944138
2023-01-23 01:46:25.682049: step: 740/526, loss: 0.012831354513764381
2023-01-23 01:46:26.837228: step: 744/526, loss: 0.022426225244998932
2023-01-23 01:46:27.986161: step: 748/526, loss: 0.003670215606689453
2023-01-23 01:46:29.123960: step: 752/526, loss: 0.001497554825618863
2023-01-23 01:46:30.269886: step: 756/526, loss: 0.01020956039428711
2023-01-23 01:46:31.409585: step: 760/526, loss: 0.10498128831386566
2023-01-23 01:46:32.537173: step: 764/526, loss: 0.04622707515954971
2023-01-23 01:46:33.695427: step: 768/526, loss: 0.02273707464337349
2023-01-23 01:46:34.843499: step: 772/526, loss: 0.1283605992794037
2023-01-23 01:46:35.990793: step: 776/526, loss: 0.02354917675256729
2023-01-23 01:46:37.147079: step: 780/526, loss: 0.08163337409496307
2023-01-23 01:46:38.273762: step: 784/526, loss: 0.01126704178750515
2023-01-23 01:46:39.426691: step: 788/526, loss: 0.01570143736898899
2023-01-23 01:46:40.554464: step: 792/526, loss: 0.010365486145019531
2023-01-23 01:46:41.688331: step: 796/526, loss: 0.28114375472068787
2023-01-23 01:46:42.858991: step: 800/526, loss: 0.13259848952293396
2023-01-23 01:46:43.981853: step: 804/526, loss: 0.015461349859833717
2023-01-23 01:46:45.195420: step: 808/526, loss: 0.010441113263368607
2023-01-23 01:46:46.318373: step: 812/526, loss: 0.04111804813146591
2023-01-23 01:46:47.463064: step: 816/526, loss: 0.09982052445411682
2023-01-23 01:46:48.579673: step: 820/526, loss: 0.03638429567217827
2023-01-23 01:46:49.707860: step: 824/526, loss: 0.021789170801639557
2023-01-23 01:46:50.848658: step: 828/526, loss: 0.0339839942753315
2023-01-23 01:46:51.988237: step: 832/526, loss: 0.03462924808263779
2023-01-23 01:46:53.103907: step: 836/526, loss: 0.0086548812687397
2023-01-23 01:46:54.228979: step: 840/526, loss: 0.0022373199462890625
2023-01-23 01:46:55.365600: step: 844/526, loss: 0.0487859770655632
2023-01-23 01:46:56.494754: step: 848/526, loss: 0.0534062385559082
2023-01-23 01:46:57.628505: step: 852/526, loss: 0.0008760690689086914
2023-01-23 01:46:58.756854: step: 856/526, loss: 0.017857860773801804
2023-01-23 01:46:59.886202: step: 860/526, loss: 0.01971343904733658
2023-01-23 01:47:01.029187: step: 864/526, loss: 0.026155853644013405
2023-01-23 01:47:02.161678: step: 868/526, loss: 0.056824494153261185
2023-01-23 01:47:03.299467: step: 872/526, loss: 0.04470262676477432
2023-01-23 01:47:04.426675: step: 876/526, loss: 0.05740748345851898
2023-01-23 01:47:05.555317: step: 880/526, loss: 0.10411418229341507
2023-01-23 01:47:06.705634: step: 884/526, loss: 0.08634739369153976
2023-01-23 01:47:07.848804: step: 888/526, loss: 1.0524760484695435
2023-01-23 01:47:08.998071: step: 892/526, loss: 0.09735670685768127
2023-01-23 01:47:10.132363: step: 896/526, loss: 0.026569750159978867
2023-01-23 01:47:11.259158: step: 900/526, loss: 0.0115820886567235
2023-01-23 01:47:12.418430: step: 904/526, loss: 0.013141918927431107
2023-01-23 01:47:13.579454: step: 908/526, loss: 0.14877520501613617
2023-01-23 01:47:14.705259: step: 912/526, loss: 0.0027168274391442537
2023-01-23 01:47:15.841647: step: 916/526, loss: 0.02921476401388645
2023-01-23 01:47:17.006311: step: 920/526, loss: 0.01851959154009819
2023-01-23 01:47:18.154691: step: 924/526, loss: 0.027705764397978783
2023-01-23 01:47:19.280451: step: 928/526, loss: 0.08063450455665588
2023-01-23 01:47:20.430129: step: 932/526, loss: 0.0413387306034565
2023-01-23 01:47:21.577304: step: 936/526, loss: 0.11855144798755646
2023-01-23 01:47:22.719085: step: 940/526, loss: 0.019108010455965996
2023-01-23 01:47:23.854796: step: 944/526, loss: 0.06180715560913086
2023-01-23 01:47:24.979547: step: 948/526, loss: 0.01549997366964817
2023-01-23 01:47:26.085310: step: 952/526, loss: 0.01909341849386692
2023-01-23 01:47:27.194228: step: 956/526, loss: 0.08234482258558273
2023-01-23 01:47:28.336157: step: 960/526, loss: 0.12263260036706924
2023-01-23 01:47:29.443090: step: 964/526, loss: 0.027236558496952057
2023-01-23 01:47:30.589178: step: 968/526, loss: 0.034651611000299454
2023-01-23 01:47:31.762394: step: 972/526, loss: 0.039281558245420456
2023-01-23 01:47:32.936543: step: 976/526, loss: 0.018955709412693977
2023-01-23 01:47:34.074247: step: 980/526, loss: 0.03333435207605362
2023-01-23 01:47:35.222487: step: 984/526, loss: 0.03172741085290909
2023-01-23 01:47:36.388500: step: 988/526, loss: 0.03255309909582138
2023-01-23 01:47:37.514819: step: 992/526, loss: 0.00015573501877952367
2023-01-23 01:47:38.642825: step: 996/526, loss: 0.021399879828095436
2023-01-23 01:47:39.793724: step: 1000/526, loss: 0.02144594117999077
2023-01-23 01:47:40.942285: step: 1004/526, loss: 0.056670188903808594
2023-01-23 01:47:42.087957: step: 1008/526, loss: 0.022966861724853516
2023-01-23 01:47:43.229279: step: 1012/526, loss: 0.12093563377857208
2023-01-23 01:47:44.358370: step: 1016/526, loss: 0.0705813392996788
2023-01-23 01:47:45.500765: step: 1020/526, loss: 0.0035948753356933594
2023-01-23 01:47:46.617400: step: 1024/526, loss: 0.09655246883630753
2023-01-23 01:47:47.747001: step: 1028/526, loss: 0.04067058861255646
2023-01-23 01:47:48.900271: step: 1032/526, loss: 0.0689840316772461
2023-01-23 01:47:49.985294: step: 1036/526, loss: 0.03283090516924858
2023-01-23 01:47:51.131093: step: 1040/526, loss: 0.004947471432387829
2023-01-23 01:47:52.259058: step: 1044/526, loss: 0.0627809539437294
2023-01-23 01:47:53.404001: step: 1048/526, loss: 0.03735370934009552
2023-01-23 01:47:54.553515: step: 1052/526, loss: 0.034029770642519
2023-01-23 01:47:55.721380: step: 1056/526, loss: 0.013742304407060146
2023-01-23 01:47:56.896018: step: 1060/526, loss: 0.08030929416418076
2023-01-23 01:47:58.065430: step: 1064/526, loss: 0.007369565777480602
2023-01-23 01:47:59.199873: step: 1068/526, loss: 0.04058799520134926
2023-01-23 01:48:00.306799: step: 1072/526, loss: 0.04046201705932617
2023-01-23 01:48:01.468166: step: 1076/526, loss: 0.016430091112852097
2023-01-23 01:48:02.600618: step: 1080/526, loss: 0.13665838539600372
2023-01-23 01:48:03.750539: step: 1084/526, loss: 0.007668304722756147
2023-01-23 01:48:04.917595: step: 1088/526, loss: 0.03161673620343208
2023-01-23 01:48:06.047322: step: 1092/526, loss: 0.028898097574710846
2023-01-23 01:48:07.189790: step: 1096/526, loss: 0.05564174801111221
2023-01-23 01:48:08.333135: step: 1100/526, loss: 0.008345984853804111
2023-01-23 01:48:09.446880: step: 1104/526, loss: 0.030109405517578125
2023-01-23 01:48:10.565519: step: 1108/526, loss: 0.005655097775161266
2023-01-23 01:48:11.742969: step: 1112/526, loss: 0.12387847900390625
2023-01-23 01:48:12.910807: step: 1116/526, loss: 0.042987726628780365
2023-01-23 01:48:14.054886: step: 1120/526, loss: 0.02583017572760582
2023-01-23 01:48:15.207813: step: 1124/526, loss: 0.0813068374991417
2023-01-23 01:48:16.365453: step: 1128/526, loss: 0.034679412841796875
2023-01-23 01:48:17.531830: step: 1132/526, loss: 0.003002262208610773
2023-01-23 01:48:18.660282: step: 1136/526, loss: 0.01450738962739706
2023-01-23 01:48:19.765160: step: 1140/526, loss: 0.01184234581887722
2023-01-23 01:48:20.896455: step: 1144/526, loss: 0.1052946075797081
2023-01-23 01:48:22.088817: step: 1148/526, loss: 0.025901008397340775
2023-01-23 01:48:23.254637: step: 1152/526, loss: 0.03181643784046173
2023-01-23 01:48:24.374913: step: 1156/526, loss: 0.005623912904411554
2023-01-23 01:48:25.541489: step: 1160/526, loss: 0.04248478263616562
2023-01-23 01:48:26.680603: step: 1164/526, loss: 0.003130245255306363
2023-01-23 01:48:27.805488: step: 1168/526, loss: 0.030846262350678444
2023-01-23 01:48:28.945862: step: 1172/526, loss: 0.0061657908372581005
2023-01-23 01:48:30.109954: step: 1176/526, loss: 0.038248300552368164
2023-01-23 01:48:31.254265: step: 1180/526, loss: 0.04946904256939888
2023-01-23 01:48:32.376398: step: 1184/526, loss: 0.0031760213896632195
2023-01-23 01:48:33.511310: step: 1188/526, loss: 0.016347885131835938
2023-01-23 01:48:34.641522: step: 1192/526, loss: 0.0021251202560961246
2023-01-23 01:48:35.767097: step: 1196/526, loss: 0.015226269140839577
2023-01-23 01:48:36.913035: step: 1200/526, loss: 0.03696164861321449
2023-01-23 01:48:38.072159: step: 1204/526, loss: 0.0946749672293663
2023-01-23 01:48:39.213246: step: 1208/526, loss: 0.09247412532567978
2023-01-23 01:48:40.363454: step: 1212/526, loss: 0.02320464886724949
2023-01-23 01:48:41.522312: step: 1216/526, loss: 0.003293800400570035
2023-01-23 01:48:42.660934: step: 1220/526, loss: 0.00538978585973382
2023-01-23 01:48:43.823276: step: 1224/526, loss: 0.02916708029806614
2023-01-23 01:48:44.960888: step: 1228/526, loss: 0.029478073120117188
2023-01-23 01:48:46.095347: step: 1232/526, loss: 0.00650176964700222
2023-01-23 01:48:47.202233: step: 1236/526, loss: 0.0022499561309814453
2023-01-23 01:48:48.344159: step: 1240/526, loss: 0.007954406552016735
2023-01-23 01:48:49.488339: step: 1244/526, loss: 0.0009212493896484375
2023-01-23 01:48:50.631834: step: 1248/526, loss: 0.09075680375099182
2023-01-23 01:48:51.755740: step: 1252/526, loss: 0.008729934692382812
2023-01-23 01:48:52.884635: step: 1256/526, loss: 0.0055634500458836555
2023-01-23 01:48:54.026871: step: 1260/526, loss: 0.03166494518518448
2023-01-23 01:48:55.175495: step: 1264/526, loss: 0.0009611129644326866
2023-01-23 01:48:56.286399: step: 1268/526, loss: 0.011462783440947533
2023-01-23 01:48:57.405039: step: 1272/526, loss: 0.050531625747680664
2023-01-23 01:48:58.530265: step: 1276/526, loss: 0.057877495884895325
2023-01-23 01:48:59.671250: step: 1280/526, loss: 0.02187213860452175
2023-01-23 01:49:00.827073: step: 1284/526, loss: 0.02775602415204048
2023-01-23 01:49:01.989700: step: 1288/526, loss: 0.033225297927856445
2023-01-23 01:49:03.115755: step: 1292/526, loss: 0.009862899780273438
2023-01-23 01:49:04.267522: step: 1296/526, loss: 0.039669036865234375
2023-01-23 01:49:05.432202: step: 1300/526, loss: 0.0007548332796432078
2023-01-23 01:49:06.576349: step: 1304/526, loss: 0.05173492431640625
2023-01-23 01:49:07.680182: step: 1308/526, loss: 0.08933629840612411
2023-01-23 01:49:08.784961: step: 1312/526, loss: 0.05989236757159233
2023-01-23 01:49:09.896974: step: 1316/526, loss: 0.02345418930053711
2023-01-23 01:49:11.029354: step: 1320/526, loss: 0.03348731994628906
2023-01-23 01:49:12.156814: step: 1324/526, loss: 0.01136484183371067
2023-01-23 01:49:13.279189: step: 1328/526, loss: 0.0005401134840212762
2023-01-23 01:49:14.431904: step: 1332/526, loss: 0.09696026146411896
2023-01-23 01:49:15.577460: step: 1336/526, loss: 0.08942870795726776
2023-01-23 01:49:16.718971: step: 1340/526, loss: 0.017301559448242188
2023-01-23 01:49:17.866715: step: 1344/526, loss: 0.04023704677820206
2023-01-23 01:49:18.992114: step: 1348/526, loss: 0.006279659457504749
2023-01-23 01:49:20.126327: step: 1352/526, loss: 0.012971878051757812
2023-01-23 01:49:21.274320: step: 1356/526, loss: 0.012519550509750843
2023-01-23 01:49:22.406302: step: 1360/526, loss: 0.022723007947206497
2023-01-23 01:49:23.544958: step: 1364/526, loss: 0.03470955044031143
2023-01-23 01:49:24.659664: step: 1368/526, loss: 0.07795833796262741
2023-01-23 01:49:25.801345: step: 1372/526, loss: 0.016532326117157936
2023-01-23 01:49:26.921930: step: 1376/526, loss: 0.007169055752456188
2023-01-23 01:49:28.058641: step: 1380/526, loss: 0.04544110223650932
2023-01-23 01:49:29.229394: step: 1384/526, loss: 0.01293106097728014
2023-01-23 01:49:30.367142: step: 1388/526, loss: 0.011092161759734154
2023-01-23 01:49:31.494744: step: 1392/526, loss: 0.0023432732559740543
2023-01-23 01:49:32.598158: step: 1396/526, loss: 0.004767036531120539
2023-01-23 01:49:33.744415: step: 1400/526, loss: 0.01958489418029785
2023-01-23 01:49:34.869963: step: 1404/526, loss: 0.07528066635131836
2023-01-23 01:49:36.003859: step: 1408/526, loss: 0.2621818482875824
2023-01-23 01:49:37.131404: step: 1412/526, loss: 0.03466815873980522
2023-01-23 01:49:38.299892: step: 1416/526, loss: 0.04376044496893883
2023-01-23 01:49:39.437140: step: 1420/526, loss: 0.048659421503543854
2023-01-23 01:49:40.579073: step: 1424/526, loss: 0.0004706382751464844
2023-01-23 01:49:41.682441: step: 1428/526, loss: 0.010799694806337357
2023-01-23 01:49:42.858638: step: 1432/526, loss: 0.23829756677150726
2023-01-23 01:49:43.968730: step: 1436/526, loss: 0.09141998738050461
2023-01-23 01:49:45.077072: step: 1440/526, loss: 0.027706623077392578
2023-01-23 01:49:46.246923: step: 1444/526, loss: 0.06473293155431747
2023-01-23 01:49:47.378432: step: 1448/526, loss: 0.12289729714393616
2023-01-23 01:49:48.498665: step: 1452/526, loss: 0.021455192938447
2023-01-23 01:49:49.621291: step: 1456/526, loss: 0.04598226770758629
2023-01-23 01:49:50.778209: step: 1460/526, loss: 0.022632120177149773
2023-01-23 01:49:51.894198: step: 1464/526, loss: 0.07233905792236328
2023-01-23 01:49:53.019524: step: 1468/526, loss: 0.04462037235498428
2023-01-23 01:49:54.125160: step: 1472/526, loss: 0.04205169901251793
2023-01-23 01:49:55.255468: step: 1476/526, loss: 0.06706027686595917
2023-01-23 01:49:56.376207: step: 1480/526, loss: 0.03812894970178604
2023-01-23 01:49:57.495474: step: 1484/526, loss: 0.36283913254737854
2023-01-23 01:49:58.611166: step: 1488/526, loss: 0.0345952995121479
2023-01-23 01:49:59.735020: step: 1492/526, loss: 0.00749053992331028
2023-01-23 01:50:00.884100: step: 1496/526, loss: 0.026373863220214844
2023-01-23 01:50:02.031313: step: 1500/526, loss: 0.13010425865650177
2023-01-23 01:50:03.157985: step: 1504/526, loss: 0.008827782236039639
2023-01-23 01:50:04.297984: step: 1508/526, loss: 0.13581402599811554
2023-01-23 01:50:05.401015: step: 1512/526, loss: 0.0032296180725097656
2023-01-23 01:50:06.532621: step: 1516/526, loss: 0.018725205212831497
2023-01-23 01:50:07.691677: step: 1520/526, loss: 0.032004546374082565
2023-01-23 01:50:08.851088: step: 1524/526, loss: 0.04018688201904297
2023-01-23 01:50:09.980654: step: 1528/526, loss: 0.03525538370013237
2023-01-23 01:50:11.124283: step: 1532/526, loss: 0.011114586144685745
2023-01-23 01:50:12.272517: step: 1536/526, loss: 0.026351165026426315
2023-01-23 01:50:13.431118: step: 1540/526, loss: 0.04839515686035156
2023-01-23 01:50:14.537519: step: 1544/526, loss: 0.053110361099243164
2023-01-23 01:50:15.710181: step: 1548/526, loss: 0.010938739404082298
2023-01-23 01:50:16.850278: step: 1552/526, loss: 0.04854869842529297
2023-01-23 01:50:18.002537: step: 1556/526, loss: 0.7395030856132507
2023-01-23 01:50:19.119462: step: 1560/526, loss: 0.17734451591968536
2023-01-23 01:50:20.270896: step: 1564/526, loss: 0.015507126227021217
2023-01-23 01:50:21.418097: step: 1568/526, loss: 0.012645245529711246
2023-01-23 01:50:22.543520: step: 1572/526, loss: 0.0001027107282425277
2023-01-23 01:50:23.657289: step: 1576/526, loss: 0.018884658813476562
2023-01-23 01:50:24.799210: step: 1580/526, loss: 0.10373573005199432
2023-01-23 01:50:25.941261: step: 1584/526, loss: 0.009451961144804955
2023-01-23 01:50:27.077607: step: 1588/526, loss: 0.009971809573471546
2023-01-23 01:50:28.203146: step: 1592/526, loss: 0.012992668896913528
2023-01-23 01:50:29.343184: step: 1596/526, loss: 0.03197155147790909
2023-01-23 01:50:30.505220: step: 1600/526, loss: 0.012263203039765358
2023-01-23 01:50:31.670891: step: 1604/526, loss: 0.02445230446755886
2023-01-23 01:50:32.847211: step: 1608/526, loss: 0.016923904418945312
2023-01-23 01:50:33.981125: step: 1612/526, loss: 0.07473859935998917
2023-01-23 01:50:35.093834: step: 1616/526, loss: 0.02385730855166912
2023-01-23 01:50:36.217061: step: 1620/526, loss: 0.034781455993652344
2023-01-23 01:50:37.377058: step: 1624/526, loss: 0.07011270523071289
2023-01-23 01:50:38.530577: step: 1628/526, loss: 0.042014218866825104
2023-01-23 01:50:39.669333: step: 1632/526, loss: 0.04486117139458656
2023-01-23 01:50:40.818678: step: 1636/526, loss: 0.008313750848174095
2023-01-23 01:50:41.956568: step: 1640/526, loss: 0.02460041083395481
2023-01-23 01:50:43.085206: step: 1644/526, loss: 0.003979104105383158
2023-01-23 01:50:44.207696: step: 1648/526, loss: 0.01498270034790039
2023-01-23 01:50:45.342384: step: 1652/526, loss: 0.04777412489056587
2023-01-23 01:50:46.467399: step: 1656/526, loss: 0.11847671866416931
2023-01-23 01:50:47.597235: step: 1660/526, loss: 0.22739095985889435
2023-01-23 01:50:48.756419: step: 1664/526, loss: 0.00045385363046079874
2023-01-23 01:50:49.891429: step: 1668/526, loss: 0.318939208984375
2023-01-23 01:50:50.999164: step: 1672/526, loss: 0.0011371612781658769
2023-01-23 01:50:52.140661: step: 1676/526, loss: 0.01677551306784153
2023-01-23 01:50:53.254316: step: 1680/526, loss: 0.005530738737434149
2023-01-23 01:50:54.388966: step: 1684/526, loss: 0.04484749212861061
2023-01-23 01:50:55.521609: step: 1688/526, loss: 0.034762192517519
2023-01-23 01:50:56.670826: step: 1692/526, loss: 0.03612661361694336
2023-01-23 01:50:57.830283: step: 1696/526, loss: 0.24682140350341797
2023-01-23 01:50:58.988474: step: 1700/526, loss: 0.0073286062106490135
2023-01-23 01:51:00.095043: step: 1704/526, loss: 0.024684906005859375
2023-01-23 01:51:01.227314: step: 1708/526, loss: 0.011906147934496403
2023-01-23 01:51:02.344969: step: 1712/526, loss: 0.04727668687701225
2023-01-23 01:51:03.476559: step: 1716/526, loss: 0.021604634821414948
2023-01-23 01:51:04.594167: step: 1720/526, loss: 0.010314512066543102
2023-01-23 01:51:05.716279: step: 1724/526, loss: 0.04415760189294815
2023-01-23 01:51:06.854731: step: 1728/526, loss: 0.0003491402021609247
2023-01-23 01:51:08.004916: step: 1732/526, loss: 0.070029117166996
2023-01-23 01:51:09.126819: step: 1736/526, loss: 0.039321184158325195
2023-01-23 01:51:10.239579: step: 1740/526, loss: 0.04083128273487091
2023-01-23 01:51:11.383459: step: 1744/526, loss: 0.030246615409851074
2023-01-23 01:51:12.541321: step: 1748/526, loss: 0.0046062469482421875
2023-01-23 01:51:13.668038: step: 1752/526, loss: 0.004038667771965265
2023-01-23 01:51:14.806448: step: 1756/526, loss: 0.0022607804276049137
2023-01-23 01:51:15.924091: step: 1760/526, loss: 0.03269386291503906
2023-01-23 01:51:17.045698: step: 1764/526, loss: 0.08118186146020889
2023-01-23 01:51:18.160028: step: 1768/526, loss: 0.03135528787970543
2023-01-23 01:51:19.277192: step: 1772/526, loss: 0.04818706586956978
2023-01-23 01:51:20.386621: step: 1776/526, loss: 0.009947061538696289
2023-01-23 01:51:21.527842: step: 1780/526, loss: 0.045124150812625885
2023-01-23 01:51:22.662876: step: 1784/526, loss: 0.014792424626648426
2023-01-23 01:51:23.776915: step: 1788/526, loss: 0.01794910430908203
2023-01-23 01:51:24.939182: step: 1792/526, loss: 0.05271501839160919
2023-01-23 01:51:26.093827: step: 1796/526, loss: 0.015408897772431374
2023-01-23 01:51:27.220937: step: 1800/526, loss: 0.0028742789290845394
2023-01-23 01:51:28.369652: step: 1804/526, loss: 0.002128505613654852
2023-01-23 01:51:29.484633: step: 1808/526, loss: 0.132737934589386
2023-01-23 01:51:30.633583: step: 1812/526, loss: 0.10737285763025284
2023-01-23 01:51:31.747564: step: 1816/526, loss: 0.06412134319543839
2023-01-23 01:51:32.850441: step: 1820/526, loss: 0.11031875014305115
2023-01-23 01:51:33.993060: step: 1824/526, loss: 0.09334290772676468
2023-01-23 01:51:35.129244: step: 1828/526, loss: 0.024251842871308327
2023-01-23 01:51:36.239303: step: 1832/526, loss: 0.03070240095257759
2023-01-23 01:51:37.376858: step: 1836/526, loss: 0.06307859718799591
2023-01-23 01:51:38.496197: step: 1840/526, loss: 0.0629362091422081
2023-01-23 01:51:39.623977: step: 1844/526, loss: 0.004518937785178423
2023-01-23 01:51:40.793753: step: 1848/526, loss: 0.07525482028722763
2023-01-23 01:51:41.915689: step: 1852/526, loss: 0.035201456397771835
2023-01-23 01:51:43.103882: step: 1856/526, loss: 0.07313995063304901
2023-01-23 01:51:44.278788: step: 1860/526, loss: 0.06632176041603088
2023-01-23 01:51:45.420315: step: 1864/526, loss: 0.034888364374637604
2023-01-23 01:51:46.539988: step: 1868/526, loss: 0.04519472271203995
2023-01-23 01:51:47.649094: step: 1872/526, loss: 3.2901764370762976e-06
2023-01-23 01:51:48.809794: step: 1876/526, loss: 0.05560455098748207
2023-01-23 01:51:49.916246: step: 1880/526, loss: 0.0690622329711914
2023-01-23 01:51:51.028142: step: 1884/526, loss: 0.002453422639518976
2023-01-23 01:51:52.173204: step: 1888/526, loss: 0.0332578644156456
2023-01-23 01:51:53.318094: step: 1892/526, loss: 0.01622753217816353
2023-01-23 01:51:54.477776: step: 1896/526, loss: 0.08401737362146378
2023-01-23 01:51:55.589980: step: 1900/526, loss: 0.013556289486587048
2023-01-23 01:51:56.715826: step: 1904/526, loss: 0.016473103314638138
2023-01-23 01:51:57.850410: step: 1908/526, loss: 0.02500324323773384
2023-01-23 01:51:58.998691: step: 1912/526, loss: 0.03747615963220596
2023-01-23 01:52:00.165129: step: 1916/526, loss: 0.01623210869729519
2023-01-23 01:52:01.296644: step: 1920/526, loss: 0.020865153521299362
2023-01-23 01:52:02.444668: step: 1924/526, loss: 0.09426537156105042
2023-01-23 01:52:03.595237: step: 1928/526, loss: 0.03553667291998863
2023-01-23 01:52:04.745490: step: 1932/526, loss: 0.0386173278093338
2023-01-23 01:52:05.866669: step: 1936/526, loss: 0.04942674562335014
2023-01-23 01:52:07.015830: step: 1940/526, loss: 0.034838005900382996
2023-01-23 01:52:08.229775: step: 1944/526, loss: 0.11963681876659393
2023-01-23 01:52:09.343568: step: 1948/526, loss: 0.009502792730927467
2023-01-23 01:52:10.465342: step: 1952/526, loss: 0.05932999029755592
2023-01-23 01:52:11.644257: step: 1956/526, loss: 0.013558006845414639
2023-01-23 01:52:12.786216: step: 1960/526, loss: 0.3790111541748047
2023-01-23 01:52:13.941705: step: 1964/526, loss: 0.00024013521033339202
2023-01-23 01:52:15.113474: step: 1968/526, loss: 0.002020931337028742
2023-01-23 01:52:16.248317: step: 1972/526, loss: 0.008262872695922852
2023-01-23 01:52:17.393879: step: 1976/526, loss: 0.045568086206912994
2023-01-23 01:52:18.536156: step: 1980/526, loss: 0.03980877622961998
2023-01-23 01:52:19.650181: step: 1984/526, loss: 0.010819340124726295
2023-01-23 01:52:20.753183: step: 1988/526, loss: 0.08175916224718094
2023-01-23 01:52:21.891981: step: 1992/526, loss: 0.04726286232471466
2023-01-23 01:52:23.027698: step: 1996/526, loss: 0.013749408535659313
2023-01-23 01:52:24.181881: step: 2000/526, loss: 0.09512300789356232
2023-01-23 01:52:25.305731: step: 2004/526, loss: 0.003344666911289096
2023-01-23 01:52:26.434262: step: 2008/526, loss: 0.002407073974609375
2023-01-23 01:52:27.592747: step: 2012/526, loss: 0.0848415419459343
2023-01-23 01:52:28.735069: step: 2016/526, loss: 0.01933269575238228
2023-01-23 01:52:29.884236: step: 2020/526, loss: 0.003736400743946433
2023-01-23 01:52:31.020816: step: 2024/526, loss: 0.03413262590765953
2023-01-23 01:52:32.150461: step: 2028/526, loss: 0.024927139282226562
2023-01-23 01:52:33.267692: step: 2032/526, loss: 0.006679153069853783
2023-01-23 01:52:34.406487: step: 2036/526, loss: 0.024360084906220436
2023-01-23 01:52:35.569970: step: 2040/526, loss: 0.059807490557432175
2023-01-23 01:52:36.711264: step: 2044/526, loss: 0.11016955226659775
2023-01-23 01:52:37.828618: step: 2048/526, loss: 0.06936921924352646
2023-01-23 01:52:38.995489: step: 2052/526, loss: 0.004474448971450329
2023-01-23 01:52:40.109991: step: 2056/526, loss: 0.01922025717794895
2023-01-23 01:52:41.267227: step: 2060/526, loss: 0.04763145372271538
2023-01-23 01:52:42.380572: step: 2064/526, loss: 0.03901495784521103
2023-01-23 01:52:43.515503: step: 2068/526, loss: 0.05246410891413689
2023-01-23 01:52:44.664499: step: 2072/526, loss: 0.017983341589570045
2023-01-23 01:52:45.833004: step: 2076/526, loss: 0.024172592908143997
2023-01-23 01:52:46.936550: step: 2080/526, loss: 0.015199471265077591
2023-01-23 01:52:48.062584: step: 2084/526, loss: 0.01585559919476509
2023-01-23 01:52:49.228965: step: 2088/526, loss: 0.03293590620160103
2023-01-23 01:52:50.354581: step: 2092/526, loss: 0.03557705879211426
2023-01-23 01:52:51.468646: step: 2096/526, loss: 0.022069169208407402
2023-01-23 01:52:52.632542: step: 2100/526, loss: 0.0372493751347065
2023-01-23 01:52:53.763175: step: 2104/526, loss: 0.036190200597047806
==================================================
Loss: 0.055
--------------------
Dev: {'event': {'p': 0.6389811738648948, 'r': 0.7683089214380826, 'f1': 0.6977025392986699}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Test: {'event': {'p': 0.6328626444159179, 'r': 0.7719206680584552, 'f1': 0.6955090524335763}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Chinese: {'event': {'p': 0.6282051282051282, 'r': 0.9074074074074074, 'f1': 0.7424242424242423}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Korean: {'event': {'p': 0.7045454545454546, 'r': 0.49206349206349204, 'f1': 0.5794392523364486}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Russian: {'event': {'p': 0.4634146341463415, 'r': 0.5277777777777778, 'f1': 0.4935064935064935}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
New best chinese model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6389811738648948, 'r': 0.7683089214380826, 'f1': 0.6977025392986699}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Eng Test for Chinese: {'event': {'p': 0.6328626444159179, 'r': 0.7719206680584552, 'f1': 0.6955090524335763}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Sample Chinese: {'event': {'p': 0.6282051282051282, 'r': 0.9074074074074074, 'f1': 0.7424242424242423}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6257995735607675, 'r': 0.7816245006657789, 'f1': 0.6950858496151568}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Eng Test for Korean: {'event': {'p': 0.623113410952997, 'r': 0.7541753653444676, 'f1': 0.6824085005903188}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Sample Korean: {'event': {'p': 0.7446808510638298, 'r': 0.5555555555555556, 'f1': 0.6363636363636364}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6217672413793104, 'r': 0.7683089214380826, 'f1': 0.6873138773079214}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Eng Test for Russian: {'event': {'p': 0.6300302899177845, 'r': 0.7599164926931107, 'f1': 0.6889046605157322}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Sample Russian: {'event': {'p': 0.5, 'r': 0.5833333333333334, 'f1': 0.5384615384615384}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
******************************
Epoch: 14
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 01:53:42.279210: step: 4/526, loss: 0.028769290074706078
2023-01-23 01:53:43.439337: step: 8/526, loss: 0.010029559955000877
2023-01-23 01:53:44.577257: step: 12/526, loss: 0.052431218326091766
2023-01-23 01:53:45.708077: step: 16/526, loss: 0.0002471923944540322
2023-01-23 01:53:46.829323: step: 20/526, loss: 0.020116042345762253
2023-01-23 01:53:48.008040: step: 24/526, loss: 0.04445667192339897
2023-01-23 01:53:49.165262: step: 28/526, loss: 0.0448613166809082
2023-01-23 01:53:50.289198: step: 32/526, loss: 0.0025829316582530737
2023-01-23 01:53:51.426508: step: 36/526, loss: 0.011233711615204811
2023-01-23 01:53:52.580703: step: 40/526, loss: 0.0006347656017169356
2023-01-23 01:53:53.707118: step: 44/526, loss: 0.004898023791611195
2023-01-23 01:53:54.817488: step: 48/526, loss: 0.0010742663871496916
2023-01-23 01:53:55.958073: step: 52/526, loss: 0.056396484375
2023-01-23 01:53:57.088141: step: 56/526, loss: 0.006851291749626398
2023-01-23 01:53:58.262730: step: 60/526, loss: 0.005477714352309704
2023-01-23 01:53:59.375937: step: 64/526, loss: 0.00089178082998842
2023-01-23 01:54:00.488804: step: 68/526, loss: 0.026175975799560547
2023-01-23 01:54:01.626234: step: 72/526, loss: 0.026777077466249466
2023-01-23 01:54:02.742470: step: 76/526, loss: 0.01096954382956028
2023-01-23 01:54:03.879044: step: 80/526, loss: 0.04775390774011612
2023-01-23 01:54:05.011347: step: 84/526, loss: 0.018092917278409004
2023-01-23 01:54:06.179781: step: 88/526, loss: 0.05182266607880592
2023-01-23 01:54:07.316298: step: 92/526, loss: 0.009153938852250576
2023-01-23 01:54:08.446893: step: 96/526, loss: 0.012828255072236061
2023-01-23 01:54:09.587247: step: 100/526, loss: 0.023183632642030716
2023-01-23 01:54:10.736541: step: 104/526, loss: 0.02047748677432537
2023-01-23 01:54:11.873041: step: 108/526, loss: 0.006088924594223499
2023-01-23 01:54:13.005602: step: 112/526, loss: 0.010431480593979359
2023-01-23 01:54:14.131296: step: 116/526, loss: 0.003316784044727683
2023-01-23 01:54:15.268553: step: 120/526, loss: 0.022585012018680573
2023-01-23 01:54:16.422348: step: 124/526, loss: 0.0050903321243822575
2023-01-23 01:54:17.539708: step: 128/526, loss: 0.039612531661987305
2023-01-23 01:54:18.684540: step: 132/526, loss: 0.013351202011108398
2023-01-23 01:54:19.807500: step: 136/526, loss: 0.026549531146883965
2023-01-23 01:54:20.981171: step: 140/526, loss: 0.04821624606847763
2023-01-23 01:54:22.115368: step: 144/526, loss: 0.006395912263542414
2023-01-23 01:54:23.285577: step: 148/526, loss: 0.010717582888901234
2023-01-23 01:54:24.432806: step: 152/526, loss: 0.04908733442425728
2023-01-23 01:54:25.540166: step: 156/526, loss: 0.0012494564289227128
2023-01-23 01:54:26.691857: step: 160/526, loss: 0.025116920471191406
2023-01-23 01:54:27.819055: step: 164/526, loss: 0.05233040079474449
2023-01-23 01:54:28.958053: step: 168/526, loss: 0.004216575529426336
2023-01-23 01:54:30.101504: step: 172/526, loss: 0.04400043562054634
2023-01-23 01:54:31.231725: step: 176/526, loss: 0.018488312140107155
2023-01-23 01:54:32.387969: step: 180/526, loss: 0.06219344213604927
2023-01-23 01:54:33.530952: step: 184/526, loss: 0.0006612777942791581
2023-01-23 01:54:34.665187: step: 188/526, loss: 1.0482269525527954
2023-01-23 01:54:35.790820: step: 192/526, loss: 0.012943553738296032
2023-01-23 01:54:36.924875: step: 196/526, loss: 0.007782650180160999
2023-01-23 01:54:38.061826: step: 200/526, loss: 0.00029478073702193797
2023-01-23 01:54:39.193643: step: 204/526, loss: 0.23826980590820312
2023-01-23 01:54:40.326339: step: 208/526, loss: 0.03896646574139595
2023-01-23 01:54:41.462505: step: 212/526, loss: 0.025578143075108528
2023-01-23 01:54:42.588776: step: 216/526, loss: 0.05037498474121094
2023-01-23 01:54:43.733364: step: 220/526, loss: 0.037569332867860794
2023-01-23 01:54:44.887473: step: 224/526, loss: 0.10282401740550995
2023-01-23 01:54:46.016945: step: 228/526, loss: 0.08367414772510529
2023-01-23 01:54:47.138531: step: 232/526, loss: 0.07944760471582413
2023-01-23 01:54:48.286079: step: 236/526, loss: 0.03297453001141548
2023-01-23 01:54:49.408016: step: 240/526, loss: 0.057761382311582565
2023-01-23 01:54:50.557177: step: 244/526, loss: 0.03840923309326172
2023-01-23 01:54:51.719718: step: 248/526, loss: 0.01747150346636772
2023-01-23 01:54:52.840209: step: 252/526, loss: 0.03914625570178032
2023-01-23 01:54:53.997139: step: 256/526, loss: 0.029239464551210403
2023-01-23 01:54:55.123295: step: 260/526, loss: 0.006405830383300781
2023-01-23 01:54:56.247648: step: 264/526, loss: 0.019260313361883163
2023-01-23 01:54:57.411877: step: 268/526, loss: 0.030454635620117188
2023-01-23 01:54:58.533631: step: 272/526, loss: 0.006913661956787109
2023-01-23 01:54:59.676228: step: 276/526, loss: 0.3178260624408722
2023-01-23 01:55:00.823381: step: 280/526, loss: 0.022599412128329277
2023-01-23 01:55:01.987316: step: 284/526, loss: 0.005079174414277077
2023-01-23 01:55:03.148440: step: 288/526, loss: 6.18457852397114e-05
2023-01-23 01:55:04.287720: step: 292/526, loss: 0.009868239983916283
2023-01-23 01:55:05.429731: step: 296/526, loss: 0.014399338513612747
2023-01-23 01:55:06.582385: step: 300/526, loss: 0.009044838137924671
2023-01-23 01:55:07.712788: step: 304/526, loss: 0.11165733635425568
2023-01-23 01:55:08.845491: step: 308/526, loss: 0.021715546026825905
2023-01-23 01:55:09.996848: step: 312/526, loss: 0.018271446228027344
2023-01-23 01:55:11.152076: step: 316/526, loss: 0.048165224492549896
2023-01-23 01:55:12.328306: step: 320/526, loss: 0.002834796905517578
2023-01-23 01:55:13.454552: step: 324/526, loss: 0.08821564167737961
2023-01-23 01:55:14.599996: step: 328/526, loss: 0.003925800323486328
2023-01-23 01:55:15.721978: step: 332/526, loss: 0.010478115640580654
2023-01-23 01:55:16.851260: step: 336/526, loss: 0.0032283782493323088
2023-01-23 01:55:17.991476: step: 340/526, loss: 0.1905813217163086
2023-01-23 01:55:19.166261: step: 344/526, loss: 0.06588344275951385
2023-01-23 01:55:20.307369: step: 348/526, loss: 0.005924320314079523
2023-01-23 01:55:21.445970: step: 352/526, loss: 0.06634500622749329
2023-01-23 01:55:22.586233: step: 356/526, loss: 0.006025886163115501
2023-01-23 01:55:23.716705: step: 360/526, loss: 0.008804893121123314
2023-01-23 01:55:24.871710: step: 364/526, loss: 0.03967122733592987
2023-01-23 01:55:25.986377: step: 368/526, loss: 0.001993370009586215
2023-01-23 01:55:27.130769: step: 372/526, loss: 0.07171478122472763
2023-01-23 01:55:28.259301: step: 376/526, loss: 0.013125038705766201
2023-01-23 01:55:29.423060: step: 380/526, loss: 0.09669800102710724
2023-01-23 01:55:30.568349: step: 384/526, loss: 0.010965729132294655
2023-01-23 01:55:31.703446: step: 388/526, loss: 0.03508472442626953
2023-01-23 01:55:32.855902: step: 392/526, loss: 0.010452366434037685
2023-01-23 01:55:34.002781: step: 396/526, loss: 0.007734966464340687
2023-01-23 01:55:35.154076: step: 400/526, loss: 0.0469091460108757
2023-01-23 01:55:36.266298: step: 404/526, loss: 0.008955668658018112
2023-01-23 01:55:37.419943: step: 408/526, loss: 0.0075807576067745686
2023-01-23 01:55:38.551910: step: 412/526, loss: 0.0035459520295262337
2023-01-23 01:55:39.698222: step: 416/526, loss: 0.056842658668756485
2023-01-23 01:55:40.848556: step: 420/526, loss: 0.07088947296142578
2023-01-23 01:55:41.978376: step: 424/526, loss: 0.006724882405251265
2023-01-23 01:55:43.115366: step: 428/526, loss: 0.0016445160144940019
2023-01-23 01:55:44.259693: step: 432/526, loss: 0.016928577795624733
2023-01-23 01:55:45.389013: step: 436/526, loss: 0.035657405853271484
2023-01-23 01:55:46.532818: step: 440/526, loss: 0.0058716777712106705
2023-01-23 01:55:47.673029: step: 444/526, loss: 0.0009237289777956903
2023-01-23 01:55:48.819888: step: 448/526, loss: 0.010971833020448685
2023-01-23 01:55:49.970245: step: 452/526, loss: 0.007061720360070467
2023-01-23 01:55:51.113007: step: 456/526, loss: 0.06919269263744354
2023-01-23 01:55:52.243836: step: 460/526, loss: 0.012153435498476028
2023-01-23 01:55:53.381206: step: 464/526, loss: 0.02987213246524334
2023-01-23 01:55:54.500407: step: 468/526, loss: 0.2166258692741394
2023-01-23 01:55:55.648882: step: 472/526, loss: 0.05221042409539223
2023-01-23 01:55:56.782119: step: 476/526, loss: 4.706382969743572e-05
2023-01-23 01:55:57.957780: step: 480/526, loss: 0.1522476226091385
2023-01-23 01:55:59.138131: step: 484/526, loss: 0.027977945283055305
2023-01-23 01:56:00.253017: step: 488/526, loss: 0.011879539117217064
2023-01-23 01:56:01.356119: step: 492/526, loss: 0.004175520036369562
2023-01-23 01:56:02.484519: step: 496/526, loss: 0.03925075754523277
2023-01-23 01:56:03.625187: step: 500/526, loss: 0.0074522970244288445
2023-01-23 01:56:04.762411: step: 504/526, loss: 0.018669797107577324
2023-01-23 01:56:05.897364: step: 508/526, loss: 0.0609624870121479
2023-01-23 01:56:07.055915: step: 512/526, loss: 0.00041131972102448344
2023-01-23 01:56:08.193546: step: 516/526, loss: 0.004340362269431353
2023-01-23 01:56:09.323599: step: 520/526, loss: 0.024741938337683678
2023-01-23 01:56:10.451665: step: 524/526, loss: 0.013489819131791592
2023-01-23 01:56:11.566671: step: 528/526, loss: 0.017365837469697
2023-01-23 01:56:12.758332: step: 532/526, loss: 0.06297626346349716
2023-01-23 01:56:13.888939: step: 536/526, loss: 0.011751556769013405
2023-01-23 01:56:14.987518: step: 540/526, loss: 0.024974536150693893
2023-01-23 01:56:16.121296: step: 544/526, loss: 0.03037581592798233
2023-01-23 01:56:17.234072: step: 548/526, loss: 0.1036502867937088
2023-01-23 01:56:18.385252: step: 552/526, loss: 0.001616668771021068
2023-01-23 01:56:19.511972: step: 556/526, loss: 0.10586948692798615
2023-01-23 01:56:20.649278: step: 560/526, loss: 0.020032214000821114
2023-01-23 01:56:21.768999: step: 564/526, loss: 0.01800668239593506
2023-01-23 01:56:22.943470: step: 568/526, loss: 0.05415081977844238
2023-01-23 01:56:24.069359: step: 572/526, loss: 0.02035980299115181
2023-01-23 01:56:25.207577: step: 576/526, loss: 0.07460957020521164
2023-01-23 01:56:26.366491: step: 580/526, loss: 0.23481902480125427
2023-01-23 01:56:27.500693: step: 584/526, loss: 0.004990768618881702
2023-01-23 01:56:28.635703: step: 588/526, loss: 0.005188083276152611
2023-01-23 01:56:29.761261: step: 592/526, loss: 0.035907745361328125
2023-01-23 01:56:30.923256: step: 596/526, loss: 0.11188049614429474
2023-01-23 01:56:32.064708: step: 600/526, loss: 0.011778736487030983
2023-01-23 01:56:33.197965: step: 604/526, loss: 0.03871631622314453
2023-01-23 01:56:34.339360: step: 608/526, loss: 0.06158256530761719
2023-01-23 01:56:35.486066: step: 612/526, loss: 0.029084108769893646
2023-01-23 01:56:36.658658: step: 616/526, loss: 0.0006958007579669356
2023-01-23 01:56:37.830596: step: 620/526, loss: 0.030344391241669655
2023-01-23 01:56:38.963816: step: 624/526, loss: 0.01116247195750475
2023-01-23 01:56:40.083172: step: 628/526, loss: 0.1720743328332901
2023-01-23 01:56:41.223616: step: 632/526, loss: 0.07003584504127502
2023-01-23 01:56:42.355132: step: 636/526, loss: 0.0007466792594641447
2023-01-23 01:56:43.509052: step: 640/526, loss: 0.0038945735432207584
2023-01-23 01:56:44.684076: step: 644/526, loss: 0.010624694637954235
2023-01-23 01:56:45.849010: step: 648/526, loss: 0.03835335001349449
2023-01-23 01:56:47.001107: step: 652/526, loss: 0.0007458686595782638
2023-01-23 01:56:48.122638: step: 656/526, loss: 0.022769834846258163
2023-01-23 01:56:49.239218: step: 660/526, loss: 0.022292137145996094
2023-01-23 01:56:50.387588: step: 664/526, loss: 0.03672933578491211
2023-01-23 01:56:51.521085: step: 668/526, loss: 0.010675812140107155
2023-01-23 01:56:52.648490: step: 672/526, loss: 0.08597974479198456
2023-01-23 01:56:53.761696: step: 676/526, loss: 0.0008501053089275956
2023-01-23 01:56:54.880867: step: 680/526, loss: 0.013707256875932217
2023-01-23 01:56:56.026771: step: 684/526, loss: 0.02264699898660183
2023-01-23 01:56:57.161631: step: 688/526, loss: 0.00027980803861282766
2023-01-23 01:56:58.289696: step: 692/526, loss: 0.04479851573705673
2023-01-23 01:56:59.413496: step: 696/526, loss: 0.017988301813602448
2023-01-23 01:57:00.551546: step: 700/526, loss: 0.08115081489086151
2023-01-23 01:57:01.698210: step: 704/526, loss: 0.1008453369140625
2023-01-23 01:57:02.857584: step: 708/526, loss: 0.03654451295733452
2023-01-23 01:57:03.983237: step: 712/526, loss: 0.022855425253510475
2023-01-23 01:57:05.104908: step: 716/526, loss: 0.009132814593613148
2023-01-23 01:57:06.244678: step: 720/526, loss: 0.05775337666273117
2023-01-23 01:57:07.410219: step: 724/526, loss: 0.05679187923669815
2023-01-23 01:57:08.531496: step: 728/526, loss: 0.000560760498046875
2023-01-23 01:57:09.665406: step: 732/526, loss: 0.026170063763856888
2023-01-23 01:57:10.821625: step: 736/526, loss: 0.031717684119939804
2023-01-23 01:57:11.944294: step: 740/526, loss: 0.04638538509607315
2023-01-23 01:57:13.103635: step: 744/526, loss: 0.007654215674847364
2023-01-23 01:57:14.243170: step: 748/526, loss: 0.016956090927124023
2023-01-23 01:57:15.405439: step: 752/526, loss: 0.04389238357543945
2023-01-23 01:57:16.557154: step: 756/526, loss: 0.00855178851634264
2023-01-23 01:57:17.679534: step: 760/526, loss: 0.034254275262355804
2023-01-23 01:57:18.820826: step: 764/526, loss: 0.14534887671470642
2023-01-23 01:57:19.981358: step: 768/526, loss: 0.008438730612397194
2023-01-23 01:57:21.142600: step: 772/526, loss: 0.00020227432833053172
2023-01-23 01:57:22.273393: step: 776/526, loss: 0.025569917634129524
2023-01-23 01:57:23.383311: step: 780/526, loss: 0.06152515113353729
2023-01-23 01:57:24.481848: step: 784/526, loss: 0.0010889529949054122
2023-01-23 01:57:25.630296: step: 788/526, loss: 0.01145782507956028
2023-01-23 01:57:26.776519: step: 792/526, loss: 0.00215320591814816
2023-01-23 01:57:27.893968: step: 796/526, loss: 0.019379330798983574
2023-01-23 01:57:29.016431: step: 800/526, loss: 0.009414101019501686
2023-01-23 01:57:30.156022: step: 804/526, loss: 0.0415528304874897
2023-01-23 01:57:31.292402: step: 808/526, loss: 0.005959892645478249
2023-01-23 01:57:32.503862: step: 812/526, loss: 0.015486336313188076
2023-01-23 01:57:33.623916: step: 816/526, loss: 0.3148905634880066
2023-01-23 01:57:34.788889: step: 820/526, loss: 0.006985187530517578
2023-01-23 01:57:35.924809: step: 824/526, loss: 0.0011864661937579513
2023-01-23 01:57:37.057539: step: 828/526, loss: 0.007863283157348633
2023-01-23 01:57:38.203703: step: 832/526, loss: 0.0014211655361577868
2023-01-23 01:57:39.320318: step: 836/526, loss: 0.031378746032714844
2023-01-23 01:57:40.524623: step: 840/526, loss: 0.0496830940246582
2023-01-23 01:57:41.665587: step: 844/526, loss: 0.026904677972197533
2023-01-23 01:57:42.802860: step: 848/526, loss: 0.006833505816757679
2023-01-23 01:57:43.940702: step: 852/526, loss: 0.005734109785407782
2023-01-23 01:57:45.098286: step: 856/526, loss: 0.017026234418153763
2023-01-23 01:57:46.236900: step: 860/526, loss: 0.008176708593964577
2023-01-23 01:57:47.366315: step: 864/526, loss: 0.005719518288969994
2023-01-23 01:57:48.492119: step: 868/526, loss: 0.014420128427445889
2023-01-23 01:57:49.603762: step: 872/526, loss: 0.052733805030584335
2023-01-23 01:57:50.733351: step: 876/526, loss: 0.015298079699277878
2023-01-23 01:57:51.855572: step: 880/526, loss: 0.05374488979578018
2023-01-23 01:57:53.022042: step: 884/526, loss: 0.6681743860244751
2023-01-23 01:57:54.155519: step: 888/526, loss: 0.00038733481778763235
2023-01-23 01:57:55.272630: step: 892/526, loss: 0.011528587900102139
2023-01-23 01:57:56.399269: step: 896/526, loss: 0.006939506158232689
2023-01-23 01:57:57.528252: step: 900/526, loss: 0.06101560965180397
2023-01-23 01:57:58.650028: step: 904/526, loss: 0.0038442614022642374
2023-01-23 01:57:59.765309: step: 908/526, loss: 0.08767890930175781
2023-01-23 01:58:00.900829: step: 912/526, loss: 0.07067527621984482
2023-01-23 01:58:02.014849: step: 916/526, loss: 0.06301408261060715
2023-01-23 01:58:03.175853: step: 920/526, loss: 0.05525340884923935
2023-01-23 01:58:04.299348: step: 924/526, loss: 0.03001587465405464
2023-01-23 01:58:05.408287: step: 928/526, loss: 0.05066210404038429
2023-01-23 01:58:06.508847: step: 932/526, loss: 0.09693536907434464
2023-01-23 01:58:07.625064: step: 936/526, loss: 0.01844949647784233
2023-01-23 01:58:08.737604: step: 940/526, loss: 0.001082134316675365
2023-01-23 01:58:09.855460: step: 944/526, loss: 0.0005603790050372481
2023-01-23 01:58:10.999632: step: 948/526, loss: 0.03271665796637535
2023-01-23 01:58:12.115444: step: 952/526, loss: 0.07516960054636002
2023-01-23 01:58:13.264725: step: 956/526, loss: 0.02696523629128933
2023-01-23 01:58:14.391904: step: 960/526, loss: 0.07556271553039551
2023-01-23 01:58:15.536391: step: 964/526, loss: 0.05851192772388458
2023-01-23 01:58:16.672079: step: 968/526, loss: 0.08257904648780823
2023-01-23 01:58:17.827341: step: 972/526, loss: 0.0008014679187908769
2023-01-23 01:58:18.952865: step: 976/526, loss: 0.47696352005004883
2023-01-23 01:58:20.098279: step: 980/526, loss: 0.0007006645319052041
2023-01-23 01:58:21.242111: step: 984/526, loss: 0.011383056640625
2023-01-23 01:58:22.355975: step: 988/526, loss: 0.00690307654440403
2023-01-23 01:58:23.469252: step: 992/526, loss: 0.031540773808956146
2023-01-23 01:58:24.605607: step: 996/526, loss: 0.02640690840780735
2023-01-23 01:58:25.758879: step: 1000/526, loss: 0.015194892883300781
2023-01-23 01:58:26.900018: step: 1004/526, loss: 0.024719620123505592
2023-01-23 01:58:28.018392: step: 1008/526, loss: 0.005755424965173006
2023-01-23 01:58:29.151866: step: 1012/526, loss: 0.02340087853372097
2023-01-23 01:58:30.289479: step: 1016/526, loss: 0.0287641528993845
2023-01-23 01:58:31.444838: step: 1020/526, loss: 0.0001539230433991179
2023-01-23 01:58:32.561643: step: 1024/526, loss: 0.00240249652415514
2023-01-23 01:58:33.686372: step: 1028/526, loss: 0.009704399853944778
2023-01-23 01:58:34.818382: step: 1032/526, loss: 0.008310128003358841
2023-01-23 01:58:35.939391: step: 1036/526, loss: 0.016400909051299095
2023-01-23 01:58:37.074406: step: 1040/526, loss: 0.01180114783346653
2023-01-23 01:58:38.198107: step: 1044/526, loss: 0.08272266387939453
2023-01-23 01:58:39.328534: step: 1048/526, loss: 0.021078776568174362
2023-01-23 01:58:40.497343: step: 1052/526, loss: 0.009411525912582874
2023-01-23 01:58:41.623516: step: 1056/526, loss: 0.11165113747119904
2023-01-23 01:58:42.752618: step: 1060/526, loss: 0.05851578712463379
2023-01-23 01:58:43.884269: step: 1064/526, loss: 0.06337108463048935
2023-01-23 01:58:45.042246: step: 1068/526, loss: 0.05727062374353409
2023-01-23 01:58:46.146013: step: 1072/526, loss: 0.01905827596783638
2023-01-23 01:58:47.266134: step: 1076/526, loss: 0.09094247221946716
2023-01-23 01:58:48.377146: step: 1080/526, loss: 0.007142829708755016
2023-01-23 01:58:49.519789: step: 1084/526, loss: 0.012323188595473766
2023-01-23 01:58:50.665567: step: 1088/526, loss: 0.027137089520692825
2023-01-23 01:58:51.784828: step: 1092/526, loss: 0.04914169758558273
2023-01-23 01:58:52.894525: step: 1096/526, loss: 0.00014047622971702367
2023-01-23 01:58:54.049151: step: 1100/526, loss: 0.020443536341190338
2023-01-23 01:58:55.209637: step: 1104/526, loss: 0.0012463569873943925
2023-01-23 01:58:56.331808: step: 1108/526, loss: 0.11151676625013351
2023-01-23 01:58:57.458303: step: 1112/526, loss: 0.03851685672998428
2023-01-23 01:58:58.612718: step: 1116/526, loss: 0.05852337181568146
2023-01-23 01:58:59.753165: step: 1120/526, loss: 0.017716217786073685
2023-01-23 01:59:00.913979: step: 1124/526, loss: 0.002372789429500699
2023-01-23 01:59:02.033868: step: 1128/526, loss: 0.020529747009277344
2023-01-23 01:59:03.176465: step: 1132/526, loss: 0.00903086643666029
2023-01-23 01:59:04.321457: step: 1136/526, loss: 0.01313171349465847
2023-01-23 01:59:05.483986: step: 1140/526, loss: 0.010787487961351871
2023-01-23 01:59:06.664549: step: 1144/526, loss: 0.003053951309993863
2023-01-23 01:59:07.804631: step: 1148/526, loss: 0.017096709460020065
2023-01-23 01:59:08.936407: step: 1152/526, loss: 0.00044465065002441406
2023-01-23 01:59:10.103262: step: 1156/526, loss: 0.008677482604980469
2023-01-23 01:59:11.253115: step: 1160/526, loss: 0.012208365835249424
2023-01-23 01:59:12.350787: step: 1164/526, loss: 0.021317673847079277
2023-01-23 01:59:13.510586: step: 1168/526, loss: 0.009976488538086414
2023-01-23 01:59:14.651203: step: 1172/526, loss: 0.005944728851318359
2023-01-23 01:59:15.804613: step: 1176/526, loss: 0.008188724517822266
2023-01-23 01:59:16.950381: step: 1180/526, loss: 0.0025188445579260588
2023-01-23 01:59:18.056445: step: 1184/526, loss: 0.011735345236957073
2023-01-23 01:59:19.204267: step: 1188/526, loss: 0.022648334503173828
2023-01-23 01:59:20.321787: step: 1192/526, loss: 0.00027484894962981343
2023-01-23 01:59:21.444308: step: 1196/526, loss: 0.09759931266307831
2023-01-23 01:59:22.588462: step: 1200/526, loss: 0.00784306600689888
2023-01-23 01:59:23.746251: step: 1204/526, loss: 0.0034612659364938736
2023-01-23 01:59:24.901384: step: 1208/526, loss: 0.007220268249511719
2023-01-23 01:59:26.063941: step: 1212/526, loss: 0.0019939423073083162
2023-01-23 01:59:27.168685: step: 1216/526, loss: 0.053132928907871246
2023-01-23 01:59:28.302017: step: 1220/526, loss: 0.01638355292379856
2023-01-23 01:59:29.441403: step: 1224/526, loss: 0.13880720734596252
2023-01-23 01:59:30.567740: step: 1228/526, loss: 0.00272884382866323
2023-01-23 01:59:31.689438: step: 1232/526, loss: 0.07232251763343811
2023-01-23 01:59:32.848696: step: 1236/526, loss: 0.028873920440673828
2023-01-23 01:59:33.992842: step: 1240/526, loss: 0.0020033835899084806
2023-01-23 01:59:35.113099: step: 1244/526, loss: 0.03896808624267578
2023-01-23 01:59:36.231041: step: 1248/526, loss: 0.07329349964857101
2023-01-23 01:59:37.369860: step: 1252/526, loss: 0.016579627990722656
2023-01-23 01:59:38.522981: step: 1256/526, loss: 0.05246315151453018
2023-01-23 01:59:39.641081: step: 1260/526, loss: 0.05313308537006378
2023-01-23 01:59:40.763559: step: 1264/526, loss: 0.14537039399147034
2023-01-23 01:59:41.884707: step: 1268/526, loss: 0.011049938388168812
2023-01-23 01:59:43.071204: step: 1272/526, loss: 0.03732319176197052
2023-01-23 01:59:44.215410: step: 1276/526, loss: 0.06474075466394424
2023-01-23 01:59:45.368202: step: 1280/526, loss: 0.13269072771072388
2023-01-23 01:59:46.498494: step: 1284/526, loss: 0.07875613868236542
2023-01-23 01:59:47.654745: step: 1288/526, loss: 0.025364112108945847
2023-01-23 01:59:48.789055: step: 1292/526, loss: 0.012532235123217106
2023-01-23 01:59:49.918718: step: 1296/526, loss: 0.03448314592242241
2023-01-23 01:59:51.047991: step: 1300/526, loss: 0.01663036271929741
2023-01-23 01:59:52.165051: step: 1304/526, loss: 0.015280676074326038
2023-01-23 01:59:53.302179: step: 1308/526, loss: 0.001991367433220148
2023-01-23 01:59:54.399996: step: 1312/526, loss: 0.0353623628616333
2023-01-23 01:59:55.525224: step: 1316/526, loss: 0.0299238208681345
2023-01-23 01:59:56.654339: step: 1320/526, loss: 0.011005115695297718
2023-01-23 01:59:57.775501: step: 1324/526, loss: 0.07054109871387482
2023-01-23 01:59:58.920270: step: 1328/526, loss: 0.06421032547950745
2023-01-23 02:00:00.037995: step: 1332/526, loss: 0.012379264459013939
2023-01-23 02:00:01.186721: step: 1336/526, loss: 0.014616680331528187
2023-01-23 02:00:02.318548: step: 1340/526, loss: 0.02322368696331978
2023-01-23 02:00:03.483078: step: 1344/526, loss: 0.016550827771425247
2023-01-23 02:00:04.643886: step: 1348/526, loss: 0.017902422696352005
2023-01-23 02:00:05.750288: step: 1352/526, loss: 0.005248356144875288
2023-01-23 02:00:06.873188: step: 1356/526, loss: 0.013132667168974876
2023-01-23 02:00:07.993140: step: 1360/526, loss: 0.00671000499278307
2023-01-23 02:00:09.142896: step: 1364/526, loss: 0.023415088653564453
2023-01-23 02:00:10.283284: step: 1368/526, loss: 0.0005354405147954822
2023-01-23 02:00:11.395586: step: 1372/526, loss: 0.00042765142279677093
2023-01-23 02:00:12.527590: step: 1376/526, loss: 0.015307044610381126
2023-01-23 02:00:13.648278: step: 1380/526, loss: 0.18836478888988495
2023-01-23 02:00:14.783876: step: 1384/526, loss: 0.001861572265625
2023-01-23 02:00:15.956635: step: 1388/526, loss: 0.028600502759218216
2023-01-23 02:00:17.086371: step: 1392/526, loss: 0.004447364713996649
2023-01-23 02:00:18.219780: step: 1396/526, loss: 0.07432775944471359
2023-01-23 02:00:19.329253: step: 1400/526, loss: 0.01283111609518528
2023-01-23 02:00:20.463507: step: 1404/526, loss: 0.03626260906457901
2023-01-23 02:00:21.570382: step: 1408/526, loss: 0.03151760250329971
2023-01-23 02:00:22.710529: step: 1412/526, loss: 0.002002716064453125
2023-01-23 02:00:23.827558: step: 1416/526, loss: 0.09061814099550247
2023-01-23 02:00:24.962516: step: 1420/526, loss: 0.03536491468548775
2023-01-23 02:00:26.071614: step: 1424/526, loss: 0.01896655559539795
2023-01-23 02:00:27.193545: step: 1428/526, loss: 0.14170297980308533
2023-01-23 02:00:28.307392: step: 1432/526, loss: 0.0007655143854208291
2023-01-23 02:00:29.438801: step: 1436/526, loss: 0.06198524683713913
2023-01-23 02:00:30.559484: step: 1440/526, loss: 0.008537674322724342
2023-01-23 02:00:31.684397: step: 1444/526, loss: 0.022623158991336823
2023-01-23 02:00:32.802933: step: 1448/526, loss: 0.05109348148107529
2023-01-23 02:00:33.957393: step: 1452/526, loss: 0.012701607309281826
2023-01-23 02:00:35.069401: step: 1456/526, loss: 0.003014135407283902
2023-01-23 02:00:36.200022: step: 1460/526, loss: 0.0011701583862304688
2023-01-23 02:00:37.319475: step: 1464/526, loss: 0.0027844428550451994
2023-01-23 02:00:38.446538: step: 1468/526, loss: 0.0018871307838708162
2023-01-23 02:00:39.573057: step: 1472/526, loss: 0.0028310774359852076
2023-01-23 02:00:40.684141: step: 1476/526, loss: 0.0021018029656261206
2023-01-23 02:00:41.799312: step: 1480/526, loss: 0.002915668534114957
2023-01-23 02:00:42.947996: step: 1484/526, loss: 0.09278788417577744
2023-01-23 02:00:44.119894: step: 1488/526, loss: 0.03566303104162216
2023-01-23 02:00:45.241157: step: 1492/526, loss: 0.007505846209824085
2023-01-23 02:00:46.384469: step: 1496/526, loss: 0.0024461746215820312
2023-01-23 02:00:47.521355: step: 1500/526, loss: 0.044089317321777344
2023-01-23 02:00:48.650269: step: 1504/526, loss: 0.000953292881604284
2023-01-23 02:00:49.783899: step: 1508/526, loss: 0.0310229305177927
2023-01-23 02:00:50.907922: step: 1512/526, loss: 0.0328710600733757
2023-01-23 02:00:52.041092: step: 1516/526, loss: 0.0010725974570959806
2023-01-23 02:00:53.189176: step: 1520/526, loss: 0.5288132429122925
2023-01-23 02:00:54.330986: step: 1524/526, loss: 0.07509537041187286
2023-01-23 02:00:55.472563: step: 1528/526, loss: 0.023479079827666283
2023-01-23 02:00:56.603346: step: 1532/526, loss: 0.0011591911315917969
2023-01-23 02:00:57.749803: step: 1536/526, loss: 0.053659629076719284
2023-01-23 02:00:58.900313: step: 1540/526, loss: 0.05722217634320259
2023-01-23 02:01:00.025561: step: 1544/526, loss: 0.02186732180416584
2023-01-23 02:01:01.182363: step: 1548/526, loss: 0.07524510473012924
2023-01-23 02:01:02.317569: step: 1552/526, loss: 0.032151415944099426
2023-01-23 02:01:03.476654: step: 1556/526, loss: 0.012040138244628906
2023-01-23 02:01:04.639234: step: 1560/526, loss: 0.018299389630556107
2023-01-23 02:01:05.782137: step: 1564/526, loss: 0.01961848884820938
2023-01-23 02:01:06.925561: step: 1568/526, loss: 0.03396425396203995
2023-01-23 02:01:08.074226: step: 1572/526, loss: 0.016263389959931374
2023-01-23 02:01:09.216712: step: 1576/526, loss: 0.012240070849657059
2023-01-23 02:01:10.333443: step: 1580/526, loss: 0.006938362028449774
2023-01-23 02:01:11.449111: step: 1584/526, loss: 0.012159060686826706
2023-01-23 02:01:12.574061: step: 1588/526, loss: 0.0010875702137127519
2023-01-23 02:01:13.698136: step: 1592/526, loss: 0.00943145714700222
2023-01-23 02:01:14.838150: step: 1596/526, loss: 0.021221160888671875
2023-01-23 02:01:15.994085: step: 1600/526, loss: 0.02083129808306694
2023-01-23 02:01:17.107812: step: 1604/526, loss: 0.0012420654529705644
2023-01-23 02:01:18.258568: step: 1608/526, loss: 0.025774193927645683
2023-01-23 02:01:19.379816: step: 1612/526, loss: 0.00968628004193306
2023-01-23 02:01:20.489917: step: 1616/526, loss: 0.07935958355665207
2023-01-23 02:01:21.640213: step: 1620/526, loss: 0.07276764512062073
2023-01-23 02:01:22.789859: step: 1624/526, loss: 0.031004145741462708
2023-01-23 02:01:23.961174: step: 1628/526, loss: 0.04893860965967178
2023-01-23 02:01:25.089603: step: 1632/526, loss: 0.02863292768597603
2023-01-23 02:01:26.228946: step: 1636/526, loss: 0.012957191094756126
2023-01-23 02:01:27.366421: step: 1640/526, loss: 0.012598990462720394
2023-01-23 02:01:28.513153: step: 1644/526, loss: 0.011762047186493874
2023-01-23 02:01:29.614716: step: 1648/526, loss: 0.003974628169089556
2023-01-23 02:01:30.725864: step: 1652/526, loss: 0.1054234504699707
2023-01-23 02:01:31.890027: step: 1656/526, loss: 0.03522396460175514
2023-01-23 02:01:33.015988: step: 1660/526, loss: 0.004057598300278187
2023-01-23 02:01:34.145102: step: 1664/526, loss: 0.04009886085987091
2023-01-23 02:01:35.255629: step: 1668/526, loss: 0.029004957526922226
2023-01-23 02:01:36.408972: step: 1672/526, loss: 0.029472827911376953
2023-01-23 02:01:37.572069: step: 1676/526, loss: 0.021584415808320045
2023-01-23 02:01:38.713876: step: 1680/526, loss: 0.06130675971508026
2023-01-23 02:01:39.837465: step: 1684/526, loss: 0.014807415194809437
2023-01-23 02:01:40.978002: step: 1688/526, loss: 0.07389964908361435
2023-01-23 02:01:42.133344: step: 1692/526, loss: 0.045704230666160583
2023-01-23 02:01:43.251982: step: 1696/526, loss: 0.07203865051269531
2023-01-23 02:01:44.410398: step: 1700/526, loss: 0.027575302869081497
2023-01-23 02:01:45.552353: step: 1704/526, loss: 0.007754468824714422
2023-01-23 02:01:46.707931: step: 1708/526, loss: 0.32650527358055115
2023-01-23 02:01:47.844447: step: 1712/526, loss: 0.05932359769940376
2023-01-23 02:01:48.970925: step: 1716/526, loss: 0.11338011920452118
2023-01-23 02:01:50.088362: step: 1720/526, loss: 0.03401365503668785
2023-01-23 02:01:51.231060: step: 1724/526, loss: 0.026148034259676933
2023-01-23 02:01:52.407565: step: 1728/526, loss: 0.018466949462890625
2023-01-23 02:01:53.572029: step: 1732/526, loss: 0.04690499231219292
2023-01-23 02:01:54.708454: step: 1736/526, loss: 0.0029813051223754883
2023-01-23 02:01:55.834855: step: 1740/526, loss: 0.11627130210399628
2023-01-23 02:01:56.979829: step: 1744/526, loss: 0.6963399648666382
2023-01-23 02:01:58.118256: step: 1748/526, loss: 0.02696824073791504
2023-01-23 02:01:59.243716: step: 1752/526, loss: 0.04826998710632324
2023-01-23 02:02:00.360880: step: 1756/526, loss: 0.10515594482421875
2023-01-23 02:02:01.517219: step: 1760/526, loss: 0.015928268432617188
2023-01-23 02:02:02.647161: step: 1764/526, loss: 0.007394728250801563
2023-01-23 02:02:03.772953: step: 1768/526, loss: 0.02510528452694416
2023-01-23 02:02:04.908677: step: 1772/526, loss: 0.006548500154167414
2023-01-23 02:02:06.037041: step: 1776/526, loss: 0.03842916339635849
2023-01-23 02:02:07.183294: step: 1780/526, loss: 0.011109876446425915
2023-01-23 02:02:08.344838: step: 1784/526, loss: 0.05668430030345917
2023-01-23 02:02:09.454499: step: 1788/526, loss: 0.14935742318630219
2023-01-23 02:02:10.592582: step: 1792/526, loss: 0.05277585983276367
2023-01-23 02:02:11.733010: step: 1796/526, loss: 0.0009180069318972528
2023-01-23 02:02:12.858548: step: 1800/526, loss: 0.0048984051682055
2023-01-23 02:02:13.981550: step: 1804/526, loss: 0.022557832300662994
2023-01-23 02:02:15.130570: step: 1808/526, loss: 0.024224378168582916
2023-01-23 02:02:16.235107: step: 1812/526, loss: 0.0031709671020507812
2023-01-23 02:02:17.338215: step: 1816/526, loss: 0.006091499235481024
2023-01-23 02:02:18.486525: step: 1820/526, loss: 0.3853173553943634
2023-01-23 02:02:19.615247: step: 1824/526, loss: 0.0038299560546875
2023-01-23 02:02:20.772514: step: 1828/526, loss: 0.029605364426970482
2023-01-23 02:02:21.896054: step: 1832/526, loss: 0.017946625128388405
2023-01-23 02:02:23.081552: step: 1836/526, loss: 0.0021326064597815275
2023-01-23 02:02:24.193845: step: 1840/526, loss: 0.004783248528838158
2023-01-23 02:02:25.335492: step: 1844/526, loss: 0.004403305239975452
2023-01-23 02:02:26.479858: step: 1848/526, loss: 0.769024670124054
2023-01-23 02:02:27.615317: step: 1852/526, loss: 0.24156780540943146
2023-01-23 02:02:28.742469: step: 1856/526, loss: 0.006679534912109375
2023-01-23 02:02:29.896434: step: 1860/526, loss: 0.3477468490600586
2023-01-23 02:02:31.057239: step: 1864/526, loss: 0.0831918716430664
2023-01-23 02:02:32.196182: step: 1868/526, loss: 0.0034605979453772306
2023-01-23 02:02:33.348323: step: 1872/526, loss: 0.05076313391327858
2023-01-23 02:02:34.463665: step: 1876/526, loss: 0.011259890161454678
2023-01-23 02:02:35.612097: step: 1880/526, loss: 0.016239548102021217
2023-01-23 02:02:36.717210: step: 1884/526, loss: 0.07064676284790039
2023-01-23 02:02:37.833414: step: 1888/526, loss: 0.0006339550018310547
2023-01-23 02:02:38.991090: step: 1892/526, loss: 0.031766317784786224
2023-01-23 02:02:40.125039: step: 1896/526, loss: 0.0023015975020825863
2023-01-23 02:02:41.298580: step: 1900/526, loss: 0.0020677566062659025
2023-01-23 02:02:42.419408: step: 1904/526, loss: 0.01207809429615736
2023-01-23 02:02:43.566646: step: 1908/526, loss: 0.1251041442155838
2023-01-23 02:02:44.689942: step: 1912/526, loss: 0.03783874586224556
2023-01-23 02:02:45.812049: step: 1916/526, loss: 0.011644363403320312
2023-01-23 02:02:46.929392: step: 1920/526, loss: 0.08902013301849365
2023-01-23 02:02:48.077843: step: 1924/526, loss: 0.0004311561642680317
2023-01-23 02:02:49.268597: step: 1928/526, loss: 0.10454969108104706
2023-01-23 02:02:50.390269: step: 1932/526, loss: 0.011892891488969326
2023-01-23 02:02:51.528508: step: 1936/526, loss: 0.029772471636533737
2023-01-23 02:02:52.657301: step: 1940/526, loss: 0.06390085071325302
2023-01-23 02:02:53.768565: step: 1944/526, loss: 0.015054702758789062
2023-01-23 02:02:54.901198: step: 1948/526, loss: 0.012243938632309437
2023-01-23 02:02:56.070369: step: 1952/526, loss: 0.4398822784423828
2023-01-23 02:02:57.196155: step: 1956/526, loss: 0.08239660412073135
2023-01-23 02:02:58.341106: step: 1960/526, loss: 0.0768928974866867
2023-01-23 02:02:59.469464: step: 1964/526, loss: 0.0029317857697606087
2023-01-23 02:03:00.583222: step: 1968/526, loss: 0.0447535514831543
2023-01-23 02:03:01.735219: step: 1972/526, loss: 0.043679095804691315
2023-01-23 02:03:02.857577: step: 1976/526, loss: 0.05214405059814453
2023-01-23 02:03:04.003851: step: 1980/526, loss: 0.058764077723026276
2023-01-23 02:03:05.140479: step: 1984/526, loss: 0.00429534912109375
2023-01-23 02:03:06.277508: step: 1988/526, loss: 0.033416081219911575
2023-01-23 02:03:07.430392: step: 1992/526, loss: 0.005925274454057217
2023-01-23 02:03:08.547009: step: 1996/526, loss: 0.041114043444395065
2023-01-23 02:03:09.700782: step: 2000/526, loss: 0.11051063239574432
2023-01-23 02:03:10.862191: step: 2004/526, loss: 0.031624604016542435
2023-01-23 02:03:11.997501: step: 2008/526, loss: 0.037841081619262695
2023-01-23 02:03:13.156749: step: 2012/526, loss: 0.008747626096010208
2023-01-23 02:03:14.330503: step: 2016/526, loss: 0.019548749551177025
2023-01-23 02:03:15.474997: step: 2020/526, loss: 0.020754002034664154
2023-01-23 02:03:16.612401: step: 2024/526, loss: 0.02051960863173008
2023-01-23 02:03:17.762737: step: 2028/526, loss: 0.13297158479690552
2023-01-23 02:03:18.880342: step: 2032/526, loss: 0.0016053318977355957
2023-01-23 02:03:20.018282: step: 2036/526, loss: 0.011286449618637562
2023-01-23 02:03:21.144576: step: 2040/526, loss: 0.03196869045495987
2023-01-23 02:03:22.296243: step: 2044/526, loss: 0.0447598472237587
2023-01-23 02:03:23.425337: step: 2048/526, loss: 0.0063200946897268295
2023-01-23 02:03:24.565964: step: 2052/526, loss: 0.0020450593437999487
2023-01-23 02:03:25.717106: step: 2056/526, loss: 0.1256854087114334
2023-01-23 02:03:26.874372: step: 2060/526, loss: 0.0715525671839714
2023-01-23 02:03:27.982360: step: 2064/526, loss: 0.001021099160425365
2023-01-23 02:03:29.101347: step: 2068/526, loss: 0.04251861572265625
2023-01-23 02:03:30.220203: step: 2072/526, loss: 0.0840839371085167
2023-01-23 02:03:31.328088: step: 2076/526, loss: 0.1330556869506836
2023-01-23 02:03:32.467614: step: 2080/526, loss: 0.09395141899585724
2023-01-23 02:03:33.593546: step: 2084/526, loss: 0.025026513263583183
2023-01-23 02:03:34.716656: step: 2088/526, loss: 0.07811050117015839
2023-01-23 02:03:35.883563: step: 2092/526, loss: 0.015866661444306374
2023-01-23 02:03:37.004009: step: 2096/526, loss: 0.014677238650619984
2023-01-23 02:03:38.103331: step: 2100/526, loss: 0.05850258469581604
2023-01-23 02:03:39.255206: step: 2104/526, loss: 0.012905311770737171
==================================================
Loss: 0.044
--------------------
Dev: {'event': {'p': 0.596757852077001, 'r': 0.7842876165113183, 'f1': 0.6777905638665133}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 14}
Test: {'event': {'p': 0.6237995824634656, 'r': 0.7797494780793319, 'f1': 0.6931106471816285}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 14}
Chinese: {'event': {'p': 0.5903614457831325, 'r': 0.9074074074074074, 'f1': 0.7153284671532847}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 14}
Korean: {'event': {'p': 0.7073170731707317, 'r': 0.4603174603174603, 'f1': 0.5576923076923077}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 14}
Russian: {'event': {'p': 0.4146341463414634, 'r': 0.4722222222222222, 'f1': 0.4415584415584415}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 14}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6389811738648948, 'r': 0.7683089214380826, 'f1': 0.6977025392986699}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Eng Test for Chinese: {'event': {'p': 0.6328626444159179, 'r': 0.7719206680584552, 'f1': 0.6955090524335763}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Sample Chinese: {'event': {'p': 0.6282051282051282, 'r': 0.9074074074074074, 'f1': 0.7424242424242423}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6257995735607675, 'r': 0.7816245006657789, 'f1': 0.6950858496151568}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Eng Test for Korean: {'event': {'p': 0.623113410952997, 'r': 0.7541753653444676, 'f1': 0.6824085005903188}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Sample Korean: {'event': {'p': 0.7446808510638298, 'r': 0.5555555555555556, 'f1': 0.6363636363636364}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6217672413793104, 'r': 0.7683089214380826, 'f1': 0.6873138773079214}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Eng Test for Russian: {'event': {'p': 0.6300302899177845, 'r': 0.7599164926931107, 'f1': 0.6889046605157322}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Sample Russian: {'event': {'p': 0.5, 'r': 0.5833333333333334, 'f1': 0.5384615384615384}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
******************************
Epoch: 15
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 02:04:22.180716: step: 4/526, loss: 0.015715409070253372
2023-01-23 02:04:23.296532: step: 8/526, loss: 0.03385467454791069
2023-01-23 02:04:24.412102: step: 12/526, loss: 0.09915709495544434
2023-01-23 02:04:25.527378: step: 16/526, loss: 0.011584281921386719
2023-01-23 02:04:26.685947: step: 20/526, loss: 8.7738037109375e-05
2023-01-23 02:04:27.791866: step: 24/526, loss: 0.0006498337024822831
2023-01-23 02:04:28.922828: step: 28/526, loss: 0.013985633850097656
2023-01-23 02:04:30.038395: step: 32/526, loss: 0.020456504076719284
2023-01-23 02:04:31.166549: step: 36/526, loss: 0.008350754156708717
2023-01-23 02:04:32.285514: step: 40/526, loss: 0.026631547138094902
2023-01-23 02:04:33.392358: step: 44/526, loss: 0.058612849563360214
2023-01-23 02:04:34.510625: step: 48/526, loss: 0.018627453595399857
2023-01-23 02:04:35.659155: step: 52/526, loss: 0.07881756126880646
2023-01-23 02:04:36.847612: step: 56/526, loss: 0.011064434424042702
2023-01-23 02:04:37.970935: step: 60/526, loss: 0.027622507885098457
2023-01-23 02:04:39.138491: step: 64/526, loss: 0.02246999740600586
2023-01-23 02:04:40.275395: step: 68/526, loss: 0.007797289174050093
2023-01-23 02:04:41.425631: step: 72/526, loss: 0.000351142865838483
2023-01-23 02:04:42.547603: step: 76/526, loss: 0.07748118042945862
2023-01-23 02:04:43.722970: step: 80/526, loss: 0.006552505772560835
2023-01-23 02:04:44.859129: step: 84/526, loss: 0.032444000244140625
2023-01-23 02:04:45.987405: step: 88/526, loss: 0.002372264862060547
2023-01-23 02:04:47.110798: step: 92/526, loss: 0.06604146957397461
2023-01-23 02:04:48.251997: step: 96/526, loss: 0.006347847171127796
2023-01-23 02:04:49.384124: step: 100/526, loss: 0.03308863937854767
2023-01-23 02:04:50.489559: step: 104/526, loss: 0.011268901638686657
2023-01-23 02:04:51.637483: step: 108/526, loss: 0.049483153969049454
2023-01-23 02:04:52.765244: step: 112/526, loss: 0.012888908386230469
2023-01-23 02:04:53.901913: step: 116/526, loss: 0.06288042664527893
2023-01-23 02:04:55.066653: step: 120/526, loss: 0.006939411163330078
2023-01-23 02:04:56.218445: step: 124/526, loss: 0.017635727301239967
2023-01-23 02:04:57.366378: step: 128/526, loss: 0.0018420219421386719
2023-01-23 02:04:58.487992: step: 132/526, loss: 0.009213065728545189
2023-01-23 02:04:59.608622: step: 136/526, loss: 0.035201214253902435
2023-01-23 02:05:00.789654: step: 140/526, loss: 0.025753404945135117
2023-01-23 02:05:01.926285: step: 144/526, loss: 0.0016251562628895044
2023-01-23 02:05:03.080361: step: 148/526, loss: 0.12415160983800888
2023-01-23 02:05:04.200904: step: 152/526, loss: 0.007700157351791859
2023-01-23 02:05:05.327754: step: 156/526, loss: 0.00010375976853538305
2023-01-23 02:05:06.452989: step: 160/526, loss: 0.019460201263427734
2023-01-23 02:05:07.566141: step: 164/526, loss: 0.0004245758173055947
2023-01-23 02:05:08.723832: step: 168/526, loss: 0.02017951011657715
2023-01-23 02:05:09.844919: step: 172/526, loss: 0.07349959015846252
2023-01-23 02:05:10.983887: step: 176/526, loss: 0.01844015158712864
2023-01-23 02:05:12.136488: step: 180/526, loss: 0.032985687255859375
2023-01-23 02:05:13.288684: step: 184/526, loss: 0.008691406808793545
2023-01-23 02:05:14.445655: step: 188/526, loss: 0.0008455276256427169
2023-01-23 02:05:15.585424: step: 192/526, loss: 0.013279153034090996
2023-01-23 02:05:16.743433: step: 196/526, loss: 0.011546134948730469
2023-01-23 02:05:17.883942: step: 200/526, loss: 0.0751718059182167
2023-01-23 02:05:19.010357: step: 204/526, loss: 0.01450204849243164
2023-01-23 02:05:20.129276: step: 208/526, loss: 0.037872314453125
2023-01-23 02:05:21.252516: step: 212/526, loss: 0.009087909013032913
2023-01-23 02:05:22.365056: step: 216/526, loss: 0.010727119632065296
2023-01-23 02:05:23.488455: step: 220/526, loss: 0.0007208824390545487
2023-01-23 02:05:24.623196: step: 224/526, loss: 0.0003113746643066406
2023-01-23 02:05:25.776621: step: 228/526, loss: 0.001144456909969449
2023-01-23 02:05:26.930505: step: 232/526, loss: 0.004671192262321711
2023-01-23 02:05:28.100542: step: 236/526, loss: 0.007922370918095112
2023-01-23 02:05:29.223867: step: 240/526, loss: 0.015404893085360527
2023-01-23 02:05:30.353189: step: 244/526, loss: 0.001066494034603238
2023-01-23 02:05:31.470265: step: 248/526, loss: 0.04539012908935547
2023-01-23 02:05:32.606323: step: 252/526, loss: 0.021883105859160423
2023-01-23 02:05:33.744749: step: 256/526, loss: 0.0025157928466796875
2023-01-23 02:05:34.880942: step: 260/526, loss: 0.008914184756577015
2023-01-23 02:05:36.004504: step: 264/526, loss: 0.014430428855121136
2023-01-23 02:05:37.150384: step: 268/526, loss: 0.008715915493667126
2023-01-23 02:05:38.277415: step: 272/526, loss: 0.03676197677850723
2023-01-23 02:05:39.390289: step: 276/526, loss: 0.0006800651317462325
2023-01-23 02:05:40.513584: step: 280/526, loss: 0.025012493133544922
2023-01-23 02:05:41.644124: step: 284/526, loss: 0.035610102117061615
2023-01-23 02:05:42.803692: step: 288/526, loss: 0.008062934502959251
2023-01-23 02:05:43.945820: step: 292/526, loss: 0.0018789292080327868
2023-01-23 02:05:45.081701: step: 296/526, loss: 0.011466551572084427
2023-01-23 02:05:46.233938: step: 300/526, loss: 0.13480329513549805
2023-01-23 02:05:47.362581: step: 304/526, loss: 0.01765470579266548
2023-01-23 02:05:48.471156: step: 308/526, loss: 0.059966277331113815
2023-01-23 02:05:49.589456: step: 312/526, loss: 0.012594032101333141
2023-01-23 02:05:50.720583: step: 316/526, loss: 0.030475234612822533
2023-01-23 02:05:51.859262: step: 320/526, loss: 0.004731560125946999
2023-01-23 02:05:53.001738: step: 324/526, loss: 0.002152061555534601
2023-01-23 02:05:54.168024: step: 328/526, loss: 0.012895298190414906
2023-01-23 02:05:55.321051: step: 332/526, loss: 0.6520692706108093
2023-01-23 02:05:56.432011: step: 336/526, loss: 0.04438934475183487
2023-01-23 02:05:57.572830: step: 340/526, loss: 0.03441943973302841
2023-01-23 02:05:58.740089: step: 344/526, loss: 0.041034795343875885
2023-01-23 02:05:59.875928: step: 348/526, loss: 0.014559936709702015
2023-01-23 02:06:01.005150: step: 352/526, loss: 0.06233549118041992
2023-01-23 02:06:02.167033: step: 356/526, loss: 0.016116047278046608
2023-01-23 02:06:03.280144: step: 360/526, loss: 0.04400377348065376
2023-01-23 02:06:04.458309: step: 364/526, loss: 0.003484535263851285
2023-01-23 02:06:05.561088: step: 368/526, loss: 0.0056514739990234375
2023-01-23 02:06:06.706625: step: 372/526, loss: 0.011733055114746094
2023-01-23 02:06:07.840162: step: 376/526, loss: 0.0021009445190429688
2023-01-23 02:06:08.973558: step: 380/526, loss: 0.028389930725097656
2023-01-23 02:06:10.139110: step: 384/526, loss: 0.029287436977028847
2023-01-23 02:06:11.286289: step: 388/526, loss: 0.006999206729233265
2023-01-23 02:06:12.427504: step: 392/526, loss: 0.039727017283439636
2023-01-23 02:06:13.585965: step: 396/526, loss: 0.09039411693811417
2023-01-23 02:06:14.708141: step: 400/526, loss: 0.00019559860811568797
2023-01-23 02:06:15.832645: step: 404/526, loss: 0.02323608286678791
2023-01-23 02:06:16.938083: step: 408/526, loss: 0.006137060932815075
2023-01-23 02:06:18.114783: step: 412/526, loss: 0.03086681477725506
2023-01-23 02:06:19.223361: step: 416/526, loss: 0.07261276245117188
2023-01-23 02:06:20.353002: step: 420/526, loss: 0.0013107298873364925
2023-01-23 02:06:21.480634: step: 424/526, loss: 0.000828647636808455
2023-01-23 02:06:22.601936: step: 428/526, loss: 0.011659479700028896
2023-01-23 02:06:23.727657: step: 432/526, loss: 0.06942576915025711
2023-01-23 02:06:24.874792: step: 436/526, loss: 0.00394439697265625
2023-01-23 02:06:26.006980: step: 440/526, loss: 0.0008063316345214844
2023-01-23 02:06:27.163308: step: 444/526, loss: 0.009787273593246937
2023-01-23 02:06:28.285834: step: 448/526, loss: 0.1708083152770996
2023-01-23 02:06:29.415017: step: 452/526, loss: 0.00014190674119163305
2023-01-23 02:06:30.571010: step: 456/526, loss: 0.01170959509909153
2023-01-23 02:06:31.723412: step: 460/526, loss: 0.10126066207885742
2023-01-23 02:06:32.871042: step: 464/526, loss: 0.014204979874193668
2023-01-23 02:06:34.024041: step: 468/526, loss: 0.14807739853858948
2023-01-23 02:06:35.147797: step: 472/526, loss: 0.0011466980213299394
2023-01-23 02:06:36.264635: step: 476/526, loss: 0.013512516394257545
2023-01-23 02:06:37.387430: step: 480/526, loss: 0.007953834719955921
2023-01-23 02:06:38.497490: step: 484/526, loss: 0.006524467375129461
2023-01-23 02:06:39.656621: step: 488/526, loss: 0.0019288540352135897
2023-01-23 02:06:40.800326: step: 492/526, loss: 0.0006891250959597528
2023-01-23 02:06:41.911624: step: 496/526, loss: 0.04015376791357994
2023-01-23 02:06:43.026194: step: 500/526, loss: 0.6664199829101562
2023-01-23 02:06:44.162050: step: 504/526, loss: 0.040895987302064896
2023-01-23 02:06:45.307145: step: 508/526, loss: 0.050680164247751236
2023-01-23 02:06:46.442074: step: 512/526, loss: 0.014007186517119408
2023-01-23 02:06:47.585907: step: 516/526, loss: 0.00402679480612278
2023-01-23 02:06:48.712382: step: 520/526, loss: 0.04378996044397354
2023-01-23 02:06:49.840203: step: 524/526, loss: 0.0006673813331872225
2023-01-23 02:06:50.970969: step: 528/526, loss: 0.0032178880646824837
2023-01-23 02:06:52.119454: step: 532/526, loss: 0.008038091473281384
2023-01-23 02:06:53.263739: step: 536/526, loss: 0.009963417425751686
2023-01-23 02:06:54.373088: step: 540/526, loss: 0.0005750656127929688
2023-01-23 02:06:55.525357: step: 544/526, loss: 0.1334766298532486
2023-01-23 02:06:56.661980: step: 548/526, loss: 0.00023899078951217234
2023-01-23 02:06:57.802716: step: 552/526, loss: 0.09313793480396271
2023-01-23 02:06:58.938588: step: 556/526, loss: 0.07736358791589737
2023-01-23 02:07:00.046201: step: 560/526, loss: 0.013270950876176357
2023-01-23 02:07:01.161201: step: 564/526, loss: 0.08632683753967285
2023-01-23 02:07:02.292685: step: 568/526, loss: 0.055107977241277695
2023-01-23 02:07:03.420098: step: 572/526, loss: 0.0077197072096168995
2023-01-23 02:07:04.568607: step: 576/526, loss: 0.05015640705823898
2023-01-23 02:07:05.708676: step: 580/526, loss: 0.00459213275462389
2023-01-23 02:07:06.823146: step: 584/526, loss: 0.0058259014040231705
2023-01-23 02:07:07.940529: step: 588/526, loss: 0.019400596618652344
2023-01-23 02:07:09.102658: step: 592/526, loss: 0.0005949020269326866
2023-01-23 02:07:10.224230: step: 596/526, loss: 0.07880210876464844
2023-01-23 02:07:11.350422: step: 600/526, loss: 0.05722007900476456
2023-01-23 02:07:12.479823: step: 604/526, loss: 0.01571188122034073
2023-01-23 02:07:13.640141: step: 608/526, loss: 0.012703800573945045
2023-01-23 02:07:14.749960: step: 612/526, loss: 0.15576894581317902
2023-01-23 02:07:15.893014: step: 616/526, loss: 0.024607468396425247
2023-01-23 02:07:16.999743: step: 620/526, loss: 0.02085094526410103
2023-01-23 02:07:18.126383: step: 624/526, loss: 0.005806922912597656
2023-01-23 02:07:19.233950: step: 628/526, loss: 0.024089815095067024
2023-01-23 02:07:20.354125: step: 632/526, loss: 0.05824146419763565
2023-01-23 02:07:21.511266: step: 636/526, loss: 0.016150474548339844
2023-01-23 02:07:22.642826: step: 640/526, loss: 0.01067895907908678
2023-01-23 02:07:23.769694: step: 644/526, loss: 0.06559982150793076
2023-01-23 02:07:24.894452: step: 648/526, loss: 0.0009349823230877519
2023-01-23 02:07:26.024576: step: 652/526, loss: 0.0025187493301928043
2023-01-23 02:07:27.173951: step: 656/526, loss: 0.02749490737915039
2023-01-23 02:07:28.316323: step: 660/526, loss: 0.010251045227050781
2023-01-23 02:07:29.427302: step: 664/526, loss: 0.03259697183966637
2023-01-23 02:07:30.557702: step: 668/526, loss: 0.19118356704711914
2023-01-23 02:07:31.695628: step: 672/526, loss: 0.00396041851490736
2023-01-23 02:07:32.826225: step: 676/526, loss: 0.034720804542303085
2023-01-23 02:07:33.967356: step: 680/526, loss: 0.01591358333826065
2023-01-23 02:07:35.075328: step: 684/526, loss: 0.4573030471801758
2023-01-23 02:07:36.195777: step: 688/526, loss: 0.017461776733398438
2023-01-23 02:07:37.388397: step: 692/526, loss: 0.030918169766664505
2023-01-23 02:07:38.528409: step: 696/526, loss: 0.003731679869815707
2023-01-23 02:07:39.653249: step: 700/526, loss: 0.017079640179872513
2023-01-23 02:07:40.811356: step: 704/526, loss: 0.03582973778247833
2023-01-23 02:07:41.932506: step: 708/526, loss: 0.003549480577930808
2023-01-23 02:07:43.109825: step: 712/526, loss: 0.04098358005285263
2023-01-23 02:07:44.246141: step: 716/526, loss: 0.02720518223941326
2023-01-23 02:07:45.378505: step: 720/526, loss: 0.010844326578080654
2023-01-23 02:07:46.536835: step: 724/526, loss: 0.06526069343090057
2023-01-23 02:07:47.654611: step: 728/526, loss: 0.0010103702079504728
2023-01-23 02:07:48.810079: step: 732/526, loss: 0.013023662380874157
2023-01-23 02:07:49.928253: step: 736/526, loss: 0.10436000674962997
2023-01-23 02:07:51.057806: step: 740/526, loss: 0.018746376037597656
2023-01-23 02:07:52.194684: step: 744/526, loss: 0.010208320803940296
2023-01-23 02:07:53.356018: step: 748/526, loss: 0.03430977091193199
2023-01-23 02:07:54.506260: step: 752/526, loss: 0.011287307366728783
2023-01-23 02:07:55.636011: step: 756/526, loss: 0.0008378028869628906
2023-01-23 02:07:56.760027: step: 760/526, loss: 0.15765905380249023
2023-01-23 02:07:57.919310: step: 764/526, loss: 0.07822628319263458
2023-01-23 02:07:59.045708: step: 768/526, loss: 0.0011303424835205078
2023-01-23 02:08:00.207178: step: 772/526, loss: 0.009031486697494984
2023-01-23 02:08:01.343581: step: 776/526, loss: 0.01705322228372097
2023-01-23 02:08:02.509659: step: 780/526, loss: 0.7453729510307312
2023-01-23 02:08:03.634931: step: 784/526, loss: 0.03326597064733505
2023-01-23 02:08:04.753695: step: 788/526, loss: 0.018526364117860794
2023-01-23 02:08:05.876523: step: 792/526, loss: 0.01178207341581583
2023-01-23 02:08:07.045197: step: 796/526, loss: 0.0231457706540823
2023-01-23 02:08:08.165329: step: 800/526, loss: 9.384155418956652e-05
2023-01-23 02:08:09.310401: step: 804/526, loss: 0.009880256839096546
2023-01-23 02:08:10.448578: step: 808/526, loss: 0.021640969440340996
2023-01-23 02:08:11.595708: step: 812/526, loss: 0.010782241821289062
2023-01-23 02:08:12.731022: step: 816/526, loss: 0.003671550890430808
2023-01-23 02:08:13.865762: step: 820/526, loss: 0.006351756863296032
2023-01-23 02:08:15.015920: step: 824/526, loss: 0.0023437500931322575
2023-01-23 02:08:16.163797: step: 828/526, loss: 0.005060291383415461
2023-01-23 02:08:17.321630: step: 832/526, loss: 0.014135456643998623
2023-01-23 02:08:18.458825: step: 836/526, loss: 0.04877214506268501
2023-01-23 02:08:19.585989: step: 840/526, loss: 0.009589672088623047
2023-01-23 02:08:20.746040: step: 844/526, loss: 0.012925434857606888
2023-01-23 02:08:21.860107: step: 848/526, loss: 0.006515598390251398
2023-01-23 02:08:23.017552: step: 852/526, loss: 0.06548157334327698
2023-01-23 02:08:24.161841: step: 856/526, loss: 0.023426055908203125
2023-01-23 02:08:25.289580: step: 860/526, loss: 0.006204700563102961
2023-01-23 02:08:26.477004: step: 864/526, loss: 0.0011611938243731856
2023-01-23 02:08:27.612415: step: 868/526, loss: 0.012956619262695312
2023-01-23 02:08:28.747055: step: 872/526, loss: 0.026856709271669388
2023-01-23 02:08:29.863211: step: 876/526, loss: 0.0063949585892260075
2023-01-23 02:08:31.002483: step: 880/526, loss: 9.298325312556699e-05
2023-01-23 02:08:32.128430: step: 884/526, loss: 0.046695709228515625
2023-01-23 02:08:33.251195: step: 888/526, loss: 0.003896331647410989
2023-01-23 02:08:34.383169: step: 892/526, loss: 0.02193247154355049
2023-01-23 02:08:35.568031: step: 896/526, loss: 0.04974813759326935
2023-01-23 02:08:36.728285: step: 900/526, loss: 0.026309967041015625
2023-01-23 02:08:37.855260: step: 904/526, loss: 0.021569253876805305
2023-01-23 02:08:38.990714: step: 908/526, loss: 0.017328644171357155
2023-01-23 02:08:40.138592: step: 912/526, loss: 0.05048827826976776
2023-01-23 02:08:41.257061: step: 916/526, loss: 0.03735008090734482
2023-01-23 02:08:42.404934: step: 920/526, loss: 0.020472144708037376
2023-01-23 02:08:43.600101: step: 924/526, loss: 0.0218382366001606
2023-01-23 02:08:44.723544: step: 928/526, loss: 0.07334079593420029
2023-01-23 02:08:45.859682: step: 932/526, loss: 0.07878141105175018
2023-01-23 02:08:46.998335: step: 936/526, loss: 0.0017305375076830387
2023-01-23 02:08:48.177867: step: 940/526, loss: 0.002079582307487726
2023-01-23 02:08:49.303640: step: 944/526, loss: 0.0004038810729980469
2023-01-23 02:08:50.422502: step: 948/526, loss: 0.025563621893525124
2023-01-23 02:08:51.574815: step: 952/526, loss: 0.0032917975913733244
2023-01-23 02:08:52.749734: step: 956/526, loss: 0.005711269564926624
2023-01-23 02:08:53.921926: step: 960/526, loss: 0.042267415672540665
2023-01-23 02:08:55.057880: step: 964/526, loss: 0.06126260757446289
2023-01-23 02:08:56.186527: step: 968/526, loss: 0.11003799736499786
2023-01-23 02:08:57.322874: step: 972/526, loss: 0.054376937448978424
2023-01-23 02:08:58.474031: step: 976/526, loss: 0.324615478515625
2023-01-23 02:08:59.624219: step: 980/526, loss: 0.011299324221909046
2023-01-23 02:09:00.770442: step: 984/526, loss: 0.04791727289557457
2023-01-23 02:09:01.869947: step: 988/526, loss: 0.03502492979168892
2023-01-23 02:09:03.026030: step: 992/526, loss: 0.05111370235681534
2023-01-23 02:09:04.182861: step: 996/526, loss: 0.012689972296357155
2023-01-23 02:09:05.305689: step: 1000/526, loss: 0.01204681396484375
2023-01-23 02:09:06.425747: step: 1004/526, loss: 0.017117274925112724
2023-01-23 02:09:07.571311: step: 1008/526, loss: 0.055908337235450745
2023-01-23 02:09:08.703393: step: 1012/526, loss: 0.007498741149902344
2023-01-23 02:09:09.844757: step: 1016/526, loss: 0.009439468383789062
2023-01-23 02:09:10.962642: step: 1020/526, loss: 0.00013599396334029734
2023-01-23 02:09:12.121224: step: 1024/526, loss: 0.0611303336918354
2023-01-23 02:09:13.294260: step: 1028/526, loss: 0.08583197742700577
2023-01-23 02:09:14.464684: step: 1032/526, loss: 0.004662561230361462
2023-01-23 02:09:15.591507: step: 1036/526, loss: 0.017775440588593483
2023-01-23 02:09:16.708902: step: 1040/526, loss: 0.02116527408361435
2023-01-23 02:09:17.843543: step: 1044/526, loss: 0.02670269086956978
2023-01-23 02:09:18.972307: step: 1048/526, loss: 0.00222358712926507
2023-01-23 02:09:20.104456: step: 1052/526, loss: 0.03948249667882919
2023-01-23 02:09:21.244048: step: 1056/526, loss: 0.0013480663765221834
2023-01-23 02:09:22.373736: step: 1060/526, loss: 0.019669342786073685
2023-01-23 02:09:23.501516: step: 1064/526, loss: 0.013860797509551048
2023-01-23 02:09:24.672798: step: 1068/526, loss: 0.006151676177978516
2023-01-23 02:09:25.823479: step: 1072/526, loss: 0.14107413589954376
2023-01-23 02:09:26.961990: step: 1076/526, loss: 0.04501352459192276
2023-01-23 02:09:28.102710: step: 1080/526, loss: 0.0010957717895507812
2023-01-23 02:09:29.229790: step: 1084/526, loss: 0.040661975741386414
2023-01-23 02:09:30.365201: step: 1088/526, loss: 0.004996109288185835
2023-01-23 02:09:31.501412: step: 1092/526, loss: 0.017347240820527077
2023-01-23 02:09:32.662203: step: 1096/526, loss: 0.0011172294616699219
2023-01-23 02:09:33.770235: step: 1100/526, loss: 0.04806967079639435
2023-01-23 02:09:34.907340: step: 1104/526, loss: 0.11985526978969574
2023-01-23 02:09:36.051449: step: 1108/526, loss: 0.010937238112092018
2023-01-23 02:09:37.149454: step: 1112/526, loss: 0.07239770889282227
2023-01-23 02:09:38.276486: step: 1116/526, loss: 0.03562898933887482
2023-01-23 02:09:39.387766: step: 1120/526, loss: 0.04157219082117081
2023-01-23 02:09:40.550017: step: 1124/526, loss: 0.010804176330566406
2023-01-23 02:09:41.664897: step: 1128/526, loss: 0.020627882331609726
2023-01-23 02:09:42.801074: step: 1132/526, loss: 0.005881595890969038
2023-01-23 02:09:43.946917: step: 1136/526, loss: 0.015665389597415924
2023-01-23 02:09:45.073885: step: 1140/526, loss: 0.001398372696712613
2023-01-23 02:09:46.284977: step: 1144/526, loss: 0.11602059006690979
2023-01-23 02:09:47.427373: step: 1148/526, loss: 0.019445039331912994
2023-01-23 02:09:48.533642: step: 1152/526, loss: 0.0007688045734539628
2023-01-23 02:09:49.662323: step: 1156/526, loss: 0.03306932747364044
2023-01-23 02:09:50.800790: step: 1160/526, loss: 0.003934717271476984
2023-01-23 02:09:51.944718: step: 1164/526, loss: 0.009060859680175781
2023-01-23 02:09:53.102772: step: 1168/526, loss: 0.015883494168519974
2023-01-23 02:09:54.220773: step: 1172/526, loss: 0.06717921048402786
2023-01-23 02:09:55.352259: step: 1176/526, loss: 0.0018405914306640625
2023-01-23 02:09:56.480435: step: 1180/526, loss: 0.0010327368509024382
2023-01-23 02:09:57.605231: step: 1184/526, loss: 0.022007416933774948
2023-01-23 02:09:58.751830: step: 1188/526, loss: 0.020312214270234108
2023-01-23 02:09:59.925114: step: 1192/526, loss: 0.08988456428050995
2023-01-23 02:10:01.046194: step: 1196/526, loss: 0.015948869287967682
2023-01-23 02:10:02.167989: step: 1200/526, loss: 0.03337812423706055
2023-01-23 02:10:03.304335: step: 1204/526, loss: 0.007315540686249733
2023-01-23 02:10:04.452199: step: 1208/526, loss: 0.011577225290238857
2023-01-23 02:10:05.597732: step: 1212/526, loss: 0.008961677551269531
2023-01-23 02:10:06.735264: step: 1216/526, loss: 0.007487487979233265
2023-01-23 02:10:07.848045: step: 1220/526, loss: 0.006799888797104359
2023-01-23 02:10:08.981532: step: 1224/526, loss: 0.0004146576102357358
2023-01-23 02:10:10.111302: step: 1228/526, loss: 0.06662826985120773
2023-01-23 02:10:11.228134: step: 1232/526, loss: 0.013881397433578968
2023-01-23 02:10:12.381668: step: 1236/526, loss: 0.07209930568933487
2023-01-23 02:10:13.494175: step: 1240/526, loss: 0.0018220484489575028
2023-01-23 02:10:14.636703: step: 1244/526, loss: 0.01940889284014702
2023-01-23 02:10:15.782638: step: 1248/526, loss: 0.025511646643280983
2023-01-23 02:10:16.935055: step: 1252/526, loss: 0.00012807846360374242
2023-01-23 02:10:18.060542: step: 1256/526, loss: 0.024041080847382545
2023-01-23 02:10:19.173603: step: 1260/526, loss: 0.007365561090409756
2023-01-23 02:10:20.285384: step: 1264/526, loss: 0.36412307620048523
2023-01-23 02:10:21.419187: step: 1268/526, loss: 0.034429360181093216
2023-01-23 02:10:22.555587: step: 1272/526, loss: 0.010556411929428577
2023-01-23 02:10:23.706071: step: 1276/526, loss: 0.020966148003935814
2023-01-23 02:10:24.836423: step: 1280/526, loss: 0.0007737636333331466
2023-01-23 02:10:25.984392: step: 1284/526, loss: 0.0020576000679284334
2023-01-23 02:10:27.118700: step: 1288/526, loss: 0.05202013999223709
2023-01-23 02:10:28.278818: step: 1292/526, loss: 0.04629163816571236
2023-01-23 02:10:29.427297: step: 1296/526, loss: 0.04239015281200409
2023-01-23 02:10:30.588875: step: 1300/526, loss: 0.027730464935302734
2023-01-23 02:10:31.734683: step: 1304/526, loss: 0.0045299530029296875
2023-01-23 02:10:32.873397: step: 1308/526, loss: 0.05006713792681694
2023-01-23 02:10:34.030396: step: 1312/526, loss: 0.009278487414121628
2023-01-23 02:10:35.145108: step: 1316/526, loss: 0.01439080573618412
2023-01-23 02:10:36.293058: step: 1320/526, loss: 0.010241151787340641
2023-01-23 02:10:37.438132: step: 1324/526, loss: 0.017360782250761986
2023-01-23 02:10:38.563245: step: 1328/526, loss: 0.02648625522851944
2023-01-23 02:10:39.687434: step: 1332/526, loss: 0.014238834381103516
2023-01-23 02:10:40.824427: step: 1336/526, loss: 0.048409465700387955
2023-01-23 02:10:41.993887: step: 1340/526, loss: 0.02427687868475914
2023-01-23 02:10:43.131342: step: 1344/526, loss: 0.02034778520464897
2023-01-23 02:10:44.279313: step: 1348/526, loss: 0.02927885204553604
2023-01-23 02:10:45.440317: step: 1352/526, loss: 0.059866905212402344
2023-01-23 02:10:46.570258: step: 1356/526, loss: 0.03551807254552841
2023-01-23 02:10:47.701395: step: 1360/526, loss: 0.006972646806389093
2023-01-23 02:10:48.835033: step: 1364/526, loss: 0.01871929131448269
2023-01-23 02:10:49.965026: step: 1368/526, loss: 0.014097404666244984
2023-01-23 02:10:51.103327: step: 1372/526, loss: 0.017656372860074043
2023-01-23 02:10:52.241908: step: 1376/526, loss: 0.0036301612854003906
2023-01-23 02:10:53.371778: step: 1380/526, loss: 0.004176235292106867
2023-01-23 02:10:54.496191: step: 1384/526, loss: 0.004494952969253063
2023-01-23 02:10:55.629337: step: 1388/526, loss: 0.008702421560883522
2023-01-23 02:10:56.769480: step: 1392/526, loss: 0.007414627354592085
2023-01-23 02:10:57.948466: step: 1396/526, loss: 0.0048385621048510075
2023-01-23 02:10:59.094133: step: 1400/526, loss: 0.011631202884018421
2023-01-23 02:11:00.207326: step: 1404/526, loss: 0.0345911979675293
2023-01-23 02:11:01.339315: step: 1408/526, loss: 0.004528164863586426
2023-01-23 02:11:02.499046: step: 1412/526, loss: 0.005847168155014515
2023-01-23 02:11:03.630223: step: 1416/526, loss: 0.005957103334367275
2023-01-23 02:11:04.741072: step: 1420/526, loss: 0.03772792965173721
2023-01-23 02:11:05.850832: step: 1424/526, loss: 0.0217269416898489
2023-01-23 02:11:07.013308: step: 1428/526, loss: 0.051311589777469635
2023-01-23 02:11:08.152121: step: 1432/526, loss: 0.08636932075023651
2023-01-23 02:11:09.266573: step: 1436/526, loss: 0.029451416805386543
2023-01-23 02:11:10.390437: step: 1440/526, loss: 0.028063582256436348
2023-01-23 02:11:11.537966: step: 1444/526, loss: 0.009215736761689186
2023-01-23 02:11:12.665936: step: 1448/526, loss: 0.027518033981323242
2023-01-23 02:11:13.818349: step: 1452/526, loss: 0.007077121641486883
2023-01-23 02:11:14.961654: step: 1456/526, loss: 0.025943756103515625
2023-01-23 02:11:16.128560: step: 1460/526, loss: 0.06484813988208771
2023-01-23 02:11:17.269158: step: 1464/526, loss: 0.023143388330936432
2023-01-23 02:11:18.422598: step: 1468/526, loss: 0.021740246564149857
2023-01-23 02:11:19.568056: step: 1472/526, loss: 0.006299733649939299
2023-01-23 02:11:20.725535: step: 1476/526, loss: 0.1377815157175064
2023-01-23 02:11:21.847341: step: 1480/526, loss: 0.06675568222999573
2023-01-23 02:11:22.978948: step: 1484/526, loss: 0.02924194373190403
2023-01-23 02:11:24.101311: step: 1488/526, loss: 0.005580043885856867
2023-01-23 02:11:25.226502: step: 1492/526, loss: 0.02570180967450142
2023-01-23 02:11:26.350677: step: 1496/526, loss: 0.07973155379295349
2023-01-23 02:11:27.474424: step: 1500/526, loss: 0.016829872503876686
2023-01-23 02:11:28.615407: step: 1504/526, loss: 0.03310227394104004
2023-01-23 02:11:29.734848: step: 1508/526, loss: 0.011465931311249733
2023-01-23 02:11:30.864801: step: 1512/526, loss: 0.03176116943359375
2023-01-23 02:11:31.997459: step: 1516/526, loss: 0.06437158584594727
2023-01-23 02:11:33.115019: step: 1520/526, loss: 0.033135414123535156
2023-01-23 02:11:34.262528: step: 1524/526, loss: 0.7013838887214661
2023-01-23 02:11:35.436786: step: 1528/526, loss: 0.06686048954725266
2023-01-23 02:11:36.560504: step: 1532/526, loss: 0.04190211370587349
2023-01-23 02:11:37.677028: step: 1536/526, loss: 0.03224353864789009
2023-01-23 02:11:38.798690: step: 1540/526, loss: 0.15404310822486877
2023-01-23 02:11:39.958877: step: 1544/526, loss: 0.004715061280876398
2023-01-23 02:11:41.102923: step: 1548/526, loss: 0.055117275565862656
2023-01-23 02:11:42.249359: step: 1552/526, loss: 0.1209026351571083
2023-01-23 02:11:43.378079: step: 1556/526, loss: 0.031272079795598984
2023-01-23 02:11:44.558058: step: 1560/526, loss: 0.017296981066465378
2023-01-23 02:11:45.692155: step: 1564/526, loss: 0.558657169342041
2023-01-23 02:11:46.817342: step: 1568/526, loss: 0.003933954518288374
2023-01-23 02:11:47.995045: step: 1572/526, loss: 0.013286590576171875
2023-01-23 02:11:49.133965: step: 1576/526, loss: 0.009356856346130371
2023-01-23 02:11:50.290155: step: 1580/526, loss: 0.026461409404873848
2023-01-23 02:11:51.447840: step: 1584/526, loss: 0.0025741576682776213
2023-01-23 02:11:52.575382: step: 1588/526, loss: 0.0011539459228515625
2023-01-23 02:11:53.679001: step: 1592/526, loss: 0.0022188187576830387
2023-01-23 02:11:54.798941: step: 1596/526, loss: 0.002547240350395441
2023-01-23 02:11:55.946612: step: 1600/526, loss: 0.002344417618587613
2023-01-23 02:11:57.074782: step: 1604/526, loss: 0.051453590393066406
2023-01-23 02:11:58.220802: step: 1608/526, loss: 0.024554062634706497
2023-01-23 02:11:59.354783: step: 1612/526, loss: 0.00838475301861763
2023-01-23 02:12:00.504322: step: 1616/526, loss: 0.02063126675784588
2023-01-23 02:12:01.622713: step: 1620/526, loss: 0.009009934030473232
2023-01-23 02:12:02.769374: step: 1624/526, loss: 0.026799678802490234
2023-01-23 02:12:03.881901: step: 1628/526, loss: 0.05049638822674751
2023-01-23 02:12:05.043122: step: 1632/526, loss: 0.0020748137030750513
2023-01-23 02:12:06.200966: step: 1636/526, loss: -3.004073732881807e-06
2023-01-23 02:12:07.340081: step: 1640/526, loss: 0.07907982170581818
2023-01-23 02:12:08.467156: step: 1644/526, loss: 0.07097997516393661
2023-01-23 02:12:09.593022: step: 1648/526, loss: 0.062343597412109375
2023-01-23 02:12:10.719160: step: 1652/526, loss: 0.09758994728326797
2023-01-23 02:12:11.857317: step: 1656/526, loss: 0.11636219918727875
2023-01-23 02:12:13.008914: step: 1660/526, loss: 0.009195208549499512
2023-01-23 02:12:14.136549: step: 1664/526, loss: 0.0028181076049804688
2023-01-23 02:12:15.286000: step: 1668/526, loss: 0.0558408759534359
2023-01-23 02:12:16.396471: step: 1672/526, loss: 0.0030951977241784334
2023-01-23 02:12:17.510145: step: 1676/526, loss: 0.0024912357330322266
2023-01-23 02:12:18.630570: step: 1680/526, loss: 0.03528556600213051
2023-01-23 02:12:19.741107: step: 1684/526, loss: 0.04412698745727539
2023-01-23 02:12:20.882055: step: 1688/526, loss: 0.010465907864272594
2023-01-23 02:12:22.022666: step: 1692/526, loss: 0.012494850903749466
2023-01-23 02:12:23.169805: step: 1696/526, loss: 0.03230543062090874
2023-01-23 02:12:24.304193: step: 1700/526, loss: 0.005598688032478094
2023-01-23 02:12:25.454566: step: 1704/526, loss: 0.5719591379165649
2023-01-23 02:12:26.622163: step: 1708/526, loss: 0.00456085242331028
2023-01-23 02:12:27.770122: step: 1712/526, loss: 0.002419757889583707
2023-01-23 02:12:28.922918: step: 1716/526, loss: 0.003182315733283758
2023-01-23 02:12:30.009231: step: 1720/526, loss: 0.004273462574928999
2023-01-23 02:12:31.138576: step: 1724/526, loss: 0.08217382431030273
2023-01-23 02:12:32.281379: step: 1728/526, loss: 0.027550602331757545
2023-01-23 02:12:33.406765: step: 1732/526, loss: 0.04347586631774902
2023-01-23 02:12:34.541352: step: 1736/526, loss: 0.07771559059619904
2023-01-23 02:12:35.652948: step: 1740/526, loss: 0.013586331158876419
2023-01-23 02:12:36.788017: step: 1744/526, loss: 0.0018961429595947266
2023-01-23 02:12:37.915227: step: 1748/526, loss: 0.005118942353874445
2023-01-23 02:12:39.031022: step: 1752/526, loss: 0.026560688391327858
2023-01-23 02:12:40.140813: step: 1756/526, loss: 0.0005363464588299394
2023-01-23 02:12:41.270663: step: 1760/526, loss: 0.022364521399140358
2023-01-23 02:12:42.432794: step: 1764/526, loss: 0.018175601959228516
2023-01-23 02:12:43.602257: step: 1768/526, loss: 0.005443144124001265
2023-01-23 02:12:44.723285: step: 1772/526, loss: 0.01248016394674778
2023-01-23 02:12:45.870290: step: 1776/526, loss: 0.044884875416755676
2023-01-23 02:12:47.003821: step: 1780/526, loss: 0.01636476442217827
2023-01-23 02:12:48.175799: step: 1784/526, loss: 0.028263092041015625
2023-01-23 02:12:49.328614: step: 1788/526, loss: 0.03206014633178711
2023-01-23 02:12:50.460289: step: 1792/526, loss: 0.04886217415332794
2023-01-23 02:12:51.600228: step: 1796/526, loss: 0.0009314537164755166
2023-01-23 02:12:52.748884: step: 1800/526, loss: 0.047337912023067474
2023-01-23 02:12:53.887926: step: 1804/526, loss: 0.00031490327091887593
2023-01-23 02:12:55.044165: step: 1808/526, loss: 0.030181502923369408
2023-01-23 02:12:56.198513: step: 1812/526, loss: 0.018903352320194244
2023-01-23 02:12:57.332749: step: 1816/526, loss: 0.062339916825294495
2023-01-23 02:12:58.453507: step: 1820/526, loss: 0.0068701268173754215
2023-01-23 02:12:59.610107: step: 1824/526, loss: 0.03403320536017418
2023-01-23 02:13:00.719559: step: 1828/526, loss: 0.010880088433623314
2023-01-23 02:13:01.868210: step: 1832/526, loss: 0.017440224066376686
2023-01-23 02:13:02.983600: step: 1836/526, loss: 0.09154100716114044
2023-01-23 02:13:04.113736: step: 1840/526, loss: 0.07327929139137268
2023-01-23 02:13:05.240504: step: 1844/526, loss: 0.2678384780883789
2023-01-23 02:13:06.381449: step: 1848/526, loss: 0.005862140562385321
2023-01-23 02:13:07.510162: step: 1852/526, loss: 0.06640391796827316
2023-01-23 02:13:08.677819: step: 1856/526, loss: 0.14631310105323792
2023-01-23 02:13:09.833176: step: 1860/526, loss: 0.006291770841926336
2023-01-23 02:13:10.984310: step: 1864/526, loss: 0.02634124644100666
2023-01-23 02:13:12.110537: step: 1868/526, loss: 0.006655740551650524
2023-01-23 02:13:13.252622: step: 1872/526, loss: 0.035736940801143646
2023-01-23 02:13:14.381992: step: 1876/526, loss: 0.3259812295436859
2023-01-23 02:13:15.511144: step: 1880/526, loss: 0.045960187911987305
2023-01-23 02:13:16.683430: step: 1884/526, loss: 0.04650431126356125
2023-01-23 02:13:17.871530: step: 1888/526, loss: 0.006530856713652611
2023-01-23 02:13:18.981780: step: 1892/526, loss: 0.06782494485378265
2023-01-23 02:13:20.141176: step: 1896/526, loss: 0.005308437626808882
2023-01-23 02:13:21.311332: step: 1900/526, loss: 0.02348356321454048
2023-01-23 02:13:22.430914: step: 1904/526, loss: 0.014668083749711514
2023-01-23 02:13:23.549292: step: 1908/526, loss: 0.01696472242474556
2023-01-23 02:13:24.692637: step: 1912/526, loss: 0.020378874614834785
2023-01-23 02:13:25.816917: step: 1916/526, loss: 0.0008379936334677041
2023-01-23 02:13:26.944037: step: 1920/526, loss: 0.026038646697998047
2023-01-23 02:13:28.070480: step: 1924/526, loss: 0.026744937524199486
2023-01-23 02:13:29.220813: step: 1928/526, loss: 0.013733197003602982
2023-01-23 02:13:30.344104: step: 1932/526, loss: 0.0059073446318507195
2023-01-23 02:13:31.473480: step: 1936/526, loss: 0.16801396012306213
2023-01-23 02:13:32.602998: step: 1940/526, loss: 0.04417915269732475
2023-01-23 02:13:33.732798: step: 1944/526, loss: 0.04421444237232208
2023-01-23 02:13:34.849983: step: 1948/526, loss: 0.004235363099724054
2023-01-23 02:13:35.982689: step: 1952/526, loss: 0.003881836077198386
2023-01-23 02:13:37.102197: step: 1956/526, loss: 0.0014799118507653475
2023-01-23 02:13:38.227407: step: 1960/526, loss: 0.01616344414651394
2023-01-23 02:13:39.365923: step: 1964/526, loss: 0.027036476880311966
2023-01-23 02:13:40.511012: step: 1968/526, loss: 0.023020554333925247
2023-01-23 02:13:41.664298: step: 1972/526, loss: 0.027962446212768555
2023-01-23 02:13:42.796411: step: 1976/526, loss: 0.007340335752815008
2023-01-23 02:13:44.031380: step: 1980/526, loss: 0.007399177644401789
2023-01-23 02:13:45.163748: step: 1984/526, loss: 0.03774986416101456
2023-01-23 02:13:46.291615: step: 1988/526, loss: 0.027124499902129173
2023-01-23 02:13:47.422376: step: 1992/526, loss: 0.022027302533388138
2023-01-23 02:13:48.608428: step: 1996/526, loss: 0.009863234125077724
2023-01-23 02:13:49.751001: step: 2000/526, loss: 0.013858986087143421
2023-01-23 02:13:50.881219: step: 2004/526, loss: 0.008997059427201748
2023-01-23 02:13:51.993915: step: 2008/526, loss: 0.02874666266143322
2023-01-23 02:13:53.152174: step: 2012/526, loss: 0.01140441931784153
2023-01-23 02:13:54.284104: step: 2016/526, loss: 0.0008622646564617753
2023-01-23 02:13:55.436261: step: 2020/526, loss: 0.0729396864771843
2023-01-23 02:13:56.583620: step: 2024/526, loss: 0.016897058114409447
2023-01-23 02:13:57.738036: step: 2028/526, loss: 0.0374792106449604
2023-01-23 02:13:58.863195: step: 2032/526, loss: 0.010707378387451172
2023-01-23 02:14:00.003077: step: 2036/526, loss: 0.003799057099968195
2023-01-23 02:14:01.121113: step: 2040/526, loss: 0.11505670845508575
2023-01-23 02:14:02.252457: step: 2044/526, loss: 0.025504684075713158
2023-01-23 02:14:03.381720: step: 2048/526, loss: 0.00025835036649368703
2023-01-23 02:14:04.534192: step: 2052/526, loss: 0.019388772547245026
2023-01-23 02:14:05.684468: step: 2056/526, loss: 0.35503169894218445
2023-01-23 02:14:06.849876: step: 2060/526, loss: 0.027684496715664864
2023-01-23 02:14:07.971773: step: 2064/526, loss: 0.0491364486515522
2023-01-23 02:14:09.098442: step: 2068/526, loss: 0.006453514099121094
2023-01-23 02:14:10.249405: step: 2072/526, loss: 0.00449900608509779
2023-01-23 02:14:11.367567: step: 2076/526, loss: 0.031456850469112396
2023-01-23 02:14:12.519826: step: 2080/526, loss: 0.0054968358017504215
2023-01-23 02:14:13.656698: step: 2084/526, loss: 0.01752195507287979
2023-01-23 02:14:14.805572: step: 2088/526, loss: 0.016249418258666992
2023-01-23 02:14:15.951715: step: 2092/526, loss: 0.056441307067871094
2023-01-23 02:14:17.086172: step: 2096/526, loss: 0.020601511001586914
2023-01-23 02:14:18.194573: step: 2100/526, loss: 0.018584443256258965
2023-01-23 02:14:19.333285: step: 2104/526, loss: 0.002734279725700617
==================================================
Loss: 0.039
--------------------
Dev: {'event': {'p': 0.5861386138613861, 'r': 0.7882822902796272, 'f1': 0.6723452583759226}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Test: {'event': {'p': 0.6248436848686952, 'r': 0.7823590814196242, 'f1': 0.6947856315179607}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Chinese: {'event': {'p': 0.5813953488372093, 'r': 0.9259259259259259, 'f1': 0.7142857142857142}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Korean: {'event': {'p': 0.5818181818181818, 'r': 0.5079365079365079, 'f1': 0.5423728813559321}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Russian: {'event': {'p': 0.4888888888888889, 'r': 0.6111111111111112, 'f1': 0.5432098765432098}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6389811738648948, 'r': 0.7683089214380826, 'f1': 0.6977025392986699}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Eng Test for Chinese: {'event': {'p': 0.6328626444159179, 'r': 0.7719206680584552, 'f1': 0.6955090524335763}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Sample Chinese: {'event': {'p': 0.6282051282051282, 'r': 0.9074074074074074, 'f1': 0.7424242424242423}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6257995735607675, 'r': 0.7816245006657789, 'f1': 0.6950858496151568}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Eng Test for Korean: {'event': {'p': 0.623113410952997, 'r': 0.7541753653444676, 'f1': 0.6824085005903188}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Sample Korean: {'event': {'p': 0.7446808510638298, 'r': 0.5555555555555556, 'f1': 0.6363636363636364}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6217672413793104, 'r': 0.7683089214380826, 'f1': 0.6873138773079214}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Eng Test for Russian: {'event': {'p': 0.6300302899177845, 'r': 0.7599164926931107, 'f1': 0.6889046605157322}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Sample Russian: {'event': {'p': 0.5, 'r': 0.5833333333333334, 'f1': 0.5384615384615384}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
******************************
Epoch: 16
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 02:15:02.390324: step: 4/526, loss: 0.00011005401756847277
2023-01-23 02:15:03.501536: step: 8/526, loss: 0.000926971435546875
2023-01-23 02:15:04.655123: step: 12/526, loss: 0.029949188232421875
2023-01-23 02:15:05.820085: step: 16/526, loss: 0.006628227420151234
2023-01-23 02:15:06.918706: step: 20/526, loss: 0.037622738629579544
2023-01-23 02:15:08.034010: step: 24/526, loss: 0.009700726717710495
2023-01-23 02:15:09.154448: step: 28/526, loss: 0.003586006350815296
2023-01-23 02:15:10.308031: step: 32/526, loss: 0.0005657196161337197
2023-01-23 02:15:11.454741: step: 36/526, loss: 0.0002120971621479839
2023-01-23 02:15:12.593100: step: 40/526, loss: 0.0004032134893350303
2023-01-23 02:15:13.731200: step: 44/526, loss: 0.05403842777013779
2023-01-23 02:15:14.884158: step: 48/526, loss: 0.004210758488625288
2023-01-23 02:15:16.004094: step: 52/526, loss: 0.00917806662619114
2023-01-23 02:15:17.146916: step: 56/526, loss: 0.00089263916015625
2023-01-23 02:15:18.308225: step: 60/526, loss: 0.008420038037002087
2023-01-23 02:15:19.423259: step: 64/526, loss: 0.039496805518865585
2023-01-23 02:15:20.538920: step: 68/526, loss: 0.030106164515018463
2023-01-23 02:15:21.701653: step: 72/526, loss: 0.024308206513524055
2023-01-23 02:15:22.837080: step: 76/526, loss: 6.545782525790855e-05
2023-01-23 02:15:23.945061: step: 80/526, loss: 0.014850807376205921
2023-01-23 02:15:25.076764: step: 84/526, loss: 0.031487371772527695
2023-01-23 02:15:26.281111: step: 88/526, loss: 0.04479942470788956
2023-01-23 02:15:27.419827: step: 92/526, loss: 0.02416362799704075
2023-01-23 02:15:28.540196: step: 96/526, loss: 0.00467948941513896
2023-01-23 02:15:29.690779: step: 100/526, loss: 0.038279153406620026
2023-01-23 02:15:30.854864: step: 104/526, loss: 0.00205402378924191
2023-01-23 02:15:31.999811: step: 108/526, loss: 0.04345588758587837
2023-01-23 02:15:33.116910: step: 112/526, loss: 0.002930164337158203
2023-01-23 02:15:34.254613: step: 116/526, loss: 0.03169460594654083
2023-01-23 02:15:35.384859: step: 120/526, loss: 0.0056645870208740234
2023-01-23 02:15:36.525134: step: 124/526, loss: 0.007916831411421299
2023-01-23 02:15:37.663678: step: 128/526, loss: 0.003505706787109375
2023-01-23 02:15:38.831783: step: 132/526, loss: 0.03725452721118927
2023-01-23 02:15:39.974577: step: 136/526, loss: 0.0007162094116210938
2023-01-23 02:15:41.124405: step: 140/526, loss: 0.021389389410614967
2023-01-23 02:15:42.244231: step: 144/526, loss: 0.01701831817626953
2023-01-23 02:15:43.408653: step: 148/526, loss: 0.0033901215065270662
2023-01-23 02:15:44.550174: step: 152/526, loss: 0.0017707825172692537
2023-01-23 02:15:45.682591: step: 156/526, loss: 0.5684857368469238
2023-01-23 02:15:46.804803: step: 160/526, loss: 0.010584640316665173
2023-01-23 02:15:47.916156: step: 164/526, loss: 0.001024436904117465
2023-01-23 02:15:49.016790: step: 168/526, loss: 0.009119797497987747
2023-01-23 02:15:50.180318: step: 172/526, loss: 0.012661266140639782
2023-01-23 02:15:51.328431: step: 176/526, loss: 0.023590087890625
2023-01-23 02:15:52.436486: step: 180/526, loss: 0.01925811730325222
2023-01-23 02:15:53.558326: step: 184/526, loss: 0.011992835439741611
2023-01-23 02:15:54.695961: step: 188/526, loss: 0.06738948822021484
2023-01-23 02:15:55.845917: step: 192/526, loss: 0.007896996103227139
2023-01-23 02:15:56.985709: step: 196/526, loss: 0.0003678321954794228
2023-01-23 02:15:58.104162: step: 200/526, loss: 0.002997016767039895
2023-01-23 02:15:59.205690: step: 204/526, loss: 0.008821535855531693
2023-01-23 02:16:00.352616: step: 208/526, loss: 0.004204940982162952
2023-01-23 02:16:01.484691: step: 212/526, loss: 0.0031444551423192024
2023-01-23 02:16:02.609244: step: 216/526, loss: 0.045699309557676315
2023-01-23 02:16:03.766900: step: 220/526, loss: 0.009506797417998314
2023-01-23 02:16:04.929125: step: 224/526, loss: 0.07151356339454651
2023-01-23 02:16:06.081601: step: 228/526, loss: 0.03923730552196503
2023-01-23 02:16:07.232691: step: 232/526, loss: 0.005748939700424671
2023-01-23 02:16:08.427559: step: 236/526, loss: 0.08857040852308273
2023-01-23 02:16:09.594211: step: 240/526, loss: 0.006740999408066273
2023-01-23 02:16:10.697514: step: 244/526, loss: 0.001222896622493863
2023-01-23 02:16:11.832105: step: 248/526, loss: 0.00033245087251998484
2023-01-23 02:16:12.946255: step: 252/526, loss: 0.022715091705322266
2023-01-23 02:16:14.093478: step: 256/526, loss: 0.4950489103794098
2023-01-23 02:16:15.234913: step: 260/526, loss: 0.03233318403363228
2023-01-23 02:16:16.384405: step: 264/526, loss: 0.014944505877792835
2023-01-23 02:16:17.516738: step: 268/526, loss: 0.018395423889160156
2023-01-23 02:16:18.621323: step: 272/526, loss: 0.020806027576327324
2023-01-23 02:16:19.750651: step: 276/526, loss: 0.00037660598172806203
2023-01-23 02:16:20.860389: step: 280/526, loss: 0.0014060974353924394
2023-01-23 02:16:22.024396: step: 284/526, loss: 0.02727203443646431
2023-01-23 02:16:23.175568: step: 288/526, loss: 0.008841228671371937
2023-01-23 02:16:24.297053: step: 292/526, loss: 0.00018597840971779078
2023-01-23 02:16:25.432214: step: 296/526, loss: 0.00043563847430050373
2023-01-23 02:16:26.606820: step: 300/526, loss: 0.034189797937870026
2023-01-23 02:16:27.736744: step: 304/526, loss: 3.5953522456111386e-05
2023-01-23 02:16:28.865307: step: 308/526, loss: 0.04229774326086044
2023-01-23 02:16:30.007684: step: 312/526, loss: 0.05191965028643608
2023-01-23 02:16:31.166810: step: 316/526, loss: 0.036585234105587006
2023-01-23 02:16:32.276859: step: 320/526, loss: 0.0011564254527911544
2023-01-23 02:16:33.384500: step: 324/526, loss: 0.0020558834075927734
2023-01-23 02:16:34.532538: step: 328/526, loss: 0.0005407333374023438
2023-01-23 02:16:35.720752: step: 332/526, loss: 0.0032994269859045744
2023-01-23 02:16:36.850751: step: 336/526, loss: 0.010889149270951748
2023-01-23 02:16:37.992956: step: 340/526, loss: 0.00048341750516556203
2023-01-23 02:16:39.116173: step: 344/526, loss: 0.0035694122780114412
2023-01-23 02:16:40.247246: step: 348/526, loss: 2.3841867005103268e-06
2023-01-23 02:16:41.376589: step: 352/526, loss: 0.01700468175113201
2023-01-23 02:16:42.534186: step: 356/526, loss: 0.07163476943969727
2023-01-23 02:16:43.648493: step: 360/526, loss: 0.0033693313598632812
2023-01-23 02:16:44.793699: step: 364/526, loss: 0.005605125334113836
2023-01-23 02:16:45.927700: step: 368/526, loss: 0.010840988717973232
2023-01-23 02:16:47.057128: step: 372/526, loss: 0.0015970231033861637
2023-01-23 02:16:48.178079: step: 376/526, loss: 0.07096214592456818
2023-01-23 02:16:49.342176: step: 380/526, loss: 0.012497996911406517
2023-01-23 02:16:50.459460: step: 384/526, loss: 0.0019136428600177169
2023-01-23 02:16:51.590251: step: 388/526, loss: 0.019266463816165924
2023-01-23 02:16:52.757112: step: 392/526, loss: 0.0027828216552734375
2023-01-23 02:16:53.883587: step: 396/526, loss: 0.018727969378232956
2023-01-23 02:16:55.017876: step: 400/526, loss: 0.002200603485107422
2023-01-23 02:16:56.149492: step: 404/526, loss: 0.0007186889415606856
2023-01-23 02:16:57.318140: step: 408/526, loss: 0.016614913940429688
2023-01-23 02:16:58.435437: step: 412/526, loss: 0.10731811821460724
2023-01-23 02:16:59.574740: step: 416/526, loss: 0.007856511510908604
2023-01-23 02:17:00.731603: step: 420/526, loss: 0.07938919216394424
2023-01-23 02:17:01.865426: step: 424/526, loss: 0.00168781285174191
2023-01-23 02:17:03.012377: step: 428/526, loss: 0.017522001639008522
2023-01-23 02:17:04.153686: step: 432/526, loss: 0.028425121679902077
2023-01-23 02:17:05.292794: step: 436/526, loss: 0.1173354908823967
2023-01-23 02:17:06.406948: step: 440/526, loss: 0.0013078213669359684
2023-01-23 02:17:07.536006: step: 444/526, loss: 0.03006439283490181
2023-01-23 02:17:08.653187: step: 448/526, loss: 0.025170136243104935
2023-01-23 02:17:09.819767: step: 452/526, loss: 0.0012928962241858244
2023-01-23 02:17:10.940941: step: 456/526, loss: 0.012340545654296875
2023-01-23 02:17:12.067893: step: 460/526, loss: 5.1212311518611386e-05
2023-01-23 02:17:13.209897: step: 464/526, loss: 0.0627140998840332
2023-01-23 02:17:14.355673: step: 468/526, loss: 0.06278286129236221
2023-01-23 02:17:15.528053: step: 472/526, loss: 0.009520339779555798
2023-01-23 02:17:16.670057: step: 476/526, loss: 0.020020723342895508
2023-01-23 02:17:17.824820: step: 480/526, loss: 0.004179859068244696
2023-01-23 02:17:18.979813: step: 484/526, loss: 0.0035198212135583162
2023-01-23 02:17:20.104092: step: 488/526, loss: 0.005193233489990234
2023-01-23 02:17:21.249669: step: 492/526, loss: 0.0011620878940448165
2023-01-23 02:17:22.383862: step: 496/526, loss: 0.013108158484101295
2023-01-23 02:17:23.528183: step: 500/526, loss: 0.010790920816361904
2023-01-23 02:17:24.655238: step: 504/526, loss: 0.04725589603185654
2023-01-23 02:17:25.757887: step: 508/526, loss: 0.005801201332360506
2023-01-23 02:17:26.893008: step: 512/526, loss: 0.0016223908169195056
2023-01-23 02:17:28.015115: step: 516/526, loss: 0.033487893640995026
2023-01-23 02:17:29.135932: step: 520/526, loss: 0.0010188103187829256
2023-01-23 02:17:30.263464: step: 524/526, loss: 0.002458471106365323
2023-01-23 02:17:31.434531: step: 528/526, loss: 0.003955078311264515
2023-01-23 02:17:32.561483: step: 532/526, loss: 0.0006930351373739541
2023-01-23 02:17:33.697083: step: 536/526, loss: 0.00612220773473382
2023-01-23 02:17:34.838027: step: 540/526, loss: 0.029469633474946022
2023-01-23 02:17:35.969130: step: 544/526, loss: 0.07070689648389816
2023-01-23 02:17:37.108296: step: 548/526, loss: 0.03894519805908203
2023-01-23 02:17:38.251357: step: 552/526, loss: 0.006038665771484375
2023-01-23 02:17:39.391866: step: 556/526, loss: 0.01715373992919922
2023-01-23 02:17:40.565896: step: 560/526, loss: 0.02691631391644478
2023-01-23 02:17:41.712077: step: 564/526, loss: 0.03173065185546875
2023-01-23 02:17:42.858837: step: 568/526, loss: 0.05192279815673828
2023-01-23 02:17:43.984226: step: 572/526, loss: 0.7218326926231384
2023-01-23 02:17:45.107351: step: 576/526, loss: 0.007844829931855202
2023-01-23 02:17:46.248522: step: 580/526, loss: 0.014657092280685902
2023-01-23 02:17:47.386508: step: 584/526, loss: 0.0025338411796838045
2023-01-23 02:17:48.511150: step: 588/526, loss: 0.012466048821806908
2023-01-23 02:17:49.622378: step: 592/526, loss: 0.003747367998585105
2023-01-23 02:17:50.737442: step: 596/526, loss: 0.00015802383131813258
2023-01-23 02:17:51.884903: step: 600/526, loss: 0.0013956070179119706
2023-01-23 02:17:52.977991: step: 604/526, loss: 0.00013432501873467118
2023-01-23 02:17:54.116666: step: 608/526, loss: 0.0366269126534462
2023-01-23 02:17:55.255985: step: 612/526, loss: 0.0004051685391459614
2023-01-23 02:17:56.399169: step: 616/526, loss: 0.0031521799974143505
2023-01-23 02:17:57.553871: step: 620/526, loss: 0.011005687527358532
2023-01-23 02:17:58.684523: step: 624/526, loss: 0.004446124657988548
2023-01-23 02:17:59.791205: step: 628/526, loss: 0.0975554883480072
2023-01-23 02:18:00.924939: step: 632/526, loss: 0.03302812948822975
2023-01-23 02:18:02.042776: step: 636/526, loss: 0.008095837198197842
2023-01-23 02:18:03.165655: step: 640/526, loss: 0.06758633255958557
2023-01-23 02:18:04.292249: step: 644/526, loss: 0.04158306121826172
2023-01-23 02:18:05.431695: step: 648/526, loss: 0.009734058752655983
2023-01-23 02:18:06.561169: step: 652/526, loss: 0.05300493165850639
2023-01-23 02:18:07.717067: step: 656/526, loss: 0.0772184357047081
2023-01-23 02:18:08.863592: step: 660/526, loss: 0.0387025885283947
2023-01-23 02:18:10.002486: step: 664/526, loss: 0.056638289242982864
2023-01-23 02:18:11.153404: step: 668/526, loss: 0.021870804950594902
2023-01-23 02:18:12.269032: step: 672/526, loss: 0.002477932022884488
2023-01-23 02:18:13.416289: step: 676/526, loss: 0.0038053514435887337
2023-01-23 02:18:14.548832: step: 680/526, loss: 0.01116104144603014
2023-01-23 02:18:15.703938: step: 684/526, loss: 0.05805826559662819
2023-01-23 02:18:16.812961: step: 688/526, loss: 9.663105447543785e-05
2023-01-23 02:18:17.931494: step: 692/526, loss: 0.006488132290542126
2023-01-23 02:18:19.030464: step: 696/526, loss: 0.009644603356719017
2023-01-23 02:18:20.147329: step: 700/526, loss: 0.1351669430732727
2023-01-23 02:18:21.269934: step: 704/526, loss: 0.015242195688188076
2023-01-23 02:18:22.390141: step: 708/526, loss: 0.010523796081542969
2023-01-23 02:18:23.522295: step: 712/526, loss: 0.0018431664211675525
2023-01-23 02:18:24.652364: step: 716/526, loss: 0.03212776035070419
2023-01-23 02:18:25.807326: step: 720/526, loss: 0.029506683349609375
2023-01-23 02:18:26.936765: step: 724/526, loss: 0.019783878698945045
2023-01-23 02:18:28.073151: step: 728/526, loss: 0.03422107547521591
2023-01-23 02:18:29.201263: step: 732/526, loss: 0.00010271072096657008
2023-01-23 02:18:30.323075: step: 736/526, loss: 0.0025561333168298006
2023-01-23 02:18:31.464598: step: 740/526, loss: 0.007940388284623623
2023-01-23 02:18:32.612710: step: 744/526, loss: 0.018820475786924362
2023-01-23 02:18:33.738278: step: 748/526, loss: 0.007153606973588467
2023-01-23 02:18:34.881525: step: 752/526, loss: 0.013507843017578125
2023-01-23 02:18:36.008338: step: 756/526, loss: 0.008286476135253906
2023-01-23 02:18:37.154398: step: 760/526, loss: 0.0026101351249963045
2023-01-23 02:18:38.277070: step: 764/526, loss: 0.003011125372722745
2023-01-23 02:18:39.404660: step: 768/526, loss: 0.10370655357837677
2023-01-23 02:18:40.567732: step: 772/526, loss: 0.006145477294921875
2023-01-23 02:18:41.689519: step: 776/526, loss: 0.011046123690903187
2023-01-23 02:18:42.858576: step: 780/526, loss: 0.011315441690385342
2023-01-23 02:18:43.985492: step: 784/526, loss: 0.005061340518295765
2023-01-23 02:18:45.109777: step: 788/526, loss: 0.012497376650571823
2023-01-23 02:18:46.248974: step: 792/526, loss: 0.0424153208732605
2023-01-23 02:18:47.378605: step: 796/526, loss: 0.03855876624584198
2023-01-23 02:18:48.500841: step: 800/526, loss: 0.013813686557114124
2023-01-23 02:18:49.629654: step: 804/526, loss: 0.007894134148955345
2023-01-23 02:18:50.717217: step: 808/526, loss: 0.01721782609820366
2023-01-23 02:18:51.826334: step: 812/526, loss: 0.016414929181337357
2023-01-23 02:18:52.953636: step: 816/526, loss: 0.0011794089805334806
2023-01-23 02:18:54.084156: step: 820/526, loss: 0.018193436786532402
2023-01-23 02:18:55.186717: step: 824/526, loss: 0.0004116058407817036
2023-01-23 02:18:56.328327: step: 828/526, loss: 0.0032097341027110815
2023-01-23 02:18:57.488295: step: 832/526, loss: 8.18252592580393e-05
2023-01-23 02:18:58.598069: step: 836/526, loss: 0.0003183365042787045
2023-01-23 02:18:59.737658: step: 840/526, loss: 0.015307235531508923
2023-01-23 02:19:00.888400: step: 844/526, loss: 0.004409885033965111
2023-01-23 02:19:02.044478: step: 848/526, loss: 0.003408813616260886
2023-01-23 02:19:03.164005: step: 852/526, loss: 0.03038616105914116
2023-01-23 02:19:04.294263: step: 856/526, loss: 0.0010211020708084106
2023-01-23 02:19:05.448351: step: 860/526, loss: 0.030455972999334335
2023-01-23 02:19:06.571998: step: 864/526, loss: 0.000154399880557321
2023-01-23 02:19:07.704856: step: 868/526, loss: 0.008781814947724342
2023-01-23 02:19:08.867601: step: 872/526, loss: 0.00012149810936534777
2023-01-23 02:19:10.033291: step: 876/526, loss: 4.024505687993951e-05
2023-01-23 02:19:11.195981: step: 880/526, loss: 0.03061084821820259
2023-01-23 02:19:12.355172: step: 884/526, loss: 0.05472087860107422
2023-01-23 02:19:13.525940: step: 888/526, loss: 0.025283336639404297
2023-01-23 02:19:14.649268: step: 892/526, loss: 0.023142816498875618
2023-01-23 02:19:15.761500: step: 896/526, loss: 0.004337119869887829
2023-01-23 02:19:16.875850: step: 900/526, loss: 0.022684242576360703
2023-01-23 02:19:17.982206: step: 904/526, loss: 0.013498211279511452
2023-01-23 02:19:19.148503: step: 908/526, loss: 0.0207901019603014
2023-01-23 02:19:20.299199: step: 912/526, loss: 0.008356666192412376
2023-01-23 02:19:21.430604: step: 916/526, loss: 0.0105431554839015
2023-01-23 02:19:22.596359: step: 920/526, loss: 0.5433765649795532
2023-01-23 02:19:23.742479: step: 924/526, loss: 0.03345680236816406
2023-01-23 02:19:24.890426: step: 928/526, loss: 0.026952171698212624
2023-01-23 02:19:26.043968: step: 932/526, loss: 0.014483070932328701
2023-01-23 02:19:27.174501: step: 936/526, loss: 0.019674967974424362
2023-01-23 02:19:28.300475: step: 940/526, loss: 0.0019038678146898746
2023-01-23 02:19:29.428649: step: 944/526, loss: 0.008465766906738281
2023-01-23 02:19:30.552542: step: 948/526, loss: 0.015292310155928135
2023-01-23 02:19:31.696538: step: 952/526, loss: 0.0023895264603197575
2023-01-23 02:19:32.843103: step: 956/526, loss: 0.022774221375584602
2023-01-23 02:19:33.971400: step: 960/526, loss: 0.010180902667343616
2023-01-23 02:19:35.075085: step: 964/526, loss: 0.014191102236509323
2023-01-23 02:19:36.183644: step: 968/526, loss: 0.005507171154022217
2023-01-23 02:19:37.351223: step: 972/526, loss: 0.1057150810956955
2023-01-23 02:19:38.442161: step: 976/526, loss: 0.0006694793701171875
2023-01-23 02:19:39.602767: step: 980/526, loss: 0.017969131469726562
2023-01-23 02:19:40.783458: step: 984/526, loss: 0.034426022320985794
2023-01-23 02:19:41.931524: step: 988/526, loss: 0.06725058704614639
2023-01-23 02:19:43.080451: step: 992/526, loss: 0.09980545192956924
2023-01-23 02:19:44.214243: step: 996/526, loss: 0.006281280890107155
2023-01-23 02:19:45.401261: step: 1000/526, loss: 0.028983497992157936
2023-01-23 02:19:46.518600: step: 1004/526, loss: 0.01869940757751465
2023-01-23 02:19:47.695059: step: 1008/526, loss: 0.005263710394501686
2023-01-23 02:19:48.830266: step: 1012/526, loss: 0.029657935723662376
2023-01-23 02:19:49.968794: step: 1016/526, loss: 0.006319808773696423
2023-01-23 02:19:51.095773: step: 1020/526, loss: 0.01023800391703844
2023-01-23 02:19:52.233536: step: 1024/526, loss: 0.6852072477340698
2023-01-23 02:19:53.355796: step: 1028/526, loss: 0.011850547976791859
2023-01-23 02:19:54.500128: step: 1032/526, loss: 0.06599750369787216
2023-01-23 02:19:55.634789: step: 1036/526, loss: 0.003675317857414484
2023-01-23 02:19:56.781370: step: 1040/526, loss: 0.2622377574443817
2023-01-23 02:19:57.901745: step: 1044/526, loss: 0.019731713458895683
2023-01-23 02:19:59.059258: step: 1048/526, loss: 0.03058652952313423
2023-01-23 02:20:00.196617: step: 1052/526, loss: 0.04766717180609703
2023-01-23 02:20:01.324077: step: 1056/526, loss: 0.001121902372688055
2023-01-23 02:20:02.439166: step: 1060/526, loss: 0.014496040530502796
2023-01-23 02:20:03.590684: step: 1064/526, loss: 0.19050703942775726
2023-01-23 02:20:04.720183: step: 1068/526, loss: 0.016804981976747513
2023-01-23 02:20:05.871783: step: 1072/526, loss: 0.05126895755529404
2023-01-23 02:20:06.991895: step: 1076/526, loss: 0.029932117089629173
2023-01-23 02:20:08.132759: step: 1080/526, loss: 0.03689174726605415
2023-01-23 02:20:09.263889: step: 1084/526, loss: 0.018379880115389824
2023-01-23 02:20:10.394692: step: 1088/526, loss: 0.005470371339470148
2023-01-23 02:20:11.511113: step: 1092/526, loss: 0.017129898071289062
2023-01-23 02:20:12.675590: step: 1096/526, loss: 0.0006162643549032509
2023-01-23 02:20:13.806061: step: 1100/526, loss: 0.3256654739379883
2023-01-23 02:20:14.963385: step: 1104/526, loss: 0.001452636788599193
2023-01-23 02:20:16.109964: step: 1108/526, loss: 0.12877941131591797
2023-01-23 02:20:17.257121: step: 1112/526, loss: 0.0022145749535411596
2023-01-23 02:20:18.405469: step: 1116/526, loss: 0.017909908667206764
2023-01-23 02:20:19.545332: step: 1120/526, loss: 0.0266602523624897
2023-01-23 02:20:20.663610: step: 1124/526, loss: 0.011217355728149414
2023-01-23 02:20:21.784961: step: 1128/526, loss: 0.05366382747888565
2023-01-23 02:20:23.005487: step: 1132/526, loss: 0.004132366273552179
2023-01-23 02:20:24.148495: step: 1136/526, loss: 0.05129261314868927
2023-01-23 02:20:25.256010: step: 1140/526, loss: 0.012623215094208717
2023-01-23 02:20:26.362791: step: 1144/526, loss: 0.01526489295065403
2023-01-23 02:20:27.505006: step: 1148/526, loss: 0.0033623697236180305
2023-01-23 02:20:28.645786: step: 1152/526, loss: 0.0010648727184161544
2023-01-23 02:20:29.794199: step: 1156/526, loss: 0.04280386120080948
2023-01-23 02:20:30.928358: step: 1160/526, loss: 0.06125011295080185
2023-01-23 02:20:32.070133: step: 1164/526, loss: 0.0029735565185546875
2023-01-23 02:20:33.196539: step: 1168/526, loss: 0.10555687546730042
2023-01-23 02:20:34.352709: step: 1172/526, loss: 0.01919260062277317
2023-01-23 02:20:35.506790: step: 1176/526, loss: 0.0023391246795654297
2023-01-23 02:20:36.657403: step: 1180/526, loss: 0.03665027767419815
2023-01-23 02:20:37.788170: step: 1184/526, loss: 0.001665306044742465
2023-01-23 02:20:38.889627: step: 1188/526, loss: 0.00519218435510993
2023-01-23 02:20:40.038445: step: 1192/526, loss: 0.024559592828154564
2023-01-23 02:20:41.154346: step: 1196/526, loss: 0.0011234283447265625
2023-01-23 02:20:42.293157: step: 1200/526, loss: 0.003875160124152899
2023-01-23 02:20:43.452657: step: 1204/526, loss: 0.026830770075321198
2023-01-23 02:20:44.552430: step: 1208/526, loss: 7.731914229225367e-05
2023-01-23 02:20:45.719010: step: 1212/526, loss: 0.11283569037914276
2023-01-23 02:20:46.883093: step: 1216/526, loss: 0.03677120432257652
2023-01-23 02:20:48.044291: step: 1220/526, loss: 0.0005367517587728798
2023-01-23 02:20:49.182033: step: 1224/526, loss: 4.792213439941406e-05
2023-01-23 02:20:50.299085: step: 1228/526, loss: 0.042072393000125885
2023-01-23 02:20:51.415596: step: 1232/526, loss: 0.010038233362138271
2023-01-23 02:20:52.572947: step: 1236/526, loss: 0.047733500599861145
2023-01-23 02:20:53.694455: step: 1240/526, loss: 0.04888410493731499
2023-01-23 02:20:54.846133: step: 1244/526, loss: 0.0031155110336840153
2023-01-23 02:20:55.958099: step: 1248/526, loss: 0.039557456970214844
2023-01-23 02:20:57.073939: step: 1252/526, loss: 0.008772374130785465
2023-01-23 02:20:58.214088: step: 1256/526, loss: 0.039145469665527344
2023-01-23 02:20:59.342416: step: 1260/526, loss: 0.013201141729950905
2023-01-23 02:21:00.476191: step: 1264/526, loss: 0.00016717911057639867
2023-01-23 02:21:01.617457: step: 1268/526, loss: 0.06774864345788956
2023-01-23 02:21:02.745628: step: 1272/526, loss: 0.0020217897836118937
2023-01-23 02:21:03.887013: step: 1276/526, loss: 0.06763801723718643
2023-01-23 02:21:05.043459: step: 1280/526, loss: 0.1894427388906479
2023-01-23 02:21:06.165377: step: 1284/526, loss: 0.09113812446594238
2023-01-23 02:21:07.299596: step: 1288/526, loss: 0.07216491550207138
2023-01-23 02:21:08.411229: step: 1292/526, loss: 0.0015925407642498612
2023-01-23 02:21:09.537381: step: 1296/526, loss: 0.044083595275878906
2023-01-23 02:21:10.699987: step: 1300/526, loss: 0.03427238389849663
2023-01-23 02:21:11.825137: step: 1304/526, loss: 6.246566772460938e-05
2023-01-23 02:21:12.973189: step: 1308/526, loss: 0.030949022620916367
2023-01-23 02:21:14.074484: step: 1312/526, loss: 0.004623508546501398
2023-01-23 02:21:15.212562: step: 1316/526, loss: 0.01839613914489746
2023-01-23 02:21:16.360097: step: 1320/526, loss: 0.01687178574502468
2023-01-23 02:21:17.521963: step: 1324/526, loss: 0.00014228821964934468
2023-01-23 02:21:18.655970: step: 1328/526, loss: 0.08320808410644531
2023-01-23 02:21:19.770875: step: 1332/526, loss: 0.0011567592155188322
2023-01-23 02:21:20.912389: step: 1336/526, loss: 0.035341642796993256
2023-01-23 02:21:22.037536: step: 1340/526, loss: 0.007504272274672985
2023-01-23 02:21:23.168916: step: 1344/526, loss: 0.0002117156982421875
2023-01-23 02:21:24.291915: step: 1348/526, loss: 0.011392975226044655
2023-01-23 02:21:25.437568: step: 1352/526, loss: 0.0030735016334801912
2023-01-23 02:21:26.630341: step: 1356/526, loss: 0.022859174758195877
2023-01-23 02:21:27.747279: step: 1360/526, loss: 0.0028609277214854956
2023-01-23 02:21:28.879548: step: 1364/526, loss: 0.005170727148652077
2023-01-23 02:21:29.984257: step: 1368/526, loss: 0.06670016795396805
2023-01-23 02:21:31.125464: step: 1372/526, loss: 0.03216209635138512
2023-01-23 02:21:32.282439: step: 1376/526, loss: 0.002028340008109808
2023-01-23 02:21:33.373633: step: 1380/526, loss: 0.0033762454986572266
2023-01-23 02:21:34.497521: step: 1384/526, loss: 0.021107101812958717
2023-01-23 02:21:35.614399: step: 1388/526, loss: 0.07684288173913956
2023-01-23 02:21:36.736326: step: 1392/526, loss: 0.012826060876250267
2023-01-23 02:21:37.859622: step: 1396/526, loss: 0.027877237647771835
2023-01-23 02:21:38.976950: step: 1400/526, loss: 0.011816036887466908
2023-01-23 02:21:40.079956: step: 1404/526, loss: 2.6607514882925898e-05
2023-01-23 02:21:41.213127: step: 1408/526, loss: 0.00016078949556685984
2023-01-23 02:21:42.330821: step: 1412/526, loss: 0.03845162317156792
2023-01-23 02:21:43.445200: step: 1416/526, loss: 0.0684087723493576
2023-01-23 02:21:44.587336: step: 1420/526, loss: 0.04565334692597389
2023-01-23 02:21:45.737917: step: 1424/526, loss: 0.004640102386474609
2023-01-23 02:21:46.886155: step: 1428/526, loss: 0.015440654009580612
2023-01-23 02:21:48.054798: step: 1432/526, loss: 0.006703376770019531
2023-01-23 02:21:49.197536: step: 1436/526, loss: 0.0009208678966388106
2023-01-23 02:21:50.310474: step: 1440/526, loss: 0.001810264540836215
2023-01-23 02:21:51.436109: step: 1444/526, loss: 0.030171968042850494
2023-01-23 02:21:52.561113: step: 1448/526, loss: 0.013826275244355202
2023-01-23 02:21:53.715001: step: 1452/526, loss: 0.03273200988769531
2023-01-23 02:21:54.831257: step: 1456/526, loss: 0.020988276228308678
2023-01-23 02:21:55.987494: step: 1460/526, loss: 0.013797379098832607
2023-01-23 02:21:57.113299: step: 1464/526, loss: 0.022766876965761185
2023-01-23 02:21:58.232672: step: 1468/526, loss: 0.013074303045868874
2023-01-23 02:21:59.380717: step: 1472/526, loss: 0.009706258773803711
2023-01-23 02:22:00.491952: step: 1476/526, loss: 0.025360107421875
2023-01-23 02:22:01.642036: step: 1480/526, loss: 0.051818035542964935
2023-01-23 02:22:02.770812: step: 1484/526, loss: 0.023619651794433594
2023-01-23 02:22:03.923740: step: 1488/526, loss: 0.09215135872364044
2023-01-23 02:22:05.049990: step: 1492/526, loss: 0.059362031519412994
2023-01-23 02:22:06.196943: step: 1496/526, loss: 0.02387847937643528
2023-01-23 02:22:07.358479: step: 1500/526, loss: 0.02298736572265625
2023-01-23 02:22:08.501997: step: 1504/526, loss: 0.0031350136268883944
2023-01-23 02:22:09.632304: step: 1508/526, loss: 0.01287221908569336
2023-01-23 02:22:10.785562: step: 1512/526, loss: 0.007496643345803022
2023-01-23 02:22:11.937703: step: 1516/526, loss: 0.04456625133752823
2023-01-23 02:22:13.084287: step: 1520/526, loss: 0.036905575543642044
2023-01-23 02:22:14.213574: step: 1524/526, loss: 0.03574182838201523
2023-01-23 02:22:15.348067: step: 1528/526, loss: 0.020223427563905716
2023-01-23 02:22:16.491299: step: 1532/526, loss: 0.005044556222856045
2023-01-23 02:22:17.586227: step: 1536/526, loss: 0.01800546608865261
2023-01-23 02:22:18.717209: step: 1540/526, loss: 0.016041278839111328
2023-01-23 02:22:19.880274: step: 1544/526, loss: 0.009444808587431908
2023-01-23 02:22:21.065414: step: 1548/526, loss: 0.07086839526891708
2023-01-23 02:22:22.182571: step: 1552/526, loss: 0.0850076675415039
2023-01-23 02:22:23.285838: step: 1556/526, loss: 0.014645768329501152
2023-01-23 02:22:24.481108: step: 1560/526, loss: 0.00337562570348382
2023-01-23 02:22:25.614388: step: 1564/526, loss: 0.04385490342974663
2023-01-23 02:22:26.735659: step: 1568/526, loss: 0.03648347780108452
2023-01-23 02:22:27.881187: step: 1572/526, loss: 0.003805875778198242
2023-01-23 02:22:29.021301: step: 1576/526, loss: 0.01501169241964817
2023-01-23 02:22:30.176276: step: 1580/526, loss: 0.036768436431884766
2023-01-23 02:22:31.328487: step: 1584/526, loss: 0.005214214324951172
2023-01-23 02:22:32.438498: step: 1588/526, loss: 0.06704378128051758
2023-01-23 02:22:33.607708: step: 1592/526, loss: 0.0134324561804533
2023-01-23 02:22:34.752042: step: 1596/526, loss: 0.006333780474960804
2023-01-23 02:22:35.849527: step: 1600/526, loss: 0.003576993942260742
2023-01-23 02:22:36.993937: step: 1604/526, loss: 0.007436180487275124
2023-01-23 02:22:38.087072: step: 1608/526, loss: 0.10442066192626953
2023-01-23 02:22:39.224532: step: 1612/526, loss: 0.02715625800192356
2023-01-23 02:22:40.351495: step: 1616/526, loss: 0.0002761840878520161
2023-01-23 02:22:41.482285: step: 1620/526, loss: 0.02376708947122097
2023-01-23 02:22:42.635924: step: 1624/526, loss: 0.0425909049808979
2023-01-23 02:22:43.808558: step: 1628/526, loss: 0.007823002524673939
2023-01-23 02:22:44.945791: step: 1632/526, loss: 0.0069630625657737255
2023-01-23 02:22:46.064706: step: 1636/526, loss: 0.009379577822983265
2023-01-23 02:22:47.204947: step: 1640/526, loss: 0.04682111740112305
2023-01-23 02:22:48.340666: step: 1644/526, loss: 0.02999715879559517
2023-01-23 02:22:49.494321: step: 1648/526, loss: 5.0115584599552676e-05
2023-01-23 02:22:50.640328: step: 1652/526, loss: 0.1424911469221115
2023-01-23 02:22:51.751390: step: 1656/526, loss: 0.015407372266054153
2023-01-23 02:22:52.891562: step: 1660/526, loss: 0.013187408447265625
2023-01-23 02:22:54.015791: step: 1664/526, loss: 0.1278003752231598
2023-01-23 02:22:55.186011: step: 1668/526, loss: 0.04957018047571182
2023-01-23 02:22:56.339496: step: 1672/526, loss: 0.48830169439315796
2023-01-23 02:22:57.462388: step: 1676/526, loss: 0.04101238399744034
2023-01-23 02:22:58.578732: step: 1680/526, loss: 0.008026408962905407
2023-01-23 02:22:59.706571: step: 1684/526, loss: 0.06244621425867081
2023-01-23 02:23:00.855890: step: 1688/526, loss: 0.005667400546371937
2023-01-23 02:23:01.993736: step: 1692/526, loss: 0.029083536937832832
2023-01-23 02:23:03.154776: step: 1696/526, loss: 0.004749107174575329
2023-01-23 02:23:04.282944: step: 1700/526, loss: 0.008632849901914597
2023-01-23 02:23:05.418839: step: 1704/526, loss: 0.0051434519700706005
2023-01-23 02:23:06.566372: step: 1708/526, loss: 0.03107757493853569
2023-01-23 02:23:07.680999: step: 1712/526, loss: 0.06791611015796661
2023-01-23 02:23:08.833969: step: 1716/526, loss: 0.008446312509477139
2023-01-23 02:23:09.984466: step: 1720/526, loss: 0.0007907867548055947
2023-01-23 02:23:11.128147: step: 1724/526, loss: 0.05016594007611275
2023-01-23 02:23:12.266292: step: 1728/526, loss: 0.006982707884162664
2023-01-23 02:23:13.391972: step: 1732/526, loss: 0.012863541021943092
2023-01-23 02:23:14.534035: step: 1736/526, loss: 0.04176607355475426
2023-01-23 02:23:15.647581: step: 1740/526, loss: 0.023456193506717682
2023-01-23 02:23:16.756533: step: 1744/526, loss: 0.0015418052207678556
2023-01-23 02:23:17.893128: step: 1748/526, loss: 0.06011927127838135
2023-01-23 02:23:19.022144: step: 1752/526, loss: 0.012541437521576881
2023-01-23 02:23:20.185646: step: 1756/526, loss: 0.02001648023724556
2023-01-23 02:23:21.342422: step: 1760/526, loss: 0.0074253082275390625
2023-01-23 02:23:22.496755: step: 1764/526, loss: 0.05597114562988281
2023-01-23 02:23:23.634422: step: 1768/526, loss: 0.049950502812862396
2023-01-23 02:23:24.769453: step: 1772/526, loss: 0.06593179702758789
2023-01-23 02:23:25.899623: step: 1776/526, loss: 0.0014391898876056075
2023-01-23 02:23:27.068339: step: 1780/526, loss: 0.039015673100948334
2023-01-23 02:23:28.208683: step: 1784/526, loss: 0.02459716796875
2023-01-23 02:23:29.350852: step: 1788/526, loss: 0.020014189183712006
2023-01-23 02:23:30.476191: step: 1792/526, loss: 0.031155109405517578
2023-01-23 02:23:31.607459: step: 1796/526, loss: 0.006568908225744963
2023-01-23 02:23:32.748899: step: 1800/526, loss: 0.0071121216751635075
2023-01-23 02:23:33.953010: step: 1804/526, loss: 0.0051132203079760075
2023-01-23 02:23:35.107839: step: 1808/526, loss: 0.002435970352962613
2023-01-23 02:23:36.241747: step: 1812/526, loss: 0.005366229917854071
2023-01-23 02:23:37.372977: step: 1816/526, loss: 0.0003819465928245336
2023-01-23 02:23:38.547816: step: 1820/526, loss: 0.033179473131895065
2023-01-23 02:23:39.706065: step: 1824/526, loss: 0.0011067867744714022
2023-01-23 02:23:40.878703: step: 1828/526, loss: 0.004168510437011719
2023-01-23 02:23:42.064656: step: 1832/526, loss: 0.003395223757252097
2023-01-23 02:23:43.196329: step: 1836/526, loss: 0.003672695253044367
2023-01-23 02:23:44.322160: step: 1840/526, loss: 0.00021986961655784398
2023-01-23 02:23:45.470561: step: 1844/526, loss: 0.04323158040642738
2023-01-23 02:23:46.596828: step: 1848/526, loss: 0.03374312072992325
2023-01-23 02:23:47.773284: step: 1852/526, loss: 0.028297901153564453
2023-01-23 02:23:48.913175: step: 1856/526, loss: 0.01671133004128933
2023-01-23 02:23:50.023869: step: 1860/526, loss: 0.009083127602934837
2023-01-23 02:23:51.190910: step: 1864/526, loss: 0.006672191899269819
2023-01-23 02:23:52.316579: step: 1868/526, loss: 0.012367821298539639
2023-01-23 02:23:53.442194: step: 1872/526, loss: 0.04822073131799698
2023-01-23 02:23:54.569265: step: 1876/526, loss: 0.004676866345107555
2023-01-23 02:23:55.676974: step: 1880/526, loss: 0.000821018242277205
2023-01-23 02:23:56.848996: step: 1884/526, loss: 0.17603187263011932
2023-01-23 02:23:57.999950: step: 1888/526, loss: 0.04731273651123047
2023-01-23 02:23:59.129629: step: 1892/526, loss: 0.012217044830322266
2023-01-23 02:24:00.276581: step: 1896/526, loss: 0.13915623724460602
2023-01-23 02:24:01.413555: step: 1900/526, loss: 0.0026071546599268913
2023-01-23 02:24:02.553417: step: 1904/526, loss: 0.00045003893319517374
2023-01-23 02:24:03.673900: step: 1908/526, loss: 0.006118870340287685
2023-01-23 02:24:04.818049: step: 1912/526, loss: 0.04653315618634224
2023-01-23 02:24:05.985980: step: 1916/526, loss: 0.03326454386115074
2023-01-23 02:24:07.107304: step: 1920/526, loss: 0.0023725510109215975
2023-01-23 02:24:08.271131: step: 1924/526, loss: 0.0069987536408007145
2023-01-23 02:24:09.396568: step: 1928/526, loss: 0.0011455535423010588
2023-01-23 02:24:10.543191: step: 1932/526, loss: 0.01862793043255806
2023-01-23 02:24:11.650585: step: 1936/526, loss: 0.11043939739465714
2023-01-23 02:24:12.786436: step: 1940/526, loss: 0.007619666866958141
2023-01-23 02:24:13.907673: step: 1944/526, loss: 0.078722283244133
2023-01-23 02:24:15.059677: step: 1948/526, loss: 0.052454378455877304
2023-01-23 02:24:16.188246: step: 1952/526, loss: 0.022197771817445755
2023-01-23 02:24:17.322182: step: 1956/526, loss: 5.53131121705519e-06
2023-01-23 02:24:18.433867: step: 1960/526, loss: 0.06036224216222763
2023-01-23 02:24:19.578550: step: 1964/526, loss: 0.06706800311803818
2023-01-23 02:24:20.701478: step: 1968/526, loss: 0.02777853049337864
2023-01-23 02:24:21.850592: step: 1972/526, loss: 0.28656381368637085
2023-01-23 02:24:22.993855: step: 1976/526, loss: 0.07560410350561142
2023-01-23 02:24:24.131445: step: 1980/526, loss: 0.0016263008583337069
2023-01-23 02:24:25.265636: step: 1984/526, loss: 0.01938037946820259
2023-01-23 02:24:26.397920: step: 1988/526, loss: 0.01508321799337864
2023-01-23 02:24:27.562796: step: 1992/526, loss: 0.03717451170086861
2023-01-23 02:24:28.691548: step: 1996/526, loss: 0.03589196130633354
2023-01-23 02:24:29.819810: step: 2000/526, loss: 0.052363112568855286
2023-01-23 02:24:30.945263: step: 2004/526, loss: 0.01964740827679634
2023-01-23 02:24:32.085919: step: 2008/526, loss: 0.035630084574222565
2023-01-23 02:24:33.227820: step: 2012/526, loss: 0.035118866711854935
2023-01-23 02:24:34.338777: step: 2016/526, loss: 0.0008286953088827431
2023-01-23 02:24:35.468474: step: 2020/526, loss: 0.044460296630859375
2023-01-23 02:24:36.599180: step: 2024/526, loss: 0.01126632746309042
2023-01-23 02:24:37.744679: step: 2028/526, loss: 0.016485977917909622
2023-01-23 02:24:38.864797: step: 2032/526, loss: 0.007075023837387562
2023-01-23 02:24:40.020883: step: 2036/526, loss: 0.03506527096033096
2023-01-23 02:24:41.167681: step: 2040/526, loss: 0.005649232771247625
2023-01-23 02:24:42.280343: step: 2044/526, loss: 0.003901576856151223
2023-01-23 02:24:43.431457: step: 2048/526, loss: 0.00407066335901618
2023-01-23 02:24:44.566291: step: 2052/526, loss: 0.059488486498594284
2023-01-23 02:24:45.715218: step: 2056/526, loss: 0.011468411423265934
2023-01-23 02:24:46.845181: step: 2060/526, loss: 0.001214742660522461
2023-01-23 02:24:47.986834: step: 2064/526, loss: 0.0040495870634913445
2023-01-23 02:24:49.110842: step: 2068/526, loss: 0.002097702119499445
2023-01-23 02:24:50.266140: step: 2072/526, loss: 0.020907068625092506
2023-01-23 02:24:51.382113: step: 2076/526, loss: 0.0009271144517697394
2023-01-23 02:24:52.508259: step: 2080/526, loss: 0.05711951479315758
2023-01-23 02:24:53.636622: step: 2084/526, loss: 0.06822071224451065
2023-01-23 02:24:54.769988: step: 2088/526, loss: 0.0037601469084620476
2023-01-23 02:24:55.930094: step: 2092/526, loss: 0.00111980433575809
2023-01-23 02:24:57.080970: step: 2096/526, loss: 1.564025842526462e-05
2023-01-23 02:24:58.209529: step: 2100/526, loss: 0.02524433098733425
2023-01-23 02:24:59.344566: step: 2104/526, loss: 0.0006954193231649697
==================================================
Loss: 0.032
--------------------
Dev: {'event': {'p': 0.5800575263662512, 'r': 0.8055925432756325, 'f1': 0.6744704570791527}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
Test: {'event': {'p': 0.5962534874451972, 'r': 0.7807933194154488, 'f1': 0.6761581920903954}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
Chinese: {'event': {'p': 0.5747126436781609, 'r': 0.9259259259259259, 'f1': 0.7092198581560283}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
Korean: {'event': {'p': 0.6166666666666667, 'r': 0.5873015873015873, 'f1': 0.6016260162601625}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
Russian: {'event': {'p': 0.48936170212765956, 'r': 0.6388888888888888, 'f1': 0.5542168674698795}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
New best russian model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6389811738648948, 'r': 0.7683089214380826, 'f1': 0.6977025392986699}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Eng Test for Chinese: {'event': {'p': 0.6328626444159179, 'r': 0.7719206680584552, 'f1': 0.6955090524335763}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Sample Chinese: {'event': {'p': 0.6282051282051282, 'r': 0.9074074074074074, 'f1': 0.7424242424242423}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6257995735607675, 'r': 0.7816245006657789, 'f1': 0.6950858496151568}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Eng Test for Korean: {'event': {'p': 0.623113410952997, 'r': 0.7541753653444676, 'f1': 0.6824085005903188}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Sample Korean: {'event': {'p': 0.7446808510638298, 'r': 0.5555555555555556, 'f1': 0.6363636363636364}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5800575263662512, 'r': 0.8055925432756325, 'f1': 0.6744704570791527}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
Eng Test for Russian: {'event': {'p': 0.5962534874451972, 'r': 0.7807933194154488, 'f1': 0.6761581920903954}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
Sample Russian: {'event': {'p': 0.48936170212765956, 'r': 0.6388888888888888, 'f1': 0.5542168674698795}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
******************************
Epoch: 17
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 02:25:51.460794: step: 4/526, loss: 0.02712268754839897
2023-01-23 02:25:52.580089: step: 8/526, loss: 0.001408039010129869
2023-01-23 02:25:53.751053: step: 12/526, loss: 0.012801457196474075
2023-01-23 02:25:54.906820: step: 16/526, loss: 0.0024095536209642887
2023-01-23 02:25:56.010282: step: 20/526, loss: 0.09601977467536926
2023-01-23 02:25:57.173883: step: 24/526, loss: 0.0018514633411541581
2023-01-23 02:25:58.303852: step: 28/526, loss: 0.025252724066376686
2023-01-23 02:25:59.465356: step: 32/526, loss: 0.0019448280800133944
2023-01-23 02:26:00.658676: step: 36/526, loss: 0.08267202973365784
2023-01-23 02:26:01.782085: step: 40/526, loss: 0.05796356499195099
2023-01-23 02:26:02.912140: step: 44/526, loss: 0.004552364349365234
2023-01-23 02:26:04.053291: step: 48/526, loss: 0.03374652937054634
2023-01-23 02:26:05.185749: step: 52/526, loss: 0.005305671598762274
2023-01-23 02:26:06.319109: step: 56/526, loss: 0.07305049896240234
2023-01-23 02:26:07.433938: step: 60/526, loss: 0.06041393429040909
2023-01-23 02:26:08.542063: step: 64/526, loss: 0.004543781280517578
2023-01-23 02:26:09.685673: step: 68/526, loss: 0.040546514093875885
2023-01-23 02:26:10.828620: step: 72/526, loss: 0.0002662658516783267
2023-01-23 02:26:11.956073: step: 76/526, loss: 0.0124657629057765
2023-01-23 02:26:13.101138: step: 80/526, loss: 0.08264666050672531
2023-01-23 02:26:14.241613: step: 84/526, loss: 0.005223465152084827
2023-01-23 02:26:15.392533: step: 88/526, loss: 0.015918731689453125
2023-01-23 02:26:16.529951: step: 92/526, loss: 0.003290843917056918
2023-01-23 02:26:17.651571: step: 96/526, loss: 0.01964450068771839
2023-01-23 02:26:18.779027: step: 100/526, loss: 0.029907705262303352
2023-01-23 02:26:19.921213: step: 104/526, loss: 0.0026391029823571444
2023-01-23 02:26:21.068435: step: 108/526, loss: 0.01197052001953125
2023-01-23 02:26:22.182000: step: 112/526, loss: 0.0004809380043298006
2023-01-23 02:26:23.278358: step: 116/526, loss: 0.02562703564763069
2023-01-23 02:26:24.423377: step: 120/526, loss: 1.3805336952209473
2023-01-23 02:26:25.548580: step: 124/526, loss: 0.030428458005189896
2023-01-23 02:26:26.679253: step: 128/526, loss: 0.0010852813720703125
2023-01-23 02:26:27.830876: step: 132/526, loss: 0.029212377965450287
2023-01-23 02:26:28.979027: step: 136/526, loss: 0.010221099480986595
2023-01-23 02:26:30.142646: step: 140/526, loss: 0.0008207320934161544
2023-01-23 02:26:31.249243: step: 144/526, loss: 0.03578338772058487
2023-01-23 02:26:32.405407: step: 148/526, loss: 0.028288459405303
2023-01-23 02:26:33.540871: step: 152/526, loss: 0.028358841314911842
2023-01-23 02:26:34.661614: step: 156/526, loss: -7.152557373046875e-06
2023-01-23 02:26:35.800478: step: 160/526, loss: 0.038114070892333984
2023-01-23 02:26:36.929268: step: 164/526, loss: 0.0076299188658595085
2023-01-23 02:26:38.056181: step: 168/526, loss: 0.02585907094180584
2023-01-23 02:26:39.185263: step: 172/526, loss: 0.0006128311506472528
2023-01-23 02:26:40.334592: step: 176/526, loss: 0.020081330090761185
2023-01-23 02:26:41.492825: step: 180/526, loss: 0.0035316466819494963
2023-01-23 02:26:42.585856: step: 184/526, loss: 0.0006196022150106728
2023-01-23 02:26:43.746053: step: 188/526, loss: 0.04908294603228569
2023-01-23 02:26:44.870340: step: 192/526, loss: 0.0001585006684763357
2023-01-23 02:26:46.030234: step: 196/526, loss: 0.03778076171875
2023-01-23 02:26:47.170064: step: 200/526, loss: 0.0007956505287438631
2023-01-23 02:26:48.341144: step: 204/526, loss: 0.0016698837280273438
2023-01-23 02:26:49.447677: step: 208/526, loss: 0.01373300515115261
2023-01-23 02:26:50.586719: step: 212/526, loss: 0.006088066380470991
2023-01-23 02:26:51.749570: step: 216/526, loss: 0.050337694585323334
2023-01-23 02:26:52.887461: step: 220/526, loss: 0.005057477857917547
2023-01-23 02:26:54.002467: step: 224/526, loss: 0.0005259513854980469
2023-01-23 02:26:55.146506: step: 228/526, loss: 0.018445681780576706
2023-01-23 02:26:56.281039: step: 232/526, loss: 0.001512980554252863
2023-01-23 02:26:57.428297: step: 236/526, loss: 0.000976181065198034
2023-01-23 02:26:58.547827: step: 240/526, loss: 0.008683395572006702
2023-01-23 02:26:59.681304: step: 244/526, loss: 0.03286619111895561
2023-01-23 02:27:00.813801: step: 248/526, loss: 0.0032364847138524055
2023-01-23 02:27:01.953124: step: 252/526, loss: 0.07784061133861542
2023-01-23 02:27:03.111334: step: 256/526, loss: 0.046559907495975494
2023-01-23 02:27:04.219363: step: 260/526, loss: 0.004661845974624157
2023-01-23 02:27:05.358191: step: 264/526, loss: 0.001417827676050365
2023-01-23 02:27:06.488176: step: 268/526, loss: 1.7642974853515625e-05
2023-01-23 02:27:07.611256: step: 272/526, loss: 0.007066536229103804
2023-01-23 02:27:08.742864: step: 276/526, loss: 0.00266265869140625
2023-01-23 02:27:09.919409: step: 280/526, loss: 0.00022516549506690353
2023-01-23 02:27:11.061248: step: 284/526, loss: 6.246566772460938e-05
2023-01-23 02:27:12.203875: step: 288/526, loss: 0.0021077156998217106
2023-01-23 02:27:13.354222: step: 292/526, loss: 0.023946000263094902
2023-01-23 02:27:14.463214: step: 296/526, loss: 0.004250526428222656
2023-01-23 02:27:15.590032: step: 300/526, loss: 0.023140527307987213
2023-01-23 02:27:16.748164: step: 304/526, loss: 0.008922828361392021
2023-01-23 02:27:17.900636: step: 308/526, loss: 0.008628463372588158
2023-01-23 02:27:19.058806: step: 312/526, loss: 0.013683510944247246
2023-01-23 02:27:20.208632: step: 316/526, loss: 0.038454435765743256
2023-01-23 02:27:21.361062: step: 320/526, loss: 0.0037343979347497225
2023-01-23 02:27:22.490398: step: 324/526, loss: 4.76837158203125e-06
2023-01-23 02:27:23.653048: step: 328/526, loss: 0.006391811650246382
2023-01-23 02:27:24.784065: step: 332/526, loss: 0.0008426666026934981
2023-01-23 02:27:25.922879: step: 336/526, loss: 0.01620674319565296
2023-01-23 02:27:27.034012: step: 340/526, loss: 0.0063485149294137955
2023-01-23 02:27:28.176907: step: 344/526, loss: 0.05706596374511719
2023-01-23 02:27:29.313187: step: 348/526, loss: 0.014854812994599342
2023-01-23 02:27:30.479196: step: 352/526, loss: 0.018103981390595436
2023-01-23 02:27:31.609071: step: 356/526, loss: 0.013170433230698109
2023-01-23 02:27:32.741073: step: 360/526, loss: 0.00872888509184122
2023-01-23 02:27:33.877952: step: 364/526, loss: 0.0010667801834642887
2023-01-23 02:27:35.009774: step: 368/526, loss: 0.010018778033554554
2023-01-23 02:27:36.160319: step: 372/526, loss: 0.003550910856574774
2023-01-23 02:27:37.298083: step: 376/526, loss: 0.0032329559326171875
2023-01-23 02:27:38.436819: step: 380/526, loss: 0.036969948559999466
2023-01-23 02:27:39.554271: step: 384/526, loss: 0.01533060148358345
2023-01-23 02:27:40.683415: step: 388/526, loss: 0.0010803223121911287
2023-01-23 02:27:41.801324: step: 392/526, loss: 0.03152661398053169
2023-01-23 02:27:42.938607: step: 396/526, loss: 0.03798218071460724
2023-01-23 02:27:44.103610: step: 400/526, loss: 0.022547628730535507
2023-01-23 02:27:45.264322: step: 404/526, loss: 0.0395687110722065
2023-01-23 02:27:46.397349: step: 408/526, loss: 0.018436836078763008
2023-01-23 02:27:47.516020: step: 412/526, loss: 0.0046918392181396484
2023-01-23 02:27:48.663969: step: 416/526, loss: 0.002600288251414895
2023-01-23 02:27:49.797899: step: 420/526, loss: 0.00018777848163153976
2023-01-23 02:27:50.901092: step: 424/526, loss: 0.0015184402000159025
2023-01-23 02:27:52.021234: step: 428/526, loss: 0.008309555239975452
2023-01-23 02:27:53.131149: step: 432/526, loss: 0.014017963781952858
2023-01-23 02:27:54.256322: step: 436/526, loss: 0.017172621563076973
2023-01-23 02:27:55.400181: step: 440/526, loss: 0.008749008178710938
2023-01-23 02:27:56.525980: step: 444/526, loss: 0.029176950454711914
2023-01-23 02:27:57.693342: step: 448/526, loss: 0.004161929711699486
2023-01-23 02:27:58.850202: step: 452/526, loss: 0.13465367257595062
2023-01-23 02:27:59.974156: step: 456/526, loss: 0.00015053153038024902
2023-01-23 02:28:01.110902: step: 460/526, loss: 0.015687370672822
2023-01-23 02:28:02.233887: step: 464/526, loss: 0.0012549401726573706
2023-01-23 02:28:03.357659: step: 468/526, loss: 0.0904931128025055
2023-01-23 02:28:04.502300: step: 472/526, loss: 0.0018959998851642013
2023-01-23 02:28:05.628452: step: 476/526, loss: 0.007970333099365234
2023-01-23 02:28:06.737836: step: 480/526, loss: 0.0007155895000323653
2023-01-23 02:28:07.902226: step: 484/526, loss: 0.019067956134676933
2023-01-23 02:28:09.032662: step: 488/526, loss: 0.039622265845537186
2023-01-23 02:28:10.181209: step: 492/526, loss: 0.009263277053833008
2023-01-23 02:28:11.305661: step: 496/526, loss: 0.0007642745622433722
2023-01-23 02:28:12.477121: step: 500/526, loss: 0.02133016474545002
2023-01-23 02:28:13.626923: step: 504/526, loss: 0.001066494034603238
2023-01-23 02:28:14.743906: step: 508/526, loss: 0.018526649102568626
2023-01-23 02:28:15.884636: step: 512/526, loss: 0.020804978907108307
2023-01-23 02:28:17.050915: step: 516/526, loss: 0.00030651091947220266
2023-01-23 02:28:18.222289: step: 520/526, loss: 0.004455185029655695
2023-01-23 02:28:19.374963: step: 524/526, loss: 0.017485808581113815
2023-01-23 02:28:20.532052: step: 528/526, loss: 0.07302455604076385
2023-01-23 02:28:21.651934: step: 532/526, loss: 0.013042259030044079
2023-01-23 02:28:22.777549: step: 536/526, loss: 0.10113011300563812
2023-01-23 02:28:23.920385: step: 540/526, loss: 0.09660720825195312
2023-01-23 02:28:25.064244: step: 544/526, loss: 0.1760028898715973
2023-01-23 02:28:26.202462: step: 548/526, loss: 0.03047924116253853
2023-01-23 02:28:27.313445: step: 552/526, loss: 0.00045604706974700093
2023-01-23 02:28:28.450156: step: 556/526, loss: 0.019284822046756744
2023-01-23 02:28:29.612927: step: 560/526, loss: 0.1884039044380188
2023-01-23 02:28:30.734181: step: 564/526, loss: 0.002670383546501398
2023-01-23 02:28:31.875682: step: 568/526, loss: 0.001455974648706615
2023-01-23 02:28:33.040967: step: 572/526, loss: 0.0010818482842296362
2023-01-23 02:28:34.158340: step: 576/526, loss: 0.027611160650849342
2023-01-23 02:28:35.276765: step: 580/526, loss: 0.01098489761352539
2023-01-23 02:28:36.426285: step: 584/526, loss: 0.00024318695068359375
2023-01-23 02:28:37.565621: step: 588/526, loss: 0.0003849029599223286
2023-01-23 02:28:38.705811: step: 592/526, loss: 0.0005496024969033897
2023-01-23 02:28:39.854573: step: 596/526, loss: 0.023192215710878372
2023-01-23 02:28:40.981556: step: 600/526, loss: 0.00019583702669478953
2023-01-23 02:28:42.128792: step: 604/526, loss: 0.03303699195384979
2023-01-23 02:28:43.248722: step: 608/526, loss: 0.005811119452118874
2023-01-23 02:28:44.400577: step: 612/526, loss: 0.019014358520507812
2023-01-23 02:28:45.551837: step: 616/526, loss: 0.016980934888124466
2023-01-23 02:28:46.681263: step: 620/526, loss: 0.020771218463778496
2023-01-23 02:28:47.827987: step: 624/526, loss: 0.007435798645019531
2023-01-23 02:28:48.985067: step: 628/526, loss: 0.009545231238007545
2023-01-23 02:28:50.120113: step: 632/526, loss: 0.0004153251647949219
2023-01-23 02:28:51.239618: step: 636/526, loss: 0.0009140014881268144
2023-01-23 02:28:52.379896: step: 640/526, loss: 0.0005583763122558594
2023-01-23 02:28:53.523519: step: 644/526, loss: 0.014668464660644531
2023-01-23 02:28:54.659784: step: 648/526, loss: 0.0015415191883221269
2023-01-23 02:28:55.800578: step: 652/526, loss: 0.0037648677825927734
2023-01-23 02:28:56.917517: step: 656/526, loss: 0.0073036192916333675
2023-01-23 02:28:58.044275: step: 660/526, loss: 0.04812183603644371
2023-01-23 02:28:59.157058: step: 664/526, loss: 0.010242628864943981
2023-01-23 02:29:00.284268: step: 668/526, loss: 0.010446930304169655
2023-01-23 02:29:01.410896: step: 672/526, loss: 0.0010035515297204256
2023-01-23 02:29:02.529888: step: 676/526, loss: 0.0029952051118016243
2023-01-23 02:29:03.659572: step: 680/526, loss: 0.013922125101089478
2023-01-23 02:29:04.760724: step: 684/526, loss: 0.007066535763442516
2023-01-23 02:29:05.906036: step: 688/526, loss: 0.00043640134390443563
2023-01-23 02:29:07.016824: step: 692/526, loss: 6.103515261202119e-06
2023-01-23 02:29:08.156872: step: 696/526, loss: 0.0038742662873119116
2023-01-23 02:29:09.272187: step: 700/526, loss: 0.00345191964879632
2023-01-23 02:29:10.425699: step: 704/526, loss: 0.052428338676691055
2023-01-23 02:29:11.567204: step: 708/526, loss: 0.0028247355949133635
2023-01-23 02:29:12.771007: step: 712/526, loss: 0.0007513046730309725
2023-01-23 02:29:13.921331: step: 716/526, loss: 0.011724472045898438
2023-01-23 02:29:15.046831: step: 720/526, loss: 7.221699343062937e-05
2023-01-23 02:29:16.171263: step: 724/526, loss: 0.018499374389648438
2023-01-23 02:29:17.292994: step: 728/526, loss: 0.024643326178193092
2023-01-23 02:29:18.407253: step: 732/526, loss: 0.010480117984116077
2023-01-23 02:29:19.540326: step: 736/526, loss: 0.0007181167602539062
2023-01-23 02:29:20.678777: step: 740/526, loss: 0.008913851343095303
2023-01-23 02:29:21.825967: step: 744/526, loss: 5.4168704082258046e-05
2023-01-23 02:29:22.982130: step: 748/526, loss: 0.009173410944640636
2023-01-23 02:29:24.143609: step: 752/526, loss: 0.0004017830069642514
2023-01-23 02:29:25.261583: step: 756/526, loss: 0.13221673667430878
2023-01-23 02:29:26.421854: step: 760/526, loss: 0.1255381554365158
2023-01-23 02:29:27.573882: step: 764/526, loss: 0.005768394563347101
2023-01-23 02:29:28.677453: step: 768/526, loss: 0.033943939954042435
2023-01-23 02:29:29.823958: step: 772/526, loss: 0.037000179290771484
2023-01-23 02:29:30.958337: step: 776/526, loss: 0.0602506622672081
2023-01-23 02:29:32.103945: step: 780/526, loss: 0.03467750549316406
2023-01-23 02:29:33.209126: step: 784/526, loss: 0.00912933424115181
2023-01-23 02:29:34.353837: step: 788/526, loss: 0.0054340362548828125
2023-01-23 02:29:35.493901: step: 792/526, loss: 0.0002578258572611958
2023-01-23 02:29:36.640625: step: 796/526, loss: 0.3241601884365082
2023-01-23 02:29:37.794689: step: 800/526, loss: 0.035428620874881744
2023-01-23 02:29:38.929128: step: 804/526, loss: 0.006259727291762829
2023-01-23 02:29:40.083939: step: 808/526, loss: 0.01959390565752983
2023-01-23 02:29:41.238132: step: 812/526, loss: 0.0006286621210165322
2023-01-23 02:29:42.344515: step: 816/526, loss: 0.0002814769686665386
2023-01-23 02:29:43.476326: step: 820/526, loss: 0.02241516299545765
2023-01-23 02:29:44.610758: step: 824/526, loss: 0.00877304095774889
2023-01-23 02:29:45.772251: step: 828/526, loss: 0.03837409242987633
2023-01-23 02:29:46.899791: step: 832/526, loss: 0.007070064544677734
2023-01-23 02:29:48.030701: step: 836/526, loss: 0.00011606216139625758
2023-01-23 02:29:49.183618: step: 840/526, loss: 0.0033384801354259253
2023-01-23 02:29:50.319685: step: 844/526, loss: 0.008058643899857998
2023-01-23 02:29:51.502794: step: 848/526, loss: 0.14827671647071838
2023-01-23 02:29:52.611977: step: 852/526, loss: 0.020801736041903496
2023-01-23 02:29:53.727034: step: 856/526, loss: 0.022509479895234108
2023-01-23 02:29:54.851120: step: 860/526, loss: 0.22603388130664825
2023-01-23 02:29:55.974075: step: 864/526, loss: 0.035506583750247955
2023-01-23 02:29:57.101588: step: 868/526, loss: 0.0006921768072061241
2023-01-23 02:29:58.239833: step: 872/526, loss: 0.0003002643643412739
2023-01-23 02:29:59.366990: step: 876/526, loss: 0.01151504460722208
2023-01-23 02:30:00.511325: step: 880/526, loss: 0.07331258058547974
2023-01-23 02:30:01.653735: step: 884/526, loss: 0.0001354217529296875
2023-01-23 02:30:02.787233: step: 888/526, loss: 0.4261000454425812
2023-01-23 02:30:03.913097: step: 892/526, loss: 0.0052032470703125
2023-01-23 02:30:05.032283: step: 896/526, loss: 0.10094952583312988
2023-01-23 02:30:06.170950: step: 900/526, loss: 0.01489410363137722
2023-01-23 02:30:07.276043: step: 904/526, loss: 0.014415360055863857
2023-01-23 02:30:08.398601: step: 908/526, loss: 0.004832458682358265
2023-01-23 02:30:09.513587: step: 912/526, loss: 0.010731220245361328
2023-01-23 02:30:10.692109: step: 916/526, loss: 0.031651876866817474
2023-01-23 02:30:11.830332: step: 920/526, loss: 0.00012969970703125
2023-01-23 02:30:12.961702: step: 924/526, loss: 0.003452110104262829
2023-01-23 02:30:14.077508: step: 928/526, loss: 0.0018125057686120272
2023-01-23 02:30:15.221269: step: 932/526, loss: 0.0011042595142498612
2023-01-23 02:30:16.381913: step: 936/526, loss: 0.0008923053974285722
2023-01-23 02:30:17.491540: step: 940/526, loss: 0.062303829938173294
2023-01-23 02:30:18.636984: step: 944/526, loss: 0.0046176910400390625
2023-01-23 02:30:19.798756: step: 948/526, loss: 0.013587666675448418
2023-01-23 02:30:20.915607: step: 952/526, loss: 0.027117349207401276
2023-01-23 02:30:22.067565: step: 956/526, loss: 0.01620473898947239
2023-01-23 02:30:23.208667: step: 960/526, loss: 0.024223709478974342
2023-01-23 02:30:24.341307: step: 964/526, loss: 0.0005677223089151084
2023-01-23 02:30:25.490289: step: 968/526, loss: 0.049275971949100494
2023-01-23 02:30:26.625078: step: 972/526, loss: 0.013196706771850586
2023-01-23 02:30:27.766942: step: 976/526, loss: 0.004477214999496937
2023-01-23 02:30:28.900269: step: 980/526, loss: 0.0018205642700195312
2023-01-23 02:30:30.031806: step: 984/526, loss: 0.0017698288429528475
2023-01-23 02:30:31.165386: step: 988/526, loss: 0.08145418763160706
2023-01-23 02:30:32.299693: step: 992/526, loss: 0.03809700161218643
2023-01-23 02:30:33.470489: step: 996/526, loss: 0.0009351730113849044
2023-01-23 02:30:34.610753: step: 1000/526, loss: 0.009448624216020107
2023-01-23 02:30:35.748300: step: 1004/526, loss: 0.005946922115981579
2023-01-23 02:30:36.875617: step: 1008/526, loss: 0.0005452156183309853
2023-01-23 02:30:38.006554: step: 1012/526, loss: 0.0021003722213208675
2023-01-23 02:30:39.133162: step: 1016/526, loss: 1.2731552487821318e-05
2023-01-23 02:30:40.298500: step: 1020/526, loss: 0.01615314558148384
2023-01-23 02:30:41.419455: step: 1024/526, loss: 0.04951968044042587
2023-01-23 02:30:42.558448: step: 1028/526, loss: 0.0113379480317235
2023-01-23 02:30:43.690763: step: 1032/526, loss: 0.003451442578807473
2023-01-23 02:30:44.821584: step: 1036/526, loss: 0.002733421279117465
2023-01-23 02:30:46.005153: step: 1040/526, loss: 0.059688374400138855
2023-01-23 02:30:47.146047: step: 1044/526, loss: 0.05275745689868927
2023-01-23 02:30:48.296930: step: 1048/526, loss: 0.0033521652221679688
2023-01-23 02:30:49.436169: step: 1052/526, loss: 8.0108642578125e-05
2023-01-23 02:30:50.536186: step: 1056/526, loss: 0.0004809856473002583
2023-01-23 02:30:51.666290: step: 1060/526, loss: 0.02368602715432644
2023-01-23 02:30:52.810901: step: 1064/526, loss: 0.025569915771484375
2023-01-23 02:30:53.931322: step: 1068/526, loss: 0.0009590148692950606
2023-01-23 02:30:55.056645: step: 1072/526, loss: 0.006788397207856178
2023-01-23 02:30:56.207523: step: 1076/526, loss: 0.007541084196418524
2023-01-23 02:30:57.326572: step: 1080/526, loss: 0.02177600748836994
2023-01-23 02:30:58.484171: step: 1084/526, loss: 0.010368348099291325
2023-01-23 02:30:59.588387: step: 1088/526, loss: 0.02678089216351509
2023-01-23 02:31:00.728539: step: 1092/526, loss: 0.00021057129197288305
2023-01-23 02:31:01.878984: step: 1096/526, loss: 0.06157388910651207
2023-01-23 02:31:03.019858: step: 1100/526, loss: 0.006807089317589998
2023-01-23 02:31:04.167918: step: 1104/526, loss: 0.0009675025357864797
2023-01-23 02:31:05.298026: step: 1108/526, loss: 0.0021232604049146175
2023-01-23 02:31:06.435936: step: 1112/526, loss: 0.013833428733050823
2023-01-23 02:31:07.557296: step: 1116/526, loss: 0.021033724769949913
2023-01-23 02:31:08.677403: step: 1120/526, loss: 0.03125705569982529
2023-01-23 02:31:09.786431: step: 1124/526, loss: 0.0031599043868482113
2023-01-23 02:31:10.921384: step: 1128/526, loss: 0.00025959016056731343
2023-01-23 02:31:12.075609: step: 1132/526, loss: 0.01864500157535076
2023-01-23 02:31:13.203927: step: 1136/526, loss: 0.03527240827679634
2023-01-23 02:31:14.324431: step: 1140/526, loss: 0.02262091636657715
2023-01-23 02:31:15.491199: step: 1144/526, loss: 0.008797263726592064
2023-01-23 02:31:16.619813: step: 1148/526, loss: 0.02583150938153267
2023-01-23 02:31:17.766078: step: 1152/526, loss: 0.05012664943933487
2023-01-23 02:31:18.938249: step: 1156/526, loss: -7.4386593951203395e-06
2023-01-23 02:31:20.074300: step: 1160/526, loss: 0.0020987512543797493
2023-01-23 02:31:21.213673: step: 1164/526, loss: 0.0019715309608727694
2023-01-23 02:31:22.325840: step: 1168/526, loss: 0.0058629512786865234
2023-01-23 02:31:23.435718: step: 1172/526, loss: 0.004943275358527899
2023-01-23 02:31:24.565916: step: 1176/526, loss: 0.053217317909002304
2023-01-23 02:31:25.687915: step: 1180/526, loss: 0.016385745257139206
2023-01-23 02:31:26.815529: step: 1184/526, loss: 0.017311764881014824
2023-01-23 02:31:27.965056: step: 1188/526, loss: 0.027155686169862747
2023-01-23 02:31:29.096594: step: 1192/526, loss: 0.09188447892665863
2023-01-23 02:31:30.228129: step: 1196/526, loss: 0.024518754333257675
2023-01-23 02:31:31.337316: step: 1200/526, loss: 0.0013476371532306075
2023-01-23 02:31:32.468105: step: 1204/526, loss: 0.028818178921937943
2023-01-23 02:31:33.576550: step: 1208/526, loss: 0.07680292427539825
2023-01-23 02:31:34.680152: step: 1212/526, loss: 0.005534553434699774
2023-01-23 02:31:35.797254: step: 1216/526, loss: 0.15463100373744965
2023-01-23 02:31:36.926856: step: 1220/526, loss: 0.019785745069384575
2023-01-23 02:31:38.036776: step: 1224/526, loss: 0.0016452790005132556
2023-01-23 02:31:39.234585: step: 1228/526, loss: 0.19144554436206818
2023-01-23 02:31:40.385122: step: 1232/526, loss: 0.0007670402410440147
2023-01-23 02:31:41.512580: step: 1236/526, loss: 0.024678993970155716
2023-01-23 02:31:42.652374: step: 1240/526, loss: 0.007084846496582031
2023-01-23 02:31:43.806129: step: 1244/526, loss: 0.02675933949649334
2023-01-23 02:31:44.973878: step: 1248/526, loss: 0.0006745815626345575
2023-01-23 02:31:46.121999: step: 1252/526, loss: 0.027397824451327324
2023-01-23 02:31:47.231908: step: 1256/526, loss: 0.001489925431087613
2023-01-23 02:31:48.346929: step: 1260/526, loss: 0.003269004635512829
2023-01-23 02:31:49.492930: step: 1264/526, loss: 0.01984553411602974
2023-01-23 02:31:50.633056: step: 1268/526, loss: 0.1360720694065094
2023-01-23 02:31:51.798514: step: 1272/526, loss: 0.2584635615348816
2023-01-23 02:31:52.928887: step: 1276/526, loss: 0.005172157660126686
2023-01-23 02:31:54.065210: step: 1280/526, loss: 0.04760890081524849
2023-01-23 02:31:55.202927: step: 1284/526, loss: 0.03189058229327202
2023-01-23 02:31:56.319840: step: 1288/526, loss: 0.0071957590989768505
2023-01-23 02:31:57.435371: step: 1292/526, loss: 0.0004414558643475175
2023-01-23 02:31:58.584531: step: 1296/526, loss: 0.005295705981552601
2023-01-23 02:31:59.720206: step: 1300/526, loss: 0.0015960694290697575
2023-01-23 02:32:00.846029: step: 1304/526, loss: 0.020749665796756744
2023-01-23 02:32:01.990256: step: 1308/526, loss: 0.016248416155576706
2023-01-23 02:32:03.158885: step: 1312/526, loss: 0.07596893608570099
2023-01-23 02:32:04.266841: step: 1316/526, loss: 0.00019531250291038305
2023-01-23 02:32:05.425937: step: 1320/526, loss: 0.009435654617846012
2023-01-23 02:32:06.558832: step: 1324/526, loss: 0.00395622244104743
2023-01-23 02:32:07.708386: step: 1328/526, loss: 0.14249287545681
2023-01-23 02:32:08.829107: step: 1332/526, loss: 0.028884029015898705
2023-01-23 02:32:09.954909: step: 1336/526, loss: 0.0010064125526696444
2023-01-23 02:32:11.093331: step: 1340/526, loss: 0.0003430366632528603
2023-01-23 02:32:12.247165: step: 1344/526, loss: 0.024555303156375885
2023-01-23 02:32:13.362605: step: 1348/526, loss: 0.05074882507324219
2023-01-23 02:32:14.507077: step: 1352/526, loss: 0.07233371585607529
2023-01-23 02:32:15.655534: step: 1356/526, loss: 0.022238444536924362
2023-01-23 02:32:16.781160: step: 1360/526, loss: 0.011472320184111595
2023-01-23 02:32:17.907647: step: 1364/526, loss: 0.011249256320297718
2023-01-23 02:32:19.008594: step: 1368/526, loss: 0.010108756832778454
2023-01-23 02:32:20.137983: step: 1372/526, loss: 0.026175880804657936
2023-01-23 02:32:21.258520: step: 1376/526, loss: 0.07446374744176865
2023-01-23 02:32:22.403709: step: 1380/526, loss: 0.007753944024443626
2023-01-23 02:32:23.532304: step: 1384/526, loss: 0.017905618995428085
2023-01-23 02:32:24.658659: step: 1388/526, loss: 0.07091198116540909
2023-01-23 02:32:25.786204: step: 1392/526, loss: 0.00263385777361691
2023-01-23 02:32:26.955209: step: 1396/526, loss: 0.0222946647554636
2023-01-23 02:32:28.097518: step: 1400/526, loss: 0.0017691315151751041
2023-01-23 02:32:29.232609: step: 1404/526, loss: 0.030976485460996628
2023-01-23 02:32:30.365197: step: 1408/526, loss: 0.002493190811946988
2023-01-23 02:32:31.533587: step: 1412/526, loss: 0.0020665167830884457
2023-01-23 02:32:32.658897: step: 1416/526, loss: 0.007055854890495539
2023-01-23 02:32:33.820823: step: 1420/526, loss: 0.00730972271412611
2023-01-23 02:32:34.920684: step: 1424/526, loss: 0.0026132583152502775
2023-01-23 02:32:36.038794: step: 1428/526, loss: 0.01791706122457981
2023-01-23 02:32:37.193910: step: 1432/526, loss: 0.0013868332607671618
2023-01-23 02:32:38.363120: step: 1436/526, loss: 0.021071529015898705
2023-01-23 02:32:39.507600: step: 1440/526, loss: 0.057860471308231354
2023-01-23 02:32:40.636186: step: 1444/526, loss: 0.012936783023178577
2023-01-23 02:32:41.776838: step: 1448/526, loss: 0.0010332107776775956
2023-01-23 02:32:42.910504: step: 1452/526, loss: 0.005069923587143421
2023-01-23 02:32:44.024134: step: 1456/526, loss: 0.0034369470085948706
2023-01-23 02:32:45.163303: step: 1460/526, loss: 3.409385681152344e-05
2023-01-23 02:32:46.300814: step: 1464/526, loss: 0.00012722014798782766
2023-01-23 02:32:47.457055: step: 1468/526, loss: 0.0047471048310399055
2023-01-23 02:32:48.578675: step: 1472/526, loss: 0.006742286495864391
2023-01-23 02:32:49.705190: step: 1476/526, loss: 0.00024127960205078125
2023-01-23 02:32:50.811350: step: 1480/526, loss: 0.0060630799271166325
2023-01-23 02:32:51.993495: step: 1484/526, loss: 0.0009752750629559159
2023-01-23 02:32:53.129817: step: 1488/526, loss: 0.0025264739524573088
2023-01-23 02:32:54.271205: step: 1492/526, loss: 0.019185258075594902
2023-01-23 02:32:55.407749: step: 1496/526, loss: 0.03000679239630699
2023-01-23 02:32:56.547191: step: 1500/526, loss: 0.0030374526977539062
2023-01-23 02:32:57.665969: step: 1504/526, loss: 0.00015316010103560984
2023-01-23 02:32:58.803142: step: 1508/526, loss: 0.03774048015475273
2023-01-23 02:32:59.941171: step: 1512/526, loss: 0.0017588615883141756
2023-01-23 02:33:01.057686: step: 1516/526, loss: 0.0760623961687088
2023-01-23 02:33:02.190977: step: 1520/526, loss: 0.026489639654755592
2023-01-23 02:33:03.325885: step: 1524/526, loss: 0.03952217102050781
2023-01-23 02:33:04.463135: step: 1528/526, loss: 0.03390655294060707
2023-01-23 02:33:05.603944: step: 1532/526, loss: 0.004974079318344593
2023-01-23 02:33:06.756154: step: 1536/526, loss: 0.001953601837158203
2023-01-23 02:33:07.893873: step: 1540/526, loss: 0.0025721550919115543
2023-01-23 02:33:09.023429: step: 1544/526, loss: 0.019340038299560547
2023-01-23 02:33:10.145858: step: 1548/526, loss: 0.0048046112060546875
2023-01-23 02:33:11.330209: step: 1552/526, loss: 0.04182777553796768
2023-01-23 02:33:12.466343: step: 1556/526, loss: 0.0015128612285479903
2023-01-23 02:33:13.626810: step: 1560/526, loss: 0.0004330635129008442
2023-01-23 02:33:14.772523: step: 1564/526, loss: 0.005412387661635876
2023-01-23 02:33:15.928919: step: 1568/526, loss: 0.07815251499414444
2023-01-23 02:33:17.062546: step: 1572/526, loss: 0.08765692263841629
2023-01-23 02:33:18.199740: step: 1576/526, loss: 0.1259164810180664
2023-01-23 02:33:19.312905: step: 1580/526, loss: 0.00020141601271461695
2023-01-23 02:33:20.443966: step: 1584/526, loss: 0.0005550385103560984
2023-01-23 02:33:21.596065: step: 1588/526, loss: 0.1288854479789734
2023-01-23 02:33:22.724637: step: 1592/526, loss: 0.009970474988222122
2023-01-23 02:33:23.856908: step: 1596/526, loss: 0.003493356751278043
2023-01-23 02:33:24.985281: step: 1600/526, loss: 0.03868560865521431
2023-01-23 02:33:26.100293: step: 1604/526, loss: 0.004835701081901789
2023-01-23 02:33:27.233984: step: 1608/526, loss: 0.012922096997499466
2023-01-23 02:33:28.344371: step: 1612/526, loss: 0.03222351148724556
2023-01-23 02:33:29.468069: step: 1616/526, loss: 0.02324523963034153
2023-01-23 02:33:30.607062: step: 1620/526, loss: 0.0004547596035990864
2023-01-23 02:33:31.750869: step: 1624/526, loss: 0.01389312744140625
2023-01-23 02:33:32.898282: step: 1628/526, loss: 0.016480065882205963
2023-01-23 02:33:34.040146: step: 1632/526, loss: 0.0018655776511877775
2023-01-23 02:33:35.173527: step: 1636/526, loss: 0.00044288637582212687
2023-01-23 02:33:36.299125: step: 1640/526, loss: 0.01916208304464817
2023-01-23 02:33:37.476994: step: 1644/526, loss: 0.0024417878594249487
2023-01-23 02:33:38.607507: step: 1648/526, loss: 0.003782844403758645
2023-01-23 02:33:39.727291: step: 1652/526, loss: 0.09213085472583771
2023-01-23 02:33:40.837865: step: 1656/526, loss: 0.0001305341866100207
2023-01-23 02:33:41.978016: step: 1660/526, loss: 0.023404503241181374
2023-01-23 02:33:43.103123: step: 1664/526, loss: 0.01796851120889187
2023-01-23 02:33:44.234028: step: 1668/526, loss: 0.07622671127319336
2023-01-23 02:33:45.457499: step: 1672/526, loss: 0.00355281843803823
2023-01-23 02:33:46.586165: step: 1676/526, loss: 0.011435317806899548
2023-01-23 02:33:47.702461: step: 1680/526, loss: 0.062442779541015625
2023-01-23 02:33:48.824226: step: 1684/526, loss: 0.003697299864143133
2023-01-23 02:33:49.925985: step: 1688/526, loss: 0.0004693031369242817
2023-01-23 02:33:51.061399: step: 1692/526, loss: 0.003188514616340399
2023-01-23 02:33:52.189114: step: 1696/526, loss: 0.0014663697220385075
2023-01-23 02:33:53.319511: step: 1700/526, loss: 0.008653735741972923
2023-01-23 02:33:54.497657: step: 1704/526, loss: 0.05044383928179741
2023-01-23 02:33:55.578618: step: 1708/526, loss: 0.0019284725422039628
2023-01-23 02:33:56.724213: step: 1712/526, loss: 0.0005409240839071572
2023-01-23 02:33:57.857811: step: 1716/526, loss: 0.00618248013779521
2023-01-23 02:33:58.998405: step: 1720/526, loss: 0.004835701081901789
2023-01-23 02:34:00.137145: step: 1724/526, loss: 0.0015562057960778475
2023-01-23 02:34:01.271415: step: 1728/526, loss: 0.03382463380694389
2023-01-23 02:34:02.400746: step: 1732/526, loss: 0.006190681364387274
2023-01-23 02:34:03.499430: step: 1736/526, loss: 0.012252426706254482
2023-01-23 02:34:04.656258: step: 1740/526, loss: 0.02145414426922798
2023-01-23 02:34:05.796926: step: 1744/526, loss: 0.010240936651825905
2023-01-23 02:34:06.948670: step: 1748/526, loss: 0.013096618466079235
2023-01-23 02:34:08.074029: step: 1752/526, loss: 0.07340545952320099
2023-01-23 02:34:09.228270: step: 1756/526, loss: 0.045792482793331146
2023-01-23 02:34:10.378990: step: 1760/526, loss: 0.041458990424871445
2023-01-23 02:34:11.539262: step: 1764/526, loss: 0.012446975335478783
2023-01-23 02:34:12.711919: step: 1768/526, loss: 0.015450382605195045
2023-01-23 02:34:13.901758: step: 1772/526, loss: 0.014376641251146793
2023-01-23 02:34:15.057584: step: 1776/526, loss: 0.00141487130895257
2023-01-23 02:34:16.210173: step: 1780/526, loss: 0.0013548850547522306
2023-01-23 02:34:17.363993: step: 1784/526, loss: 0.015245819464325905
2023-01-23 02:34:18.503286: step: 1788/526, loss: 0.002990627195686102
2023-01-23 02:34:19.650082: step: 1792/526, loss: 0.0029386519454419613
2023-01-23 02:34:20.783802: step: 1796/526, loss: 0.015460300259292126
2023-01-23 02:34:21.902489: step: 1800/526, loss: 0.0013916492462158203
2023-01-23 02:34:23.021366: step: 1804/526, loss: 0.0035120011307299137
2023-01-23 02:34:24.144395: step: 1808/526, loss: 0.024268342182040215
2023-01-23 02:34:25.266833: step: 1812/526, loss: 0.006486320868134499
2023-01-23 02:34:26.389763: step: 1816/526, loss: 0.008128166198730469
2023-01-23 02:34:27.488473: step: 1820/526, loss: 0.0009676933404989541
2023-01-23 02:34:28.620835: step: 1824/526, loss: 0.15685276687145233
2023-01-23 02:34:29.741366: step: 1828/526, loss: 0.00397916417568922
2023-01-23 02:34:30.883483: step: 1832/526, loss: 0.985771119594574
2023-01-23 02:34:32.000471: step: 1836/526, loss: 0.02320842817425728
2023-01-23 02:34:33.152659: step: 1840/526, loss: 0.30618131160736084
2023-01-23 02:34:34.278669: step: 1844/526, loss: 7.877349707996473e-05
2023-01-23 02:34:35.433737: step: 1848/526, loss: 0.012806988321244717
2023-01-23 02:34:36.557883: step: 1852/526, loss: 0.002792453859001398
2023-01-23 02:34:37.768581: step: 1856/526, loss: 0.01624937169253826
2023-01-23 02:34:38.908097: step: 1860/526, loss: 0.029878806322813034
2023-01-23 02:34:40.053794: step: 1864/526, loss: 0.01139225997030735
2023-01-23 02:34:41.164414: step: 1868/526, loss: 0.009100723080337048
2023-01-23 02:34:42.285845: step: 1872/526, loss: 0.004316282458603382
2023-01-23 02:34:43.437097: step: 1876/526, loss: 0.0011700630420818925
2023-01-23 02:34:44.565350: step: 1880/526, loss: 0.0056847091764211655
2023-01-23 02:34:45.697901: step: 1884/526, loss: 0.01797514036297798
2023-01-23 02:34:46.842305: step: 1888/526, loss: 0.013667869381606579
2023-01-23 02:34:47.960327: step: 1892/526, loss: 0.005320072639733553
2023-01-23 02:34:49.101584: step: 1896/526, loss: 0.0018579482566565275
2023-01-23 02:34:50.239287: step: 1900/526, loss: 0.0007995605119504035
2023-01-23 02:34:51.379719: step: 1904/526, loss: 0.01890571229159832
2023-01-23 02:34:52.493546: step: 1908/526, loss: 0.00027914048405364156
2023-01-23 02:34:53.649020: step: 1912/526, loss: 0.0026869773864746094
2023-01-23 02:34:54.775368: step: 1916/526, loss: 0.0664713904261589
2023-01-23 02:34:55.919148: step: 1920/526, loss: 0.0016141415107995272
2023-01-23 02:34:57.085529: step: 1924/526, loss: 0.05968360975384712
2023-01-23 02:34:58.225228: step: 1928/526, loss: 0.03923375532031059
2023-01-23 02:34:59.373038: step: 1932/526, loss: 0.0008770108688622713
2023-01-23 02:35:00.504774: step: 1936/526, loss: 0.0027625083457678556
2023-01-23 02:35:01.668916: step: 1940/526, loss: 0.0037410736549645662
2023-01-23 02:35:02.812294: step: 1944/526, loss: 0.010704612359404564
2023-01-23 02:35:03.934520: step: 1948/526, loss: 0.04006776958703995
2023-01-23 02:35:05.071912: step: 1952/526, loss: 0.0019824982155114412
2023-01-23 02:35:06.222588: step: 1956/526, loss: 0.0740472823381424
2023-01-23 02:35:07.333167: step: 1960/526, loss: 0.0035758339799940586
2023-01-23 02:35:08.452390: step: 1964/526, loss: 0.07524452358484268
2023-01-23 02:35:09.571885: step: 1968/526, loss: 0.00036373137845657766
2023-01-23 02:35:10.686618: step: 1972/526, loss: 0.0012372017372399569
2023-01-23 02:35:11.857550: step: 1976/526, loss: 0.06256141513586044
2023-01-23 02:35:12.994489: step: 1980/526, loss: 0.030743980780243874
2023-01-23 02:35:14.138264: step: 1984/526, loss: 0.00283985142596066
2023-01-23 02:35:15.278646: step: 1988/526, loss: 0.008736992254853249
2023-01-23 02:35:16.394457: step: 1992/526, loss: 0.0036020278930664062
2023-01-23 02:35:17.563207: step: 1996/526, loss: 0.035840604454278946
2023-01-23 02:35:18.731713: step: 2000/526, loss: 0.0004417419258970767
2023-01-23 02:35:19.864368: step: 2004/526, loss: 0.047985076904296875
2023-01-23 02:35:21.008425: step: 2008/526, loss: 0.0020084381103515625
2023-01-23 02:35:22.127723: step: 2012/526, loss: 0.0019193650223314762
2023-01-23 02:35:23.266469: step: 2016/526, loss: 0.027818774804472923
2023-01-23 02:35:24.444163: step: 2020/526, loss: 0.003223610110580921
2023-01-23 02:35:25.567703: step: 2024/526, loss: 0.05363426357507706
2023-01-23 02:35:26.692548: step: 2028/526, loss: 0.0018838882679119706
2023-01-23 02:35:27.824752: step: 2032/526, loss: 0.05442104488611221
2023-01-23 02:35:28.954602: step: 2036/526, loss: 0.005970573518425226
2023-01-23 02:35:30.090632: step: 2040/526, loss: 0.0636780709028244
2023-01-23 02:35:31.226133: step: 2044/526, loss: 0.007358265109360218
2023-01-23 02:35:32.378224: step: 2048/526, loss: 0.003989601042121649
2023-01-23 02:35:33.534698: step: 2052/526, loss: 0.05000562593340874
2023-01-23 02:35:34.681592: step: 2056/526, loss: 0.08075566589832306
2023-01-23 02:35:35.818761: step: 2060/526, loss: 0.006933736614882946
2023-01-23 02:35:36.982147: step: 2064/526, loss: 0.03279101848602295
2023-01-23 02:35:38.097030: step: 2068/526, loss: 0.0010629177559167147
2023-01-23 02:35:39.269821: step: 2072/526, loss: 0.001238059950992465
2023-01-23 02:35:40.428654: step: 2076/526, loss: 0.10594367980957031
2023-01-23 02:35:41.576869: step: 2080/526, loss: 0.002029800321906805
2023-01-23 02:35:42.725393: step: 2084/526, loss: 0.14116555452346802
2023-01-23 02:35:43.860445: step: 2088/526, loss: 0.0003570556582417339
2023-01-23 02:35:45.000716: step: 2092/526, loss: 0.016153432428836823
2023-01-23 02:35:46.120585: step: 2096/526, loss: 0.0487184040248394
2023-01-23 02:35:47.302249: step: 2100/526, loss: 0.2527340054512024
2023-01-23 02:35:48.421067: step: 2104/526, loss: 0.05380944907665253
==================================================
Loss: 0.029
--------------------
Dev: {'event': {'p': 0.5993657505285412, 'r': 0.7549933422103862, 'f1': 0.6682380671773719}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
Test: {'event': {'p': 0.6199000832639467, 'r': 0.7771398747390397, 'f1': 0.6896711440481704}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
Chinese: {'event': {'p': 0.5802469135802469, 'r': 0.8703703703703703, 'f1': 0.6962962962962963}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
Korean: {'event': {'p': 0.6341463414634146, 'r': 0.4126984126984127, 'f1': 0.5}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
Russian: {'event': {'p': 0.5, 'r': 0.5555555555555556, 'f1': 0.5263157894736842}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6389811738648948, 'r': 0.7683089214380826, 'f1': 0.6977025392986699}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Eng Test for Chinese: {'event': {'p': 0.6328626444159179, 'r': 0.7719206680584552, 'f1': 0.6955090524335763}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Sample Chinese: {'event': {'p': 0.6282051282051282, 'r': 0.9074074074074074, 'f1': 0.7424242424242423}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6257995735607675, 'r': 0.7816245006657789, 'f1': 0.6950858496151568}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Eng Test for Korean: {'event': {'p': 0.623113410952997, 'r': 0.7541753653444676, 'f1': 0.6824085005903188}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Sample Korean: {'event': {'p': 0.7446808510638298, 'r': 0.5555555555555556, 'f1': 0.6363636363636364}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5800575263662512, 'r': 0.8055925432756325, 'f1': 0.6744704570791527}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
Eng Test for Russian: {'event': {'p': 0.5962534874451972, 'r': 0.7807933194154488, 'f1': 0.6761581920903954}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
Sample Russian: {'event': {'p': 0.48936170212765956, 'r': 0.6388888888888888, 'f1': 0.5542168674698795}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
******************************
Epoch: 18
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 02:36:31.329200: step: 4/526, loss: 0.006751632783561945
2023-01-23 02:36:32.530328: step: 8/526, loss: 0.08588533848524094
2023-01-23 02:36:33.680392: step: 12/526, loss: 0.018348027020692825
2023-01-23 02:36:34.806195: step: 16/526, loss: 0.0015828133327886462
2023-01-23 02:36:35.934462: step: 20/526, loss: 0.011808491311967373
2023-01-23 02:36:37.028960: step: 24/526, loss: 0.0005998611450195312
2023-01-23 02:36:38.149535: step: 28/526, loss: 0.07798881828784943
2023-01-23 02:36:39.302668: step: 32/526, loss: 0.02732066996395588
2023-01-23 02:36:40.452103: step: 36/526, loss: 0.004439449403434992
2023-01-23 02:36:41.573011: step: 40/526, loss: 0.006948280613869429
2023-01-23 02:36:42.691937: step: 44/526, loss: 0.0681842640042305
2023-01-23 02:36:43.852338: step: 48/526, loss: 0.08184299618005753
2023-01-23 02:36:44.969225: step: 52/526, loss: 0.002940845675766468
2023-01-23 02:36:46.115138: step: 56/526, loss: 0.003729534102603793
2023-01-23 02:36:47.233872: step: 60/526, loss: 0.0034748080652207136
2023-01-23 02:36:48.409349: step: 64/526, loss: 0.001116943429224193
2023-01-23 02:36:49.544061: step: 68/526, loss: 0.044062234461307526
2023-01-23 02:36:50.716308: step: 72/526, loss: 0.0335724838078022
2023-01-23 02:36:51.845881: step: 76/526, loss: 0.03290729597210884
2023-01-23 02:36:52.984432: step: 80/526, loss: 0.0008903503767214715
2023-01-23 02:36:54.143714: step: 84/526, loss: 0.00013465881056617945
2023-01-23 02:36:55.266940: step: 88/526, loss: 0.0010342597961425781
2023-01-23 02:36:56.387468: step: 92/526, loss: 0.000347995781339705
2023-01-23 02:36:57.495227: step: 96/526, loss: 0.0003503561019897461
2023-01-23 02:36:58.659245: step: 100/526, loss: 0.09323463588953018
2023-01-23 02:36:59.813304: step: 104/526, loss: 0.013824081979691982
2023-01-23 02:37:00.949783: step: 108/526, loss: 0.0370057113468647
2023-01-23 02:37:02.069077: step: 112/526, loss: 0.012207889929413795
2023-01-23 02:37:03.197608: step: 116/526, loss: 0.03219299390912056
2023-01-23 02:37:04.356269: step: 120/526, loss: 0.011827278882265091
2023-01-23 02:37:05.485212: step: 124/526, loss: 0.007548856548964977
2023-01-23 02:37:06.632690: step: 128/526, loss: 0.025111723691225052
2023-01-23 02:37:07.765293: step: 132/526, loss: 0.0021045685280114412
2023-01-23 02:37:08.881375: step: 136/526, loss: 0.0032861712388694286
2023-01-23 02:37:10.010242: step: 140/526, loss: 0.047944262623786926
2023-01-23 02:37:11.129396: step: 144/526, loss: 0.012397385202348232
2023-01-23 02:37:12.247682: step: 148/526, loss: 0.008004856295883656
2023-01-23 02:37:13.389365: step: 152/526, loss: 0.051562026143074036
2023-01-23 02:37:14.506039: step: 156/526, loss: 0.02565789222717285
2023-01-23 02:37:15.645449: step: 160/526, loss: 0.020117856562137604
2023-01-23 02:37:16.754166: step: 164/526, loss: 0.04840121418237686
2023-01-23 02:37:17.887449: step: 168/526, loss: 0.0011371612781658769
2023-01-23 02:37:19.024913: step: 172/526, loss: 0.008522129617631435
2023-01-23 02:37:20.150760: step: 176/526, loss: 0.003469085553660989
2023-01-23 02:37:21.313664: step: 180/526, loss: 0.004070281982421875
2023-01-23 02:37:22.486384: step: 184/526, loss: 0.010434150695800781
2023-01-23 02:37:23.605975: step: 188/526, loss: 0.011482620611786842
2023-01-23 02:37:24.742549: step: 192/526, loss: 0.0036216736771166325
2023-01-23 02:37:25.861041: step: 196/526, loss: 0.06496667861938477
2023-01-23 02:37:27.001539: step: 200/526, loss: 0.00014371871657203883
2023-01-23 02:37:28.135604: step: 204/526, loss: 0.0011555672390386462
2023-01-23 02:37:29.271738: step: 208/526, loss: 0.003719329833984375
2023-01-23 02:37:30.399118: step: 212/526, loss: 0.0025718689430505037
2023-01-23 02:37:31.517287: step: 216/526, loss: 0.0031719207763671875
2023-01-23 02:37:32.632341: step: 220/526, loss: 0.004272651858627796
2023-01-23 02:37:33.794148: step: 224/526, loss: 0.0006236553308553994
2023-01-23 02:37:34.917809: step: 228/526, loss: 0.011204147711396217
2023-01-23 02:37:36.062658: step: 232/526, loss: 0.004658222198486328
2023-01-23 02:37:37.238450: step: 236/526, loss: 0.08171777427196503
2023-01-23 02:37:38.393104: step: 240/526, loss: 0.0040607452392578125
2023-01-23 02:37:39.510079: step: 244/526, loss: 0.018023205921053886
2023-01-23 02:37:40.677436: step: 248/526, loss: 0.0017507553566247225
2023-01-23 02:37:41.798259: step: 252/526, loss: 0.004785728175193071
2023-01-23 02:37:42.932056: step: 256/526, loss: 0.0007618427043780684
2023-01-23 02:37:44.060362: step: 260/526, loss: 0.00016336441331077367
2023-01-23 02:37:45.170654: step: 264/526, loss: 0.018542669713497162
2023-01-23 02:37:46.297992: step: 268/526, loss: 0.0008250236860476434
2023-01-23 02:37:47.455055: step: 272/526, loss: 0.10582657158374786
2023-01-23 02:37:48.609543: step: 276/526, loss: 0.022313691675662994
2023-01-23 02:37:49.742635: step: 280/526, loss: 0.02405899204313755
2023-01-23 02:37:50.873284: step: 284/526, loss: 0.0092652328312397
2023-01-23 02:37:51.999040: step: 288/526, loss: 0.025114823132753372
2023-01-23 02:37:53.141519: step: 292/526, loss: 0.0009074211120605469
2023-01-23 02:37:54.260388: step: 296/526, loss: 0.03528418764472008
2023-01-23 02:37:55.394484: step: 300/526, loss: 0.0016310691135004163
2023-01-23 02:37:56.511344: step: 304/526, loss: 0.0011116027599200606
2023-01-23 02:37:57.666966: step: 308/526, loss: 0.0032452105078846216
2023-01-23 02:37:58.801162: step: 312/526, loss: 0.007528114598244429
2023-01-23 02:37:59.947545: step: 316/526, loss: 0.003603696823120117
2023-01-23 02:38:01.069211: step: 320/526, loss: 0.04394540935754776
2023-01-23 02:38:02.227701: step: 324/526, loss: 0.01797657087445259
2023-01-23 02:38:03.375941: step: 328/526, loss: 0.01444101333618164
2023-01-23 02:38:04.484992: step: 332/526, loss: 0.01026687677949667
2023-01-23 02:38:05.613299: step: 336/526, loss: 0.03797459602355957
2023-01-23 02:38:06.797985: step: 340/526, loss: 0.00041179655818268657
2023-01-23 02:38:07.948124: step: 344/526, loss: 0.0007867813110351562
2023-01-23 02:38:09.081798: step: 348/526, loss: 0.00028057099552825093
2023-01-23 02:38:10.217511: step: 352/526, loss: 0.004292118828743696
2023-01-23 02:38:11.364623: step: 356/526, loss: 0.0612298958003521
2023-01-23 02:38:12.496172: step: 360/526, loss: 0.04290733486413956
2023-01-23 02:38:13.636268: step: 364/526, loss: 0.0001811981201171875
2023-01-23 02:38:14.741601: step: 368/526, loss: 4.758834620588459e-05
2023-01-23 02:38:15.880204: step: 372/526, loss: 0.0016165734268724918
2023-01-23 02:38:17.007997: step: 376/526, loss: 0.012668227776885033
2023-01-23 02:38:18.169716: step: 380/526, loss: 0.006336403079330921
2023-01-23 02:38:19.290510: step: 384/526, loss: 0.0005701064947061241
2023-01-23 02:38:20.415652: step: 388/526, loss: 0.06245927885174751
2023-01-23 02:38:21.547548: step: 392/526, loss: 0.037491992115974426
2023-01-23 02:38:22.667491: step: 396/526, loss: 0.00023846626572776586
2023-01-23 02:38:23.791335: step: 400/526, loss: 0.01639585569500923
2023-01-23 02:38:24.922597: step: 404/526, loss: 0.015825271606445312
2023-01-23 02:38:26.049116: step: 408/526, loss: 0.0014722824562340975
2023-01-23 02:38:27.153490: step: 412/526, loss: 0.4467828869819641
2023-01-23 02:38:28.289965: step: 416/526, loss: 0.005568218417465687
2023-01-23 02:38:29.441096: step: 420/526, loss: 0.03647371381521225
2023-01-23 02:38:30.572385: step: 424/526, loss: 0.011580754071474075
2023-01-23 02:38:31.694208: step: 428/526, loss: 0.00029234885005280375
2023-01-23 02:38:32.823074: step: 432/526, loss: 0.07661227881908417
2023-01-23 02:38:33.989494: step: 436/526, loss: 0.00045804979163222015
2023-01-23 02:38:35.145955: step: 440/526, loss: 0.008469962514936924
2023-01-23 02:38:36.286221: step: 444/526, loss: 0.248646542429924
2023-01-23 02:38:37.400870: step: 448/526, loss: 0.021618841215968132
2023-01-23 02:38:38.539267: step: 452/526, loss: 0.003064966294914484
2023-01-23 02:38:39.670854: step: 456/526, loss: 0.01999364048242569
2023-01-23 02:38:40.806599: step: 460/526, loss: 0.10535955429077148
2023-01-23 02:38:41.933607: step: 464/526, loss: 0.03682585060596466
2023-01-23 02:38:43.073536: step: 468/526, loss: -4.76837158203125e-06
2023-01-23 02:38:44.251909: step: 472/526, loss: 0.0159517303109169
2023-01-23 02:38:45.375393: step: 476/526, loss: 0.01844158209860325
2023-01-23 02:38:46.545567: step: 480/526, loss: 0.0036512850783765316
2023-01-23 02:38:47.655888: step: 484/526, loss: 0.0010453701252117753
2023-01-23 02:38:48.794137: step: 488/526, loss: 0.00029220583382993937
2023-01-23 02:38:49.924514: step: 492/526, loss: 0.0017512321937829256
2023-01-23 02:38:51.029416: step: 496/526, loss: 0.004153633024543524
2023-01-23 02:38:52.193095: step: 500/526, loss: 0.0034191133454442024
2023-01-23 02:38:53.336073: step: 504/526, loss: 0.007610511966049671
2023-01-23 02:38:54.446054: step: 508/526, loss: 0.0011955260997638106
2023-01-23 02:38:55.563107: step: 512/526, loss: 0.00015220644127111882
2023-01-23 02:38:56.691586: step: 516/526, loss: 0.010968017391860485
2023-01-23 02:38:57.836228: step: 520/526, loss: 0.004528808407485485
2023-01-23 02:38:58.964794: step: 524/526, loss: 0.02071418985724449
2023-01-23 02:39:00.056926: step: 528/526, loss: 0.0004985809791833162
2023-01-23 02:39:01.227447: step: 532/526, loss: 0.03955373913049698
2023-01-23 02:39:02.353889: step: 536/526, loss: 0.009877586737275124
2023-01-23 02:39:03.490586: step: 540/526, loss: 0.0025396349374204874
2023-01-23 02:39:04.612219: step: 544/526, loss: 0.001487827394157648
2023-01-23 02:39:05.770264: step: 548/526, loss: 0.0034872053656727076
2023-01-23 02:39:06.907535: step: 552/526, loss: 0.0031486512161791325
2023-01-23 02:39:08.035996: step: 556/526, loss: 0.00038394928560592234
2023-01-23 02:39:09.194622: step: 560/526, loss: 0.0001447677641408518
2023-01-23 02:39:10.354932: step: 564/526, loss: 4.043579247081652e-05
2023-01-23 02:39:11.521303: step: 568/526, loss: 0.003654670901596546
2023-01-23 02:39:12.644764: step: 572/526, loss: 0.0066085816361010075
2023-01-23 02:39:13.770757: step: 576/526, loss: 0.0010699272388592362
2023-01-23 02:39:14.907987: step: 580/526, loss: 0.006632233038544655
2023-01-23 02:39:16.061121: step: 584/526, loss: 0.009936332702636719
2023-01-23 02:39:17.205365: step: 588/526, loss: 0.0074797626584768295
2023-01-23 02:39:18.328241: step: 592/526, loss: 0.0006622314685955644
2023-01-23 02:39:19.464476: step: 596/526, loss: 0.025319386273622513
2023-01-23 02:39:20.572613: step: 600/526, loss: 0.007889366708695889
2023-01-23 02:39:21.715162: step: 604/526, loss: 0.011844825930893421
2023-01-23 02:39:22.849596: step: 608/526, loss: 7.534027099609375e-05
2023-01-23 02:39:23.974783: step: 612/526, loss: 0.0005170822259970009
2023-01-23 02:39:25.109322: step: 616/526, loss: 0.0006565094226971269
2023-01-23 02:39:26.255168: step: 620/526, loss: 0.0029603957664221525
2023-01-23 02:39:27.383058: step: 624/526, loss: 0.009745597839355469
2023-01-23 02:39:28.501972: step: 628/526, loss: 0.00015172958956100047
2023-01-23 02:39:29.639367: step: 632/526, loss: 0.08412046730518341
2023-01-23 02:39:30.783470: step: 636/526, loss: 0.02991456910967827
2023-01-23 02:39:31.913828: step: 640/526, loss: 0.029345132410526276
2023-01-23 02:39:33.063190: step: 644/526, loss: 0.047356415539979935
2023-01-23 02:39:34.198115: step: 648/526, loss: 0.00168523786123842
2023-01-23 02:39:35.349887: step: 652/526, loss: 0.06777477264404297
2023-01-23 02:39:36.482284: step: 656/526, loss: 0.001197004341520369
2023-01-23 02:39:37.591535: step: 660/526, loss: 0.012173175811767578
2023-01-23 02:39:38.734095: step: 664/526, loss: 0.02936248853802681
2023-01-23 02:39:39.880171: step: 668/526, loss: 0.13716450333595276
2023-01-23 02:39:41.029954: step: 672/526, loss: 0.0002035141078522429
2023-01-23 02:39:42.144907: step: 676/526, loss: 0.030060291290283203
2023-01-23 02:39:43.268610: step: 680/526, loss: 0.0007513046148233116
2023-01-23 02:39:44.375352: step: 684/526, loss: 0.019878387451171875
2023-01-23 02:39:45.546074: step: 688/526, loss: 0.00892949104309082
2023-01-23 02:39:46.663237: step: 692/526, loss: 0.006954574957489967
2023-01-23 02:39:47.796419: step: 696/526, loss: 0.00027439594850875437
2023-01-23 02:39:48.921052: step: 700/526, loss: 0.0015366554725915194
2023-01-23 02:39:50.048868: step: 704/526, loss: 0.017702102661132812
2023-01-23 02:39:51.195816: step: 708/526, loss: 0.11855965107679367
2023-01-23 02:39:52.319008: step: 712/526, loss: 0.0006343841669149697
2023-01-23 02:39:53.418169: step: 716/526, loss: 0.0032587528694421053
2023-01-23 02:39:54.540152: step: 720/526, loss: 0.00033979417639784515
2023-01-23 02:39:55.672414: step: 724/526, loss: 0.0005846023559570312
2023-01-23 02:39:56.789308: step: 728/526, loss: 0.004286289215087891
2023-01-23 02:39:57.918882: step: 732/526, loss: 0.025553608313202858
2023-01-23 02:39:59.055457: step: 736/526, loss: 0.0019258499378338456
2023-01-23 02:40:00.192189: step: 740/526, loss: 0.0750301331281662
2023-01-23 02:40:01.326410: step: 744/526, loss: 0.0254149679094553
2023-01-23 02:40:02.467223: step: 748/526, loss: 0.0009754180791787803
2023-01-23 02:40:03.579195: step: 752/526, loss: 0.2893388867378235
2023-01-23 02:40:04.746644: step: 756/526, loss: 0.014654017053544521
2023-01-23 02:40:05.840348: step: 760/526, loss: 0.003608894534409046
2023-01-23 02:40:06.963980: step: 764/526, loss: 0.016156386584043503
2023-01-23 02:40:08.076628: step: 768/526, loss: 0.0036128521896898746
2023-01-23 02:40:09.209656: step: 772/526, loss: 0.1001136377453804
2023-01-23 02:40:10.341496: step: 776/526, loss: 0.010996627621352673
2023-01-23 02:40:11.464803: step: 780/526, loss: 0.3185775876045227
2023-01-23 02:40:12.646407: step: 784/526, loss: 0.00040454865666106343
2023-01-23 02:40:13.794273: step: 788/526, loss: 0.033834267407655716
2023-01-23 02:40:14.917944: step: 792/526, loss: 0.04966411739587784
2023-01-23 02:40:16.061311: step: 796/526, loss: 0.011606693267822266
2023-01-23 02:40:17.189766: step: 800/526, loss: 0.0005444526905193925
2023-01-23 02:40:18.307924: step: 804/526, loss: 0.0015051126247271895
2023-01-23 02:40:19.431478: step: 808/526, loss: 0.04326934739947319
2023-01-23 02:40:20.580503: step: 812/526, loss: 0.0002534866507630795
2023-01-23 02:40:21.720296: step: 816/526, loss: 0.4787864685058594
2023-01-23 02:40:22.846382: step: 820/526, loss: 0.0009424686431884766
2023-01-23 02:40:23.964458: step: 824/526, loss: 0.010087060742080212
2023-01-23 02:40:25.090137: step: 828/526, loss: 0.007407856173813343
2023-01-23 02:40:26.221754: step: 832/526, loss: 0.0007472991710528731
2023-01-23 02:40:27.363725: step: 836/526, loss: 0.00671997107565403
2023-01-23 02:40:28.525666: step: 840/526, loss: 0.004812860395759344
2023-01-23 02:40:29.655285: step: 844/526, loss: 0.030461406335234642
2023-01-23 02:40:30.809262: step: 848/526, loss: 0.012452412396669388
2023-01-23 02:40:31.915678: step: 852/526, loss: 0.008803559467196465
2023-01-23 02:40:33.055616: step: 856/526, loss: 0.001974487444385886
2023-01-23 02:40:34.185290: step: 860/526, loss: 0.020607374608516693
2023-01-23 02:40:35.306385: step: 864/526, loss: 0.018451310694217682
2023-01-23 02:40:36.429036: step: 868/526, loss: 0.0005424499395303428
2023-01-23 02:40:37.572261: step: 872/526, loss: 0.00715980539098382
2023-01-23 02:40:38.721756: step: 876/526, loss: 0.00910329818725586
2023-01-23 02:40:39.853425: step: 880/526, loss: 0.013965129852294922
2023-01-23 02:40:40.977125: step: 884/526, loss: 0.0044203754514455795
2023-01-23 02:40:42.108769: step: 888/526, loss: 0.045957569032907486
2023-01-23 02:40:43.265045: step: 892/526, loss: 0.0010749816428869963
2023-01-23 02:40:44.426069: step: 896/526, loss: 0.011577701196074486
2023-01-23 02:40:45.537825: step: 900/526, loss: 0.00041518211946822703
2023-01-23 02:40:46.693415: step: 904/526, loss: 0.042954470962285995
2023-01-23 02:40:47.824292: step: 908/526, loss: 0.0006189346313476562
2023-01-23 02:40:48.980714: step: 912/526, loss: 0.026955222710967064
2023-01-23 02:40:50.132970: step: 916/526, loss: 0.00064001081045717
2023-01-23 02:40:51.254084: step: 920/526, loss: 0.001116847968660295
2023-01-23 02:40:52.398576: step: 924/526, loss: 7.21931501175277e-05
2023-01-23 02:40:53.510358: step: 928/526, loss: 0.23166485130786896
2023-01-23 02:40:54.605160: step: 932/526, loss: 0.0034762383438646793
2023-01-23 02:40:55.753046: step: 936/526, loss: 0.0320739783346653
2023-01-23 02:40:56.896511: step: 940/526, loss: 0.03420533984899521
2023-01-23 02:40:58.039716: step: 944/526, loss: 0.003828811924904585
2023-01-23 02:40:59.153994: step: 948/526, loss: 0.031687453389167786
2023-01-23 02:41:00.291925: step: 952/526, loss: 0.007382297422736883
2023-01-23 02:41:01.443202: step: 956/526, loss: 0.1173815205693245
2023-01-23 02:41:02.566811: step: 960/526, loss: 0.01780223846435547
2023-01-23 02:41:03.705056: step: 964/526, loss: 0.06351308524608612
2023-01-23 02:41:04.846390: step: 968/526, loss: 0.01303086243569851
2023-01-23 02:41:05.993964: step: 972/526, loss: 0.015380574390292168
2023-01-23 02:41:07.113886: step: 976/526, loss: 9.732246689964086e-05
2023-01-23 02:41:08.272283: step: 980/526, loss: 0.0003514289855957031
2023-01-23 02:41:09.407724: step: 984/526, loss: 0.005112933926284313
2023-01-23 02:41:10.534864: step: 988/526, loss: 0.0030620575416833162
2023-01-23 02:41:11.722875: step: 992/526, loss: 0.008502769283950329
2023-01-23 02:41:12.882860: step: 996/526, loss: 0.00021657944307662547
2023-01-23 02:41:14.016600: step: 1000/526, loss: 0.011288738809525967
2023-01-23 02:41:15.170852: step: 1004/526, loss: 0.026064587756991386
2023-01-23 02:41:16.345663: step: 1008/526, loss: 0.10760241001844406
2023-01-23 02:41:17.510930: step: 1012/526, loss: 0.0012613296275958419
2023-01-23 02:41:18.619635: step: 1016/526, loss: 0.0011058807140216231
2023-01-23 02:41:19.753514: step: 1020/526, loss: 0.00409202603623271
2023-01-23 02:41:20.903536: step: 1024/526, loss: 0.01920166052877903
2023-01-23 02:41:22.008327: step: 1028/526, loss: 0.00015954971604514867
2023-01-23 02:41:23.162426: step: 1032/526, loss: 4.5299530029296875e-05
2023-01-23 02:41:24.303642: step: 1036/526, loss: 0.0046485899947583675
2023-01-23 02:41:25.465033: step: 1040/526, loss: 8.96453821042087e-06
2023-01-23 02:41:26.623019: step: 1044/526, loss: 0.00014934540376998484
2023-01-23 02:41:27.813718: step: 1048/526, loss: 0.0034685134887695312
2023-01-23 02:41:28.956060: step: 1052/526, loss: 0.01864943467080593
2023-01-23 02:41:30.094694: step: 1056/526, loss: 0.019978713244199753
2023-01-23 02:41:31.251627: step: 1060/526, loss: 0.0019093513255938888
2023-01-23 02:41:32.373190: step: 1064/526, loss: 0.01450891513377428
2023-01-23 02:41:33.488306: step: 1068/526, loss: 0.08216586709022522
2023-01-23 02:41:34.640040: step: 1072/526, loss: 1.9073486328125e-05
2023-01-23 02:41:35.797568: step: 1076/526, loss: 0.0030183792114257812
2023-01-23 02:41:36.938662: step: 1080/526, loss: 0.0012455940013751388
2023-01-23 02:41:38.075900: step: 1084/526, loss: 0.0063187601044774055
2023-01-23 02:41:39.218258: step: 1088/526, loss: 0.0017118453979492188
2023-01-23 02:41:40.366008: step: 1092/526, loss: 0.04254655912518501
2023-01-23 02:41:41.486573: step: 1096/526, loss: 0.030933095142245293
2023-01-23 02:41:42.605466: step: 1100/526, loss: 0.0005690098041668534
2023-01-23 02:41:43.769252: step: 1104/526, loss: 0.035735514014959335
2023-01-23 02:41:44.913465: step: 1108/526, loss: 0.031011486425995827
2023-01-23 02:41:46.039725: step: 1112/526, loss: 0.022867776453495026
2023-01-23 02:41:47.207853: step: 1116/526, loss: 0.02181835100054741
2023-01-23 02:41:48.334952: step: 1120/526, loss: 0.002197647001594305
2023-01-23 02:41:49.465441: step: 1124/526, loss: 0.02172575145959854
2023-01-23 02:41:50.579188: step: 1128/526, loss: 0.024561645463109016
2023-01-23 02:41:51.709885: step: 1132/526, loss: 0.0028888701926916838
2023-01-23 02:41:52.811386: step: 1136/526, loss: 0.051204510033130646
2023-01-23 02:41:53.930062: step: 1140/526, loss: 0.003107261611148715
2023-01-23 02:41:55.081941: step: 1144/526, loss: 0.0001703739253571257
2023-01-23 02:41:56.205864: step: 1148/526, loss: 0.002641010330989957
2023-01-23 02:41:57.356151: step: 1152/526, loss: 0.028209306299686432
2023-01-23 02:41:58.465497: step: 1156/526, loss: 0.0008631706587038934
2023-01-23 02:41:59.619423: step: 1160/526, loss: 0.0034566400572657585
2023-01-23 02:42:00.775129: step: 1164/526, loss: 0.004465484991669655
2023-01-23 02:42:01.886792: step: 1168/526, loss: 0.005255413241684437
2023-01-23 02:42:03.046320: step: 1172/526, loss: 0.062155917286872864
2023-01-23 02:42:04.154106: step: 1176/526, loss: 0.02624053880572319
2023-01-23 02:42:05.297465: step: 1180/526, loss: 0.01065750140696764
2023-01-23 02:42:06.439351: step: 1184/526, loss: 0.02648334577679634
2023-01-23 02:42:07.556752: step: 1188/526, loss: 0.0012329102028161287
2023-01-23 02:42:08.672267: step: 1192/526, loss: 0.0015469550853595138
2023-01-23 02:42:09.787894: step: 1196/526, loss: 0.09007377922534943
2023-01-23 02:42:10.919184: step: 1200/526, loss: 0.012814425863325596
2023-01-23 02:42:12.078455: step: 1204/526, loss: 0.014897346496582031
2023-01-23 02:42:13.238707: step: 1208/526, loss: 0.001088905381038785
2023-01-23 02:42:14.373457: step: 1212/526, loss: 0.023442650213837624
2023-01-23 02:42:15.494457: step: 1216/526, loss: 0.04458579793572426
2023-01-23 02:42:16.629133: step: 1220/526, loss: 0.0002468109014444053
2023-01-23 02:42:17.753063: step: 1224/526, loss: 0.011535453610122204
2023-01-23 02:42:18.896395: step: 1228/526, loss: 0.022029779851436615
2023-01-23 02:42:20.030393: step: 1232/526, loss: 0.007533550262451172
2023-01-23 02:42:21.178015: step: 1236/526, loss: 0.015412712469696999
2023-01-23 02:42:22.300417: step: 1240/526, loss: 0.00017709731764625758
2023-01-23 02:42:23.412161: step: 1244/526, loss: 0.00043492316035553813
2023-01-23 02:42:24.538165: step: 1248/526, loss: 0.05779552459716797
2023-01-23 02:42:25.679263: step: 1252/526, loss: 0.02234034612774849
2023-01-23 02:42:26.797988: step: 1256/526, loss: 0.018366623669862747
2023-01-23 02:42:27.936680: step: 1260/526, loss: 0.0005928039900027215
2023-01-23 02:42:29.082399: step: 1264/526, loss: 0.01376113947480917
2023-01-23 02:42:30.228775: step: 1268/526, loss: 0.05060577392578125
2023-01-23 02:42:31.351601: step: 1272/526, loss: 0.0036373138427734375
2023-01-23 02:42:32.490495: step: 1276/526, loss: 0.029652167111635208
2023-01-23 02:42:33.666135: step: 1280/526, loss: 0.04644804075360298
2023-01-23 02:42:34.832643: step: 1284/526, loss: 0.0029702186584472656
2023-01-23 02:42:35.963051: step: 1288/526, loss: 0.003202104475349188
2023-01-23 02:42:37.113315: step: 1292/526, loss: 0.05603065341711044
2023-01-23 02:42:38.239626: step: 1296/526, loss: 0.016869639977812767
2023-01-23 02:42:39.401272: step: 1300/526, loss: 0.0038928985595703125
2023-01-23 02:42:40.536386: step: 1304/526, loss: 0.04448118433356285
2023-01-23 02:42:41.699818: step: 1308/526, loss: 0.0053289649076759815
2023-01-23 02:42:42.856285: step: 1312/526, loss: 0.44483301043510437
2023-01-23 02:42:43.983414: step: 1316/526, loss: 0.0007533073076047003
2023-01-23 02:42:45.118536: step: 1320/526, loss: 0.000522994960192591
2023-01-23 02:42:46.269658: step: 1324/526, loss: 0.25938504934310913
2023-01-23 02:42:47.417515: step: 1328/526, loss: 0.20688065886497498
2023-01-23 02:42:48.569376: step: 1332/526, loss: 0.02909240685403347
2023-01-23 02:42:49.690471: step: 1336/526, loss: 0.01870584487915039
2023-01-23 02:42:50.835077: step: 1340/526, loss: 0.025593310594558716
2023-01-23 02:42:51.935998: step: 1344/526, loss: 0.0005415916675701737
2023-01-23 02:42:53.044810: step: 1348/526, loss: 0.0066468240693211555
2023-01-23 02:42:54.159397: step: 1352/526, loss: 0.1011747419834137
2023-01-23 02:42:55.289900: step: 1356/526, loss: 0.030309487134218216
2023-01-23 02:42:56.415245: step: 1360/526, loss: 0.032256029546260834
2023-01-23 02:42:57.583222: step: 1364/526, loss: 0.021113110706210136
2023-01-23 02:42:58.736022: step: 1368/526, loss: 0.022073745727539062
2023-01-23 02:42:59.862214: step: 1372/526, loss: 0.017027663066983223
2023-01-23 02:43:01.015900: step: 1376/526, loss: 0.00087652204092592
2023-01-23 02:43:02.152530: step: 1380/526, loss: 0.0020315172150731087
2023-01-23 02:43:03.279741: step: 1384/526, loss: 0.005466843023896217
2023-01-23 02:43:04.386115: step: 1388/526, loss: 4.5108794438419864e-05
2023-01-23 02:43:05.514823: step: 1392/526, loss: 0.0009288787841796875
2023-01-23 02:43:06.706123: step: 1396/526, loss: 0.0031188009306788445
2023-01-23 02:43:07.813060: step: 1400/526, loss: 0.008556175045669079
2023-01-23 02:43:08.928602: step: 1404/526, loss: 0.02328958548605442
2023-01-23 02:43:10.079633: step: 1408/526, loss: 0.0011438369983807206
2023-01-23 02:43:11.229462: step: 1412/526, loss: 0.13003291189670563
2023-01-23 02:43:12.376122: step: 1416/526, loss: 0.005061817355453968
2023-01-23 02:43:13.524620: step: 1420/526, loss: 0.08237877488136292
2023-01-23 02:43:14.680312: step: 1424/526, loss: 0.006093216128647327
2023-01-23 02:43:15.827833: step: 1428/526, loss: 0.010690021328628063
2023-01-23 02:43:16.960526: step: 1432/526, loss: 0.005165672395378351
2023-01-23 02:43:18.117698: step: 1436/526, loss: 0.0027582168113440275
2023-01-23 02:43:19.238181: step: 1440/526, loss: 0.014203167520463467
2023-01-23 02:43:20.374824: step: 1444/526, loss: 0.0035703659523278475
2023-01-23 02:43:21.494790: step: 1448/526, loss: 0.0007405281066894531
2023-01-23 02:43:22.657700: step: 1452/526, loss: 0.048860300332307816
2023-01-23 02:43:23.805175: step: 1456/526, loss: 0.05387945473194122
2023-01-23 02:43:24.949661: step: 1460/526, loss: 0.0007026434177532792
2023-01-23 02:43:26.029317: step: 1464/526, loss: 0.0004672825161833316
2023-01-23 02:43:27.187661: step: 1468/526, loss: 0.334145724773407
2023-01-23 02:43:28.313067: step: 1472/526, loss: 0.00843515433371067
2023-01-23 02:43:29.460690: step: 1476/526, loss: 0.00026111601619049907
2023-01-23 02:43:30.604869: step: 1480/526, loss: 0.0380183607339859
2023-01-23 02:43:31.744763: step: 1484/526, loss: 0.00114526750985533
2023-01-23 02:43:32.922136: step: 1488/526, loss: 0.005035209935158491
2023-01-23 02:43:34.042149: step: 1492/526, loss: 0.0095077995210886
2023-01-23 02:43:35.175207: step: 1496/526, loss: 0.00024890899658203125
2023-01-23 02:43:36.298096: step: 1500/526, loss: 0.00029144284781068563
2023-01-23 02:43:37.424206: step: 1504/526, loss: 0.0007922649383544922
2023-01-23 02:43:38.586840: step: 1508/526, loss: 0.008802032098174095
2023-01-23 02:43:39.732767: step: 1512/526, loss: 0.006653976161032915
2023-01-23 02:43:40.879996: step: 1516/526, loss: 0.00032367705716751516
2023-01-23 02:43:42.028113: step: 1520/526, loss: 0.020620156079530716
2023-01-23 02:43:43.180492: step: 1524/526, loss: 0.0002572059747762978
2023-01-23 02:43:44.334659: step: 1528/526, loss: 0.00015363693819381297
2023-01-23 02:43:45.456497: step: 1532/526, loss: 0.013950919732451439
2023-01-23 02:43:46.608016: step: 1536/526, loss: 5.426407005870715e-05
2023-01-23 02:43:47.742995: step: 1540/526, loss: 0.026434611529111862
2023-01-23 02:43:48.876418: step: 1544/526, loss: 0.00018100740271620452
2023-01-23 02:43:49.997334: step: 1548/526, loss: 0.008823871612548828
2023-01-23 02:43:51.129754: step: 1552/526, loss: 3.1471254260395654e-06
2023-01-23 02:43:52.256364: step: 1556/526, loss: 0.07268200814723969
2023-01-23 02:43:53.415801: step: 1560/526, loss: 0.049806978553533554
2023-01-23 02:43:54.567460: step: 1564/526, loss: 0.012389754876494408
2023-01-23 02:43:55.702047: step: 1568/526, loss: 7.781983003951609e-05
2023-01-23 02:43:56.859197: step: 1572/526, loss: 0.014441299252212048
2023-01-23 02:43:58.065842: step: 1576/526, loss: 0.014146995730698109
2023-01-23 02:43:59.227958: step: 1580/526, loss: 0.0002803802490234375
2023-01-23 02:44:00.361619: step: 1584/526, loss: 0.034462932497262955
2023-01-23 02:44:01.504999: step: 1588/526, loss: 1.5753436088562012
2023-01-23 02:44:02.641143: step: 1592/526, loss: 0.001132965087890625
2023-01-23 02:44:03.779620: step: 1596/526, loss: 0.01793518103659153
2023-01-23 02:44:04.913055: step: 1600/526, loss: 0.030055763199925423
2023-01-23 02:44:06.059994: step: 1604/526, loss: 0.014671134762465954
2023-01-23 02:44:07.207191: step: 1608/526, loss: 0.0075120930559933186
2023-01-23 02:44:08.342885: step: 1612/526, loss: 0.009023762308061123
2023-01-23 02:44:09.483420: step: 1616/526, loss: 0.0018198012840002775
2023-01-23 02:44:10.611015: step: 1620/526, loss: 0.0001615524379303679
2023-01-23 02:44:11.728401: step: 1624/526, loss: 0.008576393127441406
2023-01-23 02:44:12.858230: step: 1628/526, loss: 0.0005743026849813759
2023-01-23 02:44:13.981840: step: 1632/526, loss: 0.0025877475272864103
2023-01-23 02:44:15.122690: step: 1636/526, loss: 0.04479098320007324
2023-01-23 02:44:16.264052: step: 1640/526, loss: 0.009057330898940563
2023-01-23 02:44:17.391395: step: 1644/526, loss: 0.00747337331995368
2023-01-23 02:44:18.548943: step: 1648/526, loss: 0.0029829025734215975
2023-01-23 02:44:19.659875: step: 1652/526, loss: 0.008117579855024815
2023-01-23 02:44:20.796715: step: 1656/526, loss: 0.010360908694565296
2023-01-23 02:44:21.956750: step: 1660/526, loss: 0.011524582281708717
2023-01-23 02:44:23.106059: step: 1664/526, loss: 0.03401918336749077
2023-01-23 02:44:24.227115: step: 1668/526, loss: 0.005031013395637274
2023-01-23 02:44:25.356341: step: 1672/526, loss: 0.004806423559784889
2023-01-23 02:44:26.492360: step: 1676/526, loss: 0.019953345879912376
2023-01-23 02:44:27.620440: step: 1680/526, loss: 0.01844792440533638
2023-01-23 02:44:28.750085: step: 1684/526, loss: 0.0008735657320357859
2023-01-23 02:44:29.903407: step: 1688/526, loss: 0.0035420418716967106
2023-01-23 02:44:31.056816: step: 1692/526, loss: 0.007732200901955366
2023-01-23 02:44:32.197817: step: 1696/526, loss: 0.0007713317754678428
2023-01-23 02:44:33.348195: step: 1700/526, loss: 0.03784923627972603
2023-01-23 02:44:34.477769: step: 1704/526, loss: 0.015230274759232998
2023-01-23 02:44:35.617780: step: 1708/526, loss: 0.0011760711204260588
2023-01-23 02:44:36.770308: step: 1712/526, loss: 0.010625649243593216
2023-01-23 02:44:37.904225: step: 1716/526, loss: 0.005139159969985485
2023-01-23 02:44:39.083922: step: 1720/526, loss: 0.03791771084070206
2023-01-23 02:44:40.222142: step: 1724/526, loss: 0.0262099988758564
2023-01-23 02:44:41.349443: step: 1728/526, loss: 0.0007447600364685059
2023-01-23 02:44:42.479461: step: 1732/526, loss: 0.00066547398455441
2023-01-23 02:44:43.611612: step: 1736/526, loss: 0.039075613021850586
2023-01-23 02:44:44.715662: step: 1740/526, loss: 0.006984138861298561
2023-01-23 02:44:45.850881: step: 1744/526, loss: 0.0003493308904580772
2023-01-23 02:44:47.014390: step: 1748/526, loss: 0.004170799162238836
2023-01-23 02:44:48.124455: step: 1752/526, loss: 0.001493167830631137
2023-01-23 02:44:49.308599: step: 1756/526, loss: 0.025445174425840378
2023-01-23 02:44:50.456373: step: 1760/526, loss: 0.012231064029037952
2023-01-23 02:44:51.610774: step: 1764/526, loss: 0.0006394386291503906
2023-01-23 02:44:52.736213: step: 1768/526, loss: 0.011926889419555664
2023-01-23 02:44:53.875073: step: 1772/526, loss: 0.04630432277917862
2023-01-23 02:44:54.997125: step: 1776/526, loss: 0.01020674780011177
2023-01-23 02:44:56.149932: step: 1780/526, loss: 0.03478426858782768
2023-01-23 02:44:57.300787: step: 1784/526, loss: 0.00114526750985533
2023-01-23 02:44:58.450473: step: 1788/526, loss: 0.0029139756225049496
2023-01-23 02:44:59.610958: step: 1792/526, loss: 0.03370952606201172
2023-01-23 02:45:00.730693: step: 1796/526, loss: 0.03203010559082031
2023-01-23 02:45:01.878669: step: 1800/526, loss: 0.0054104807786643505
2023-01-23 02:45:03.004497: step: 1804/526, loss: 0.013263989239931107
2023-01-23 02:45:04.131436: step: 1808/526, loss: 0.013837659731507301
2023-01-23 02:45:05.268412: step: 1812/526, loss: 0.03971576690673828
2023-01-23 02:45:06.397079: step: 1816/526, loss: 0.019826795905828476
2023-01-23 02:45:07.517716: step: 1820/526, loss: 0.00041570665780454874
2023-01-23 02:45:08.634237: step: 1824/526, loss: 0.010503023862838745
2023-01-23 02:45:09.771329: step: 1828/526, loss: 2.57968895311933e-05
2023-01-23 02:45:10.902292: step: 1832/526, loss: 0.014549542218446732
2023-01-23 02:45:12.072667: step: 1836/526, loss: 0.0004096984921488911
2023-01-23 02:45:13.203375: step: 1840/526, loss: 0.008773994632065296
2023-01-23 02:45:14.332365: step: 1844/526, loss: 0.06470699608325958
2023-01-23 02:45:15.456449: step: 1848/526, loss: 0.0035255432594567537
2023-01-23 02:45:16.570964: step: 1852/526, loss: 0.0013734817039221525
2023-01-23 02:45:17.729216: step: 1856/526, loss: 0.003048897022381425
2023-01-23 02:45:18.888439: step: 1860/526, loss: 0.027164697647094727
2023-01-23 02:45:20.082014: step: 1864/526, loss: 0.5487657189369202
2023-01-23 02:45:21.191275: step: 1868/526, loss: 0.01311645470559597
2023-01-23 02:45:22.318933: step: 1872/526, loss: 0.001676368759945035
2023-01-23 02:45:23.430879: step: 1876/526, loss: 0.0007895469898357987
2023-01-23 02:45:24.576920: step: 1880/526, loss: 0.0019960403442382812
2023-01-23 02:45:25.702981: step: 1884/526, loss: 0.08450088649988174
2023-01-23 02:45:26.837700: step: 1888/526, loss: 0.001560211181640625
2023-01-23 02:45:27.991023: step: 1892/526, loss: 4.310607982915826e-05
2023-01-23 02:45:29.136531: step: 1896/526, loss: 0.25707730650901794
2023-01-23 02:45:30.268658: step: 1900/526, loss: 0.009438895620405674
2023-01-23 02:45:31.389184: step: 1904/526, loss: 0.0024895668029785156
2023-01-23 02:45:32.538298: step: 1908/526, loss: 0.003894710447639227
2023-01-23 02:45:33.692415: step: 1912/526, loss: 0.00026617050752975047
2023-01-23 02:45:34.810114: step: 1916/526, loss: 9.689330909168348e-05
2023-01-23 02:45:35.935475: step: 1920/526, loss: 0.00023465156846214086
2023-01-23 02:45:37.046632: step: 1924/526, loss: 0.0017255783313885331
2023-01-23 02:45:38.172745: step: 1928/526, loss: 6.351470801746473e-05
2023-01-23 02:45:39.347179: step: 1932/526, loss: 0.0013942718505859375
2023-01-23 02:45:40.475252: step: 1936/526, loss: 0.008255386725068092
2023-01-23 02:45:41.601271: step: 1940/526, loss: 0.005553054623305798
2023-01-23 02:45:42.740328: step: 1944/526, loss: 0.0006347656017169356
2023-01-23 02:45:43.865172: step: 1948/526, loss: 0.008454657159745693
2023-01-23 02:45:44.981518: step: 1952/526, loss: 0.00027956964913755655
2023-01-23 02:45:46.110628: step: 1956/526, loss: 0.0069716451689600945
2023-01-23 02:45:47.235759: step: 1960/526, loss: 1.0779386758804321
2023-01-23 02:45:48.384048: step: 1964/526, loss: 0.018053723499178886
2023-01-23 02:45:49.514334: step: 1968/526, loss: 0.05226755142211914
2023-01-23 02:45:50.654223: step: 1972/526, loss: 0.024973010644316673
2023-01-23 02:45:51.785396: step: 1976/526, loss: 0.00859222374856472
2023-01-23 02:45:52.938221: step: 1980/526, loss: 0.007870674133300781
2023-01-23 02:45:54.106601: step: 1984/526, loss: 0.0009204865200445056
2023-01-23 02:45:55.237968: step: 1988/526, loss: 0.010213280096650124
2023-01-23 02:45:56.360840: step: 1992/526, loss: 0.0029568197205662727
2023-01-23 02:45:57.509194: step: 1996/526, loss: 0.00034322740975767374
2023-01-23 02:45:58.641541: step: 2000/526, loss: 0.0283355712890625
2023-01-23 02:45:59.762317: step: 2004/526, loss: 0.04610319435596466
2023-01-23 02:46:00.902892: step: 2008/526, loss: 0.035727739334106445
2023-01-23 02:46:02.051353: step: 2012/526, loss: 0.00164031982421875
2023-01-23 02:46:03.196082: step: 2016/526, loss: 0.013270759955048561
2023-01-23 02:46:04.332686: step: 2020/526, loss: 0.0016202926635742188
2023-01-23 02:46:05.465450: step: 2024/526, loss: 0.007674217224121094
2023-01-23 02:46:06.615487: step: 2028/526, loss: 0.0795714408159256
2023-01-23 02:46:07.738022: step: 2032/526, loss: 0.00148773193359375
2023-01-23 02:46:08.878299: step: 2036/526, loss: 0.000966835068538785
2023-01-23 02:46:10.026845: step: 2040/526, loss: 0.04186592251062393
2023-01-23 02:46:11.192943: step: 2044/526, loss: 0.006205367855727673
2023-01-23 02:46:12.330370: step: 2048/526, loss: 0.012000561691820621
2023-01-23 02:46:13.470565: step: 2052/526, loss: 0.03836984559893608
2023-01-23 02:46:14.596620: step: 2056/526, loss: 0.0773535743355751
2023-01-23 02:46:15.734522: step: 2060/526, loss: 0.004939270205795765
2023-01-23 02:46:16.860909: step: 2064/526, loss: 0.000782489834818989
2023-01-23 02:46:17.978348: step: 2068/526, loss: 0.018858909606933594
2023-01-23 02:46:19.112571: step: 2072/526, loss: 0.10593309253454208
2023-01-23 02:46:20.224006: step: 2076/526, loss: 0.03182802349328995
2023-01-23 02:46:21.373910: step: 2080/526, loss: 0.013780689798295498
2023-01-23 02:46:22.493170: step: 2084/526, loss: 0.010799598880112171
2023-01-23 02:46:23.602666: step: 2088/526, loss: 0.0016660690307617188
2023-01-23 02:46:24.719300: step: 2092/526, loss: 0.0021753788460046053
2023-01-23 02:46:25.864377: step: 2096/526, loss: 0.023459387943148613
2023-01-23 02:46:27.000789: step: 2100/526, loss: 0.007106876000761986
2023-01-23 02:46:28.151042: step: 2104/526, loss: 0.005678844638168812
==================================================
Loss: 0.029
--------------------
Dev: {'event': {'p': 0.5940695296523517, 'r': 0.7736351531291611, 'f1': 0.6720647773279351}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
Test: {'event': {'p': 0.6000808734330773, 'r': 0.7745302713987474, 'f1': 0.6762360446570974}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
Chinese: {'event': {'p': 0.6049382716049383, 'r': 0.9074074074074074, 'f1': 0.725925925925926}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
Korean: {'event': {'p': 0.66, 'r': 0.5238095238095238, 'f1': 0.584070796460177}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
Russian: {'event': {'p': 0.46511627906976744, 'r': 0.5555555555555556, 'f1': 0.5063291139240507}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6389811738648948, 'r': 0.7683089214380826, 'f1': 0.6977025392986699}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Eng Test for Chinese: {'event': {'p': 0.6328626444159179, 'r': 0.7719206680584552, 'f1': 0.6955090524335763}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Sample Chinese: {'event': {'p': 0.6282051282051282, 'r': 0.9074074074074074, 'f1': 0.7424242424242423}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6257995735607675, 'r': 0.7816245006657789, 'f1': 0.6950858496151568}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Eng Test for Korean: {'event': {'p': 0.623113410952997, 'r': 0.7541753653444676, 'f1': 0.6824085005903188}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Sample Korean: {'event': {'p': 0.7446808510638298, 'r': 0.5555555555555556, 'f1': 0.6363636363636364}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5800575263662512, 'r': 0.8055925432756325, 'f1': 0.6744704570791527}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
Eng Test for Russian: {'event': {'p': 0.5962534874451972, 'r': 0.7807933194154488, 'f1': 0.6761581920903954}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
Sample Russian: {'event': {'p': 0.48936170212765956, 'r': 0.6388888888888888, 'f1': 0.5542168674698795}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
******************************
Epoch: 19
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 02:47:11.577247: step: 4/526, loss: 0.0013688564067706466
2023-01-23 02:47:12.695664: step: 8/526, loss: 0.009413529187440872
2023-01-23 02:47:13.832197: step: 12/526, loss: 0.004992390051484108
2023-01-23 02:47:14.959144: step: 16/526, loss: 0.011704063974320889
2023-01-23 02:47:16.083992: step: 20/526, loss: 0.017786597833037376
2023-01-23 02:47:17.202040: step: 24/526, loss: 0.00257453927770257
2023-01-23 02:47:18.334781: step: 28/526, loss: 0.00282535539008677
2023-01-23 02:47:19.478018: step: 32/526, loss: 0.0008752822759561241
2023-01-23 02:47:20.623253: step: 36/526, loss: 0.0016429901588708162
2023-01-23 02:47:21.783849: step: 40/526, loss: 0.0029681206215173006
2023-01-23 02:47:22.912252: step: 44/526, loss: 0.002914714626967907
2023-01-23 02:47:24.040253: step: 48/526, loss: 0.00579118775203824
2023-01-23 02:47:25.175049: step: 52/526, loss: 0.00026912690373137593
2023-01-23 02:47:26.316347: step: 56/526, loss: 0.005245208740234375
2023-01-23 02:47:27.435264: step: 60/526, loss: 0.00550003070384264
2023-01-23 02:47:28.574248: step: 64/526, loss: 0.002261352725327015
2023-01-23 02:47:29.678515: step: 68/526, loss: 0.013428974896669388
2023-01-23 02:47:30.824458: step: 72/526, loss: 0.008398962207138538
2023-01-23 02:47:31.978380: step: 76/526, loss: 0.0016423225170001388
2023-01-23 02:47:33.114318: step: 80/526, loss: 0.017499733716249466
2023-01-23 02:47:34.236158: step: 84/526, loss: 0.017882632091641426
2023-01-23 02:47:35.389029: step: 88/526, loss: 0.013245927169919014
2023-01-23 02:47:36.533854: step: 92/526, loss: 0.0012380600674077868
2023-01-23 02:47:37.703829: step: 96/526, loss: 0.006217003334313631
2023-01-23 02:47:38.843674: step: 100/526, loss: 0.04063883051276207
2023-01-23 02:47:39.994453: step: 104/526, loss: 0.0019698143005371094
2023-01-23 02:47:41.118363: step: 108/526, loss: 0.0016646385192871094
2023-01-23 02:47:42.279908: step: 112/526, loss: 0.004708099644631147
2023-01-23 02:47:43.415794: step: 116/526, loss: 0.03622474893927574
2023-01-23 02:47:44.582413: step: 120/526, loss: 1.9168854123563506e-05
2023-01-23 02:47:45.706768: step: 124/526, loss: 0.0359533317387104
2023-01-23 02:47:46.902952: step: 128/526, loss: 0.044225696474313736
2023-01-23 02:47:48.040019: step: 132/526, loss: 0.0012380600674077868
2023-01-23 02:47:49.143712: step: 136/526, loss: 0.0010036468738690019
2023-01-23 02:47:50.278409: step: 140/526, loss: 0.002115965122357011
2023-01-23 02:47:51.400077: step: 144/526, loss: 0.010544968768954277
2023-01-23 02:47:52.544495: step: 148/526, loss: 0.0009315490606240928
2023-01-23 02:47:53.665202: step: 152/526, loss: 0.002503872150555253
2023-01-23 02:47:54.761611: step: 156/526, loss: 0.6769391298294067
2023-01-23 02:47:55.914086: step: 160/526, loss: 0.015960121527314186
2023-01-23 02:47:57.025678: step: 164/526, loss: 0.0006322860717773438
2023-01-23 02:47:58.141996: step: 168/526, loss: 0.00020385385141707957
2023-01-23 02:47:59.250638: step: 172/526, loss: 0.000362205522833392
2023-01-23 02:48:00.414326: step: 176/526, loss: 0.011219596490263939
2023-01-23 02:48:01.538099: step: 180/526, loss: 0.002458763075992465
2023-01-23 02:48:02.690536: step: 184/526, loss: 0.056160926818847656
2023-01-23 02:48:03.819070: step: 188/526, loss: 0.00288143171928823
2023-01-23 02:48:04.992528: step: 192/526, loss: 0.00013942719670012593
2023-01-23 02:48:06.113796: step: 196/526, loss: 0.001413250109180808
2023-01-23 02:48:07.245816: step: 200/526, loss: -5.817413693876006e-06
2023-01-23 02:48:08.386264: step: 204/526, loss: 0.0038799287285655737
2023-01-23 02:48:09.538513: step: 208/526, loss: 0.00246429443359375
2023-01-23 02:48:10.691622: step: 212/526, loss: 0.0011867821449413896
2023-01-23 02:48:11.842407: step: 216/526, loss: 0.005230140872299671
2023-01-23 02:48:12.950433: step: 220/526, loss: 0.000162029275088571
2023-01-23 02:48:14.086108: step: 224/526, loss: 0.08713188767433167
2023-01-23 02:48:15.219731: step: 228/526, loss: 0.0001279830903513357
2023-01-23 02:48:16.346208: step: 232/526, loss: 0.00016760826110839844
2023-01-23 02:48:17.498310: step: 236/526, loss: 0.007582283113151789
2023-01-23 02:48:18.635142: step: 240/526, loss: 0.006156730465590954
2023-01-23 02:48:19.767319: step: 244/526, loss: 0.3327018916606903
2023-01-23 02:48:20.922807: step: 248/526, loss: 0.026578903198242188
2023-01-23 02:48:22.072498: step: 252/526, loss: 0.031252577900886536
2023-01-23 02:48:23.229700: step: 256/526, loss: 0.04587908089160919
2023-01-23 02:48:24.355556: step: 260/526, loss: 0.006936264224350452
2023-01-23 02:48:25.464273: step: 264/526, loss: 0.034091949462890625
2023-01-23 02:48:26.595758: step: 268/526, loss: 0.014538002200424671
2023-01-23 02:48:27.753497: step: 272/526, loss: 0.0017744064098224044
2023-01-23 02:48:28.867897: step: 276/526, loss: 0.0016389847733080387
2023-01-23 02:48:30.004986: step: 280/526, loss: 0.00045623781625181437
2023-01-23 02:48:31.140522: step: 284/526, loss: 3.490447852527723e-05
2023-01-23 02:48:32.272660: step: 288/526, loss: 0.004144859500229359
2023-01-23 02:48:33.401386: step: 292/526, loss: 0.001394808292388916
2023-01-23 02:48:34.516446: step: 296/526, loss: 0.0065250396728515625
2023-01-23 02:48:35.625116: step: 300/526, loss: 0.00018525123596191406
2023-01-23 02:48:36.745482: step: 304/526, loss: 0.02166776731610298
2023-01-23 02:48:37.873216: step: 308/526, loss: 0.0007217407692223787
2023-01-23 02:48:39.012505: step: 312/526, loss: 0.020790722221136093
2023-01-23 02:48:40.177091: step: 316/526, loss: 0.0076885223388671875
2023-01-23 02:48:41.340278: step: 320/526, loss: 0.0006165504455566406
2023-01-23 02:48:42.486539: step: 324/526, loss: 0.00026769639225676656
2023-01-23 02:48:43.642627: step: 328/526, loss: 0.00012283996329642832
2023-01-23 02:48:44.763645: step: 332/526, loss: 0.00047454837476834655
2023-01-23 02:48:45.922746: step: 336/526, loss: 0.04615335538983345
2023-01-23 02:48:47.059813: step: 340/526, loss: 0.02505502849817276
2023-01-23 02:48:48.193709: step: 344/526, loss: 0.012150764465332031
2023-01-23 02:48:49.305582: step: 348/526, loss: 0.00016164779663085938
2023-01-23 02:48:50.433289: step: 352/526, loss: 2.555847095209174e-05
2023-01-23 02:48:51.549108: step: 356/526, loss: 0.0003909110964741558
2023-01-23 02:48:52.679302: step: 360/526, loss: 0.0009027481428347528
2023-01-23 02:48:53.794392: step: 364/526, loss: 0.0010707378387451172
2023-01-23 02:48:54.943796: step: 368/526, loss: 0.006009960081428289
2023-01-23 02:48:56.059650: step: 372/526, loss: 0.0016978741623461246
2023-01-23 02:48:57.184635: step: 376/526, loss: 2.593994213384576e-05
2023-01-23 02:48:58.338459: step: 380/526, loss: 0.41187816858291626
2023-01-23 02:48:59.484531: step: 384/526, loss: 0.01841878890991211
2023-01-23 02:49:00.613346: step: 388/526, loss: 0.0015591621631756425
2023-01-23 02:49:01.838237: step: 392/526, loss: 0.001306819962337613
2023-01-23 02:49:02.980995: step: 396/526, loss: 0.0013326645130291581
2023-01-23 02:49:04.129063: step: 400/526, loss: 0.005376148037612438
2023-01-23 02:49:05.236543: step: 404/526, loss: 0.0003391265927348286
2023-01-23 02:49:06.351775: step: 408/526, loss: 0.010370636358857155
2023-01-23 02:49:07.517536: step: 412/526, loss: 0.013152694329619408
2023-01-23 02:49:08.649218: step: 416/526, loss: 0.00027751922607421875
2023-01-23 02:49:09.780657: step: 420/526, loss: 0.003524303436279297
2023-01-23 02:49:10.927669: step: 424/526, loss: 0.0001924514799611643
2023-01-23 02:49:12.067916: step: 428/526, loss: 0.00030245783273130655
2023-01-23 02:49:13.208955: step: 432/526, loss: 0.008660316467285156
2023-01-23 02:49:14.345383: step: 436/526, loss: 0.0016996384365484118
2023-01-23 02:49:15.498528: step: 440/526, loss: 0.07145905494689941
2023-01-23 02:49:16.634224: step: 444/526, loss: 0.011229896917939186
2023-01-23 02:49:17.764894: step: 448/526, loss: 0.0004977226490154862
2023-01-23 02:49:18.934067: step: 452/526, loss: 0.0056528570130467415
2023-01-23 02:49:20.075268: step: 456/526, loss: 0.031906794756650925
2023-01-23 02:49:21.210921: step: 460/526, loss: 0.03872022405266762
2023-01-23 02:49:22.359475: step: 464/526, loss: 0.0749279037117958
2023-01-23 02:49:23.506613: step: 468/526, loss: 0.016022302210330963
2023-01-23 02:49:24.639276: step: 472/526, loss: 0.012515926733613014
2023-01-23 02:49:25.771784: step: 476/526, loss: 0.008679866790771484
2023-01-23 02:49:26.881999: step: 480/526, loss: 0.009264945983886719
2023-01-23 02:49:28.024503: step: 484/526, loss: 0.00012111663818359375
2023-01-23 02:49:29.162358: step: 488/526, loss: 0.0001070022553903982
2023-01-23 02:49:30.295689: step: 492/526, loss: 0.001993560930714011
2023-01-23 02:49:31.437558: step: 496/526, loss: 0.0893864706158638
2023-01-23 02:49:32.611789: step: 500/526, loss: 0.003783321473747492
2023-01-23 02:49:33.765160: step: 504/526, loss: 0.05378151312470436
2023-01-23 02:49:34.896388: step: 508/526, loss: 0.004395103082060814
2023-01-23 02:49:36.024700: step: 512/526, loss: 0.0027160646859556437
2023-01-23 02:49:37.154702: step: 516/526, loss: 0.0011004448169842362
2023-01-23 02:49:38.317668: step: 520/526, loss: 0.004351044073700905
2023-01-23 02:49:39.459580: step: 524/526, loss: 0.00025691985501907766
2023-01-23 02:49:40.597293: step: 528/526, loss: 0.07616004347801208
2023-01-23 02:49:41.735084: step: 532/526, loss: 0.019036103039979935
2023-01-23 02:49:42.910883: step: 536/526, loss: 0.03952808678150177
2023-01-23 02:49:44.082146: step: 540/526, loss: 0.04286599159240723
2023-01-23 02:49:45.206975: step: 544/526, loss: 0.004156684968620539
2023-01-23 02:49:46.324450: step: 548/526, loss: 0.004384326748549938
2023-01-23 02:49:47.476500: step: 552/526, loss: 0.053180109709501266
2023-01-23 02:49:48.596962: step: 556/526, loss: 0.19768953323364258
2023-01-23 02:49:49.717070: step: 560/526, loss: 0.051331423223018646
2023-01-23 02:49:50.842280: step: 564/526, loss: 0.009510518051683903
2023-01-23 02:49:51.983676: step: 568/526, loss: 0.008899974636733532
2023-01-23 02:49:53.138157: step: 572/526, loss: 0.7971934080123901
2023-01-23 02:49:54.262734: step: 576/526, loss: 5.550384594243951e-05
2023-01-23 02:49:55.435928: step: 580/526, loss: 0.08259773254394531
2023-01-23 02:49:56.547772: step: 584/526, loss: 0.002389383502304554
2023-01-23 02:49:57.689405: step: 588/526, loss: 0.07661718130111694
2023-01-23 02:49:58.800478: step: 592/526, loss: 0.01572561450302601
2023-01-23 02:49:59.932365: step: 596/526, loss: 0.002519035479053855
2023-01-23 02:50:01.072292: step: 600/526, loss: 0.06179647520184517
2023-01-23 02:50:02.204893: step: 604/526, loss: 5.702972339349799e-05
2023-01-23 02:50:03.348221: step: 608/526, loss: 0.0007839202880859375
2023-01-23 02:50:04.447132: step: 612/526, loss: 0.13024960458278656
2023-01-23 02:50:05.588543: step: 616/526, loss: 0.027873611077666283
2023-01-23 02:50:06.726069: step: 620/526, loss: 0.00025959016056731343
2023-01-23 02:50:07.862826: step: 624/526, loss: 0.005276489537209272
2023-01-23 02:50:08.987645: step: 628/526, loss: 0.0034673691261559725
2023-01-23 02:50:10.132913: step: 632/526, loss: 0.009805584326386452
2023-01-23 02:50:11.263192: step: 636/526, loss: 0.1329864263534546
2023-01-23 02:50:12.413925: step: 640/526, loss: 0.00028667450533248484
2023-01-23 02:50:13.598544: step: 644/526, loss: 0.00048513413639739156
2023-01-23 02:50:14.766141: step: 648/526, loss: 0.003796863602474332
2023-01-23 02:50:15.908507: step: 652/526, loss: 0.0006948470836505294
2023-01-23 02:50:17.036647: step: 656/526, loss: 0.0022129060234874487
2023-01-23 02:50:18.153067: step: 660/526, loss: 0.00074005126953125
2023-01-23 02:50:19.259386: step: 664/526, loss: 0.018998026847839355
2023-01-23 02:50:20.382617: step: 668/526, loss: 0.0002020835963776335
2023-01-23 02:50:21.504776: step: 672/526, loss: 0.0016401291359215975
2023-01-23 02:50:22.621303: step: 676/526, loss: 7.805824861861765e-05
2023-01-23 02:50:23.753377: step: 680/526, loss: 0.04405937343835831
2023-01-23 02:50:24.887387: step: 684/526, loss: 0.0008193969842977822
2023-01-23 02:50:26.059452: step: 688/526, loss: 0.011666107922792435
2023-01-23 02:50:27.213834: step: 692/526, loss: 0.0013137817149981856
2023-01-23 02:50:28.366182: step: 696/526, loss: 0.0564454086124897
2023-01-23 02:50:29.477503: step: 700/526, loss: 0.0020854950416833162
2023-01-23 02:50:30.603464: step: 704/526, loss: 0.0004592418554238975
2023-01-23 02:50:31.750526: step: 708/526, loss: 0.0007997512584552169
2023-01-23 02:50:32.873936: step: 712/526, loss: 0.0018640517955645919
2023-01-23 02:50:33.994148: step: 716/526, loss: 0.0017558097606524825
2023-01-23 02:50:35.108786: step: 720/526, loss: 0.005951118189841509
2023-01-23 02:50:36.226018: step: 724/526, loss: 0.011051272973418236
2023-01-23 02:50:37.377730: step: 728/526, loss: 3.461838059592992e-05
2023-01-23 02:50:38.482196: step: 732/526, loss: 0.0335872657597065
2023-01-23 02:50:39.618626: step: 736/526, loss: 0.0017366409301757812
2023-01-23 02:50:40.781329: step: 740/526, loss: 0.0009332179906778038
2023-01-23 02:50:41.904099: step: 744/526, loss: 0.0045379637740552425
2023-01-23 02:50:43.052085: step: 748/526, loss: 0.00244560232385993
2023-01-23 02:50:44.228986: step: 752/526, loss: 0.007321167271584272
2023-01-23 02:50:45.359250: step: 756/526, loss: 0.010950089432299137
2023-01-23 02:50:46.494441: step: 760/526, loss: 0.00978775043040514
2023-01-23 02:50:47.655090: step: 764/526, loss: 0.0007270813221111894
2023-01-23 02:50:48.758371: step: 768/526, loss: 0.0001143455519923009
2023-01-23 02:50:49.868927: step: 772/526, loss: 0.0007000922923907638
2023-01-23 02:50:51.022187: step: 776/526, loss: 0.02962322160601616
2023-01-23 02:50:52.148650: step: 780/526, loss: 0.009371757507324219
2023-01-23 02:50:53.279226: step: 784/526, loss: 0.03220539167523384
2023-01-23 02:50:54.384293: step: 788/526, loss: 0.0026785852387547493
2023-01-23 02:50:55.535283: step: 792/526, loss: 0.0012484551407396793
2023-01-23 02:50:56.699704: step: 796/526, loss: 0.002890300704166293
2023-01-23 02:50:57.815772: step: 800/526, loss: 0.0004921913496218622
2023-01-23 02:50:58.952619: step: 804/526, loss: 0.007667350582778454
2023-01-23 02:51:00.095460: step: 808/526, loss: 0.0024403573479503393
2023-01-23 02:51:01.222399: step: 812/526, loss: 0.03808155283331871
2023-01-23 02:51:02.367188: step: 816/526, loss: 0.001123619033023715
2023-01-23 02:51:03.531037: step: 820/526, loss: 0.0014673233963549137
2023-01-23 02:51:04.652156: step: 824/526, loss: 0.003963470458984375
2023-01-23 02:51:05.795414: step: 828/526, loss: 0.0033691406715661287
2023-01-23 02:51:06.962864: step: 832/526, loss: 0.00855865515768528
2023-01-23 02:51:08.086107: step: 836/526, loss: 0.06293001025915146
2023-01-23 02:51:09.221656: step: 840/526, loss: 0.0031220437958836555
2023-01-23 02:51:10.342741: step: 844/526, loss: 0.0012376784579828382
2023-01-23 02:51:11.505232: step: 848/526, loss: 0.0039009093306958675
2023-01-23 02:51:12.622096: step: 852/526, loss: 0.00121135707013309
2023-01-23 02:51:13.720132: step: 856/526, loss: 0.004396343603730202
2023-01-23 02:51:14.873332: step: 860/526, loss: 0.003361320588737726
2023-01-23 02:51:15.997134: step: 864/526, loss: 0.009370803833007812
2023-01-23 02:51:17.152008: step: 868/526, loss: 0.00013895034499000758
2023-01-23 02:51:18.304240: step: 872/526, loss: 0.0012997627491131425
2023-01-23 02:51:19.467270: step: 876/526, loss: 0.00011072159395553172
2023-01-23 02:51:20.594651: step: 880/526, loss: 0.0006776810041628778
2023-01-23 02:51:21.708861: step: 884/526, loss: 0.0007840633625164628
2023-01-23 02:51:22.851842: step: 888/526, loss: 0.002006149385124445
2023-01-23 02:51:24.000962: step: 892/526, loss: 0.07366943359375
2023-01-23 02:51:25.128740: step: 896/526, loss: 0.010111522860825062
2023-01-23 02:51:26.259047: step: 900/526, loss: 0.002279567765071988
2023-01-23 02:51:27.400523: step: 904/526, loss: 0.0200684554874897
2023-01-23 02:51:28.546718: step: 908/526, loss: 0.04132337495684624
2023-01-23 02:51:29.671273: step: 912/526, loss: 0.0006594657897949219
2023-01-23 02:51:30.823329: step: 916/526, loss: 0.012527895160019398
2023-01-23 02:51:31.983987: step: 920/526, loss: 0.02466306835412979
2023-01-23 02:51:33.130001: step: 924/526, loss: 0.0007373809348791838
2023-01-23 02:51:34.243879: step: 928/526, loss: 0.004340458195656538
2023-01-23 02:51:35.370168: step: 932/526, loss: 0.0008606493356637657
2023-01-23 02:51:36.492807: step: 936/526, loss: 0.0002482891140971333
2023-01-23 02:51:37.659014: step: 940/526, loss: 0.005392646882683039
2023-01-23 02:51:38.793457: step: 944/526, loss: 0.002089262008666992
2023-01-23 02:51:39.941549: step: 948/526, loss: 7.686614844715223e-05
2023-01-23 02:51:41.041328: step: 952/526, loss: 0.006218052003532648
2023-01-23 02:51:42.163328: step: 956/526, loss: 0.011279726400971413
2023-01-23 02:51:43.317158: step: 960/526, loss: 0.0017913817428052425
2023-01-23 02:51:44.454846: step: 964/526, loss: 0.025225544348359108
2023-01-23 02:51:45.618267: step: 968/526, loss: 0.0002473831409588456
2023-01-23 02:51:46.751374: step: 972/526, loss: 0.006342696957290173
2023-01-23 02:51:47.875078: step: 976/526, loss: 0.041419509798288345
2023-01-23 02:51:49.015979: step: 980/526, loss: 0.0053726197220385075
2023-01-23 02:51:50.173087: step: 984/526, loss: 0.012337112799286842
2023-01-23 02:51:51.290204: step: 988/526, loss: 0.0006395340315066278
2023-01-23 02:51:52.401691: step: 992/526, loss: 0.00015773772611282766
2023-01-23 02:51:53.534295: step: 996/526, loss: 0.0021259307395666838
2023-01-23 02:51:54.654108: step: 1000/526, loss: 0.2614225447177887
2023-01-23 02:51:55.788660: step: 1004/526, loss: 0.008846092969179153
2023-01-23 02:51:56.914189: step: 1008/526, loss: 0.0010235786903649569
2023-01-23 02:51:58.036766: step: 1012/526, loss: 0.0001354217529296875
2023-01-23 02:51:59.202569: step: 1016/526, loss: 0.007870960049331188
2023-01-23 02:52:00.335495: step: 1020/526, loss: 0.28966444730758667
2023-01-23 02:52:01.466396: step: 1024/526, loss: 0.03288641199469566
2023-01-23 02:52:02.573578: step: 1028/526, loss: 0.003364419797435403
2023-01-23 02:52:03.689110: step: 1032/526, loss: 0.00110626220703125
2023-01-23 02:52:04.815660: step: 1036/526, loss: 0.010199260897934437
2023-01-23 02:52:05.921105: step: 1040/526, loss: 0.0016743659507483244
2023-01-23 02:52:07.071238: step: 1044/526, loss: 0.0010484218364581466
2023-01-23 02:52:08.197348: step: 1048/526, loss: 0.06405496597290039
2023-01-23 02:52:09.301831: step: 1052/526, loss: 0.000982570694759488
2023-01-23 02:52:10.448874: step: 1056/526, loss: 9.89913969533518e-05
2023-01-23 02:52:11.580940: step: 1060/526, loss: 0.020412160083651543
2023-01-23 02:52:12.677998: step: 1064/526, loss: 0.005828285589814186
2023-01-23 02:52:13.817603: step: 1068/526, loss: 0.0015296937199309468
2023-01-23 02:52:14.955841: step: 1072/526, loss: 0.0021698474884033203
2023-01-23 02:52:16.118772: step: 1076/526, loss: 0.16330471634864807
2023-01-23 02:52:17.236769: step: 1080/526, loss: 0.011344050988554955
2023-01-23 02:52:18.382806: step: 1084/526, loss: 0.004983521066606045
2023-01-23 02:52:19.529152: step: 1088/526, loss: 0.03205425664782524
2023-01-23 02:52:20.653557: step: 1092/526, loss: 0.006979084108024836
2023-01-23 02:52:21.771344: step: 1096/526, loss: 7.934570021461695e-05
2023-01-23 02:52:22.927923: step: 1100/526, loss: 0.006379425525665283
2023-01-23 02:52:24.081221: step: 1104/526, loss: 0.06604786217212677
2023-01-23 02:52:25.188896: step: 1108/526, loss: 0.0006956100696697831
2023-01-23 02:52:26.316621: step: 1112/526, loss: 0.030487921088933945
2023-01-23 02:52:27.447941: step: 1116/526, loss: 0.007526207249611616
2023-01-23 02:52:28.608777: step: 1120/526, loss: 3.3572022914886475
2023-01-23 02:52:29.756015: step: 1124/526, loss: 0.010141563601791859
2023-01-23 02:52:30.889969: step: 1128/526, loss: 0.02692718431353569
2023-01-23 02:52:32.024945: step: 1132/526, loss: 0.017857838422060013
2023-01-23 02:52:33.142221: step: 1136/526, loss: 0.045717716217041016
2023-01-23 02:52:34.275110: step: 1140/526, loss: 0.004385566804558039
2023-01-23 02:52:35.421777: step: 1144/526, loss: 0.008656119927763939
2023-01-23 02:52:36.571813: step: 1148/526, loss: 0.0003086090146098286
2023-01-23 02:52:37.718532: step: 1152/526, loss: 0.00015363693819381297
2023-01-23 02:52:38.855421: step: 1156/526, loss: 0.00024380684772040695
2023-01-23 02:52:40.009086: step: 1160/526, loss: 0.1223064437508583
2023-01-23 02:52:41.154866: step: 1164/526, loss: 0.0002887725713662803
2023-01-23 02:52:42.279748: step: 1168/526, loss: 0.0001964569091796875
2023-01-23 02:52:43.446640: step: 1172/526, loss: 0.0037279129028320312
2023-01-23 02:52:44.561461: step: 1176/526, loss: 0.04041862487792969
2023-01-23 02:52:45.701952: step: 1180/526, loss: 0.003768491791561246
2023-01-23 02:52:46.833776: step: 1184/526, loss: 0.008487510494887829
2023-01-23 02:52:47.970686: step: 1188/526, loss: 0.004865836817771196
2023-01-23 02:52:49.111122: step: 1192/526, loss: 0.0011693955166265368
2023-01-23 02:52:50.246387: step: 1196/526, loss: 0.009299135766923428
2023-01-23 02:52:51.354494: step: 1200/526, loss: 0.004569625947624445
2023-01-23 02:52:52.467414: step: 1204/526, loss: 0.0004795074346475303
2023-01-23 02:52:53.635101: step: 1208/526, loss: 0.0012329102028161287
2023-01-23 02:52:54.822131: step: 1212/526, loss: 0.00013685226440429688
2023-01-23 02:52:55.939661: step: 1216/526, loss: 0.0016552448505535722
2023-01-23 02:52:57.067193: step: 1220/526, loss: 0.010214329697191715
2023-01-23 02:52:58.186768: step: 1224/526, loss: 0.020691586658358574
2023-01-23 02:52:59.327994: step: 1228/526, loss: 0.04051556438207626
2023-01-23 02:53:00.494480: step: 1232/526, loss: 0.0010293960804119706
2023-01-23 02:53:01.612323: step: 1236/526, loss: 0.004351616371423006
2023-01-23 02:53:02.771219: step: 1240/526, loss: 0.12619838118553162
2023-01-23 02:53:03.898095: step: 1244/526, loss: 0.04470691829919815
2023-01-23 02:53:05.028667: step: 1248/526, loss: 9.50813337112777e-05
2023-01-23 02:53:06.132029: step: 1252/526, loss: 0.005921554751694202
2023-01-23 02:53:07.320371: step: 1256/526, loss: 0.05605030059814453
2023-01-23 02:53:08.482094: step: 1260/526, loss: 0.03684492036700249
2023-01-23 02:53:09.609141: step: 1264/526, loss: 4.3201445805607364e-05
2023-01-23 02:53:10.751385: step: 1268/526, loss: 0.0005382538074627519
2023-01-23 02:53:11.894189: step: 1272/526, loss: 0.026052093133330345
2023-01-23 02:53:13.068687: step: 1276/526, loss: 0.023760223761200905
2023-01-23 02:53:14.198577: step: 1280/526, loss: 0.019644739106297493
2023-01-23 02:53:15.332703: step: 1284/526, loss: 0.07892999798059464
2023-01-23 02:53:16.461724: step: 1288/526, loss: 0.07939004898071289
2023-01-23 02:53:17.615931: step: 1292/526, loss: 0.007223606109619141
2023-01-23 02:53:18.763690: step: 1296/526, loss: 0.0036398889496922493
2023-01-23 02:53:19.882134: step: 1300/526, loss: 0.023408319801092148
2023-01-23 02:53:21.012872: step: 1304/526, loss: 0.0007158517837524414
2023-01-23 02:53:22.140115: step: 1308/526, loss: 0.0004914283636026084
2023-01-23 02:53:23.281917: step: 1312/526, loss: 0.015314054675400257
2023-01-23 02:53:24.412529: step: 1316/526, loss: 0.04575519636273384
2023-01-23 02:53:25.529899: step: 1320/526, loss: 0.00456581125035882
2023-01-23 02:53:26.653990: step: 1324/526, loss: 0.024317646399140358
2023-01-23 02:53:27.788644: step: 1328/526, loss: 0.0018795013893395662
2023-01-23 02:53:28.907077: step: 1332/526, loss: 0.0001222610444528982
2023-01-23 02:53:30.038085: step: 1336/526, loss: 6.780624244129285e-05
2023-01-23 02:53:31.172170: step: 1340/526, loss: 0.023294735699892044
2023-01-23 02:53:32.343981: step: 1344/526, loss: 0.005407619755715132
2023-01-23 02:53:33.490515: step: 1348/526, loss: 0.004045581910759211
2023-01-23 02:53:34.617436: step: 1352/526, loss: 0.002442646073177457
2023-01-23 02:53:35.743531: step: 1356/526, loss: 0.011979865841567516
2023-01-23 02:53:36.920478: step: 1360/526, loss: 0.0003926277277059853
2023-01-23 02:53:38.071601: step: 1364/526, loss: 0.056911028921604156
2023-01-23 02:53:39.231977: step: 1368/526, loss: 0.0006860733265057206
2023-01-23 02:53:40.410562: step: 1372/526, loss: 0.020235443487763405
2023-01-23 02:53:41.536764: step: 1376/526, loss: 0.0019110202556475997
2023-01-23 02:53:42.743290: step: 1380/526, loss: 0.0029584886506199837
2023-01-23 02:53:43.863003: step: 1384/526, loss: 0.056556131690740585
2023-01-23 02:53:44.986146: step: 1388/526, loss: 0.0019749163184314966
2023-01-23 02:53:46.123345: step: 1392/526, loss: 0.018282413482666016
2023-01-23 02:53:47.281779: step: 1396/526, loss: 0.049361322075128555
2023-01-23 02:53:48.432295: step: 1400/526, loss: 0.012869263999164104
2023-01-23 02:53:49.551261: step: 1404/526, loss: 0.013207531534135342
2023-01-23 02:53:50.703330: step: 1408/526, loss: 0.0507933609187603
2023-01-23 02:53:51.843328: step: 1412/526, loss: 0.001056671142578125
2023-01-23 02:53:52.982196: step: 1416/526, loss: 0.05953407287597656
2023-01-23 02:53:54.108780: step: 1420/526, loss: 0.00025424957857467234
2023-01-23 02:53:55.253527: step: 1424/526, loss: 0.008554554544389248
2023-01-23 02:53:56.386886: step: 1428/526, loss: 0.0001846313534770161
2023-01-23 02:53:57.568545: step: 1432/526, loss: 0.0018165588844567537
2023-01-23 02:53:58.676989: step: 1436/526, loss: 0.006369304843246937
2023-01-23 02:53:59.810531: step: 1440/526, loss: 1.2578611373901367
2023-01-23 02:54:00.926242: step: 1444/526, loss: 0.04019184038043022
2023-01-23 02:54:02.105483: step: 1448/526, loss: 0.0037845612969249487
2023-01-23 02:54:03.219266: step: 1452/526, loss: 0.011424875818192959
2023-01-23 02:54:04.363593: step: 1456/526, loss: 0.017191004008054733
2023-01-23 02:54:05.508531: step: 1460/526, loss: 0.00021476746769621968
2023-01-23 02:54:06.647189: step: 1464/526, loss: 0.02669076807796955
2023-01-23 02:54:07.759643: step: 1468/526, loss: 0.015716170892119408
2023-01-23 02:54:08.899785: step: 1472/526, loss: 0.3119939863681793
2023-01-23 02:54:10.035177: step: 1476/526, loss: 0.043900683522224426
2023-01-23 02:54:11.179979: step: 1480/526, loss: 0.013406753540039062
2023-01-23 02:54:12.301029: step: 1484/526, loss: 0.005054283421486616
2023-01-23 02:54:13.460096: step: 1488/526, loss: 9.54627976170741e-05
2023-01-23 02:54:14.565368: step: 1492/526, loss: 8.74519391800277e-05
2023-01-23 02:54:15.705533: step: 1496/526, loss: 0.0009054184192791581
2023-01-23 02:54:16.850173: step: 1500/526, loss: 0.02503795549273491
2023-01-23 02:54:17.990791: step: 1504/526, loss: 0.03236541897058487
2023-01-23 02:54:19.136778: step: 1508/526, loss: 0.011465073563158512
2023-01-23 02:54:20.262180: step: 1512/526, loss: 0.0006618499755859375
2023-01-23 02:54:21.407806: step: 1516/526, loss: 0.019887637346982956
2023-01-23 02:54:22.563306: step: 1520/526, loss: 0.024776078760623932
2023-01-23 02:54:23.704761: step: 1524/526, loss: 0.06181182712316513
2023-01-23 02:54:24.804471: step: 1528/526, loss: 0.012237167917191982
2023-01-23 02:54:25.938684: step: 1532/526, loss: 0.022452736273407936
2023-01-23 02:54:27.088495: step: 1536/526, loss: 0.004935645963996649
2023-01-23 02:54:28.232892: step: 1540/526, loss: 0.09390906989574432
2023-01-23 02:54:29.365005: step: 1544/526, loss: 0.06961756199598312
2023-01-23 02:54:30.494471: step: 1548/526, loss: 0.00020637513080146164
2023-01-23 02:54:31.647410: step: 1552/526, loss: 0.00033464431180618703
2023-01-23 02:54:32.765327: step: 1556/526, loss: 0.008463717065751553
2023-01-23 02:54:33.918788: step: 1560/526, loss: 0.006465005688369274
2023-01-23 02:54:35.048020: step: 1564/526, loss: 0.010308075696229935
2023-01-23 02:54:36.171837: step: 1568/526, loss: 0.00166234967764467
2023-01-23 02:54:37.302683: step: 1572/526, loss: 0.000884628330823034
2023-01-23 02:54:38.437314: step: 1576/526, loss: 0.02577190473675728
2023-01-23 02:54:39.592171: step: 1580/526, loss: 0.00014653205289505422
2023-01-23 02:54:40.739596: step: 1584/526, loss: 0.01144180353730917
2023-01-23 02:54:41.869875: step: 1588/526, loss: 0.06480150669813156
2023-01-23 02:54:43.013069: step: 1592/526, loss: 0.022624492645263672
2023-01-23 02:54:44.141955: step: 1596/526, loss: 0.007863807491958141
2023-01-23 02:54:45.281788: step: 1600/526, loss: 0.07386551052331924
2023-01-23 02:54:46.417966: step: 1604/526, loss: 0.00031976698664948344
2023-01-23 02:54:47.544431: step: 1608/526, loss: 0.0014957428211346269
2023-01-23 02:54:48.652290: step: 1612/526, loss: 0.0033864020369946957
2023-01-23 02:54:49.775138: step: 1616/526, loss: 0.00646553048864007
2023-01-23 02:54:50.923326: step: 1620/526, loss: 0.0007458686595782638
2023-01-23 02:54:52.039134: step: 1624/526, loss: 0.0003383636358194053
2023-01-23 02:54:53.159812: step: 1628/526, loss: 0.0008148193592205644
2023-01-23 02:54:54.308374: step: 1632/526, loss: 0.0019855499267578125
2023-01-23 02:54:55.425156: step: 1636/526, loss: 0.0309618953615427
2023-01-23 02:54:56.566498: step: 1640/526, loss: 0.11971358954906464
2023-01-23 02:54:57.705771: step: 1644/526, loss: 0.045342352241277695
2023-01-23 02:54:58.852854: step: 1648/526, loss: 0.012560510076582432
2023-01-23 02:55:00.018900: step: 1652/526, loss: 0.5659523606300354
2023-01-23 02:55:01.144551: step: 1656/526, loss: 8.678436279296875e-05
2023-01-23 02:55:02.283439: step: 1660/526, loss: 0.08686403930187225
2023-01-23 02:55:03.440798: step: 1664/526, loss: 0.01342916488647461
2023-01-23 02:55:04.556492: step: 1668/526, loss: 0.0015675545437261462
2023-01-23 02:55:05.694666: step: 1672/526, loss: 0.018215179443359375
2023-01-23 02:55:06.806395: step: 1676/526, loss: 0.0036699294578284025
2023-01-23 02:55:07.962314: step: 1680/526, loss: 0.002609443850815296
2023-01-23 02:55:09.154849: step: 1684/526, loss: 0.040708158165216446
2023-01-23 02:55:10.285475: step: 1688/526, loss: 0.00033969880314543843
2023-01-23 02:55:11.444494: step: 1692/526, loss: 0.007490825839340687
2023-01-23 02:55:12.584291: step: 1696/526, loss: 0.0001761198218446225
2023-01-23 02:55:13.719542: step: 1700/526, loss: 0.0016808509826660156
2023-01-23 02:55:14.840333: step: 1704/526, loss: 0.11907405406236649
2023-01-23 02:55:15.972699: step: 1708/526, loss: 0.000491237617097795
2023-01-23 02:55:17.116105: step: 1712/526, loss: 0.009769630618393421
2023-01-23 02:55:18.218368: step: 1716/526, loss: 0.004180431831628084
2023-01-23 02:55:19.351890: step: 1720/526, loss: 0.00036249158438295126
2023-01-23 02:55:20.476548: step: 1724/526, loss: 0.018470002338290215
2023-01-23 02:55:21.624517: step: 1728/526, loss: 0.0008161545265465975
2023-01-23 02:55:22.766574: step: 1732/526, loss: 0.0032661438453942537
2023-01-23 02:55:23.870527: step: 1736/526, loss: 0.003948402591049671
2023-01-23 02:55:25.021622: step: 1740/526, loss: 0.004609107971191406
2023-01-23 02:55:26.158892: step: 1744/526, loss: 1.087188684323337e-05
2023-01-23 02:55:27.303984: step: 1748/526, loss: 8.764266385696828e-05
2023-01-23 02:55:28.417040: step: 1752/526, loss: 0.0004631519550457597
2023-01-23 02:55:29.543576: step: 1756/526, loss: 0.04333467409014702
2023-01-23 02:55:30.688016: step: 1760/526, loss: 0.006010818760842085
2023-01-23 02:55:31.815101: step: 1764/526, loss: 0.012990808114409447
2023-01-23 02:55:32.938252: step: 1768/526, loss: 0.00030841826810501516
2023-01-23 02:55:34.075137: step: 1772/526, loss: 0.015382003039121628
2023-01-23 02:55:35.234910: step: 1776/526, loss: 0.0013078690972179174
2023-01-23 02:55:36.376956: step: 1780/526, loss: 0.01412954367697239
2023-01-23 02:55:37.503094: step: 1784/526, loss: 0.015067672356963158
2023-01-23 02:55:38.649955: step: 1788/526, loss: 0.0002401351957814768
2023-01-23 02:55:39.801437: step: 1792/526, loss: 0.010203742422163486
2023-01-23 02:55:40.914403: step: 1796/526, loss: 0.011493491940200329
2023-01-23 02:55:42.093305: step: 1800/526, loss: 0.00045299530029296875
2023-01-23 02:55:43.240157: step: 1804/526, loss: 0.00174713134765625
2023-01-23 02:55:44.399065: step: 1808/526, loss: 0.0053535462357103825
2023-01-23 02:55:45.556856: step: 1812/526, loss: 0.04392185062170029
2023-01-23 02:55:46.690361: step: 1816/526, loss: 0.03929167240858078
2023-01-23 02:55:47.816560: step: 1820/526, loss: 0.0029132843483239412
2023-01-23 02:55:48.952209: step: 1824/526, loss: 0.003966331481933594
2023-01-23 02:55:50.089720: step: 1828/526, loss: 4.119873119634576e-05
2023-01-23 02:55:51.260745: step: 1832/526, loss: 0.0009430170175619423
2023-01-23 02:55:52.382065: step: 1836/526, loss: 0.0008721351623535156
2023-01-23 02:55:53.518197: step: 1840/526, loss: 0.0004553794860839844
2023-01-23 02:55:54.657870: step: 1844/526, loss: 0.01766662672162056
2023-01-23 02:55:55.817395: step: 1848/526, loss: 0.06209850311279297
2023-01-23 02:55:56.946437: step: 1852/526, loss: 0.0024175643920898438
2023-01-23 02:55:58.101576: step: 1856/526, loss: 0.015548134222626686
2023-01-23 02:55:59.241031: step: 1860/526, loss: 0.05914344638586044
2023-01-23 02:56:00.352581: step: 1864/526, loss: 0.015493202954530716
2023-01-23 02:56:01.460098: step: 1868/526, loss: 0.0035613062791526318
2023-01-23 02:56:02.581569: step: 1872/526, loss: 0.03834743797779083
2023-01-23 02:56:03.731120: step: 1876/526, loss: 0.003623581025749445
2023-01-23 02:56:04.871010: step: 1880/526, loss: 0.10078783333301544
2023-01-23 02:56:06.035414: step: 1884/526, loss: 0.004490470979362726
2023-01-23 02:56:07.157407: step: 1888/526, loss: 0.029277898371219635
2023-01-23 02:56:08.319065: step: 1892/526, loss: 0.05825882405042648
2023-01-23 02:56:09.447722: step: 1896/526, loss: 0.0011039734818041325
2023-01-23 02:56:10.606121: step: 1900/526, loss: 0.01141433697193861
2023-01-23 02:56:11.748452: step: 1904/526, loss: 0.03253369405865669
2023-01-23 02:56:12.914075: step: 1908/526, loss: 0.04561123996973038
2023-01-23 02:56:14.053852: step: 1912/526, loss: 0.21059799194335938
2023-01-23 02:56:15.178884: step: 1916/526, loss: 0.0005908012972213328
2023-01-23 02:56:16.311985: step: 1920/526, loss: 0.03829069063067436
2023-01-23 02:56:17.459640: step: 1924/526, loss: 0.0013586044078692794
2023-01-23 02:56:18.636926: step: 1928/526, loss: 0.0010437011951580644
2023-01-23 02:56:19.765097: step: 1932/526, loss: 0.03102397918701172
2023-01-23 02:56:20.893991: step: 1936/526, loss: 0.04813690111041069
2023-01-23 02:56:22.061977: step: 1940/526, loss: 0.0011905670398846269
2023-01-23 02:56:23.198997: step: 1944/526, loss: 0.015375280752778053
2023-01-23 02:56:24.322452: step: 1948/526, loss: 0.0049228668212890625
2023-01-23 02:56:25.460113: step: 1952/526, loss: 0.015409660525619984
2023-01-23 02:56:26.608083: step: 1956/526, loss: 0.0035962106194347143
2023-01-23 02:56:27.719026: step: 1960/526, loss: 0.0007603645208291709
2023-01-23 02:56:28.828446: step: 1964/526, loss: 0.0023645402397960424
2023-01-23 02:56:29.991075: step: 1968/526, loss: 0.009099221788346767
2023-01-23 02:56:31.122021: step: 1972/526, loss: 1.1745659112930298
2023-01-23 02:56:32.244773: step: 1976/526, loss: 0.00012474060349632055
2023-01-23 02:56:33.380591: step: 1980/526, loss: 0.05372639000415802
2023-01-23 02:56:34.496684: step: 1984/526, loss: 0.0029954910278320312
2023-01-23 02:56:35.625704: step: 1988/526, loss: 0.02149381674826145
2023-01-23 02:56:36.762248: step: 1992/526, loss: 0.010166740976274014
2023-01-23 02:56:37.873102: step: 1996/526, loss: 0.006605816073715687
2023-01-23 02:56:39.000991: step: 2000/526, loss: 0.004673957824707031
2023-01-23 02:56:40.128591: step: 2004/526, loss: 0.05335378646850586
2023-01-23 02:56:41.242056: step: 2008/526, loss: 0.002769661135971546
2023-01-23 02:56:42.336827: step: 2012/526, loss: 0.012269878759980202
2023-01-23 02:56:43.472164: step: 2016/526, loss: 0.0002658843877725303
2023-01-23 02:56:44.589788: step: 2020/526, loss: 0.008564758114516735
2023-01-23 02:56:45.718950: step: 2024/526, loss: 0.020326614379882812
2023-01-23 02:56:46.847667: step: 2028/526, loss: 0.004642868414521217
2023-01-23 02:56:47.980052: step: 2032/526, loss: 0.05483055114746094
2023-01-23 02:56:49.128131: step: 2036/526, loss: 0.03961320221424103
2023-01-23 02:56:50.277620: step: 2040/526, loss: 0.0009190559503622353
2023-01-23 02:56:51.390021: step: 2044/526, loss: 0.00111560826189816
2023-01-23 02:56:52.539119: step: 2048/526, loss: 0.0001163482666015625
2023-01-23 02:56:53.668941: step: 2052/526, loss: 0.0025037764571607113
2023-01-23 02:56:54.854463: step: 2056/526, loss: 0.0027428148314356804
2023-01-23 02:56:55.988657: step: 2060/526, loss: 0.000681972480379045
2023-01-23 02:56:57.122997: step: 2064/526, loss: 0.04315071552991867
2023-01-23 02:56:58.235279: step: 2068/526, loss: 0.06378169357776642
2023-01-23 02:56:59.415501: step: 2072/526, loss: 0.05233726650476456
2023-01-23 02:57:00.526432: step: 2076/526, loss: 0.05550270155072212
2023-01-23 02:57:01.641799: step: 2080/526, loss: 0.000972366367932409
2023-01-23 02:57:02.753626: step: 2084/526, loss: 0.0005901813274249434
2023-01-23 02:57:03.899885: step: 2088/526, loss: 3.24249267578125e-05
2023-01-23 02:57:05.010674: step: 2092/526, loss: 0.002309608506038785
2023-01-23 02:57:06.144691: step: 2096/526, loss: 0.001995277591049671
2023-01-23 02:57:07.335413: step: 2100/526, loss: 0.010618305765092373
2023-01-23 02:57:08.496125: step: 2104/526, loss: 0.6264249682426453
==================================================
Loss: 0.035
--------------------
Dev: {'event': {'p': 0.6002076843198338, 'r': 0.7696404793608522, 'f1': 0.6744457409568262}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
Test: {'event': {'p': 0.6195244055068836, 'r': 0.7750521920668059, 'f1': 0.6886158126594017}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
Chinese: {'event': {'p': 0.6049382716049383, 'r': 0.9074074074074074, 'f1': 0.725925925925926}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
Korean: {'event': {'p': 0.625, 'r': 0.47619047619047616, 'f1': 0.5405405405405405}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
Russian: {'event': {'p': 0.48717948717948717, 'r': 0.5277777777777778, 'f1': 0.5066666666666667}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6389811738648948, 'r': 0.7683089214380826, 'f1': 0.6977025392986699}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Eng Test for Chinese: {'event': {'p': 0.6328626444159179, 'r': 0.7719206680584552, 'f1': 0.6955090524335763}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Sample Chinese: {'event': {'p': 0.6282051282051282, 'r': 0.9074074074074074, 'f1': 0.7424242424242423}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6257995735607675, 'r': 0.7816245006657789, 'f1': 0.6950858496151568}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Eng Test for Korean: {'event': {'p': 0.623113410952997, 'r': 0.7541753653444676, 'f1': 0.6824085005903188}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Sample Korean: {'event': {'p': 0.7446808510638298, 'r': 0.5555555555555556, 'f1': 0.6363636363636364}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5800575263662512, 'r': 0.8055925432756325, 'f1': 0.6744704570791527}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
Eng Test for Russian: {'event': {'p': 0.5962534874451972, 'r': 0.7807933194154488, 'f1': 0.6761581920903954}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
Sample Russian: {'event': {'p': 0.48936170212765956, 'r': 0.6388888888888888, 'f1': 0.5542168674698795}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
******************************
Epoch: 20
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 02:57:51.382539: step: 4/526, loss: 0.008662414737045765
2023-01-23 02:57:52.526366: step: 8/526, loss: 0.0022936819586902857
2023-01-23 02:57:53.647889: step: 12/526, loss: 0.026631593704223633
2023-01-23 02:57:54.766376: step: 16/526, loss: 0.004110813140869141
2023-01-23 02:57:55.932424: step: 20/526, loss: 0.03275737911462784
2023-01-23 02:57:57.083998: step: 24/526, loss: 0.008294296450912952
2023-01-23 02:57:58.204023: step: 28/526, loss: 0.0003543853817973286
2023-01-23 02:57:59.332369: step: 32/526, loss: 0.0267989169806242
2023-01-23 02:58:00.472740: step: 36/526, loss: 0.0016130447620525956
2023-01-23 02:58:01.636051: step: 40/526, loss: 0.0018735886551439762
2023-01-23 02:58:02.768806: step: 44/526, loss: 0.017012406140565872
2023-01-23 02:58:03.910143: step: 48/526, loss: 0.031696319580078125
2023-01-23 02:58:05.040780: step: 52/526, loss: 0.0003904342884197831
2023-01-23 02:58:06.183409: step: 56/526, loss: 0.0060860635712742805
2023-01-23 02:58:07.323057: step: 60/526, loss: 0.004594231024384499
2023-01-23 02:58:08.455281: step: 64/526, loss: 0.0503849983215332
2023-01-23 02:58:09.571382: step: 68/526, loss: 0.03251781314611435
2023-01-23 02:58:10.676913: step: 72/526, loss: 0.030513763427734375
2023-01-23 02:58:11.806162: step: 76/526, loss: 0.004304409027099609
2023-01-23 02:58:12.964783: step: 80/526, loss: 0.02356109768152237
2023-01-23 02:58:14.112356: step: 84/526, loss: 0.0033503533340990543
2023-01-23 02:58:15.240901: step: 88/526, loss: 0.10881023108959198
2023-01-23 02:58:16.370911: step: 92/526, loss: 0.005959033966064453
2023-01-23 02:58:17.497112: step: 96/526, loss: 0.038561441004276276
2023-01-23 02:58:18.628629: step: 100/526, loss: 0.08673276752233505
2023-01-23 02:58:19.811856: step: 104/526, loss: 0.009797859936952591
2023-01-23 02:58:20.930761: step: 108/526, loss: 0.0013260364066809416
2023-01-23 02:58:22.079147: step: 112/526, loss: 0.0035336497239768505
2023-01-23 02:58:23.191899: step: 116/526, loss: 0.0030756951309740543
2023-01-23 02:58:24.321938: step: 120/526, loss: 0.00119953160174191
2023-01-23 02:58:25.447965: step: 124/526, loss: 0.13245049118995667
2023-01-23 02:58:26.570972: step: 128/526, loss: 0.026577377691864967
2023-01-23 02:58:27.718931: step: 132/526, loss: 0.0005876541254110634
2023-01-23 02:58:28.880696: step: 136/526, loss: 4.6539309551008046e-05
2023-01-23 02:58:30.040347: step: 140/526, loss: 0.46959877014160156
2023-01-23 02:58:31.146882: step: 144/526, loss: 4.472732689464465e-05
2023-01-23 02:58:32.268932: step: 148/526, loss: 0.06671886146068573
2023-01-23 02:58:33.395098: step: 152/526, loss: 0.01216268539428711
2023-01-23 02:58:34.522500: step: 156/526, loss: 0.07796640694141388
2023-01-23 02:58:35.685393: step: 160/526, loss: 0.0018405914306640625
2023-01-23 02:58:36.806441: step: 164/526, loss: 0.013413524255156517
2023-01-23 02:58:37.953927: step: 168/526, loss: 0.01057729683816433
2023-01-23 02:58:39.107459: step: 172/526, loss: 0.003068685531616211
2023-01-23 02:58:40.249766: step: 176/526, loss: 0.011515045538544655
2023-01-23 02:58:41.391140: step: 180/526, loss: 0.0022478103637695312
2023-01-23 02:58:42.513347: step: 184/526, loss: 0.00024209023104049265
2023-01-23 02:58:43.663324: step: 188/526, loss: 0.015596580691635609
2023-01-23 02:58:44.783088: step: 192/526, loss: 0.001821327256038785
2023-01-23 02:58:45.912513: step: 196/526, loss: 0.002061271807178855
2023-01-23 02:58:47.060015: step: 200/526, loss: 0.0034610747825354338
2023-01-23 02:58:48.202836: step: 204/526, loss: 0.0010433197021484375
2023-01-23 02:58:49.329309: step: 208/526, loss: 0.066799096763134
2023-01-23 02:58:50.470783: step: 212/526, loss: 0.02425518073141575
2023-01-23 02:58:51.644195: step: 216/526, loss: 0.0002548217598814517
2023-01-23 02:58:52.791550: step: 220/526, loss: 8.0108642578125e-05
2023-01-23 02:58:53.901255: step: 224/526, loss: 0.0036037445534020662
2023-01-23 02:58:55.042172: step: 228/526, loss: 0.0024479867424815893
2023-01-23 02:58:56.213007: step: 232/526, loss: 0.0008649826049804688
2023-01-23 02:58:57.347626: step: 236/526, loss: 7.610320608364418e-05
2023-01-23 02:58:58.490449: step: 240/526, loss: 0.007566928863525391
2023-01-23 02:58:59.649054: step: 244/526, loss: 0.014372158795595169
2023-01-23 02:59:00.824287: step: 248/526, loss: 0.0122231962159276
2023-01-23 02:59:01.997308: step: 252/526, loss: 0.010809803381562233
2023-01-23 02:59:03.135853: step: 256/526, loss: 0.0030279161874204874
2023-01-23 02:59:04.270039: step: 260/526, loss: 0.017367172986268997
2023-01-23 02:59:05.398963: step: 264/526, loss: 0.003933716099709272
2023-01-23 02:59:06.508746: step: 268/526, loss: 0.0010600090026855469
2023-01-23 02:59:07.671231: step: 272/526, loss: 0.005539131350815296
2023-01-23 02:59:08.793330: step: 276/526, loss: 0.0018835067749023438
2023-01-23 02:59:09.938615: step: 280/526, loss: 0.04064541310071945
2023-01-23 02:59:11.068348: step: 284/526, loss: 0.018976211547851562
2023-01-23 02:59:12.200049: step: 288/526, loss: 0.000465583783807233
2023-01-23 02:59:13.321544: step: 292/526, loss: 0.016098307445645332
2023-01-23 02:59:14.436653: step: 296/526, loss: 0.03547964245080948
2023-01-23 02:59:15.541892: step: 300/526, loss: 3.4332275390625e-05
2023-01-23 02:59:16.670136: step: 304/526, loss: 0.0005561828729696572
2023-01-23 02:59:17.823552: step: 308/526, loss: 0.04275531694293022
2023-01-23 02:59:18.944761: step: 312/526, loss: 0.029764842242002487
2023-01-23 02:59:20.100912: step: 316/526, loss: 0.0011840820079669356
2023-01-23 02:59:21.252471: step: 320/526, loss: 0.00020751955162268132
2023-01-23 02:59:22.400685: step: 324/526, loss: 0.0038070681039243937
2023-01-23 02:59:23.514744: step: 328/526, loss: 0.0008877277723513544
2023-01-23 02:59:24.660010: step: 332/526, loss: 0.0111550809815526
2023-01-23 02:59:25.798865: step: 336/526, loss: 0.005178261082619429
2023-01-23 02:59:26.950203: step: 340/526, loss: 0.005114555358886719
2023-01-23 02:59:28.073723: step: 344/526, loss: 0.04802040755748749
2023-01-23 02:59:29.179748: step: 348/526, loss: 0.03889113664627075
2023-01-23 02:59:30.319425: step: 352/526, loss: 0.0025335310492664576
2023-01-23 02:59:31.479640: step: 356/526, loss: 0.0007738113636150956
2023-01-23 02:59:32.624431: step: 360/526, loss: 0.003078365232795477
2023-01-23 02:59:33.732301: step: 364/526, loss: 0.00016260147094726562
2023-01-23 02:59:34.842524: step: 368/526, loss: 0.00022807122149970382
2023-01-23 02:59:35.960140: step: 372/526, loss: 0.0009864807361736894
2023-01-23 02:59:37.106005: step: 376/526, loss: 0.013430309481918812
2023-01-23 02:59:38.238417: step: 380/526, loss: 0.039034079760313034
2023-01-23 02:59:39.356529: step: 384/526, loss: 0.022102834656834602
2023-01-23 02:59:40.532943: step: 388/526, loss: 0.04153728485107422
2023-01-23 02:59:41.694191: step: 392/526, loss: 0.019054889678955078
2023-01-23 02:59:42.845383: step: 396/526, loss: 0.002621936844661832
2023-01-23 02:59:43.995108: step: 400/526, loss: 0.0005519867409020662
2023-01-23 02:59:45.160835: step: 404/526, loss: 0.004413604736328125
2023-01-23 02:59:46.272739: step: 408/526, loss: 0.0004318237479310483
2023-01-23 02:59:47.406352: step: 412/526, loss: 0.0005514145013876259
2023-01-23 02:59:48.532408: step: 416/526, loss: 0.011383152566850185
2023-01-23 02:59:49.671306: step: 420/526, loss: 0.000705337559338659
2023-01-23 02:59:50.782538: step: 424/526, loss: 0.0006591796991415322
2023-01-23 02:59:51.909121: step: 428/526, loss: 0.016489028930664062
2023-01-23 02:59:53.055490: step: 432/526, loss: 0.0018028260674327612
2023-01-23 02:59:54.189918: step: 436/526, loss: 0.004520082380622625
2023-01-23 02:59:55.319011: step: 440/526, loss: 0.019710969179868698
2023-01-23 02:59:56.445107: step: 444/526, loss: 0.02992267720401287
2023-01-23 02:59:57.591285: step: 448/526, loss: 0.0019376755226403475
2023-01-23 02:59:58.758510: step: 452/526, loss: 0.010999870486557484
2023-01-23 02:59:59.870467: step: 456/526, loss: 0.001827335450798273
2023-01-23 03:00:01.000024: step: 460/526, loss: 0.030975341796875
2023-01-23 03:00:02.132449: step: 464/526, loss: 0.003909969702363014
2023-01-23 03:00:03.262381: step: 468/526, loss: 0.01716022565960884
2023-01-23 03:00:04.427223: step: 472/526, loss: 0.02118987962603569
2023-01-23 03:00:05.592791: step: 476/526, loss: 0.005733489990234375
2023-01-23 03:00:06.691913: step: 480/526, loss: 0.035212136805057526
2023-01-23 03:00:07.831749: step: 484/526, loss: 0.0033697127364575863
2023-01-23 03:00:08.945940: step: 488/526, loss: 0.00046815871610306203
2023-01-23 03:00:10.057000: step: 492/526, loss: 0.00011920929682673886
2023-01-23 03:00:11.178775: step: 496/526, loss: 0.00930414255708456
2023-01-23 03:00:12.351533: step: 500/526, loss: 0.03080577775835991
2023-01-23 03:00:13.478448: step: 504/526, loss: 0.0016635895008221269
2023-01-23 03:00:14.606773: step: 508/526, loss: 0.018720198422670364
2023-01-23 03:00:15.726272: step: 512/526, loss: 0.021756650879979134
2023-01-23 03:00:16.847060: step: 516/526, loss: 0.003030061721801758
2023-01-23 03:00:17.983773: step: 520/526, loss: 0.006154346279799938
2023-01-23 03:00:19.123360: step: 524/526, loss: 0.03164198622107506
2023-01-23 03:00:20.249700: step: 528/526, loss: 0.0017748832469806075
2023-01-23 03:00:21.386796: step: 532/526, loss: 0.9338005185127258
2023-01-23 03:00:22.533189: step: 536/526, loss: 0.016043568029999733
2023-01-23 03:00:23.659024: step: 540/526, loss: 0.0060829161666333675
2023-01-23 03:00:24.800396: step: 544/526, loss: 0.0071166991256177425
2023-01-23 03:00:25.907982: step: 548/526, loss: 0.022026633843779564
2023-01-23 03:00:27.049022: step: 552/526, loss: 0.012973785400390625
2023-01-23 03:00:28.169389: step: 556/526, loss: 0.04305992275476456
2023-01-23 03:00:29.335305: step: 560/526, loss: 0.1744460165500641
2023-01-23 03:00:30.445644: step: 564/526, loss: 0.005134296137839556
2023-01-23 03:00:31.580414: step: 568/526, loss: 0.01647663116455078
2023-01-23 03:00:32.692490: step: 572/526, loss: 0.017051076516509056
2023-01-23 03:00:33.829116: step: 576/526, loss: 0.00013923646474722773
2023-01-23 03:00:34.977973: step: 580/526, loss: 0.8529098629951477
2023-01-23 03:00:36.090205: step: 584/526, loss: 0.00033941271249204874
2023-01-23 03:00:37.221349: step: 588/526, loss: 0.04522562026977539
2023-01-23 03:00:38.354492: step: 592/526, loss: 0.013078402727842331
2023-01-23 03:00:39.480748: step: 596/526, loss: 7.896423630882055e-05
2023-01-23 03:00:40.612324: step: 600/526, loss: 0.00023504496493842453
2023-01-23 03:00:41.745182: step: 604/526, loss: 0.006578922271728516
2023-01-23 03:00:42.929482: step: 608/526, loss: 0.004994774237275124
2023-01-23 03:00:44.085368: step: 612/526, loss: 0.015529632568359375
2023-01-23 03:00:45.184316: step: 616/526, loss: 0.00028600695077329874
2023-01-23 03:00:46.341989: step: 620/526, loss: 0.045827675610780716
2023-01-23 03:00:47.478427: step: 624/526, loss: 0.029549982398748398
2023-01-23 03:00:48.609117: step: 628/526, loss: 0.020139122381806374
2023-01-23 03:00:49.739445: step: 632/526, loss: 0.08129234611988068
2023-01-23 03:00:50.855847: step: 636/526, loss: 0.025841902941465378
2023-01-23 03:00:51.997286: step: 640/526, loss: 0.00016098022751975805
2023-01-23 03:00:53.175641: step: 644/526, loss: 0.004547500517219305
2023-01-23 03:00:54.293958: step: 648/526, loss: 0.008652115240693092
2023-01-23 03:00:55.436416: step: 652/526, loss: 0.036055564880371094
2023-01-23 03:00:56.558369: step: 656/526, loss: 0.045095063745975494
2023-01-23 03:00:57.675054: step: 660/526, loss: 0.039093874394893646
2023-01-23 03:00:58.822120: step: 664/526, loss: 0.01661090739071369
2023-01-23 03:00:59.980022: step: 668/526, loss: 0.019431401044130325
2023-01-23 03:01:01.152063: step: 672/526, loss: 0.0045073507353663445
2023-01-23 03:01:02.282431: step: 676/526, loss: 0.0020751953125
2023-01-23 03:01:03.409808: step: 680/526, loss: 0.010302400216460228
2023-01-23 03:01:04.585608: step: 684/526, loss: 0.0017220497829839587
2023-01-23 03:01:05.750903: step: 688/526, loss: 0.010897255502641201
2023-01-23 03:01:06.889631: step: 692/526, loss: 0.0023220062721520662
2023-01-23 03:01:08.025442: step: 696/526, loss: 0.07908478379249573
2023-01-23 03:01:09.143019: step: 700/526, loss: 0.006512641906738281
2023-01-23 03:01:10.265432: step: 704/526, loss: 1.4495850336970761e-05
2023-01-23 03:01:11.417058: step: 708/526, loss: 9.069442603504285e-05
2023-01-23 03:01:12.592527: step: 712/526, loss: 3.070831735385582e-05
2023-01-23 03:01:13.714299: step: 716/526, loss: 0.005942916963249445
2023-01-23 03:01:14.852442: step: 720/526, loss: 0.027880191802978516
2023-01-23 03:01:15.955167: step: 724/526, loss: 0.014525700360536575
2023-01-23 03:01:17.091834: step: 728/526, loss: 0.020452117547392845
2023-01-23 03:01:18.283256: step: 732/526, loss: 0.0024368285667151213
2023-01-23 03:01:19.429087: step: 736/526, loss: 0.035151004791259766
2023-01-23 03:01:20.557574: step: 740/526, loss: 0.003737926483154297
2023-01-23 03:01:21.666586: step: 744/526, loss: 0.0006657600752077997
2023-01-23 03:01:22.793634: step: 748/526, loss: 0.0006807803874835372
2023-01-23 03:01:23.909461: step: 752/526, loss: 0.006023693364113569
2023-01-23 03:01:25.007539: step: 756/526, loss: 0.00024518967256881297
2023-01-23 03:01:26.124945: step: 760/526, loss: 0.00254230503924191
2023-01-23 03:01:27.248738: step: 764/526, loss: 0.009168815799057484
2023-01-23 03:01:28.361210: step: 768/526, loss: 0.009664822369813919
2023-01-23 03:01:29.482052: step: 772/526, loss: 0.011925315484404564
2023-01-23 03:01:30.613293: step: 776/526, loss: 0.03355713188648224
2023-01-23 03:01:31.746686: step: 780/526, loss: 0.0022844793274998665
2023-01-23 03:01:32.888876: step: 784/526, loss: 0.03353118896484375
2023-01-23 03:01:34.019503: step: 788/526, loss: 0.0007905960083007812
2023-01-23 03:01:35.135260: step: 792/526, loss: 0.0034228325821459293
2023-01-23 03:01:36.250186: step: 796/526, loss: 0.0060859681107103825
2023-01-23 03:01:37.390852: step: 800/526, loss: 0.02203807793557644
2023-01-23 03:01:38.536660: step: 804/526, loss: 0.0038338659796863794
2023-01-23 03:01:39.617461: step: 808/526, loss: 0.00023289918317459524
2023-01-23 03:01:40.730667: step: 812/526, loss: 8.01086389401462e-06
2023-01-23 03:01:41.877372: step: 816/526, loss: 0.009660053066909313
2023-01-23 03:01:43.016676: step: 820/526, loss: 0.006104851141571999
2023-01-23 03:01:44.147769: step: 824/526, loss: 0.00021295547776389867
2023-01-23 03:01:45.284055: step: 828/526, loss: 0.0024540661834180355
2023-01-23 03:01:46.395820: step: 832/526, loss: 0.0009092808468267322
2023-01-23 03:01:47.530184: step: 836/526, loss: 0.0017095566727221012
2023-01-23 03:01:48.672126: step: 840/526, loss: 0.002094268798828125
2023-01-23 03:01:49.824000: step: 844/526, loss: 0.014912033453583717
2023-01-23 03:01:50.937553: step: 848/526, loss: 0.0023727419320493937
2023-01-23 03:01:52.070286: step: 852/526, loss: 0.0012662888038903475
2023-01-23 03:01:53.206320: step: 856/526, loss: 0.0008008956792764366
2023-01-23 03:01:54.345141: step: 860/526, loss: 0.027820492163300514
2023-01-23 03:01:55.459273: step: 864/526, loss: 0.00093164446298033
2023-01-23 03:01:56.622203: step: 868/526, loss: 0.006908941548317671
2023-01-23 03:01:57.737836: step: 872/526, loss: 0.0052032470703125
2023-01-23 03:01:58.870888: step: 876/526, loss: 0.002834892366081476
2023-01-23 03:02:00.011672: step: 880/526, loss: 8.78334030858241e-05
2023-01-23 03:02:01.178260: step: 884/526, loss: 0.004516029264777899
2023-01-23 03:02:02.297816: step: 888/526, loss: 3.0231476557673886e-05
2023-01-23 03:02:03.456906: step: 892/526, loss: 0.17814789712429047
2023-01-23 03:02:04.597486: step: 896/526, loss: 0.0008721351623535156
2023-01-23 03:02:05.732169: step: 900/526, loss: 0.003397655440494418
2023-01-23 03:02:06.866012: step: 904/526, loss: 0.0005017280345782638
2023-01-23 03:02:07.985026: step: 908/526, loss: 0.0015083312755450606
2023-01-23 03:02:09.101717: step: 912/526, loss: 0.003467035247012973
2023-01-23 03:02:10.244666: step: 916/526, loss: 0.00012092590623069555
2023-01-23 03:02:11.406395: step: 920/526, loss: 0.0008860588422976434
2023-01-23 03:02:12.534293: step: 924/526, loss: 0.008481503464281559
2023-01-23 03:02:13.649346: step: 928/526, loss: 0.05268440395593643
2023-01-23 03:02:14.804765: step: 932/526, loss: 0.0008344650268554688
2023-01-23 03:02:15.924151: step: 936/526, loss: 0.08935165405273438
2023-01-23 03:02:17.045074: step: 940/526, loss: 0.00023298263840842992
2023-01-23 03:02:18.165079: step: 944/526, loss: 0.010291003622114658
2023-01-23 03:02:19.281572: step: 948/526, loss: 0.009380913339555264
2023-01-23 03:02:20.398933: step: 952/526, loss: 0.0025942802894860506
2023-01-23 03:02:21.524621: step: 956/526, loss: 3.6245583032723516e-05
2023-01-23 03:02:22.638557: step: 960/526, loss: 0.010713004507124424
2023-01-23 03:02:23.796765: step: 964/526, loss: 0.01556782703846693
2023-01-23 03:02:24.940979: step: 968/526, loss: 0.00559577951207757
2023-01-23 03:02:26.079482: step: 972/526, loss: 0.0298798568546772
2023-01-23 03:02:27.216190: step: 976/526, loss: 0.010061835870146751
2023-01-23 03:02:28.316355: step: 980/526, loss: 0.00012836456880904734
2023-01-23 03:02:29.440545: step: 984/526, loss: 0.061211489140987396
2023-01-23 03:02:30.587300: step: 988/526, loss: 0.00014433861360885203
2023-01-23 03:02:31.716367: step: 992/526, loss: 0.023717977106571198
2023-01-23 03:02:32.834219: step: 996/526, loss: 0.0044172764755785465
2023-01-23 03:02:33.956319: step: 1000/526, loss: 0.0002582550223451108
2023-01-23 03:02:35.062043: step: 1004/526, loss: 0.05900716781616211
2023-01-23 03:02:36.241555: step: 1008/526, loss: 0.0012770653702318668
2023-01-23 03:02:37.375587: step: 1012/526, loss: 0.00642442749813199
2023-01-23 03:02:38.513318: step: 1016/526, loss: 0.007118606474250555
2023-01-23 03:02:39.660668: step: 1020/526, loss: 0.0038975717034190893
2023-01-23 03:02:40.795335: step: 1024/526, loss: 0.01047973707318306
2023-01-23 03:02:41.945046: step: 1028/526, loss: -8.39233416627394e-06
2023-01-23 03:02:43.098744: step: 1032/526, loss: 0.026009369641542435
2023-01-23 03:02:44.228686: step: 1036/526, loss: 0.00013732911611441523
2023-01-23 03:02:45.380590: step: 1040/526, loss: 0.03740882873535156
2023-01-23 03:02:46.524197: step: 1044/526, loss: 0.026148606091737747
2023-01-23 03:02:47.670818: step: 1048/526, loss: 0.028035450726747513
2023-01-23 03:02:48.775599: step: 1052/526, loss: 0.0016407014336436987
2023-01-23 03:02:49.921888: step: 1056/526, loss: 0.0015090943779796362
2023-01-23 03:02:51.070129: step: 1060/526, loss: 0.007592296227812767
2023-01-23 03:02:52.180111: step: 1064/526, loss: 0.028738783672451973
2023-01-23 03:02:53.297774: step: 1068/526, loss: 0.00063323974609375
2023-01-23 03:02:54.428029: step: 1072/526, loss: 0.1336756944656372
2023-01-23 03:02:55.558611: step: 1076/526, loss: 0.006005287170410156
2023-01-23 03:02:56.712883: step: 1080/526, loss: 0.0259659793227911
2023-01-23 03:02:57.819774: step: 1084/526, loss: 0.038306236267089844
2023-01-23 03:02:58.946951: step: 1088/526, loss: 0.00036706926766783
2023-01-23 03:03:00.100647: step: 1092/526, loss: 0.0016206741565838456
2023-01-23 03:03:01.240644: step: 1096/526, loss: 0.021438980475068092
2023-01-23 03:03:02.394259: step: 1100/526, loss: 8.702278137207031e-05
2023-01-23 03:03:03.560516: step: 1104/526, loss: 0.012619209475815296
2023-01-23 03:03:04.689477: step: 1108/526, loss: 0.007122039794921875
2023-01-23 03:03:05.821451: step: 1112/526, loss: 0.001700592110864818
2023-01-23 03:03:06.965211: step: 1116/526, loss: 0.0017173767555505037
2023-01-23 03:03:08.114541: step: 1120/526, loss: 0.02399158664047718
2023-01-23 03:03:09.224589: step: 1124/526, loss: 0.009321880526840687
2023-01-23 03:03:10.358387: step: 1128/526, loss: 0.0030158995650708675
2023-01-23 03:03:11.522900: step: 1132/526, loss: 0.009538650512695312
2023-01-23 03:03:12.659648: step: 1136/526, loss: 0.003050136612728238
2023-01-23 03:03:13.815913: step: 1140/526, loss: 0.02655353583395481
2023-01-23 03:03:14.953382: step: 1144/526, loss: 0.007510185241699219
2023-01-23 03:03:16.093008: step: 1148/526, loss: 0.00955886859446764
2023-01-23 03:03:17.250225: step: 1152/526, loss: 0.0025625228881835938
2023-01-23 03:03:18.405499: step: 1156/526, loss: 0.008837985806167126
2023-01-23 03:03:19.575421: step: 1160/526, loss: 0.023253632709383965
2023-01-23 03:03:20.702568: step: 1164/526, loss: 4.77790817967616e-05
2023-01-23 03:03:21.864596: step: 1168/526, loss: 0.0711750015616417
2023-01-23 03:03:23.027366: step: 1172/526, loss: 0.0004561901150736958
2023-01-23 03:03:24.139544: step: 1176/526, loss: 0.007734775543212891
2023-01-23 03:03:25.265040: step: 1180/526, loss: 0.010203743353486061
2023-01-23 03:03:26.399132: step: 1184/526, loss: 0.007632446475327015
2023-01-23 03:03:27.543058: step: 1188/526, loss: 0.0016374588012695312
2023-01-23 03:03:28.674520: step: 1192/526, loss: 0.00011482239642646164
2023-01-23 03:03:29.785910: step: 1196/526, loss: 0.0007000923505984247
2023-01-23 03:03:30.947400: step: 1200/526, loss: 0.030180789530277252
2023-01-23 03:03:32.101592: step: 1204/526, loss: 0.004850482568144798
2023-01-23 03:03:33.247021: step: 1208/526, loss: 0.0007051468128338456
2023-01-23 03:03:34.360873: step: 1212/526, loss: 0.0001503944513387978
2023-01-23 03:03:35.505007: step: 1216/526, loss: 7.333754911087453e-05
2023-01-23 03:03:36.626855: step: 1220/526, loss: 8.983612497104332e-05
2023-01-23 03:03:37.779243: step: 1224/526, loss: 0.017517566680908203
2023-01-23 03:03:38.918762: step: 1228/526, loss: 0.0009068489307537675
2023-01-23 03:03:40.067835: step: 1232/526, loss: 0.0009227752452716231
2023-01-23 03:03:41.184993: step: 1236/526, loss: 0.018269730731844902
2023-01-23 03:03:42.326835: step: 1240/526, loss: 0.10956688970327377
2023-01-23 03:03:43.467455: step: 1244/526, loss: 0.012059974484145641
2023-01-23 03:03:44.600935: step: 1248/526, loss: 0.002231693360954523
2023-01-23 03:03:45.719599: step: 1252/526, loss: 0.006430435460060835
2023-01-23 03:03:46.845762: step: 1256/526, loss: 0.029808808118104935
2023-01-23 03:03:47.976604: step: 1260/526, loss: 0.09743861854076385
2023-01-23 03:03:49.124467: step: 1264/526, loss: 0.0007110595470294356
2023-01-23 03:03:50.276383: step: 1268/526, loss: 0.00442085275426507
2023-01-23 03:03:51.393336: step: 1272/526, loss: 5.769729978055693e-05
2023-01-23 03:03:52.537453: step: 1276/526, loss: 0.026811979711055756
2023-01-23 03:03:53.669152: step: 1280/526, loss: 0.009513664990663528
2023-01-23 03:03:54.842407: step: 1284/526, loss: 0.0004098892386537045
2023-01-23 03:03:55.970243: step: 1288/526, loss: 3.056526475120336e-05
2023-01-23 03:03:57.133937: step: 1292/526, loss: 0.0001312017411692068
2023-01-23 03:03:58.245053: step: 1296/526, loss: 0.0023645402397960424
2023-01-23 03:03:59.379093: step: 1300/526, loss: 0.0050830841064453125
2023-01-23 03:04:00.503469: step: 1304/526, loss: 0.011212158016860485
2023-01-23 03:04:01.638865: step: 1308/526, loss: 0.006687736138701439
2023-01-23 03:04:02.765662: step: 1312/526, loss: 0.022497082129120827
2023-01-23 03:04:03.899464: step: 1316/526, loss: 0.0004042625369038433
2023-01-23 03:04:05.027120: step: 1320/526, loss: 0.0005655288696289062
2023-01-23 03:04:06.179558: step: 1324/526, loss: 0.0006029129144735634
2023-01-23 03:04:07.304573: step: 1328/526, loss: 0.0004343033069744706
2023-01-23 03:04:08.419856: step: 1332/526, loss: 0.0008636474958620965
2023-01-23 03:04:09.556819: step: 1336/526, loss: 0.0014085769653320312
2023-01-23 03:04:10.706957: step: 1340/526, loss: 0.007404327392578125
2023-01-23 03:04:11.840451: step: 1344/526, loss: 1.2302399227337446e-05
2023-01-23 03:04:12.977418: step: 1348/526, loss: 0.0005500793340615928
2023-01-23 03:04:14.112870: step: 1352/526, loss: 0.013394355773925781
2023-01-23 03:04:15.238347: step: 1356/526, loss: 0.0038290023803710938
2023-01-23 03:04:16.377443: step: 1360/526, loss: 0.032061006873846054
2023-01-23 03:04:17.510234: step: 1364/526, loss: 0.0014435768825933337
2023-01-23 03:04:18.667431: step: 1368/526, loss: 0.0025581358931958675
2023-01-23 03:04:19.788035: step: 1372/526, loss: 0.0125579833984375
2023-01-23 03:04:20.928389: step: 1376/526, loss: 0.015253543853759766
2023-01-23 03:04:22.072620: step: 1380/526, loss: 0.00168437953107059
2023-01-23 03:04:23.207129: step: 1384/526, loss: 0.0017072678310796618
2023-01-23 03:04:24.376531: step: 1388/526, loss: 6.351470801746473e-05
2023-01-23 03:04:25.496504: step: 1392/526, loss: 0.0006200790521688759
2023-01-23 03:04:26.633552: step: 1396/526, loss: 0.011794853955507278
2023-01-23 03:04:27.791758: step: 1400/526, loss: 8.430481830146164e-05
2023-01-23 03:04:28.923343: step: 1404/526, loss: 0.03389101102948189
2023-01-23 03:04:30.045423: step: 1408/526, loss: 3.814697265625e-06
2023-01-23 03:04:31.175867: step: 1412/526, loss: 0.0016368867363780737
2023-01-23 03:04:32.292593: step: 1416/526, loss: 0.007273769471794367
2023-01-23 03:04:33.415725: step: 1420/526, loss: 0.002724885940551758
2023-01-23 03:04:34.578337: step: 1424/526, loss: 7.877350435592234e-05
2023-01-23 03:04:35.743917: step: 1428/526, loss: 0.000632858311291784
2023-01-23 03:04:36.861742: step: 1432/526, loss: 0.018408775329589844
2023-01-23 03:04:37.979153: step: 1436/526, loss: 0.050493624061346054
2023-01-23 03:04:39.122075: step: 1440/526, loss: 0.021533681079745293
2023-01-23 03:04:40.271612: step: 1444/526, loss: 0.05006542056798935
2023-01-23 03:04:41.439172: step: 1448/526, loss: 0.00021409988403320312
2023-01-23 03:04:42.601558: step: 1452/526, loss: 0.05549333244562149
2023-01-23 03:04:43.756799: step: 1456/526, loss: 0.43433818221092224
2023-01-23 03:04:44.901000: step: 1460/526, loss: 8.56399565236643e-05
2023-01-23 03:04:46.031497: step: 1464/526, loss: 0.007652473170310259
2023-01-23 03:04:47.189107: step: 1468/526, loss: 0.039629556238651276
2023-01-23 03:04:48.328802: step: 1472/526, loss: 0.000604820204898715
2023-01-23 03:04:49.455390: step: 1476/526, loss: 0.006085109896957874
2023-01-23 03:04:50.575332: step: 1480/526, loss: 0.0056047444231808186
2023-01-23 03:04:51.695269: step: 1484/526, loss: 0.057358741760253906
2023-01-23 03:04:52.835595: step: 1488/526, loss: 0.027588654309511185
2023-01-23 03:04:53.967623: step: 1492/526, loss: 0.40248459577560425
2023-01-23 03:04:55.093517: step: 1496/526, loss: 0.009130382910370827
2023-01-23 03:04:56.228034: step: 1500/526, loss: 0.004675865173339844
2023-01-23 03:04:57.370193: step: 1504/526, loss: 0.00014390944852493703
2023-01-23 03:04:58.505693: step: 1508/526, loss: 0.00026857852935791016
2023-01-23 03:04:59.629723: step: 1512/526, loss: 0.007316971197724342
2023-01-23 03:05:00.751277: step: 1516/526, loss: 0.0026476620696485043
2023-01-23 03:05:01.890575: step: 1520/526, loss: 0.019067764282226562
2023-01-23 03:05:03.062472: step: 1524/526, loss: 0.00047588348388671875
2023-01-23 03:05:04.217607: step: 1528/526, loss: 0.0011170387733727694
2023-01-23 03:05:05.383707: step: 1532/526, loss: 0.004993247799575329
2023-01-23 03:05:06.519016: step: 1536/526, loss: 0.00129871373064816
2023-01-23 03:05:07.633527: step: 1540/526, loss: 0.03675823286175728
2023-01-23 03:05:08.761362: step: 1544/526, loss: 1.2269428968429565
2023-01-23 03:05:09.917508: step: 1548/526, loss: 0.009882926940917969
2023-01-23 03:05:11.043530: step: 1552/526, loss: 0.0015347481239587069
2023-01-23 03:05:12.170288: step: 1556/526, loss: 0.007928013801574707
2023-01-23 03:05:13.314663: step: 1560/526, loss: 0.04843468591570854
2023-01-23 03:05:14.460802: step: 1564/526, loss: 0.018177462741732597
2023-01-23 03:05:15.619921: step: 1568/526, loss: 0.00067729945294559
2023-01-23 03:05:16.750161: step: 1572/526, loss: 0.0002335071621928364
2023-01-23 03:05:17.913281: step: 1576/526, loss: 0.00524482736364007
2023-01-23 03:05:19.055558: step: 1580/526, loss: 0.00015735626220703125
2023-01-23 03:05:20.206497: step: 1584/526, loss: 0.0009131431579589844
2023-01-23 03:05:21.334356: step: 1588/526, loss: 0.0005405425908975303
2023-01-23 03:05:22.436267: step: 1592/526, loss: 0.00019330979557707906
2023-01-23 03:05:23.604936: step: 1596/526, loss: 0.03341560438275337
2023-01-23 03:05:24.749057: step: 1600/526, loss: 0.0042653209529817104
2023-01-23 03:05:25.887055: step: 1604/526, loss: 0.0010721206199377775
2023-01-23 03:05:27.007507: step: 1608/526, loss: 0.054396819323301315
2023-01-23 03:05:28.153221: step: 1612/526, loss: 0.004126167390495539
2023-01-23 03:05:29.305980: step: 1616/526, loss: 0.002502918243408203
2023-01-23 03:05:30.437230: step: 1620/526, loss: 1.6307831174344756e-05
2023-01-23 03:05:31.562346: step: 1624/526, loss: 0.0012418747646734118
2023-01-23 03:05:32.686942: step: 1628/526, loss: 0.0021982192993164062
2023-01-23 03:05:33.791167: step: 1632/526, loss: 0.002097225282341242
2023-01-23 03:05:34.912559: step: 1636/526, loss: 0.0384831428527832
2023-01-23 03:05:36.066011: step: 1640/526, loss: 0.008099555969238281
2023-01-23 03:05:37.235120: step: 1644/526, loss: 0.007973861880600452
2023-01-23 03:05:38.360652: step: 1648/526, loss: 0.00038051605224609375
2023-01-23 03:05:39.498215: step: 1652/526, loss: 0.009347342886030674
2023-01-23 03:05:40.637302: step: 1656/526, loss: 0.0318608283996582
2023-01-23 03:05:41.765769: step: 1660/526, loss: 0.07543551921844482
2023-01-23 03:05:42.910346: step: 1664/526, loss: 0.001445007394067943
2023-01-23 03:05:44.045328: step: 1668/526, loss: 0.003109932178631425
2023-01-23 03:05:45.157526: step: 1672/526, loss: 0.02376575395464897
2023-01-23 03:05:46.290386: step: 1676/526, loss: 0.0015651227440685034
2023-01-23 03:05:47.405829: step: 1680/526, loss: 0.010297202505171299
2023-01-23 03:05:48.507686: step: 1684/526, loss: 0.00041303635225631297
2023-01-23 03:05:49.644262: step: 1688/526, loss: 0.002592372940853238
2023-01-23 03:05:50.751468: step: 1692/526, loss: 0.0707603469491005
2023-01-23 03:05:51.870260: step: 1696/526, loss: 0.009849262423813343
2023-01-23 03:05:53.008091: step: 1700/526, loss: 0.0008469581953249872
2023-01-23 03:05:54.153226: step: 1704/526, loss: 0.0008864402770996094
2023-01-23 03:05:55.292927: step: 1708/526, loss: 0.001918744994327426
2023-01-23 03:05:56.417432: step: 1712/526, loss: 0.026782894507050514
2023-01-23 03:05:57.570663: step: 1716/526, loss: 2.059936559817288e-05
2023-01-23 03:05:58.703670: step: 1720/526, loss: 0.022302914410829544
2023-01-23 03:05:59.856598: step: 1724/526, loss: 0.00028324127197265625
2023-01-23 03:06:00.989531: step: 1728/526, loss: 0.0019309998024255037
2023-01-23 03:06:02.131233: step: 1732/526, loss: 4.57763690064894e-06
2023-01-23 03:06:03.279716: step: 1736/526, loss: 0.004938888363540173
2023-01-23 03:06:04.422412: step: 1740/526, loss: 0.012362862005829811
2023-01-23 03:06:05.545629: step: 1744/526, loss: 0.00020093917555641383
2023-01-23 03:06:06.696557: step: 1748/526, loss: 0.0027158737648278475
2023-01-23 03:06:07.852264: step: 1752/526, loss: 0.01735553704202175
2023-01-23 03:06:08.976541: step: 1756/526, loss: 0.006782913580536842
2023-01-23 03:06:10.100855: step: 1760/526, loss: 0.001158905099146068
2023-01-23 03:06:11.235192: step: 1764/526, loss: 0.014737891964614391
2023-01-23 03:06:12.356730: step: 1768/526, loss: 0.001072788261808455
2023-01-23 03:06:13.502935: step: 1772/526, loss: 0.031169412657618523
2023-01-23 03:06:14.620076: step: 1776/526, loss: 0.03193054348230362
2023-01-23 03:06:15.769694: step: 1780/526, loss: 0.002986431121826172
2023-01-23 03:06:16.879825: step: 1784/526, loss: 0.00018558502779342234
2023-01-23 03:06:18.047799: step: 1788/526, loss: 0.0008165836334228516
2023-01-23 03:06:19.203256: step: 1792/526, loss: 0.0003337860107421875
2023-01-23 03:06:20.348467: step: 1796/526, loss: 0.0016701698768883944
2023-01-23 03:06:21.476114: step: 1800/526, loss: 0.42012128233909607
2023-01-23 03:06:22.580864: step: 1804/526, loss: 0.0033001780975610018
2023-01-23 03:06:23.710684: step: 1808/526, loss: 0.003208064939826727
2023-01-23 03:06:24.856093: step: 1812/526, loss: 0.0028989792335778475
2023-01-23 03:06:25.994391: step: 1816/526, loss: 0.03765994310379028
2023-01-23 03:06:27.156071: step: 1820/526, loss: 0.0039904117584228516
2023-01-23 03:06:28.294405: step: 1824/526, loss: 0.00241680140607059
2023-01-23 03:06:29.410359: step: 1828/526, loss: 0.0024551867973059416
2023-01-23 03:06:30.569263: step: 1832/526, loss: 0.0008853912586346269
2023-01-23 03:06:31.682413: step: 1836/526, loss: 0.010827924124896526
2023-01-23 03:06:32.796138: step: 1840/526, loss: 0.16075249016284943
2023-01-23 03:06:33.934708: step: 1844/526, loss: 0.09786505252122879
2023-01-23 03:06:35.044939: step: 1848/526, loss: 0.0006225586403161287
2023-01-23 03:06:36.186602: step: 1852/526, loss: 0.010860443115234375
2023-01-23 03:06:37.310715: step: 1856/526, loss: 0.0007551193702965975
2023-01-23 03:06:38.471235: step: 1860/526, loss: 0.02900247648358345
2023-01-23 03:06:39.624825: step: 1864/526, loss: 0.005084800999611616
2023-01-23 03:06:40.772268: step: 1868/526, loss: 0.0016214370261877775
2023-01-23 03:06:41.938022: step: 1872/526, loss: 0.05117174983024597
2023-01-23 03:06:43.187085: step: 1876/526, loss: 0.006907367613166571
2023-01-23 03:06:44.345597: step: 1880/526, loss: 0.0006016730912961066
2023-01-23 03:06:45.478369: step: 1884/526, loss: 0.0024353028275072575
2023-01-23 03:06:46.586910: step: 1888/526, loss: 0.024439144879579544
2023-01-23 03:06:47.701549: step: 1892/526, loss: 0.018228817731142044
2023-01-23 03:06:48.853197: step: 1896/526, loss: 0.04074735566973686
2023-01-23 03:06:50.004526: step: 1900/526, loss: 0.01277256105095148
2023-01-23 03:06:51.127656: step: 1904/526, loss: 0.05594091862440109
2023-01-23 03:06:52.243152: step: 1908/526, loss: 0.02311687543988228
2023-01-23 03:06:53.354206: step: 1912/526, loss: 0.06925544887781143
2023-01-23 03:06:54.488012: step: 1916/526, loss: 0.0009435653919354081
2023-01-23 03:06:55.613861: step: 1920/526, loss: 0.00385456089861691
2023-01-23 03:06:56.756904: step: 1924/526, loss: 0.031569674611091614
2023-01-23 03:06:57.875561: step: 1928/526, loss: 0.005666256416589022
2023-01-23 03:06:59.002238: step: 1932/526, loss: 0.0007661819690838456
2023-01-23 03:07:00.137275: step: 1936/526, loss: 0.02087726630270481
2023-01-23 03:07:01.294677: step: 1940/526, loss: 0.022549821063876152
2023-01-23 03:07:02.449311: step: 1944/526, loss: 0.0001398563472321257
2023-01-23 03:07:03.586638: step: 1948/526, loss: 0.037169814109802246
2023-01-23 03:07:04.717843: step: 1952/526, loss: 0.0021746635902673006
2023-01-23 03:07:05.861798: step: 1956/526, loss: 0.00014352798461914062
2023-01-23 03:07:06.998383: step: 1960/526, loss: 0.003190517658367753
2023-01-23 03:07:08.173189: step: 1964/526, loss: 0.0036753653548657894
2023-01-23 03:07:09.315670: step: 1968/526, loss: 2.555847095209174e-05
2023-01-23 03:07:10.422335: step: 1972/526, loss: 0.012353808619081974
2023-01-23 03:07:11.533765: step: 1976/526, loss: 0.0004582405090332031
2023-01-23 03:07:12.656738: step: 1980/526, loss: 2.212524486822076e-05
2023-01-23 03:07:13.793264: step: 1984/526, loss: 0.0007988453144207597
2023-01-23 03:07:14.937483: step: 1988/526, loss: 0.017854977399110794
2023-01-23 03:07:16.099921: step: 1992/526, loss: 0.0005401134840212762
2023-01-23 03:07:17.223581: step: 1996/526, loss: 0.0009823114378377795
2023-01-23 03:07:18.334535: step: 2000/526, loss: 0.0006556510925292969
2023-01-23 03:07:19.472481: step: 2004/526, loss: 0.05289506912231445
2023-01-23 03:07:20.619698: step: 2008/526, loss: 0.05361061170697212
2023-01-23 03:07:21.741080: step: 2012/526, loss: 8.687972876941785e-05
2023-01-23 03:07:22.843956: step: 2016/526, loss: 0.00011148452904308215
2023-01-23 03:07:24.025447: step: 2020/526, loss: 0.047094155102968216
2023-01-23 03:07:25.147436: step: 2024/526, loss: 0.00011892318434547633
2023-01-23 03:07:26.284624: step: 2028/526, loss: 0.022041702643036842
2023-01-23 03:07:27.455489: step: 2032/526, loss: 0.0018604277865961194
2023-01-23 03:07:28.611232: step: 2036/526, loss: 0.013186503201723099
2023-01-23 03:07:29.761119: step: 2040/526, loss: 0.0009047508356161416
2023-01-23 03:07:30.894871: step: 2044/526, loss: 0.005512333009392023
2023-01-23 03:07:32.032060: step: 2048/526, loss: 0.002853298094123602
2023-01-23 03:07:33.183798: step: 2052/526, loss: 0.014701366424560547
2023-01-23 03:07:34.324568: step: 2056/526, loss: 0.04941254109144211
2023-01-23 03:07:35.437233: step: 2060/526, loss: 0.0003387451288290322
2023-01-23 03:07:36.565322: step: 2064/526, loss: 0.00037937163142487407
2023-01-23 03:07:37.711647: step: 2068/526, loss: 0.0008299828041344881
2023-01-23 03:07:38.879651: step: 2072/526, loss: 0.020668793469667435
2023-01-23 03:07:40.034371: step: 2076/526, loss: 0.008508491329848766
2023-01-23 03:07:41.170668: step: 2080/526, loss: 0.0931495651602745
2023-01-23 03:07:42.306978: step: 2084/526, loss: 0.011777115054428577
2023-01-23 03:07:43.476389: step: 2088/526, loss: 0.012471389025449753
2023-01-23 03:07:44.616239: step: 2092/526, loss: 0.0012497901916503906
2023-01-23 03:07:45.745436: step: 2096/526, loss: 0.00043773651123046875
2023-01-23 03:07:46.881064: step: 2100/526, loss: 0.001194095704704523
2023-01-23 03:07:48.031521: step: 2104/526, loss: 9.72747802734375e-05
==================================================
Loss: 0.023
--------------------
Dev: {'event': {'p': 0.5604914933837429, 'r': 0.7896138482023968, 'f1': 0.6556108347153123}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 20}
Test: {'event': {'p': 0.5925349922239502, 'r': 0.7954070981210856, 'f1': 0.679144385026738}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 20}
Chinese: {'event': {'p': 0.49019607843137253, 'r': 0.9259259259259259, 'f1': 0.6410256410256411}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 20}
Korean: {'event': {'p': 0.5873015873015873, 'r': 0.5873015873015873, 'f1': 0.5873015873015873}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 20}
Russian: {'event': {'p': 0.4583333333333333, 'r': 0.6111111111111112, 'f1': 0.5238095238095238}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 20}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6389811738648948, 'r': 0.7683089214380826, 'f1': 0.6977025392986699}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Eng Test for Chinese: {'event': {'p': 0.6328626444159179, 'r': 0.7719206680584552, 'f1': 0.6955090524335763}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Sample Chinese: {'event': {'p': 0.6282051282051282, 'r': 0.9074074074074074, 'f1': 0.7424242424242423}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6257995735607675, 'r': 0.7816245006657789, 'f1': 0.6950858496151568}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Eng Test for Korean: {'event': {'p': 0.623113410952997, 'r': 0.7541753653444676, 'f1': 0.6824085005903188}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Sample Korean: {'event': {'p': 0.7446808510638298, 'r': 0.5555555555555556, 'f1': 0.6363636363636364}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5800575263662512, 'r': 0.8055925432756325, 'f1': 0.6744704570791527}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
Eng Test for Russian: {'event': {'p': 0.5962534874451972, 'r': 0.7807933194154488, 'f1': 0.6761581920903954}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
Sample Russian: {'event': {'p': 0.48936170212765956, 'r': 0.6388888888888888, 'f1': 0.5542168674698795}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
******************************
Epoch: 21
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 03:08:31.713288: step: 4/526, loss: 0.0009955406421795487
2023-01-23 03:08:32.842899: step: 8/526, loss: 0.032643888145685196
2023-01-23 03:08:33.963062: step: 12/526, loss: 6.0749058320652694e-05
2023-01-23 03:08:35.083831: step: 16/526, loss: 0.06737546622753143
2023-01-23 03:08:36.235356: step: 20/526, loss: 0.0030429840553551912
2023-01-23 03:08:37.376690: step: 24/526, loss: 0.03221569210290909
2023-01-23 03:08:38.491309: step: 28/526, loss: 0.006129169370979071
2023-01-23 03:08:39.645532: step: 32/526, loss: 0.0014341354835778475
2023-01-23 03:08:40.740515: step: 36/526, loss: 0.00033102036104537547
2023-01-23 03:08:41.868943: step: 40/526, loss: 0.007520007900893688
2023-01-23 03:08:43.012914: step: 44/526, loss: 0.004151535220444202
2023-01-23 03:08:44.141693: step: 48/526, loss: 0.027634240686893463
2023-01-23 03:08:45.285381: step: 52/526, loss: 0.014844131655991077
2023-01-23 03:08:46.421916: step: 56/526, loss: 0.012241172604262829
2023-01-23 03:08:47.564040: step: 60/526, loss: 0.0017638206481933594
2023-01-23 03:08:48.712498: step: 64/526, loss: 0.11033602058887482
2023-01-23 03:08:49.854136: step: 68/526, loss: 0.014161776751279831
2023-01-23 03:08:50.993615: step: 72/526, loss: 0.00036020277184434235
2023-01-23 03:08:52.129316: step: 76/526, loss: 0.002583503955975175
2023-01-23 03:08:53.281832: step: 80/526, loss: 0.00039119721623137593
2023-01-23 03:08:54.404794: step: 84/526, loss: 0.008385754190385342
2023-01-23 03:08:55.574782: step: 88/526, loss: 0.0198225025087595
2023-01-23 03:08:56.719402: step: 92/526, loss: 6.332397606456652e-05
2023-01-23 03:08:57.854458: step: 96/526, loss: 0.00029497145442292094
2023-01-23 03:08:58.994169: step: 100/526, loss: 0.009635734371840954
2023-01-23 03:09:00.125407: step: 104/526, loss: 0.0007391691324301064
2023-01-23 03:09:01.254886: step: 108/526, loss: 0.0006021499866619706
2023-01-23 03:09:02.400109: step: 112/526, loss: 0.00021438598923850805
2023-01-23 03:09:03.529483: step: 116/526, loss: 0.001714563462883234
2023-01-23 03:09:04.659613: step: 120/526, loss: 0.0015277386410161853
2023-01-23 03:09:05.781170: step: 124/526, loss: 0.009488677605986595
2023-01-23 03:09:06.913654: step: 128/526, loss: 0.00044264792813919485
2023-01-23 03:09:08.035422: step: 132/526, loss: 0.14051762223243713
2023-01-23 03:09:09.167512: step: 136/526, loss: 0.002780866576358676
2023-01-23 03:09:10.274873: step: 140/526, loss: 0.0004968166467733681
2023-01-23 03:09:11.443171: step: 144/526, loss: 0.048073720186948776
2023-01-23 03:09:12.599437: step: 148/526, loss: 0.005917549133300781
2023-01-23 03:09:13.711087: step: 152/526, loss: 0.004196167457848787
2023-01-23 03:09:14.831891: step: 156/526, loss: 0.011194133199751377
2023-01-23 03:09:15.983776: step: 160/526, loss: 0.007124233525246382
2023-01-23 03:09:17.119298: step: 164/526, loss: 0.0038658143021166325
2023-01-23 03:09:18.254185: step: 168/526, loss: 0.0017652511596679688
2023-01-23 03:09:19.390535: step: 172/526, loss: 0.0005502700805664062
2023-01-23 03:09:20.488388: step: 176/526, loss: 0.002340364269912243
2023-01-23 03:09:21.610136: step: 180/526, loss: 0.017264556139707565
2023-01-23 03:09:22.763114: step: 184/526, loss: 0.021281886845827103
2023-01-23 03:09:23.908888: step: 188/526, loss: 0.021313440054655075
2023-01-23 03:09:25.051901: step: 192/526, loss: 1.506805438111769e-05
2023-01-23 03:09:26.197262: step: 196/526, loss: 0.0015953064430505037
2023-01-23 03:09:27.344765: step: 200/526, loss: 0.019234657287597656
2023-01-23 03:09:28.455442: step: 204/526, loss: 0.00336456298828125
2023-01-23 03:09:29.615656: step: 208/526, loss: 0.020078469067811966
2023-01-23 03:09:30.750420: step: 212/526, loss: 0.028565121814608574
2023-01-23 03:09:31.885789: step: 216/526, loss: 0.0008527755853720009
2023-01-23 03:09:33.041307: step: 220/526, loss: 2.8753278456861153e-05
2023-01-23 03:09:34.192997: step: 224/526, loss: 0.006253433413803577
2023-01-23 03:09:35.302804: step: 228/526, loss: 7.905960228526965e-05
2023-01-23 03:09:36.433854: step: 232/526, loss: 0.04281196743249893
2023-01-23 03:09:37.553043: step: 236/526, loss: 0.00027484894962981343
2023-01-23 03:09:38.726070: step: 240/526, loss: 0.0028964995872229338
2023-01-23 03:09:39.867374: step: 244/526, loss: 0.019318198785185814
2023-01-23 03:09:40.999061: step: 248/526, loss: 5.044937279308215e-05
2023-01-23 03:09:42.134757: step: 252/526, loss: 0.006527137476950884
2023-01-23 03:09:43.343720: step: 256/526, loss: 0.006454754155129194
2023-01-23 03:09:44.460169: step: 260/526, loss: 0.03245840221643448
2023-01-23 03:09:45.617789: step: 264/526, loss: 0.006314659025520086
2023-01-23 03:09:46.727745: step: 268/526, loss: 0.01365203782916069
2023-01-23 03:09:47.866104: step: 272/526, loss: 0.003501224797219038
2023-01-23 03:09:48.979269: step: 276/526, loss: 0.0031845092307776213
2023-01-23 03:09:50.141424: step: 280/526, loss: 0.00025005341740325093
2023-01-23 03:09:51.252494: step: 284/526, loss: 0.0012862683506682515
2023-01-23 03:09:52.379546: step: 288/526, loss: 0.0013446807861328125
2023-01-23 03:09:53.528997: step: 292/526, loss: 0.04877147823572159
2023-01-23 03:09:54.674551: step: 296/526, loss: 0.012141609564423561
2023-01-23 03:09:55.817765: step: 300/526, loss: 0.006172561552375555
2023-01-23 03:09:56.939457: step: 304/526, loss: 0.03891048580408096
2023-01-23 03:09:58.037015: step: 308/526, loss: 0.0011526108719408512
2023-01-23 03:09:59.164973: step: 312/526, loss: 0.010182762518525124
2023-01-23 03:10:00.284972: step: 316/526, loss: 5.367398262023926e-05
2023-01-23 03:10:01.430415: step: 320/526, loss: 0.019713783636689186
2023-01-23 03:10:02.577692: step: 324/526, loss: 0.03429565578699112
2023-01-23 03:10:03.711606: step: 328/526, loss: 0.0009423256269656122
2023-01-23 03:10:04.845217: step: 332/526, loss: 9.117126319324598e-05
2023-01-23 03:10:05.981421: step: 336/526, loss: 2.5272369384765625e-05
2023-01-23 03:10:07.125477: step: 340/526, loss: 0.03172626718878746
2023-01-23 03:10:08.297035: step: 344/526, loss: 0.01759166829288006
2023-01-23 03:10:09.412669: step: 348/526, loss: 0.003347778460010886
2023-01-23 03:10:10.561838: step: 352/526, loss: 0.0017461776733398438
2023-01-23 03:10:11.697930: step: 356/526, loss: 0.03577089309692383
2023-01-23 03:10:12.842079: step: 360/526, loss: 0.016684724017977715
2023-01-23 03:10:13.985153: step: 364/526, loss: 0.015204716473817825
2023-01-23 03:10:15.116285: step: 368/526, loss: 0.000576877617277205
2023-01-23 03:10:16.238126: step: 372/526, loss: 7.643699791515246e-05
2023-01-23 03:10:17.359781: step: 376/526, loss: 0.18345527350902557
2023-01-23 03:10:18.495706: step: 380/526, loss: 0.0004954338073730469
2023-01-23 03:10:19.634104: step: 384/526, loss: 9.474754187976941e-05
2023-01-23 03:10:20.780288: step: 388/526, loss: 0.0012785911094397306
2023-01-23 03:10:21.913690: step: 392/526, loss: 0.00176830287091434
2023-01-23 03:10:23.049570: step: 396/526, loss: 0.04534664377570152
2023-01-23 03:10:24.179168: step: 400/526, loss: 0.000691795430611819
2023-01-23 03:10:25.299657: step: 404/526, loss: 0.007149696350097656
2023-01-23 03:10:26.431194: step: 408/526, loss: 0.00011005401756847277
2023-01-23 03:10:27.551577: step: 412/526, loss: 9.784698340808973e-05
2023-01-23 03:10:28.677422: step: 416/526, loss: 0.0015617371536791325
2023-01-23 03:10:29.806223: step: 420/526, loss: 0.002857112791389227
2023-01-23 03:10:30.941299: step: 424/526, loss: 0.00821542739868164
2023-01-23 03:10:32.079127: step: 428/526, loss: 0.018573950976133347
2023-01-23 03:10:33.248992: step: 432/526, loss: 0.0013235092628747225
2023-01-23 03:10:34.405898: step: 436/526, loss: 0.016424084082245827
2023-01-23 03:10:35.529852: step: 440/526, loss: 0.029625415802001953
2023-01-23 03:10:36.650707: step: 444/526, loss: 0.0004285812610760331
2023-01-23 03:10:37.790224: step: 448/526, loss: 0.005054282955825329
2023-01-23 03:10:38.933621: step: 452/526, loss: 5.7220458984375e-06
2023-01-23 03:10:40.047007: step: 456/526, loss: 0.017589950934052467
2023-01-23 03:10:41.174265: step: 460/526, loss: 0.0017057419754564762
2023-01-23 03:10:42.295145: step: 464/526, loss: 0.0012001991271972656
2023-01-23 03:10:43.469399: step: 468/526, loss: 0.010443019680678844
2023-01-23 03:10:44.608359: step: 472/526, loss: 0.00037508009700104594
2023-01-23 03:10:45.720503: step: 476/526, loss: 0.02084674872457981
2023-01-23 03:10:46.860123: step: 480/526, loss: 0.0100480318069458
2023-01-23 03:10:47.976692: step: 484/526, loss: 0.005688333418220282
2023-01-23 03:10:49.094471: step: 488/526, loss: 0.0008464812999591231
2023-01-23 03:10:50.213888: step: 492/526, loss: 0.0024870873894542456
2023-01-23 03:10:51.335140: step: 496/526, loss: 0.03071155585348606
2023-01-23 03:10:52.481043: step: 500/526, loss: 0.00010585784912109375
2023-01-23 03:10:53.624663: step: 504/526, loss: 0.03797359764575958
2023-01-23 03:10:54.774845: step: 508/526, loss: 0.00014562607975676656
2023-01-23 03:10:55.900090: step: 512/526, loss: 0.04983320087194443
2023-01-23 03:10:57.022364: step: 516/526, loss: 0.0011019706726074219
2023-01-23 03:10:58.122199: step: 520/526, loss: 1.0967256685034954e-06
2023-01-23 03:10:59.276449: step: 524/526, loss: 0.009551430121064186
2023-01-23 03:11:00.443169: step: 528/526, loss: 0.004874038510024548
2023-01-23 03:11:01.595718: step: 532/526, loss: 0.00013256072998046875
2023-01-23 03:11:02.726358: step: 536/526, loss: 0.008013343438506126
2023-01-23 03:11:03.867493: step: 540/526, loss: 0.0006774902576580644
2023-01-23 03:11:05.032246: step: 544/526, loss: 0.00036277773324400187
2023-01-23 03:11:06.176778: step: 548/526, loss: 0.014105415903031826
2023-01-23 03:11:07.343422: step: 552/526, loss: 0.001499176025390625
2023-01-23 03:11:08.479522: step: 556/526, loss: 0.01841278187930584
2023-01-23 03:11:09.624745: step: 560/526, loss: 0.012327957898378372
2023-01-23 03:11:10.765372: step: 564/526, loss: 0.0008825302356854081
2023-01-23 03:11:11.905110: step: 568/526, loss: 0.00016288759070448577
2023-01-23 03:11:13.088287: step: 572/526, loss: 0.0002874374622479081
2023-01-23 03:11:14.238616: step: 576/526, loss: 0.0012821197742596269
2023-01-23 03:11:15.345373: step: 580/526, loss: 0.00027785301790572703
2023-01-23 03:11:16.473940: step: 584/526, loss: 0.008230590261518955
2023-01-23 03:11:17.616687: step: 588/526, loss: 0.0018922805320471525
2023-01-23 03:11:18.764991: step: 592/526, loss: 0.0015671729343011975
2023-01-23 03:11:19.898068: step: 596/526, loss: 0.004811477847397327
2023-01-23 03:11:21.034031: step: 600/526, loss: 0.0003749847528524697
2023-01-23 03:11:22.186454: step: 604/526, loss: 0.017642594873905182
2023-01-23 03:11:23.297318: step: 608/526, loss: 0.0011973382206633687
2023-01-23 03:11:24.446121: step: 612/526, loss: 0.0010057450272142887
2023-01-23 03:11:25.589580: step: 616/526, loss: 0.019736479967832565
2023-01-23 03:11:26.714083: step: 620/526, loss: 0.00016841889009810984
2023-01-23 03:11:27.882220: step: 624/526, loss: 0.0011733531719073653
2023-01-23 03:11:29.022984: step: 628/526, loss: 0.01329965703189373
2023-01-23 03:11:30.157810: step: 632/526, loss: 0.020113373175263405
2023-01-23 03:11:31.261934: step: 636/526, loss: 0.0003427505725994706
2023-01-23 03:11:32.361649: step: 640/526, loss: 2.09808349609375e-05
2023-01-23 03:11:33.501178: step: 644/526, loss: 0.02185802534222603
2023-01-23 03:11:34.644132: step: 648/526, loss: 0.008469867520034313
2023-01-23 03:11:35.803819: step: 652/526, loss: 0.07594814151525497
2023-01-23 03:11:36.919223: step: 656/526, loss: 0.00014095305232331157
2023-01-23 03:11:38.062650: step: 660/526, loss: 0.02503986284136772
2023-01-23 03:11:39.175357: step: 664/526, loss: 0.0002735138114076108
2023-01-23 03:11:40.314759: step: 668/526, loss: 0.05170421674847603
2023-01-23 03:11:41.445769: step: 672/526, loss: 0.001561927841976285
2023-01-23 03:11:42.574916: step: 676/526, loss: 0.03464946523308754
2023-01-23 03:11:43.727714: step: 680/526, loss: 0.002483940217643976
2023-01-23 03:11:44.834539: step: 684/526, loss: 0.0005573272937908769
2023-01-23 03:11:45.972686: step: 688/526, loss: 0.011051654815673828
2023-01-23 03:11:47.155214: step: 692/526, loss: 0.024146461859345436
2023-01-23 03:11:48.291214: step: 696/526, loss: 6.67572021484375e-06
2023-01-23 03:11:49.454453: step: 700/526, loss: 0.0608489029109478
2023-01-23 03:11:50.597047: step: 704/526, loss: 0.0009290695306845009
2023-01-23 03:11:51.743491: step: 708/526, loss: 0.00016860962205100805
2023-01-23 03:11:52.867083: step: 712/526, loss: 2.765655517578125e-05
2023-01-23 03:11:53.983997: step: 716/526, loss: 0.008852767758071423
2023-01-23 03:11:55.098597: step: 720/526, loss: 0.0005374908214434981
2023-01-23 03:11:56.257601: step: 724/526, loss: 0.00016546249389648438
2023-01-23 03:11:57.379155: step: 728/526, loss: 0.003566169645637274
2023-01-23 03:11:58.508572: step: 732/526, loss: 0.049204062670469284
2023-01-23 03:11:59.673191: step: 736/526, loss: 0.007140922360122204
2023-01-23 03:12:00.788612: step: 740/526, loss: 0.00022611618624068797
2023-01-23 03:12:01.936351: step: 744/526, loss: 0.0006732940673828125
2023-01-23 03:12:03.111803: step: 748/526, loss: 4.138946678722277e-05
2023-01-23 03:12:04.249968: step: 752/526, loss: 0.005099296569824219
2023-01-23 03:12:05.418681: step: 756/526, loss: 0.006854534149169922
2023-01-23 03:12:06.546289: step: 760/526, loss: 2.0980833141948096e-06
2023-01-23 03:12:07.684900: step: 764/526, loss: 0.012611293233931065
2023-01-23 03:12:08.844087: step: 768/526, loss: 0.004787635989487171
2023-01-23 03:12:09.983845: step: 772/526, loss: 0.3584173321723938
2023-01-23 03:12:11.138248: step: 776/526, loss: 0.003460693173110485
2023-01-23 03:12:12.242643: step: 780/526, loss: 0.003250503446906805
2023-01-23 03:12:13.398953: step: 784/526, loss: 0.005113798193633556
2023-01-23 03:12:14.514814: step: 788/526, loss: 0.0018720626831054688
2023-01-23 03:12:15.649623: step: 792/526, loss: 0.0089095588773489
2023-01-23 03:12:16.776563: step: 796/526, loss: 0.05566377937793732
2023-01-23 03:12:17.966043: step: 800/526, loss: 4.38690176451928e-06
2023-01-23 03:12:19.113987: step: 804/526, loss: 0.02503671869635582
2023-01-23 03:12:20.229423: step: 808/526, loss: 8.301809430122375e-05
2023-01-23 03:12:21.375913: step: 812/526, loss: 0.03979034349322319
2023-01-23 03:12:22.497319: step: 816/526, loss: 0.00033016205998137593
2023-01-23 03:12:23.644897: step: 820/526, loss: 0.020508289337158203
2023-01-23 03:12:24.791048: step: 824/526, loss: 0.0008488655439577997
2023-01-23 03:12:25.916684: step: 828/526, loss: 0.0023378373589366674
2023-01-23 03:12:27.061719: step: 832/526, loss: 0.0005554199451580644
2023-01-23 03:12:28.195625: step: 836/526, loss: 0.04146156460046768
2023-01-23 03:12:29.341303: step: 840/526, loss: 0.008087158203125
2023-01-23 03:12:30.455216: step: 844/526, loss: 0.026282453909516335
2023-01-23 03:12:31.618233: step: 848/526, loss: 0.00015186071686912328
2023-01-23 03:12:32.767663: step: 852/526, loss: 0.012221241369843483
2023-01-23 03:12:33.901894: step: 856/526, loss: 0.016178417950868607
2023-01-23 03:12:35.079871: step: 860/526, loss: 0.18164634704589844
2023-01-23 03:12:36.193316: step: 864/526, loss: 0.03341054916381836
2023-01-23 03:12:37.321530: step: 868/526, loss: 0.01939220540225506
2023-01-23 03:12:38.463782: step: 872/526, loss: 0.018245983868837357
2023-01-23 03:12:39.588393: step: 876/526, loss: 0.014223290607333183
2023-01-23 03:12:40.758593: step: 880/526, loss: 0.010126161389052868
2023-01-23 03:12:41.893121: step: 884/526, loss: 0.0027590752579271793
2023-01-23 03:12:43.009846: step: 888/526, loss: 0.0005181313026696444
2023-01-23 03:12:44.171094: step: 892/526, loss: 0.0002513885556254536
2023-01-23 03:12:45.337385: step: 896/526, loss: 0.009302664548158646
2023-01-23 03:12:46.473061: step: 900/526, loss: 0.038389064371585846
2023-01-23 03:12:47.627664: step: 904/526, loss: 0.00014157296391204
2023-01-23 03:12:48.762480: step: 908/526, loss: 0.006889533717185259
2023-01-23 03:12:49.940171: step: 912/526, loss: 0.0006856918334960938
2023-01-23 03:12:51.061888: step: 916/526, loss: 2.346038854739163e-05
2023-01-23 03:12:52.205636: step: 920/526, loss: 0.06824145466089249
2023-01-23 03:12:53.324278: step: 924/526, loss: 0.00043606761028058827
2023-01-23 03:12:54.454586: step: 928/526, loss: 0.012229920364916325
2023-01-23 03:12:55.571114: step: 932/526, loss: 0.021875381469726562
2023-01-23 03:12:56.701125: step: 936/526, loss: 0.007502079010009766
2023-01-23 03:12:57.809926: step: 940/526, loss: -1.4019013178767636e-05
2023-01-23 03:12:58.965900: step: 944/526, loss: 0.0029477120842784643
2023-01-23 03:13:00.105119: step: 948/526, loss: 0.08689117431640625
2023-01-23 03:13:01.209812: step: 952/526, loss: 0.015105342492461205
2023-01-23 03:13:02.333738: step: 956/526, loss: 0.00018024444580078125
2023-01-23 03:13:03.440597: step: 960/526, loss: 0.07650360465049744
2023-01-23 03:13:04.565215: step: 964/526, loss: 0.0001720428408589214
2023-01-23 03:13:05.710035: step: 968/526, loss: 0.0004440307675395161
2023-01-23 03:13:06.845051: step: 972/526, loss: 0.02216949500143528
2023-01-23 03:13:07.984485: step: 976/526, loss: 0.004005050752311945
2023-01-23 03:13:09.114776: step: 980/526, loss: 0.0025488617829978466
2023-01-23 03:13:10.233295: step: 984/526, loss: 0.01591334491968155
2023-01-23 03:13:11.369781: step: 988/526, loss: 0.006067085079848766
2023-01-23 03:13:12.513230: step: 992/526, loss: 2.8991700673941523e-05
2023-01-23 03:13:13.638486: step: 996/526, loss: 0.00057392125017941
2023-01-23 03:13:14.769127: step: 1000/526, loss: 0.0010517120826989412
2023-01-23 03:13:15.916815: step: 1004/526, loss: 0.0011048555606976151
2023-01-23 03:13:17.040799: step: 1008/526, loss: 0.0008025169372558594
2023-01-23 03:13:18.181294: step: 1012/526, loss: 0.01602649874985218
2023-01-23 03:13:19.339411: step: 1016/526, loss: 0.010249900631606579
2023-01-23 03:13:20.450765: step: 1020/526, loss: 0.00043778421240858734
2023-01-23 03:13:21.602260: step: 1024/526, loss: 0.00016508101543877274
2023-01-23 03:13:22.749692: step: 1028/526, loss: 0.17733134329319
2023-01-23 03:13:23.895812: step: 1032/526, loss: 0.30967026948928833
2023-01-23 03:13:25.025460: step: 1036/526, loss: 0.01845226250588894
2023-01-23 03:13:26.174965: step: 1040/526, loss: 0.0006390571943484247
2023-01-23 03:13:27.322324: step: 1044/526, loss: 0.0012401581043377519
2023-01-23 03:13:28.483462: step: 1048/526, loss: 0.00530586251989007
2023-01-23 03:13:29.632040: step: 1052/526, loss: 0.00022907258244231343
2023-01-23 03:13:30.773905: step: 1056/526, loss: 7.658005051780492e-05
2023-01-23 03:13:31.915419: step: 1060/526, loss: 7.715225365245715e-05
2023-01-23 03:13:33.049792: step: 1064/526, loss: 0.00028133392333984375
2023-01-23 03:13:34.151375: step: 1068/526, loss: 0.0010894775623455644
2023-01-23 03:13:35.296867: step: 1072/526, loss: 0.4035331606864929
2023-01-23 03:13:36.440300: step: 1076/526, loss: 0.0030317308846861124
2023-01-23 03:13:37.549698: step: 1080/526, loss: 0.0018420219421386719
2023-01-23 03:13:38.706118: step: 1084/526, loss: 0.0005134582170285285
2023-01-23 03:13:39.844767: step: 1088/526, loss: 0.002246570773422718
2023-01-23 03:13:40.969038: step: 1092/526, loss: 0.0010133743053302169
2023-01-23 03:13:42.092406: step: 1096/526, loss: 0.004272079560905695
2023-01-23 03:13:43.248096: step: 1100/526, loss: 0.00017108916654251516
2023-01-23 03:13:44.390604: step: 1104/526, loss: 0.009885216131806374
2023-01-23 03:13:45.545509: step: 1108/526, loss: 0.050868988037109375
2023-01-23 03:13:46.667943: step: 1112/526, loss: 0.012102174572646618
2023-01-23 03:13:47.813439: step: 1116/526, loss: 0.00146827707067132
2023-01-23 03:13:48.928387: step: 1120/526, loss: 0.006963539402931929
2023-01-23 03:13:50.030391: step: 1124/526, loss: 0.00031266213045455515
2023-01-23 03:13:51.186542: step: 1128/526, loss: 0.00020513535127975047
2023-01-23 03:13:52.314219: step: 1132/526, loss: 0.0005605578771792352
2023-01-23 03:13:53.448904: step: 1136/526, loss: 0.010409070178866386
2023-01-23 03:13:54.573508: step: 1140/526, loss: 0.005105781834572554
2023-01-23 03:13:55.690734: step: 1144/526, loss: 0.00016026497178245336
2023-01-23 03:13:56.840376: step: 1148/526, loss: 1.7833708625403233e-05
2023-01-23 03:13:57.965146: step: 1152/526, loss: 0.0006553650018759072
2023-01-23 03:13:59.117359: step: 1156/526, loss: 0.013267803937196732
2023-01-23 03:14:00.245625: step: 1160/526, loss: 0.004382896237075329
2023-01-23 03:14:01.411620: step: 1164/526, loss: 0.08456211537122726
2023-01-23 03:14:02.514932: step: 1168/526, loss: 0.013112069107592106
2023-01-23 03:14:03.627565: step: 1172/526, loss: 0.019095564261078835
2023-01-23 03:14:04.746448: step: 1176/526, loss: 0.0008366585243493319
2023-01-23 03:14:05.863581: step: 1180/526, loss: 0.05835561826825142
2023-01-23 03:14:06.992264: step: 1184/526, loss: 0.017320729792118073
2023-01-23 03:14:08.131299: step: 1188/526, loss: 0.005169105716049671
2023-01-23 03:14:09.266412: step: 1192/526, loss: 0.0017440796364098787
2023-01-23 03:14:10.417673: step: 1196/526, loss: 0.2281607687473297
2023-01-23 03:14:11.552512: step: 1200/526, loss: 0.033351849764585495
2023-01-23 03:14:12.699410: step: 1204/526, loss: 0.007132434751838446
2023-01-23 03:14:13.863944: step: 1208/526, loss: 0.0007819175953045487
2023-01-23 03:14:14.977486: step: 1212/526, loss: 0.004265117924660444
2023-01-23 03:14:16.104597: step: 1216/526, loss: 0.08878135681152344
2023-01-23 03:14:17.295992: step: 1220/526, loss: 2.717971983656753e-05
2023-01-23 03:14:18.447706: step: 1224/526, loss: 0.00024590492830611765
2023-01-23 03:14:19.563967: step: 1228/526, loss: 0.036859702318906784
2023-01-23 03:14:20.672877: step: 1232/526, loss: 0.015033578500151634
2023-01-23 03:14:21.799502: step: 1236/526, loss: 0.02354106865823269
2023-01-23 03:14:22.957526: step: 1240/526, loss: 0.018633080646395683
2023-01-23 03:14:24.076833: step: 1244/526, loss: 0.0032699587754905224
2023-01-23 03:14:25.192121: step: 1248/526, loss: 0.014067268930375576
2023-01-23 03:14:26.326689: step: 1252/526, loss: 0.01876812055706978
2023-01-23 03:14:27.447034: step: 1256/526, loss: 0.0006593227153643966
2023-01-23 03:14:28.609084: step: 1260/526, loss: 0.005448865704238415
2023-01-23 03:14:29.729485: step: 1264/526, loss: 0.00014724732318427414
2023-01-23 03:14:30.860109: step: 1268/526, loss: 0.0012784005375579
2023-01-23 03:14:32.010938: step: 1272/526, loss: 0.12202782183885574
2023-01-23 03:14:33.125986: step: 1276/526, loss: 0.009560966864228249
2023-01-23 03:14:34.249862: step: 1280/526, loss: 0.010747050866484642
2023-01-23 03:14:35.375993: step: 1284/526, loss: 0.05109863355755806
2023-01-23 03:14:36.524774: step: 1288/526, loss: 0.01661095581948757
2023-01-23 03:14:37.643011: step: 1292/526, loss: 0.0007375717395916581
2023-01-23 03:14:38.802233: step: 1296/526, loss: 0.0022489549592137337
2023-01-23 03:14:39.919773: step: 1300/526, loss: 5.760193016612902e-05
2023-01-23 03:14:41.033635: step: 1304/526, loss: 0.018601704388856888
2023-01-23 03:14:42.174920: step: 1308/526, loss: 0.002262258669361472
2023-01-23 03:14:43.365102: step: 1312/526, loss: 0.006157303228974342
2023-01-23 03:14:44.497123: step: 1316/526, loss: 0.044877052307128906
2023-01-23 03:14:45.658312: step: 1320/526, loss: 0.020856190472841263
2023-01-23 03:14:46.782277: step: 1324/526, loss: 0.007565116975456476
2023-01-23 03:14:47.906861: step: 1328/526, loss: 0.00040340423583984375
2023-01-23 03:14:49.064145: step: 1332/526, loss: 0.011701202020049095
2023-01-23 03:14:50.185242: step: 1336/526, loss: 0.0007734298706054688
2023-01-23 03:14:51.323827: step: 1340/526, loss: 1.721382068353705e-05
2023-01-23 03:14:52.443647: step: 1344/526, loss: 0.05681648105382919
2023-01-23 03:14:53.603184: step: 1348/526, loss: 0.002610588213428855
2023-01-23 03:14:54.743996: step: 1352/526, loss: 0.002860641572624445
2023-01-23 03:14:55.871586: step: 1356/526, loss: 0.0002707481326069683
2023-01-23 03:14:56.976639: step: 1360/526, loss: 0.04086341708898544
2023-01-23 03:14:58.119097: step: 1364/526, loss: 0.12624701857566833
2023-01-23 03:14:59.259174: step: 1368/526, loss: 0.008828163146972656
2023-01-23 03:15:00.461030: step: 1372/526, loss: 0.0027866840828210115
2023-01-23 03:15:01.598794: step: 1376/526, loss: 0.0015918733552098274
2023-01-23 03:15:02.686688: step: 1380/526, loss: 0.003572464222088456
2023-01-23 03:15:03.827875: step: 1384/526, loss: 0.028323937207460403
2023-01-23 03:15:04.987960: step: 1388/526, loss: 0.005240440834313631
2023-01-23 03:15:06.130745: step: 1392/526, loss: 0.00039329531136900187
2023-01-23 03:15:07.268709: step: 1396/526, loss: 0.003461647080257535
2023-01-23 03:15:08.434673: step: 1400/526, loss: 0.01656322553753853
2023-01-23 03:15:09.568694: step: 1404/526, loss: 1.068115216185106e-05
2023-01-23 03:15:10.695775: step: 1408/526, loss: 0.0008235931163653731
2023-01-23 03:15:11.826311: step: 1412/526, loss: 0.019260406494140625
2023-01-23 03:15:12.960158: step: 1416/526, loss: 0.00432510394603014
2023-01-23 03:15:14.118087: step: 1420/526, loss: 0.016992948949337006
2023-01-23 03:15:15.260093: step: 1424/526, loss: 0.06199779361486435
2023-01-23 03:15:16.380601: step: 1428/526, loss: 0.0243072509765625
2023-01-23 03:15:17.531067: step: 1432/526, loss: 0.000606536865234375
2023-01-23 03:15:18.663806: step: 1436/526, loss: 0.0020130157936364412
2023-01-23 03:15:19.819541: step: 1440/526, loss: 0.011735916137695312
2023-01-23 03:15:20.987298: step: 1444/526, loss: 0.001981067704036832
2023-01-23 03:15:22.112237: step: 1448/526, loss: 0.0027264594100415707
2023-01-23 03:15:23.262867: step: 1452/526, loss: 0.018256474286317825
2023-01-23 03:15:24.386366: step: 1456/526, loss: 0.00015134812565520406
2023-01-23 03:15:25.506678: step: 1460/526, loss: 0.00010147095599677414
2023-01-23 03:15:26.633419: step: 1464/526, loss: 0.02340984344482422
2023-01-23 03:15:27.755433: step: 1468/526, loss: 0.0003719329833984375
2023-01-23 03:15:28.855103: step: 1472/526, loss: 3.414153979974799e-05
2023-01-23 03:15:30.048767: step: 1476/526, loss: 0.00016951560974121094
2023-01-23 03:15:31.170065: step: 1480/526, loss: 0.002627468202263117
2023-01-23 03:15:32.331687: step: 1484/526, loss: 0.0038399696350097656
2023-01-23 03:15:33.461022: step: 1488/526, loss: 0.005883598700165749
2023-01-23 03:15:34.593501: step: 1492/526, loss: 0.005117988679558039
2023-01-23 03:15:35.722341: step: 1496/526, loss: 0.0009925365447998047
2023-01-23 03:15:36.865305: step: 1500/526, loss: 0.0002210617094533518
2023-01-23 03:15:38.009792: step: 1504/526, loss: 0.0004280090215615928
2023-01-23 03:15:39.135824: step: 1508/526, loss: 0.0026557922828942537
2023-01-23 03:15:40.301060: step: 1512/526, loss: 1.4066697985981591e-05
2023-01-23 03:15:41.430011: step: 1516/526, loss: 0.004556751344352961
2023-01-23 03:15:42.593182: step: 1520/526, loss: 0.00031127932015806437
2023-01-23 03:15:43.708113: step: 1524/526, loss: 0.00597772654145956
2023-01-23 03:15:44.824150: step: 1528/526, loss: 0.003357029054313898
2023-01-23 03:15:45.972636: step: 1532/526, loss: 0.003941250033676624
2023-01-23 03:15:47.124603: step: 1536/526, loss: 0.03617596626281738
2023-01-23 03:15:48.246059: step: 1540/526, loss: 0.0002265930233988911
2023-01-23 03:15:49.351798: step: 1544/526, loss: 0.05983848497271538
2023-01-23 03:15:50.463348: step: 1548/526, loss: 9.183883958030492e-05
2023-01-23 03:15:51.589494: step: 1552/526, loss: 8.907318260753527e-05
2023-01-23 03:15:52.762373: step: 1556/526, loss: 0.021170424297451973
2023-01-23 03:15:53.897260: step: 1560/526, loss: 0.015160751529037952
2023-01-23 03:15:55.025911: step: 1564/526, loss: 0.0039014818612486124
2023-01-23 03:15:56.173471: step: 1568/526, loss: 1.7507259845733643
2023-01-23 03:15:57.304910: step: 1572/526, loss: 0.05242729187011719
2023-01-23 03:15:58.464536: step: 1576/526, loss: 0.04152173921465874
2023-01-23 03:15:59.579777: step: 1580/526, loss: 0.016037559136748314
2023-01-23 03:16:00.761607: step: 1584/526, loss: 0.03182535246014595
2023-01-23 03:16:01.884141: step: 1588/526, loss: 0.00027570725069381297
2023-01-23 03:16:03.014523: step: 1592/526, loss: 0.00564231863245368
2023-01-23 03:16:04.171017: step: 1596/526, loss: 0.0014621734153479338
2023-01-23 03:16:05.279699: step: 1600/526, loss: 0.025625038892030716
2023-01-23 03:16:06.461723: step: 1604/526, loss: 0.0006814957014285028
2023-01-23 03:16:07.607405: step: 1608/526, loss: 0.06305217742919922
2023-01-23 03:16:08.740758: step: 1612/526, loss: 0.01867065392434597
2023-01-23 03:16:09.871288: step: 1616/526, loss: 0.005424689967185259
2023-01-23 03:16:10.975095: step: 1620/526, loss: 0.05246276780962944
2023-01-23 03:16:12.122618: step: 1624/526, loss: 0.002684974577277899
2023-01-23 03:16:13.256652: step: 1628/526, loss: 0.02296895906329155
2023-01-23 03:16:14.386910: step: 1632/526, loss: 0.0018346786964684725
2023-01-23 03:16:15.522759: step: 1636/526, loss: 0.000812911952380091
2023-01-23 03:16:16.654034: step: 1640/526, loss: 0.014117050915956497
2023-01-23 03:16:17.806877: step: 1644/526, loss: 0.00014972686767578125
2023-01-23 03:16:18.933094: step: 1648/526, loss: 0.0015670761931687593
2023-01-23 03:16:20.069263: step: 1652/526, loss: 5.588531348621473e-05
2023-01-23 03:16:21.213516: step: 1656/526, loss: 0.0005754471058025956
2023-01-23 03:16:22.319332: step: 1660/526, loss: 0.005262947175651789
2023-01-23 03:16:23.449813: step: 1664/526, loss: 0.006017589475959539
2023-01-23 03:16:24.588625: step: 1668/526, loss: 0.00173015589825809
2023-01-23 03:16:25.721812: step: 1672/526, loss: 0.0006680488586425781
2023-01-23 03:16:26.854725: step: 1676/526, loss: 0.003529167268425226
2023-01-23 03:16:28.001617: step: 1680/526, loss: 0.0002471923944540322
2023-01-23 03:16:29.182652: step: 1684/526, loss: 0.008989477530121803
2023-01-23 03:16:30.301917: step: 1688/526, loss: 0.0008058547973632812
2023-01-23 03:16:31.440290: step: 1692/526, loss: 0.0038166046142578125
2023-01-23 03:16:32.598489: step: 1696/526, loss: 0.0017557144165039062
2023-01-23 03:16:33.716175: step: 1700/526, loss: 0.0081939697265625
2023-01-23 03:16:34.850389: step: 1704/526, loss: 0.021613502874970436
2023-01-23 03:16:35.986709: step: 1708/526, loss: 0.035605236887931824
2023-01-23 03:16:37.127951: step: 1712/526, loss: 0.0005512237548828125
2023-01-23 03:16:38.259641: step: 1716/526, loss: 0.01061544381082058
2023-01-23 03:16:39.377371: step: 1720/526, loss: 0.0032670022919774055
2023-01-23 03:16:40.524259: step: 1724/526, loss: 0.0008528709295205772
2023-01-23 03:16:41.646201: step: 1728/526, loss: 0.008709335699677467
2023-01-23 03:16:42.848343: step: 1732/526, loss: 0.029759027063846588
2023-01-23 03:16:43.981208: step: 1736/526, loss: 0.0010891915298998356
2023-01-23 03:16:45.087071: step: 1740/526, loss: 0.03299140930175781
2023-01-23 03:16:46.254771: step: 1744/526, loss: 0.006450462620705366
2023-01-23 03:16:47.367398: step: 1748/526, loss: 0.00022296907263807952
2023-01-23 03:16:48.512393: step: 1752/526, loss: 0.6999875903129578
2023-01-23 03:16:49.620193: step: 1756/526, loss: 0.013203429989516735
2023-01-23 03:16:50.739437: step: 1760/526, loss: 0.019240187481045723
2023-01-23 03:16:51.869327: step: 1764/526, loss: 0.014280319213867188
2023-01-23 03:16:52.993015: step: 1768/526, loss: 0.037392906844615936
2023-01-23 03:16:54.094821: step: 1772/526, loss: 0.003247309010475874
2023-01-23 03:16:55.241501: step: 1776/526, loss: 0.11433238536119461
2023-01-23 03:16:56.389716: step: 1780/526, loss: 0.0004230976337566972
2023-01-23 03:16:57.512512: step: 1784/526, loss: 0.04884061962366104
2023-01-23 03:16:58.626485: step: 1788/526, loss: 0.0024560929741710424
2023-01-23 03:16:59.753823: step: 1792/526, loss: 0.00013895034499000758
2023-01-23 03:17:00.884623: step: 1796/526, loss: 0.003559970995411277
2023-01-23 03:17:02.007121: step: 1800/526, loss: 0.19359055161476135
2023-01-23 03:17:03.116810: step: 1804/526, loss: 0.0281982421875
2023-01-23 03:17:04.244329: step: 1808/526, loss: 0.03411865234375
2023-01-23 03:17:05.358921: step: 1812/526, loss: 0.025551510974764824
2023-01-23 03:17:06.484647: step: 1816/526, loss: 0.054657746106386185
2023-01-23 03:17:07.623214: step: 1820/526, loss: 0.0024213790893554688
2023-01-23 03:17:08.791161: step: 1824/526, loss: 0.01178665179759264
2023-01-23 03:17:09.930526: step: 1828/526, loss: 4.5585635234601796e-05
2023-01-23 03:17:11.103722: step: 1832/526, loss: 0.01709447056055069
2023-01-23 03:17:12.220457: step: 1836/526, loss: 0.051303982734680176
2023-01-23 03:17:13.403571: step: 1840/526, loss: 0.015493965707719326
2023-01-23 03:17:14.516952: step: 1844/526, loss: 0.0005868911975994706
2023-01-23 03:17:15.661737: step: 1848/526, loss: 0.037518978118896484
2023-01-23 03:17:16.791939: step: 1852/526, loss: 0.0012385367881506681
2023-01-23 03:17:17.909383: step: 1856/526, loss: 0.005905342288315296
2023-01-23 03:17:19.055492: step: 1860/526, loss: 0.04580039903521538
2023-01-23 03:17:20.183291: step: 1864/526, loss: 0.00042896269587799907
2023-01-23 03:17:21.305567: step: 1868/526, loss: 0.024512099102139473
2023-01-23 03:17:22.433108: step: 1872/526, loss: 0.003866004990413785
2023-01-23 03:17:23.540088: step: 1876/526, loss: 5.073547436040826e-05
2023-01-23 03:17:24.678296: step: 1880/526, loss: 0.01756775751709938
2023-01-23 03:17:25.823442: step: 1884/526, loss: 0.07593861222267151
2023-01-23 03:17:26.961350: step: 1888/526, loss: 0.08946084976196289
2023-01-23 03:17:28.079071: step: 1892/526, loss: 0.07267895340919495
2023-01-23 03:17:29.179983: step: 1896/526, loss: 0.009779549203813076
2023-01-23 03:17:30.293996: step: 1900/526, loss: 0.0004269600030966103
2023-01-23 03:17:31.420251: step: 1904/526, loss: 0.0006159782642498612
2023-01-23 03:17:32.557327: step: 1908/526, loss: 0.0002957344113383442
2023-01-23 03:17:33.674938: step: 1912/526, loss: -2.956390289909905e-06
2023-01-23 03:17:34.857366: step: 1916/526, loss: 0.061963651329278946
2023-01-23 03:17:35.981752: step: 1920/526, loss: 5.4836273193359375e-06
2023-01-23 03:17:37.151634: step: 1924/526, loss: 0.007011794950813055
2023-01-23 03:17:38.293794: step: 1928/526, loss: 0.00021085739717818797
2023-01-23 03:17:39.417386: step: 1932/526, loss: 0.010194159112870693
2023-01-23 03:17:40.553924: step: 1936/526, loss: 0.009520625695586205
2023-01-23 03:17:41.673524: step: 1940/526, loss: 0.00036578180151991546
2023-01-23 03:17:42.850906: step: 1944/526, loss: 0.1800640970468521
2023-01-23 03:17:43.998009: step: 1948/526, loss: 5.559921555686742e-05
2023-01-23 03:17:45.176914: step: 1952/526, loss: 0.03282508999109268
2023-01-23 03:17:46.298035: step: 1956/526, loss: 0.0002084731968352571
2023-01-23 03:17:47.437758: step: 1960/526, loss: 0.006457519717514515
2023-01-23 03:17:48.596823: step: 1964/526, loss: 0.0986722931265831
2023-01-23 03:17:49.725364: step: 1968/526, loss: 0.03753481060266495
2023-01-23 03:17:50.851356: step: 1972/526, loss: 0.00035009384737350047
2023-01-23 03:17:52.006964: step: 1976/526, loss: 0.029037287458777428
2023-01-23 03:17:53.166588: step: 1980/526, loss: 0.00014438628568314016
2023-01-23 03:17:54.345576: step: 1984/526, loss: 0.005448341369628906
2023-01-23 03:17:55.476578: step: 1988/526, loss: 0.00855798739939928
2023-01-23 03:17:56.609204: step: 1992/526, loss: 0.007789993658661842
2023-01-23 03:17:57.776121: step: 1996/526, loss: 0.024349499493837357
2023-01-23 03:17:58.901347: step: 2000/526, loss: 0.0103591438382864
2023-01-23 03:18:00.047858: step: 2004/526, loss: 0.00107746128924191
2023-01-23 03:18:01.196446: step: 2008/526, loss: 0.007900619879364967
2023-01-23 03:18:02.349379: step: 2012/526, loss: 0.00010185241990257055
2023-01-23 03:18:03.516579: step: 2016/526, loss: 0.0004634857177734375
2023-01-23 03:18:04.654388: step: 2020/526, loss: 0.000782489834818989
2023-01-23 03:18:05.769019: step: 2024/526, loss: 0.014005064964294434
2023-01-23 03:18:06.884453: step: 2028/526, loss: 9.956360736396164e-05
2023-01-23 03:18:08.004156: step: 2032/526, loss: 0.006955218501389027
2023-01-23 03:18:09.137953: step: 2036/526, loss: 0.0004516601620707661
2023-01-23 03:18:10.282358: step: 2040/526, loss: 0.011570167727768421
2023-01-23 03:18:11.428390: step: 2044/526, loss: 0.02163248136639595
2023-01-23 03:18:12.577043: step: 2048/526, loss: 0.0007787704817019403
2023-01-23 03:18:13.742519: step: 2052/526, loss: 0.014159774407744408
2023-01-23 03:18:14.852730: step: 2056/526, loss: 0.00038356782170012593
2023-01-23 03:18:15.991754: step: 2060/526, loss: 0.0012542724143713713
2023-01-23 03:18:17.103006: step: 2064/526, loss: 0.007300854194909334
2023-01-23 03:18:18.233942: step: 2068/526, loss: 0.17027434706687927
2023-01-23 03:18:19.363554: step: 2072/526, loss: 0.0008005141862668097
2023-01-23 03:18:20.539148: step: 2076/526, loss: 0.0014862060779705644
2023-01-23 03:18:21.658340: step: 2080/526, loss: 0.03993682935833931
2023-01-23 03:18:22.776231: step: 2084/526, loss: 0.003623581025749445
2023-01-23 03:18:23.925993: step: 2088/526, loss: 0.003777885576710105
2023-01-23 03:18:25.089413: step: 2092/526, loss: 0.0019784928299486637
2023-01-23 03:18:26.248901: step: 2096/526, loss: 0.010195732116699219
2023-01-23 03:18:27.372407: step: 2100/526, loss: 0.00015802383131813258
2023-01-23 03:18:28.552847: step: 2104/526, loss: 0.0027029039338231087
==================================================
Loss: 0.022
--------------------
Dev: {'event': {'p': 0.5841784989858012, 'r': 0.7669773635153129, 'f1': 0.6632124352331606}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
Test: {'event': {'p': 0.6179129005751849, 'r': 0.7849686847599165, 'f1': 0.6914942528735631}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
Chinese: {'event': {'p': 0.5568181818181818, 'r': 0.9074074074074074, 'f1': 0.6901408450704225}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
Korean: {'event': {'p': 0.6595744680851063, 'r': 0.49206349206349204, 'f1': 0.5636363636363635}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
Russian: {'event': {'p': 0.4634146341463415, 'r': 0.5277777777777778, 'f1': 0.4935064935064935}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6389811738648948, 'r': 0.7683089214380826, 'f1': 0.6977025392986699}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Eng Test for Chinese: {'event': {'p': 0.6328626444159179, 'r': 0.7719206680584552, 'f1': 0.6955090524335763}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Sample Chinese: {'event': {'p': 0.6282051282051282, 'r': 0.9074074074074074, 'f1': 0.7424242424242423}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6257995735607675, 'r': 0.7816245006657789, 'f1': 0.6950858496151568}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Eng Test for Korean: {'event': {'p': 0.623113410952997, 'r': 0.7541753653444676, 'f1': 0.6824085005903188}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Sample Korean: {'event': {'p': 0.7446808510638298, 'r': 0.5555555555555556, 'f1': 0.6363636363636364}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5800575263662512, 'r': 0.8055925432756325, 'f1': 0.6744704570791527}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
Eng Test for Russian: {'event': {'p': 0.5962534874451972, 'r': 0.7807933194154488, 'f1': 0.6761581920903954}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
Sample Russian: {'event': {'p': 0.48936170212765956, 'r': 0.6388888888888888, 'f1': 0.5542168674698795}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
******************************
Epoch: 22
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 03:19:11.522121: step: 4/526, loss: 0.007927894592285156
2023-01-23 03:19:12.645217: step: 8/526, loss: 0.01830759085714817
2023-01-23 03:19:13.767305: step: 12/526, loss: 0.006164455320686102
2023-01-23 03:19:14.888369: step: 16/526, loss: 0.0023234367836266756
2023-01-23 03:19:16.036288: step: 20/526, loss: 0.0170153621584177
2023-01-23 03:19:17.186329: step: 24/526, loss: 0.009967708960175514
2023-01-23 03:19:18.307612: step: 28/526, loss: 0.0002826690615620464
2023-01-23 03:19:19.440690: step: 32/526, loss: 0.6450921297073364
2023-01-23 03:19:20.568893: step: 36/526, loss: 0.018439723178744316
2023-01-23 03:19:21.738238: step: 40/526, loss: 0.008635140024125576
2023-01-23 03:19:22.853164: step: 44/526, loss: 0.0040780543349683285
2023-01-23 03:19:24.000102: step: 48/526, loss: 0.00013108253187965602
2023-01-23 03:19:25.112752: step: 52/526, loss: 0.00545082101598382
2023-01-23 03:19:26.284928: step: 56/526, loss: 2.3269654775504023e-05
2023-01-23 03:19:27.414000: step: 60/526, loss: 0.0013195037608966231
2023-01-23 03:19:28.519696: step: 64/526, loss: 0.0001579284726176411
2023-01-23 03:19:29.621817: step: 68/526, loss: 0.00047860146150924265
2023-01-23 03:19:30.718562: step: 72/526, loss: 0.01788778230547905
2023-01-23 03:19:31.832651: step: 76/526, loss: 0.0006915092235431075
2023-01-23 03:19:32.965785: step: 80/526, loss: 0.003161525819450617
2023-01-23 03:19:34.138515: step: 84/526, loss: 0.015518855303525925
2023-01-23 03:19:35.262557: step: 88/526, loss: 0.05212097242474556
2023-01-23 03:19:36.422738: step: 92/526, loss: 0.007357597351074219
2023-01-23 03:19:37.579039: step: 96/526, loss: 0.007423591800034046
2023-01-23 03:19:38.709910: step: 100/526, loss: 0.008754349313676357
2023-01-23 03:19:39.831801: step: 104/526, loss: 0.00018110274686478078
2023-01-23 03:19:40.972572: step: 108/526, loss: 0.02275228500366211
2023-01-23 03:19:42.112053: step: 112/526, loss: 0.034697722643613815
2023-01-23 03:19:43.236060: step: 116/526, loss: 0.005748939700424671
2023-01-23 03:19:44.352815: step: 120/526, loss: 0.00022096632164902985
2023-01-23 03:19:45.479414: step: 124/526, loss: 0.00020313262939453125
2023-01-23 03:19:46.570629: step: 128/526, loss: 0.0030817033257335424
2023-01-23 03:19:47.724759: step: 132/526, loss: 0.014430142007768154
2023-01-23 03:19:48.869732: step: 136/526, loss: 0.0003222465456929058
2023-01-23 03:19:50.010824: step: 140/526, loss: 0.0027914047241210938
2023-01-23 03:19:51.127652: step: 144/526, loss: 2.403259350103326e-05
2023-01-23 03:19:52.234654: step: 148/526, loss: 4.482269287109375e-05
2023-01-23 03:19:53.348585: step: 152/526, loss: 0.0007287979242391884
2023-01-23 03:19:54.460700: step: 156/526, loss: 0.0012479304568842053
2023-01-23 03:19:55.592232: step: 160/526, loss: 9.35554489842616e-05
2023-01-23 03:19:56.724124: step: 164/526, loss: 0.0001068115234375
2023-01-23 03:19:57.855538: step: 168/526, loss: 0.005153274163603783
2023-01-23 03:19:58.986496: step: 172/526, loss: 0.0010914802551269531
2023-01-23 03:20:00.105595: step: 176/526, loss: 2.8371810913085938e-05
2023-01-23 03:20:01.233083: step: 180/526, loss: 0.0051104542799293995
2023-01-23 03:20:02.358260: step: 184/526, loss: 2.2315980459097773e-05
2023-01-23 03:20:03.483382: step: 188/526, loss: 0.00010414123244117945
2023-01-23 03:20:04.609115: step: 192/526, loss: 2.117157055181451e-05
2023-01-23 03:20:05.775552: step: 196/526, loss: 0.012742423452436924
2023-01-23 03:20:06.929425: step: 200/526, loss: 0.006153441034257412
2023-01-23 03:20:08.053516: step: 204/526, loss: 0.003979873843491077
2023-01-23 03:20:09.196227: step: 208/526, loss: 8.940697625803296e-06
2023-01-23 03:20:10.357345: step: 212/526, loss: 0.0009913444519042969
2023-01-23 03:20:11.496697: step: 216/526, loss: 0.010290145874023438
2023-01-23 03:20:12.612035: step: 220/526, loss: 0.0016716003883630037
2023-01-23 03:20:13.770884: step: 224/526, loss: 0.0007602691766805947
2023-01-23 03:20:14.875372: step: 228/526, loss: 0.010515929199755192
2023-01-23 03:20:15.987632: step: 232/526, loss: 0.0025112151633948088
2023-01-23 03:20:17.161989: step: 236/526, loss: 2.059936559817288e-05
2023-01-23 03:20:18.285153: step: 240/526, loss: 0.0011378765339031816
2023-01-23 03:20:19.408272: step: 244/526, loss: 0.004144859500229359
2023-01-23 03:20:20.591610: step: 248/526, loss: 0.0035165308509021997
2023-01-23 03:20:21.719504: step: 252/526, loss: 0.015324783511459827
2023-01-23 03:20:22.875761: step: 256/526, loss: 0.0038444518577307463
2023-01-23 03:20:24.034737: step: 260/526, loss: 0.006503296084702015
2023-01-23 03:20:25.169783: step: 264/526, loss: 0.00010218620445812121
2023-01-23 03:20:26.319940: step: 268/526, loss: 9.412765211891383e-05
2023-01-23 03:20:27.432796: step: 272/526, loss: 0.0021088600624352694
2023-01-23 03:20:28.557895: step: 276/526, loss: 0.007213306613266468
2023-01-23 03:20:29.686936: step: 280/526, loss: 0.007621001917868853
2023-01-23 03:20:30.829398: step: 284/526, loss: 0.007354068569839001
2023-01-23 03:20:31.942577: step: 288/526, loss: 0.00010778904106700793
2023-01-23 03:20:33.105520: step: 292/526, loss: 0.0006166935199871659
2023-01-23 03:20:34.230530: step: 296/526, loss: 0.0029600143898278475
2023-01-23 03:20:35.368962: step: 300/526, loss: 0.0003224372921977192
2023-01-23 03:20:36.508594: step: 304/526, loss: 0.057908058166503906
2023-01-23 03:20:37.629868: step: 308/526, loss: 0.00014481545076705515
2023-01-23 03:20:38.747897: step: 312/526, loss: 0.0019966126419603825
2023-01-23 03:20:39.868510: step: 316/526, loss: 0.03961486741900444
2023-01-23 03:20:41.039033: step: 320/526, loss: 0.004118156619369984
2023-01-23 03:20:42.181531: step: 324/526, loss: 0.008019733242690563
2023-01-23 03:20:43.361633: step: 328/526, loss: 0.0170777328312397
2023-01-23 03:20:44.476058: step: 332/526, loss: 0.009152126498520374
2023-01-23 03:20:45.626450: step: 336/526, loss: 3.366470627952367e-05
2023-01-23 03:20:46.760793: step: 340/526, loss: 0.00020987987227272242
2023-01-23 03:20:47.867403: step: 344/526, loss: 5.73158249608241e-05
2023-01-23 03:20:49.015541: step: 348/526, loss: 6.198883056640625e-05
2023-01-23 03:20:50.161426: step: 352/526, loss: 0.00716090202331543
2023-01-23 03:20:51.301468: step: 356/526, loss: 0.04049749672412872
2023-01-23 03:20:52.422256: step: 360/526, loss: 0.0026858330238610506
2023-01-23 03:20:53.564664: step: 364/526, loss: 0.07527142018079758
2023-01-23 03:20:54.705570: step: 368/526, loss: 0.04919242858886719
2023-01-23 03:20:55.812405: step: 372/526, loss: 0.00884170550853014
2023-01-23 03:20:56.957777: step: 376/526, loss: 0.0017216682899743319
2023-01-23 03:20:58.111509: step: 380/526, loss: 8.907318260753527e-05
2023-01-23 03:20:59.256173: step: 384/526, loss: 0.00685730017721653
2023-01-23 03:21:00.371142: step: 388/526, loss: 1.9168854123563506e-05
2023-01-23 03:21:01.501908: step: 392/526, loss: 3.976821608375758e-05
2023-01-23 03:21:02.638260: step: 396/526, loss: 0.018412113189697266
2023-01-23 03:21:03.766447: step: 400/526, loss: 0.00039801598177291453
2023-01-23 03:21:04.920414: step: 404/526, loss: 0.03472766652703285
2023-01-23 03:21:06.038879: step: 408/526, loss: 0.000697231269441545
2023-01-23 03:21:07.188859: step: 412/526, loss: 0.012841224670410156
2023-01-23 03:21:08.341616: step: 416/526, loss: 0.0001047134428517893
2023-01-23 03:21:09.469142: step: 420/526, loss: 0.0023822307121008635
2023-01-23 03:21:10.586024: step: 424/526, loss: 0.00858459435403347
2023-01-23 03:21:11.702684: step: 428/526, loss: 0.05080986022949219
2023-01-23 03:21:12.867064: step: 432/526, loss: 0.003403568407520652
2023-01-23 03:21:13.951372: step: 436/526, loss: 0.0002197265566792339
2023-01-23 03:21:15.071232: step: 440/526, loss: 0.001726341200992465
2023-01-23 03:21:16.246184: step: 444/526, loss: 0.00049762730486691
2023-01-23 03:21:17.362881: step: 448/526, loss: 0.0047966004349291325
2023-01-23 03:21:18.494145: step: 452/526, loss: 0.0840265303850174
2023-01-23 03:21:19.640411: step: 456/526, loss: 0.02573399432003498
2023-01-23 03:21:20.761338: step: 460/526, loss: 0.0239639300853014
2023-01-23 03:21:21.865917: step: 464/526, loss: 0.0007068633567541838
2023-01-23 03:21:22.991809: step: 468/526, loss: 0.0003845214960165322
2023-01-23 03:21:24.130071: step: 472/526, loss: 0.0009997368324548006
2023-01-23 03:21:25.284558: step: 476/526, loss: 0.0020549774635583162
2023-01-23 03:21:26.432201: step: 480/526, loss: 0.007887459360063076
2023-01-23 03:21:27.554725: step: 484/526, loss: 0.0002263069327455014
2023-01-23 03:21:28.723356: step: 488/526, loss: 0.0339902862906456
2023-01-23 03:21:29.898356: step: 492/526, loss: 0.15515127778053284
2023-01-23 03:21:31.018316: step: 496/526, loss: 0.001995182130485773
2023-01-23 03:21:32.167295: step: 500/526, loss: 0.0018994332058355212
2023-01-23 03:21:33.292115: step: 504/526, loss: 0.0006412506336346269
2023-01-23 03:21:34.423803: step: 508/526, loss: 0.09061269462108612
2023-01-23 03:21:35.544004: step: 512/526, loss: 0.032679032534360886
2023-01-23 03:21:36.672670: step: 516/526, loss: 0.03268270567059517
2023-01-23 03:21:37.796345: step: 520/526, loss: 0.00012302398681640625
2023-01-23 03:21:38.918823: step: 524/526, loss: 1.964569128176663e-05
2023-01-23 03:21:40.085185: step: 528/526, loss: 4.215240551275201e-05
2023-01-23 03:21:41.195852: step: 532/526, loss: 0.0028465748764574528
2023-01-23 03:21:42.339438: step: 536/526, loss: 0.04000244289636612
2023-01-23 03:21:43.476469: step: 540/526, loss: 0.016924476251006126
2023-01-23 03:21:44.622837: step: 544/526, loss: 0.0002304077206645161
2023-01-23 03:21:45.752464: step: 548/526, loss: 0.0010737419361248612
2023-01-23 03:21:46.903287: step: 552/526, loss: 0.011624526232481003
2023-01-23 03:21:48.029119: step: 556/526, loss: 2.3746490114717744e-05
2023-01-23 03:21:49.164666: step: 560/526, loss: 0.004565524868667126
2023-01-23 03:21:50.312666: step: 564/526, loss: 0.006567955017089844
2023-01-23 03:21:51.442896: step: 568/526, loss: 0.0016528129344806075
2023-01-23 03:21:52.576914: step: 572/526, loss: 0.0319090336561203
2023-01-23 03:21:53.722730: step: 576/526, loss: 0.0030702592339366674
2023-01-23 03:21:54.908884: step: 580/526, loss: 0.0033736228942871094
2023-01-23 03:21:56.041920: step: 584/526, loss: 0.008761786855757236
2023-01-23 03:21:57.190712: step: 588/526, loss: 0.0039994241669774055
2023-01-23 03:21:58.296193: step: 592/526, loss: 0.00029087066650390625
2023-01-23 03:21:59.406108: step: 596/526, loss: 0.00018396378436591476
2023-01-23 03:22:00.535536: step: 600/526, loss: 0.0013347625499591231
2023-01-23 03:22:01.672582: step: 604/526, loss: 0.0004343986511230469
2023-01-23 03:22:02.833886: step: 608/526, loss: 0.0002654552517924458
2023-01-23 03:22:03.949373: step: 612/526, loss: 5.836486889165826e-05
2023-01-23 03:22:05.088646: step: 616/526, loss: 0.00011577605619095266
2023-01-23 03:22:06.281841: step: 620/526, loss: 0.0035202025901526213
2023-01-23 03:22:07.440077: step: 624/526, loss: 0.0050741201266646385
2023-01-23 03:22:08.549474: step: 628/526, loss: 0.0012866974575445056
2023-01-23 03:22:09.686471: step: 632/526, loss: 0.0017437934875488281
2023-01-23 03:22:10.829605: step: 636/526, loss: 0.004202461335808039
2023-01-23 03:22:11.955968: step: 640/526, loss: 0.014503669925034046
2023-01-23 03:22:13.076079: step: 644/526, loss: 0.00015449525380972773
2023-01-23 03:22:14.210120: step: 648/526, loss: 0.006404972169548273
2023-01-23 03:22:15.337368: step: 652/526, loss: 0.03534698486328125
2023-01-23 03:22:16.428584: step: 656/526, loss: 0.01896214485168457
2023-01-23 03:22:17.574494: step: 660/526, loss: 0.06032419204711914
2023-01-23 03:22:18.711543: step: 664/526, loss: 0.001501321792602539
2023-01-23 03:22:19.846941: step: 668/526, loss: 0.00011882781836902723
2023-01-23 03:22:20.960892: step: 672/526, loss: 2.479553813827806e-06
2023-01-23 03:22:22.129995: step: 676/526, loss: 0.0029453278984874487
2023-01-23 03:22:23.290938: step: 680/526, loss: 4.2533876694506034e-05
2023-01-23 03:22:24.424074: step: 684/526, loss: 0.006904792971909046
2023-01-23 03:22:25.569634: step: 688/526, loss: 0.051347922533750534
2023-01-23 03:22:26.712962: step: 692/526, loss: 0.003003883408382535
2023-01-23 03:22:27.836581: step: 696/526, loss: 0.017427731305360794
2023-01-23 03:22:28.997645: step: 700/526, loss: 0.0020576477982103825
2023-01-23 03:22:30.114360: step: 704/526, loss: 0.02699604257941246
2023-01-23 03:22:31.259056: step: 708/526, loss: 0.018704796209931374
2023-01-23 03:22:32.412457: step: 712/526, loss: 0.0003643035888671875
2023-01-23 03:22:33.559568: step: 716/526, loss: 0.02192096970975399
2023-01-23 03:22:34.676062: step: 720/526, loss: 0.0002208709775004536
2023-01-23 03:22:35.827823: step: 724/526, loss: 0.013079643249511719
2023-01-23 03:22:36.966659: step: 728/526, loss: 0.01146697998046875
2023-01-23 03:22:38.108921: step: 732/526, loss: 0.008603858761489391
2023-01-23 03:22:39.258393: step: 736/526, loss: 0.0084381103515625
2023-01-23 03:22:40.424304: step: 740/526, loss: 0.00033397675724700093
2023-01-23 03:22:41.568503: step: 744/526, loss: 0.0003135681326966733
2023-01-23 03:22:42.731373: step: 748/526, loss: 3.967285010730848e-05
2023-01-23 03:22:43.860443: step: 752/526, loss: 0.00019092560978606343
2023-01-23 03:22:44.995276: step: 756/526, loss: 0.011512375436723232
2023-01-23 03:22:46.143098: step: 760/526, loss: 0.0016561507945880294
2023-01-23 03:22:47.282826: step: 764/526, loss: 0.007869553752243519
2023-01-23 03:22:48.412030: step: 768/526, loss: 6.12258882028982e-05
2023-01-23 03:22:49.574525: step: 772/526, loss: 0.006527757737785578
2023-01-23 03:22:50.723063: step: 776/526, loss: 0.029040098190307617
2023-01-23 03:22:51.868341: step: 780/526, loss: 0.3104965090751648
2023-01-23 03:22:53.007810: step: 784/526, loss: 0.0012784957652911544
2023-01-23 03:22:54.139053: step: 788/526, loss: 0.0036839963868260384
2023-01-23 03:22:55.303390: step: 792/526, loss: 9.15527380129788e-06
2023-01-23 03:22:56.438489: step: 796/526, loss: 0.000598907470703125
2023-01-23 03:22:57.551409: step: 800/526, loss: 0.0003949165402445942
2023-01-23 03:22:58.691606: step: 804/526, loss: 0.02554044872522354
2023-01-23 03:22:59.802664: step: 808/526, loss: 0.009838295169174671
2023-01-23 03:23:00.915614: step: 812/526, loss: 0.3151658773422241
2023-01-23 03:23:02.068318: step: 816/526, loss: 0.013678264804184437
2023-01-23 03:23:03.202404: step: 820/526, loss: 0.0452360138297081
2023-01-23 03:23:04.338549: step: 824/526, loss: 0.0013882637722417712
2023-01-23 03:23:05.446011: step: 828/526, loss: 0.003352546598762274
2023-01-23 03:23:06.580005: step: 832/526, loss: 0.0010985374683514237
2023-01-23 03:23:07.710303: step: 836/526, loss: 0.06973180919885635
2023-01-23 03:23:08.832551: step: 840/526, loss: 0.010907936841249466
2023-01-23 03:23:09.967310: step: 844/526, loss: 0.01543283462524414
2023-01-23 03:23:11.150290: step: 848/526, loss: 0.06298086792230606
2023-01-23 03:23:12.284504: step: 852/526, loss: 0.06486663967370987
2023-01-23 03:23:13.432819: step: 856/526, loss: 0.002442693803459406
2023-01-23 03:23:14.543614: step: 860/526, loss: 0.011987256817519665
2023-01-23 03:23:15.661606: step: 864/526, loss: 0.011977958492934704
2023-01-23 03:23:16.802336: step: 868/526, loss: 0.002745342208072543
2023-01-23 03:23:17.946612: step: 872/526, loss: 0.0009664535755291581
2023-01-23 03:23:19.087813: step: 876/526, loss: 0.00018625259690452367
2023-01-23 03:23:20.196143: step: 880/526, loss: 0.00108423235360533
2023-01-23 03:23:21.315923: step: 884/526, loss: 0.10615768283605576
2023-01-23 03:23:22.468353: step: 888/526, loss: 0.09314422309398651
2023-01-23 03:23:23.654463: step: 892/526, loss: 0.0025674819480627775
2023-01-23 03:23:24.772103: step: 896/526, loss: 9.021758887683973e-05
2023-01-23 03:23:25.905438: step: 900/526, loss: 0.0004505157412495464
2023-01-23 03:23:27.050492: step: 904/526, loss: 0.00024919508723542094
2023-01-23 03:23:28.185556: step: 908/526, loss: 0.0020849229767918587
2023-01-23 03:23:29.357499: step: 912/526, loss: 0.0002765655517578125
2023-01-23 03:23:30.478866: step: 916/526, loss: 0.000866842339746654
2023-01-23 03:23:31.615780: step: 920/526, loss: 0.03200606256723404
2023-01-23 03:23:32.741230: step: 924/526, loss: 0.0011563301086425781
2023-01-23 03:23:33.865957: step: 928/526, loss: 0.0001295089750783518
2023-01-23 03:23:34.988505: step: 932/526, loss: 0.0001903533993754536
2023-01-23 03:23:36.132780: step: 936/526, loss: 0.0025975226890295744
2023-01-23 03:23:37.298413: step: 940/526, loss: 0.0005887985462322831
2023-01-23 03:23:38.422819: step: 944/526, loss: 0.011120987124741077
2023-01-23 03:23:39.565261: step: 948/526, loss: 0.056415461003780365
2023-01-23 03:23:40.678150: step: 952/526, loss: 0.017654899507761
2023-01-23 03:23:41.823792: step: 956/526, loss: 0.0032493590842932463
2023-01-23 03:23:42.989715: step: 960/526, loss: 0.04450645670294762
2023-01-23 03:23:44.147051: step: 964/526, loss: 5.42163870704826e-05
2023-01-23 03:23:45.266880: step: 968/526, loss: 1.0967254638671875e-05
2023-01-23 03:23:46.428478: step: 972/526, loss: 0.007106209173798561
2023-01-23 03:23:47.561799: step: 976/526, loss: 0.0002753734588623047
2023-01-23 03:23:48.677911: step: 980/526, loss: 0.003381061600521207
2023-01-23 03:23:49.799805: step: 984/526, loss: 0.03594255447387695
2023-01-23 03:23:50.937984: step: 988/526, loss: 0.047146987169981
2023-01-23 03:23:52.082364: step: 992/526, loss: 0.013032246381044388
2023-01-23 03:23:53.218114: step: 996/526, loss: 0.0005305290105752647
2023-01-23 03:23:54.339679: step: 1000/526, loss: 0.03170814365148544
2023-01-23 03:23:55.462662: step: 1004/526, loss: 0.026973627507686615
2023-01-23 03:23:56.604758: step: 1008/526, loss: 0.029405688866972923
2023-01-23 03:23:57.754365: step: 1012/526, loss: 0.0001583099365234375
2023-01-23 03:23:58.883028: step: 1016/526, loss: 0.009625243954360485
2023-01-23 03:24:00.014284: step: 1020/526, loss: 0.00681152381002903
2023-01-23 03:24:01.155288: step: 1024/526, loss: 0.012583828531205654
2023-01-23 03:24:02.288384: step: 1028/526, loss: 0.00015993117995094508
2023-01-23 03:24:03.416476: step: 1032/526, loss: 3.61442580469884e-05
2023-01-23 03:24:04.558881: step: 1036/526, loss: 0.05180578678846359
2023-01-23 03:24:05.713565: step: 1040/526, loss: 0.0014400483341887593
2023-01-23 03:24:06.863090: step: 1044/526, loss: 0.01643834076821804
2023-01-23 03:24:07.994803: step: 1048/526, loss: 0.013430404476821423
2023-01-23 03:24:09.145270: step: 1052/526, loss: 0.00013236999802757055
2023-01-23 03:24:10.275964: step: 1056/526, loss: 0.025191688910126686
2023-01-23 03:24:11.419575: step: 1060/526, loss: 0.012255859561264515
2023-01-23 03:24:12.580123: step: 1064/526, loss: 0.039710428565740585
2023-01-23 03:24:13.704542: step: 1068/526, loss: 0.00537033099681139
2023-01-23 03:24:14.830251: step: 1072/526, loss: 4.491805884754285e-05
2023-01-23 03:24:15.944291: step: 1076/526, loss: 1.406669707648689e-05
2023-01-23 03:24:17.096327: step: 1080/526, loss: 0.000125885009765625
2023-01-23 03:24:18.202950: step: 1084/526, loss: 0.053790852427482605
2023-01-23 03:24:19.339170: step: 1088/526, loss: 1.773834264895413e-05
2023-01-23 03:24:20.475596: step: 1092/526, loss: 0.0011372566223144531
2023-01-23 03:24:21.613005: step: 1096/526, loss: 0.010393811389803886
2023-01-23 03:24:22.786113: step: 1100/526, loss: 0.0008558273548260331
2023-01-23 03:24:23.919046: step: 1104/526, loss: 0.00024337769718840718
2023-01-23 03:24:25.079808: step: 1108/526, loss: 0.001394939492456615
2023-01-23 03:24:26.205912: step: 1112/526, loss: 0.00951242446899414
2023-01-23 03:24:27.361201: step: 1116/526, loss: 0.002495241118595004
2023-01-23 03:24:28.487896: step: 1120/526, loss: 0.013024520128965378
2023-01-23 03:24:29.609157: step: 1124/526, loss: 0.0010013104183599353
2023-01-23 03:24:30.769180: step: 1128/526, loss: 0.016613198444247246
2023-01-23 03:24:31.897778: step: 1132/526, loss: 0.007111930754035711
2023-01-23 03:24:33.038981: step: 1136/526, loss: 1.296997106692288e-05
2023-01-23 03:24:34.175047: step: 1140/526, loss: 0.03424868360161781
2023-01-23 03:24:35.292825: step: 1144/526, loss: 0.0014286995865404606
2023-01-23 03:24:36.394862: step: 1148/526, loss: 0.009533500298857689
2023-01-23 03:24:37.527144: step: 1152/526, loss: 0.006971550174057484
2023-01-23 03:24:38.696044: step: 1156/526, loss: 0.03789863735437393
2023-01-23 03:24:39.823548: step: 1160/526, loss: 0.0006389617919921875
2023-01-23 03:24:40.940476: step: 1164/526, loss: 0.006878376007080078
2023-01-23 03:24:42.070536: step: 1168/526, loss: 0.002097606658935547
2023-01-23 03:24:43.202718: step: 1172/526, loss: 0.018703175708651543
2023-01-23 03:24:44.367115: step: 1176/526, loss: 0.005656242370605469
2023-01-23 03:24:45.499724: step: 1180/526, loss: 0.0009202957153320312
2023-01-23 03:24:46.636513: step: 1184/526, loss: 0.00011105537851108238
2023-01-23 03:24:47.788448: step: 1188/526, loss: 0.0008386612171307206
2023-01-23 03:24:48.908579: step: 1192/526, loss: 0.0035538673400878906
2023-01-23 03:24:50.075544: step: 1196/526, loss: 0.05066833272576332
2023-01-23 03:24:51.228156: step: 1200/526, loss: 0.002857208251953125
2023-01-23 03:24:52.364794: step: 1204/526, loss: 0.013005065731704235
2023-01-23 03:24:53.461793: step: 1208/526, loss: 0.00037097930908203125
2023-01-23 03:24:54.607735: step: 1212/526, loss: 0.0021614073775708675
2023-01-23 03:24:55.752386: step: 1216/526, loss: 0.0004459381161723286
2023-01-23 03:24:56.896848: step: 1220/526, loss: 0.016316134482622147
2023-01-23 03:24:58.033669: step: 1224/526, loss: 0.003688812255859375
2023-01-23 03:24:59.178237: step: 1228/526, loss: 0.000263214111328125
2023-01-23 03:25:00.334620: step: 1232/526, loss: 0.00021133421978447586
2023-01-23 03:25:01.453461: step: 1236/526, loss: 0.00019788742065429688
2023-01-23 03:25:02.575890: step: 1240/526, loss: 0.0004879951593466103
2023-01-23 03:25:03.707185: step: 1244/526, loss: 0.0003581047058105469
2023-01-23 03:25:04.890671: step: 1248/526, loss: 0.000263214111328125
2023-01-23 03:25:06.018338: step: 1252/526, loss: 0.0006858825800009072
2023-01-23 03:25:07.176836: step: 1256/526, loss: 0.03709583356976509
2023-01-23 03:25:08.302304: step: 1260/526, loss: 6.246566772460938e-05
2023-01-23 03:25:09.451573: step: 1264/526, loss: 2.059936559817288e-05
2023-01-23 03:25:10.608414: step: 1268/526, loss: 0.046073149889707565
2023-01-23 03:25:11.735826: step: 1272/526, loss: 2.098083541568485e-06
2023-01-23 03:25:12.905977: step: 1276/526, loss: 0.00023145676823332906
2023-01-23 03:25:14.036890: step: 1280/526, loss: 0.00011024475679732859
2023-01-23 03:25:15.153207: step: 1284/526, loss: 0.00864114798605442
2023-01-23 03:25:16.283618: step: 1288/526, loss: 0.013900947757065296
2023-01-23 03:25:17.449269: step: 1292/526, loss: 0.0022674561478197575
2023-01-23 03:25:18.602665: step: 1296/526, loss: 0.00211334228515625
2023-01-23 03:25:19.726573: step: 1300/526, loss: 9.460448927711695e-05
2023-01-23 03:25:20.872880: step: 1304/526, loss: 0.0007321357843466103
2023-01-23 03:25:22.051132: step: 1308/526, loss: 0.0005928039317950606
2023-01-23 03:25:23.215170: step: 1312/526, loss: 0.0014251709217205644
2023-01-23 03:25:24.325306: step: 1316/526, loss: 0.00107746128924191
2023-01-23 03:25:25.470573: step: 1320/526, loss: 4.787445141118951e-05
2023-01-23 03:25:26.595627: step: 1324/526, loss: 0.00011014938354492188
2023-01-23 03:25:27.720027: step: 1328/526, loss: 0.0008003234979696572
2023-01-23 03:25:28.887492: step: 1332/526, loss: 0.010824394412338734
2023-01-23 03:25:30.017856: step: 1336/526, loss: 4.4155120122013614e-05
2023-01-23 03:25:31.135080: step: 1340/526, loss: 0.0014827728737145662
2023-01-23 03:25:32.236461: step: 1344/526, loss: 0.00039892198401503265
2023-01-23 03:25:33.369956: step: 1348/526, loss: 0.0003302574041299522
2023-01-23 03:25:34.485637: step: 1352/526, loss: 0.0015388489700853825
2023-01-23 03:25:35.644299: step: 1356/526, loss: 0.07164879143238068
2023-01-23 03:25:36.756119: step: 1360/526, loss: 0.00306529994122684
2023-01-23 03:25:37.902005: step: 1364/526, loss: 0.007248306646943092
2023-01-23 03:25:39.029290: step: 1368/526, loss: 8.583068620282575e-07
2023-01-23 03:25:40.141734: step: 1372/526, loss: 0.0007380486349575222
2023-01-23 03:25:41.303208: step: 1376/526, loss: 8.478164818370715e-05
2023-01-23 03:25:42.437864: step: 1380/526, loss: 0.01052713394165039
2023-01-23 03:25:43.594173: step: 1384/526, loss: 0.015980910509824753
2023-01-23 03:25:44.735743: step: 1388/526, loss: 0.06886310875415802
2023-01-23 03:25:45.843136: step: 1392/526, loss: 0.0002882003609556705
2023-01-23 03:25:46.972969: step: 1396/526, loss: 0.0003448486386332661
2023-01-23 03:25:48.118835: step: 1400/526, loss: 0.011772585101425648
2023-01-23 03:25:49.256937: step: 1404/526, loss: 0.0002038955717580393
2023-01-23 03:25:50.383592: step: 1408/526, loss: 0.0018633842701092362
2023-01-23 03:25:51.522386: step: 1412/526, loss: 8.654594421386719e-05
2023-01-23 03:25:52.666043: step: 1416/526, loss: 0.004313564393669367
2023-01-23 03:25:53.777761: step: 1420/526, loss: 0.00011711120896507055
2023-01-23 03:25:54.903753: step: 1424/526, loss: 0.23872889578342438
2023-01-23 03:25:56.047352: step: 1428/526, loss: 0.6750664114952087
2023-01-23 03:25:57.185925: step: 1432/526, loss: 0.04905061796307564
2023-01-23 03:25:58.354318: step: 1436/526, loss: 0.007182503119111061
2023-01-23 03:25:59.594953: step: 1440/526, loss: 0.07318788021802902
2023-01-23 03:26:00.713368: step: 1444/526, loss: 0.06385822594165802
2023-01-23 03:26:01.838004: step: 1448/526, loss: 8.640289161121473e-05
2023-01-23 03:26:02.979971: step: 1452/526, loss: 0.015682749450206757
2023-01-23 03:26:04.109223: step: 1456/526, loss: 0.0009546280489303172
2023-01-23 03:26:05.265004: step: 1460/526, loss: 0.009378910064697266
2023-01-23 03:26:06.388089: step: 1464/526, loss: 0.056096456944942474
2023-01-23 03:26:07.523962: step: 1468/526, loss: 0.04520893469452858
2023-01-23 03:26:08.644152: step: 1472/526, loss: 0.10247516632080078
2023-01-23 03:26:09.815463: step: 1476/526, loss: 0.02235870435833931
2023-01-23 03:26:10.938118: step: 1480/526, loss: 0.006798172369599342
2023-01-23 03:26:12.075464: step: 1484/526, loss: 0.0004818916495423764
2023-01-23 03:26:13.182135: step: 1488/526, loss: 0.0001104354887502268
2023-01-23 03:26:14.326079: step: 1492/526, loss: 0.00032444001408293843
2023-01-23 03:26:15.453644: step: 1496/526, loss: 0.0039916993118822575
2023-01-23 03:26:16.552585: step: 1500/526, loss: 0.007906818762421608
2023-01-23 03:26:17.684591: step: 1504/526, loss: 0.0018359185196459293
2023-01-23 03:26:18.850551: step: 1508/526, loss: 0.017743302509188652
2023-01-23 03:26:19.984348: step: 1512/526, loss: 0.00039405826828442514
2023-01-23 03:26:21.099718: step: 1516/526, loss: 0.05438556522130966
2023-01-23 03:26:22.262356: step: 1520/526, loss: 0.04722042381763458
2023-01-23 03:26:23.411548: step: 1524/526, loss: 0.003061676165089011
2023-01-23 03:26:24.559447: step: 1528/526, loss: 0.0003373146173544228
2023-01-23 03:26:25.675813: step: 1532/526, loss: 5.4073334467830136e-05
2023-01-23 03:26:26.809012: step: 1536/526, loss: 3.790855407714844e-05
2023-01-23 03:26:27.965275: step: 1540/526, loss: 0.015591240487992764
2023-01-23 03:26:29.083810: step: 1544/526, loss: 0.023667145520448685
2023-01-23 03:26:30.219492: step: 1548/526, loss: 0.0005550384521484375
2023-01-23 03:26:31.346036: step: 1552/526, loss: 0.0005651474348269403
2023-01-23 03:26:32.495801: step: 1556/526, loss: 0.002125549130141735
2023-01-23 03:26:33.609563: step: 1560/526, loss: 0.0041055199690163136
2023-01-23 03:26:34.725591: step: 1564/526, loss: 0.46366769075393677
2023-01-23 03:26:35.890829: step: 1568/526, loss: 0.0003819942648988217
2023-01-23 03:26:37.019533: step: 1572/526, loss: 0.06436386704444885
2023-01-23 03:26:38.148025: step: 1576/526, loss: 0.0013162612449377775
2023-01-23 03:26:39.245474: step: 1580/526, loss: 0.0005640983581542969
2023-01-23 03:26:40.372544: step: 1584/526, loss: 0.0007989883306436241
2023-01-23 03:26:41.559925: step: 1588/526, loss: 0.02109508588910103
2023-01-23 03:26:42.684664: step: 1592/526, loss: 0.0007202147971838713
2023-01-23 03:26:43.834759: step: 1596/526, loss: 0.008037377148866653
2023-01-23 03:26:44.945135: step: 1600/526, loss: 0.0018079758156090975
2023-01-23 03:26:46.109968: step: 1604/526, loss: 0.02293567731976509
2023-01-23 03:26:47.248305: step: 1608/526, loss: 0.00011510848707985133
2023-01-23 03:26:48.390875: step: 1612/526, loss: 0.0007442474598065019
2023-01-23 03:26:49.536174: step: 1616/526, loss: 0.09318371117115021
2023-01-23 03:26:50.672811: step: 1620/526, loss: 0.1565997153520584
2023-01-23 03:26:51.777266: step: 1624/526, loss: 0.0023903846740722656
2023-01-23 03:26:52.926663: step: 1628/526, loss: 5.207061622058973e-05
2023-01-23 03:26:54.063380: step: 1632/526, loss: 0.36484020948410034
2023-01-23 03:26:55.202448: step: 1636/526, loss: 0.04972992092370987
2023-01-23 03:26:56.335057: step: 1640/526, loss: 0.01793498918414116
2023-01-23 03:26:57.463491: step: 1644/526, loss: 0.011297320947051048
2023-01-23 03:26:58.596596: step: 1648/526, loss: 9.5367431640625e-05
2023-01-23 03:26:59.717449: step: 1652/526, loss: 0.034090518951416016
2023-01-23 03:27:00.885621: step: 1656/526, loss: 0.012037324719130993
2023-01-23 03:27:01.999198: step: 1660/526, loss: 0.0037815095856785774
2023-01-23 03:27:03.135145: step: 1664/526, loss: 0.00022306441678665578
2023-01-23 03:27:04.253833: step: 1668/526, loss: 0.020898818969726562
2023-01-23 03:27:05.372093: step: 1672/526, loss: 0.0025756836403161287
2023-01-23 03:27:06.502881: step: 1676/526, loss: 0.0031532763969153166
2023-01-23 03:27:07.640652: step: 1680/526, loss: 0.0014539242256432772
2023-01-23 03:27:08.789029: step: 1684/526, loss: 0.0037601471412926912
2023-01-23 03:27:09.919443: step: 1688/526, loss: 0.03642597422003746
2023-01-23 03:27:11.042023: step: 1692/526, loss: 0.0008725167135708034
2023-01-23 03:27:12.153754: step: 1696/526, loss: 0.0001462936488678679
2023-01-23 03:27:13.273465: step: 1700/526, loss: 0.004838180728256702
2023-01-23 03:27:14.423123: step: 1704/526, loss: 0.008051491342484951
2023-01-23 03:27:15.554476: step: 1708/526, loss: 0.005165672395378351
2023-01-23 03:27:16.692828: step: 1712/526, loss: 0.28592395782470703
2023-01-23 03:27:17.832138: step: 1716/526, loss: 0.02497396431863308
2023-01-23 03:27:18.966542: step: 1720/526, loss: 0.0007458209875039756
2023-01-23 03:27:20.107182: step: 1724/526, loss: 0.0026048661675304174
2023-01-23 03:27:21.220682: step: 1728/526, loss: 0.0004734039248432964
2023-01-23 03:27:22.347300: step: 1732/526, loss: 0.042105820029973984
2023-01-23 03:27:23.494516: step: 1736/526, loss: 8.406638517044485e-05
2023-01-23 03:27:24.616529: step: 1740/526, loss: 0.0004470825369935483
2023-01-23 03:27:25.782658: step: 1744/526, loss: 0.022427940741181374
2023-01-23 03:27:26.906825: step: 1748/526, loss: 0.004199123475700617
2023-01-23 03:27:28.049863: step: 1752/526, loss: 0.0019474030705168843
2023-01-23 03:27:29.184543: step: 1756/526, loss: 0.00014629363431595266
2023-01-23 03:27:30.290001: step: 1760/526, loss: 7.390976406895788e-06
2023-01-23 03:27:31.408981: step: 1764/526, loss: 0.009794902987778187
2023-01-23 03:27:32.554027: step: 1768/526, loss: 0.01474075298756361
2023-01-23 03:27:33.691551: step: 1772/526, loss: 0.00010910034325206652
2023-01-23 03:27:34.814281: step: 1776/526, loss: 0.022666549310088158
2023-01-23 03:27:35.969197: step: 1780/526, loss: 0.00017051697068382055
2023-01-23 03:27:37.091611: step: 1784/526, loss: 5.187988426769152e-05
2023-01-23 03:27:38.244707: step: 1788/526, loss: 0.007553768344223499
2023-01-23 03:27:39.381010: step: 1792/526, loss: 0.07739105075597763
2023-01-23 03:27:40.538647: step: 1796/526, loss: 0.0001371383696096018
2023-01-23 03:27:41.709243: step: 1800/526, loss: 0.001453495118767023
2023-01-23 03:27:42.859121: step: 1804/526, loss: -1.411438006471144e-05
2023-01-23 03:27:43.979589: step: 1808/526, loss: 0.0005991935613565147
2023-01-23 03:27:45.135078: step: 1812/526, loss: 0.0014359474880620837
2023-01-23 03:27:46.275321: step: 1816/526, loss: 5.950928243692033e-05
2023-01-23 03:27:47.388903: step: 1820/526, loss: 0.0008203506586141884
2023-01-23 03:27:48.551991: step: 1824/526, loss: 0.010953378863632679
2023-01-23 03:27:49.674881: step: 1828/526, loss: 0.007882309146225452
2023-01-23 03:27:50.837585: step: 1832/526, loss: 0.0008634567493572831
2023-01-23 03:27:51.949349: step: 1836/526, loss: 0.0004085063992533833
2023-01-23 03:27:53.078636: step: 1840/526, loss: 0.0013549805153161287
2023-01-23 03:27:54.213647: step: 1844/526, loss: 0.011856365948915482
2023-01-23 03:27:55.355866: step: 1848/526, loss: 1.0117520093917847
2023-01-23 03:27:56.487032: step: 1852/526, loss: 0.023229314014315605
2023-01-23 03:27:57.613136: step: 1856/526, loss: 0.00020742416381835938
2023-01-23 03:27:58.760604: step: 1860/526, loss: 0.03857707977294922
2023-01-23 03:27:59.900316: step: 1864/526, loss: 0.0009004116291180253
2023-01-23 03:28:00.997715: step: 1868/526, loss: 0.00024518967256881297
2023-01-23 03:28:02.131447: step: 1872/526, loss: 0.0006789207691326737
2023-01-23 03:28:03.287945: step: 1876/526, loss: 0.003887748811393976
2023-01-23 03:28:04.435470: step: 1880/526, loss: 0.05139608308672905
2023-01-23 03:28:05.561487: step: 1884/526, loss: 0.006644821260124445
2023-01-23 03:28:06.743021: step: 1888/526, loss: 0.035083770751953125
2023-01-23 03:28:07.863426: step: 1892/526, loss: 0.0072428700514137745
2023-01-23 03:28:08.980417: step: 1896/526, loss: 0.004093742463737726
2023-01-23 03:28:10.120756: step: 1900/526, loss: 0.0022306444589048624
2023-01-23 03:28:11.276586: step: 1904/526, loss: 0.06239604949951172
2023-01-23 03:28:12.446655: step: 1908/526, loss: 0.00032558440580032766
2023-01-23 03:28:13.614461: step: 1912/526, loss: 0.07036600261926651
2023-01-23 03:28:14.718730: step: 1916/526, loss: 5.130767749506049e-05
2023-01-23 03:28:15.841708: step: 1920/526, loss: 0.022225569933652878
2023-01-23 03:28:17.008562: step: 1924/526, loss: 0.0007571220048703253
2023-01-23 03:28:18.133865: step: 1928/526, loss: 0.0005041122785769403
2023-01-23 03:28:19.275430: step: 1932/526, loss: 0.0003651142178568989
2023-01-23 03:28:20.424241: step: 1936/526, loss: 0.0773773193359375
2023-01-23 03:28:21.538966: step: 1940/526, loss: 0.016583634540438652
2023-01-23 03:28:22.663982: step: 1944/526, loss: 0.0005136490217410028
2023-01-23 03:28:23.784144: step: 1948/526, loss: 0.000676918076351285
2023-01-23 03:28:24.907418: step: 1952/526, loss: 0.0316162109375
2023-01-23 03:28:26.060103: step: 1956/526, loss: 0.007002830505371094
2023-01-23 03:28:27.217050: step: 1960/526, loss: 0.016753101721405983
2023-01-23 03:28:28.342721: step: 1964/526, loss: 0.03154182434082031
2023-01-23 03:28:29.477739: step: 1968/526, loss: 2.7751922971219756e-05
2023-01-23 03:28:30.631770: step: 1972/526, loss: 0.00022759436978958547
2023-01-23 03:28:31.773781: step: 1976/526, loss: 0.009221648797392845
2023-01-23 03:28:32.917952: step: 1980/526, loss: 0.003183126449584961
2023-01-23 03:28:34.035914: step: 1984/526, loss: 0.0009048461797647178
2023-01-23 03:28:35.173103: step: 1988/526, loss: 0.001155090401880443
2023-01-23 03:28:36.310265: step: 1992/526, loss: 0.0022377970162779093
2023-01-23 03:28:37.407027: step: 1996/526, loss: 0.0015698432689532638
2023-01-23 03:28:38.554543: step: 2000/526, loss: 0.004531955812126398
2023-01-23 03:28:39.723805: step: 2004/526, loss: 0.00027027129544876516
2023-01-23 03:28:40.860542: step: 2008/526, loss: 0.05013151094317436
2023-01-23 03:28:41.995204: step: 2012/526, loss: 0.023787595331668854
2023-01-23 03:28:43.178730: step: 2016/526, loss: 0.017963409423828125
2023-01-23 03:28:44.284565: step: 2020/526, loss: 0.01220550574362278
2023-01-23 03:28:45.422613: step: 2024/526, loss: 0.0020858377683907747
2023-01-23 03:28:46.528406: step: 2028/526, loss: 8.335113670909777e-05
2023-01-23 03:28:47.702349: step: 2032/526, loss: 0.0033470632042735815
2023-01-23 03:28:48.802961: step: 2036/526, loss: 0.0022212981712073088
2023-01-23 03:28:49.932231: step: 2040/526, loss: 0.000404548627557233
2023-01-23 03:28:51.040440: step: 2044/526, loss: 3.1948089599609375e-05
2023-01-23 03:28:52.170977: step: 2048/526, loss: 0.0012963295448571444
2023-01-23 03:28:53.335053: step: 2052/526, loss: 0.0009089470258913934
2023-01-23 03:28:54.485643: step: 2056/526, loss: 0.0011604309547692537
2023-01-23 03:28:55.605196: step: 2060/526, loss: 0.0005937576061114669
2023-01-23 03:28:56.731404: step: 2064/526, loss: 0.030721569433808327
2023-01-23 03:28:57.852812: step: 2068/526, loss: 0.0628567710518837
2023-01-23 03:28:58.990554: step: 2072/526, loss: 0.00010251998173771426
2023-01-23 03:29:00.130106: step: 2076/526, loss: 0.0002650260867085308
2023-01-23 03:29:01.247804: step: 2080/526, loss: 2.3508071535616182e-05
2023-01-23 03:29:02.378019: step: 2084/526, loss: 0.004207802005112171
2023-01-23 03:29:03.512402: step: 2088/526, loss: 0.027065325528383255
2023-01-23 03:29:04.674773: step: 2092/526, loss: 0.0002834320184774697
2023-01-23 03:29:05.815693: step: 2096/526, loss: 0.00039920807466842234
2023-01-23 03:29:06.944104: step: 2100/526, loss: 0.0002849579032044858
2023-01-23 03:29:08.079026: step: 2104/526, loss: 8.926392183639109e-05
==================================================
Loss: 0.020
--------------------
Dev: {'event': {'p': 0.5920245398773006, 'r': 0.7709720372836218, 'f1': 0.6697513013302487}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Test: {'event': {'p': 0.6204047914085089, 'r': 0.7839248434237995, 'f1': 0.6926446852663132}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Chinese: {'event': {'p': 0.573170731707317, 'r': 0.8703703703703703, 'f1': 0.6911764705882353}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Korean: {'event': {'p': 0.6170212765957447, 'r': 0.4603174603174603, 'f1': 0.5272727272727272}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Russian: {'event': {'p': 0.45652173913043476, 'r': 0.5833333333333334, 'f1': 0.5121951219512195}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6389811738648948, 'r': 0.7683089214380826, 'f1': 0.6977025392986699}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Eng Test for Chinese: {'event': {'p': 0.6328626444159179, 'r': 0.7719206680584552, 'f1': 0.6955090524335763}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Sample Chinese: {'event': {'p': 0.6282051282051282, 'r': 0.9074074074074074, 'f1': 0.7424242424242423}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6257995735607675, 'r': 0.7816245006657789, 'f1': 0.6950858496151568}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Eng Test for Korean: {'event': {'p': 0.623113410952997, 'r': 0.7541753653444676, 'f1': 0.6824085005903188}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Sample Korean: {'event': {'p': 0.7446808510638298, 'r': 0.5555555555555556, 'f1': 0.6363636363636364}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5800575263662512, 'r': 0.8055925432756325, 'f1': 0.6744704570791527}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
Eng Test for Russian: {'event': {'p': 0.5962534874451972, 'r': 0.7807933194154488, 'f1': 0.6761581920903954}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
Sample Russian: {'event': {'p': 0.48936170212765956, 'r': 0.6388888888888888, 'f1': 0.5542168674698795}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
******************************
Epoch: 23
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 03:29:51.065106: step: 4/526, loss: 0.004995489027351141
2023-01-23 03:29:52.180147: step: 8/526, loss: 0.00027647020760923624
2023-01-23 03:29:53.304287: step: 12/526, loss: 0.0015367508167400956
2023-01-23 03:29:54.449941: step: 16/526, loss: 0.06378059834241867
2023-01-23 03:29:55.579070: step: 20/526, loss: 4.5490269258152694e-05
2023-01-23 03:29:56.736607: step: 24/526, loss: 0.02482783794403076
2023-01-23 03:29:57.876683: step: 28/526, loss: 0.00034933091956190765
2023-01-23 03:29:59.010389: step: 32/526, loss: 0.013775492087006569
2023-01-23 03:30:00.147102: step: 36/526, loss: 0.01672840118408203
2023-01-23 03:30:01.280897: step: 40/526, loss: 0.001422977540642023
2023-01-23 03:30:02.431490: step: 44/526, loss: 0.0017678738804534078
2023-01-23 03:30:03.578600: step: 48/526, loss: 0.0004125595442019403
2023-01-23 03:30:04.698193: step: 52/526, loss: 0.0027025220915675163
2023-01-23 03:30:05.862686: step: 56/526, loss: 0.000676059746183455
2023-01-23 03:30:07.017110: step: 60/526, loss: 0.0004665374872274697
2023-01-23 03:30:08.147550: step: 64/526, loss: 0.08500690758228302
2023-01-23 03:30:09.242845: step: 68/526, loss: 0.0008096694946289062
2023-01-23 03:30:10.368023: step: 72/526, loss: 0.03862740099430084
2023-01-23 03:30:11.515299: step: 76/526, loss: 0.004749011714011431
2023-01-23 03:30:12.685233: step: 80/526, loss: 0.024715041741728783
2023-01-23 03:30:13.813707: step: 84/526, loss: 0.00031595228938385844
2023-01-23 03:30:14.923736: step: 88/526, loss: 0.14136847853660583
2023-01-23 03:30:16.088439: step: 92/526, loss: 0.0005692958948202431
2023-01-23 03:30:17.218191: step: 96/526, loss: 0.00046720507089048624
2023-01-23 03:30:18.376953: step: 100/526, loss: 0.002639675047248602
2023-01-23 03:30:19.509147: step: 104/526, loss: 0.00017113685316871852
2023-01-23 03:30:20.658258: step: 108/526, loss: 0.00014209747314453125
2023-01-23 03:30:21.802515: step: 112/526, loss: 0.0005893707275390625
2023-01-23 03:30:22.930751: step: 116/526, loss: 0.0042701722122728825
2023-01-23 03:30:24.082296: step: 120/526, loss: 0.023633575066924095
2023-01-23 03:30:25.222538: step: 124/526, loss: 0.04454836994409561
2023-01-23 03:30:26.381426: step: 128/526, loss: 0.1259869933128357
2023-01-23 03:30:27.504937: step: 132/526, loss: 0.016383077949285507
2023-01-23 03:30:28.631082: step: 136/526, loss: 0.0038488388527184725
2023-01-23 03:30:29.782347: step: 140/526, loss: 0.00481073884293437
2023-01-23 03:30:30.910674: step: 144/526, loss: 0.0006084441556595266
2023-01-23 03:30:32.050087: step: 148/526, loss: 0.02895202673971653
2023-01-23 03:30:33.194470: step: 152/526, loss: 0.016843700781464577
2023-01-23 03:30:34.334555: step: 156/526, loss: 0.009022139944136143
2023-01-23 03:30:35.501167: step: 160/526, loss: 0.04529685899615288
2023-01-23 03:30:36.706451: step: 164/526, loss: 0.002326106885448098
2023-01-23 03:30:37.866406: step: 168/526, loss: 0.0005415916675701737
2023-01-23 03:30:38.989298: step: 172/526, loss: 0.009449243545532227
2023-01-23 03:30:40.137294: step: 176/526, loss: 0.01536102220416069
2023-01-23 03:30:41.261917: step: 180/526, loss: 0.0008292198181152344
2023-01-23 03:30:42.410976: step: 184/526, loss: 0.018462562933564186
2023-01-23 03:30:43.524496: step: 188/526, loss: 0.002765655517578125
2023-01-23 03:30:44.639265: step: 192/526, loss: 0.00808868370950222
2023-01-23 03:30:45.784917: step: 196/526, loss: 0.0014797210460528731
2023-01-23 03:30:46.908181: step: 200/526, loss: 0.0010051727294921875
2023-01-23 03:30:48.048615: step: 204/526, loss: 4.444122168933973e-05
2023-01-23 03:30:49.179588: step: 208/526, loss: 0.007484245114028454
2023-01-23 03:30:50.302723: step: 212/526, loss: 0.0037946701049804688
2023-01-23 03:30:51.442502: step: 216/526, loss: 0.013715839944779873
2023-01-23 03:30:52.572005: step: 220/526, loss: 0.007614707574248314
2023-01-23 03:30:53.719124: step: 224/526, loss: 0.023600006476044655
2023-01-23 03:30:54.836515: step: 228/526, loss: 0.0019225120777264237
2023-01-23 03:30:55.987335: step: 232/526, loss: 0.012050151824951172
2023-01-23 03:30:57.108263: step: 236/526, loss: 0.00013294219388626516
2023-01-23 03:30:58.244622: step: 240/526, loss: 0.0009471892844885588
2023-01-23 03:30:59.375611: step: 244/526, loss: 0.00407066335901618
2023-01-23 03:31:00.530952: step: 248/526, loss: 0.0004299163701944053
2023-01-23 03:31:01.665841: step: 252/526, loss: 0.012555313296616077
2023-01-23 03:31:02.786555: step: 256/526, loss: 0.04630317538976669
2023-01-23 03:31:03.895916: step: 260/526, loss: 0.002934694290161133
2023-01-23 03:31:05.021743: step: 264/526, loss: 0.07266712188720703
2023-01-23 03:31:06.183001: step: 268/526, loss: 0.0003631591680459678
2023-01-23 03:31:07.290892: step: 272/526, loss: 0.019245052710175514
2023-01-23 03:31:08.407548: step: 276/526, loss: 0.0011472702026367188
2023-01-23 03:31:09.556031: step: 280/526, loss: 0.0005469322204589844
2023-01-23 03:31:10.693704: step: 284/526, loss: 0.02994556538760662
2023-01-23 03:31:11.850929: step: 288/526, loss: 0.006078099831938744
2023-01-23 03:31:12.999590: step: 292/526, loss: 0.05078592523932457
2023-01-23 03:31:14.125057: step: 296/526, loss: 0.0004914283636026084
2023-01-23 03:31:15.252655: step: 300/526, loss: 0.00041999819222837687
2023-01-23 03:31:16.379341: step: 304/526, loss: 0.0035699845757335424
2023-01-23 03:31:17.538005: step: 308/526, loss: 0.006222724914550781
2023-01-23 03:31:18.678882: step: 312/526, loss: 0.009252166375517845
2023-01-23 03:31:19.837015: step: 316/526, loss: 0.00013742447481490672
2023-01-23 03:31:20.954156: step: 320/526, loss: 0.01678619347512722
2023-01-23 03:31:22.100813: step: 324/526, loss: 5.626678466796875e-05
2023-01-23 03:31:23.232801: step: 328/526, loss: 1.7166139514301904e-06
2023-01-23 03:31:24.338195: step: 332/526, loss: 9.822846186580136e-05
2023-01-23 03:31:25.451362: step: 336/526, loss: 0.00018215179443359375
2023-01-23 03:31:26.602967: step: 340/526, loss: 0.00020189284987282008
2023-01-23 03:31:27.744999: step: 344/526, loss: 0.005839729681611061
2023-01-23 03:31:28.923189: step: 348/526, loss: 0.00021705626568291336
2023-01-23 03:31:30.079866: step: 352/526, loss: 7.629394644936838e-07
2023-01-23 03:31:31.212113: step: 356/526, loss: 0.0013200759422034025
2023-01-23 03:31:32.375987: step: 360/526, loss: 0.010667610913515091
2023-01-23 03:31:33.492684: step: 364/526, loss: 0.007733345031738281
2023-01-23 03:31:34.609007: step: 368/526, loss: 0.024980831891298294
2023-01-23 03:31:35.765644: step: 372/526, loss: 0.0006782531854696572
2023-01-23 03:31:36.909690: step: 376/526, loss: 0.023363113403320312
2023-01-23 03:31:38.035270: step: 380/526, loss: 0.00031976698664948344
2023-01-23 03:31:39.186923: step: 384/526, loss: 0.00013618469529319555
2023-01-23 03:31:40.320700: step: 388/526, loss: 0.019942427054047585
2023-01-23 03:31:41.442379: step: 392/526, loss: 0.0007611275068484247
2023-01-23 03:31:42.579453: step: 396/526, loss: 0.004407405853271484
2023-01-23 03:31:43.702510: step: 400/526, loss: 0.0009386062738485634
2023-01-23 03:31:44.862175: step: 404/526, loss: 3.166198803228326e-05
2023-01-23 03:31:46.006074: step: 408/526, loss: 0.07454881072044373
2023-01-23 03:31:47.139695: step: 412/526, loss: 0.0027969360817223787
2023-01-23 03:31:48.241111: step: 416/526, loss: 0.003816795302554965
2023-01-23 03:31:49.376289: step: 420/526, loss: 0.00043487548828125
2023-01-23 03:31:50.490334: step: 424/526, loss: 0.002858400344848633
2023-01-23 03:31:51.668960: step: 428/526, loss: 3.776550147449598e-05
2023-01-23 03:31:52.796314: step: 432/526, loss: 0.004890060517936945
2023-01-23 03:31:53.932055: step: 436/526, loss: 0.0008033752674236894
2023-01-23 03:31:55.065969: step: 440/526, loss: 0.0015236377948895097
2023-01-23 03:31:56.203898: step: 444/526, loss: 0.023052215576171875
2023-01-23 03:31:57.335843: step: 448/526, loss: 0.026891136541962624
2023-01-23 03:31:58.453112: step: 452/526, loss: 0.0019168853759765625
2023-01-23 03:31:59.627710: step: 456/526, loss: 0.05372047424316406
2023-01-23 03:32:00.760971: step: 460/526, loss: 2.365112231927924e-05
2023-01-23 03:32:01.910499: step: 464/526, loss: 5.3691863286076114e-05
2023-01-23 03:32:03.023698: step: 468/526, loss: 0.0008518219692632556
2023-01-23 03:32:04.147865: step: 472/526, loss: 0.05989604443311691
2023-01-23 03:32:05.278524: step: 476/526, loss: 0.04166469722986221
2023-01-23 03:32:06.430219: step: 480/526, loss: 0.051915835589170456
2023-01-23 03:32:07.549547: step: 484/526, loss: 0.005378532223403454
2023-01-23 03:32:08.676650: step: 488/526, loss: 0.013560676947236061
2023-01-23 03:32:09.814405: step: 492/526, loss: 0.001990890596061945
2023-01-23 03:32:10.972349: step: 496/526, loss: 0.0232830997556448
2023-01-23 03:32:12.093318: step: 500/526, loss: 0.00031909943209029734
2023-01-23 03:32:13.241685: step: 504/526, loss: 0.011682510375976562
2023-01-23 03:32:14.338356: step: 508/526, loss: 0.02809171751141548
2023-01-23 03:32:15.501549: step: 512/526, loss: 0.04712257161736488
2023-01-23 03:32:16.653792: step: 516/526, loss: 0.07752871513366699
2023-01-23 03:32:17.761653: step: 520/526, loss: 0.0003688812430482358
2023-01-23 03:32:18.895346: step: 524/526, loss: 0.0041211131028831005
2023-01-23 03:32:20.016471: step: 528/526, loss: 0.0012222289806231856
2023-01-23 03:32:21.182536: step: 532/526, loss: 0.0576297789812088
2023-01-23 03:32:22.304522: step: 536/526, loss: 0.006798172369599342
2023-01-23 03:32:23.433514: step: 540/526, loss: 0.02004213258624077
2023-01-23 03:32:24.564172: step: 544/526, loss: 0.023140907287597656
2023-01-23 03:32:25.735277: step: 548/526, loss: 0.0010047436226159334
2023-01-23 03:32:26.876344: step: 552/526, loss: 1.068115216185106e-05
2023-01-23 03:32:27.977855: step: 556/526, loss: 0.00013217926607467234
2023-01-23 03:32:29.080389: step: 560/526, loss: 0.00028266909066587687
2023-01-23 03:32:30.228232: step: 564/526, loss: 0.0017215728294104338
2023-01-23 03:32:31.408701: step: 568/526, loss: 0.0007062911754474044
2023-01-23 03:32:32.556427: step: 572/526, loss: 0.00015115737915039062
2023-01-23 03:32:33.670434: step: 576/526, loss: 1.220703143189894e-05
2023-01-23 03:32:34.799236: step: 580/526, loss: -3.280639793956652e-05
2023-01-23 03:32:35.930591: step: 584/526, loss: 0.00160560617223382
2023-01-23 03:32:37.068291: step: 588/526, loss: 0.00043239592923782766
2023-01-23 03:32:38.204412: step: 592/526, loss: 0.017119886353611946
2023-01-23 03:32:39.344455: step: 596/526, loss: 0.0004044532834086567
2023-01-23 03:32:40.460012: step: 600/526, loss: 0.020192433148622513
2023-01-23 03:32:41.571281: step: 604/526, loss: 0.023328544571995735
2023-01-23 03:32:42.681300: step: 608/526, loss: 0.0003105163632426411
2023-01-23 03:32:43.826368: step: 612/526, loss: 0.003456688020378351
2023-01-23 03:32:44.948713: step: 616/526, loss: 0.0010906219249591231
2023-01-23 03:32:46.086490: step: 620/526, loss: 0.0527406707406044
2023-01-23 03:32:47.217119: step: 624/526, loss: 0.004522228147834539
2023-01-23 03:32:48.389571: step: 628/526, loss: 0.021945619955658913
2023-01-23 03:32:49.558132: step: 632/526, loss: 0.0007540702936239541
2023-01-23 03:32:50.657182: step: 636/526, loss: 6.608963303733617e-05
2023-01-23 03:32:51.807679: step: 640/526, loss: 0.014848614111542702
2023-01-23 03:32:52.946803: step: 644/526, loss: 0.0002599715953692794
2023-01-23 03:32:54.082595: step: 648/526, loss: 0.0009558200836181641
2023-01-23 03:32:55.228213: step: 652/526, loss: 0.0023431777954101562
2023-01-23 03:32:56.365764: step: 656/526, loss: 0.00024509429931640625
2023-01-23 03:32:57.524547: step: 660/526, loss: -1.0490416570974048e-06
2023-01-23 03:32:58.681209: step: 664/526, loss: 0.002943706465885043
2023-01-23 03:32:59.829718: step: 668/526, loss: 0.0008965492015704513
2023-01-23 03:33:00.982721: step: 672/526, loss: 0.0004547119315247983
2023-01-23 03:33:02.121374: step: 676/526, loss: 3.166198803228326e-05
2023-01-23 03:33:03.271614: step: 680/526, loss: 0.00245418562553823
2023-01-23 03:33:04.401515: step: 684/526, loss: 0.046572305262088776
2023-01-23 03:33:05.534070: step: 688/526, loss: 0.023625563830137253
2023-01-23 03:33:06.636834: step: 692/526, loss: 0.012465858832001686
2023-01-23 03:33:07.779287: step: 696/526, loss: 0.07640743255615234
2023-01-23 03:33:08.902833: step: 700/526, loss: 0.015327739529311657
2023-01-23 03:33:10.029558: step: 704/526, loss: 0.01274871826171875
2023-01-23 03:33:11.142016: step: 708/526, loss: 8.850097947288305e-05
2023-01-23 03:33:12.284172: step: 712/526, loss: 2.593994213384576e-05
2023-01-23 03:33:13.429953: step: 716/526, loss: 0.04666538164019585
2023-01-23 03:33:14.618116: step: 720/526, loss: 0.0005118369590491056
2023-01-23 03:33:15.760480: step: 724/526, loss: 0.0012772560585290194
2023-01-23 03:33:16.895518: step: 728/526, loss: 0.033873654901981354
2023-01-23 03:33:18.039080: step: 732/526, loss: 0.001488494803197682
2023-01-23 03:33:19.189121: step: 736/526, loss: 0.006680202670395374
2023-01-23 03:33:20.341552: step: 740/526, loss: 0.09278898686170578
2023-01-23 03:33:21.496338: step: 744/526, loss: 0.007106018252670765
2023-01-23 03:33:22.637943: step: 748/526, loss: 0.0015020847786217928
2023-01-23 03:33:23.772760: step: 752/526, loss: 0.008099175058305264
2023-01-23 03:33:24.883108: step: 756/526, loss: 0.02871551550924778
2023-01-23 03:33:26.034175: step: 760/526, loss: 0.05673703923821449
2023-01-23 03:33:27.173209: step: 764/526, loss: 0.0018929005600512028
2023-01-23 03:33:28.303743: step: 768/526, loss: 7.80105619924143e-05
2023-01-23 03:33:29.456779: step: 772/526, loss: 0.0005279541364870965
2023-01-23 03:33:30.608227: step: 776/526, loss: 0.00011672973778331652
2023-01-23 03:33:31.754146: step: 780/526, loss: 0.009870147332549095
2023-01-23 03:33:32.867978: step: 784/526, loss: 0.0007446289528161287
2023-01-23 03:33:34.003696: step: 788/526, loss: 0.0004868507385253906
2023-01-23 03:33:35.153773: step: 792/526, loss: 0.005836391821503639
2023-01-23 03:33:36.310953: step: 796/526, loss: 0.0003986358642578125
2023-01-23 03:33:37.472325: step: 800/526, loss: 0.0921657532453537
2023-01-23 03:33:38.602185: step: 804/526, loss: 3.604888843256049e-05
2023-01-23 03:33:39.755650: step: 808/526, loss: 0.010436106473207474
2023-01-23 03:33:40.904173: step: 812/526, loss: 0.07317447662353516
2023-01-23 03:33:42.042461: step: 816/526, loss: 2.4700166250113398e-05
2023-01-23 03:33:43.171913: step: 820/526, loss: 0.0016826629871502519
2023-01-23 03:33:44.325003: step: 824/526, loss: 0.0030189515091478825
2023-01-23 03:33:45.452863: step: 828/526, loss: 1.926422191900201e-05
2023-01-23 03:33:46.590005: step: 832/526, loss: 0.012021971866488457
2023-01-23 03:33:47.692670: step: 836/526, loss: 0.004403495695441961
2023-01-23 03:33:48.817221: step: 840/526, loss: 1.316070574830519e-05
2023-01-23 03:33:49.934918: step: 844/526, loss: 0.0027968406211584806
2023-01-23 03:33:51.045719: step: 848/526, loss: 0.00020885467529296875
2023-01-23 03:33:52.177233: step: 852/526, loss: 0.0009811401832848787
2023-01-23 03:33:53.326932: step: 856/526, loss: -1.182556115963962e-05
2023-01-23 03:33:54.451625: step: 860/526, loss: 0.007063866127282381
2023-01-23 03:33:55.574296: step: 864/526, loss: 2.231597864010837e-05
2023-01-23 03:33:56.707762: step: 868/526, loss: 0.008090972900390625
2023-01-23 03:33:57.849077: step: 872/526, loss: 0.05535387992858887
2023-01-23 03:33:58.984370: step: 876/526, loss: 0.000846481358166784
2023-01-23 03:34:00.117506: step: 880/526, loss: 0.004799842834472656
2023-01-23 03:34:01.257677: step: 884/526, loss: 0.0028884888160973787
2023-01-23 03:34:02.390875: step: 888/526, loss: 0.002346038818359375
2023-01-23 03:34:03.501505: step: 892/526, loss: 0.0571783073246479
2023-01-23 03:34:04.626235: step: 896/526, loss: 0.00010061264038085938
2023-01-23 03:34:05.749699: step: 900/526, loss: 0.005844783969223499
2023-01-23 03:34:06.862056: step: 904/526, loss: 2.5272368020523572e-06
2023-01-23 03:34:07.983825: step: 908/526, loss: 0.029066849499940872
2023-01-23 03:34:09.110065: step: 912/526, loss: 0.03276043012738228
2023-01-23 03:34:10.249910: step: 916/526, loss: 0.0020089149475097656
2023-01-23 03:34:11.406422: step: 920/526, loss: 0.00017299651517532766
2023-01-23 03:34:12.571615: step: 924/526, loss: 1.430511474609375e-06
2023-01-23 03:34:13.717617: step: 928/526, loss: 0.01763172261416912
2023-01-23 03:34:14.880480: step: 932/526, loss: 0.02422161214053631
2023-01-23 03:34:16.012247: step: 936/526, loss: 0.07827749848365784
2023-01-23 03:34:17.146990: step: 940/526, loss: 0.006887365132570267
2023-01-23 03:34:18.262389: step: 944/526, loss: 4.234314110362902e-05
2023-01-23 03:34:19.372135: step: 948/526, loss: 0.0005025863647460938
2023-01-23 03:34:20.498815: step: 952/526, loss: 0.022162437438964844
2023-01-23 03:34:21.671421: step: 956/526, loss: 0.011558962054550648
2023-01-23 03:34:22.800906: step: 960/526, loss: -5.34057608092553e-06
2023-01-23 03:34:23.918525: step: 964/526, loss: 0.006871223449707031
2023-01-23 03:34:25.054781: step: 968/526, loss: 0.31347334384918213
2023-01-23 03:34:26.171170: step: 972/526, loss: 0.002418327145278454
2023-01-23 03:34:27.262757: step: 976/526, loss: 0.0009500504238530993
2023-01-23 03:34:28.411192: step: 980/526, loss: 0.00171241769567132
2023-01-23 03:34:29.555864: step: 984/526, loss: 0.0006884574540890753
2023-01-23 03:34:30.728985: step: 988/526, loss: 0.0013051987625658512
2023-01-23 03:34:31.885826: step: 992/526, loss: 0.005212021060287952
2023-01-23 03:34:32.992778: step: 996/526, loss: 0.003074789186939597
2023-01-23 03:34:34.140946: step: 1000/526, loss: 0.02366046980023384
2023-01-23 03:34:35.281199: step: 1004/526, loss: 0.029489515349268913
2023-01-23 03:34:36.405574: step: 1008/526, loss: 8.535384949936997e-06
2023-01-23 03:34:37.521501: step: 1012/526, loss: 0.010569954290986061
2023-01-23 03:34:38.656312: step: 1016/526, loss: 0.009633922018110752
2023-01-23 03:34:39.788585: step: 1020/526, loss: 0.005270099733024836
2023-01-23 03:34:40.935856: step: 1024/526, loss: 0.03340597450733185
2023-01-23 03:34:42.063589: step: 1028/526, loss: 2.6226043701171875e-05
2023-01-23 03:34:43.203023: step: 1032/526, loss: 0.0009810447227209806
2023-01-23 03:34:44.358221: step: 1036/526, loss: 0.3842960298061371
2023-01-23 03:34:45.536942: step: 1040/526, loss: 0.006016159430146217
2023-01-23 03:34:46.677001: step: 1044/526, loss: 8.125305612338707e-05
2023-01-23 03:34:47.814050: step: 1048/526, loss: 0.0012985230423510075
2023-01-23 03:34:48.955559: step: 1052/526, loss: 0.0002464294375386089
2023-01-23 03:34:50.097366: step: 1056/526, loss: 0.004669857211410999
2023-01-23 03:34:51.217181: step: 1060/526, loss: 0.0007157326326705515
2023-01-23 03:34:52.364040: step: 1064/526, loss: 0.03144645690917969
2023-01-23 03:34:53.479297: step: 1068/526, loss: 0.011163617484271526
2023-01-23 03:34:54.634617: step: 1072/526, loss: 0.04239053651690483
2023-01-23 03:34:55.762234: step: 1076/526, loss: 0.03916988521814346
2023-01-23 03:34:56.899816: step: 1080/526, loss: 0.0012094498379155993
2023-01-23 03:34:58.024781: step: 1084/526, loss: 5.760193016612902e-05
2023-01-23 03:34:59.148198: step: 1088/526, loss: 0.00014019012451171875
2023-01-23 03:35:00.249113: step: 1092/526, loss: 3.8480757211800665e-05
2023-01-23 03:35:01.382090: step: 1096/526, loss: 0.0001485824614064768
2023-01-23 03:35:02.515831: step: 1100/526, loss: 9.202957153320312e-05
2023-01-23 03:35:03.629422: step: 1104/526, loss: 0.010206985287368298
2023-01-23 03:35:04.741088: step: 1108/526, loss: 0.001665306044742465
2023-01-23 03:35:05.880012: step: 1112/526, loss: 3.261566234868951e-05
2023-01-23 03:35:07.020177: step: 1116/526, loss: 9.369850886287168e-06
2023-01-23 03:35:08.151060: step: 1120/526, loss: 0.050013162195682526
2023-01-23 03:35:09.278126: step: 1124/526, loss: 0.05823250114917755
2023-01-23 03:35:10.418880: step: 1128/526, loss: 0.02266078069806099
2023-01-23 03:35:11.535033: step: 1132/526, loss: 0.0002397537318756804
2023-01-23 03:35:12.656183: step: 1136/526, loss: 0.0002952575741801411
2023-01-23 03:35:13.794876: step: 1140/526, loss: 0.00010452270362293348
2023-01-23 03:35:14.924466: step: 1144/526, loss: 1.0395049685030244e-05
2023-01-23 03:35:16.071756: step: 1148/526, loss: 0.00023469925508834422
2023-01-23 03:35:17.205887: step: 1152/526, loss: 0.00027751922607421875
2023-01-23 03:35:18.299482: step: 1156/526, loss: 6.67572021484375e-06
2023-01-23 03:35:19.433953: step: 1160/526, loss: 0.003107452532276511
2023-01-23 03:35:20.580068: step: 1164/526, loss: 0.0003467559872660786
2023-01-23 03:35:21.735338: step: 1168/526, loss: 0.0020801543723791838
2023-01-23 03:35:22.908491: step: 1172/526, loss: 0.00515360850840807
2023-01-23 03:35:24.059706: step: 1176/526, loss: 0.002410888671875
2023-01-23 03:35:25.169501: step: 1180/526, loss: 2.3555756342830136e-05
2023-01-23 03:35:26.318144: step: 1184/526, loss: 1.9073486328125e-05
2023-01-23 03:35:27.452272: step: 1188/526, loss: 0.00010356902930652723
2023-01-23 03:35:28.586897: step: 1192/526, loss: 0.0003186225949320942
2023-01-23 03:35:29.733413: step: 1196/526, loss: 0.005884647369384766
2023-01-23 03:35:30.871558: step: 1200/526, loss: 6.008148193359375e-05
2023-01-23 03:35:32.016215: step: 1204/526, loss: 4.00543212890625e-05
2023-01-23 03:35:33.174129: step: 1208/526, loss: 0.004184532444924116
2023-01-23 03:35:34.297769: step: 1212/526, loss: 0.004657554440200329
2023-01-23 03:35:35.430744: step: 1216/526, loss: 0.0033084871247410774
2023-01-23 03:35:36.580888: step: 1220/526, loss: 0.0008123398292809725
2023-01-23 03:35:37.748816: step: 1224/526, loss: 0.00013704299635719508
2023-01-23 03:35:38.882684: step: 1228/526, loss: 0.0007137298816815019
2023-01-23 03:35:40.006764: step: 1232/526, loss: 0.0443572998046875
2023-01-23 03:35:41.113730: step: 1236/526, loss: 0.00747184781357646
2023-01-23 03:35:42.284658: step: 1240/526, loss: 0.012370300479233265
2023-01-23 03:35:43.413705: step: 1244/526, loss: 0.07369355857372284
2023-01-23 03:35:44.528632: step: 1248/526, loss: 0.030431175604462624
2023-01-23 03:35:45.683818: step: 1252/526, loss: 5.035400317865424e-05
2023-01-23 03:35:46.895325: step: 1256/526, loss: 0.009019088931381702
2023-01-23 03:35:48.044271: step: 1260/526, loss: 0.0035072327591478825
2023-01-23 03:35:49.172431: step: 1264/526, loss: 0.0009922027820721269
2023-01-23 03:35:50.292338: step: 1268/526, loss: 0.01670055463910103
2023-01-23 03:35:51.432862: step: 1272/526, loss: 0.0004646301385946572
2023-01-23 03:35:52.589241: step: 1276/526, loss: 0.02537689357995987
2023-01-23 03:35:53.728522: step: 1280/526, loss: 0.0001780986785888672
2023-01-23 03:35:54.853416: step: 1284/526, loss: 0.0008717536693438888
2023-01-23 03:35:55.977945: step: 1288/526, loss: 0.010530662722885609
2023-01-23 03:35:57.153866: step: 1292/526, loss: 0.0009741783142089844
2023-01-23 03:35:58.281141: step: 1296/526, loss: 0.03679867088794708
2023-01-23 03:35:59.418216: step: 1300/526, loss: 0.003546428866684437
2023-01-23 03:36:00.540807: step: 1304/526, loss: 7.667541649425402e-05
2023-01-23 03:36:01.673700: step: 1308/526, loss: 0.039972878992557526
2023-01-23 03:36:02.830623: step: 1312/526, loss: 6.182193465065211e-05
2023-01-23 03:36:03.988467: step: 1316/526, loss: 0.0005231857649050653
2023-01-23 03:36:05.140438: step: 1320/526, loss: 0.11816863715648651
2023-01-23 03:36:06.270420: step: 1324/526, loss: 0.14015941321849823
2023-01-23 03:36:07.389707: step: 1328/526, loss: 0.006325960624963045
2023-01-23 03:36:08.553715: step: 1332/526, loss: 0.0002244949428131804
2023-01-23 03:36:09.681215: step: 1336/526, loss: 0.0004566192801576108
2023-01-23 03:36:10.818213: step: 1340/526, loss: 0.009648323059082031
2023-01-23 03:36:11.964449: step: 1344/526, loss: 0.00038394928560592234
2023-01-23 03:36:13.087450: step: 1348/526, loss: 0.0013529777061194181
2023-01-23 03:36:14.245634: step: 1352/526, loss: 0.07061338424682617
2023-01-23 03:36:15.401535: step: 1356/526, loss: 0.007945633493363857
2023-01-23 03:36:16.545110: step: 1360/526, loss: 2.5415420168428682e-05
2023-01-23 03:36:17.658486: step: 1364/526, loss: 0.0037233352195471525
2023-01-23 03:36:18.821078: step: 1368/526, loss: 0.033083345741033554
2023-01-23 03:36:19.965273: step: 1372/526, loss: 0.001010894775390625
2023-01-23 03:36:21.098458: step: 1376/526, loss: 0.00030393601628020406
2023-01-23 03:36:22.240977: step: 1380/526, loss: 4.806518700206652e-05
2023-01-23 03:36:23.393903: step: 1384/526, loss: 0.0007904052617959678
2023-01-23 03:36:24.531529: step: 1388/526, loss: 0.06448288261890411
2023-01-23 03:36:25.664076: step: 1392/526, loss: 0.008920097723603249
2023-01-23 03:36:26.770393: step: 1396/526, loss: 0.001951885293237865
2023-01-23 03:36:27.886772: step: 1400/526, loss: 0.0010952949523925781
2023-01-23 03:36:29.037328: step: 1404/526, loss: 7.45773286325857e-05
2023-01-23 03:36:30.133685: step: 1408/526, loss: 0.012462139129638672
2023-01-23 03:36:31.318031: step: 1412/526, loss: 0.08644609153270721
2023-01-23 03:36:32.462218: step: 1416/526, loss: 0.00010337829735362902
2023-01-23 03:36:33.600470: step: 1420/526, loss: 0.05374488607048988
2023-01-23 03:36:34.711875: step: 1424/526, loss: 0.0050987242721021175
2023-01-23 03:36:35.814266: step: 1428/526, loss: 0.043480873107910156
2023-01-23 03:36:36.955141: step: 1432/526, loss: 0.0016631126636639237
2023-01-23 03:36:38.098174: step: 1436/526, loss: 0.0013042449718341231
2023-01-23 03:36:39.240378: step: 1440/526, loss: 0.0020846365951001644
2023-01-23 03:36:40.369088: step: 1444/526, loss: 0.06253280490636826
2023-01-23 03:36:41.534710: step: 1448/526, loss: 0.5543445944786072
2023-01-23 03:36:42.675774: step: 1452/526, loss: 0.001891326974146068
2023-01-23 03:36:43.804642: step: 1456/526, loss: 0.0017368317348882556
2023-01-23 03:36:44.960692: step: 1460/526, loss: 8.077621168922633e-05
2023-01-23 03:36:46.065762: step: 1464/526, loss: 0.0007710456848144531
2023-01-23 03:36:47.182909: step: 1468/526, loss: 0.00141315464861691
2023-01-23 03:36:48.342229: step: 1472/526, loss: 0.017116069793701172
2023-01-23 03:36:49.464906: step: 1476/526, loss: 0.00010776519775390625
2023-01-23 03:36:50.589907: step: 1480/526, loss: 6.28471389063634e-05
2023-01-23 03:36:51.735580: step: 1484/526, loss: 0.014305973425507545
2023-01-23 03:36:52.888074: step: 1488/526, loss: 0.0008440017700195312
2023-01-23 03:36:54.031162: step: 1492/526, loss: 0.052460383623838425
2023-01-23 03:36:55.143692: step: 1496/526, loss: 0.017572879791259766
2023-01-23 03:36:56.269311: step: 1500/526, loss: 0.009979343973100185
2023-01-23 03:36:57.399851: step: 1504/526, loss: 3.051757857974735e-06
2023-01-23 03:36:58.503988: step: 1508/526, loss: 0.001967143965885043
2023-01-23 03:36:59.632322: step: 1512/526, loss: 0.02408142015337944
2023-01-23 03:37:00.756717: step: 1516/526, loss: 0.00844874419271946
2023-01-23 03:37:01.878742: step: 1520/526, loss: 0.0014387130504474044
2023-01-23 03:37:03.033483: step: 1524/526, loss: 0.009016323834657669
2023-01-23 03:37:04.166259: step: 1528/526, loss: 0.007923698052763939
2023-01-23 03:37:05.300437: step: 1532/526, loss: 0.0007848739624023438
2023-01-23 03:37:06.483863: step: 1536/526, loss: 0.014157581143081188
2023-01-23 03:37:07.620459: step: 1540/526, loss: 0.5811004042625427
2023-01-23 03:37:08.747086: step: 1544/526, loss: 0.01493148785084486
2023-01-23 03:37:09.870609: step: 1548/526, loss: 0.049453262239694595
2023-01-23 03:37:10.976397: step: 1552/526, loss: 0.00040273668128065765
2023-01-23 03:37:12.124736: step: 1556/526, loss: 0.0008309364202432334
2023-01-23 03:37:13.236206: step: 1560/526, loss: 0.00013446809316519648
2023-01-23 03:37:14.370593: step: 1564/526, loss: 0.06089053303003311
2023-01-23 03:37:15.509476: step: 1568/526, loss: 0.017856597900390625
2023-01-23 03:37:16.610468: step: 1572/526, loss: 1.8024446035269648e-05
2023-01-23 03:37:17.757829: step: 1576/526, loss: 0.006492328830063343
2023-01-23 03:37:18.897102: step: 1580/526, loss: 0.0007374763954430819
2023-01-23 03:37:20.044005: step: 1584/526, loss: 0.039803504943847656
2023-01-23 03:37:21.168190: step: 1588/526, loss: 7.133484177757055e-05
2023-01-23 03:37:22.286813: step: 1592/526, loss: 0.003092861268669367
2023-01-23 03:37:23.430414: step: 1596/526, loss: 0.0014581680297851562
2023-01-23 03:37:24.552442: step: 1600/526, loss: 7.820130122127011e-06
2023-01-23 03:37:25.663370: step: 1604/526, loss: 0.005928420927375555
2023-01-23 03:37:26.808398: step: 1608/526, loss: 0.010188293643295765
2023-01-23 03:37:27.943502: step: 1612/526, loss: 5.9700014389818534e-05
2023-01-23 03:37:29.091310: step: 1616/526, loss: 0.00165901193395257
2023-01-23 03:37:30.227463: step: 1620/526, loss: 0.048157691955566406
2023-01-23 03:37:31.366994: step: 1624/526, loss: 0.04464760050177574
2023-01-23 03:37:32.482258: step: 1628/526, loss: 0.004692935850471258
2023-01-23 03:37:33.591247: step: 1632/526, loss: 1.23977656585339e-06
2023-01-23 03:37:34.736670: step: 1636/526, loss: 0.009289741516113281
2023-01-23 03:37:35.874438: step: 1640/526, loss: 0.015642547979950905
2023-01-23 03:37:37.017923: step: 1644/526, loss: 0.0037658691871911287
2023-01-23 03:37:38.130674: step: 1648/526, loss: 0.01901531219482422
2023-01-23 03:37:39.239812: step: 1652/526, loss: 1.373290979245212e-05
2023-01-23 03:37:40.357214: step: 1656/526, loss: 0.00691752415150404
2023-01-23 03:37:41.468020: step: 1660/526, loss: 0.06677704304456711
2023-01-23 03:37:42.584192: step: 1664/526, loss: 0.00026683806208893657
2023-01-23 03:37:43.721885: step: 1668/526, loss: 0.00016689300537109375
2023-01-23 03:37:44.809974: step: 1672/526, loss: 0.00023756027803756297
2023-01-23 03:37:45.935437: step: 1676/526, loss: 0.00021667480177711695
2023-01-23 03:37:47.079871: step: 1680/526, loss: 0.004671812057495117
2023-01-23 03:37:48.227960: step: 1684/526, loss: 0.0045506954193115234
2023-01-23 03:37:49.398499: step: 1688/526, loss: 5.5599211918888614e-05
2023-01-23 03:37:50.561494: step: 1692/526, loss: 0.00588569650426507
2023-01-23 03:37:51.682125: step: 1696/526, loss: 0.01765899732708931
2023-01-23 03:37:52.825214: step: 1700/526, loss: 0.008499765768647194
2023-01-23 03:37:53.952533: step: 1704/526, loss: 0.0036149502266198397
2023-01-23 03:37:55.107493: step: 1708/526, loss: 0.00021781922259833664
2023-01-23 03:37:56.252287: step: 1712/526, loss: 2.4032591682043858e-05
2023-01-23 03:37:57.392228: step: 1716/526, loss: 0.013953781686723232
2023-01-23 03:37:58.526672: step: 1720/526, loss: 0.10758963227272034
2023-01-23 03:37:59.658139: step: 1724/526, loss: 0.000690460205078125
2023-01-23 03:38:00.821276: step: 1728/526, loss: 0.0019339561695232987
2023-01-23 03:38:01.970612: step: 1732/526, loss: 0.00045766832772642374
2023-01-23 03:38:03.098585: step: 1736/526, loss: 0.001689481781795621
2023-01-23 03:38:04.279180: step: 1740/526, loss: 2.8133392333984375e-05
2023-01-23 03:38:05.434122: step: 1744/526, loss: 0.04057254642248154
2023-01-23 03:38:06.604664: step: 1748/526, loss: 0.004868698306381702
2023-01-23 03:38:07.725235: step: 1752/526, loss: 0.0002922535059042275
2023-01-23 03:38:08.860070: step: 1756/526, loss: 0.0002534866507630795
2023-01-23 03:38:09.972106: step: 1760/526, loss: 0.016299057751893997
2023-01-23 03:38:11.100800: step: 1764/526, loss: 0.014888573437929153
2023-01-23 03:38:12.229380: step: 1768/526, loss: 0.01587958261370659
2023-01-23 03:38:13.376003: step: 1772/526, loss: 0.009452628903090954
2023-01-23 03:38:14.495603: step: 1776/526, loss: 0.0019157410133630037
2023-01-23 03:38:15.597125: step: 1780/526, loss: 0.03770046308636665
2023-01-23 03:38:16.725981: step: 1784/526, loss: 0.00021038056001998484
2023-01-23 03:38:17.831255: step: 1788/526, loss: 0.0023446083068847656
2023-01-23 03:38:18.944858: step: 1792/526, loss: 0.008762932382524014
2023-01-23 03:38:20.091221: step: 1796/526, loss: 0.00503196706995368
2023-01-23 03:38:21.270681: step: 1800/526, loss: 0.02203540876507759
2023-01-23 03:38:22.411404: step: 1804/526, loss: 0.002111339708790183
2023-01-23 03:38:23.524696: step: 1808/526, loss: 0.0003903389151673764
2023-01-23 03:38:24.677690: step: 1812/526, loss: 0.04990902170538902
2023-01-23 03:38:25.809954: step: 1816/526, loss: 0.24043616652488708
2023-01-23 03:38:26.968472: step: 1820/526, loss: 0.01688213460147381
2023-01-23 03:38:28.100117: step: 1824/526, loss: 0.022153044119477272
2023-01-23 03:38:29.245732: step: 1828/526, loss: 0.00613174494355917
2023-01-23 03:38:30.359793: step: 1832/526, loss: 0.0007495880126953125
2023-01-23 03:38:31.481843: step: 1836/526, loss: 0.001712036202661693
2023-01-23 03:38:32.642468: step: 1840/526, loss: 0.004852008540183306
2023-01-23 03:38:33.783514: step: 1844/526, loss: 4.520416405284777e-05
2023-01-23 03:38:34.909535: step: 1848/526, loss: 1.9955636162194423e-05
2023-01-23 03:38:36.029355: step: 1852/526, loss: 2.079009937006049e-05
2023-01-23 03:38:37.152340: step: 1856/526, loss: 7.591247413074598e-05
2023-01-23 03:38:38.326207: step: 1860/526, loss: 0.03272972255945206
2023-01-23 03:38:39.429484: step: 1864/526, loss: 6.8664553509734105e-06
2023-01-23 03:38:40.567718: step: 1868/526, loss: 0.00040216444176621735
2023-01-23 03:38:41.741678: step: 1872/526, loss: 0.14620837569236755
2023-01-23 03:38:42.910711: step: 1876/526, loss: 0.0017440796364098787
2023-01-23 03:38:44.047427: step: 1880/526, loss: 1.811981201171875e-05
2023-01-23 03:38:45.164471: step: 1884/526, loss: 0.0002244949428131804
2023-01-23 03:38:46.318811: step: 1888/526, loss: 0.006790351588279009
2023-01-23 03:38:47.418976: step: 1892/526, loss: 0.000678634678479284
2023-01-23 03:38:48.542485: step: 1896/526, loss: 0.0024310590233653784
2023-01-23 03:38:49.683575: step: 1900/526, loss: 0.03702693060040474
2023-01-23 03:38:50.804387: step: 1904/526, loss: 0.11375927925109863
2023-01-23 03:38:51.937391: step: 1908/526, loss: 0.009799766354262829
2023-01-23 03:38:53.107623: step: 1912/526, loss: 0.02885112725198269
2023-01-23 03:38:54.275949: step: 1916/526, loss: 0.0016406059730798006
2023-01-23 03:38:55.416919: step: 1920/526, loss: 5.474090721691027e-05
2023-01-23 03:38:56.551035: step: 1924/526, loss: 0.002544498536735773
2023-01-23 03:38:57.685300: step: 1928/526, loss: 0.003158187959343195
2023-01-23 03:38:58.825416: step: 1932/526, loss: 0.0005628585931845009
2023-01-23 03:38:59.964027: step: 1936/526, loss: 0.009442901238799095
2023-01-23 03:39:01.079588: step: 1940/526, loss: 0.00022220613027457148
2023-01-23 03:39:02.234548: step: 1944/526, loss: 0.00058155064471066
2023-01-23 03:39:03.371422: step: 1948/526, loss: 0.012954997830092907
2023-01-23 03:39:04.533355: step: 1952/526, loss: -2.155303991457913e-05
2023-01-23 03:39:05.682064: step: 1956/526, loss: 0.0025014879647642374
2023-01-23 03:39:06.820765: step: 1960/526, loss: 0.014387416653335094
2023-01-23 03:39:07.967740: step: 1964/526, loss: 0.00043506623478606343
2023-01-23 03:39:09.111075: step: 1968/526, loss: 0.0001312255917582661
2023-01-23 03:39:10.216010: step: 1972/526, loss: 0.0005878448719158769
2023-01-23 03:39:11.345489: step: 1976/526, loss: 0.0018257141346111894
2023-01-23 03:39:12.512982: step: 1980/526, loss: 7.114410254871473e-05
2023-01-23 03:39:13.661762: step: 1984/526, loss: 0.002582073211669922
2023-01-23 03:39:14.796979: step: 1988/526, loss: 0.0004734039248432964
2023-01-23 03:39:15.958906: step: 1992/526, loss: 0.019530678167939186
2023-01-23 03:39:17.076402: step: 1996/526, loss: 0.00031156541081145406
2023-01-23 03:39:18.233812: step: 2000/526, loss: 1.1444090887380298e-05
2023-01-23 03:39:19.360414: step: 2004/526, loss: 0.0009313584305346012
2023-01-23 03:39:20.531658: step: 2008/526, loss: 0.05644664913415909
2023-01-23 03:39:21.687056: step: 2012/526, loss: 0.004493999760597944
2023-01-23 03:39:22.827403: step: 2016/526, loss: 2.403259350103326e-05
2023-01-23 03:39:23.949490: step: 2020/526, loss: 0.0026079178787767887
2023-01-23 03:39:25.101905: step: 2024/526, loss: 0.025112152099609375
2023-01-23 03:39:26.228543: step: 2028/526, loss: 0.021279573440551758
2023-01-23 03:39:27.356801: step: 2032/526, loss: 0.00015411376080010086
2023-01-23 03:39:28.504018: step: 2036/526, loss: 0.0014522551791742444
2023-01-23 03:39:29.638521: step: 2040/526, loss: 0.00020856858463957906
2023-01-23 03:39:30.768290: step: 2044/526, loss: 0.000896072422619909
2023-01-23 03:39:31.893271: step: 2048/526, loss: 0.0009895324474200606
2023-01-23 03:39:33.015057: step: 2052/526, loss: 0.2350166290998459
2023-01-23 03:39:34.148768: step: 2056/526, loss: 0.007348204031586647
2023-01-23 03:39:35.283098: step: 2060/526, loss: 3.271103196311742e-05
2023-01-23 03:39:36.439366: step: 2064/526, loss: 0.014737558551132679
2023-01-23 03:39:37.627367: step: 2068/526, loss: 0.0003450393851380795
2023-01-23 03:39:38.797942: step: 2072/526, loss: 0.002077293349429965
2023-01-23 03:39:39.958384: step: 2076/526, loss: 0.00012512208195403218
2023-01-23 03:39:41.080311: step: 2080/526, loss: 0.8806449174880981
2023-01-23 03:39:42.206071: step: 2084/526, loss: 0.016659926623106003
2023-01-23 03:39:43.358909: step: 2088/526, loss: 0.008400822058320045
2023-01-23 03:39:44.498203: step: 2092/526, loss: 2.8896331059513614e-05
2023-01-23 03:39:45.642844: step: 2096/526, loss: 0.0043472289107739925
2023-01-23 03:39:46.761271: step: 2100/526, loss: 0.002697181887924671
2023-01-23 03:39:47.865976: step: 2104/526, loss: 0.0050490377470850945
==================================================
Loss: 0.018
--------------------
Dev: {'event': {'p': 0.6266519823788547, 'r': 0.7576564580559254, 'f1': 0.6859553948161543}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Test: {'event': {'p': 0.6313522825150732, 'r': 0.7651356993736952, 'f1': 0.6918357715903728}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Chinese: {'event': {'p': 0.6621621621621622, 'r': 0.9074074074074074, 'f1': 0.765625}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Korean: {'event': {'p': 0.75, 'r': 0.47619047619047616, 'f1': 0.58252427184466}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Russian: {'event': {'p': 0.5384615384615384, 'r': 0.5833333333333334, 'f1': 0.5599999999999999}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
New best chinese model...
New best russian model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6266519823788547, 'r': 0.7576564580559254, 'f1': 0.6859553948161543}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Eng Test for Chinese: {'event': {'p': 0.6313522825150732, 'r': 0.7651356993736952, 'f1': 0.6918357715903728}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Sample Chinese: {'event': {'p': 0.6621621621621622, 'r': 0.9074074074074074, 'f1': 0.765625}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6257995735607675, 'r': 0.7816245006657789, 'f1': 0.6950858496151568}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Eng Test for Korean: {'event': {'p': 0.623113410952997, 'r': 0.7541753653444676, 'f1': 0.6824085005903188}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Sample Korean: {'event': {'p': 0.7446808510638298, 'r': 0.5555555555555556, 'f1': 0.6363636363636364}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6266519823788547, 'r': 0.7576564580559254, 'f1': 0.6859553948161543}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Eng Test for Russian: {'event': {'p': 0.6313522825150732, 'r': 0.7651356993736952, 'f1': 0.6918357715903728}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Sample Russian: {'event': {'p': 0.5384615384615384, 'r': 0.5833333333333334, 'f1': 0.5599999999999999}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
******************************
Epoch: 24
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 03:40:46.724316: step: 4/526, loss: 0.0003543853817973286
2023-01-23 03:40:47.847570: step: 8/526, loss: 0.0016130446456372738
2023-01-23 03:40:48.986621: step: 12/526, loss: 7.41958647267893e-05
2023-01-23 03:40:50.102182: step: 16/526, loss: 0.002418422605842352
2023-01-23 03:40:51.239044: step: 20/526, loss: 0.0007433891878463328
2023-01-23 03:40:52.345746: step: 24/526, loss: 0.006683063693344593
2023-01-23 03:40:53.483068: step: 28/526, loss: 1.087188684323337e-05
2023-01-23 03:40:54.633637: step: 32/526, loss: 0.00281944265589118
2023-01-23 03:40:55.750884: step: 36/526, loss: 1.7929078239831142e-05
2023-01-23 03:40:56.873249: step: 40/526, loss: 0.0001478672056691721
2023-01-23 03:40:58.015764: step: 44/526, loss: 0.06127338483929634
2023-01-23 03:40:59.164875: step: 48/526, loss: 0.04185633733868599
2023-01-23 03:41:00.291648: step: 52/526, loss: 8.39233416627394e-06
2023-01-23 03:41:01.402916: step: 56/526, loss: 0.03674716874957085
2023-01-23 03:41:02.527997: step: 60/526, loss: 0.002529716584831476
2023-01-23 03:41:03.690371: step: 64/526, loss: -1.0490416570974048e-06
2023-01-23 03:41:04.794101: step: 68/526, loss: 0.00017271040997002274
2023-01-23 03:41:05.914630: step: 72/526, loss: 0.0007569313165731728
2023-01-23 03:41:07.035165: step: 76/526, loss: 0.0017543792491778731
2023-01-23 03:41:08.183299: step: 80/526, loss: 0.0019897460006177425
2023-01-23 03:41:09.311607: step: 84/526, loss: 0.0011582374572753906
2023-01-23 03:41:10.453959: step: 88/526, loss: 0.013387167826294899
2023-01-23 03:41:11.568306: step: 92/526, loss: 0.028180886059999466
2023-01-23 03:41:12.694398: step: 96/526, loss: 0.005329036619514227
2023-01-23 03:41:13.816048: step: 100/526, loss: 0.009954262524843216
2023-01-23 03:41:14.957028: step: 104/526, loss: 0.002077818149700761
2023-01-23 03:41:16.100308: step: 108/526, loss: 0.005972862243652344
2023-01-23 03:41:17.234022: step: 112/526, loss: 0.011602973565459251
2023-01-23 03:41:18.361089: step: 116/526, loss: 0.04768562316894531
2023-01-23 03:41:19.534995: step: 120/526, loss: 0.0004989624139852822
2023-01-23 03:41:20.657900: step: 124/526, loss: 3.719329924933845e-06
2023-01-23 03:41:21.781630: step: 128/526, loss: 0.00041828156099654734
2023-01-23 03:41:22.882053: step: 132/526, loss: 0.0011971474159508944
2023-01-23 03:41:24.010763: step: 136/526, loss: 0.00016460419283248484
2023-01-23 03:41:25.148858: step: 140/526, loss: 1.8024446035269648e-05
2023-01-23 03:41:26.283344: step: 144/526, loss: 0.001442480250261724
2023-01-23 03:41:27.410098: step: 148/526, loss: 9.784699068404734e-05
2023-01-23 03:41:28.550438: step: 152/526, loss: -5.385280019254424e-06
2023-01-23 03:41:29.689909: step: 156/526, loss: 0.004082011990249157
2023-01-23 03:41:30.788137: step: 160/526, loss: 0.00688095111399889
2023-01-23 03:41:31.918261: step: 164/526, loss: 0.00023670197697356343
2023-01-23 03:41:33.043509: step: 168/526, loss: 0.011916732415556908
2023-01-23 03:41:34.164707: step: 172/526, loss: 5.745887756347656e-05
2023-01-23 03:41:35.306293: step: 176/526, loss: 1.1730194273695815e-05
2023-01-23 03:41:36.434757: step: 180/526, loss: 0.0007794380653649569
2023-01-23 03:41:37.566192: step: 184/526, loss: 0.0006580352783203125
2023-01-23 03:41:38.727294: step: 188/526, loss: 1.773834264895413e-05
2023-01-23 03:41:39.902948: step: 192/526, loss: 0.00013456345186568797
2023-01-23 03:41:41.040986: step: 196/526, loss: 0.018192196264863014
2023-01-23 03:41:42.168190: step: 200/526, loss: 0.00015716553025413305
2023-01-23 03:41:43.331907: step: 204/526, loss: 1.1110305422334932e-05
2023-01-23 03:41:44.486714: step: 208/526, loss: 0.03754596784710884
2023-01-23 03:41:45.612297: step: 212/526, loss: 0.056490231305360794
2023-01-23 03:41:46.735237: step: 216/526, loss: 0.016968728974461555
2023-01-23 03:41:47.871023: step: 220/526, loss: 8.578300912631676e-05
2023-01-23 03:41:49.006791: step: 224/526, loss: 0.000798130058683455
2023-01-23 03:41:50.136971: step: 228/526, loss: 1.4495850336970761e-05
2023-01-23 03:41:51.283091: step: 232/526, loss: 0.0005743026849813759
2023-01-23 03:41:52.441773: step: 236/526, loss: 0.00010976791963912547
2023-01-23 03:41:53.566813: step: 240/526, loss: 5.507469177246094e-05
2023-01-23 03:41:54.719440: step: 244/526, loss: 0.034583281725645065
2023-01-23 03:41:55.841246: step: 248/526, loss: 0.0036297799088060856
2023-01-23 03:41:56.995146: step: 252/526, loss: 0.05945110321044922
2023-01-23 03:41:58.113963: step: 256/526, loss: 2.8610236313397763e-07
2023-01-23 03:41:59.242910: step: 260/526, loss: 0.00013637542724609375
2023-01-23 03:42:00.382352: step: 264/526, loss: 0.024252891540527344
2023-01-23 03:42:01.515054: step: 268/526, loss: 1.926422191900201e-05
2023-01-23 03:42:02.661858: step: 272/526, loss: 0.009486389346420765
2023-01-23 03:42:03.773556: step: 276/526, loss: 0.007299995981156826
2023-01-23 03:42:04.886524: step: 280/526, loss: 0.0032514571212232113
2023-01-23 03:42:05.997325: step: 284/526, loss: 0.02510061301290989
2023-01-23 03:42:07.128864: step: 288/526, loss: 0.08238621056079865
2023-01-23 03:42:08.290789: step: 292/526, loss: 0.00023784636869095266
2023-01-23 03:42:09.435842: step: 296/526, loss: 0.0066242218017578125
2023-01-23 03:42:10.578141: step: 300/526, loss: 0.0002933502255473286
2023-01-23 03:42:11.722869: step: 304/526, loss: 0.0032695771660655737
2023-01-23 03:42:12.859108: step: 308/526, loss: 0.0004551887686830014
2023-01-23 03:42:14.000523: step: 312/526, loss: 0.0027387142181396484
2023-01-23 03:42:15.117189: step: 316/526, loss: 0.00040121079655364156
2023-01-23 03:42:16.255532: step: 320/526, loss: 0.026807021349668503
2023-01-23 03:42:17.358066: step: 324/526, loss: 0.0006674290052615106
2023-01-23 03:42:18.507660: step: 328/526, loss: 0.00032258033752441406
2023-01-23 03:42:19.624172: step: 332/526, loss: 0.0767589583992958
2023-01-23 03:42:20.770724: step: 336/526, loss: 0.0006695747142657638
2023-01-23 03:42:21.911390: step: 340/526, loss: 0.08317708969116211
2023-01-23 03:42:23.028141: step: 344/526, loss: 0.00021195411682128906
2023-01-23 03:42:24.159158: step: 348/526, loss: 0.0009900092845782638
2023-01-23 03:42:25.319284: step: 352/526, loss: 0.022437285631895065
2023-01-23 03:42:26.444182: step: 356/526, loss: -0.0
2023-01-23 03:42:27.587465: step: 360/526, loss: 0.0013381957542151213
2023-01-23 03:42:28.754732: step: 364/526, loss: 0.004854011815041304
2023-01-23 03:42:29.892166: step: 368/526, loss: 0.0022419930901378393
2023-01-23 03:42:31.024282: step: 372/526, loss: 0.010491943918168545
2023-01-23 03:42:32.158864: step: 376/526, loss: 0.002476310823112726
2023-01-23 03:42:33.270405: step: 380/526, loss: 0.00018367767916060984
2023-01-23 03:42:34.426293: step: 384/526, loss: 0.0026439668145030737
2023-01-23 03:42:35.538730: step: 388/526, loss: 0.00012774467177223414
2023-01-23 03:42:36.695567: step: 392/526, loss: 2.2697449821862392e-05
2023-01-23 03:42:37.800204: step: 396/526, loss: 0.0019767761696130037
2023-01-23 03:42:38.925986: step: 400/526, loss: 0.05824451521039009
2023-01-23 03:42:40.025665: step: 404/526, loss: 0.0007933616871014237
2023-01-23 03:42:41.150417: step: 408/526, loss: 0.005852317903190851
2023-01-23 03:42:42.279861: step: 412/526, loss: 0.023007966578006744
2023-01-23 03:42:43.438330: step: 416/526, loss: 0.00366554269567132
2023-01-23 03:42:44.540784: step: 420/526, loss: 0.04640350490808487
2023-01-23 03:42:45.644485: step: 424/526, loss: 0.0004723549063783139
2023-01-23 03:42:46.833768: step: 428/526, loss: 0.022696591913700104
2023-01-23 03:42:47.975138: step: 432/526, loss: 0.002528953365981579
2023-01-23 03:42:49.075613: step: 436/526, loss: 7.07626313669607e-05
2023-01-23 03:42:50.214588: step: 440/526, loss: 0.04513902962207794
2023-01-23 03:42:51.356740: step: 444/526, loss: 0.0002626419300213456
2023-01-23 03:42:52.480269: step: 448/526, loss: 0.0005931854248046875
2023-01-23 03:42:53.627925: step: 452/526, loss: 0.00011329651169944555
2023-01-23 03:42:54.744290: step: 456/526, loss: 0.0231507308781147
2023-01-23 03:42:55.878620: step: 460/526, loss: 0.0009976864093914628
2023-01-23 03:42:57.020371: step: 464/526, loss: 0.05659074708819389
2023-01-23 03:42:58.150226: step: 468/526, loss: 0.003830432891845703
2023-01-23 03:42:59.281060: step: 472/526, loss: 0.0009501457097940147
2023-01-23 03:43:00.393952: step: 476/526, loss: 0.006242990959435701
2023-01-23 03:43:01.552307: step: 480/526, loss: 0.01744966395199299
2023-01-23 03:43:02.673284: step: 484/526, loss: 1.678466833254788e-05
2023-01-23 03:43:03.795253: step: 488/526, loss: 7.247925623232732e-06
2023-01-23 03:43:04.912722: step: 492/526, loss: 0.04512348398566246
2023-01-23 03:43:06.037810: step: 496/526, loss: 0.004738807678222656
2023-01-23 03:43:07.170613: step: 500/526, loss: 0.0009008407942019403
2023-01-23 03:43:08.276989: step: 504/526, loss: 0.0022682668641209602
2023-01-23 03:43:09.412711: step: 508/526, loss: 0.005920696537941694
2023-01-23 03:43:10.555522: step: 512/526, loss: 0.04358692094683647
2023-01-23 03:43:11.677577: step: 516/526, loss: 0.00025053025456145406
2023-01-23 03:43:12.855880: step: 520/526, loss: 0.00191326136700809
2023-01-23 03:43:13.958572: step: 524/526, loss: 3.705024573719129e-05
2023-01-23 03:43:15.103235: step: 528/526, loss: 0.00021781922259833664
2023-01-23 03:43:16.269229: step: 532/526, loss: 0.005717658903449774
2023-01-23 03:43:17.409353: step: 536/526, loss: 0.00472602853551507
2023-01-23 03:43:18.579615: step: 540/526, loss: 0.0017313479911535978
2023-01-23 03:43:19.716859: step: 544/526, loss: 0.004014492034912109
2023-01-23 03:43:20.847403: step: 548/526, loss: 0.0023202896118164062
2023-01-23 03:43:22.014318: step: 552/526, loss: 7.972717139637098e-05
2023-01-23 03:43:23.158697: step: 556/526, loss: 0.0293413158506155
2023-01-23 03:43:24.272931: step: 560/526, loss: 0.008193492889404297
2023-01-23 03:43:25.399707: step: 564/526, loss: 0.006133651826530695
2023-01-23 03:43:26.555883: step: 568/526, loss: 0.0006778716924600303
2023-01-23 03:43:27.667629: step: 572/526, loss: 0.0003970146062783897
2023-01-23 03:43:28.809324: step: 576/526, loss: 0.00011472702317405492
2023-01-23 03:43:29.942344: step: 580/526, loss: 2.6321409677620977e-05
2023-01-23 03:43:31.108017: step: 584/526, loss: 3.681182715808973e-05
2023-01-23 03:43:32.224894: step: 588/526, loss: 1.0776519047794864e-05
2023-01-23 03:43:33.327275: step: 592/526, loss: 0.015050698071718216
2023-01-23 03:43:34.478751: step: 596/526, loss: 0.02680053934454918
2023-01-23 03:43:35.625602: step: 600/526, loss: 0.01822662353515625
2023-01-23 03:43:36.800276: step: 604/526, loss: 0.05724554508924484
2023-01-23 03:43:37.948836: step: 608/526, loss: 0.00027551650418899953
2023-01-23 03:43:39.090434: step: 612/526, loss: 0.0007148743025027215
2023-01-23 03:43:40.236330: step: 616/526, loss: 0.0012170792324468493
2023-01-23 03:43:41.367339: step: 620/526, loss: 3.2901763916015625e-05
2023-01-23 03:43:42.507753: step: 624/526, loss: 9.679794311523438e-05
2023-01-23 03:43:43.652477: step: 628/526, loss: 0.017675209790468216
2023-01-23 03:43:44.781393: step: 632/526, loss: 0.0008423805120401084
2023-01-23 03:43:45.919675: step: 636/526, loss: 0.004496097564697266
2023-01-23 03:43:47.118573: step: 640/526, loss: 7.61032133596018e-05
2023-01-23 03:43:48.273326: step: 644/526, loss: 0.02545623853802681
2023-01-23 03:43:49.421634: step: 648/526, loss: 0.016273116692900658
2023-01-23 03:43:50.567987: step: 652/526, loss: 0.035306550562381744
2023-01-23 03:43:51.682995: step: 656/526, loss: 0.0016454696888104081
2023-01-23 03:43:52.798682: step: 660/526, loss: 3.185272362316027e-05
2023-01-23 03:43:53.945024: step: 664/526, loss: 0.00437507638707757
2023-01-23 03:43:55.031809: step: 668/526, loss: 0.0035715103149414062
2023-01-23 03:43:56.140695: step: 672/526, loss: 0.0013638496166095138
2023-01-23 03:43:57.282947: step: 676/526, loss: 8.77380352903856e-06
2023-01-23 03:43:58.433904: step: 680/526, loss: 0.00018968581571243703
2023-01-23 03:43:59.573777: step: 684/526, loss: 0.007482767105102539
2023-01-23 03:44:00.717074: step: 688/526, loss: 0.0005333900917321444
2023-01-23 03:44:01.842072: step: 692/526, loss: 0.0004784584161825478
2023-01-23 03:44:03.022226: step: 696/526, loss: 0.0002773285086732358
2023-01-23 03:44:04.170412: step: 700/526, loss: 0.004928970243781805
2023-01-23 03:44:05.314023: step: 704/526, loss: 0.013131809420883656
2023-01-23 03:44:06.449892: step: 708/526, loss: 0.0003971099795307964
2023-01-23 03:44:07.588626: step: 712/526, loss: 0.02708374708890915
2023-01-23 03:44:08.707250: step: 716/526, loss: 0.05870051309466362
2023-01-23 03:44:09.866101: step: 720/526, loss: 0.00011129378981422633
2023-01-23 03:44:10.987792: step: 724/526, loss: 0.00032711029052734375
2023-01-23 03:44:12.141015: step: 728/526, loss: 0.47495585680007935
2023-01-23 03:44:13.274419: step: 732/526, loss: 0.005985069554299116
2023-01-23 03:44:14.369398: step: 736/526, loss: 0.0004085540713276714
2023-01-23 03:44:15.519381: step: 740/526, loss: 0.020210934802889824
2023-01-23 03:44:16.665547: step: 744/526, loss: 0.029415130615234375
2023-01-23 03:44:17.792068: step: 748/526, loss: 2.384185791015625e-05
2023-01-23 03:44:18.946685: step: 752/526, loss: 0.008944511413574219
2023-01-23 03:44:20.064619: step: 756/526, loss: 0.0005935192457400262
2023-01-23 03:44:21.202968: step: 760/526, loss: 0.0001256942778127268
2023-01-23 03:44:22.343640: step: 764/526, loss: 0.0003887176571879536
2023-01-23 03:44:23.471201: step: 768/526, loss: 0.0040260315872728825
2023-01-23 03:44:24.620240: step: 772/526, loss: 0.0012353897327557206
2023-01-23 03:44:25.728671: step: 776/526, loss: 1.850128137448337e-05
2023-01-23 03:44:26.864333: step: 780/526, loss: 0.02021818235516548
2023-01-23 03:44:27.999010: step: 784/526, loss: 0.028534317389130592
2023-01-23 03:44:29.117968: step: 788/526, loss: 0.0019321441650390625
2023-01-23 03:44:30.252673: step: 792/526, loss: 0.003497791476547718
2023-01-23 03:44:31.372997: step: 796/526, loss: 2.307891918462701e-05
2023-01-23 03:44:32.476593: step: 800/526, loss: 0.0014812469016760588
2023-01-23 03:44:33.607460: step: 804/526, loss: 0.0007188796880654991
2023-01-23 03:44:34.731435: step: 808/526, loss: 0.06550207734107971
2023-01-23 03:44:35.838173: step: 812/526, loss: 0.0005131721845827997
2023-01-23 03:44:36.986192: step: 816/526, loss: 0.0046897889114916325
2023-01-23 03:44:38.129625: step: 820/526, loss: 0.00021324156841728836
2023-01-23 03:44:39.280268: step: 824/526, loss: 0.0005862236139364541
2023-01-23 03:44:40.431842: step: 828/526, loss: 6.48498553346144e-06
2023-01-23 03:44:41.592958: step: 832/526, loss: 0.04538403078913689
2023-01-23 03:44:42.727340: step: 836/526, loss: 0.0003143310605082661
2023-01-23 03:44:43.868935: step: 840/526, loss: 0.01945781707763672
2023-01-23 03:44:44.995415: step: 844/526, loss: 0.001015520072542131
2023-01-23 03:44:46.153359: step: 848/526, loss: 0.0020095824729651213
2023-01-23 03:44:47.285501: step: 852/526, loss: 0.023306705057621002
2023-01-23 03:44:48.424542: step: 856/526, loss: 4.57763671875e-05
2023-01-23 03:44:49.539569: step: 860/526, loss: 0.014178657904267311
2023-01-23 03:44:50.657638: step: 864/526, loss: 0.0015453338855877519
2023-01-23 03:44:51.798817: step: 868/526, loss: 0.002031993819400668
2023-01-23 03:44:52.936323: step: 872/526, loss: 0.06039486080408096
2023-01-23 03:44:54.070296: step: 876/526, loss: 0.03189563751220703
2023-01-23 03:44:55.187693: step: 880/526, loss: 4.158019874012098e-05
2023-01-23 03:44:56.360365: step: 884/526, loss: 0.014531994238495827
2023-01-23 03:44:57.504263: step: 888/526, loss: 0.00010585784912109375
2023-01-23 03:44:58.675996: step: 892/526, loss: 0.0007903099758550525
2023-01-23 03:44:59.810895: step: 896/526, loss: 0.005035972688347101
2023-01-23 03:45:00.920088: step: 900/526, loss: 0.0354883186519146
2023-01-23 03:45:02.069444: step: 904/526, loss: 0.003201007843017578
2023-01-23 03:45:03.190316: step: 908/526, loss: 0.009349632076919079
2023-01-23 03:45:04.357746: step: 912/526, loss: 0.034232523292303085
2023-01-23 03:45:05.452243: step: 916/526, loss: 9.489059448242188e-05
2023-01-23 03:45:06.634018: step: 920/526, loss: 0.020899200811982155
2023-01-23 03:45:07.755654: step: 924/526, loss: 0.004879761021584272
2023-01-23 03:45:08.886784: step: 928/526, loss: 0.0004287242772988975
2023-01-23 03:45:10.027007: step: 932/526, loss: 0.0016637801891192794
2023-01-23 03:45:11.181763: step: 936/526, loss: 0.0013332366943359375
2023-01-23 03:45:12.342731: step: 940/526, loss: 0.0002853393380064517
2023-01-23 03:45:13.525875: step: 944/526, loss: 0.026480484753847122
2023-01-23 03:45:14.675815: step: 948/526, loss: 0.04964113235473633
2023-01-23 03:45:15.780492: step: 952/526, loss: 0.28571662306785583
2023-01-23 03:45:16.901300: step: 956/526, loss: 0.0009974478743970394
2023-01-23 03:45:18.053437: step: 960/526, loss: 0.0036619186867028475
2023-01-23 03:45:19.193931: step: 964/526, loss: 0.0006009578937664628
2023-01-23 03:45:20.335254: step: 968/526, loss: 0.0019067287212237716
2023-01-23 03:45:21.475094: step: 972/526, loss: 0.0072498321533203125
2023-01-23 03:45:22.586080: step: 976/526, loss: 0.01940612867474556
2023-01-23 03:45:23.762115: step: 980/526, loss: 0.08336753398180008
2023-01-23 03:45:24.917639: step: 984/526, loss: 0.0011601448059082031
2023-01-23 03:45:26.060998: step: 988/526, loss: 0.004457283299416304
2023-01-23 03:45:27.203065: step: 992/526, loss: 0.018612097948789597
2023-01-23 03:45:28.342830: step: 996/526, loss: 0.03325996547937393
2023-01-23 03:45:29.463600: step: 1000/526, loss: 0.005961274728178978
2023-01-23 03:45:30.583985: step: 1004/526, loss: 0.02926664426922798
2023-01-23 03:45:31.713282: step: 1008/526, loss: 0.06164827570319176
2023-01-23 03:45:32.835922: step: 1012/526, loss: 0.00033903124858625233
2023-01-23 03:45:33.961124: step: 1016/526, loss: 0.0006549835670739412
2023-01-23 03:45:35.139721: step: 1020/526, loss: 0.014649391174316406
2023-01-23 03:45:36.267446: step: 1024/526, loss: 0.0009042740566655993
2023-01-23 03:45:37.376406: step: 1028/526, loss: 0.002101993653923273
2023-01-23 03:45:38.505071: step: 1032/526, loss: 0.0008924484718590975
2023-01-23 03:45:39.669094: step: 1036/526, loss: 0.0008095264784060419
2023-01-23 03:45:40.844394: step: 1040/526, loss: 0.008431053720414639
2023-01-23 03:45:41.968108: step: 1044/526, loss: 3.767013822653098e-06
2023-01-23 03:45:43.183755: step: 1048/526, loss: 0.003498077392578125
2023-01-23 03:45:44.308717: step: 1052/526, loss: 0.0001203536958200857
2023-01-23 03:45:45.446964: step: 1056/526, loss: 0.2820812165737152
2023-01-23 03:45:46.546836: step: 1060/526, loss: 7.939338684082031e-05
2023-01-23 03:45:47.704832: step: 1064/526, loss: 0.00047206878662109375
2023-01-23 03:45:48.832403: step: 1068/526, loss: 7.772445314913057e-06
2023-01-23 03:45:49.968036: step: 1072/526, loss: 0.003941059578210115
2023-01-23 03:45:51.080119: step: 1076/526, loss: 0.014945030212402344
2023-01-23 03:45:52.263827: step: 1080/526, loss: 0.00442428607493639
2023-01-23 03:45:53.415225: step: 1084/526, loss: 0.0024404525756835938
2023-01-23 03:45:54.564836: step: 1088/526, loss: 1.5258792700478807e-06
2023-01-23 03:45:55.687023: step: 1092/526, loss: 0.00015316010103560984
2023-01-23 03:45:56.832874: step: 1096/526, loss: 0.00018272399029228836
2023-01-23 03:45:57.989562: step: 1100/526, loss: 1.4877318790240679e-05
2023-01-23 03:45:59.134938: step: 1104/526, loss: 0.040668487548828125
2023-01-23 03:46:00.255861: step: 1108/526, loss: 0.018201828002929688
2023-01-23 03:46:01.379878: step: 1112/526, loss: 0.0006000519497320056
2023-01-23 03:46:02.508227: step: 1116/526, loss: 0.03940659016370773
2023-01-23 03:46:03.636914: step: 1120/526, loss: 0.0017597199184820056
2023-01-23 03:46:04.770682: step: 1124/526, loss: 0.00037136077298782766
2023-01-23 03:46:05.906686: step: 1128/526, loss: 0.0001710891810944304
2023-01-23 03:46:07.053867: step: 1132/526, loss: 0.02481565624475479
2023-01-23 03:46:08.203684: step: 1136/526, loss: 2.1409989130916074e-05
2023-01-23 03:46:09.333804: step: 1140/526, loss: 0.00046899321023374796
2023-01-23 03:46:10.468721: step: 1144/526, loss: 0.0003192901785951108
2023-01-23 03:46:11.606216: step: 1148/526, loss: 0.02814960479736328
2023-01-23 03:46:12.737740: step: 1152/526, loss: 0.022788619622588158
2023-01-23 03:46:13.905398: step: 1156/526, loss: 0.002585887908935547
2023-01-23 03:46:15.078201: step: 1160/526, loss: 0.00947427749633789
2023-01-23 03:46:16.225843: step: 1164/526, loss: 0.0436311736702919
2023-01-23 03:46:17.380988: step: 1168/526, loss: 0.013833713717758656
2023-01-23 03:46:18.532574: step: 1172/526, loss: 0.013602066785097122
2023-01-23 03:46:19.659671: step: 1176/526, loss: 0.01815180853009224
2023-01-23 03:46:20.813912: step: 1180/526, loss: 0.0021659850608557463
2023-01-23 03:46:21.961713: step: 1184/526, loss: 5.931854320806451e-05
2023-01-23 03:46:23.102437: step: 1188/526, loss: 0.0044879917986691
2023-01-23 03:46:24.250278: step: 1192/526, loss: 0.0024885176680982113
2023-01-23 03:46:25.368523: step: 1196/526, loss: 0.08112716674804688
2023-01-23 03:46:26.497840: step: 1200/526, loss: 0.00940713845193386
2023-01-23 03:46:27.639151: step: 1204/526, loss: 0.004264450166374445
2023-01-23 03:46:28.785390: step: 1208/526, loss: 0.0004259109846316278
2023-01-23 03:46:29.910757: step: 1212/526, loss: 0.00015192032151389867
2023-01-23 03:46:31.076986: step: 1216/526, loss: 0.313162624835968
2023-01-23 03:46:32.208045: step: 1220/526, loss: 5.3882598876953125e-05
2023-01-23 03:46:33.341669: step: 1224/526, loss: 6.0033802583348006e-05
2023-01-23 03:46:34.452588: step: 1228/526, loss: 0.00025005341740325093
2023-01-23 03:46:35.589563: step: 1232/526, loss: 0.0013680459233000875
2023-01-23 03:46:36.738633: step: 1236/526, loss: 0.0001597404625499621
2023-01-23 03:46:37.865551: step: 1240/526, loss: 0.0002983093145303428
2023-01-23 03:46:38.977970: step: 1244/526, loss: 0.0068229674361646175
2023-01-23 03:46:40.085439: step: 1248/526, loss: 2.155303991457913e-05
2023-01-23 03:46:41.208135: step: 1252/526, loss: 0.2867697775363922
2023-01-23 03:46:42.332573: step: 1256/526, loss: 0.0001184463471872732
2023-01-23 03:46:43.489213: step: 1260/526, loss: 0.006624412722885609
2023-01-23 03:46:44.621624: step: 1264/526, loss: 0.005353641230612993
2023-01-23 03:46:45.769500: step: 1268/526, loss: 0.0012070179218426347
2023-01-23 03:46:46.883247: step: 1272/526, loss: 0.00045108795166015625
2023-01-23 03:46:47.999860: step: 1276/526, loss: 0.000192546853213571
2023-01-23 03:46:49.101046: step: 1280/526, loss: 0.002213859697803855
2023-01-23 03:46:50.250625: step: 1284/526, loss: 0.0009983063209801912
2023-01-23 03:46:51.375404: step: 1288/526, loss: 6.961822691664565e-06
2023-01-23 03:46:52.502354: step: 1292/526, loss: 0.005574035923928022
2023-01-23 03:46:53.611585: step: 1296/526, loss: 0.006134224124252796
2023-01-23 03:46:54.731220: step: 1300/526, loss: 0.00228710169903934
2023-01-23 03:46:55.856316: step: 1304/526, loss: 0.0001657485991017893
2023-01-23 03:46:57.010549: step: 1308/526, loss: 0.003320026444271207
2023-01-23 03:46:58.116297: step: 1312/526, loss: 0.00012602806964423507
2023-01-23 03:46:59.240844: step: 1316/526, loss: 0.006726741790771484
2023-01-23 03:47:00.363402: step: 1320/526, loss: 0.03466634452342987
2023-01-23 03:47:01.506428: step: 1324/526, loss: -1.506805438111769e-05
2023-01-23 03:47:02.615258: step: 1328/526, loss: 0.0002075195370707661
2023-01-23 03:47:03.756130: step: 1332/526, loss: 0.04439039155840874
2023-01-23 03:47:04.871233: step: 1336/526, loss: 0.0009511836105957627
2023-01-23 03:47:06.030251: step: 1340/526, loss: 0.0005867004510946572
2023-01-23 03:47:07.178866: step: 1344/526, loss: 6.895065598655492e-05
2023-01-23 03:47:08.307826: step: 1348/526, loss: 0.0010419845348224044
2023-01-23 03:47:09.429184: step: 1352/526, loss: 0.0008003235561773181
2023-01-23 03:47:10.530614: step: 1356/526, loss: 0.01979966089129448
2023-01-23 03:47:11.676916: step: 1360/526, loss: 8.37326078908518e-05
2023-01-23 03:47:12.788836: step: 1364/526, loss: 0.008275032043457031
2023-01-23 03:47:13.917861: step: 1368/526, loss: 0.0048618316650390625
2023-01-23 03:47:15.075660: step: 1372/526, loss: 0.00020580290583893657
2023-01-23 03:47:16.188873: step: 1376/526, loss: 0.003113794606178999
2023-01-23 03:47:17.340007: step: 1380/526, loss: 0.0343870185315609
2023-01-23 03:47:18.468940: step: 1384/526, loss: 0.0012341499095782638
2023-01-23 03:47:19.581001: step: 1388/526, loss: 4.9209596909349784e-05
2023-01-23 03:47:20.709091: step: 1392/526, loss: 0.0002454757923260331
2023-01-23 03:47:21.835111: step: 1396/526, loss: 0.0017900944221764803
2023-01-23 03:47:22.988973: step: 1400/526, loss: 0.0031234740745276213
2023-01-23 03:47:24.155198: step: 1404/526, loss: -1.33514404296875e-05
2023-01-23 03:47:25.291169: step: 1408/526, loss: 0.06752175837755203
2023-01-23 03:47:26.434640: step: 1412/526, loss: 0.019492531195282936
2023-01-23 03:47:27.569445: step: 1416/526, loss: 0.04481372609734535
2023-01-23 03:47:28.719861: step: 1420/526, loss: 0.00041065216646529734
2023-01-23 03:47:29.856517: step: 1424/526, loss: 0.0003224372921977192
2023-01-23 03:47:30.975769: step: 1428/526, loss: 0.00020689965458586812
2023-01-23 03:47:32.116525: step: 1432/526, loss: -2.6702882678364404e-06
2023-01-23 03:47:33.251416: step: 1436/526, loss: 0.04386467859148979
2023-01-23 03:47:34.415738: step: 1440/526, loss: 5.588532076217234e-05
2023-01-23 03:47:35.567845: step: 1444/526, loss: 0.003950232174247503
2023-01-23 03:47:36.715138: step: 1448/526, loss: 0.07215669751167297
2023-01-23 03:47:37.846679: step: 1452/526, loss: 1.182556115963962e-05
2023-01-23 03:47:38.978793: step: 1456/526, loss: 0.0023937225341796875
2023-01-23 03:47:40.087768: step: 1460/526, loss: 0.0002323150692973286
2023-01-23 03:47:41.236075: step: 1464/526, loss: 0.05893097072839737
2023-01-23 03:47:42.350847: step: 1468/526, loss: 0.6178361773490906
2023-01-23 03:47:43.484398: step: 1472/526, loss: 0.007234144490212202
2023-01-23 03:47:44.623718: step: 1476/526, loss: 0.0031185150146484375
2023-01-23 03:47:45.749399: step: 1480/526, loss: 0.0002645492786541581
2023-01-23 03:47:46.889890: step: 1484/526, loss: 0.00013699530973099172
2023-01-23 03:47:48.037981: step: 1488/526, loss: 0.007129478733986616
2023-01-23 03:47:49.178163: step: 1492/526, loss: 0.0006588220712728798
2023-01-23 03:47:50.337950: step: 1496/526, loss: 0.018398571759462357
2023-01-23 03:47:51.494354: step: 1500/526, loss: -9.250640687241685e-06
2023-01-23 03:47:52.616606: step: 1504/526, loss: 0.01704854890704155
2023-01-23 03:47:53.745176: step: 1508/526, loss: 7.758140418445691e-05
2023-01-23 03:47:54.894663: step: 1512/526, loss: 0.00525321951135993
2023-01-23 03:47:56.014425: step: 1516/526, loss: 0.00032634736271575093
2023-01-23 03:47:57.156423: step: 1520/526, loss: 0.015398693270981312
2023-01-23 03:47:58.287924: step: 1524/526, loss: 0.0006237507332116365
2023-01-23 03:47:59.417862: step: 1528/526, loss: 0.004484463017433882
2023-01-23 03:48:00.563499: step: 1532/526, loss: 0.05192699283361435
2023-01-23 03:48:01.680117: step: 1536/526, loss: 0.0070996759459376335
2023-01-23 03:48:02.805128: step: 1540/526, loss: 0.00010223388380836695
2023-01-23 03:48:03.944044: step: 1544/526, loss: 0.007494211196899414
2023-01-23 03:48:05.086859: step: 1548/526, loss: 0.03178148344159126
2023-01-23 03:48:06.250838: step: 1552/526, loss: 3.805160304182209e-05
2023-01-23 03:48:07.378997: step: 1556/526, loss: 0.047258712351322174
2023-01-23 03:48:08.502836: step: 1560/526, loss: 0.006660843268036842
2023-01-23 03:48:09.647832: step: 1564/526, loss: 0.08737526088953018
2023-01-23 03:48:10.754351: step: 1568/526, loss: 0.00011920928955078125
2023-01-23 03:48:11.861668: step: 1572/526, loss: 0.0018775940407067537
2023-01-23 03:48:13.015191: step: 1576/526, loss: 0.07419309765100479
2023-01-23 03:48:14.134467: step: 1580/526, loss: 0.0007379531743936241
2023-01-23 03:48:15.280311: step: 1584/526, loss: 0.05375843122601509
2023-01-23 03:48:16.424770: step: 1588/526, loss: 0.00013999939255882055
2023-01-23 03:48:17.579356: step: 1592/526, loss: 0.00026607513427734375
2023-01-23 03:48:18.700146: step: 1596/526, loss: 0.004611778538674116
2023-01-23 03:48:19.824080: step: 1600/526, loss: 0.007579517550766468
2023-01-23 03:48:20.960000: step: 1604/526, loss: 0.025613022968173027
2023-01-23 03:48:22.086503: step: 1608/526, loss: 0.00110626220703125
2023-01-23 03:48:23.230773: step: 1612/526, loss: 0.0025236131623387337
2023-01-23 03:48:24.363673: step: 1616/526, loss: 0.0002037048398051411
2023-01-23 03:48:25.511139: step: 1620/526, loss: 0.00012702941603492945
2023-01-23 03:48:26.653959: step: 1624/526, loss: 0.002845382783561945
2023-01-23 03:48:27.791676: step: 1628/526, loss: 8.049011375987902e-05
2023-01-23 03:48:28.923190: step: 1632/526, loss: 0.40420445799827576
2023-01-23 03:48:30.052545: step: 1636/526, loss: 5.0354006816633046e-05
2023-01-23 03:48:31.199086: step: 1640/526, loss: 2.956390380859375e-05
2023-01-23 03:48:32.331517: step: 1644/526, loss: 0.0019522667862474918
2023-01-23 03:48:33.467293: step: 1648/526, loss: 5.14984139954322e-06
2023-01-23 03:48:34.619652: step: 1652/526, loss: 0.00043964385986328125
2023-01-23 03:48:35.761788: step: 1656/526, loss: 0.020165156573057175
2023-01-23 03:48:36.890867: step: 1660/526, loss: 0.0002988815540447831
2023-01-23 03:48:37.994989: step: 1664/526, loss: 0.047823715955019
2023-01-23 03:48:39.109562: step: 1668/526, loss: -0.0
2023-01-23 03:48:40.245022: step: 1672/526, loss: 0.011056900024414062
2023-01-23 03:48:41.367627: step: 1676/526, loss: 0.003069305559620261
2023-01-23 03:48:42.499972: step: 1680/526, loss: 0.005118656437844038
2023-01-23 03:48:43.648162: step: 1684/526, loss: 0.003489971160888672
2023-01-23 03:48:44.757294: step: 1688/526, loss: 0.0018761157989501953
2023-01-23 03:48:45.881071: step: 1692/526, loss: 0.0032494545448571444
2023-01-23 03:48:47.036399: step: 1696/526, loss: 0.005176162347197533
2023-01-23 03:48:48.157875: step: 1700/526, loss: 0.0032299996819347143
2023-01-23 03:48:49.295260: step: 1704/526, loss: 4.673004150390625e-05
2023-01-23 03:48:50.462373: step: 1708/526, loss: 2.4890900022001006e-05
2023-01-23 03:48:51.613466: step: 1712/526, loss: 0.00055780413094908
2023-01-23 03:48:52.755951: step: 1716/526, loss: 0.01767864264547825
2023-01-23 03:48:53.890943: step: 1720/526, loss: 0.0003445625479798764
2023-01-23 03:48:55.033670: step: 1724/526, loss: 0.00011425017873989418
2023-01-23 03:48:56.157950: step: 1728/526, loss: 0.0015711784362792969
2023-01-23 03:48:57.312401: step: 1732/526, loss: 0.04193558543920517
2023-01-23 03:48:58.426098: step: 1736/526, loss: 5.91278057981981e-06
2023-01-23 03:48:59.545953: step: 1740/526, loss: 0.012828493490815163
2023-01-23 03:49:00.712020: step: 1744/526, loss: 0.00210914621129632
2023-01-23 03:49:01.838741: step: 1748/526, loss: 0.3500072658061981
2023-01-23 03:49:02.999312: step: 1752/526, loss: 0.005663109011948109
2023-01-23 03:49:04.137343: step: 1756/526, loss: 0.0003544807550497353
2023-01-23 03:49:05.263070: step: 1760/526, loss: 0.0001990795135498047
2023-01-23 03:49:06.371285: step: 1764/526, loss: 0.02201671525835991
2023-01-23 03:49:07.494211: step: 1768/526, loss: 0.0013246058952063322
2023-01-23 03:49:08.656079: step: 1772/526, loss: 0.00013217926607467234
2023-01-23 03:49:09.756310: step: 1776/526, loss: 0.014777851291000843
2023-01-23 03:49:10.905705: step: 1780/526, loss: 7.305145118152723e-05
2023-01-23 03:49:12.045375: step: 1784/526, loss: 0.011471175588667393
2023-01-23 03:49:13.192675: step: 1788/526, loss: 0.047315407544374466
2023-01-23 03:49:14.347951: step: 1792/526, loss: 0.007222938816994429
2023-01-23 03:49:15.472404: step: 1796/526, loss: 0.0006201743963174522
2023-01-23 03:49:16.668179: step: 1800/526, loss: 0.007343387696892023
2023-01-23 03:49:17.786354: step: 1804/526, loss: 0.0018410682678222656
2023-01-23 03:49:18.908536: step: 1808/526, loss: 0.0002980232238769531
2023-01-23 03:49:20.073536: step: 1812/526, loss: -5.4836273193359375e-06
2023-01-23 03:49:21.213574: step: 1816/526, loss: 0.03268451988697052
2023-01-23 03:49:22.353227: step: 1820/526, loss: 0.013419151306152344
2023-01-23 03:49:23.479614: step: 1824/526, loss: 0.02773771435022354
2023-01-23 03:49:24.617218: step: 1828/526, loss: 0.00028333664522506297
2023-01-23 03:49:25.767859: step: 1832/526, loss: 0.12107352912425995
2023-01-23 03:49:26.902902: step: 1836/526, loss: 0.024143792688846588
2023-01-23 03:49:28.008480: step: 1840/526, loss: 0.017164994031190872
2023-01-23 03:49:29.105113: step: 1844/526, loss: 8.449554297840223e-05
2023-01-23 03:49:30.226583: step: 1848/526, loss: 0.3749936819076538
2023-01-23 03:49:31.364996: step: 1852/526, loss: 0.00472183246165514
2023-01-23 03:49:32.500234: step: 1856/526, loss: 0.00114612584002316
2023-01-23 03:49:33.619966: step: 1860/526, loss: 2.6035308110294864e-05
2023-01-23 03:49:34.755819: step: 1864/526, loss: 0.0008787155384197831
2023-01-23 03:49:35.865398: step: 1868/526, loss: 0.015067482367157936
2023-01-23 03:49:37.007814: step: 1872/526, loss: 7.724762326688506e-06
2023-01-23 03:49:38.158199: step: 1876/526, loss: 0.0010809899540618062
2023-01-23 03:49:39.270312: step: 1880/526, loss: 0.0318942554295063
2023-01-23 03:49:40.410136: step: 1884/526, loss: 0.005975151434540749
2023-01-23 03:49:41.543150: step: 1888/526, loss: 0.008412457071244717
2023-01-23 03:49:42.698732: step: 1892/526, loss: 0.00031046869116835296
2023-01-23 03:49:43.871834: step: 1896/526, loss: 0.0007589340093545616
2023-01-23 03:49:44.993643: step: 1900/526, loss: 0.0001552104949951172
2023-01-23 03:49:46.131863: step: 1904/526, loss: 0.024302775040268898
2023-01-23 03:49:47.279342: step: 1908/526, loss: 0.0002381324884481728
2023-01-23 03:49:48.448069: step: 1912/526, loss: 0.018163396045565605
2023-01-23 03:49:49.597050: step: 1916/526, loss: 9.412765939487144e-05
2023-01-23 03:49:50.739994: step: 1920/526, loss: 1.3256073543743696e-05
2023-01-23 03:49:51.920245: step: 1924/526, loss: 0.06012916564941406
2023-01-23 03:49:53.053210: step: 1928/526, loss: 0.021240903064608574
2023-01-23 03:49:54.176503: step: 1932/526, loss: 0.00926980935037136
2023-01-23 03:49:55.309537: step: 1936/526, loss: 0.0023797035682946444
2023-01-23 03:49:56.488132: step: 1940/526, loss: 0.012895584106445312
2023-01-23 03:49:57.625070: step: 1944/526, loss: 0.0018672943115234375
2023-01-23 03:49:58.807777: step: 1948/526, loss: 0.014040709473192692
2023-01-23 03:49:59.985856: step: 1952/526, loss: 1.621246337890625e-05
2023-01-23 03:50:01.132342: step: 1956/526, loss: 0.00034794810926541686
2023-01-23 03:50:02.283237: step: 1960/526, loss: 0.0002079010009765625
2023-01-23 03:50:03.405361: step: 1964/526, loss: 0.0021209716796875
2023-01-23 03:50:04.552990: step: 1968/526, loss: 0.007848930545151234
2023-01-23 03:50:05.698769: step: 1972/526, loss: 0.0007929801940917969
2023-01-23 03:50:06.818144: step: 1976/526, loss: 0.00033969880314543843
2023-01-23 03:50:07.935988: step: 1980/526, loss: 0.0021348954178392887
2023-01-23 03:50:09.067517: step: 1984/526, loss: 0.0006766319274902344
2023-01-23 03:50:10.177865: step: 1988/526, loss: 0.13882236182689667
2023-01-23 03:50:11.321556: step: 1992/526, loss: 0.00038022996159270406
2023-01-23 03:50:12.448438: step: 1996/526, loss: 0.010604476556181908
2023-01-23 03:50:13.604853: step: 2000/526, loss: 0.0010848998790606856
2023-01-23 03:50:14.714596: step: 2004/526, loss: 0.00010786057100631297
2023-01-23 03:50:15.847835: step: 2008/526, loss: 0.01777353323996067
2023-01-23 03:50:16.974537: step: 2012/526, loss: 0.01016454678028822
2023-01-23 03:50:18.113489: step: 2016/526, loss: 0.011587905697524548
2023-01-23 03:50:19.233706: step: 2020/526, loss: 0.0012754440540447831
2023-01-23 03:50:20.379268: step: 2024/526, loss: 3.013610876223538e-05
2023-01-23 03:50:21.496017: step: 2028/526, loss: 0.00038013458834029734
2023-01-23 03:50:22.626286: step: 2032/526, loss: 0.0002818107604980469
2023-01-23 03:50:23.739115: step: 2036/526, loss: 3.4809113458322827e-06
2023-01-23 03:50:24.885925: step: 2040/526, loss: 0.009374809451401234
2023-01-23 03:50:25.999479: step: 2044/526, loss: 0.0018835067749023438
2023-01-23 03:50:27.134680: step: 2048/526, loss: 0.018840981647372246
2023-01-23 03:50:28.285646: step: 2052/526, loss: 0.0005063057178631425
2023-01-23 03:50:29.407011: step: 2056/526, loss: 8.964539119915571e-06
2023-01-23 03:50:30.550299: step: 2060/526, loss: 0.6696677207946777
2023-01-23 03:50:31.673635: step: 2064/526, loss: 4.634857032215223e-05
2023-01-23 03:50:32.797861: step: 2068/526, loss: 0.00021247864060569555
2023-01-23 03:50:33.969664: step: 2072/526, loss: 0.0015189171535894275
2023-01-23 03:50:35.081469: step: 2076/526, loss: 0.008635425940155983
2023-01-23 03:50:36.229720: step: 2080/526, loss: 0.0007112979656085372
2023-01-23 03:50:37.385194: step: 2084/526, loss: -1.087188684323337e-05
2023-01-23 03:50:38.515381: step: 2088/526, loss: -2.2506712411995977e-05
2023-01-23 03:50:39.631962: step: 2092/526, loss: 2.8991700673941523e-05
2023-01-23 03:50:40.759074: step: 2096/526, loss: 0.00027294160099700093
2023-01-23 03:50:41.912008: step: 2100/526, loss: 0.00018835067749023438
2023-01-23 03:50:43.078985: step: 2104/526, loss: 6.365776062011719e-05
==================================================
Loss: 0.018
--------------------
Dev: {'event': {'p': 0.5985552115583075, 'r': 0.7723035952063915, 'f1': 0.6744186046511628}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 24}
Test: {'event': {'p': 0.6182707993474714, 'r': 0.791231732776618, 'f1': 0.694139194139194}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 24}
Chinese: {'event': {'p': 0.5844155844155844, 'r': 0.8333333333333334, 'f1': 0.6870229007633588}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 24}
Korean: {'event': {'p': 0.6888888888888889, 'r': 0.49206349206349204, 'f1': 0.5740740740740741}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 24}
Russian: {'event': {'p': 0.42857142857142855, 'r': 0.5, 'f1': 0.4615384615384615}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 24}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6266519823788547, 'r': 0.7576564580559254, 'f1': 0.6859553948161543}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Eng Test for Chinese: {'event': {'p': 0.6313522825150732, 'r': 0.7651356993736952, 'f1': 0.6918357715903728}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Sample Chinese: {'event': {'p': 0.6621621621621622, 'r': 0.9074074074074074, 'f1': 0.765625}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6257995735607675, 'r': 0.7816245006657789, 'f1': 0.6950858496151568}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Eng Test for Korean: {'event': {'p': 0.623113410952997, 'r': 0.7541753653444676, 'f1': 0.6824085005903188}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Sample Korean: {'event': {'p': 0.7446808510638298, 'r': 0.5555555555555556, 'f1': 0.6363636363636364}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6266519823788547, 'r': 0.7576564580559254, 'f1': 0.6859553948161543}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Eng Test for Russian: {'event': {'p': 0.6313522825150732, 'r': 0.7651356993736952, 'f1': 0.6918357715903728}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Sample Russian: {'event': {'p': 0.5384615384615384, 'r': 0.5833333333333334, 'f1': 0.5599999999999999}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
******************************
Epoch: 25
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 03:51:25.953779: step: 4/526, loss: 0.02930307388305664
2023-01-23 03:51:27.101087: step: 8/526, loss: 0.04721498861908913
2023-01-23 03:51:28.228546: step: 12/526, loss: 1.7166138377433526e-06
2023-01-23 03:51:29.355421: step: 16/526, loss: 0.0007007598760537803
2023-01-23 03:51:30.480491: step: 20/526, loss: 0.025460338220000267
2023-01-23 03:51:31.600680: step: 24/526, loss: 4.954338146490045e-05
2023-01-23 03:51:32.741146: step: 28/526, loss: 0.00046215057955123484
2023-01-23 03:51:33.863302: step: 32/526, loss: 0.12230377644300461
2023-01-23 03:51:35.010582: step: 36/526, loss: 4.5299530029296875e-05
2023-01-23 03:51:36.148744: step: 40/526, loss: 0.040052127093076706
2023-01-23 03:51:37.254821: step: 44/526, loss: 0.0003772735653910786
2023-01-23 03:51:38.359098: step: 48/526, loss: 0.0046042026951909065
2023-01-23 03:51:39.498814: step: 52/526, loss: 0.00035533905611373484
2023-01-23 03:51:40.656811: step: 56/526, loss: 0.0014753341674804688
2023-01-23 03:51:41.794131: step: 60/526, loss: 0.0007164001581259072
2023-01-23 03:51:42.932368: step: 64/526, loss: 0.00021076203847769648
2023-01-23 03:51:44.046776: step: 68/526, loss: 0.0056937215849757195
2023-01-23 03:51:45.189240: step: 72/526, loss: 0.007486533839255571
2023-01-23 03:51:46.346149: step: 76/526, loss: 0.0001832008274504915
2023-01-23 03:51:47.467879: step: 80/526, loss: 5.245208740234375e-06
2023-01-23 03:51:48.594381: step: 84/526, loss: 3.910065061063506e-06
2023-01-23 03:51:49.755150: step: 88/526, loss: 0.005286216735839844
2023-01-23 03:51:50.900017: step: 92/526, loss: 2.8324126105871983e-05
2023-01-23 03:51:52.020362: step: 96/526, loss: 0.003423976944759488
2023-01-23 03:51:53.156619: step: 100/526, loss: 3.862381163344253e-06
2023-01-23 03:51:54.301202: step: 104/526, loss: 0.0007698058616369963
2023-01-23 03:51:55.432563: step: 108/526, loss: 0.0009496689308434725
2023-01-23 03:51:56.548559: step: 112/526, loss: 0.07140665501356125
2023-01-23 03:51:57.687041: step: 116/526, loss: 0.00467834435403347
2023-01-23 03:51:58.860672: step: 120/526, loss: 0.0016530990833416581
2023-01-23 03:52:00.000853: step: 124/526, loss: 0.0007596969371661544
2023-01-23 03:52:01.120627: step: 128/526, loss: 0.001174282981082797
2023-01-23 03:52:02.258851: step: 132/526, loss: 0.051836684346199036
2023-01-23 03:52:03.375122: step: 136/526, loss: 0.0017196654807776213
2023-01-23 03:52:04.507973: step: 140/526, loss: -1.2397763384797145e-06
2023-01-23 03:52:05.637089: step: 144/526, loss: 0.015848541632294655
2023-01-23 03:52:06.789154: step: 148/526, loss: 0.021215438842773438
2023-01-23 03:52:07.934494: step: 152/526, loss: 5.674362000718247e-06
2023-01-23 03:52:09.072983: step: 156/526, loss: 0.025526810437440872
2023-01-23 03:52:10.201374: step: 160/526, loss: 0.0024314881302416325
2023-01-23 03:52:11.350053: step: 164/526, loss: 0.0006305694114416838
2023-01-23 03:52:12.454736: step: 168/526, loss: 0.0001483917294535786
2023-01-23 03:52:13.622515: step: 172/526, loss: 0.0022073746658861637
2023-01-23 03:52:14.756375: step: 176/526, loss: 9.117127046920359e-05
2023-01-23 03:52:15.872788: step: 180/526, loss: 0.0001585006684763357
2023-01-23 03:52:16.995944: step: 184/526, loss: 0.04893188551068306
2023-01-23 03:52:18.116842: step: 188/526, loss: 8.03947405074723e-05
2023-01-23 03:52:19.288352: step: 192/526, loss: 0.001464462373405695
2023-01-23 03:52:20.402349: step: 196/526, loss: 3.4046173823298886e-05
2023-01-23 03:52:21.535588: step: 200/526, loss: 1.506805438111769e-05
2023-01-23 03:52:22.670560: step: 204/526, loss: 0.008358573541045189
2023-01-23 03:52:23.775966: step: 208/526, loss: 3.4618376957951114e-05
2023-01-23 03:52:24.896858: step: 212/526, loss: -6.675721124338452e-06
2023-01-23 03:52:26.025993: step: 216/526, loss: 0.032373812049627304
2023-01-23 03:52:27.182306: step: 220/526, loss: 3.2901763916015625e-05
2023-01-23 03:52:28.291162: step: 224/526, loss: 0.00879597757011652
2023-01-23 03:52:29.436437: step: 228/526, loss: 0.003954506013542414
2023-01-23 03:52:30.558650: step: 232/526, loss: 0.001010894775390625
2023-01-23 03:52:31.682622: step: 236/526, loss: 3.461838059592992e-05
2023-01-23 03:52:32.832822: step: 240/526, loss: -7.43865984986769e-06
2023-01-23 03:52:33.965428: step: 244/526, loss: 0.005058479495346546
2023-01-23 03:52:35.101329: step: 248/526, loss: 0.014174079522490501
2023-01-23 03:52:36.237135: step: 252/526, loss: 4.041195279569365e-05
2023-01-23 03:52:37.391562: step: 256/526, loss: 0.11412124335765839
2023-01-23 03:52:38.502323: step: 260/526, loss: 0.0003936767752747983
2023-01-23 03:52:39.649513: step: 264/526, loss: 0.007677269168198109
2023-01-23 03:52:40.747869: step: 268/526, loss: 0.0005231857649050653
2023-01-23 03:52:41.902647: step: 272/526, loss: 0.011204719543457031
2023-01-23 03:52:43.046964: step: 276/526, loss: 0.0002613067626953125
2023-01-23 03:52:44.167924: step: 280/526, loss: 0.081090547144413
2023-01-23 03:52:45.313212: step: 284/526, loss: 0.0013433456188067794
2023-01-23 03:52:46.437949: step: 288/526, loss: 0.00867304764688015
2023-01-23 03:52:47.546649: step: 292/526, loss: 8.258819434558973e-05
2023-01-23 03:52:48.706763: step: 296/526, loss: 0.0012937545543536544
2023-01-23 03:52:49.828514: step: 300/526, loss: 0.0004927635309286416
2023-01-23 03:52:50.956484: step: 304/526, loss: 0.023227596655488014
2023-01-23 03:52:52.100855: step: 308/526, loss: 0.026096869260072708
2023-01-23 03:52:53.227019: step: 312/526, loss: 0.019597148522734642
2023-01-23 03:52:54.354733: step: 316/526, loss: 0.0008947373135015368
2023-01-23 03:52:55.479021: step: 320/526, loss: -7.629391802765895e-07
2023-01-23 03:52:56.595672: step: 324/526, loss: 0.0008543014992028475
2023-01-23 03:52:57.687939: step: 328/526, loss: 9.441375732421875e-05
2023-01-23 03:52:58.810512: step: 332/526, loss: 0.0010314941173419356
2023-01-23 03:52:59.983455: step: 336/526, loss: 0.028462981805205345
2023-01-23 03:53:01.085984: step: 340/526, loss: -9.536742595628311e-08
2023-01-23 03:53:02.210190: step: 344/526, loss: 0.03591118007898331
2023-01-23 03:53:03.346023: step: 348/526, loss: 0.0002541542053222656
2023-01-23 03:53:04.499375: step: 352/526, loss: 0.07203960418701172
2023-01-23 03:53:05.630053: step: 356/526, loss: 0.002747821621596813
2023-01-23 03:53:06.798933: step: 360/526, loss: 0.00025215151254087687
2023-01-23 03:53:07.951567: step: 364/526, loss: 0.0003071785031352192
2023-01-23 03:53:09.062251: step: 368/526, loss: 1.964569128176663e-05
2023-01-23 03:53:10.220676: step: 372/526, loss: 0.0003894805849995464
2023-01-23 03:53:11.337028: step: 376/526, loss: 0.004029655363410711
2023-01-23 03:53:12.464774: step: 380/526, loss: 0.00010814666893566027
2023-01-23 03:53:13.614262: step: 384/526, loss: 0.011087036691606045
2023-01-23 03:53:14.736180: step: 388/526, loss: 0.0011505127185955644
2023-01-23 03:53:15.868201: step: 392/526, loss: 0.0016177654033526778
2023-01-23 03:53:17.025272: step: 396/526, loss: 0.000289726274786517
2023-01-23 03:53:18.185038: step: 400/526, loss: 8.125305612338707e-05
2023-01-23 03:53:19.323433: step: 404/526, loss: 0.00697903661057353
2023-01-23 03:53:20.423475: step: 408/526, loss: 1.0299683708581142e-05
2023-01-23 03:53:21.537419: step: 412/526, loss: -5.722046125811175e-07
2023-01-23 03:53:22.676751: step: 416/526, loss: 0.01753692701458931
2023-01-23 03:53:23.851602: step: 420/526, loss: 0.005646086297929287
2023-01-23 03:53:24.986774: step: 424/526, loss: 0.0003219604550395161
2023-01-23 03:53:26.118701: step: 428/526, loss: 0.004481506533920765
2023-01-23 03:53:27.264373: step: 432/526, loss: 0.013388622552156448
2023-01-23 03:53:28.398554: step: 436/526, loss: 0.00013456345186568797
2023-01-23 03:53:29.523012: step: 440/526, loss: 0.01545257493853569
2023-01-23 03:53:30.636425: step: 444/526, loss: 0.005069160833954811
2023-01-23 03:53:31.770759: step: 448/526, loss: 0.025766562670469284
2023-01-23 03:53:32.897467: step: 452/526, loss: 0.00119065644685179
2023-01-23 03:53:34.071895: step: 456/526, loss: 0.003124427981674671
2023-01-23 03:53:35.194803: step: 460/526, loss: -5.769729796156753e-06
2023-01-23 03:53:36.330456: step: 464/526, loss: 3.108978125965223e-05
2023-01-23 03:53:37.457167: step: 468/526, loss: 0.00037212372990325093
2023-01-23 03:53:38.585005: step: 472/526, loss: 3.2711028325138614e-05
2023-01-23 03:53:39.717562: step: 476/526, loss: 0.0009131432161666453
2023-01-23 03:53:40.869701: step: 480/526, loss: 0.00037479400634765625
2023-01-23 03:53:42.023732: step: 484/526, loss: 1.449584942747606e-05
2023-01-23 03:53:43.168219: step: 488/526, loss: 0.0009846687316894531
2023-01-23 03:53:44.306640: step: 492/526, loss: 0.0003299713134765625
2023-01-23 03:53:45.413593: step: 496/526, loss: 0.004880142398178577
2023-01-23 03:53:46.560249: step: 500/526, loss: 1.6593934560660273e-05
2023-01-23 03:53:47.677498: step: 504/526, loss: 0.0005884647252969444
2023-01-23 03:53:48.815703: step: 508/526, loss: 8.487701052217744e-06
2023-01-23 03:53:49.935368: step: 512/526, loss: 8.087157766567543e-05
2023-01-23 03:53:51.103335: step: 516/526, loss: 0.011248111724853516
2023-01-23 03:53:52.259253: step: 520/526, loss: 0.01270752027630806
2023-01-23 03:53:53.404001: step: 524/526, loss: 0.012514687143266201
2023-01-23 03:53:54.552473: step: 528/526, loss: 3.681182715808973e-05
2023-01-23 03:53:55.706307: step: 532/526, loss: 0.0004520416259765625
2023-01-23 03:53:56.851807: step: 536/526, loss: 0.003604126162827015
2023-01-23 03:53:57.977921: step: 540/526, loss: 6.12258882028982e-05
2023-01-23 03:53:59.100126: step: 544/526, loss: 0.0019002915360033512
2023-01-23 03:54:00.216067: step: 548/526, loss: 0.004593372344970703
2023-01-23 03:54:01.349765: step: 552/526, loss: 0.011429023928940296
2023-01-23 03:54:02.478235: step: 556/526, loss: 0.003665924072265625
2023-01-23 03:54:03.612068: step: 560/526, loss: 0.011133193969726562
2023-01-23 03:54:04.727713: step: 564/526, loss: 0.0021597864106297493
2023-01-23 03:54:05.850154: step: 568/526, loss: 0.006019401829689741
2023-01-23 03:54:06.991018: step: 572/526, loss: 0.10567913204431534
2023-01-23 03:54:08.150642: step: 576/526, loss: 0.0020154952071607113
2023-01-23 03:54:09.306588: step: 580/526, loss: 0.056601669639348984
2023-01-23 03:54:10.447225: step: 584/526, loss: 2.002715973503655e-06
2023-01-23 03:54:11.592682: step: 588/526, loss: 0.0002389907749602571
2023-01-23 03:54:12.730595: step: 592/526, loss: 0.006484031677246094
2023-01-23 03:54:13.920143: step: 596/526, loss: 0.014467430301010609
2023-01-23 03:54:15.030116: step: 600/526, loss: 0.00019912720017600805
2023-01-23 03:54:16.137146: step: 604/526, loss: 3.471374657237902e-05
2023-01-23 03:54:17.264168: step: 608/526, loss: 0.00933847390115261
2023-01-23 03:54:18.402152: step: 612/526, loss: 0.0008516312227584422
2023-01-23 03:54:19.522034: step: 616/526, loss: 0.0021648884285241365
2023-01-23 03:54:20.656344: step: 620/526, loss: 0.0027592184487730265
2023-01-23 03:54:21.781360: step: 624/526, loss: 0.0009501457680016756
2023-01-23 03:54:22.891802: step: 628/526, loss: 0.026536082848906517
2023-01-23 03:54:24.043568: step: 632/526, loss: 0.045363474637269974
2023-01-23 03:54:25.239963: step: 636/526, loss: 0.0002666473446879536
2023-01-23 03:54:26.374733: step: 640/526, loss: 0.037862878292798996
2023-01-23 03:54:27.511147: step: 644/526, loss: 0.00020294188288971782
2023-01-23 03:54:28.656406: step: 648/526, loss: 0.00828852690756321
2023-01-23 03:54:29.800132: step: 652/526, loss: 0.04934177175164223
2023-01-23 03:54:30.923362: step: 656/526, loss: 0.026671981438994408
2023-01-23 03:54:32.064438: step: 660/526, loss: 0.015010691247880459
2023-01-23 03:54:33.188062: step: 664/526, loss: 0.0007877349853515625
2023-01-23 03:54:34.350375: step: 668/526, loss: 0.005845355801284313
2023-01-23 03:54:35.446738: step: 672/526, loss: 9.536744016713783e-08
2023-01-23 03:54:36.611672: step: 676/526, loss: 0.0005153656238690019
2023-01-23 03:54:37.738661: step: 680/526, loss: 0.02548046037554741
2023-01-23 03:54:38.848649: step: 684/526, loss: 0.00014467239088844508
2023-01-23 03:54:40.001117: step: 688/526, loss: 0.0018161773914471269
2023-01-23 03:54:41.124765: step: 692/526, loss: 1.1634827387752011e-05
2023-01-23 03:54:42.302937: step: 696/526, loss: 0.0023976326920092106
2023-01-23 03:54:43.433367: step: 700/526, loss: 0.0037027359940111637
2023-01-23 03:54:44.578387: step: 704/526, loss: -1.1253356205997989e-05
2023-01-23 03:54:45.705162: step: 708/526, loss: 0.1141473799943924
2023-01-23 03:54:46.854393: step: 712/526, loss: 0.012693977914750576
2023-01-23 03:54:47.945145: step: 716/526, loss: 3.814697265625e-06
2023-01-23 03:54:49.097094: step: 720/526, loss: 0.36805686354637146
2023-01-23 03:54:50.220162: step: 724/526, loss: 0.015682794153690338
2023-01-23 03:54:51.362828: step: 728/526, loss: 0.017478562891483307
2023-01-23 03:54:52.496804: step: 732/526, loss: 0.03909454494714737
2023-01-23 03:54:53.676321: step: 736/526, loss: 7.82012939453125e-05
2023-01-23 03:54:54.804762: step: 740/526, loss: 0.0005135297542437911
2023-01-23 03:54:55.955688: step: 744/526, loss: 4.9591067181609105e-06
2023-01-23 03:54:57.134114: step: 748/526, loss: 0.00016045570373535156
2023-01-23 03:54:58.262321: step: 752/526, loss: 0.00846099853515625
2023-01-23 03:54:59.358470: step: 756/526, loss: 0.006530380342155695
2023-01-23 03:55:00.461363: step: 760/526, loss: 0.0071388245560228825
2023-01-23 03:55:01.595185: step: 764/526, loss: 0.0018610954284667969
2023-01-23 03:55:02.703347: step: 768/526, loss: 0.00010395050048828125
2023-01-23 03:55:03.836225: step: 772/526, loss: 0.0001646041782805696
2023-01-23 03:55:04.937411: step: 776/526, loss: 0.034526824951171875
2023-01-23 03:55:06.065309: step: 780/526, loss: 5.078315552964341e-06
2023-01-23 03:55:07.192324: step: 784/526, loss: 0.004657936282455921
2023-01-23 03:55:08.309688: step: 788/526, loss: 0.00014991759962867945
2023-01-23 03:55:09.426779: step: 792/526, loss: 0.0002193450927734375
2023-01-23 03:55:10.550999: step: 796/526, loss: 8.20159948489163e-06
2023-01-23 03:55:11.664295: step: 800/526, loss: 0.0005762100336141884
2023-01-23 03:55:12.775300: step: 804/526, loss: 9.126662916969508e-05
2023-01-23 03:55:13.895882: step: 808/526, loss: 0.06104621663689613
2023-01-23 03:55:15.044049: step: 812/526, loss: 0.0007038116455078125
2023-01-23 03:55:16.143445: step: 816/526, loss: 0.0010636806255206466
2023-01-23 03:55:17.256676: step: 820/526, loss: 0.0005322843790054321
2023-01-23 03:55:18.435861: step: 824/526, loss: 0.000579833984375
2023-01-23 03:55:19.542117: step: 828/526, loss: 8.316040475619957e-05
2023-01-23 03:55:20.659209: step: 832/526, loss: 0.0018756866920739412
2023-01-23 03:55:21.778577: step: 836/526, loss: 0.0017618179554119706
2023-01-23 03:55:22.926171: step: 840/526, loss: 0.03902454674243927
2023-01-23 03:55:24.054019: step: 844/526, loss: 0.04044094309210777
2023-01-23 03:55:25.182707: step: 848/526, loss: 0.04602847248315811
2023-01-23 03:55:26.322317: step: 852/526, loss: 0.012273024767637253
2023-01-23 03:55:27.462240: step: 856/526, loss: 0.0018209457630291581
2023-01-23 03:55:28.588999: step: 860/526, loss: 3.4332276754867053e-06
2023-01-23 03:55:29.727422: step: 864/526, loss: 0.015171051025390625
2023-01-23 03:55:30.827580: step: 868/526, loss: -3.623962356869015e-06
2023-01-23 03:55:31.962493: step: 872/526, loss: 0.0035392760764807463
2023-01-23 03:55:33.100591: step: 876/526, loss: 0.03569640964269638
2023-01-23 03:55:34.231586: step: 880/526, loss: 2.822876012942288e-05
2023-01-23 03:55:35.363346: step: 884/526, loss: 0.22572708129882812
2023-01-23 03:55:36.489091: step: 888/526, loss: 0.004665422718971968
2023-01-23 03:55:37.626900: step: 892/526, loss: 1.430511474609375e-05
2023-01-23 03:55:38.766836: step: 896/526, loss: 0.0027769089210778475
2023-01-23 03:55:39.891458: step: 900/526, loss: 0.0001483917294535786
2023-01-23 03:55:41.014247: step: 904/526, loss: 0.0030285834800451994
2023-01-23 03:55:42.163469: step: 908/526, loss: 0.00257282261736691
2023-01-23 03:55:43.362574: step: 912/526, loss: 0.017187023535370827
2023-01-23 03:55:44.494032: step: 916/526, loss: 0.011454201303422451
2023-01-23 03:55:45.633244: step: 920/526, loss: 0.3685436248779297
2023-01-23 03:55:46.770014: step: 924/526, loss: 0.019519424065947533
2023-01-23 03:55:47.916492: step: 928/526, loss: 0.04216348007321358
2023-01-23 03:55:49.085831: step: 932/526, loss: 0.027657128870487213
2023-01-23 03:55:50.225812: step: 936/526, loss: 0.007106495089828968
2023-01-23 03:55:51.377545: step: 940/526, loss: 0.0003859996795654297
2023-01-23 03:55:52.505186: step: 944/526, loss: 1.4591217222914565e-05
2023-01-23 03:55:53.636040: step: 948/526, loss: 0.0023360252380371094
2023-01-23 03:55:54.786706: step: 952/526, loss: 0.03049764782190323
2023-01-23 03:55:55.926396: step: 956/526, loss: 1.659393274167087e-05
2023-01-23 03:55:57.144404: step: 960/526, loss: -4.291534423828125e-06
2023-01-23 03:55:58.258647: step: 964/526, loss: 0.028342438861727715
2023-01-23 03:55:59.398471: step: 968/526, loss: 0.0014786720275878906
2023-01-23 03:56:00.537595: step: 972/526, loss: 0.007918739691376686
2023-01-23 03:56:01.678415: step: 976/526, loss: 0.0002422332763671875
2023-01-23 03:56:02.790403: step: 980/526, loss: 0.0006341934204101562
2023-01-23 03:56:03.917367: step: 984/526, loss: 0.0004841327609028667
2023-01-23 03:56:05.033952: step: 988/526, loss: 0.00021295547776389867
2023-01-23 03:56:06.174487: step: 992/526, loss: 0.00031604766263626516
2023-01-23 03:56:07.312616: step: 996/526, loss: 0.00686149625107646
2023-01-23 03:56:08.465681: step: 1000/526, loss: 0.04132575914263725
2023-01-23 03:56:09.622819: step: 1004/526, loss: 0.010339736938476562
2023-01-23 03:56:10.760741: step: 1008/526, loss: 0.00044403073843568563
2023-01-23 03:56:11.886331: step: 1012/526, loss: 0.0029230117797851562
2023-01-23 03:56:13.009219: step: 1016/526, loss: 0.0018386841984465718
2023-01-23 03:56:14.122425: step: 1020/526, loss: 0.00011067390732932836
2023-01-23 03:56:15.302283: step: 1024/526, loss: 0.01800861395895481
2023-01-23 03:56:16.424133: step: 1028/526, loss: 0.03227043151855469
2023-01-23 03:56:17.578511: step: 1032/526, loss: 0.024683762341737747
2023-01-23 03:56:18.703741: step: 1036/526, loss: 0.01766028441488743
2023-01-23 03:56:19.830643: step: 1040/526, loss: 2.0790101189049892e-05
2023-01-23 03:56:20.972103: step: 1044/526, loss: 0.0006039619329385459
2023-01-23 03:56:22.082934: step: 1048/526, loss: 0.0011785507667809725
2023-01-23 03:56:23.213674: step: 1052/526, loss: 0.019766902551054955
2023-01-23 03:56:24.384002: step: 1056/526, loss: 0.03691139444708824
2023-01-23 03:56:25.519137: step: 1060/526, loss: 0.0012372970813885331
2023-01-23 03:56:26.668083: step: 1064/526, loss: 1.506805438111769e-05
2023-01-23 03:56:27.798267: step: 1068/526, loss: 0.0003185272216796875
2023-01-23 03:56:28.961133: step: 1072/526, loss: 0.002008295152336359
2023-01-23 03:56:30.073655: step: 1076/526, loss: 0.00754814175888896
2023-01-23 03:56:31.219512: step: 1080/526, loss: 6.179809861350805e-05
2023-01-23 03:56:32.366587: step: 1084/526, loss: 6.732940528308973e-05
2023-01-23 03:56:33.487084: step: 1088/526, loss: 0.00010747909982455894
2023-01-23 03:56:34.637829: step: 1092/526, loss: 0.04722805321216583
2023-01-23 03:56:35.800376: step: 1096/526, loss: 0.006152534857392311
2023-01-23 03:56:36.965852: step: 1100/526, loss: 0.00010032653517555445
2023-01-23 03:56:38.143093: step: 1104/526, loss: 0.008452988229691982
2023-01-23 03:56:39.296491: step: 1108/526, loss: 0.0018753051990643144
2023-01-23 03:56:40.417492: step: 1112/526, loss: 7.152557373046875e-05
2023-01-23 03:56:41.556673: step: 1116/526, loss: 0.014368534088134766
2023-01-23 03:56:42.683323: step: 1120/526, loss: 0.00046539306640625
2023-01-23 03:56:43.815574: step: 1124/526, loss: 2.1743775505456142e-05
2023-01-23 03:56:44.981621: step: 1128/526, loss: 0.021529100835323334
2023-01-23 03:56:46.081032: step: 1132/526, loss: 0.004278755281120539
2023-01-23 03:56:47.216679: step: 1136/526, loss: 0.0002008915034821257
2023-01-23 03:56:48.345809: step: 1140/526, loss: 0.0007059097406454384
2023-01-23 03:56:49.441076: step: 1144/526, loss: 0.00031871796818450093
2023-01-23 03:56:50.563236: step: 1148/526, loss: 0.0003121376212220639
2023-01-23 03:56:51.694537: step: 1152/526, loss: 0.013891697861254215
2023-01-23 03:56:52.841893: step: 1156/526, loss: 0.024333763867616653
2023-01-23 03:56:53.955141: step: 1160/526, loss: 0.0025947571266442537
2023-01-23 03:56:55.062306: step: 1164/526, loss: 0.0001605987490620464
2023-01-23 03:56:56.190626: step: 1168/526, loss: 0.0017118455143645406
2023-01-23 03:56:57.335240: step: 1172/526, loss: 0.003590821987017989
2023-01-23 03:56:58.507992: step: 1176/526, loss: 0.024665450677275658
2023-01-23 03:56:59.659402: step: 1180/526, loss: 0.02268209494650364
2023-01-23 03:57:00.764709: step: 1184/526, loss: 0.0011107444297522306
2023-01-23 03:57:01.905052: step: 1188/526, loss: 2.9373170036706142e-05
2023-01-23 03:57:03.064181: step: 1192/526, loss: 0.02532787248492241
2023-01-23 03:57:04.225150: step: 1196/526, loss: 0.0009091377141885459
2023-01-23 03:57:05.356697: step: 1200/526, loss: 0.003118324326351285
2023-01-23 03:57:06.464505: step: 1204/526, loss: 0.0008320808410644531
2023-01-23 03:57:07.601292: step: 1208/526, loss: 0.00031528473482467234
2023-01-23 03:57:08.750291: step: 1212/526, loss: 0.031816866248846054
2023-01-23 03:57:09.879743: step: 1216/526, loss: 0.0009879112476482987
2023-01-23 03:57:11.021227: step: 1220/526, loss: 0.0006337165832519531
2023-01-23 03:57:12.172236: step: 1224/526, loss: 0.6496032476425171
2023-01-23 03:57:13.411775: step: 1228/526, loss: 1.2874604180979077e-05
2023-01-23 03:57:14.553835: step: 1232/526, loss: 0.0019760846626013517
2023-01-23 03:57:15.658580: step: 1236/526, loss: 0.0003295898495707661
2023-01-23 03:57:16.803695: step: 1240/526, loss: 0.003175163408741355
2023-01-23 03:57:17.932250: step: 1244/526, loss: 0.00020513535127975047
2023-01-23 03:57:19.060277: step: 1248/526, loss: 5.2165985835017636e-05
2023-01-23 03:57:20.188435: step: 1252/526, loss: 3.0517578125e-05
2023-01-23 03:57:21.322021: step: 1256/526, loss: 0.001052475068718195
2023-01-23 03:57:22.481459: step: 1260/526, loss: 0.014911365695297718
2023-01-23 03:57:23.615469: step: 1264/526, loss: 0.0041027069091796875
2023-01-23 03:57:24.752451: step: 1268/526, loss: 0.0008115768432617188
2023-01-23 03:57:25.934489: step: 1272/526, loss: 0.004632758907973766
2023-01-23 03:57:27.063409: step: 1276/526, loss: 0.0002115249662892893
2023-01-23 03:57:28.173066: step: 1280/526, loss: 0.0008586883777752519
2023-01-23 03:57:29.312017: step: 1284/526, loss: 0.0020294189453125
2023-01-23 03:57:30.455581: step: 1288/526, loss: 0.0013658524258062243
2023-01-23 03:57:31.585009: step: 1292/526, loss: 0.000529861485119909
2023-01-23 03:57:32.723323: step: 1296/526, loss: 0.003073024796321988
2023-01-23 03:57:33.842085: step: 1300/526, loss: 0.013638305477797985
2023-01-23 03:57:34.965797: step: 1304/526, loss: 0.0015863418811932206
2023-01-23 03:57:36.075295: step: 1308/526, loss: 0.00022411346435546875
2023-01-23 03:57:37.189486: step: 1312/526, loss: 6.809234764659777e-05
2023-01-23 03:57:38.309544: step: 1316/526, loss: 0.0008967399480752647
2023-01-23 03:57:39.418709: step: 1320/526, loss: 0.011912345886230469
2023-01-23 03:57:40.561579: step: 1324/526, loss: 3.337860107421875e-05
2023-01-23 03:57:41.687693: step: 1328/526, loss: 0.00169200892560184
2023-01-23 03:57:42.799202: step: 1332/526, loss: 0.00022325516329146922
2023-01-23 03:57:43.954871: step: 1336/526, loss: 0.011070584878325462
2023-01-23 03:57:45.111212: step: 1340/526, loss: 5.187988426769152e-05
2023-01-23 03:57:46.265981: step: 1344/526, loss: 1.163482647825731e-05
2023-01-23 03:57:47.384868: step: 1348/526, loss: 0.014441752806305885
2023-01-23 03:57:48.545246: step: 1352/526, loss: 0.00017395020404364914
2023-01-23 03:57:49.684894: step: 1356/526, loss: 0.0003949165402445942
2023-01-23 03:57:50.827935: step: 1360/526, loss: 0.00042104723979718983
2023-01-23 03:57:51.970266: step: 1364/526, loss: 0.000446128862677142
2023-01-23 03:57:53.112715: step: 1368/526, loss: 0.009949063882231712
2023-01-23 03:57:54.241620: step: 1372/526, loss: 0.004015636630356312
2023-01-23 03:57:55.354656: step: 1376/526, loss: 0.0001991748868022114
2023-01-23 03:57:56.507160: step: 1380/526, loss: 8.716584125068039e-05
2023-01-23 03:57:57.636220: step: 1384/526, loss: 0.0002954483206849545
2023-01-23 03:57:58.791330: step: 1388/526, loss: 0.06758461147546768
2023-01-23 03:57:59.924320: step: 1392/526, loss: 0.0004936218028888106
2023-01-23 03:58:01.046428: step: 1396/526, loss: 0.003154182340949774
2023-01-23 03:58:02.186717: step: 1400/526, loss: 0.044655606150627136
2023-01-23 03:58:03.330710: step: 1404/526, loss: 0.025870133191347122
2023-01-23 03:58:04.426936: step: 1408/526, loss: 0.004344177432358265
2023-01-23 03:58:05.552381: step: 1412/526, loss: 0.0005369663122110069
2023-01-23 03:58:06.692108: step: 1416/526, loss: 0.0012508392101153731
2023-01-23 03:58:07.826595: step: 1420/526, loss: 0.00033693312434479594
2023-01-23 03:58:08.983412: step: 1424/526, loss: 0.025281762704253197
2023-01-23 03:58:10.104240: step: 1428/526, loss: 0.0004226684395689517
2023-01-23 03:58:11.216471: step: 1432/526, loss: 2.841949390131049e-05
2023-01-23 03:58:12.385386: step: 1436/526, loss: 0.02558300644159317
2023-01-23 03:58:13.510363: step: 1440/526, loss: 0.0008280754555016756
2023-01-23 03:58:14.639543: step: 1444/526, loss: 0.00592694291844964
2023-01-23 03:58:15.737135: step: 1448/526, loss: 0.006555843632668257
2023-01-23 03:58:16.900313: step: 1452/526, loss: 6.065368506824598e-05
2023-01-23 03:58:18.034610: step: 1456/526, loss: 0.017021847888827324
2023-01-23 03:58:19.176560: step: 1460/526, loss: 0.00017132758512161672
2023-01-23 03:58:20.314953: step: 1464/526, loss: 0.00010938644118141383
2023-01-23 03:58:21.462705: step: 1468/526, loss: 0.030788231641054153
2023-01-23 03:58:22.573670: step: 1472/526, loss: 0.0008681774488650262
2023-01-23 03:58:23.691466: step: 1476/526, loss: 0.024807168170809746
2023-01-23 03:58:24.815570: step: 1480/526, loss: 0.5409547686576843
2023-01-23 03:58:25.946388: step: 1484/526, loss: 0.0005863190162926912
2023-01-23 03:58:27.090723: step: 1488/526, loss: 0.0024511339142918587
2023-01-23 03:58:28.230356: step: 1492/526, loss: 0.003298044204711914
2023-01-23 03:58:29.399861: step: 1496/526, loss: 0.0007040023920126259
2023-01-23 03:58:30.526367: step: 1500/526, loss: 0.015483285300433636
2023-01-23 03:58:31.659921: step: 1504/526, loss: 0.0019904612563550472
2023-01-23 03:58:32.824034: step: 1508/526, loss: 0.006766891572624445
2023-01-23 03:58:33.956914: step: 1512/526, loss: 0.014547348022460938
2023-01-23 03:58:35.074434: step: 1516/526, loss: 0.0007663726573809981
2023-01-23 03:58:36.254978: step: 1520/526, loss: 0.01921234279870987
2023-01-23 03:58:37.391802: step: 1524/526, loss: 0.0017212779494002461
2023-01-23 03:58:38.511700: step: 1528/526, loss: 3.337860107421875e-05
2023-01-23 03:58:39.621327: step: 1532/526, loss: 9.250641596736386e-06
2023-01-23 03:58:40.734166: step: 1536/526, loss: 0.0008694648859091103
2023-01-23 03:58:41.869546: step: 1540/526, loss: 0.007087897974997759
2023-01-23 03:58:43.011999: step: 1544/526, loss: 0.067865751683712
2023-01-23 03:58:44.163014: step: 1548/526, loss: 3.194809323758818e-05
2023-01-23 03:58:45.303267: step: 1552/526, loss: 0.005407905671745539
2023-01-23 03:58:46.439790: step: 1556/526, loss: 0.00016927719116210938
2023-01-23 03:58:47.572905: step: 1560/526, loss: 0.05326547846198082
2023-01-23 03:58:48.707641: step: 1564/526, loss: 0.044206809252500534
2023-01-23 03:58:49.827322: step: 1568/526, loss: 0.01596670225262642
2023-01-23 03:58:50.978735: step: 1572/526, loss: 0.00010375976853538305
2023-01-23 03:58:52.120601: step: 1576/526, loss: 0.06024513393640518
2023-01-23 03:58:53.243556: step: 1580/526, loss: 2.8944017685716972e-05
2023-01-23 03:58:54.392053: step: 1584/526, loss: 4.00543212890625e-05
2023-01-23 03:58:55.527336: step: 1588/526, loss: -4.38690176451928e-06
2023-01-23 03:58:56.652647: step: 1592/526, loss: 0.0002382278471486643
2023-01-23 03:58:57.772357: step: 1596/526, loss: 0.016375351697206497
2023-01-23 03:58:58.928009: step: 1600/526, loss: 0.0009118079906329513
2023-01-23 03:59:00.074617: step: 1604/526, loss: 0.013803672976791859
2023-01-23 03:59:01.209025: step: 1608/526, loss: 0.03435096517205238
2023-01-23 03:59:02.348707: step: 1612/526, loss: 0.025008726865053177
2023-01-23 03:59:03.479079: step: 1616/526, loss: 0.00011234283010708168
2023-01-23 03:59:04.617081: step: 1620/526, loss: 0.06903248280286789
2023-01-23 03:59:05.734648: step: 1624/526, loss: 0.00012454987154342234
2023-01-23 03:59:06.882147: step: 1628/526, loss: 0.006815052125602961
2023-01-23 03:59:08.019708: step: 1632/526, loss: 0.0050216675736010075
2023-01-23 03:59:09.184889: step: 1636/526, loss: 0.0023239136207848787
2023-01-23 03:59:10.346370: step: 1640/526, loss: 0.00264568324200809
2023-01-23 03:59:11.472951: step: 1644/526, loss: 0.004068136215209961
2023-01-23 03:59:12.603070: step: 1648/526, loss: 0.012709570117294788
2023-01-23 03:59:13.741490: step: 1652/526, loss: 0.0004522323433775455
2023-01-23 03:59:14.845175: step: 1656/526, loss: 0.09492845833301544
2023-01-23 03:59:15.991341: step: 1660/526, loss: 1.52587890625e-05
2023-01-23 03:59:17.152097: step: 1664/526, loss: 0.002302408218383789
2023-01-23 03:59:18.326691: step: 1668/526, loss: 0.005969524383544922
2023-01-23 03:59:19.477399: step: 1672/526, loss: 0.0042438507080078125
2023-01-23 03:59:20.624330: step: 1676/526, loss: 0.0013067246181890368
2023-01-23 03:59:21.753810: step: 1680/526, loss: 0.020853521302342415
2023-01-23 03:59:22.894156: step: 1684/526, loss: 0.00040068625821731985
2023-01-23 03:59:24.060428: step: 1688/526, loss: 8.735657320357859e-05
2023-01-23 03:59:25.223040: step: 1692/526, loss: 0.0009587288368493319
2023-01-23 03:59:26.361851: step: 1696/526, loss: 2.555847095209174e-05
2023-01-23 03:59:27.496578: step: 1700/526, loss: 0.00028171538724564016
2023-01-23 03:59:28.650380: step: 1704/526, loss: 0.039979077875614166
2023-01-23 03:59:29.762100: step: 1708/526, loss: 0.0009181976784020662
2023-01-23 03:59:30.899918: step: 1712/526, loss: 0.058440208435058594
2023-01-23 03:59:32.034599: step: 1716/526, loss: 0.0007172584882937372
2023-01-23 03:59:33.160483: step: 1720/526, loss: 6.341934204101562e-05
2023-01-23 03:59:34.297037: step: 1724/526, loss: 0.002150630811229348
2023-01-23 03:59:35.432049: step: 1728/526, loss: 0.0019634247291833162
2023-01-23 03:59:36.562366: step: 1732/526, loss: 0.0008495331276208162
2023-01-23 03:59:37.681695: step: 1736/526, loss: 0.00019321442232467234
2023-01-23 03:59:38.819407: step: 1740/526, loss: 2.9850005375919864e-05
2023-01-23 03:59:39.946361: step: 1744/526, loss: 0.0001634597865631804
2023-01-23 03:59:41.093671: step: 1748/526, loss: 0.21984100341796875
2023-01-23 03:59:42.223453: step: 1752/526, loss: 0.006243038456887007
2023-01-23 03:59:43.358881: step: 1756/526, loss: 0.00016789436631370336
2023-01-23 03:59:44.474093: step: 1760/526, loss: 0.008794593624770641
2023-01-23 03:59:45.595920: step: 1764/526, loss: 0.016346361488103867
2023-01-23 03:59:46.755132: step: 1768/526, loss: 0.00031871796818450093
2023-01-23 03:59:47.863750: step: 1772/526, loss: 0.01442489679902792
2023-01-23 03:59:48.986536: step: 1776/526, loss: 0.011054611764848232
2023-01-23 03:59:50.139583: step: 1780/526, loss: 0.021292496472597122
2023-01-23 03:59:51.286396: step: 1784/526, loss: 0.00636787386611104
2023-01-23 03:59:52.407363: step: 1788/526, loss: 2.5177003408316523e-05
2023-01-23 03:59:53.515330: step: 1792/526, loss: 0.008274412713944912
2023-01-23 03:59:54.671327: step: 1796/526, loss: 0.005169105716049671
2023-01-23 03:59:55.833623: step: 1800/526, loss: 0.046772003173828125
2023-01-23 03:59:56.971455: step: 1804/526, loss: 2.555847095209174e-05
2023-01-23 03:59:58.109527: step: 1808/526, loss: 0.00038657188997603953
2023-01-23 03:59:59.246549: step: 1812/526, loss: 0.00029544829158112407
2023-01-23 04:00:00.400236: step: 1816/526, loss: 0.01974639855325222
2023-01-23 04:00:01.559649: step: 1820/526, loss: 3.0040740966796875e-05
2023-01-23 04:00:02.683024: step: 1824/526, loss: 0.00049591064453125
2023-01-23 04:00:03.814674: step: 1828/526, loss: 0.012825775891542435
2023-01-23 04:00:05.012748: step: 1832/526, loss: 1.945495569088962e-05
2023-01-23 04:00:06.129776: step: 1836/526, loss: 0.02095937728881836
2023-01-23 04:00:07.294937: step: 1840/526, loss: 0.0006735802162438631
2023-01-23 04:00:08.447901: step: 1844/526, loss: 0.002120590303093195
2023-01-23 04:00:09.590588: step: 1848/526, loss: 0.03468761220574379
2023-01-23 04:00:10.728319: step: 1852/526, loss: 2.0980833141948096e-06
2023-01-23 04:00:11.849329: step: 1856/526, loss: 0.00227527623064816
2023-01-23 04:00:12.972879: step: 1860/526, loss: -3.051757857974735e-06
2023-01-23 04:00:14.151384: step: 1864/526, loss: 0.005071449093520641
2023-01-23 04:00:15.272070: step: 1868/526, loss: 0.010010338388383389
2023-01-23 04:00:16.414877: step: 1872/526, loss: 0.003715706057846546
2023-01-23 04:00:17.543311: step: 1876/526, loss: 7.190704491222277e-05
2023-01-23 04:00:18.697742: step: 1880/526, loss: 0.0013969421852380037
2023-01-23 04:00:19.844457: step: 1884/526, loss: 0.000670957553666085
2023-01-23 04:00:20.962241: step: 1888/526, loss: 0.0007257461547851562
2023-01-23 04:00:22.107272: step: 1892/526, loss: 7.02858014847152e-05
2023-01-23 04:00:23.243833: step: 1896/526, loss: 0.0012634277809411287
2023-01-23 04:00:24.396080: step: 1900/526, loss: 0.0018157958984375
2023-01-23 04:00:25.520353: step: 1904/526, loss: 0.06537322700023651
2023-01-23 04:00:26.636622: step: 1908/526, loss: 0.35081273317337036
2023-01-23 04:00:27.754083: step: 1912/526, loss: 0.005593585781753063
2023-01-23 04:00:28.908313: step: 1916/526, loss: 2.474784923833795e-05
2023-01-23 04:00:30.055183: step: 1920/526, loss: 0.03758401796221733
2023-01-23 04:00:31.186871: step: 1924/526, loss: 0.05770282819867134
2023-01-23 04:00:32.293845: step: 1928/526, loss: 0.027628041803836823
2023-01-23 04:00:33.445269: step: 1932/526, loss: 0.002439403673633933
2023-01-23 04:00:34.587087: step: 1936/526, loss: 1.773834264895413e-05
2023-01-23 04:00:35.721529: step: 1940/526, loss: 8.301735215354711e-05
2023-01-23 04:00:36.863637: step: 1944/526, loss: 0.000713348388671875
2023-01-23 04:00:37.984284: step: 1948/526, loss: 0.019584273919463158
2023-01-23 04:00:39.131062: step: 1952/526, loss: 0.0038118362426757812
2023-01-23 04:00:40.300243: step: 1956/526, loss: 4.4298172724666074e-05
2023-01-23 04:00:41.414937: step: 1960/526, loss: 4.5585635234601796e-05
2023-01-23 04:00:42.563854: step: 1964/526, loss: 0.014797830954194069
2023-01-23 04:00:43.677040: step: 1968/526, loss: 0.0013304711319506168
2023-01-23 04:00:44.802131: step: 1972/526, loss: 5.5122378398664296e-05
2023-01-23 04:00:45.943174: step: 1976/526, loss: 0.00906076468527317
2023-01-23 04:00:47.092312: step: 1980/526, loss: 9.074211266124621e-05
2023-01-23 04:00:48.216261: step: 1984/526, loss: 0.0001579284726176411
2023-01-23 04:00:49.382761: step: 1988/526, loss: 0.0009207725524902344
2023-01-23 04:00:50.532329: step: 1992/526, loss: 0.0011457443470135331
2023-01-23 04:00:51.689558: step: 1996/526, loss: 0.02708606794476509
2023-01-23 04:00:52.828062: step: 2000/526, loss: 4.75883498438634e-05
2023-01-23 04:00:53.975787: step: 2004/526, loss: 0.03226013109087944
2023-01-23 04:00:55.126802: step: 2008/526, loss: 0.0427764393389225
2023-01-23 04:00:56.314688: step: 2012/526, loss: 0.0005900383112020791
2023-01-23 04:00:57.454980: step: 2016/526, loss: 0.06280136853456497
2023-01-23 04:00:58.615806: step: 2020/526, loss: 8.411407907260582e-05
2023-01-23 04:00:59.750439: step: 2024/526, loss: 0.00017490386380814016
2023-01-23 04:01:00.872334: step: 2028/526, loss: 0.015264797024428844
2023-01-23 04:01:01.962355: step: 2032/526, loss: 9.250640687241685e-06
2023-01-23 04:01:03.092397: step: 2036/526, loss: 0.11339378356933594
2023-01-23 04:01:04.227009: step: 2040/526, loss: 0.0010231018532067537
2023-01-23 04:01:05.355987: step: 2044/526, loss: 0.0001900196075439453
2023-01-23 04:01:06.511863: step: 2048/526, loss: 1.888275073724799e-05
2023-01-23 04:01:07.621118: step: 2052/526, loss: 0.02208881452679634
2023-01-23 04:01:08.770399: step: 2056/526, loss: 0.00037832261295989156
2023-01-23 04:01:09.925809: step: 2060/526, loss: 0.0033551694359630346
2023-01-23 04:01:11.051750: step: 2064/526, loss: 4.751682354253717e-05
2023-01-23 04:01:12.184708: step: 2068/526, loss: 0.026750946417450905
2023-01-23 04:01:13.339389: step: 2072/526, loss: 0.0016255378723144531
2023-01-23 04:01:14.483049: step: 2076/526, loss: 0.02459249459207058
2023-01-23 04:01:15.625542: step: 2080/526, loss: 0.002175712725147605
2023-01-23 04:01:16.758024: step: 2084/526, loss: 0.0005808353307656944
2023-01-23 04:01:17.886024: step: 2088/526, loss: 2.1600722902803682e-05
2023-01-23 04:01:19.048022: step: 2092/526, loss: 0.023267697542905807
2023-01-23 04:01:20.166640: step: 2096/526, loss: 0.013891267590224743
2023-01-23 04:01:21.304592: step: 2100/526, loss: 0.0023319243919104338
2023-01-23 04:01:22.433494: step: 2104/526, loss: 0.0018161773914471269
==================================================
Loss: 0.015
--------------------
Dev: {'event': {'p': 0.6187904967602592, 'r': 0.762982689747004, 'f1': 0.6833631484794276}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 25}
Test: {'event': {'p': 0.6157007809288944, 'r': 0.7818371607515657, 'f1': 0.6888939986203725}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 25}
Chinese: {'event': {'p': 0.6125, 'r': 0.9074074074074074, 'f1': 0.7313432835820897}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 25}
Korean: {'event': {'p': 0.6904761904761905, 'r': 0.4603174603174603, 'f1': 0.5523809523809524}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 25}
Russian: {'event': {'p': 0.475, 'r': 0.5277777777777778, 'f1': 0.5}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 25}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6266519823788547, 'r': 0.7576564580559254, 'f1': 0.6859553948161543}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Eng Test for Chinese: {'event': {'p': 0.6313522825150732, 'r': 0.7651356993736952, 'f1': 0.6918357715903728}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Sample Chinese: {'event': {'p': 0.6621621621621622, 'r': 0.9074074074074074, 'f1': 0.765625}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6257995735607675, 'r': 0.7816245006657789, 'f1': 0.6950858496151568}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Eng Test for Korean: {'event': {'p': 0.623113410952997, 'r': 0.7541753653444676, 'f1': 0.6824085005903188}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Sample Korean: {'event': {'p': 0.7446808510638298, 'r': 0.5555555555555556, 'f1': 0.6363636363636364}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6266519823788547, 'r': 0.7576564580559254, 'f1': 0.6859553948161543}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Eng Test for Russian: {'event': {'p': 0.6313522825150732, 'r': 0.7651356993736952, 'f1': 0.6918357715903728}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Sample Russian: {'event': {'p': 0.5384615384615384, 'r': 0.5833333333333334, 'f1': 0.5599999999999999}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
******************************
Epoch: 26
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 04:02:05.621893: step: 4/526, loss: 0.007556724362075329
2023-01-23 04:02:06.776214: step: 8/526, loss: 0.0009531020768918097
2023-01-23 04:02:07.874271: step: 12/526, loss: 0.0008697509765625
2023-01-23 04:02:09.000988: step: 16/526, loss: 0.04036998748779297
2023-01-23 04:02:10.137026: step: 20/526, loss: 6.27517729299143e-05
2023-01-23 04:02:11.273630: step: 24/526, loss: 0.000240325927734375
2023-01-23 04:02:12.415345: step: 28/526, loss: 0.00011749267287086695
2023-01-23 04:02:13.550867: step: 32/526, loss: 0.00029087066650390625
2023-01-23 04:02:14.687429: step: 36/526, loss: 2.5081633793888614e-05
2023-01-23 04:02:15.826497: step: 40/526, loss: 0.016751719638705254
2023-01-23 04:02:16.963293: step: 44/526, loss: 0.00027332306490279734
2023-01-23 04:02:18.145725: step: 48/526, loss: 1.1730194273695815e-05
2023-01-23 04:02:19.281346: step: 52/526, loss: 0.0001827240048442036
2023-01-23 04:02:20.450179: step: 56/526, loss: 0.0011865615379065275
2023-01-23 04:02:21.598787: step: 60/526, loss: 0.015289688482880592
2023-01-23 04:02:22.739798: step: 64/526, loss: 0.0006167411920614541
2023-01-23 04:02:23.891910: step: 68/526, loss: 0.001567840576171875
2023-01-23 04:02:25.017560: step: 72/526, loss: 0.00014972686767578125
2023-01-23 04:02:26.138266: step: 76/526, loss: 0.09377880394458771
2023-01-23 04:02:27.287897: step: 80/526, loss: 0.0002579212305136025
2023-01-23 04:02:28.441376: step: 84/526, loss: 0.012417316436767578
2023-01-23 04:02:29.575359: step: 88/526, loss: 3.776550147449598e-05
2023-01-23 04:02:30.718822: step: 92/526, loss: 0.0004746437189169228
2023-01-23 04:02:31.844546: step: 96/526, loss: 0.0002685546933207661
2023-01-23 04:02:32.965798: step: 100/526, loss: 6.074905104469508e-05
2023-01-23 04:02:34.069203: step: 104/526, loss: 0.00011405945406295359
2023-01-23 04:02:35.206025: step: 108/526, loss: 6.408691115211695e-05
2023-01-23 04:02:36.338049: step: 112/526, loss: 0.0005860328674316406
2023-01-23 04:02:37.452916: step: 116/526, loss: 0.019515324383974075
2023-01-23 04:02:38.590300: step: 120/526, loss: 0.00012149811664130539
2023-01-23 04:02:39.733042: step: 124/526, loss: 0.00013446807861328125
2023-01-23 04:02:40.873423: step: 128/526, loss: 0.00024337769718840718
2023-01-23 04:02:42.018232: step: 132/526, loss: 4.558563159662299e-05
2023-01-23 04:02:43.137858: step: 136/526, loss: 3.185272362316027e-05
2023-01-23 04:02:44.273181: step: 140/526, loss: 4.119873119634576e-05
2023-01-23 04:02:45.405310: step: 144/526, loss: 0.004657173529267311
2023-01-23 04:02:46.520982: step: 148/526, loss: 0.0016197204822674394
2023-01-23 04:02:47.649438: step: 152/526, loss: 8.640289161121473e-05
2023-01-23 04:02:48.785750: step: 156/526, loss: 0.0006341457483358681
2023-01-23 04:02:49.891981: step: 160/526, loss: 0.00833044108003378
2023-01-23 04:02:51.017651: step: 164/526, loss: 0.07270584255456924
2023-01-23 04:02:52.145417: step: 168/526, loss: 0.001204681466333568
2023-01-23 04:02:53.265132: step: 172/526, loss: 5.283355858409777e-05
2023-01-23 04:02:54.420562: step: 176/526, loss: 0.0007898330804891884
2023-01-23 04:02:55.575066: step: 180/526, loss: 1.3351440202313825e-06
2023-01-23 04:02:56.719229: step: 184/526, loss: 0.025954438373446465
2023-01-23 04:02:57.844085: step: 188/526, loss: 0.03493804857134819
2023-01-23 04:02:58.974996: step: 192/526, loss: 0.015324211679399014
2023-01-23 04:03:00.099122: step: 196/526, loss: 1.926422191900201e-05
2023-01-23 04:03:01.240552: step: 200/526, loss: 0.0002452850458212197
2023-01-23 04:03:02.391141: step: 204/526, loss: 0.0545385368168354
2023-01-23 04:03:03.510166: step: 208/526, loss: 0.0003283977566752583
2023-01-23 04:03:04.618574: step: 212/526, loss: 0.009693384170532227
2023-01-23 04:03:05.772063: step: 216/526, loss: 0.02314901351928711
2023-01-23 04:03:06.912213: step: 220/526, loss: 0.0013080596690997481
2023-01-23 04:03:08.019208: step: 224/526, loss: 1.5354155038949102e-05
2023-01-23 04:03:09.151651: step: 228/526, loss: 0.001273346017114818
2023-01-23 04:03:10.270482: step: 232/526, loss: -6.198883056640625e-06
2023-01-23 04:03:11.389802: step: 236/526, loss: 0.04493580013513565
2023-01-23 04:03:12.523603: step: 240/526, loss: 0.0015001296997070312
2023-01-23 04:03:13.644739: step: 244/526, loss: 0.019270705059170723
2023-01-23 04:03:14.786465: step: 248/526, loss: 0.00045018194941803813
2023-01-23 04:03:15.897465: step: 252/526, loss: 0.008627128787338734
2023-01-23 04:03:17.016870: step: 256/526, loss: 0.004911995027214289
2023-01-23 04:03:18.133798: step: 260/526, loss: 0.007460975553840399
2023-01-23 04:03:19.255185: step: 264/526, loss: 0.00738677941262722
2023-01-23 04:03:20.403596: step: 268/526, loss: 0.037473488599061966
2023-01-23 04:03:21.513353: step: 272/526, loss: 0.0009285926935262978
2023-01-23 04:03:22.658458: step: 276/526, loss: 0.0006183624500408769
2023-01-23 04:03:23.831913: step: 280/526, loss: 2.613067590573337e-05
2023-01-23 04:03:24.982085: step: 284/526, loss: 0.00033843517303466797
2023-01-23 04:03:26.122192: step: 288/526, loss: 0.0003466606140136719
2023-01-23 04:03:27.273065: step: 292/526, loss: 0.019819164648652077
2023-01-23 04:03:28.399240: step: 296/526, loss: 3.681182715808973e-05
2023-01-23 04:03:29.537959: step: 300/526, loss: 0.00012569426326081157
2023-01-23 04:03:30.677026: step: 304/526, loss: 3.566742088878527e-05
2023-01-23 04:03:31.823686: step: 308/526, loss: 0.017421722412109375
2023-01-23 04:03:32.945112: step: 312/526, loss: 0.00769434031099081
2023-01-23 04:03:34.049176: step: 316/526, loss: 0.029249096289277077
2023-01-23 04:03:35.224684: step: 320/526, loss: 0.20623761415481567
2023-01-23 04:03:36.366003: step: 324/526, loss: 3.8719179428881034e-05
2023-01-23 04:03:37.482983: step: 328/526, loss: 0.006597327999770641
2023-01-23 04:03:38.609234: step: 332/526, loss: 0.017350196838378906
2023-01-23 04:03:39.731372: step: 336/526, loss: 4.234314110362902e-05
2023-01-23 04:03:40.867864: step: 340/526, loss: 0.00074939732439816
2023-01-23 04:03:41.994681: step: 344/526, loss: 0.00010004043724620715
2023-01-23 04:03:43.138481: step: 348/526, loss: 0.0003980636829510331
2023-01-23 04:03:44.263049: step: 352/526, loss: -4.2915337417070987e-07
2023-01-23 04:03:45.382235: step: 356/526, loss: 0.009605025872588158
2023-01-23 04:03:46.528408: step: 360/526, loss: 0.0008918762323446572
2023-01-23 04:03:47.635259: step: 364/526, loss: 0.01379938144236803
2023-01-23 04:03:48.743469: step: 368/526, loss: 0.004503726959228516
2023-01-23 04:03:49.911906: step: 372/526, loss: 0.008883095346391201
2023-01-23 04:03:51.056306: step: 376/526, loss: 0.004547023680061102
2023-01-23 04:03:52.202975: step: 380/526, loss: 0.0017359734047204256
2023-01-23 04:03:53.322697: step: 384/526, loss: 0.001637363457120955
2023-01-23 04:03:54.458625: step: 388/526, loss: 8.955002704169601e-05
2023-01-23 04:03:55.583618: step: 392/526, loss: 0.01388168428093195
2023-01-23 04:03:56.724492: step: 396/526, loss: 0.00014228820509742945
2023-01-23 04:03:57.852460: step: 400/526, loss: 0.0016307354671880603
2023-01-23 04:03:58.993387: step: 404/526, loss: 3.452301098150201e-05
2023-01-23 04:04:00.167381: step: 408/526, loss: 0.0004264831659384072
2023-01-23 04:04:01.308535: step: 412/526, loss: 0.00015449525380972773
2023-01-23 04:04:02.443472: step: 416/526, loss: 0.000974464463070035
2023-01-23 04:04:03.598584: step: 420/526, loss: 6.513595872092992e-05
2023-01-23 04:04:04.738224: step: 424/526, loss: 0.009265899658203125
2023-01-23 04:04:05.852017: step: 428/526, loss: 0.0015789985191076994
2023-01-23 04:04:07.007449: step: 432/526, loss: 0.00357818603515625
2023-01-23 04:04:08.134607: step: 436/526, loss: 8.935928053688258e-05
2023-01-23 04:04:09.298740: step: 440/526, loss: 0.005554104223847389
2023-01-23 04:04:10.428254: step: 444/526, loss: 6.198883056640625e-06
2023-01-23 04:04:11.554598: step: 448/526, loss: 3.404617018532008e-05
2023-01-23 04:04:12.704455: step: 452/526, loss: 0.0028277398087084293
2023-01-23 04:04:13.862259: step: 456/526, loss: 0.05595993995666504
2023-01-23 04:04:14.971241: step: 460/526, loss: 1.354217511106981e-05
2023-01-23 04:04:16.121083: step: 464/526, loss: 0.009227370843291283
2023-01-23 04:04:17.251536: step: 468/526, loss: 0.0004972458118572831
2023-01-23 04:04:18.410643: step: 472/526, loss: 0.00037469863309524953
2023-01-23 04:04:19.524135: step: 476/526, loss: 0.0009104252094402909
2023-01-23 04:04:20.655752: step: 480/526, loss: 0.00010395050048828125
2023-01-23 04:04:21.755832: step: 484/526, loss: 5.5122378398664296e-05
2023-01-23 04:04:22.875538: step: 488/526, loss: 0.006502723786979914
2023-01-23 04:04:24.010215: step: 492/526, loss: 0.00020742416381835938
2023-01-23 04:04:25.180257: step: 496/526, loss: 4.940032886224799e-05
2023-01-23 04:04:26.332397: step: 500/526, loss: 0.022144699469208717
2023-01-23 04:04:27.472477: step: 504/526, loss: 0.0005148887867107987
2023-01-23 04:04:28.572598: step: 508/526, loss: 0.0037399292923510075
2023-01-23 04:04:29.709739: step: 512/526, loss: 4.863738922722405e-06
2023-01-23 04:04:30.829527: step: 516/526, loss: 0.0009296417119912803
2023-01-23 04:04:31.948517: step: 520/526, loss: 0.007831573486328125
2023-01-23 04:04:33.074003: step: 524/526, loss: 0.016057778149843216
2023-01-23 04:04:34.209069: step: 528/526, loss: 0.009468460455536842
2023-01-23 04:04:35.322837: step: 532/526, loss: 1.8024444216280244e-05
2023-01-23 04:04:36.444992: step: 536/526, loss: 0.0016936302417889237
2023-01-23 04:04:37.558041: step: 540/526, loss: 0.0018484116299077868
2023-01-23 04:04:38.690649: step: 544/526, loss: 0.00066204066388309
2023-01-23 04:04:39.829228: step: 548/526, loss: 0.00150556571315974
2023-01-23 04:04:40.996624: step: 552/526, loss: 0.08858375251293182
2023-01-23 04:04:42.107945: step: 556/526, loss: 2.0694733393611386e-05
2023-01-23 04:04:43.233892: step: 560/526, loss: 0.02140979655086994
2023-01-23 04:04:44.366113: step: 564/526, loss: 6.132126145530492e-05
2023-01-23 04:04:45.504931: step: 568/526, loss: 4.606247239280492e-05
2023-01-23 04:04:46.640152: step: 572/526, loss: 0.02465667575597763
2023-01-23 04:04:47.799235: step: 576/526, loss: -2.2602082026423886e-05
2023-01-23 04:04:48.916371: step: 580/526, loss: 0.001093959785066545
2023-01-23 04:04:50.056040: step: 584/526, loss: 0.0027973176911473274
2023-01-23 04:04:51.202612: step: 588/526, loss: 0.0019176483619958162
2023-01-23 04:04:52.339485: step: 592/526, loss: 0.01902599260210991
2023-01-23 04:04:53.445277: step: 596/526, loss: 0.00029392243595793843
2023-01-23 04:04:54.581689: step: 600/526, loss: 0.09647312760353088
2023-01-23 04:04:55.717385: step: 604/526, loss: 0.0016601562965661287
2023-01-23 04:04:56.844561: step: 608/526, loss: 2.784729076665826e-05
2023-01-23 04:04:57.961769: step: 612/526, loss: 0.017209911718964577
2023-01-23 04:04:59.073471: step: 616/526, loss: 4.00543194700731e-06
2023-01-23 04:05:00.203029: step: 620/526, loss: 1.7642974853515625e-05
2023-01-23 04:05:01.357755: step: 624/526, loss: 0.0022843361366540194
2023-01-23 04:05:02.477181: step: 628/526, loss: 0.0005439758533611894
2023-01-23 04:05:03.628805: step: 632/526, loss: 0.01005172822624445
2023-01-23 04:05:04.752333: step: 636/526, loss: 2.3174286980065517e-05
2023-01-23 04:05:05.889006: step: 640/526, loss: -2.8610230629055877e-07
2023-01-23 04:05:07.005980: step: 644/526, loss: 0.008971786126494408
2023-01-23 04:05:08.172541: step: 648/526, loss: 3.0517578125e-05
2023-01-23 04:05:09.304125: step: 652/526, loss: 0.06203971058130264
2023-01-23 04:05:10.455897: step: 656/526, loss: 0.002213096711784601
2023-01-23 04:05:11.614067: step: 660/526, loss: 0.00011129378981422633
2023-01-23 04:05:12.748914: step: 664/526, loss: 0.021052028983831406
2023-01-23 04:05:13.892961: step: 668/526, loss: 0.002640247344970703
2023-01-23 04:05:15.044888: step: 672/526, loss: 0.012523031793534756
2023-01-23 04:05:16.224812: step: 676/526, loss: 0.001190781593322754
2023-01-23 04:05:17.378875: step: 680/526, loss: 0.0007537842029705644
2023-01-23 04:05:18.545972: step: 684/526, loss: 0.35065269470214844
2023-01-23 04:05:19.710548: step: 688/526, loss: 0.0002990722714457661
2023-01-23 04:05:20.842719: step: 692/526, loss: 0.009204578585922718
2023-01-23 04:05:21.959350: step: 696/526, loss: 0.009508133865892887
2023-01-23 04:05:23.105322: step: 700/526, loss: 0.00028228759765625
2023-01-23 04:05:24.261089: step: 704/526, loss: 0.0004445076046977192
2023-01-23 04:05:25.400304: step: 708/526, loss: 0.0019628526642918587
2023-01-23 04:05:26.535804: step: 712/526, loss: 0.002403402468189597
2023-01-23 04:05:27.654306: step: 716/526, loss: 0.018903542309999466
2023-01-23 04:05:28.788446: step: 720/526, loss: 0.0007581710815429688
2023-01-23 04:05:29.904113: step: 724/526, loss: 0.12390461564064026
2023-01-23 04:05:31.050599: step: 728/526, loss: 0.0007229328039102256
2023-01-23 04:05:32.170317: step: 732/526, loss: 0.005139350891113281
2023-01-23 04:05:33.285272: step: 736/526, loss: 2.6702880859375e-05
2023-01-23 04:05:34.421089: step: 740/526, loss: 0.012955952435731888
2023-01-23 04:05:35.528251: step: 744/526, loss: 3.957748504035408e-06
2023-01-23 04:05:36.640142: step: 748/526, loss: 6.0081479205109645e-06
2023-01-23 04:05:37.796992: step: 752/526, loss: 0.009667587466537952
2023-01-23 04:05:38.915092: step: 756/526, loss: 0.012731075286865234
2023-01-23 04:05:40.074594: step: 760/526, loss: 0.00022697450185660273
2023-01-23 04:05:41.248375: step: 764/526, loss: 0.03037109225988388
2023-01-23 04:05:42.373619: step: 768/526, loss: 0.09213504940271378
2023-01-23 04:05:43.500463: step: 772/526, loss: 7.62939453125e-06
2023-01-23 04:05:44.644648: step: 776/526, loss: 7.543564424850047e-05
2023-01-23 04:05:45.772357: step: 780/526, loss: 4.692077709478326e-05
2023-01-23 04:05:46.894989: step: 784/526, loss: 3.25202927342616e-05
2023-01-23 04:05:48.012131: step: 788/526, loss: 0.0003370285267010331
2023-01-23 04:05:49.143620: step: 792/526, loss: 0.005739402957260609
2023-01-23 04:05:50.297186: step: 796/526, loss: 0.0013688086764886975
2023-01-23 04:05:51.427738: step: 800/526, loss: 7.286071922862902e-05
2023-01-23 04:05:52.546999: step: 804/526, loss: 6.46591215627268e-05
2023-01-23 04:05:53.675037: step: 808/526, loss: 0.023021508008241653
2023-01-23 04:05:54.793654: step: 812/526, loss: 0.0003647804260253906
2023-01-23 04:05:55.938767: step: 816/526, loss: 0.02536792680621147
2023-01-23 04:05:57.080033: step: 820/526, loss: 0.00819616299122572
2023-01-23 04:05:58.184283: step: 824/526, loss: 0.04157199710607529
2023-01-23 04:05:59.287219: step: 828/526, loss: 0.02962922677397728
2023-01-23 04:06:00.496468: step: 832/526, loss: 0.0003867149353027344
2023-01-23 04:06:01.642923: step: 836/526, loss: 0.008469581604003906
2023-01-23 04:06:02.788986: step: 840/526, loss: 0.00365447998046875
2023-01-23 04:06:03.913853: step: 844/526, loss: 2.2792815798311494e-05
2023-01-23 04:06:05.060230: step: 848/526, loss: 0.0005125046009197831
2023-01-23 04:06:06.240376: step: 852/526, loss: 4.172772241872735e-05
2023-01-23 04:06:07.390940: step: 856/526, loss: 3.52859501617786e-06
2023-01-23 04:06:08.545111: step: 860/526, loss: 0.007661628536880016
2023-01-23 04:06:09.650983: step: 864/526, loss: 3.7765505112474784e-05
2023-01-23 04:06:10.765186: step: 868/526, loss: 0.03570890426635742
2023-01-23 04:06:11.900554: step: 872/526, loss: 0.04351940006017685
2023-01-23 04:06:13.039612: step: 876/526, loss: 0.0012695312034338713
2023-01-23 04:06:14.181482: step: 880/526, loss: 7.181167893577367e-05
2023-01-23 04:06:15.310059: step: 884/526, loss: 0.00034275054349564016
2023-01-23 04:06:16.467223: step: 888/526, loss: 4.19616708313697e-06
2023-01-23 04:06:17.605781: step: 892/526, loss: 0.0003177642938680947
2023-01-23 04:06:18.765292: step: 896/526, loss: 0.02492561563849449
2023-01-23 04:06:19.866523: step: 900/526, loss: -1.754760705807712e-05
2023-01-23 04:06:20.999229: step: 904/526, loss: 0.0002747535763774067
2023-01-23 04:06:22.153469: step: 908/526, loss: 0.0001509666326455772
2023-01-23 04:06:23.271736: step: 912/526, loss: 0.040938328951597214
2023-01-23 04:06:24.417062: step: 916/526, loss: 0.0013833999400958419
2023-01-23 04:06:25.540039: step: 920/526, loss: 0.00010170936729991809
2023-01-23 04:06:26.702971: step: 924/526, loss: 0.0002418518124613911
2023-01-23 04:06:27.839501: step: 928/526, loss: 0.00029201508732512593
2023-01-23 04:06:28.995220: step: 932/526, loss: 0.00101642613299191
2023-01-23 04:06:30.133204: step: 936/526, loss: 0.0035598755348473787
2023-01-23 04:06:31.243847: step: 940/526, loss: 4.053116208524443e-05
2023-01-23 04:06:32.409121: step: 944/526, loss: 4.901886131847277e-05
2023-01-23 04:06:33.552553: step: 948/526, loss: 0.010883331298828125
2023-01-23 04:06:34.724557: step: 952/526, loss: 0.015796469524502754
2023-01-23 04:06:35.858691: step: 956/526, loss: 0.001987934112548828
2023-01-23 04:06:36.991148: step: 960/526, loss: 0.08326959609985352
2023-01-23 04:06:38.100923: step: 964/526, loss: 0.00015087128849700093
2023-01-23 04:06:39.219151: step: 968/526, loss: 0.00042748451232910156
2023-01-23 04:06:40.331165: step: 972/526, loss: 2.5081633793888614e-05
2023-01-23 04:06:41.483275: step: 976/526, loss: 0.0030844209250062704
2023-01-23 04:06:42.617709: step: 980/526, loss: 0.02462296560406685
2023-01-23 04:06:43.747979: step: 984/526, loss: 0.0024687768891453743
2023-01-23 04:06:44.850702: step: 988/526, loss: 0.018194103613495827
2023-01-23 04:06:45.982197: step: 992/526, loss: 0.05408220365643501
2023-01-23 04:06:47.121121: step: 996/526, loss: 0.04926195368170738
2023-01-23 04:06:48.265960: step: 1000/526, loss: 0.0001615524379303679
2023-01-23 04:06:49.392448: step: 1004/526, loss: 1.3732910701946821e-05
2023-01-23 04:06:50.507484: step: 1008/526, loss: 0.0024916650727391243
2023-01-23 04:06:51.620548: step: 1012/526, loss: 0.00020990372286178172
2023-01-23 04:06:52.737927: step: 1016/526, loss: 0.002630996983498335
2023-01-23 04:06:53.844538: step: 1020/526, loss: 0.0008620262378826737
2023-01-23 04:06:54.993943: step: 1024/526, loss: 0.014086627401411533
2023-01-23 04:06:56.100668: step: 1028/526, loss: 8.611679368186742e-05
2023-01-23 04:06:57.260114: step: 1032/526, loss: 0.961580753326416
2023-01-23 04:06:58.364473: step: 1036/526, loss: 2.86102294921875e-06
2023-01-23 04:06:59.498310: step: 1040/526, loss: 0.00024867060710676014
2023-01-23 04:07:00.633310: step: 1044/526, loss: 0.0006837844848632812
2023-01-23 04:07:01.756191: step: 1048/526, loss: 0.0003898620489053428
2023-01-23 04:07:02.888567: step: 1052/526, loss: 4.901886131847277e-05
2023-01-23 04:07:04.016394: step: 1056/526, loss: 0.0005243301275186241
2023-01-23 04:07:05.235833: step: 1060/526, loss: 0.00020923613919876516
2023-01-23 04:07:06.389844: step: 1064/526, loss: 7.209777686512098e-05
2023-01-23 04:07:07.510341: step: 1068/526, loss: 0.0007066726684570312
2023-01-23 04:07:08.662349: step: 1072/526, loss: 0.0028179169166833162
2023-01-23 04:07:09.816803: step: 1076/526, loss: 0.018347740173339844
2023-01-23 04:07:10.953714: step: 1080/526, loss: 0.000834560371004045
2023-01-23 04:07:12.082865: step: 1084/526, loss: 0.0001028060942189768
2023-01-23 04:07:13.212396: step: 1088/526, loss: 0.0017168044578284025
2023-01-23 04:07:14.327972: step: 1092/526, loss: 4.100799742445815e-06
2023-01-23 04:07:15.475188: step: 1096/526, loss: 0.014684582129120827
2023-01-23 04:07:16.632436: step: 1100/526, loss: 4.4822695599577855e-06
2023-01-23 04:07:17.774529: step: 1104/526, loss: 0.014325332827866077
2023-01-23 04:07:18.892464: step: 1108/526, loss: 0.6066886186599731
2023-01-23 04:07:20.042664: step: 1112/526, loss: -2.174377368646674e-05
2023-01-23 04:07:21.195959: step: 1116/526, loss: 0.012491131201386452
2023-01-23 04:07:22.351439: step: 1120/526, loss: 0.05121555179357529
2023-01-23 04:07:23.473799: step: 1124/526, loss: 1.926422191900201e-05
2023-01-23 04:07:24.598831: step: 1128/526, loss: 0.0006259918445721269
2023-01-23 04:07:25.739989: step: 1132/526, loss: 8.773804438533261e-06
2023-01-23 04:07:26.871251: step: 1136/526, loss: 0.0011281968327239156
2023-01-23 04:07:27.998072: step: 1140/526, loss: 1.0204315003647935e-05
2023-01-23 04:07:29.164254: step: 1144/526, loss: -1.888275073724799e-05
2023-01-23 04:07:30.306733: step: 1148/526, loss: -2.47955313170678e-06
2023-01-23 04:07:31.412216: step: 1152/526, loss: 0.00010070801363326609
2023-01-23 04:07:32.555771: step: 1156/526, loss: 0.006709480658173561
2023-01-23 04:07:33.671574: step: 1160/526, loss: 3.9863589336164296e-05
2023-01-23 04:07:34.790269: step: 1164/526, loss: 0.012752914801239967
2023-01-23 04:07:35.941892: step: 1168/526, loss: 0.0033310416620224714
2023-01-23 04:07:37.043377: step: 1172/526, loss: 7.629394644936838e-07
2023-01-23 04:07:38.180171: step: 1176/526, loss: 0.031670376658439636
2023-01-23 04:07:39.313500: step: 1180/526, loss: 0.04897937923669815
2023-01-23 04:07:40.439933: step: 1184/526, loss: 5.617141869151965e-05
2023-01-23 04:07:41.614909: step: 1188/526, loss: 0.08169842511415482
2023-01-23 04:07:42.773196: step: 1192/526, loss: 9.441375732421875e-05
2023-01-23 04:07:43.889058: step: 1196/526, loss: 0.000514984130859375
2023-01-23 04:07:45.026704: step: 1200/526, loss: 0.0007412910345010459
2023-01-23 04:07:46.142745: step: 1204/526, loss: 7.581710633530747e-06
2023-01-23 04:07:47.283513: step: 1208/526, loss: 2.5844574338407256e-05
2023-01-23 04:07:48.410365: step: 1212/526, loss: 5.722046353184851e-06
2023-01-23 04:07:49.566014: step: 1216/526, loss: -5.91278057981981e-06
2023-01-23 04:07:50.699282: step: 1220/526, loss: 0.00439796457067132
2023-01-23 04:07:51.815536: step: 1224/526, loss: 0.00179376604501158
2023-01-23 04:07:52.965988: step: 1228/526, loss: 0.0030015946831554174
2023-01-23 04:07:54.137898: step: 1232/526, loss: 0.0011264800559729338
2023-01-23 04:07:55.253352: step: 1236/526, loss: 0.47378939390182495
2023-01-23 04:07:56.375106: step: 1240/526, loss: 2.6702882678364404e-05
2023-01-23 04:07:57.510522: step: 1244/526, loss: 0.014657068066298962
2023-01-23 04:07:58.645934: step: 1248/526, loss: 6.370544724632055e-05
2023-01-23 04:07:59.785804: step: 1252/526, loss: 0.000556993531063199
2023-01-23 04:08:00.956440: step: 1256/526, loss: 0.003033923916518688
2023-01-23 04:08:02.104640: step: 1260/526, loss: 0.01989002153277397
2023-01-23 04:08:03.227996: step: 1264/526, loss: 0.003425073577091098
2023-01-23 04:08:04.359538: step: 1268/526, loss: 0.00032329559326171875
2023-01-23 04:08:05.469707: step: 1272/526, loss: 8.39233416627394e-06
2023-01-23 04:08:06.611529: step: 1276/526, loss: 5.435943421616685e-06
2023-01-23 04:08:07.729814: step: 1280/526, loss: 0.007731151767075062
2023-01-23 04:08:08.871393: step: 1284/526, loss: 0.01676969602704048
2023-01-23 04:08:09.978863: step: 1288/526, loss: 2.002715973503655e-06
2023-01-23 04:08:11.116353: step: 1292/526, loss: 0.0001844406215241179
2023-01-23 04:08:12.251126: step: 1296/526, loss: 1.4114380974206142e-05
2023-01-23 04:08:13.413237: step: 1300/526, loss: 0.00155982980504632
2023-01-23 04:08:14.560238: step: 1304/526, loss: 0.028210550546646118
2023-01-23 04:08:15.678991: step: 1308/526, loss: -1.8978118532686494e-05
2023-01-23 04:08:16.805180: step: 1312/526, loss: 0.0002628326474223286
2023-01-23 04:08:17.933343: step: 1316/526, loss: 0.013109779916703701
2023-01-23 04:08:19.061034: step: 1320/526, loss: 0.004711723420768976
2023-01-23 04:08:20.199435: step: 1324/526, loss: 8.687973604537547e-05
2023-01-23 04:08:21.324419: step: 1328/526, loss: 1.1444091796875e-05
2023-01-23 04:08:22.442883: step: 1332/526, loss: 0.026537800207734108
2023-01-23 04:08:23.571469: step: 1336/526, loss: 5.264282299322076e-05
2023-01-23 04:08:24.692134: step: 1340/526, loss: 9.117127046920359e-05
2023-01-23 04:08:25.823060: step: 1344/526, loss: 0.000827407871838659
2023-01-23 04:08:26.941897: step: 1348/526, loss: 0.0022382736206054688
2023-01-23 04:08:28.103036: step: 1352/526, loss: 0.03650626912713051
2023-01-23 04:08:29.246028: step: 1356/526, loss: 0.004920482635498047
2023-01-23 04:08:30.384106: step: 1360/526, loss: 0.003426170442253351
2023-01-23 04:08:31.511484: step: 1364/526, loss: 0.056017305701971054
2023-01-23 04:08:32.664566: step: 1368/526, loss: 0.02686176262795925
2023-01-23 04:08:33.788788: step: 1372/526, loss: 0.008903312496840954
2023-01-23 04:08:34.942625: step: 1376/526, loss: 0.0030012130737304688
2023-01-23 04:08:36.107943: step: 1380/526, loss: 0.0007151603931561112
2023-01-23 04:08:37.258140: step: 1384/526, loss: 0.0038175582885742188
2023-01-23 04:08:38.364715: step: 1388/526, loss: 4.95910626341356e-06
2023-01-23 04:08:39.493464: step: 1392/526, loss: 0.0019253731006756425
2023-01-23 04:08:40.618844: step: 1396/526, loss: 7.486343747586943e-06
2023-01-23 04:08:41.758297: step: 1400/526, loss: 4.95910626341356e-06
2023-01-23 04:08:42.900112: step: 1404/526, loss: 1.5830992197152227e-05
2023-01-23 04:08:44.027804: step: 1408/526, loss: 0.002237510634586215
2023-01-23 04:08:45.158913: step: 1412/526, loss: 5.53131121705519e-06
2023-01-23 04:08:46.265011: step: 1416/526, loss: 0.00014820098294876516
2023-01-23 04:08:47.383713: step: 1420/526, loss: 0.0006631851429119706
2023-01-23 04:08:48.521594: step: 1424/526, loss: 0.03126220777630806
2023-01-23 04:08:49.698770: step: 1428/526, loss: -9.059906005859375e-06
2023-01-23 04:08:50.826434: step: 1432/526, loss: 0.00897140521556139
2023-01-23 04:08:51.968407: step: 1436/526, loss: 0.00128602993208915
2023-01-23 04:08:53.120804: step: 1440/526, loss: 0.000240325927734375
2023-01-23 04:08:54.259803: step: 1444/526, loss: 3.8909915019758046e-05
2023-01-23 04:08:55.411514: step: 1448/526, loss: 0.000702714896760881
2023-01-23 04:08:56.537930: step: 1452/526, loss: 0.020237160846590996
2023-01-23 04:08:57.659745: step: 1456/526, loss: 0.0599786750972271
2023-01-23 04:08:58.810152: step: 1460/526, loss: 0.00022621154494117945
2023-01-23 04:08:59.938998: step: 1464/526, loss: 2.994537317135837e-05
2023-01-23 04:09:01.074310: step: 1468/526, loss: 0.0005204200861044228
2023-01-23 04:09:02.171641: step: 1472/526, loss: 1.0967254638671875e-05
2023-01-23 04:09:03.307063: step: 1476/526, loss: 3.852844383800402e-05
2023-01-23 04:09:04.456504: step: 1480/526, loss: 0.0002305030939169228
2023-01-23 04:09:05.597858: step: 1484/526, loss: 0.0034009935334324837
2023-01-23 04:09:06.756944: step: 1488/526, loss: 2.765655608527595e-06
2023-01-23 04:09:07.922181: step: 1492/526, loss: 6.642342486884445e-05
2023-01-23 04:09:09.069354: step: 1496/526, loss: 2.6893614631262608e-05
2023-01-23 04:09:10.224867: step: 1500/526, loss: 0.003851318499073386
2023-01-23 04:09:11.367089: step: 1504/526, loss: 0.005389881320297718
2023-01-23 04:09:12.500670: step: 1508/526, loss: 0.0027903555892407894
2023-01-23 04:09:13.633328: step: 1512/526, loss: 2.899169885495212e-05
2023-01-23 04:09:14.770683: step: 1516/526, loss: 0.02359333075582981
2023-01-23 04:09:15.927696: step: 1520/526, loss: 5.8460234868107364e-05
2023-01-23 04:09:17.071910: step: 1524/526, loss: 0.012447738088667393
2023-01-23 04:09:18.220380: step: 1528/526, loss: 0.00042195318383164704
2023-01-23 04:09:19.330137: step: 1532/526, loss: 0.0006528854137286544
2023-01-23 04:09:20.505871: step: 1536/526, loss: -4.76837158203125e-06
2023-01-23 04:09:21.648892: step: 1540/526, loss: 0.015368843451142311
2023-01-23 04:09:22.764390: step: 1544/526, loss: 0.004864597227424383
2023-01-23 04:09:23.894063: step: 1548/526, loss: 0.0036489488556981087
2023-01-23 04:09:25.034254: step: 1552/526, loss: 0.0011518478859215975
2023-01-23 04:09:26.175885: step: 1556/526, loss: 0.0016561509110033512
2023-01-23 04:09:27.317214: step: 1560/526, loss: 0.0016248702304437757
2023-01-23 04:09:28.431697: step: 1564/526, loss: 0.012558747082948685
2023-01-23 04:09:29.536354: step: 1568/526, loss: 0.00028476715669967234
2023-01-23 04:09:30.691461: step: 1572/526, loss: 0.00011701584298862144
2023-01-23 04:09:31.836332: step: 1576/526, loss: 2.5081635612878017e-05
2023-01-23 04:09:32.952873: step: 1580/526, loss: 1.1253358024987392e-05
2023-01-23 04:09:34.097218: step: 1584/526, loss: 0.0037362100556492805
2023-01-23 04:09:35.311742: step: 1588/526, loss: 0.007292896509170532
2023-01-23 04:09:36.467178: step: 1592/526, loss: 0.014206696301698685
2023-01-23 04:09:37.626062: step: 1596/526, loss: -3.0517576306010596e-06
2023-01-23 04:09:38.753232: step: 1600/526, loss: 9.622573998058215e-05
2023-01-23 04:09:39.857851: step: 1604/526, loss: 0.00013065338134765625
2023-01-23 04:09:40.973094: step: 1608/526, loss: 0.00247707380913198
2023-01-23 04:09:42.135491: step: 1612/526, loss: 0.002977752825245261
2023-01-23 04:09:43.317552: step: 1616/526, loss: 5.455017162603326e-05
2023-01-23 04:09:44.443888: step: 1620/526, loss: 0.0002422332763671875
2023-01-23 04:09:45.611471: step: 1624/526, loss: 0.020637035369873047
2023-01-23 04:09:46.783653: step: 1628/526, loss: 0.0024837495293468237
2023-01-23 04:09:47.937393: step: 1632/526, loss: 2.002715973503655e-06
2023-01-23 04:09:49.079562: step: 1636/526, loss: 0.000663328159134835
2023-01-23 04:09:50.195790: step: 1640/526, loss: 3.604888843256049e-05
2023-01-23 04:09:51.342577: step: 1644/526, loss: 0.0050809383392333984
2023-01-23 04:09:52.487894: step: 1648/526, loss: 0.03238420560956001
2023-01-23 04:09:53.637555: step: 1652/526, loss: 0.01873464696109295
2023-01-23 04:09:54.758625: step: 1656/526, loss: 0.007911873050034046
2023-01-23 04:09:55.887745: step: 1660/526, loss: 0.0007429122924804688
2023-01-23 04:09:57.006024: step: 1664/526, loss: 0.030498409643769264
2023-01-23 04:09:58.110701: step: 1668/526, loss: 0.0016943931113928556
2023-01-23 04:09:59.252354: step: 1672/526, loss: 0.005672645755112171
2023-01-23 04:10:00.427109: step: 1676/526, loss: 0.007938671857118607
2023-01-23 04:10:01.574509: step: 1680/526, loss: 0.0017467498546466231
2023-01-23 04:10:02.687348: step: 1684/526, loss: 0.032073974609375
2023-01-23 04:10:03.815501: step: 1688/526, loss: 0.2091618925333023
2023-01-23 04:10:04.962677: step: 1692/526, loss: 0.022150231525301933
2023-01-23 04:10:06.095423: step: 1696/526, loss: 0.0018977165454998612
2023-01-23 04:10:07.233915: step: 1700/526, loss: 0.02743702009320259
2023-01-23 04:10:08.383913: step: 1704/526, loss: 0.036840301007032394
2023-01-23 04:10:09.494415: step: 1708/526, loss: 0.0004852294805459678
2023-01-23 04:10:10.615586: step: 1712/526, loss: 4.4536591303767636e-05
2023-01-23 04:10:11.791497: step: 1716/526, loss: 0.00040631293086335063
2023-01-23 04:10:12.940406: step: 1720/526, loss: 0.0007458687177859247
2023-01-23 04:10:14.087027: step: 1724/526, loss: 0.001009273575618863
2023-01-23 04:10:15.226720: step: 1728/526, loss: 0.00031156541081145406
2023-01-23 04:10:16.348469: step: 1732/526, loss: 1.2395102977752686
2023-01-23 04:10:17.480790: step: 1736/526, loss: 0.0013378143776208162
2023-01-23 04:10:18.601437: step: 1740/526, loss: 0.03308725729584694
2023-01-23 04:10:19.728686: step: 1744/526, loss: 0.10715971142053604
2023-01-23 04:10:20.875789: step: 1748/526, loss: 0.04743032529950142
2023-01-23 04:10:22.000257: step: 1752/526, loss: 5.626678557746345e-06
2023-01-23 04:10:23.152430: step: 1756/526, loss: 0.00030431748018600047
2023-01-23 04:10:24.289843: step: 1760/526, loss: 0.004824638366699219
2023-01-23 04:10:25.426784: step: 1764/526, loss: 0.023418808355927467
2023-01-23 04:10:26.601850: step: 1768/526, loss: 0.00148525252006948
2023-01-23 04:10:27.764211: step: 1772/526, loss: 0.03056774102151394
2023-01-23 04:10:28.941135: step: 1776/526, loss: 0.000388669956009835
2023-01-23 04:10:30.076247: step: 1780/526, loss: 0.0007776260026730597
2023-01-23 04:10:31.221973: step: 1784/526, loss: 0.017757128924131393
2023-01-23 04:10:32.374986: step: 1788/526, loss: 0.0242964755743742
2023-01-23 04:10:33.494538: step: 1792/526, loss: 0.016392040997743607
2023-01-23 04:10:34.613474: step: 1796/526, loss: 0.0017921447288244963
2023-01-23 04:10:35.720195: step: 1800/526, loss: 0.0018837453098967671
2023-01-23 04:10:36.840444: step: 1804/526, loss: 1.9168852304574102e-05
2023-01-23 04:10:37.962176: step: 1808/526, loss: 1.258850079466356e-05
2023-01-23 04:10:39.072978: step: 1812/526, loss: 8.592606172896922e-05
2023-01-23 04:10:40.214370: step: 1816/526, loss: 0.002609729766845703
2023-01-23 04:10:41.312248: step: 1820/526, loss: 0.0008083343273028731
2023-01-23 04:10:42.456601: step: 1824/526, loss: 0.00023536680964753032
2023-01-23 04:10:43.650409: step: 1828/526, loss: 0.0002002716064453125
2023-01-23 04:10:44.803430: step: 1832/526, loss: 0.005363273900002241
2023-01-23 04:10:45.952981: step: 1836/526, loss: 0.008018827065825462
2023-01-23 04:10:47.113102: step: 1840/526, loss: 0.007731246761977673
2023-01-23 04:10:48.262673: step: 1844/526, loss: 0.03594532236456871
2023-01-23 04:10:49.409488: step: 1848/526, loss: 0.3161148130893707
2023-01-23 04:10:50.521582: step: 1852/526, loss: 0.004541588015854359
2023-01-23 04:10:51.677884: step: 1856/526, loss: 0.00018424988957121968
2023-01-23 04:10:52.784655: step: 1860/526, loss: 0.0008784294477663934
2023-01-23 04:10:53.923869: step: 1864/526, loss: 0.00011901855759788305
2023-01-23 04:10:55.031195: step: 1868/526, loss: 0.0008966445457190275
2023-01-23 04:10:56.210040: step: 1872/526, loss: 0.0034414289984852076
2023-01-23 04:10:57.352116: step: 1876/526, loss: 0.00013656617375090718
2023-01-23 04:10:58.454638: step: 1880/526, loss: 6.999969627941027e-05
2023-01-23 04:10:59.584714: step: 1884/526, loss: 1.0580861568450928
2023-01-23 04:11:00.719038: step: 1888/526, loss: 0.008166313171386719
2023-01-23 04:11:01.846269: step: 1892/526, loss: 0.1165875494480133
2023-01-23 04:11:02.998453: step: 1896/526, loss: 4.920959327137098e-05
2023-01-23 04:11:04.155027: step: 1900/526, loss: 0.0001811981201171875
2023-01-23 04:11:05.314409: step: 1904/526, loss: 0.0002621650928631425
2023-01-23 04:11:06.480268: step: 1908/526, loss: -4.95910626341356e-06
2023-01-23 04:11:07.634835: step: 1912/526, loss: 0.004971933551132679
2023-01-23 04:11:08.801168: step: 1916/526, loss: 0.008744620718061924
2023-01-23 04:11:09.970524: step: 1920/526, loss: 7.343292236328125e-05
2023-01-23 04:11:11.119595: step: 1924/526, loss: 0.015537834726274014
2023-01-23 04:11:12.276376: step: 1928/526, loss: 0.00037384033203125
2023-01-23 04:11:13.411432: step: 1932/526, loss: 0.0004722595331259072
2023-01-23 04:11:14.547924: step: 1936/526, loss: 7.82012921263231e-06
2023-01-23 04:11:15.683232: step: 1940/526, loss: 0.0003864288446493447
2023-01-23 04:11:16.861636: step: 1944/526, loss: 0.0012104033958166838
2023-01-23 04:11:17.987363: step: 1948/526, loss: 0.010028649121522903
2023-01-23 04:11:19.130074: step: 1952/526, loss: 0.0003222465456929058
2023-01-23 04:11:20.250774: step: 1956/526, loss: 0.016926003620028496
2023-01-23 04:11:21.403593: step: 1960/526, loss: 0.008316612802445889
2023-01-23 04:11:22.531121: step: 1964/526, loss: 0.0005629539955407381
2023-01-23 04:11:23.681034: step: 1968/526, loss: 0.01044845674186945
2023-01-23 04:11:24.813644: step: 1972/526, loss: 0.0008127212640829384
2023-01-23 04:11:25.945530: step: 1976/526, loss: 0.0001337051362497732
2023-01-23 04:11:27.063088: step: 1980/526, loss: 1.4781951904296875e-05
2023-01-23 04:11:28.193395: step: 1984/526, loss: 0.00020828247943427414
2023-01-23 04:11:29.344234: step: 1988/526, loss: 0.0007927894475869834
2023-01-23 04:11:30.479209: step: 1992/526, loss: 0.0060024261474609375
2023-01-23 04:11:31.614337: step: 1996/526, loss: 0.0017284393543377519
2023-01-23 04:11:32.791342: step: 2000/526, loss: 0.0007156849023886025
2023-01-23 04:11:33.914774: step: 2004/526, loss: 0.0001312255917582661
2023-01-23 04:11:35.014599: step: 2008/526, loss: 1.2254714420123491e-05
2023-01-23 04:11:36.141903: step: 2012/526, loss: 7.934570749057457e-05
2023-01-23 04:11:37.300249: step: 2016/526, loss: 7.390976679744199e-05
2023-01-23 04:11:38.445313: step: 2020/526, loss: 0.013234615325927734
2023-01-23 04:11:39.563805: step: 2024/526, loss: 0.0004430771223269403
2023-01-23 04:11:40.725407: step: 2028/526, loss: 0.03345470875501633
2023-01-23 04:11:41.856156: step: 2032/526, loss: 0.02077198028564453
2023-01-23 04:11:43.012718: step: 2036/526, loss: 0.0002658843877725303
2023-01-23 04:11:44.152241: step: 2040/526, loss: 2.1362302504712716e-05
2023-01-23 04:11:45.268595: step: 2044/526, loss: 0.0018316269852221012
2023-01-23 04:11:46.418518: step: 2048/526, loss: 0.04275708273053169
2023-01-23 04:11:47.534719: step: 2052/526, loss: 2.0027162008773303e-06
2023-01-23 04:11:48.691533: step: 2056/526, loss: 0.12838879227638245
2023-01-23 04:11:49.780561: step: 2060/526, loss: 3.5762786865234375e-06
2023-01-23 04:11:50.914932: step: 2064/526, loss: -2.6702882678364404e-06
2023-01-23 04:11:52.061234: step: 2068/526, loss: 5.245209104032256e-05
2023-01-23 04:11:53.181926: step: 2072/526, loss: 0.0006593704456463456
2023-01-23 04:11:54.294247: step: 2076/526, loss: 0.0001570224849274382
2023-01-23 04:11:55.398372: step: 2080/526, loss: 0.0014127731556072831
2023-01-23 04:11:56.548701: step: 2084/526, loss: 0.00016708373732399195
2023-01-23 04:11:57.681438: step: 2088/526, loss: 4.158019874012098e-05
2023-01-23 04:11:58.808232: step: 2092/526, loss: 0.0018079758156090975
2023-01-23 04:11:59.936942: step: 2096/526, loss: 0.00243377685546875
2023-01-23 04:12:01.043170: step: 2100/526, loss: 1.9073486328125e-06
2023-01-23 04:12:02.165442: step: 2104/526, loss: 0.00010166168067371473
==================================================
Loss: 0.018
--------------------
Dev: {'event': {'p': 0.5684729064039409, 'r': 0.7683089214380826, 'f1': 0.653454133635334}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
Test: {'event': {'p': 0.6110655737704918, 'r': 0.7781837160751566, 'f1': 0.6845730027548209}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
Chinese: {'event': {'p': 0.5168539325842697, 'r': 0.8518518518518519, 'f1': 0.6433566433566433}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
Korean: {'event': {'p': 0.62, 'r': 0.49206349206349204, 'f1': 0.5486725663716814}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
Russian: {'event': {'p': 0.4, 'r': 0.5, 'f1': 0.4444444444444445}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6266519823788547, 'r': 0.7576564580559254, 'f1': 0.6859553948161543}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Eng Test for Chinese: {'event': {'p': 0.6313522825150732, 'r': 0.7651356993736952, 'f1': 0.6918357715903728}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Sample Chinese: {'event': {'p': 0.6621621621621622, 'r': 0.9074074074074074, 'f1': 0.765625}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6257995735607675, 'r': 0.7816245006657789, 'f1': 0.6950858496151568}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Eng Test for Korean: {'event': {'p': 0.623113410952997, 'r': 0.7541753653444676, 'f1': 0.6824085005903188}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Sample Korean: {'event': {'p': 0.7446808510638298, 'r': 0.5555555555555556, 'f1': 0.6363636363636364}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6266519823788547, 'r': 0.7576564580559254, 'f1': 0.6859553948161543}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Eng Test for Russian: {'event': {'p': 0.6313522825150732, 'r': 0.7651356993736952, 'f1': 0.6918357715903728}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Sample Russian: {'event': {'p': 0.5384615384615384, 'r': 0.5833333333333334, 'f1': 0.5599999999999999}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
******************************
Epoch: 27
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 04:12:45.212702: step: 4/526, loss: 0.0002765655517578125
2023-01-23 04:12:46.336607: step: 8/526, loss: 5.054473876953125e-05
2023-01-23 04:12:47.462812: step: 12/526, loss: 1.893043372547254e-05
2023-01-23 04:12:48.585839: step: 16/526, loss: 0.012279605492949486
2023-01-23 04:12:49.726951: step: 20/526, loss: 3.132819983875379e-05
2023-01-23 04:12:50.855171: step: 24/526, loss: 0.0015066623454913497
2023-01-23 04:12:51.980587: step: 28/526, loss: 6.961823237361386e-05
2023-01-23 04:12:53.094218: step: 32/526, loss: 0.0018840789562091231
2023-01-23 04:12:54.225023: step: 36/526, loss: 0.006211709696799517
2023-01-23 04:12:55.366292: step: 40/526, loss: 0.011351299472153187
2023-01-23 04:12:56.468025: step: 44/526, loss: 0.00311622628942132
2023-01-23 04:12:57.612174: step: 48/526, loss: 0.0006634712335653603
2023-01-23 04:12:58.753504: step: 52/526, loss: 4.043579247081652e-05
2023-01-23 04:12:59.895941: step: 56/526, loss: 0.005677509121596813
2023-01-23 04:13:01.024306: step: 60/526, loss: 0.0002114296075887978
2023-01-23 04:13:02.167571: step: 64/526, loss: 0.000727748847566545
2023-01-23 04:13:03.300250: step: 68/526, loss: 0.005809879396110773
2023-01-23 04:13:04.434060: step: 72/526, loss: 0.028379440307617188
2023-01-23 04:13:05.562238: step: 76/526, loss: 0.0004896164173260331
2023-01-23 04:13:06.681855: step: 80/526, loss: 0.0007036208990029991
2023-01-23 04:13:07.824468: step: 84/526, loss: -2.059936559817288e-05
2023-01-23 04:13:08.937975: step: 88/526, loss: 0.0008453846094198525
2023-01-23 04:13:10.067185: step: 92/526, loss: 1.659393274167087e-05
2023-01-23 04:13:11.170446: step: 96/526, loss: 0.0001484871027059853
2023-01-23 04:13:12.289467: step: 100/526, loss: 8.726119631319307e-06
2023-01-23 04:13:13.421028: step: 104/526, loss: 0.00019378661818336695
2023-01-23 04:13:14.557015: step: 108/526, loss: 9.098053124034777e-05
2023-01-23 04:13:15.713169: step: 112/526, loss: 0.00171070103533566
2023-01-23 04:13:16.860970: step: 116/526, loss: 0.0003231048467569053
2023-01-23 04:13:17.997546: step: 120/526, loss: 0.000392723100958392
2023-01-23 04:13:19.134173: step: 124/526, loss: 0.022927286103367805
2023-01-23 04:13:20.253443: step: 128/526, loss: 0.007363128941506147
2023-01-23 04:13:21.404410: step: 132/526, loss: 0.027758406475186348
2023-01-23 04:13:22.521546: step: 136/526, loss: 1.239776611328125e-05
2023-01-23 04:13:23.679366: step: 140/526, loss: -7.915497008070815e-06
2023-01-23 04:13:24.824617: step: 144/526, loss: 0.05431995540857315
2023-01-23 04:13:25.921714: step: 148/526, loss: 0.00033893584623001516
2023-01-23 04:13:27.037776: step: 152/526, loss: 2.765655608527595e-06
2023-01-23 04:13:28.163634: step: 156/526, loss: 0.00021991731773596257
2023-01-23 04:13:29.302148: step: 160/526, loss: 8.39233416627394e-06
2023-01-23 04:13:30.435492: step: 164/526, loss: 4.806518700206652e-05
2023-01-23 04:13:31.562709: step: 168/526, loss: 0.0008997917757369578
2023-01-23 04:13:32.684496: step: 172/526, loss: 7.534027190558845e-06
2023-01-23 04:13:33.812862: step: 176/526, loss: 5.168914867681451e-05
2023-01-23 04:13:34.934157: step: 180/526, loss: 0.0027696609031409025
2023-01-23 04:13:36.042998: step: 184/526, loss: 1.6880036127986386e-05
2023-01-23 04:13:37.189913: step: 188/526, loss: 0.0010470390552654862
2023-01-23 04:13:38.327691: step: 192/526, loss: 0.06860151886940002
2023-01-23 04:13:39.448885: step: 196/526, loss: 3.614425440900959e-05
2023-01-23 04:13:40.588255: step: 200/526, loss: 0.00404777517542243
2023-01-23 04:13:41.760885: step: 204/526, loss: 0.0008954048389568925
2023-01-23 04:13:42.941808: step: 208/526, loss: 3.051757857974735e-06
2023-01-23 04:13:44.084361: step: 212/526, loss: 0.0039577484130859375
2023-01-23 04:13:45.212526: step: 216/526, loss: 3.0040740966796875e-05
2023-01-23 04:13:46.344311: step: 220/526, loss: 0.001960658933967352
2023-01-23 04:13:47.472022: step: 224/526, loss: 0.00022811890812590718
2023-01-23 04:13:48.602171: step: 228/526, loss: 0.010171127505600452
2023-01-23 04:13:49.745394: step: 232/526, loss: 0.0003105163632426411
2023-01-23 04:13:50.880693: step: 236/526, loss: 0.002224540803581476
2023-01-23 04:13:52.032364: step: 240/526, loss: 0.0057853697799146175
2023-01-23 04:13:53.193886: step: 244/526, loss: 0.0003604888916015625
2023-01-23 04:13:54.318777: step: 248/526, loss: 0.0408940352499485
2023-01-23 04:13:55.482272: step: 252/526, loss: 7.057189577608369e-06
2023-01-23 04:13:56.621213: step: 256/526, loss: 9.760856482898816e-05
2023-01-23 04:13:57.759042: step: 260/526, loss: 0.0003845214960165322
2023-01-23 04:13:58.885417: step: 264/526, loss: 0.0005950927734375
2023-01-23 04:14:00.073085: step: 268/526, loss: 0.0004058837948832661
2023-01-23 04:14:01.225896: step: 272/526, loss: 0.006672763731330633
2023-01-23 04:14:02.375371: step: 276/526, loss: 0.0016333579551428556
2023-01-23 04:14:03.522008: step: 280/526, loss: 0.00050182337872684
2023-01-23 04:14:04.648304: step: 284/526, loss: 0.00019378661818336695
2023-01-23 04:14:05.811816: step: 288/526, loss: 0.0002842903195414692
2023-01-23 04:14:06.912606: step: 292/526, loss: 0.0001317977876169607
2023-01-23 04:14:08.027466: step: 296/526, loss: 2.646446409926284e-05
2023-01-23 04:14:09.207460: step: 300/526, loss: 0.029449844732880592
2023-01-23 04:14:10.354694: step: 304/526, loss: 0.009784317575395107
2023-01-23 04:14:11.476364: step: 308/526, loss: -9.72747784544481e-06
2023-01-23 04:14:12.595592: step: 312/526, loss: 0.0013284683227539062
2023-01-23 04:14:13.733014: step: 316/526, loss: 7.190704491222277e-05
2023-01-23 04:14:14.857217: step: 320/526, loss: 1.8787384760798886e-05
2023-01-23 04:14:15.996382: step: 324/526, loss: 9.088516526389867e-05
2023-01-23 04:14:17.108900: step: 328/526, loss: 0.0009706497075967491
2023-01-23 04:14:18.252389: step: 332/526, loss: 7.2479248046875e-05
2023-01-23 04:14:19.389454: step: 336/526, loss: -1.640319896978326e-05
2023-01-23 04:14:20.556262: step: 340/526, loss: 0.0007809638627804816
2023-01-23 04:14:21.679682: step: 344/526, loss: 0.00013914107694290578
2023-01-23 04:14:22.793471: step: 348/526, loss: -2.4795533590804553e-06
2023-01-23 04:14:23.912833: step: 352/526, loss: 3.4904482163256034e-05
2023-01-23 04:14:25.042279: step: 356/526, loss: -1.4019012269272935e-05
2023-01-23 04:14:26.192984: step: 360/526, loss: 0.00012416840763762593
2023-01-23 04:14:27.324443: step: 364/526, loss: 0.004153633024543524
2023-01-23 04:14:28.444348: step: 368/526, loss: 3.2711028325138614e-05
2023-01-23 04:14:29.593248: step: 372/526, loss: 0.00031347275944426656
2023-01-23 04:14:30.722982: step: 376/526, loss: 0.004353714175522327
2023-01-23 04:14:31.833056: step: 380/526, loss: 6.0987476899754256e-05
2023-01-23 04:14:32.993118: step: 384/526, loss: -3.433226083870977e-06
2023-01-23 04:14:34.130668: step: 388/526, loss: 0.00129871373064816
2023-01-23 04:14:35.261232: step: 392/526, loss: 0.002247190335765481
2023-01-23 04:14:36.378692: step: 396/526, loss: 0.011980055831372738
2023-01-23 04:14:37.535509: step: 400/526, loss: 9.269714792026207e-05
2023-01-23 04:14:38.681093: step: 404/526, loss: 2.1076202756376006e-05
2023-01-23 04:14:39.829868: step: 408/526, loss: 0.0003170013369526714
2023-01-23 04:14:40.984197: step: 412/526, loss: 0.0005190849187783897
2023-01-23 04:14:42.141087: step: 416/526, loss: 0.012317943386733532
2023-01-23 04:14:43.326282: step: 420/526, loss: 0.06505031138658524
2023-01-23 04:14:44.461501: step: 424/526, loss: 0.0004749298095703125
2023-01-23 04:14:45.594671: step: 428/526, loss: 0.0015095234848558903
2023-01-23 04:14:46.748693: step: 432/526, loss: 0.000209808349609375
2023-01-23 04:14:47.871190: step: 436/526, loss: 0.00159111013635993
2023-01-23 04:14:49.000464: step: 440/526, loss: 0.03256235271692276
2023-01-23 04:14:50.103353: step: 444/526, loss: 1.239776611328125e-05
2023-01-23 04:14:51.235033: step: 448/526, loss: 0.0009539604070596397
2023-01-23 04:14:52.367225: step: 452/526, loss: 6.389617919921875e-05
2023-01-23 04:14:53.488252: step: 456/526, loss: 8.773804438533261e-06
2023-01-23 04:14:54.618836: step: 460/526, loss: 0.003558540251106024
2023-01-23 04:14:55.777379: step: 464/526, loss: 0.0015316009521484375
2023-01-23 04:14:56.915511: step: 468/526, loss: 0.008338737301528454
2023-01-23 04:14:58.074661: step: 472/526, loss: 1.926422191900201e-05
2023-01-23 04:14:59.212251: step: 476/526, loss: 0.0008203506586141884
2023-01-23 04:15:00.326706: step: 480/526, loss: 0.0014940261607989669
2023-01-23 04:15:01.458843: step: 484/526, loss: 0.0001235961972270161
2023-01-23 04:15:02.603565: step: 488/526, loss: 0.0004393577401060611
2023-01-23 04:15:03.793317: step: 492/526, loss: 2.017021324718371e-05
2023-01-23 04:15:04.917259: step: 496/526, loss: 2.384185791015625e-05
2023-01-23 04:15:06.048595: step: 500/526, loss: 0.00401725759729743
2023-01-23 04:15:07.184629: step: 504/526, loss: 0.006469154264777899
2023-01-23 04:15:08.318135: step: 508/526, loss: 2.2220612663659267e-05
2023-01-23 04:15:09.456780: step: 512/526, loss: 2.593994213384576e-05
2023-01-23 04:15:10.571958: step: 516/526, loss: -8.01086389401462e-06
2023-01-23 04:15:11.704341: step: 520/526, loss: 0.020737363025546074
2023-01-23 04:15:12.851210: step: 524/526, loss: 1.888275073724799e-05
2023-01-23 04:15:14.020267: step: 528/526, loss: 0.0001293182431254536
2023-01-23 04:15:15.159478: step: 532/526, loss: 4.301071385270916e-05
2023-01-23 04:15:16.258962: step: 536/526, loss: 0.00024671555729582906
2023-01-23 04:15:17.383288: step: 540/526, loss: 1.3446808225126006e-05
2023-01-23 04:15:18.519455: step: 544/526, loss: 2.574920654296875e-05
2023-01-23 04:15:19.685629: step: 548/526, loss: 0.00031948089599609375
2023-01-23 04:15:20.789478: step: 552/526, loss: 3.337860107421875e-05
2023-01-23 04:15:21.946714: step: 556/526, loss: 0.009712982922792435
2023-01-23 04:15:23.053437: step: 560/526, loss: 8.735657320357859e-05
2023-01-23 04:15:24.211658: step: 564/526, loss: 0.0017586707836017013
2023-01-23 04:15:25.308353: step: 568/526, loss: 3.185272362316027e-05
2023-01-23 04:15:26.463005: step: 572/526, loss: 9.422302537132055e-05
2023-01-23 04:15:27.578623: step: 576/526, loss: 0.012394714169204235
2023-01-23 04:15:28.718203: step: 580/526, loss: 0.03634929656982422
2023-01-23 04:15:29.853219: step: 584/526, loss: 3.910065061063506e-05
2023-01-23 04:15:30.986681: step: 588/526, loss: 0.08449192345142365
2023-01-23 04:15:32.117026: step: 592/526, loss: 0.0006435394752770662
2023-01-23 04:15:33.233044: step: 596/526, loss: 0.014098548330366611
2023-01-23 04:15:34.376533: step: 600/526, loss: 0.0021797181107103825
2023-01-23 04:15:35.507112: step: 604/526, loss: 0.022112369537353516
2023-01-23 04:15:36.664009: step: 608/526, loss: 0.0021508217323571444
2023-01-23 04:15:37.795388: step: 612/526, loss: 9.975433204090223e-05
2023-01-23 04:15:38.927515: step: 616/526, loss: 0.016420556232333183
2023-01-23 04:15:40.066169: step: 620/526, loss: 0.0005218505975790322
2023-01-23 04:15:41.187515: step: 624/526, loss: 0.0005505562294274569
2023-01-23 04:15:42.350509: step: 628/526, loss: 0.005284309387207031
2023-01-23 04:15:43.489535: step: 632/526, loss: 0.0033848288003355265
2023-01-23 04:15:44.637898: step: 636/526, loss: 6.408691842807457e-05
2023-01-23 04:15:45.767315: step: 640/526, loss: 0.002997970674186945
2023-01-23 04:15:46.910852: step: 644/526, loss: 0.05346536636352539
2023-01-23 04:15:48.057952: step: 648/526, loss: 7.877349707996473e-05
2023-01-23 04:15:49.190907: step: 652/526, loss: 3.814697629422881e-05
2023-01-23 04:15:50.310363: step: 656/526, loss: 5.92231735936366e-05
2023-01-23 04:15:51.458497: step: 660/526, loss: 0.0013502121437340975
2023-01-23 04:15:52.581532: step: 664/526, loss: 0.00023527146549895406
2023-01-23 04:15:53.718377: step: 668/526, loss: 2.250671423098538e-05
2023-01-23 04:15:54.852484: step: 672/526, loss: 0.0001464843808207661
2023-01-23 04:15:55.986573: step: 676/526, loss: 0.07876253128051758
2023-01-23 04:15:57.112563: step: 680/526, loss: 0.0002496719534974545
2023-01-23 04:15:58.236857: step: 684/526, loss: 0.034255217760801315
2023-01-23 04:15:59.352829: step: 688/526, loss: 8.106231689453125e-06
2023-01-23 04:16:00.527085: step: 692/526, loss: 0.0017586946487426758
2023-01-23 04:16:01.658187: step: 696/526, loss: 0.006284141913056374
2023-01-23 04:16:02.824725: step: 700/526, loss: 0.00022354126849677414
2023-01-23 04:16:03.992036: step: 704/526, loss: 3.738403756869957e-05
2023-01-23 04:16:05.103319: step: 708/526, loss: 1.4591218132409267e-05
2023-01-23 04:16:06.227960: step: 712/526, loss: 1.6689300537109375e-05
2023-01-23 04:16:07.331489: step: 716/526, loss: 5.1307681133039296e-05
2023-01-23 04:16:08.518760: step: 720/526, loss: 0.009741402231156826
2023-01-23 04:16:09.646854: step: 724/526, loss: 0.005017471499741077
2023-01-23 04:16:10.794420: step: 728/526, loss: 0.0003294944763183594
2023-01-23 04:16:11.916283: step: 732/526, loss: 0.0008516788366250694
2023-01-23 04:16:13.060158: step: 736/526, loss: 0.0080420495942235
2023-01-23 04:16:14.205780: step: 740/526, loss: 8.125305612338707e-05
2023-01-23 04:16:15.348888: step: 744/526, loss: -3.4332275390625e-05
2023-01-23 04:16:16.498453: step: 748/526, loss: 0.0007475852617062628
2023-01-23 04:16:17.653256: step: 752/526, loss: 0.006243610754609108
2023-01-23 04:16:18.796884: step: 756/526, loss: 1.8596649169921875e-05
2023-01-23 04:16:19.916520: step: 760/526, loss: 6.160736666060984e-05
2023-01-23 04:16:21.063070: step: 764/526, loss: 0.0005108893383294344
2023-01-23 04:16:22.175057: step: 768/526, loss: 0.024231290444731712
2023-01-23 04:16:23.331008: step: 772/526, loss: 1.7166141788038658e-06
2023-01-23 04:16:24.460788: step: 776/526, loss: 3.328323509776965e-05
2023-01-23 04:16:25.600901: step: 780/526, loss: 0.009100914001464844
2023-01-23 04:16:26.757202: step: 784/526, loss: 0.00023050307936500758
2023-01-23 04:16:27.889511: step: 788/526, loss: 0.00033574103144928813
2023-01-23 04:16:29.031378: step: 792/526, loss: 1.9645693100756034e-05
2023-01-23 04:16:30.163566: step: 796/526, loss: 0.0018773078918457031
2023-01-23 04:16:31.264680: step: 800/526, loss: 0.00017633437528274953
2023-01-23 04:16:32.410439: step: 804/526, loss: 0.06858577579259872
2023-01-23 04:16:33.540257: step: 808/526, loss: 0.008789253421127796
2023-01-23 04:16:34.681168: step: 812/526, loss: 0.0004965782281942666
2023-01-23 04:16:35.804041: step: 816/526, loss: 0.0041870116256177425
2023-01-23 04:16:36.947974: step: 820/526, loss: 0.004493141081184149
2023-01-23 04:16:38.070443: step: 824/526, loss: 0.6073503494262695
2023-01-23 04:16:39.192743: step: 828/526, loss: 0.00023174285888671875
2023-01-23 04:16:40.337122: step: 832/526, loss: 0.032556917518377304
2023-01-23 04:16:41.460150: step: 836/526, loss: 0.002376651857048273
2023-01-23 04:16:42.583811: step: 840/526, loss: 0.007678401190787554
2023-01-23 04:16:43.735611: step: 844/526, loss: 0.004945182707160711
2023-01-23 04:16:44.846462: step: 848/526, loss: 0.00032529831514693797
2023-01-23 04:16:45.968708: step: 852/526, loss: 0.006610870361328125
2023-01-23 04:16:47.107498: step: 856/526, loss: 0.012574577704071999
2023-01-23 04:16:48.250238: step: 860/526, loss: 0.016125869005918503
2023-01-23 04:16:49.400192: step: 864/526, loss: 0.0003427505725994706
2023-01-23 04:16:50.549742: step: 868/526, loss: 0.006281661801040173
2023-01-23 04:16:51.694870: step: 872/526, loss: -1.9073486328125e-06
2023-01-23 04:16:52.861560: step: 876/526, loss: 7.43865984986769e-06
2023-01-23 04:16:53.960602: step: 880/526, loss: 0.0005115509266033769
2023-01-23 04:16:55.076910: step: 884/526, loss: 7.262230064952746e-05
2023-01-23 04:16:56.226680: step: 888/526, loss: 0.020418357104063034
2023-01-23 04:16:57.352115: step: 892/526, loss: 3.9768219721736386e-05
2023-01-23 04:16:58.518885: step: 896/526, loss: 0.016159821301698685
2023-01-23 04:16:59.648155: step: 900/526, loss: -8.106231689453125e-06
2023-01-23 04:17:00.775222: step: 904/526, loss: 0.007848739624023438
2023-01-23 04:17:01.936686: step: 908/526, loss: 0.02537841908633709
2023-01-23 04:17:03.063033: step: 912/526, loss: 4.4345855712890625e-05
2023-01-23 04:17:04.210643: step: 916/526, loss: 0.0004116058407817036
2023-01-23 04:17:05.339276: step: 920/526, loss: 0.1156230941414833
2023-01-23 04:17:06.467620: step: 924/526, loss: 0.0006291389581747353
2023-01-23 04:17:07.614335: step: 928/526, loss: 0.0011343955993652344
2023-01-23 04:17:08.752171: step: 932/526, loss: 1.773834264895413e-05
2023-01-23 04:17:09.904344: step: 936/526, loss: 0.001533126924186945
2023-01-23 04:17:11.050395: step: 940/526, loss: 0.00025386811466887593
2023-01-23 04:17:12.196339: step: 944/526, loss: 1.354217511106981e-05
2023-01-23 04:17:13.362737: step: 948/526, loss: 0.5998144149780273
2023-01-23 04:17:14.487112: step: 952/526, loss: 5.981922004139051e-05
2023-01-23 04:17:15.614565: step: 956/526, loss: 3.7002566386945546e-05
2023-01-23 04:17:16.764578: step: 960/526, loss: 0.00599795812740922
2023-01-23 04:17:17.927300: step: 964/526, loss: 0.0029155733063817024
2023-01-23 04:17:19.086254: step: 968/526, loss: 0.001951539539732039
2023-01-23 04:17:20.233116: step: 972/526, loss: 0.010029601864516735
2023-01-23 04:17:21.373938: step: 976/526, loss: 0.0002944946172647178
2023-01-23 04:17:22.504703: step: 980/526, loss: 7.3432925091765355e-06
2023-01-23 04:17:23.649110: step: 984/526, loss: 0.0006487369537353516
2023-01-23 04:17:24.792883: step: 988/526, loss: 0.04792454466223717
2023-01-23 04:17:25.924734: step: 992/526, loss: 8.049011375987902e-05
2023-01-23 04:17:27.072563: step: 996/526, loss: 0.004157734103500843
2023-01-23 04:17:28.231359: step: 1000/526, loss: 0.001708221505396068
2023-01-23 04:17:29.350325: step: 1004/526, loss: 0.0020089149475097656
2023-01-23 04:17:30.470531: step: 1008/526, loss: 4.911422820441658e-06
2023-01-23 04:17:31.614584: step: 1012/526, loss: 0.0021471979562193155
2023-01-23 04:17:32.750788: step: 1016/526, loss: 0.00010185241990257055
2023-01-23 04:17:33.869683: step: 1020/526, loss: 3.051757857974735e-06
2023-01-23 04:17:34.997047: step: 1024/526, loss: 3.0517578125e-05
2023-01-23 04:17:36.129915: step: 1028/526, loss: 0.0010009766556322575
2023-01-23 04:17:37.276279: step: 1032/526, loss: 0.00011339188495185226
2023-01-23 04:17:38.410192: step: 1036/526, loss: 0.2311851978302002
2023-01-23 04:17:39.557371: step: 1040/526, loss: 0.001352500868961215
2023-01-23 04:17:40.681467: step: 1044/526, loss: 0.0010618210071697831
2023-01-23 04:17:41.826931: step: 1048/526, loss: 3.852844747598283e-05
2023-01-23 04:17:42.968204: step: 1052/526, loss: 0.00031651853350922465
2023-01-23 04:17:44.118352: step: 1056/526, loss: 0.0011723518837243319
2023-01-23 04:17:45.276994: step: 1060/526, loss: 5.5313107623078395e-06
2023-01-23 04:17:46.412765: step: 1064/526, loss: 0.00017204285541083664
2023-01-23 04:17:47.531562: step: 1068/526, loss: 0.00351715087890625
2023-01-23 04:17:48.661738: step: 1072/526, loss: 3.9672853745287284e-05
2023-01-23 04:17:49.802220: step: 1076/526, loss: 0.0001314163237111643
2023-01-23 04:17:50.911838: step: 1080/526, loss: 5.741119457525201e-05
2023-01-23 04:17:52.042500: step: 1084/526, loss: 0.009083651937544346
2023-01-23 04:17:53.199660: step: 1088/526, loss: 0.06130790710449219
2023-01-23 04:17:54.353055: step: 1092/526, loss: 0.0018129348754882812
2023-01-23 04:17:55.523816: step: 1096/526, loss: 0.00509986886754632
2023-01-23 04:17:56.667559: step: 1100/526, loss: 0.013837147504091263
2023-01-23 04:17:57.790379: step: 1104/526, loss: 5.91278057981981e-06
2023-01-23 04:17:58.929886: step: 1108/526, loss: 0.0002700805780477822
2023-01-23 04:18:00.053912: step: 1112/526, loss: 0.00014400482177734375
2023-01-23 04:18:01.172739: step: 1116/526, loss: 0.023198891431093216
2023-01-23 04:18:02.302206: step: 1120/526, loss: 0.004236125852912664
2023-01-23 04:18:03.417017: step: 1124/526, loss: 0.1325935423374176
2023-01-23 04:18:04.557403: step: 1128/526, loss: 0.0166015625
2023-01-23 04:18:05.702843: step: 1132/526, loss: 0.0017906189896166325
2023-01-23 04:18:06.810113: step: 1136/526, loss: 0.00027728083659894764
2023-01-23 04:18:07.952684: step: 1140/526, loss: 0.004579353146255016
2023-01-23 04:18:09.092467: step: 1144/526, loss: 0.00022583008103538305
2023-01-23 04:18:10.246178: step: 1148/526, loss: 0.0007657051319256425
2023-01-23 04:18:11.396257: step: 1152/526, loss: 0.016341017559170723
2023-01-23 04:18:12.551745: step: 1156/526, loss: 5.7220458984375e-06
2023-01-23 04:18:13.706254: step: 1160/526, loss: 0.10946149379014969
2023-01-23 04:18:14.845576: step: 1164/526, loss: 0.009315108880400658
2023-01-23 04:18:15.989723: step: 1168/526, loss: 0.00040664675179868937
2023-01-23 04:18:17.162022: step: 1172/526, loss: 8.487701961712446e-06
2023-01-23 04:18:18.281703: step: 1176/526, loss: 1.3065338862361386e-05
2023-01-23 04:18:19.400205: step: 1180/526, loss: -7.152556946721234e-08
2023-01-23 04:18:20.524788: step: 1184/526, loss: 0.006881427951157093
2023-01-23 04:18:21.633657: step: 1188/526, loss: 2.86102294921875e-05
2023-01-23 04:18:22.805376: step: 1192/526, loss: 0.02059183083474636
2023-01-23 04:18:23.944810: step: 1196/526, loss: -8.583065209677443e-07
2023-01-23 04:18:25.090954: step: 1200/526, loss: 0.0018804550636559725
2023-01-23 04:18:26.217100: step: 1204/526, loss: 0.006845378782600164
2023-01-23 04:18:27.310387: step: 1208/526, loss: 8.535384949936997e-06
2023-01-23 04:18:28.444588: step: 1212/526, loss: 0.034250449389219284
2023-01-23 04:18:29.569963: step: 1216/526, loss: 7.677078428969253e-06
2023-01-23 04:18:30.712512: step: 1220/526, loss: 0.011291694827377796
2023-01-23 04:18:31.868450: step: 1224/526, loss: 0.0005156517145223916
2023-01-23 04:18:33.026994: step: 1228/526, loss: 0.0013139724032953382
2023-01-23 04:18:34.174362: step: 1232/526, loss: 0.0016376018757000566
2023-01-23 04:18:35.328302: step: 1236/526, loss: 0.0072765350341796875
2023-01-23 04:18:36.477086: step: 1240/526, loss: 3.2138825190486386e-05
2023-01-23 04:18:37.612196: step: 1244/526, loss: 1.1444091796875e-05
2023-01-23 04:18:38.751811: step: 1248/526, loss: 0.0003936767461709678
2023-01-23 04:18:39.903998: step: 1252/526, loss: 0.07505837082862854
2023-01-23 04:18:41.032500: step: 1256/526, loss: 0.0004282951704226434
2023-01-23 04:18:42.187512: step: 1260/526, loss: 0.006148433778434992
2023-01-23 04:18:43.362178: step: 1264/526, loss: 3.604888843256049e-05
2023-01-23 04:18:44.491526: step: 1268/526, loss: 0.00011596680269576609
2023-01-23 04:18:45.661073: step: 1272/526, loss: 0.00016794205293990672
2023-01-23 04:18:46.754874: step: 1276/526, loss: 0.0003505706845317036
2023-01-23 04:18:47.905964: step: 1280/526, loss: 6.48498553346144e-06
2023-01-23 04:18:49.037098: step: 1284/526, loss: 1.316070574830519e-05
2023-01-23 04:18:50.189239: step: 1288/526, loss: 0.10438423603773117
2023-01-23 04:18:51.313205: step: 1292/526, loss: 0.0013463973300531507
2023-01-23 04:18:52.457614: step: 1296/526, loss: 0.0001501083461334929
2023-01-23 04:18:53.634658: step: 1300/526, loss: 0.042860984802246094
2023-01-23 04:18:54.769761: step: 1304/526, loss: 0.00031223296537064016
2023-01-23 04:18:55.924166: step: 1308/526, loss: 0.0028631212189793587
2023-01-23 04:18:57.046236: step: 1312/526, loss: 0.0017815589671954513
2023-01-23 04:18:58.196175: step: 1316/526, loss: 0.023362064734101295
2023-01-23 04:18:59.340494: step: 1320/526, loss: 0.0005491256597451866
2023-01-23 04:19:00.435326: step: 1324/526, loss: 8.144378080032766e-05
2023-01-23 04:19:01.592931: step: 1328/526, loss: 0.0805664137005806
2023-01-23 04:19:02.759065: step: 1332/526, loss: 1.0871888662222773e-05
2023-01-23 04:19:03.882337: step: 1336/526, loss: 4.291534787626006e-05
2023-01-23 04:19:05.004114: step: 1340/526, loss: 0.0004345893976278603
2023-01-23 04:19:06.124242: step: 1344/526, loss: -1.716613724056515e-06
2023-01-23 04:19:07.267478: step: 1348/526, loss: 0.02762756496667862
2023-01-23 04:19:08.409356: step: 1352/526, loss: 0.042530059814453125
2023-01-23 04:19:09.548852: step: 1356/526, loss: 0.00038051605224609375
2023-01-23 04:19:10.681552: step: 1360/526, loss: 0.020390892401337624
2023-01-23 04:19:11.828268: step: 1364/526, loss: 0.0005153656238690019
2023-01-23 04:19:12.945687: step: 1368/526, loss: 0.000133514404296875
2023-01-23 04:19:14.073645: step: 1372/526, loss: 0.006777000613510609
2023-01-23 04:19:15.215212: step: 1376/526, loss: 0.0012608527904376388
2023-01-23 04:19:16.333371: step: 1380/526, loss: 0.008293438702821732
2023-01-23 04:19:17.472926: step: 1384/526, loss: 0.0027749063447117805
2023-01-23 04:19:18.596434: step: 1388/526, loss: 0.0037401202134788036
2023-01-23 04:19:19.748008: step: 1392/526, loss: 0.0009616852039471269
2023-01-23 04:19:20.869899: step: 1396/526, loss: 1.296997106692288e-05
2023-01-23 04:19:22.013227: step: 1400/526, loss: 0.008121108636260033
2023-01-23 04:19:23.159588: step: 1404/526, loss: 4.76837158203125e-06
2023-01-23 04:19:24.282944: step: 1408/526, loss: 0.00025072097196243703
2023-01-23 04:19:25.434420: step: 1412/526, loss: 0.0007710456848144531
2023-01-23 04:19:26.582596: step: 1416/526, loss: 0.026173783466219902
2023-01-23 04:19:27.735571: step: 1420/526, loss: 0.024512100964784622
2023-01-23 04:19:28.831290: step: 1424/526, loss: 0.07559618353843689
2023-01-23 04:19:29.932168: step: 1428/526, loss: 4.57763690064894e-06
2023-01-23 04:19:31.084061: step: 1432/526, loss: 0.7336997985839844
2023-01-23 04:19:32.211043: step: 1436/526, loss: 0.001161432359367609
2023-01-23 04:19:33.360870: step: 1440/526, loss: 0.012558316811919212
2023-01-23 04:19:34.489354: step: 1444/526, loss: 0.04235009849071503
2023-01-23 04:19:35.629595: step: 1448/526, loss: 1.087188684323337e-05
2023-01-23 04:19:36.730328: step: 1452/526, loss: 3.356933666509576e-05
2023-01-23 04:19:37.837440: step: 1456/526, loss: 0.0007003784412518144
2023-01-23 04:19:38.968113: step: 1460/526, loss: 0.0005109787452965975
2023-01-23 04:19:40.100770: step: 1464/526, loss: 4.9591067181609105e-06
2023-01-23 04:19:41.233555: step: 1468/526, loss: 5.722046353184851e-06
2023-01-23 04:19:42.391942: step: 1472/526, loss: 6.294249760685489e-05
2023-01-23 04:19:43.541123: step: 1476/526, loss: 0.0004680633428506553
2023-01-23 04:19:44.700171: step: 1480/526, loss: 0.0031726837623864412
2023-01-23 04:19:45.842457: step: 1484/526, loss: 1.76429750808893e-06
2023-01-23 04:19:46.969516: step: 1488/526, loss: 0.003940010443329811
2023-01-23 04:19:48.137635: step: 1492/526, loss: 0.007775497157126665
2023-01-23 04:19:49.259244: step: 1496/526, loss: 9.727478754939511e-06
2023-01-23 04:19:50.396159: step: 1500/526, loss: 8.64505855133757e-05
2023-01-23 04:19:51.554295: step: 1504/526, loss: 0.044715117663145065
2023-01-23 04:19:52.666194: step: 1508/526, loss: 0.002186393830925226
2023-01-23 04:19:53.810621: step: 1512/526, loss: 0.0029252052772790194
2023-01-23 04:19:54.954678: step: 1516/526, loss: 0.0035707473289221525
2023-01-23 04:19:56.110078: step: 1520/526, loss: 0.00016727446927689016
2023-01-23 04:19:57.226150: step: 1524/526, loss: 0.00037192701711319387
2023-01-23 04:19:58.351285: step: 1528/526, loss: -1.9073486328125e-06
2023-01-23 04:19:59.495736: step: 1532/526, loss: 0.06125602871179581
2023-01-23 04:20:00.625500: step: 1536/526, loss: 0.0005928039317950606
2023-01-23 04:20:01.787939: step: 1540/526, loss: 0.00128850934561342
2023-01-23 04:20:02.951140: step: 1544/526, loss: 0.0016193389892578125
2023-01-23 04:20:04.077931: step: 1548/526, loss: 0.08031503856182098
2023-01-23 04:20:05.234296: step: 1552/526, loss: 0.0033309936989098787
2023-01-23 04:20:06.383639: step: 1556/526, loss: 1.5926361811580136e-05
2023-01-23 04:20:07.510891: step: 1560/526, loss: 3.80516066798009e-05
2023-01-23 04:20:08.659470: step: 1564/526, loss: 0.0001712799130473286
2023-01-23 04:20:09.800015: step: 1568/526, loss: 0.009743690490722656
2023-01-23 04:20:10.956067: step: 1572/526, loss: 0.0004024505615234375
2023-01-23 04:20:12.068017: step: 1576/526, loss: -6.4373016357421875e-06
2023-01-23 04:20:13.194426: step: 1580/526, loss: 0.272746741771698
2023-01-23 04:20:14.326855: step: 1584/526, loss: 0.0018127441871911287
2023-01-23 04:20:15.484842: step: 1588/526, loss: 0.0005079269176349044
2023-01-23 04:20:16.646276: step: 1592/526, loss: 0.001050758408382535
2023-01-23 04:20:17.780563: step: 1596/526, loss: 0.0014330863486975431
2023-01-23 04:20:18.904763: step: 1600/526, loss: 0.015057658776640892
2023-01-23 04:20:20.027845: step: 1604/526, loss: 0.04213309288024902
2023-01-23 04:20:21.126643: step: 1608/526, loss: 0.0001644372969167307
2023-01-23 04:20:22.324733: step: 1612/526, loss: 0.0016588210128247738
2023-01-23 04:20:23.473575: step: 1616/526, loss: 3.898143768310547e-05
2023-01-23 04:20:24.620375: step: 1620/526, loss: 0.00263214111328125
2023-01-23 04:20:25.752560: step: 1624/526, loss: 6.771087646484375e-05
2023-01-23 04:20:26.864766: step: 1628/526, loss: 0.0016007423400878906
2023-01-23 04:20:28.037653: step: 1632/526, loss: 0.00038547517033293843
2023-01-23 04:20:29.162875: step: 1636/526, loss: 5.0735470722429454e-05
2023-01-23 04:20:30.291557: step: 1640/526, loss: 0.0005164146423339844
2023-01-23 04:20:31.392675: step: 1644/526, loss: 1.9073486328125e-05
2023-01-23 04:20:32.498391: step: 1648/526, loss: 0.020950699225068092
2023-01-23 04:20:33.632644: step: 1652/526, loss: 1.1634827387752011e-05
2023-01-23 04:20:34.747517: step: 1656/526, loss: 0.013421058654785156
2023-01-23 04:20:35.883644: step: 1660/526, loss: 0.01631312444806099
2023-01-23 04:20:37.005180: step: 1664/526, loss: -7.05719003235572e-06
2023-01-23 04:20:38.120982: step: 1668/526, loss: 0.0001385688956361264
2023-01-23 04:20:39.265026: step: 1672/526, loss: 0.01915550045669079
2023-01-23 04:20:40.408453: step: 1676/526, loss: 0.0016635895008221269
2023-01-23 04:20:41.537717: step: 1680/526, loss: 0.05268049240112305
2023-01-23 04:20:42.669793: step: 1684/526, loss: 5.831718590343371e-05
2023-01-23 04:20:43.810334: step: 1688/526, loss: 0.00021495818509720266
2023-01-23 04:20:44.973312: step: 1692/526, loss: 0.0003068924124818295
2023-01-23 04:20:46.110648: step: 1696/526, loss: 3.051757857974735e-06
2023-01-23 04:20:47.271031: step: 1700/526, loss: -1.52587890625e-05
2023-01-23 04:20:48.381233: step: 1704/526, loss: 1.4400482541532256e-05
2023-01-23 04:20:49.503325: step: 1708/526, loss: 0.019866324961185455
2023-01-23 04:20:50.629127: step: 1712/526, loss: 2.622604552016128e-05
2023-01-23 04:20:51.743354: step: 1716/526, loss: 0.0023622512817382812
2023-01-23 04:20:52.853262: step: 1720/526, loss: -7.62939453125e-06
2023-01-23 04:20:54.004452: step: 1724/526, loss: 0.00035152435884810984
2023-01-23 04:20:55.111424: step: 1728/526, loss: -1.4781952586417901e-06
2023-01-23 04:20:56.237834: step: 1732/526, loss: 0.000339508056640625
2023-01-23 04:20:57.384689: step: 1736/526, loss: 0.0001672744838288054
2023-01-23 04:20:58.539516: step: 1740/526, loss: 0.025621796026825905
2023-01-23 04:20:59.649479: step: 1744/526, loss: 0.0007631301996298134
2023-01-23 04:21:00.793971: step: 1748/526, loss: 0.002261257264763117
2023-01-23 04:21:01.929026: step: 1752/526, loss: 0.008528710342943668
2023-01-23 04:21:03.045052: step: 1756/526, loss: 0.013813590630888939
2023-01-23 04:21:04.145119: step: 1760/526, loss: 0.00030117033747956157
2023-01-23 04:21:05.284954: step: 1764/526, loss: 0.0006011963123455644
2023-01-23 04:21:06.408115: step: 1768/526, loss: 3.5285947888041846e-06
2023-01-23 04:21:07.534710: step: 1772/526, loss: 0.0001256942778127268
2023-01-23 04:21:08.665510: step: 1776/526, loss: 1.811981201171875e-05
2023-01-23 04:21:09.812801: step: 1780/526, loss: 1.7929078239831142e-05
2023-01-23 04:21:10.935530: step: 1784/526, loss: 0.00043010711669921875
2023-01-23 04:21:12.101034: step: 1788/526, loss: 0.0030249119736254215
2023-01-23 04:21:13.241170: step: 1792/526, loss: 0.0048306467942893505
2023-01-23 04:21:14.392737: step: 1796/526, loss: 0.001056671142578125
2023-01-23 04:21:15.541891: step: 1800/526, loss: 0.0009451866499148309
2023-01-23 04:21:16.657875: step: 1804/526, loss: 0.07289252430200577
2023-01-23 04:21:17.773343: step: 1808/526, loss: 0.08858004212379456
2023-01-23 04:21:18.910276: step: 1812/526, loss: 0.00022373200044967234
2023-01-23 04:21:20.051793: step: 1816/526, loss: 0.02032756805419922
2023-01-23 04:21:21.228900: step: 1820/526, loss: 0.017384672537446022
2023-01-23 04:21:22.358656: step: 1824/526, loss: 0.0001659393310546875
2023-01-23 04:21:23.498800: step: 1828/526, loss: 0.009712601080536842
2023-01-23 04:21:24.650898: step: 1832/526, loss: 3.967285010730848e-05
2023-01-23 04:21:25.809675: step: 1836/526, loss: 0.0002857208310160786
2023-01-23 04:21:26.931378: step: 1840/526, loss: 0.00012111663818359375
2023-01-23 04:21:28.065436: step: 1844/526, loss: 0.04125986248254776
2023-01-23 04:21:29.172972: step: 1848/526, loss: 0.001188087509945035
2023-01-23 04:21:30.310260: step: 1852/526, loss: 0.007689285557717085
2023-01-23 04:21:31.458374: step: 1856/526, loss: 0.00015559197345282882
2023-01-23 04:21:32.570135: step: 1860/526, loss: 0.0003532409609761089
2023-01-23 04:21:33.706311: step: 1864/526, loss: 0.0001885414239950478
2023-01-23 04:21:34.850581: step: 1868/526, loss: 0.0015705109108239412
2023-01-23 04:21:35.993068: step: 1872/526, loss: 0.000545501708984375
2023-01-23 04:21:37.106093: step: 1876/526, loss: 0.0002323150692973286
2023-01-23 04:21:38.243896: step: 1880/526, loss: 0.00027551650418899953
2023-01-23 04:21:39.386489: step: 1884/526, loss: 0.007864952087402344
2023-01-23 04:21:40.563930: step: 1888/526, loss: 0.27130481600761414
2023-01-23 04:21:41.684201: step: 1892/526, loss: 2.9277802241267636e-05
2023-01-23 04:21:42.854694: step: 1896/526, loss: 2.0027162008773303e-06
2023-01-23 04:21:43.967074: step: 1900/526, loss: 5.817413693876006e-06
2023-01-23 04:21:45.111218: step: 1904/526, loss: 0.0028642655815929174
2023-01-23 04:21:46.245394: step: 1908/526, loss: 6.10351571594947e-06
2023-01-23 04:21:47.380234: step: 1912/526, loss: 1.087188684323337e-05
2023-01-23 04:21:48.483139: step: 1916/526, loss: 0.0011740685440599918
2023-01-23 04:21:49.622948: step: 1920/526, loss: 0.09104882180690765
2023-01-23 04:21:50.736719: step: 1924/526, loss: 0.002863311907276511
2023-01-23 04:21:51.875154: step: 1928/526, loss: 1.678466833254788e-05
2023-01-23 04:21:52.998171: step: 1932/526, loss: 0.00023956299992278218
2023-01-23 04:21:54.181170: step: 1936/526, loss: 7.181167165981606e-05
2023-01-23 04:21:55.292627: step: 1940/526, loss: 0.0010404587956145406
2023-01-23 04:21:56.415444: step: 1944/526, loss: 0.02699403651058674
2023-01-23 04:21:57.561086: step: 1948/526, loss: 0.00089349749032408
2023-01-23 04:21:58.701880: step: 1952/526, loss: 0.010082244873046875
2023-01-23 04:21:59.815921: step: 1956/526, loss: 5.378723290050402e-05
2023-01-23 04:22:00.979980: step: 1960/526, loss: 0.002050781389698386
2023-01-23 04:22:02.110615: step: 1964/526, loss: 0.00013637542724609375
2023-01-23 04:22:03.228198: step: 1968/526, loss: 4.673004241340095e-06
2023-01-23 04:22:04.335874: step: 1972/526, loss: 0.0005458832019940019
2023-01-23 04:22:05.478416: step: 1976/526, loss: 0.00014085769362282008
2023-01-23 04:22:06.606854: step: 1980/526, loss: 0.0729871392250061
2023-01-23 04:22:07.754757: step: 1984/526, loss: 0.00127582554705441
2023-01-23 04:22:08.858661: step: 1988/526, loss: 0.01306066568940878
2023-01-23 04:22:09.964461: step: 1992/526, loss: 0.013928795233368874
2023-01-23 04:22:11.136922: step: 1996/526, loss: 0.010881423950195312
2023-01-23 04:22:12.267491: step: 2000/526, loss: 0.33638009428977966
2023-01-23 04:22:13.389348: step: 2004/526, loss: 3.528594970703125e-05
2023-01-23 04:22:14.520671: step: 2008/526, loss: 0.00032930372981354594
2023-01-23 04:22:15.652212: step: 2012/526, loss: 0.010987472720444202
2023-01-23 04:22:16.820489: step: 2016/526, loss: 0.012489271350204945
2023-01-23 04:22:17.964351: step: 2020/526, loss: 5.2165985835017636e-05
2023-01-23 04:22:19.078480: step: 2024/526, loss: 1.4829635802016128e-05
2023-01-23 04:22:20.211258: step: 2028/526, loss: 0.05006008222699165
2023-01-23 04:22:21.315922: step: 2032/526, loss: 5.760193016612902e-05
2023-01-23 04:22:22.461705: step: 2036/526, loss: 0.00137157435528934
2023-01-23 04:22:23.626081: step: 2040/526, loss: 0.026972580701112747
2023-01-23 04:22:24.749345: step: 2044/526, loss: 7.82012921263231e-06
2023-01-23 04:22:25.874865: step: 2048/526, loss: 1.239776611328125e-05
2023-01-23 04:22:27.001381: step: 2052/526, loss: 0.018094254657626152
2023-01-23 04:22:28.131184: step: 2056/526, loss: 0.0017058133380487561
2023-01-23 04:22:29.295430: step: 2060/526, loss: 0.0008918762323446572
2023-01-23 04:22:30.395523: step: 2064/526, loss: 0.00017433166794944555
2023-01-23 04:22:31.583824: step: 2068/526, loss: 9.889602370094508e-05
2023-01-23 04:22:32.726095: step: 2072/526, loss: 0.0003669738944154233
2023-01-23 04:22:33.880965: step: 2076/526, loss: 9.059906733455136e-05
2023-01-23 04:22:35.021561: step: 2080/526, loss: 0.011842727661132812
2023-01-23 04:22:36.155162: step: 2084/526, loss: 0.06062927097082138
2023-01-23 04:22:37.271713: step: 2088/526, loss: 0.016322897747159004
2023-01-23 04:22:38.409345: step: 2092/526, loss: -2.2029877072782256e-05
2023-01-23 04:22:39.543649: step: 2096/526, loss: 0.00043077467125840485
2023-01-23 04:22:40.661767: step: 2100/526, loss: 3.62396240234375e-05
2023-01-23 04:22:41.817126: step: 2104/526, loss: 0.02538776397705078
==================================================
Loss: 0.013
--------------------
Dev: {'event': {'p': 0.614240170031881, 'r': 0.7696404793608522, 'f1': 0.6832151300236406}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
Test: {'event': {'p': 0.6294871794871795, 'r': 0.7687891440501043, 'f1': 0.6921992481203008}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
Chinese: {'event': {'p': 0.631578947368421, 'r': 0.8888888888888888, 'f1': 0.7384615384615385}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
Korean: {'event': {'p': 0.6818181818181818, 'r': 0.47619047619047616, 'f1': 0.5607476635514018}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
Russian: {'event': {'p': 0.4473684210526316, 'r': 0.4722222222222222, 'f1': 0.4594594594594595}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6266519823788547, 'r': 0.7576564580559254, 'f1': 0.6859553948161543}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Eng Test for Chinese: {'event': {'p': 0.6313522825150732, 'r': 0.7651356993736952, 'f1': 0.6918357715903728}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Sample Chinese: {'event': {'p': 0.6621621621621622, 'r': 0.9074074074074074, 'f1': 0.765625}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6257995735607675, 'r': 0.7816245006657789, 'f1': 0.6950858496151568}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Eng Test for Korean: {'event': {'p': 0.623113410952997, 'r': 0.7541753653444676, 'f1': 0.6824085005903188}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Sample Korean: {'event': {'p': 0.7446808510638298, 'r': 0.5555555555555556, 'f1': 0.6363636363636364}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6266519823788547, 'r': 0.7576564580559254, 'f1': 0.6859553948161543}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Eng Test for Russian: {'event': {'p': 0.6313522825150732, 'r': 0.7651356993736952, 'f1': 0.6918357715903728}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Sample Russian: {'event': {'p': 0.5384615384615384, 'r': 0.5833333333333334, 'f1': 0.5599999999999999}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
******************************
Epoch: 28
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 04:23:24.530455: step: 4/526, loss: 0.012076378799974918
2023-01-23 04:23:25.702960: step: 8/526, loss: 0.012168694287538528
2023-01-23 04:23:26.831323: step: 12/526, loss: 0.0034654466435313225
2023-01-23 04:23:27.966419: step: 16/526, loss: 0.0021366120781749487
2023-01-23 04:23:29.090036: step: 20/526, loss: 0.00029096603975631297
2023-01-23 04:23:30.215711: step: 24/526, loss: 9.880065772449598e-05
2023-01-23 04:23:31.330692: step: 28/526, loss: 1.2207032341393642e-05
2023-01-23 04:23:32.440202: step: 32/526, loss: 0.00024100541486404836
2023-01-23 04:23:33.554884: step: 36/526, loss: 0.003618240589275956
2023-01-23 04:23:34.695067: step: 40/526, loss: 0.02555117756128311
2023-01-23 04:23:35.785971: step: 44/526, loss: 9.775161743164062e-06
2023-01-23 04:23:36.924131: step: 48/526, loss: 0.04503012076020241
2023-01-23 04:23:38.042018: step: 52/526, loss: 0.0017394066089764237
2023-01-23 04:23:39.203150: step: 56/526, loss: 0.06529799103736877
2023-01-23 04:23:40.358094: step: 60/526, loss: 3.566742088878527e-05
2023-01-23 04:23:41.474958: step: 64/526, loss: 2.098083541568485e-06
2023-01-23 04:23:42.624617: step: 68/526, loss: 0.02854161337018013
2023-01-23 04:23:43.752667: step: 72/526, loss: 0.06816143542528152
2023-01-23 04:23:44.865511: step: 76/526, loss: 0.018248939886689186
2023-01-23 04:23:45.984464: step: 80/526, loss: 8.58306884765625e-05
2023-01-23 04:23:47.114609: step: 84/526, loss: 0.0007057190523482859
2023-01-23 04:23:48.244706: step: 88/526, loss: 0.0052852630615234375
2023-01-23 04:23:49.375469: step: 92/526, loss: 1.125335711549269e-05
2023-01-23 04:23:50.491070: step: 96/526, loss: 0.00024313927860930562
2023-01-23 04:23:51.642941: step: 100/526, loss: 0.0002695083385333419
2023-01-23 04:23:52.780111: step: 104/526, loss: 0.0020261763129383326
2023-01-23 04:23:53.931581: step: 108/526, loss: 0.0001333236723439768
2023-01-23 04:23:55.091828: step: 112/526, loss: 0.0025209428276866674
2023-01-23 04:23:56.230126: step: 116/526, loss: 8.77380352903856e-06
2023-01-23 04:23:57.366860: step: 120/526, loss: 2.0980837689421605e-06
2023-01-23 04:23:58.544387: step: 124/526, loss: 0.036746978759765625
2023-01-23 04:23:59.670406: step: 128/526, loss: 0.0001458644837839529
2023-01-23 04:24:00.811050: step: 132/526, loss: 0.00012021065049339086
2023-01-23 04:24:01.962725: step: 136/526, loss: 0.0001428842660970986
2023-01-23 04:24:03.101042: step: 140/526, loss: 7.867813110351562e-06
2023-01-23 04:24:04.227090: step: 144/526, loss: 1.583099401614163e-05
2023-01-23 04:24:05.371685: step: 148/526, loss: 8.344650268554688e-06
2023-01-23 04:24:06.478854: step: 152/526, loss: 0.0009455680847167969
2023-01-23 04:24:07.619123: step: 156/526, loss: 0.0001331329403910786
2023-01-23 04:24:08.728558: step: 160/526, loss: 0.0005329131963662803
2023-01-23 04:24:09.869039: step: 164/526, loss: 0.001282692071981728
2023-01-23 04:24:10.991193: step: 168/526, loss: 0.0004152298206463456
2023-01-23 04:24:12.141703: step: 172/526, loss: 0.0011913300259038806
2023-01-23 04:24:13.256357: step: 176/526, loss: 0.03232569620013237
2023-01-23 04:24:14.359224: step: 180/526, loss: 0.0036855696234852076
2023-01-23 04:24:15.512004: step: 184/526, loss: 0.00052728655282408
2023-01-23 04:24:16.636398: step: 188/526, loss: 4.243850526108872e-06
2023-01-23 04:24:17.774705: step: 192/526, loss: 0.006767845246940851
2023-01-23 04:24:18.896963: step: 196/526, loss: 3.1089784897631034e-05
2023-01-23 04:24:20.068891: step: 200/526, loss: 0.0008615494007244706
2023-01-23 04:24:21.191071: step: 204/526, loss: 1.2493132999225054e-05
2023-01-23 04:24:22.344506: step: 208/526, loss: 0.006457710172981024
2023-01-23 04:24:23.490602: step: 212/526, loss: 0.00015373229689430445
2023-01-23 04:24:24.633484: step: 216/526, loss: 0.06100053712725639
2023-01-23 04:24:25.756256: step: 220/526, loss: 0.019083594903349876
2023-01-23 04:24:26.889865: step: 224/526, loss: 0.0010037422180175781
2023-01-23 04:24:28.015578: step: 228/526, loss: 0.02661914750933647
2023-01-23 04:24:29.122832: step: 232/526, loss: 9.193419828079641e-05
2023-01-23 04:24:30.279934: step: 236/526, loss: 0.08594484627246857
2023-01-23 04:24:31.422987: step: 240/526, loss: 2.8133392333984375e-05
2023-01-23 04:24:32.645975: step: 244/526, loss: 5.950927879894152e-05
2023-01-23 04:24:33.785894: step: 248/526, loss: 0.0008760452619753778
2023-01-23 04:24:34.953298: step: 252/526, loss: 0.003277254058048129
2023-01-23 04:24:36.117656: step: 256/526, loss: 0.0628608763217926
2023-01-23 04:24:37.287059: step: 260/526, loss: 0.02050018310546875
2023-01-23 04:24:38.431101: step: 264/526, loss: 0.00021457672119140625
2023-01-23 04:24:39.564582: step: 268/526, loss: 8.39233416627394e-06
2023-01-23 04:24:40.691353: step: 272/526, loss: 0.014435388147830963
2023-01-23 04:24:41.838779: step: 276/526, loss: 0.003130245255306363
2023-01-23 04:24:42.971389: step: 280/526, loss: 0.0004459381161723286
2023-01-23 04:24:44.126387: step: 284/526, loss: 1.3351441339182202e-06
2023-01-23 04:24:45.261788: step: 288/526, loss: 8.897781663108617e-05
2023-01-23 04:24:46.382131: step: 292/526, loss: 0.0006437301635742188
2023-01-23 04:24:47.493237: step: 296/526, loss: 0.004516029264777899
2023-01-23 04:24:48.615150: step: 300/526, loss: 0.009015274234116077
2023-01-23 04:24:49.756486: step: 304/526, loss: 0.02776656113564968
2023-01-23 04:24:50.861270: step: 308/526, loss: 6.10351571594947e-06
2023-01-23 04:24:51.990885: step: 312/526, loss: 0.00010604858834994957
2023-01-23 04:24:53.155060: step: 316/526, loss: 0.00014171600923873484
2023-01-23 04:24:54.306061: step: 320/526, loss: 0.0011230945819988847
2023-01-23 04:24:55.452534: step: 324/526, loss: 0.007213592529296875
2023-01-23 04:24:56.581354: step: 328/526, loss: 0.005086231045424938
2023-01-23 04:24:57.710202: step: 332/526, loss: 0.04716377332806587
2023-01-23 04:24:58.864427: step: 336/526, loss: 8.020401583053172e-05
2023-01-23 04:24:59.987624: step: 340/526, loss: 0.03883972018957138
2023-01-23 04:25:01.144094: step: 344/526, loss: 7.82012939453125e-05
2023-01-23 04:25:02.285306: step: 348/526, loss: 0.714342474937439
2023-01-23 04:25:03.426822: step: 352/526, loss: 0.00027503969613462687
2023-01-23 04:25:04.526963: step: 356/526, loss: 6.637573824264109e-05
2023-01-23 04:25:05.662019: step: 360/526, loss: 2.1791458493680693e-05
2023-01-23 04:25:06.805040: step: 364/526, loss: 0.0007914542802609503
2023-01-23 04:25:07.944954: step: 368/526, loss: 0.27310752868652344
2023-01-23 04:25:09.069385: step: 372/526, loss: 4.482269287109375e-05
2023-01-23 04:25:10.215523: step: 376/526, loss: 1.71661376953125e-05
2023-01-23 04:25:11.329250: step: 380/526, loss: 0.0014087200397625566
2023-01-23 04:25:12.445839: step: 384/526, loss: 0.00010261536226607859
2023-01-23 04:25:13.615109: step: 388/526, loss: 6.66618361719884e-05
2023-01-23 04:25:14.736163: step: 392/526, loss: 0.0027841569390147924
2023-01-23 04:25:15.910797: step: 396/526, loss: 0.0003030777152162045
2023-01-23 04:25:17.041934: step: 400/526, loss: 0.0002817154163494706
2023-01-23 04:25:18.180872: step: 404/526, loss: 7.686614844715223e-05
2023-01-23 04:25:19.347655: step: 408/526, loss: 0.0007841110345907509
2023-01-23 04:25:20.498726: step: 412/526, loss: 0.0003810882626567036
2023-01-23 04:25:21.658399: step: 416/526, loss: 1.1634827387752011e-05
2023-01-23 04:25:22.775758: step: 420/526, loss: 0.0004432678397279233
2023-01-23 04:25:23.933362: step: 424/526, loss: 0.006811332888901234
2023-01-23 04:25:25.090067: step: 428/526, loss: 0.0010438918834552169
2023-01-23 04:25:26.209701: step: 432/526, loss: 0.0017036438221111894
2023-01-23 04:25:27.325973: step: 436/526, loss: 0.0005007743602618575
2023-01-23 04:25:28.474256: step: 440/526, loss: 0.001735734986141324
2023-01-23 04:25:29.624451: step: 444/526, loss: 0.0012195587623864412
2023-01-23 04:25:30.751696: step: 448/526, loss: 0.00018138886662200093
2023-01-23 04:25:31.866448: step: 452/526, loss: 0.00047025681124068797
2023-01-23 04:25:33.006375: step: 456/526, loss: 0.004047823138535023
2023-01-23 04:25:34.181634: step: 460/526, loss: 0.014491081237792969
2023-01-23 04:25:35.302450: step: 464/526, loss: -3.4332276754867053e-06
2023-01-23 04:25:36.466003: step: 468/526, loss: 0.011139297857880592
2023-01-23 04:25:37.614186: step: 472/526, loss: 2.765655517578125e-05
2023-01-23 04:25:38.733086: step: 476/526, loss: 0.0001720428408589214
2023-01-23 04:25:39.855619: step: 480/526, loss: -8.96453821042087e-06
2023-01-23 04:25:41.030799: step: 484/526, loss: 0.0004913330194540322
2023-01-23 04:25:42.166717: step: 488/526, loss: 1.6975403923424892e-05
2023-01-23 04:25:43.329133: step: 492/526, loss: 0.017278004437685013
2023-01-23 04:25:44.444236: step: 496/526, loss: 4.4631960918195546e-05
2023-01-23 04:25:45.644839: step: 500/526, loss: 0.00047216415987350047
2023-01-23 04:25:46.763303: step: 504/526, loss: 0.07259654998779297
2023-01-23 04:25:47.884834: step: 508/526, loss: 1.087188684323337e-05
2023-01-23 04:25:49.004890: step: 512/526, loss: 0.00179119105450809
2023-01-23 04:25:50.175380: step: 516/526, loss: 0.00010814666893566027
2023-01-23 04:25:51.290286: step: 520/526, loss: 0.0005269527900964022
2023-01-23 04:25:52.406719: step: 524/526, loss: 0.0021200180053710938
2023-01-23 04:25:53.545809: step: 528/526, loss: 0.00012512206740211695
2023-01-23 04:25:54.674829: step: 532/526, loss: 0.004712152760475874
2023-01-23 04:25:55.779226: step: 536/526, loss: 0.00177001953125
2023-01-23 04:25:56.892346: step: 540/526, loss: 0.05389223247766495
2023-01-23 04:25:58.057836: step: 544/526, loss: 0.00669097900390625
2023-01-23 04:25:59.200547: step: 548/526, loss: 7.43865984986769e-06
2023-01-23 04:26:00.334095: step: 552/526, loss: 0.0019368171924725175
2023-01-23 04:26:01.497569: step: 556/526, loss: 0.5350887179374695
2023-01-23 04:26:02.641538: step: 560/526, loss: 2.384185791015625e-05
2023-01-23 04:26:03.765775: step: 564/526, loss: 0.004017638973891735
2023-01-23 04:26:04.854036: step: 568/526, loss: 1.4781952586417901e-06
2023-01-23 04:26:05.989528: step: 572/526, loss: 0.011543608270585537
2023-01-23 04:26:07.137366: step: 576/526, loss: 0.0011549950577318668
2023-01-23 04:26:08.283121: step: 580/526, loss: -2.86102294921875e-05
2023-01-23 04:26:09.411279: step: 584/526, loss: 0.003205585526302457
2023-01-23 04:26:10.541646: step: 588/526, loss: 0.0004784584161825478
2023-01-23 04:26:11.669206: step: 592/526, loss: 3.528594970703125e-05
2023-01-23 04:26:12.840229: step: 596/526, loss: 9.279252117266878e-05
2023-01-23 04:26:13.957604: step: 600/526, loss: 0.0007670402992516756
2023-01-23 04:26:15.092838: step: 604/526, loss: 0.0010917664039880037
2023-01-23 04:26:16.236227: step: 608/526, loss: 0.04972153156995773
2023-01-23 04:26:17.376591: step: 612/526, loss: 0.012523460201919079
2023-01-23 04:26:18.505248: step: 616/526, loss: 0.0001637458917684853
2023-01-23 04:26:19.606886: step: 620/526, loss: 0.0012747765285894275
2023-01-23 04:26:20.712589: step: 624/526, loss: -6.198883056640625e-06
2023-01-23 04:26:21.836643: step: 628/526, loss: 0.0009052276145666838
2023-01-23 04:26:22.996326: step: 632/526, loss: 0.05101451650261879
2023-01-23 04:26:24.138629: step: 636/526, loss: 0.004829693119972944
2023-01-23 04:26:25.276094: step: 640/526, loss: 0.0006771088228560984
2023-01-23 04:26:26.394501: step: 644/526, loss: 0.008210944943130016
2023-01-23 04:26:27.532457: step: 648/526, loss: 0.003708410309627652
2023-01-23 04:26:28.660062: step: 652/526, loss: -8.296966370835435e-06
2023-01-23 04:26:29.790956: step: 656/526, loss: 0.00738601665943861
2023-01-23 04:26:30.917536: step: 660/526, loss: 2.8705595468636602e-05
2023-01-23 04:26:32.071483: step: 664/526, loss: 0.003025054931640625
2023-01-23 04:26:33.229057: step: 668/526, loss: 0.010843753814697266
2023-01-23 04:26:34.346970: step: 672/526, loss: 1.7166139514301904e-06
2023-01-23 04:26:35.485122: step: 676/526, loss: 0.0007969856378622353
2023-01-23 04:26:36.601145: step: 680/526, loss: 0.028282547369599342
2023-01-23 04:26:37.730441: step: 684/526, loss: 0.00011711120896507055
2023-01-23 04:26:38.913051: step: 688/526, loss: 3.6048892070539296e-05
2023-01-23 04:26:40.063049: step: 692/526, loss: 4.863738922722405e-06
2023-01-23 04:26:41.214183: step: 696/526, loss: 0.0001727580965962261
2023-01-23 04:26:42.345888: step: 700/526, loss: 0.00011482238187454641
2023-01-23 04:26:43.479993: step: 704/526, loss: 0.008797836489975452
2023-01-23 04:26:44.619532: step: 708/526, loss: 0.0014982223510742188
2023-01-23 04:26:45.742935: step: 712/526, loss: 8.344650996150449e-05
2023-01-23 04:26:46.872841: step: 716/526, loss: 0.00037832261295989156
2023-01-23 04:26:48.020890: step: 720/526, loss: 0.055109117180109024
2023-01-23 04:26:49.166228: step: 724/526, loss: 0.00867166556417942
2023-01-23 04:26:50.292668: step: 728/526, loss: 0.002102804370224476
2023-01-23 04:26:51.390279: step: 732/526, loss: 0.002773284912109375
2023-01-23 04:26:52.523878: step: 736/526, loss: 0.0007508278358727694
2023-01-23 04:26:53.649643: step: 740/526, loss: 0.0006198883056640625
2023-01-23 04:26:54.788474: step: 744/526, loss: 0.0018260955112054944
2023-01-23 04:26:55.925251: step: 748/526, loss: 0.00012454987154342234
2023-01-23 04:26:57.043681: step: 752/526, loss: 0.009970664978027344
2023-01-23 04:26:58.181598: step: 756/526, loss: 0.021911144256591797
2023-01-23 04:26:59.289464: step: 760/526, loss: 1.0776519957289565e-05
2023-01-23 04:27:00.420625: step: 764/526, loss: 1.8692018784349784e-05
2023-01-23 04:27:01.562906: step: 768/526, loss: 2.536773718020413e-05
2023-01-23 04:27:02.708740: step: 772/526, loss: 6.866455805720761e-05
2023-01-23 04:27:03.831086: step: 776/526, loss: 0.0012810706393793225
2023-01-23 04:27:04.952666: step: 780/526, loss: 0.0014472008915618062
2023-01-23 04:27:06.086516: step: 784/526, loss: 0.02641601487994194
2023-01-23 04:27:07.202542: step: 788/526, loss: 0.002408027881756425
2023-01-23 04:27:08.335580: step: 792/526, loss: 2.021789623540826e-05
2023-01-23 04:27:09.435372: step: 796/526, loss: 0.024468136951327324
2023-01-23 04:27:10.578193: step: 800/526, loss: 0.0036302567459642887
2023-01-23 04:27:11.693268: step: 804/526, loss: 0.0004161834658589214
2023-01-23 04:27:12.910976: step: 808/526, loss: 0.007156944368034601
2023-01-23 04:27:14.034051: step: 812/526, loss: 0.0001233577640959993
2023-01-23 04:27:15.159875: step: 816/526, loss: 0.0041217803955078125
2023-01-23 04:27:16.310744: step: 820/526, loss: 0.01782817766070366
2023-01-23 04:27:17.437150: step: 824/526, loss: 8.869171142578125e-05
2023-01-23 04:27:18.565062: step: 828/526, loss: 0.0035326960496604443
2023-01-23 04:27:19.665069: step: 832/526, loss: 3.986358569818549e-05
2023-01-23 04:27:20.813697: step: 836/526, loss: 5.1116945542162284e-05
2023-01-23 04:27:21.925061: step: 840/526, loss: -2.86102294921875e-06
2023-01-23 04:27:23.086860: step: 844/526, loss: 0.0006128310924395919
2023-01-23 04:27:24.233301: step: 848/526, loss: 8.75473051564768e-05
2023-01-23 04:27:25.357547: step: 852/526, loss: -2.002715973503655e-06
2023-01-23 04:27:26.497643: step: 856/526, loss: 0.027760697528719902
2023-01-23 04:27:27.653737: step: 860/526, loss: 0.0004444122314453125
2023-01-23 04:27:28.782512: step: 864/526, loss: 2.3651124138268642e-05
2023-01-23 04:27:29.956681: step: 868/526, loss: 0.005697059445083141
2023-01-23 04:27:31.084213: step: 872/526, loss: 0.00011959076073253527
2023-01-23 04:27:32.230988: step: 876/526, loss: 0.009966659359633923
2023-01-23 04:27:33.374997: step: 880/526, loss: 0.06708285212516785
2023-01-23 04:27:34.515661: step: 884/526, loss: 8.354186866199598e-05
2023-01-23 04:27:35.653018: step: 888/526, loss: 0.004384040366858244
2023-01-23 04:27:36.810292: step: 892/526, loss: 0.007876587100327015
2023-01-23 04:27:37.977605: step: 896/526, loss: 0.01158838253468275
2023-01-23 04:27:39.088627: step: 900/526, loss: 0.0033540725708007812
2023-01-23 04:27:40.241091: step: 904/526, loss: 2.212524486822076e-05
2023-01-23 04:27:41.415312: step: 908/526, loss: 0.04241600260138512
2023-01-23 04:27:42.545861: step: 912/526, loss: 0.0035985945723950863
2023-01-23 04:27:43.719618: step: 916/526, loss: 0.000552749668713659
2023-01-23 04:27:44.883952: step: 920/526, loss: 0.00013828277587890625
2023-01-23 04:27:46.003204: step: 924/526, loss: 0.001910400460474193
2023-01-23 04:27:47.186647: step: 928/526, loss: 0.0011866569984704256
2023-01-23 04:27:48.331136: step: 932/526, loss: 0.0017074585193768144
2023-01-23 04:27:49.469582: step: 936/526, loss: 0.001060104463249445
2023-01-23 04:27:50.616708: step: 940/526, loss: 1.506805438111769e-05
2023-01-23 04:27:51.741101: step: 944/526, loss: 0.00022454261488746852
2023-01-23 04:27:52.889521: step: 948/526, loss: 0.0009961128234863281
2023-01-23 04:27:54.014054: step: 952/526, loss: 0.0019540786743164062
2023-01-23 04:27:55.150162: step: 956/526, loss: 1.792907642084174e-05
2023-01-23 04:27:56.282069: step: 960/526, loss: 0.0009687423589639366
2023-01-23 04:27:57.400885: step: 964/526, loss: 0.00042819976806640625
2023-01-23 04:27:58.533364: step: 968/526, loss: 0.0016031265258789062
2023-01-23 04:27:59.682172: step: 972/526, loss: 0.0008888245210982859
2023-01-23 04:28:00.798215: step: 976/526, loss: 0.0009263515239581466
2023-01-23 04:28:01.959499: step: 980/526, loss: 0.01993555948138237
2023-01-23 04:28:03.100813: step: 984/526, loss: 0.0012018203269690275
2023-01-23 04:28:04.282781: step: 988/526, loss: 0.00438580522313714
2023-01-23 04:28:05.428506: step: 992/526, loss: 0.029940033331513405
2023-01-23 04:28:06.539031: step: 996/526, loss: 0.009188842959702015
2023-01-23 04:28:07.675422: step: 1000/526, loss: 0.221476748585701
2023-01-23 04:28:08.797074: step: 1004/526, loss: 0.00042743684025481343
2023-01-23 04:28:09.929551: step: 1008/526, loss: 0.0022742270957678556
2023-01-23 04:28:11.072031: step: 1012/526, loss: 0.07159347832202911
2023-01-23 04:28:12.211121: step: 1016/526, loss: 0.0038324357010424137
2023-01-23 04:28:13.346362: step: 1020/526, loss: 0.0001354217529296875
2023-01-23 04:28:14.478899: step: 1024/526, loss: 4.6396256948355585e-05
2023-01-23 04:28:15.637189: step: 1028/526, loss: 0.0808926522731781
2023-01-23 04:28:16.771516: step: 1032/526, loss: 0.00011205673217773438
2023-01-23 04:28:17.921035: step: 1036/526, loss: 0.0029749395325779915
2023-01-23 04:28:19.040614: step: 1040/526, loss: 0.0007938385242596269
2023-01-23 04:28:20.180695: step: 1044/526, loss: 0.0007907628896646202
2023-01-23 04:28:21.297752: step: 1048/526, loss: 0.011900520883500576
2023-01-23 04:28:22.460032: step: 1052/526, loss: 0.000537872314453125
2023-01-23 04:28:23.576759: step: 1056/526, loss: 0.0026862144004553556
2023-01-23 04:28:24.697527: step: 1060/526, loss: 7.019042823230848e-05
2023-01-23 04:28:25.836904: step: 1064/526, loss: 6.67572021484375e-06
2023-01-23 04:28:26.988534: step: 1068/526, loss: 0.0005766868707723916
2023-01-23 04:28:28.110881: step: 1072/526, loss: 0.0001841068296926096
2023-01-23 04:28:29.211720: step: 1076/526, loss: 7.43865966796875e-05
2023-01-23 04:28:30.335677: step: 1080/526, loss: 0.012058544903993607
2023-01-23 04:28:31.478051: step: 1084/526, loss: 0.0003757476806640625
2023-01-23 04:28:32.595823: step: 1088/526, loss: 4.444122168933973e-05
2023-01-23 04:28:33.755649: step: 1092/526, loss: 0.0003086090146098286
2023-01-23 04:28:34.913963: step: 1096/526, loss: 0.0008723258506506681
2023-01-23 04:28:36.046715: step: 1100/526, loss: -9.96589551505167e-06
2023-01-23 04:28:37.164738: step: 1104/526, loss: 0.001121616456657648
2023-01-23 04:28:38.312266: step: 1108/526, loss: 0.0035851479042321444
2023-01-23 04:28:39.439906: step: 1112/526, loss: 0.00014991759962867945
2023-01-23 04:28:40.589828: step: 1116/526, loss: 0.009939765557646751
2023-01-23 04:28:41.697739: step: 1120/526, loss: 1.220703143189894e-05
2023-01-23 04:28:42.851488: step: 1124/526, loss: 2.8800963264075108e-05
2023-01-23 04:28:43.978569: step: 1128/526, loss: 0.050063323229551315
2023-01-23 04:28:45.104670: step: 1132/526, loss: 0.06774502247571945
2023-01-23 04:28:46.233371: step: 1136/526, loss: 0.013505172915756702
2023-01-23 04:28:47.350757: step: 1140/526, loss: 0.000812149082776159
2023-01-23 04:28:48.499145: step: 1144/526, loss: 0.005931663792580366
2023-01-23 04:28:49.649536: step: 1148/526, loss: 0.0008241653558798134
2023-01-23 04:28:50.778937: step: 1152/526, loss: 8.94546537892893e-05
2023-01-23 04:28:51.930306: step: 1156/526, loss: 0.0008180618169717491
2023-01-23 04:28:53.054003: step: 1160/526, loss: 7.839203317416832e-05
2023-01-23 04:28:54.203311: step: 1164/526, loss: 0.01895885355770588
2023-01-23 04:28:55.352797: step: 1168/526, loss: 0.0021076202392578125
2023-01-23 04:28:56.520206: step: 1172/526, loss: 0.006271648686379194
2023-01-23 04:28:57.640788: step: 1176/526, loss: 0.0004314422549214214
2023-01-23 04:28:58.772670: step: 1180/526, loss: 5.273819260764867e-05
2023-01-23 04:28:59.903256: step: 1184/526, loss: 0.0005692005506716669
2023-01-23 04:29:01.062496: step: 1188/526, loss: 0.009467697702348232
2023-01-23 04:29:02.182466: step: 1192/526, loss: 0.019235610961914062
2023-01-23 04:29:03.323355: step: 1196/526, loss: 0.00020694732666015625
2023-01-23 04:29:04.451006: step: 1200/526, loss: 9.34600848268019e-06
2023-01-23 04:29:05.567063: step: 1204/526, loss: 1.487731969973538e-05
2023-01-23 04:29:06.702566: step: 1208/526, loss: 0.017633533105254173
2023-01-23 04:29:07.840201: step: 1212/526, loss: 6.256104097701609e-05
2023-01-23 04:29:08.946824: step: 1216/526, loss: 0.015104102902114391
2023-01-23 04:29:10.101037: step: 1220/526, loss: 0.017835520207881927
2023-01-23 04:29:11.247991: step: 1224/526, loss: 4.463195728021674e-05
2023-01-23 04:29:12.365608: step: 1228/526, loss: 0.0007609367021359503
2023-01-23 04:29:13.511800: step: 1232/526, loss: 0.00041375160799361765
2023-01-23 04:29:14.646448: step: 1236/526, loss: 0.00022687911405228078
2023-01-23 04:29:15.808033: step: 1240/526, loss: 0.00036234856816008687
2023-01-23 04:29:16.949741: step: 1244/526, loss: 0.00010929107520496473
2023-01-23 04:29:18.068716: step: 1248/526, loss: 0.013018418103456497
2023-01-23 04:29:19.211960: step: 1252/526, loss: 0.024806689471006393
2023-01-23 04:29:20.352502: step: 1256/526, loss: 2.1123885744600557e-05
2023-01-23 04:29:21.505131: step: 1260/526, loss: 7.901191565906629e-05
2023-01-23 04:29:22.611037: step: 1264/526, loss: 0.0036570073571056128
2023-01-23 04:29:23.728093: step: 1268/526, loss: 0.0015617371536791325
2023-01-23 04:29:24.868411: step: 1272/526, loss: 0.00046758653479628265
2023-01-23 04:29:26.037171: step: 1276/526, loss: 0.008194160647690296
2023-01-23 04:29:27.151587: step: 1280/526, loss: 0.016090966761112213
2023-01-23 04:29:28.268197: step: 1284/526, loss: 1.1444091796875e-05
2023-01-23 04:29:29.417071: step: 1288/526, loss: 0.03010845184326172
2023-01-23 04:29:30.587355: step: 1292/526, loss: 0.00021958351135253906
2023-01-23 04:29:31.707661: step: 1296/526, loss: 4.081726001459174e-05
2023-01-23 04:29:32.834931: step: 1300/526, loss: 0.09383416175842285
2023-01-23 04:29:33.968267: step: 1304/526, loss: 0.0034228325821459293
2023-01-23 04:29:35.069864: step: 1308/526, loss: 3.108978125965223e-05
2023-01-23 04:29:36.205730: step: 1312/526, loss: 0.0033784867264330387
2023-01-23 04:29:37.335184: step: 1316/526, loss: 0.033480264246463776
2023-01-23 04:29:38.449024: step: 1320/526, loss: 0.0035385130904614925
2023-01-23 04:29:39.584396: step: 1324/526, loss: 0.008394241333007812
2023-01-23 04:29:40.695597: step: 1328/526, loss: 0.001901817275211215
2023-01-23 04:29:41.869293: step: 1332/526, loss: 0.00017967224994208664
2023-01-23 04:29:43.003526: step: 1336/526, loss: 0.0004960060468874872
2023-01-23 04:29:44.141553: step: 1340/526, loss: 0.015882110223174095
2023-01-23 04:29:45.290668: step: 1344/526, loss: 0.00036573412944562733
2023-01-23 04:29:46.404130: step: 1348/526, loss: 0.0001012802094919607
2023-01-23 04:29:47.535886: step: 1352/526, loss: 0.013698958791792393
2023-01-23 04:29:48.643022: step: 1356/526, loss: 0.001324558281339705
2023-01-23 04:29:49.777609: step: 1360/526, loss: 0.00024776457576081157
2023-01-23 04:29:50.894555: step: 1364/526, loss: 2.670288040462765e-06
2023-01-23 04:29:52.011302: step: 1368/526, loss: 1.4400482541532256e-05
2023-01-23 04:29:53.123725: step: 1372/526, loss: 0.0011069298489019275
2023-01-23 04:29:54.244958: step: 1376/526, loss: 0.007462263107299805
2023-01-23 04:29:55.360596: step: 1380/526, loss: 0.05401735380291939
2023-01-23 04:29:56.469891: step: 1384/526, loss: 4.3582916987361386e-05
2023-01-23 04:29:57.587416: step: 1388/526, loss: 2.250671423098538e-05
2023-01-23 04:29:58.736816: step: 1392/526, loss: 0.01971612125635147
2023-01-23 04:29:59.863151: step: 1396/526, loss: 0.0009097099537029862
2023-01-23 04:30:00.991690: step: 1400/526, loss: 2.28881845032447e-06
2023-01-23 04:30:02.183186: step: 1404/526, loss: 0.013045978732407093
2023-01-23 04:30:03.289737: step: 1408/526, loss: 0.0027154923882335424
2023-01-23 04:30:04.455903: step: 1412/526, loss: 1.3351454981602728e-06
2023-01-23 04:30:05.578472: step: 1416/526, loss: 0.005413246341049671
2023-01-23 04:30:06.709772: step: 1420/526, loss: 0.005953311920166016
2023-01-23 04:30:07.837871: step: 1424/526, loss: 0.013836859725415707
2023-01-23 04:30:08.997745: step: 1428/526, loss: 0.031794264912605286
2023-01-23 04:30:10.151395: step: 1432/526, loss: 1.0967254638671875e-05
2023-01-23 04:30:11.269574: step: 1436/526, loss: 0.000247764604864642
2023-01-23 04:30:12.414635: step: 1440/526, loss: 0.00011882782564498484
2023-01-23 04:30:13.530458: step: 1444/526, loss: 5.5313107623078395e-06
2023-01-23 04:30:14.681111: step: 1448/526, loss: 0.00026893618633039296
2023-01-23 04:30:15.814347: step: 1452/526, loss: 0.0003461838059592992
2023-01-23 04:30:16.951381: step: 1456/526, loss: 0.0025379182770848274
2023-01-23 04:30:18.057609: step: 1460/526, loss: 2.5367738999193534e-05
2023-01-23 04:30:19.210632: step: 1464/526, loss: 0.05057534947991371
2023-01-23 04:30:20.399101: step: 1468/526, loss: 0.00010166168794967234
2023-01-23 04:30:21.530483: step: 1472/526, loss: 5.8841706049861386e-05
2023-01-23 04:30:22.677569: step: 1476/526, loss: 0.025016499683260918
2023-01-23 04:30:23.804393: step: 1480/526, loss: 0.007387256249785423
2023-01-23 04:30:24.937185: step: 1484/526, loss: 0.0024724958930164576
2023-01-23 04:30:26.096671: step: 1488/526, loss: 0.0008812129963189363
2023-01-23 04:30:27.216146: step: 1492/526, loss: 0.0045608519576489925
2023-01-23 04:30:28.348421: step: 1496/526, loss: 0.003621578449383378
2023-01-23 04:30:29.495328: step: 1500/526, loss: 5.578995114774443e-06
2023-01-23 04:30:30.633978: step: 1504/526, loss: 0.012771034613251686
2023-01-23 04:30:31.744062: step: 1508/526, loss: 0.00037803652230650187
2023-01-23 04:30:32.871025: step: 1512/526, loss: 7.882118370616809e-05
2023-01-23 04:30:33.998616: step: 1516/526, loss: 0.0038187026511877775
2023-01-23 04:30:35.126245: step: 1520/526, loss: 0.008404826745390892
2023-01-23 04:30:36.252129: step: 1524/526, loss: 0.00011577606346691027
2023-01-23 04:30:37.412704: step: 1528/526, loss: 2.059936559817288e-05
2023-01-23 04:30:38.535884: step: 1532/526, loss: 0.0029659748543053865
2023-01-23 04:30:39.661433: step: 1536/526, loss: 0.019263554364442825
2023-01-23 04:30:40.758826: step: 1540/526, loss: 9.536744727256519e-08
2023-01-23 04:30:41.885551: step: 1544/526, loss: 3.1948088690114673e-06
2023-01-23 04:30:43.019651: step: 1548/526, loss: 0.003868675325065851
2023-01-23 04:30:44.185684: step: 1552/526, loss: 1.773834264895413e-05
2023-01-23 04:30:45.316107: step: 1556/526, loss: 0.024718379601836205
2023-01-23 04:30:46.418462: step: 1560/526, loss: 0.023740006610751152
2023-01-23 04:30:47.545672: step: 1564/526, loss: 0.00016088486881926656
2023-01-23 04:30:48.684292: step: 1568/526, loss: 0.012238502502441406
2023-01-23 04:30:49.820052: step: 1572/526, loss: 0.006568718235939741
2023-01-23 04:30:50.958939: step: 1576/526, loss: 0.026308823376893997
2023-01-23 04:30:52.104073: step: 1580/526, loss: 0.0013119220966473222
2023-01-23 04:30:53.230523: step: 1584/526, loss: 0.005526161286979914
2023-01-23 04:30:54.393567: step: 1588/526, loss: 0.006288337986916304
2023-01-23 04:30:55.535226: step: 1592/526, loss: 0.004463767632842064
2023-01-23 04:30:56.667552: step: 1596/526, loss: 3.5953522456111386e-05
2023-01-23 04:30:57.794381: step: 1600/526, loss: 5.3977968491381034e-05
2023-01-23 04:30:58.964656: step: 1604/526, loss: 0.0005950927734375
2023-01-23 04:31:00.105339: step: 1608/526, loss: 0.0020165443420410156
2023-01-23 04:31:01.250280: step: 1612/526, loss: 0.0012900352012366056
2023-01-23 04:31:02.378966: step: 1616/526, loss: 0.00015859604172874242
2023-01-23 04:31:03.513795: step: 1620/526, loss: 0.0005213737604208291
2023-01-23 04:31:04.652856: step: 1624/526, loss: 0.0107460031285882
2023-01-23 04:31:05.806668: step: 1628/526, loss: 0.000501442002132535
2023-01-23 04:31:06.969429: step: 1632/526, loss: 0.00048006774159148335
2023-01-23 04:31:08.107889: step: 1636/526, loss: 0.00040540695772506297
2023-01-23 04:31:09.240675: step: 1640/526, loss: 0.0008028030279092491
2023-01-23 04:31:10.358088: step: 1644/526, loss: 1.1157990229548886e-05
2023-01-23 04:31:11.493991: step: 1648/526, loss: 0.0015939592849463224
2023-01-23 04:31:12.654009: step: 1652/526, loss: 0.00019164086552336812
2023-01-23 04:31:13.770000: step: 1656/526, loss: 0.005586910527199507
2023-01-23 04:31:14.897751: step: 1660/526, loss: 2.021789623540826e-05
2023-01-23 04:31:16.055282: step: 1664/526, loss: 0.00043125153752043843
2023-01-23 04:31:17.192071: step: 1668/526, loss: 0.03317022696137428
2023-01-23 04:31:18.292139: step: 1672/526, loss: 0.0001363277406198904
2023-01-23 04:31:19.412279: step: 1676/526, loss: 0.0033693313598632812
2023-01-23 04:31:20.605414: step: 1680/526, loss: 0.000546312308870256
2023-01-23 04:31:21.729873: step: 1684/526, loss: 0.00048313141451217234
2023-01-23 04:31:22.868758: step: 1688/526, loss: 4.95910626341356e-06
2023-01-23 04:31:23.983990: step: 1692/526, loss: 0.0011812209850177169
2023-01-23 04:31:25.127279: step: 1696/526, loss: 2.6035309929284267e-05
2023-01-23 04:31:26.237061: step: 1700/526, loss: 3.604888843256049e-05
2023-01-23 04:31:27.380758: step: 1704/526, loss: 0.007018089760094881
2023-01-23 04:31:28.540101: step: 1708/526, loss: 0.0001440525084035471
2023-01-23 04:31:29.686333: step: 1712/526, loss: 0.003296089358627796
2023-01-23 04:31:30.819549: step: 1716/526, loss: 7.534026735811494e-06
2023-01-23 04:31:31.940032: step: 1720/526, loss: 1.6498564946232364e-05
2023-01-23 04:31:33.073054: step: 1724/526, loss: 0.0001220703125
2023-01-23 04:31:34.212179: step: 1728/526, loss: 4.634857032215223e-05
2023-01-23 04:31:35.355554: step: 1732/526, loss: 2.1934511096333154e-06
2023-01-23 04:31:36.490457: step: 1736/526, loss: 0.0006587982061319053
2023-01-23 04:31:37.608009: step: 1740/526, loss: 0.0007326126797124743
2023-01-23 04:31:38.750637: step: 1744/526, loss: 0.002924632979556918
2023-01-23 04:31:39.877091: step: 1748/526, loss: 1.2779236385540571e-05
2023-01-23 04:31:40.997650: step: 1752/526, loss: 1.0013580322265625e-05
2023-01-23 04:31:42.117853: step: 1756/526, loss: 4.4441225327318534e-05
2023-01-23 04:31:43.266578: step: 1760/526, loss: 0.0006335258949548006
2023-01-23 04:31:44.417852: step: 1764/526, loss: 2.079009937006049e-05
2023-01-23 04:31:45.548349: step: 1768/526, loss: 0.020188046619296074
2023-01-23 04:31:46.689351: step: 1772/526, loss: 6.923675391590223e-05
2023-01-23 04:31:47.802050: step: 1776/526, loss: 0.03169002756476402
2023-01-23 04:31:48.923152: step: 1780/526, loss: 3.280639793956652e-05
2023-01-23 04:31:50.045372: step: 1784/526, loss: 2.956390289909905e-06
2023-01-23 04:31:51.184318: step: 1788/526, loss: 0.0002522468566894531
2023-01-23 04:31:52.379646: step: 1792/526, loss: 0.00489730853587389
2023-01-23 04:31:53.566633: step: 1796/526, loss: 0.00023021697415970266
2023-01-23 04:31:54.697024: step: 1800/526, loss: 0.030421828851103783
2023-01-23 04:31:55.834274: step: 1804/526, loss: 0.00046758653479628265
2023-01-23 04:31:56.993941: step: 1808/526, loss: 1.3732910701946821e-05
2023-01-23 04:31:58.137624: step: 1812/526, loss: 0.15819358825683594
2023-01-23 04:31:59.306809: step: 1816/526, loss: 0.0006811618804931641
2023-01-23 04:32:00.433918: step: 1820/526, loss: 0.012120437808334827
2023-01-23 04:32:01.544912: step: 1824/526, loss: 0.0009313583723269403
2023-01-23 04:32:02.704874: step: 1828/526, loss: 0.0070618633180856705
2023-01-23 04:32:03.871988: step: 1832/526, loss: 0.00038537976797670126
2023-01-23 04:32:05.028263: step: 1836/526, loss: 0.0002094268857035786
2023-01-23 04:32:06.142684: step: 1840/526, loss: 0.015607452020049095
2023-01-23 04:32:07.285117: step: 1844/526, loss: 5.855560448253527e-05
2023-01-23 04:32:08.425318: step: 1848/526, loss: 2.8514863515738398e-05
2023-01-23 04:32:09.554636: step: 1852/526, loss: 0.06976642459630966
2023-01-23 04:32:10.675668: step: 1856/526, loss: 0.01127328909933567
2023-01-23 04:32:11.793341: step: 1860/526, loss: 7.43865984986769e-06
2023-01-23 04:32:12.971095: step: 1864/526, loss: 0.00010213851783191785
2023-01-23 04:32:14.117264: step: 1868/526, loss: 0.0011112213833257556
2023-01-23 04:32:15.253837: step: 1872/526, loss: 7.62939453125e-06
2023-01-23 04:32:16.381288: step: 1876/526, loss: -1.6689299400240998e-06
2023-01-23 04:32:17.511676: step: 1880/526, loss: 0.005048847291618586
2023-01-23 04:32:18.639797: step: 1884/526, loss: 0.0048728943802416325
2023-01-23 04:32:19.786482: step: 1888/526, loss: 0.01232070941478014
2023-01-23 04:32:20.955136: step: 1892/526, loss: 0.0005630493396893144
2023-01-23 04:32:22.088994: step: 1896/526, loss: 0.0005395889165811241
2023-01-23 04:32:23.266140: step: 1900/526, loss: 0.01865386962890625
2023-01-23 04:32:24.389806: step: 1904/526, loss: 0.006522941868752241
2023-01-23 04:32:25.533250: step: 1908/526, loss: 8.726119631319307e-06
2023-01-23 04:32:26.662707: step: 1912/526, loss: 6.27517729299143e-05
2023-01-23 04:32:27.834906: step: 1916/526, loss: 8.583069575252011e-05
2023-01-23 04:32:28.986690: step: 1920/526, loss: 1.9550323486328125e-05
2023-01-23 04:32:30.113515: step: 1924/526, loss: 0.0019906999077647924
2023-01-23 04:32:31.233858: step: 1928/526, loss: 0.0004419327015057206
2023-01-23 04:32:32.374004: step: 1932/526, loss: 0.11033286899328232
2023-01-23 04:32:33.489605: step: 1936/526, loss: 0.0006152152782306075
2023-01-23 04:32:34.610436: step: 1940/526, loss: 0.013238906860351562
2023-01-23 04:32:35.764692: step: 1944/526, loss: 0.022258948534727097
2023-01-23 04:32:36.903783: step: 1948/526, loss: 0.0025447846855968237
2023-01-23 04:32:38.055702: step: 1952/526, loss: 0.00025153160095214844
2023-01-23 04:32:39.211968: step: 1956/526, loss: 9.765625145519152e-05
2023-01-23 04:32:40.355409: step: 1960/526, loss: 0.02020130306482315
2023-01-23 04:32:41.485214: step: 1964/526, loss: 0.010028076358139515
2023-01-23 04:32:42.588816: step: 1968/526, loss: 0.016941452398896217
2023-01-23 04:32:43.695724: step: 1972/526, loss: 0.011068678461015224
2023-01-23 04:32:44.823491: step: 1976/526, loss: 0.00063071254407987
2023-01-23 04:32:45.983203: step: 1980/526, loss: 0.0012928008800372481
2023-01-23 04:32:47.103686: step: 1984/526, loss: 1.3637542906508315e-05
2023-01-23 04:32:48.235974: step: 1988/526, loss: 0.000211620339541696
2023-01-23 04:32:49.365406: step: 1992/526, loss: 0.00566787738353014
2023-01-23 04:32:50.507733: step: 1996/526, loss: 0.0005762100336141884
2023-01-23 04:32:51.662437: step: 2000/526, loss: 0.034627534449100494
2023-01-23 04:32:52.810654: step: 2004/526, loss: 0.007682514376938343
2023-01-23 04:32:53.924724: step: 2008/526, loss: 0.009882116690278053
2023-01-23 04:32:55.057371: step: 2012/526, loss: 9.441375368623994e-06
2023-01-23 04:32:56.174536: step: 2016/526, loss: 0.008030558004975319
2023-01-23 04:32:57.298166: step: 2020/526, loss: 0.0023218155838549137
2023-01-23 04:32:58.408305: step: 2024/526, loss: 0.0001678466796875
2023-01-23 04:32:59.556961: step: 2028/526, loss: 0.0009698867797851562
2023-01-23 04:33:00.688392: step: 2032/526, loss: 4.8065183364087716e-05
2023-01-23 04:33:01.813568: step: 2036/526, loss: 2.6416779292048886e-05
2023-01-23 04:33:02.941263: step: 2040/526, loss: 0.0009784698486328125
2023-01-23 04:33:04.105447: step: 2044/526, loss: 8.177757263183594e-05
2023-01-23 04:33:05.259393: step: 2048/526, loss: 0.002227401826530695
2023-01-23 04:33:06.374162: step: 2052/526, loss: 0.04100246727466583
2023-01-23 04:33:07.545974: step: 2056/526, loss: 0.011110449209809303
2023-01-23 04:33:08.725266: step: 2060/526, loss: 0.010821151547133923
2023-01-23 04:33:09.853431: step: 2064/526, loss: 0.0009624481317587197
2023-01-23 04:33:10.999148: step: 2068/526, loss: 0.0005439758533611894
2023-01-23 04:33:12.113499: step: 2072/526, loss: 1.029968279908644e-05
2023-01-23 04:33:13.259287: step: 2076/526, loss: 5.2642819355241954e-05
2023-01-23 04:33:14.417172: step: 2080/526, loss: 5.245209194981726e-06
2023-01-23 04:33:15.521592: step: 2084/526, loss: 1.6880036127986386e-05
2023-01-23 04:33:16.666501: step: 2088/526, loss: 0.00025663376436568797
2023-01-23 04:33:17.798713: step: 2092/526, loss: 0.0034324645530432463
2023-01-23 04:33:18.908712: step: 2096/526, loss: 1.163482647825731e-05
2023-01-23 04:33:20.064189: step: 2100/526, loss: 7.343292236328125e-05
2023-01-23 04:33:21.251194: step: 2104/526, loss: -4.95910626341356e-06
==================================================
Loss: 0.010
--------------------
Dev: {'event': {'p': 0.615795090715048, 'r': 0.7683089214380826, 'f1': 0.683649289099526}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 28}
Test: {'event': {'p': 0.6265366680796948, 'r': 0.7713987473903967, 'f1': 0.6914619883040936}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 28}
Chinese: {'event': {'p': 0.6282051282051282, 'r': 0.9074074074074074, 'f1': 0.7424242424242423}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 28}
Korean: {'event': {'p': 0.6666666666666666, 'r': 0.4444444444444444, 'f1': 0.5333333333333333}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 28}
Russian: {'event': {'p': 0.4772727272727273, 'r': 0.5833333333333334, 'f1': 0.5250000000000001}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 28}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6266519823788547, 'r': 0.7576564580559254, 'f1': 0.6859553948161543}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Eng Test for Chinese: {'event': {'p': 0.6313522825150732, 'r': 0.7651356993736952, 'f1': 0.6918357715903728}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Sample Chinese: {'event': {'p': 0.6621621621621622, 'r': 0.9074074074074074, 'f1': 0.765625}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6257995735607675, 'r': 0.7816245006657789, 'f1': 0.6950858496151568}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Eng Test for Korean: {'event': {'p': 0.623113410952997, 'r': 0.7541753653444676, 'f1': 0.6824085005903188}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Sample Korean: {'event': {'p': 0.7446808510638298, 'r': 0.5555555555555556, 'f1': 0.6363636363636364}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6266519823788547, 'r': 0.7576564580559254, 'f1': 0.6859553948161543}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Eng Test for Russian: {'event': {'p': 0.6313522825150732, 'r': 0.7651356993736952, 'f1': 0.6918357715903728}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Sample Russian: {'event': {'p': 0.5384615384615384, 'r': 0.5833333333333334, 'f1': 0.5599999999999999}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
******************************
Epoch: 29
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 04:34:04.421500: step: 4/526, loss: 1.811981201171875e-05
2023-01-23 04:34:05.553092: step: 8/526, loss: 0.0001941680966410786
2023-01-23 04:34:06.679185: step: 12/526, loss: 0.0012712478637695312
2023-01-23 04:34:07.788830: step: 16/526, loss: 0.0019008637173101306
2023-01-23 04:34:08.940697: step: 20/526, loss: 0.0001235961972270161
2023-01-23 04:34:10.084599: step: 24/526, loss: 0.002497005509212613
2023-01-23 04:34:11.188877: step: 28/526, loss: 0.0007276535616256297
2023-01-23 04:34:12.313398: step: 32/526, loss: -1.9073486328125e-06
2023-01-23 04:34:13.436892: step: 36/526, loss: 0.0001348495570709929
2023-01-23 04:34:14.567163: step: 40/526, loss: 0.00010986328561557457
2023-01-23 04:34:15.708600: step: 44/526, loss: 0.0010242462158203125
2023-01-23 04:34:16.817362: step: 48/526, loss: 0.00030574799166060984
2023-01-23 04:34:17.950971: step: 52/526, loss: 8.869171142578125e-05
2023-01-23 04:34:19.075881: step: 56/526, loss: 0.0015371321933344007
2023-01-23 04:34:20.216314: step: 60/526, loss: 0.00020799637422896922
2023-01-23 04:34:21.345703: step: 64/526, loss: 3.6239625842426904e-06
2023-01-23 04:34:22.450719: step: 68/526, loss: 1.2397766795402276e-06
2023-01-23 04:34:23.571486: step: 72/526, loss: 0.27656590938568115
2023-01-23 04:34:24.708976: step: 76/526, loss: 0.0013900757767260075
2023-01-23 04:34:25.841314: step: 80/526, loss: 0.002552032470703125
2023-01-23 04:34:26.921206: step: 84/526, loss: 0.0160719882696867
2023-01-23 04:34:28.035825: step: 88/526, loss: 0.00021638871112372726
2023-01-23 04:34:29.162298: step: 92/526, loss: 0.0005153656238690019
2023-01-23 04:34:30.317218: step: 96/526, loss: 9.469986252952367e-05
2023-01-23 04:34:31.477945: step: 100/526, loss: 3.814697265625e-06
2023-01-23 04:34:32.629219: step: 104/526, loss: 0.004469108767807484
2023-01-23 04:34:33.762916: step: 108/526, loss: 0.019799232482910156
2023-01-23 04:34:34.892736: step: 112/526, loss: 7.896423630882055e-05
2023-01-23 04:34:36.044642: step: 116/526, loss: 0.0029705048073083162
2023-01-23 04:34:37.163229: step: 120/526, loss: 0.005303001496940851
2023-01-23 04:34:38.327962: step: 124/526, loss: 0.055001452565193176
2023-01-23 04:34:39.464681: step: 128/526, loss: 0.0005161285516805947
2023-01-23 04:34:40.571015: step: 132/526, loss: 0.012682723812758923
2023-01-23 04:34:41.685211: step: 136/526, loss: 0.0180924404412508
2023-01-23 04:34:42.787756: step: 140/526, loss: 0.01165628433227539
2023-01-23 04:34:43.913460: step: 144/526, loss: 0.021371990442276
2023-01-23 04:34:45.040138: step: 148/526, loss: 0.00039253238355740905
2023-01-23 04:34:46.173940: step: 152/526, loss: 0.0012218474876135588
2023-01-23 04:34:47.293403: step: 156/526, loss: 0.007853222079575062
2023-01-23 04:34:48.473979: step: 160/526, loss: 0.0006039619911462069
2023-01-23 04:34:49.616446: step: 164/526, loss: 0.0007616042857989669
2023-01-23 04:34:50.725659: step: 168/526, loss: 0.006319236941635609
2023-01-23 04:34:51.862761: step: 172/526, loss: 0.00021772386389784515
2023-01-23 04:34:53.003045: step: 176/526, loss: 0.008054065518081188
2023-01-23 04:34:54.131349: step: 180/526, loss: 0.017675232142210007
2023-01-23 04:34:55.233113: step: 184/526, loss: 6.828307959949598e-05
2023-01-23 04:34:56.375020: step: 188/526, loss: 2.1791458493680693e-05
2023-01-23 04:34:57.489340: step: 192/526, loss: 0.0004935264587402344
2023-01-23 04:34:58.625444: step: 196/526, loss: -3.14712519866589e-06
2023-01-23 04:34:59.756920: step: 200/526, loss: 0.001275444170460105
2023-01-23 04:35:00.873240: step: 204/526, loss: 3.957748504035408e-06
2023-01-23 04:35:02.018385: step: 208/526, loss: 0.00024900436983443797
2023-01-23 04:35:03.165960: step: 212/526, loss: 0.005500125698745251
2023-01-23 04:35:04.297192: step: 216/526, loss: 0.011472702026367188
2023-01-23 04:35:05.413332: step: 220/526, loss: 0.00034508705721236765
2023-01-23 04:35:06.555818: step: 224/526, loss: 0.008842945098876953
2023-01-23 04:35:07.663161: step: 228/526, loss: 0.0005613326793536544
2023-01-23 04:35:08.768019: step: 232/526, loss: 0.002803516574203968
2023-01-23 04:35:09.898888: step: 236/526, loss: 0.0018253326416015625
2023-01-23 04:35:11.050533: step: 240/526, loss: 0.04392433166503906
2023-01-23 04:35:12.192227: step: 244/526, loss: 7.62939453125e-06
2023-01-23 04:35:13.327927: step: 248/526, loss: 1.0919571650447324e-05
2023-01-23 04:35:14.452747: step: 252/526, loss: 0.006730079650878906
2023-01-23 04:35:15.608850: step: 256/526, loss: 7.247925168485381e-06
2023-01-23 04:35:16.742237: step: 260/526, loss: 0.022701837122440338
2023-01-23 04:35:17.878041: step: 264/526, loss: 0.013193607330322266
2023-01-23 04:35:19.008773: step: 268/526, loss: 0.0010380744934082031
2023-01-23 04:35:20.144773: step: 272/526, loss: 0.00043334963265806437
2023-01-23 04:35:21.292107: step: 276/526, loss: 0.251460462808609
2023-01-23 04:35:22.414740: step: 280/526, loss: 0.03471508249640465
2023-01-23 04:35:23.543496: step: 284/526, loss: 0.00291862478479743
2023-01-23 04:35:24.659095: step: 288/526, loss: 2.965927342302166e-05
2023-01-23 04:35:25.791763: step: 292/526, loss: 0.0027446746826171875
2023-01-23 04:35:26.888394: step: 296/526, loss: -2.288818359375e-05
2023-01-23 04:35:28.028814: step: 300/526, loss: 0.0005229950184002519
2023-01-23 04:35:29.163522: step: 304/526, loss: 0.0008993148803710938
2023-01-23 04:35:30.301698: step: 308/526, loss: 0.37060850858688354
2023-01-23 04:35:31.447824: step: 312/526, loss: 0.008023500442504883
2023-01-23 04:35:32.557382: step: 316/526, loss: 0.001656055566854775
2023-01-23 04:35:33.701662: step: 320/526, loss: 5.2261355449445546e-05
2023-01-23 04:35:34.820366: step: 324/526, loss: 3.662109520519152e-05
2023-01-23 04:35:35.992435: step: 328/526, loss: 0.0005950451013632119
2023-01-23 04:35:37.127980: step: 332/526, loss: 0.5303598046302795
2023-01-23 04:35:38.268815: step: 336/526, loss: 7.61985793360509e-05
2023-01-23 04:35:39.379910: step: 340/526, loss: 0.012025165371596813
2023-01-23 04:35:40.493700: step: 344/526, loss: 0.00014505386934615672
2023-01-23 04:35:41.619009: step: 348/526, loss: 8.254051499534398e-05
2023-01-23 04:35:42.757682: step: 352/526, loss: 0.0009945393539965153
2023-01-23 04:35:43.891776: step: 356/526, loss: 2.8133392788731726e-06
2023-01-23 04:35:45.049152: step: 360/526, loss: 0.0002055168297374621
2023-01-23 04:35:46.184663: step: 364/526, loss: 1.26004224512144e-05
2023-01-23 04:35:47.311075: step: 368/526, loss: 0.0018686294788494706
2023-01-23 04:35:48.444211: step: 372/526, loss: 0.01757078245282173
2023-01-23 04:35:49.605165: step: 376/526, loss: 0.002975654788315296
2023-01-23 04:35:50.776760: step: 380/526, loss: 0.0005886078579351306
2023-01-23 04:35:51.921343: step: 384/526, loss: 4.234314110362902e-05
2023-01-23 04:35:53.068457: step: 388/526, loss: 0.00012245179095771164
2023-01-23 04:35:54.217030: step: 392/526, loss: 0.0032838822808116674
2023-01-23 04:35:55.350724: step: 396/526, loss: 0.0001922607480082661
2023-01-23 04:35:56.476591: step: 400/526, loss: 0.0005361557123251259
2023-01-23 04:35:57.604440: step: 404/526, loss: 4.4441225327318534e-05
2023-01-23 04:35:58.741543: step: 408/526, loss: 0.00023374558077193797
2023-01-23 04:35:59.853618: step: 412/526, loss: 0.0006167411920614541
2023-01-23 04:36:00.977685: step: 416/526, loss: 1.7881393432617188e-05
2023-01-23 04:36:02.096430: step: 420/526, loss: 2.2737367544323206e-13
2023-01-23 04:36:03.215407: step: 424/526, loss: 1.049041748046875e-05
2023-01-23 04:36:04.377924: step: 428/526, loss: -4.0054324017546605e-06
2023-01-23 04:36:05.511962: step: 432/526, loss: 0.0031707764137536287
2023-01-23 04:36:06.648103: step: 436/526, loss: 3.0136106943245977e-05
2023-01-23 04:36:07.807677: step: 440/526, loss: 8.630752745375503e-06
2023-01-23 04:36:08.952572: step: 444/526, loss: 0.00275421142578125
2023-01-23 04:36:10.121539: step: 448/526, loss: 0.031766414642333984
2023-01-23 04:36:11.239231: step: 452/526, loss: 6.065368506824598e-05
2023-01-23 04:36:12.387438: step: 456/526, loss: 2.2697449821862392e-05
2023-01-23 04:36:13.545094: step: 460/526, loss: 0.001425933907739818
2023-01-23 04:36:14.653977: step: 464/526, loss: 0.0022575377952307463
2023-01-23 04:36:15.836803: step: 468/526, loss: 6.4849853515625e-05
2023-01-23 04:36:16.972715: step: 472/526, loss: 0.0005176544073037803
2023-01-23 04:36:18.088767: step: 476/526, loss: 0.014089202508330345
2023-01-23 04:36:19.246239: step: 480/526, loss: 0.000640869140625
2023-01-23 04:36:20.417782: step: 484/526, loss: 0.00016174315533135086
2023-01-23 04:36:21.594929: step: 488/526, loss: 2.1648407710017636e-05
2023-01-23 04:36:22.731617: step: 492/526, loss: 3.0326844353112392e-05
2023-01-23 04:36:23.889988: step: 496/526, loss: 7.82012921263231e-06
2023-01-23 04:36:25.002494: step: 500/526, loss: 0.00164794921875
2023-01-23 04:36:26.135505: step: 504/526, loss: 4.138946678722277e-05
2023-01-23 04:36:27.242343: step: 508/526, loss: 0.003694486804306507
2023-01-23 04:36:28.361272: step: 512/526, loss: 0.03291931003332138
2023-01-23 04:36:29.510119: step: 516/526, loss: 3.089904930675402e-05
2023-01-23 04:36:30.657598: step: 520/526, loss: 0.00025177001953125
2023-01-23 04:36:31.790943: step: 524/526, loss: 0.0006361007690429688
2023-01-23 04:36:32.919039: step: 528/526, loss: 0.00387153634801507
2023-01-23 04:36:34.084977: step: 532/526, loss: 4.596710277837701e-05
2023-01-23 04:36:35.221133: step: 536/526, loss: 0.00012731552124023438
2023-01-23 04:36:36.321390: step: 540/526, loss: 0.005178546998649836
2023-01-23 04:36:37.461514: step: 544/526, loss: 4.730224463855848e-05
2023-01-23 04:36:38.581620: step: 548/526, loss: 0.04731016233563423
2023-01-23 04:36:39.712426: step: 552/526, loss: 6.12258882028982e-05
2023-01-23 04:36:40.825806: step: 556/526, loss: 8.821487426757812e-05
2023-01-23 04:36:41.989730: step: 560/526, loss: 0.008287430740892887
2023-01-23 04:36:43.166109: step: 564/526, loss: 6.580352874152595e-06
2023-01-23 04:36:44.281939: step: 568/526, loss: -6.008148375258315e-06
2023-01-23 04:36:45.412717: step: 572/526, loss: 0.0027103424072265625
2023-01-23 04:36:46.525249: step: 576/526, loss: 0.0021161078475415707
2023-01-23 04:36:47.670778: step: 580/526, loss: 0.009405947290360928
2023-01-23 04:36:48.820710: step: 584/526, loss: 0.0003705501731019467
2023-01-23 04:36:49.953090: step: 588/526, loss: 0.327279657125473
2023-01-23 04:36:51.062555: step: 592/526, loss: 0.001109218574129045
2023-01-23 04:36:52.229211: step: 596/526, loss: 0.01038427371531725
2023-01-23 04:36:53.375122: step: 600/526, loss: 0.0002617835998535156
2023-01-23 04:36:54.538849: step: 604/526, loss: 0.021316051483154297
2023-01-23 04:36:55.689966: step: 608/526, loss: 1.6117097402457148e-05
2023-01-23 04:36:56.791085: step: 612/526, loss: 1.1157990229548886e-05
2023-01-23 04:36:57.931282: step: 616/526, loss: 0.0001625060976948589
2023-01-23 04:36:59.077073: step: 620/526, loss: 0.004167747683823109
2023-01-23 04:37:00.204866: step: 624/526, loss: 5.6934357417048886e-05
2023-01-23 04:37:01.350964: step: 628/526, loss: 0.003048515412956476
2023-01-23 04:37:02.485568: step: 632/526, loss: 6.4849853515625e-05
2023-01-23 04:37:03.637029: step: 636/526, loss: 4.37736525782384e-05
2023-01-23 04:37:04.795865: step: 640/526, loss: 3.910064606316155e-06
2023-01-23 04:37:05.957874: step: 644/526, loss: 0.0007059097406454384
2023-01-23 04:37:07.093559: step: 648/526, loss: 1.4209747860149946e-05
2023-01-23 04:37:08.230194: step: 652/526, loss: 2.0790101189049892e-05
2023-01-23 04:37:09.376856: step: 656/526, loss: -1.029968279908644e-05
2023-01-23 04:37:10.499431: step: 660/526, loss: 6.222724914550781e-05
2023-01-23 04:37:11.651252: step: 664/526, loss: 0.0003966331423725933
2023-01-23 04:37:12.771450: step: 668/526, loss: 0.0001813888520700857
2023-01-23 04:37:13.900381: step: 672/526, loss: 0.013968468643724918
2023-01-23 04:37:15.015930: step: 676/526, loss: 7.05719003235572e-06
2023-01-23 04:37:16.139737: step: 680/526, loss: 0.08435797691345215
2023-01-23 04:37:17.337590: step: 684/526, loss: 0.009826088324189186
2023-01-23 04:37:18.477922: step: 688/526, loss: 0.0001464843808207661
2023-01-23 04:37:19.634086: step: 692/526, loss: 0.003316784044727683
2023-01-23 04:37:20.777031: step: 696/526, loss: 0.0219466220587492
2023-01-23 04:37:21.911287: step: 700/526, loss: 0.0021963119506835938
2023-01-23 04:37:23.040631: step: 704/526, loss: 0.0028383254539221525
2023-01-23 04:37:24.246038: step: 708/526, loss: 0.00020546912855934352
2023-01-23 04:37:25.376539: step: 712/526, loss: 1.182556115963962e-05
2023-01-23 04:37:26.498192: step: 716/526, loss: 1.7261505490751006e-05
2023-01-23 04:37:27.648534: step: 720/526, loss: 0.0004368782101664692
2023-01-23 04:37:28.788363: step: 724/526, loss: 2.098083541568485e-06
2023-01-23 04:37:29.909779: step: 728/526, loss: 2.5749208361958154e-05
2023-01-23 04:37:31.035353: step: 732/526, loss: 0.0009614944574423134
2023-01-23 04:37:32.161287: step: 736/526, loss: 7.309913780773059e-05
2023-01-23 04:37:33.261739: step: 740/526, loss: 0.09430694580078125
2023-01-23 04:37:34.364575: step: 744/526, loss: 1.5258788153005298e-06
2023-01-23 04:37:35.496642: step: 748/526, loss: 4.0626528061693534e-05
2023-01-23 04:37:36.637507: step: 752/526, loss: 3.4141543437726796e-05
2023-01-23 04:37:37.802750: step: 756/526, loss: 0.0001087188720703125
2023-01-23 04:37:38.955766: step: 760/526, loss: 0.006926632020622492
2023-01-23 04:37:40.079781: step: 764/526, loss: 1.2874604180979077e-05
2023-01-23 04:37:41.229229: step: 768/526, loss: 4.9400332500226796e-05
2023-01-23 04:37:42.328417: step: 772/526, loss: 1.0538101378188003e-05
2023-01-23 04:37:43.447626: step: 776/526, loss: 0.005696487613022327
2023-01-23 04:37:44.563998: step: 780/526, loss: 0.00010628700692905113
2023-01-23 04:37:45.707532: step: 784/526, loss: -1.773834264895413e-05
2023-01-23 04:37:46.844472: step: 788/526, loss: 1.201629675051663e-05
2023-01-23 04:37:47.963802: step: 792/526, loss: 0.00011272430856479332
2023-01-23 04:37:49.100330: step: 796/526, loss: 1.201629675051663e-05
2023-01-23 04:37:50.215721: step: 800/526, loss: 0.0012041092850267887
2023-01-23 04:37:51.355853: step: 804/526, loss: 0.00011693238775478676
2023-01-23 04:37:52.493407: step: 808/526, loss: 1.831054760259576e-05
2023-01-23 04:37:53.637779: step: 812/526, loss: 3.547668529790826e-05
2023-01-23 04:37:54.759335: step: 816/526, loss: 0.47016143798828125
2023-01-23 04:37:55.885483: step: 820/526, loss: 2.1934511096333154e-06
2023-01-23 04:37:57.013625: step: 824/526, loss: 0.0002132415829692036
2023-01-23 04:37:58.156200: step: 828/526, loss: 0.010844612494111061
2023-01-23 04:37:59.259063: step: 832/526, loss: -3.433226083870977e-06
2023-01-23 04:38:00.388299: step: 836/526, loss: 0.00046825408935546875
2023-01-23 04:38:01.507555: step: 840/526, loss: 0.024965476244688034
2023-01-23 04:38:02.646732: step: 844/526, loss: 0.004096412565559149
2023-01-23 04:38:03.784367: step: 848/526, loss: 0.001560211181640625
2023-01-23 04:38:04.929783: step: 852/526, loss: -9.489059266343247e-06
2023-01-23 04:38:06.069774: step: 856/526, loss: 0.04185066372156143
2023-01-23 04:38:07.229496: step: 860/526, loss: 5.14984139954322e-06
2023-01-23 04:38:08.373199: step: 864/526, loss: 2.288818359375e-05
2023-01-23 04:38:09.564160: step: 868/526, loss: 3.8528440200025216e-05
2023-01-23 04:38:10.697247: step: 872/526, loss: 0.02396259270608425
2023-01-23 04:38:11.822326: step: 876/526, loss: 0.011084240861237049
2023-01-23 04:38:12.941922: step: 880/526, loss: 0.011517142876982689
2023-01-23 04:38:14.059328: step: 884/526, loss: 0.0014192580711096525
2023-01-23 04:38:15.197763: step: 888/526, loss: 0.0008420944795943797
2023-01-23 04:38:16.372967: step: 892/526, loss: 0.01850261725485325
2023-01-23 04:38:17.481558: step: 896/526, loss: 0.000964736973401159
2023-01-23 04:38:18.636529: step: 900/526, loss: 0.004015636630356312
2023-01-23 04:38:19.794683: step: 904/526, loss: 0.0005403519026003778
2023-01-23 04:38:20.919074: step: 908/526, loss: 0.0002155303955078125
2023-01-23 04:38:22.055525: step: 912/526, loss: 0.0023027420975267887
2023-01-23 04:38:23.216644: step: 916/526, loss: 0.011924362741410732
2023-01-23 04:38:24.367905: step: 920/526, loss: 4.625320798368193e-06
2023-01-23 04:38:25.488876: step: 924/526, loss: 0.021325349807739258
2023-01-23 04:38:26.628620: step: 928/526, loss: 0.10978536307811737
2023-01-23 04:38:27.775419: step: 932/526, loss: 0.0001068115234375
2023-01-23 04:38:28.895636: step: 936/526, loss: 0.0017185688484460115
2023-01-23 04:38:30.009112: step: 940/526, loss: 7.43865984986769e-06
2023-01-23 04:38:31.157309: step: 944/526, loss: 0.0019600866362452507
2023-01-23 04:38:32.286159: step: 948/526, loss: 2.918243444582913e-05
2023-01-23 04:38:33.432891: step: 952/526, loss: 9.922981553245336e-05
2023-01-23 04:38:34.593069: step: 956/526, loss: 1.506805438111769e-05
2023-01-23 04:38:35.717920: step: 960/526, loss: 5.817413693876006e-06
2023-01-23 04:38:36.830592: step: 964/526, loss: 2.307891918462701e-05
2023-01-23 04:38:37.962086: step: 968/526, loss: 0.01246728841215372
2023-01-23 04:38:39.091837: step: 972/526, loss: 0.0005553245428018272
2023-01-23 04:38:40.225216: step: 976/526, loss: 0.0017802715301513672
2023-01-23 04:38:41.359819: step: 980/526, loss: 1.487731969973538e-05
2023-01-23 04:38:42.496819: step: 984/526, loss: 0.001964569091796875
2023-01-23 04:38:43.663907: step: 988/526, loss: -5.9127810345671605e-06
2023-01-23 04:38:44.786261: step: 992/526, loss: 0.023551084101200104
2023-01-23 04:38:45.899210: step: 996/526, loss: 0.00039691926212981343
2023-01-23 04:38:47.044042: step: 1000/526, loss: 0.0010014533763751388
2023-01-23 04:38:48.189956: step: 1004/526, loss: 0.00030012131901457906
2023-01-23 04:38:49.320821: step: 1008/526, loss: 0.04886522516608238
2023-01-23 04:38:50.448395: step: 1012/526, loss: 0.004866885952651501
2023-01-23 04:38:51.585249: step: 1016/526, loss: 0.013799190521240234
2023-01-23 04:38:52.709627: step: 1020/526, loss: 0.0004741668817587197
2023-01-23 04:38:53.816181: step: 1024/526, loss: 5.817413693876006e-06
2023-01-23 04:38:54.941891: step: 1028/526, loss: 9.822845640883315e-06
2023-01-23 04:38:56.070042: step: 1032/526, loss: 0.0004566192510537803
2023-01-23 04:38:57.184345: step: 1036/526, loss: 3.385544005141128e-06
2023-01-23 04:38:58.311518: step: 1040/526, loss: 0.00024147034855559468
2023-01-23 04:38:59.458179: step: 1044/526, loss: 0.0007737159612588584
2023-01-23 04:39:00.581528: step: 1048/526, loss: 0.006083107087761164
2023-01-23 04:39:01.720863: step: 1052/526, loss: 0.016718007624149323
2023-01-23 04:39:02.851376: step: 1056/526, loss: 0.023111343383789062
2023-01-23 04:39:03.995244: step: 1060/526, loss: 3.2043459214037284e-05
2023-01-23 04:39:05.102256: step: 1064/526, loss: 4.00543194700731e-06
2023-01-23 04:39:06.231584: step: 1068/526, loss: 0.04320569336414337
2023-01-23 04:39:07.336074: step: 1072/526, loss: 1.430511474609375e-06
2023-01-23 04:39:08.459530: step: 1076/526, loss: 0.0413476936519146
2023-01-23 04:39:09.615394: step: 1080/526, loss: 0.0049527171067893505
2023-01-23 04:39:10.725557: step: 1084/526, loss: 0.00012702943058684468
2023-01-23 04:39:11.854121: step: 1088/526, loss: 0.005206442438066006
2023-01-23 04:39:13.001990: step: 1092/526, loss: 0.0024322508834302425
2023-01-23 04:39:14.120594: step: 1096/526, loss: 0.00022602081298828125
2023-01-23 04:39:15.257792: step: 1100/526, loss: 7.82012921263231e-06
2023-01-23 04:39:16.391937: step: 1104/526, loss: 0.0010413170093670487
2023-01-23 04:39:17.506879: step: 1108/526, loss: 0.0013490677811205387
2023-01-23 04:39:18.647131: step: 1112/526, loss: 0.00021238326735328883
2023-01-23 04:39:19.775612: step: 1116/526, loss: 7.781982276355848e-05
2023-01-23 04:39:20.929143: step: 1120/526, loss: 0.0038629532791674137
2023-01-23 04:39:22.085139: step: 1124/526, loss: 5.1021575927734375e-05
2023-01-23 04:39:23.252364: step: 1128/526, loss: 3.395080420887098e-05
2023-01-23 04:39:24.398176: step: 1132/526, loss: 0.0017368317348882556
2023-01-23 04:39:25.524344: step: 1136/526, loss: 0.0020225525368005037
2023-01-23 04:39:26.632223: step: 1140/526, loss: 5.71250930079259e-05
2023-01-23 04:39:27.777309: step: 1144/526, loss: 0.00011968612670898438
2023-01-23 04:39:28.950185: step: 1148/526, loss: 0.050405073910951614
2023-01-23 04:39:30.097794: step: 1152/526, loss: 0.07323837280273438
2023-01-23 04:39:31.230087: step: 1156/526, loss: 0.0005089759943075478
2023-01-23 04:39:32.335795: step: 1160/526, loss: 0.11612377315759659
2023-01-23 04:39:33.446981: step: 1164/526, loss: 0.008359909057617188
2023-01-23 04:39:34.582246: step: 1168/526, loss: 0.002209282014518976
2023-01-23 04:39:35.702720: step: 1172/526, loss: 0.0002244949428131804
2023-01-23 04:39:36.861817: step: 1176/526, loss: 0.009678459726274014
2023-01-23 04:39:37.993055: step: 1180/526, loss: 0.0006263732793740928
2023-01-23 04:39:39.109888: step: 1184/526, loss: 0.0002487182791810483
2023-01-23 04:39:40.227695: step: 1188/526, loss: 0.03626585006713867
2023-01-23 04:39:41.388623: step: 1192/526, loss: 0.00010070801363326609
2023-01-23 04:39:42.516375: step: 1196/526, loss: 0.0008913993951864541
2023-01-23 04:39:43.666454: step: 1200/526, loss: 0.049355123192071915
2023-01-23 04:39:44.805626: step: 1204/526, loss: 1.354217511106981e-05
2023-01-23 04:39:45.937406: step: 1208/526, loss: 0.0001028060942189768
2023-01-23 04:39:47.073248: step: 1212/526, loss: 2.1457672119140625e-06
2023-01-23 04:39:48.173738: step: 1216/526, loss: 0.0002957344113383442
2023-01-23 04:39:49.279007: step: 1220/526, loss: 0.0002740860218182206
2023-01-23 04:39:50.381321: step: 1224/526, loss: 0.00034646986750885844
2023-01-23 04:39:51.475506: step: 1228/526, loss: 0.0009620666969567537
2023-01-23 04:39:52.625153: step: 1232/526, loss: 1.087188684323337e-05
2023-01-23 04:39:53.706544: step: 1236/526, loss: 3.1471254260395654e-06
2023-01-23 04:39:54.849937: step: 1240/526, loss: 1.8596649169921875e-05
2023-01-23 04:39:55.992478: step: 1244/526, loss: 0.00021181107149459422
2023-01-23 04:39:57.107871: step: 1248/526, loss: 0.004889774601906538
2023-01-23 04:39:58.262503: step: 1252/526, loss: 0.0003567695675883442
2023-01-23 04:39:59.418969: step: 1256/526, loss: 0.00042896269587799907
2023-01-23 04:40:00.554588: step: 1260/526, loss: 0.00012784004502464086
2023-01-23 04:40:01.677782: step: 1264/526, loss: 0.008442020043730736
2023-01-23 04:40:02.810205: step: 1268/526, loss: 0.0007042884826660156
2023-01-23 04:40:03.923767: step: 1272/526, loss: 0.00027899740962311625
2023-01-23 04:40:05.083973: step: 1276/526, loss: 0.00010652541823219508
2023-01-23 04:40:06.209847: step: 1280/526, loss: 0.00031480786856263876
2023-01-23 04:40:07.329658: step: 1284/526, loss: 5.722047262679553e-07
2023-01-23 04:40:08.502914: step: 1288/526, loss: 0.0017557144165039062
2023-01-23 04:40:09.640150: step: 1292/526, loss: 0.00169792165979743
2023-01-23 04:40:10.804174: step: 1296/526, loss: 1.869201696536038e-05
2023-01-23 04:40:11.961794: step: 1300/526, loss: 2.861022494471399e-06
2023-01-23 04:40:13.134597: step: 1304/526, loss: 9.555817086948082e-05
2023-01-23 04:40:14.262127: step: 1308/526, loss: 5.435943421616685e-06
2023-01-23 04:40:15.408923: step: 1312/526, loss: 0.009656143374741077
2023-01-23 04:40:16.570751: step: 1316/526, loss: 7.400513277389109e-05
2023-01-23 04:40:17.679641: step: 1320/526, loss: 1.5068055290612392e-05
2023-01-23 04:40:18.792335: step: 1324/526, loss: 0.0036869049072265625
2023-01-23 04:40:19.955035: step: 1328/526, loss: 4.1675568354548886e-05
2023-01-23 04:40:21.091788: step: 1332/526, loss: 0.007709693629294634
2023-01-23 04:40:22.256546: step: 1336/526, loss: 0.0002304077206645161
2023-01-23 04:40:23.401354: step: 1340/526, loss: 0.0011201858287677169
2023-01-23 04:40:24.535586: step: 1344/526, loss: 4.329681542003527e-05
2023-01-23 04:40:25.678554: step: 1348/526, loss: 4.00543194700731e-06
2023-01-23 04:40:26.793828: step: 1352/526, loss: 0.05244407430291176
2023-01-23 04:40:27.960046: step: 1356/526, loss: 0.0005008697044104338
2023-01-23 04:40:29.103793: step: 1360/526, loss: 0.042695045471191406
2023-01-23 04:40:30.271968: step: 1364/526, loss: 0.007861138321459293
2023-01-23 04:40:31.409153: step: 1368/526, loss: 0.00266685476526618
2023-01-23 04:40:32.547241: step: 1372/526, loss: 0.0014341354835778475
2023-01-23 04:40:33.675124: step: 1376/526, loss: 0.0016349791549146175
2023-01-23 04:40:34.781976: step: 1380/526, loss: 0.0015510559314861894
2023-01-23 04:40:35.911343: step: 1384/526, loss: 2.8038026357535273e-05
2023-01-23 04:40:37.018967: step: 1388/526, loss: 2.5129320420091972e-05
2023-01-23 04:40:38.146107: step: 1392/526, loss: 0.002948522800579667
2023-01-23 04:40:39.252216: step: 1396/526, loss: 0.00037593842716887593
2023-01-23 04:40:40.389473: step: 1400/526, loss: 0.0003245353582315147
2023-01-23 04:40:41.518001: step: 1404/526, loss: 5.817413330078125e-05
2023-01-23 04:40:42.645762: step: 1408/526, loss: 0.022128678858280182
2023-01-23 04:40:43.788614: step: 1412/526, loss: 5.455017162603326e-05
2023-01-23 04:40:44.898934: step: 1416/526, loss: 0.0045060161501169205
2023-01-23 04:40:46.023033: step: 1420/526, loss: -1.3351439065445447e-06
2023-01-23 04:40:47.152621: step: 1424/526, loss: 5.8937075664289296e-05
2023-01-23 04:40:48.280044: step: 1428/526, loss: 0.009972859174013138
2023-01-23 04:40:49.405769: step: 1432/526, loss: 0.018579674884676933
2023-01-23 04:40:50.559367: step: 1436/526, loss: 0.00012874603271484375
2023-01-23 04:40:51.685241: step: 1440/526, loss: 0.0007793426048010588
2023-01-23 04:40:52.826050: step: 1444/526, loss: 0.6036515831947327
2023-01-23 04:40:53.980780: step: 1448/526, loss: 0.13037262856960297
2023-01-23 04:40:55.117245: step: 1452/526, loss: 0.01944446563720703
2023-01-23 04:40:56.221306: step: 1456/526, loss: 0.031284235417842865
2023-01-23 04:40:57.370140: step: 1460/526, loss: 0.006911468226462603
2023-01-23 04:40:58.554225: step: 1464/526, loss: 1.0013580322265625e-05
2023-01-23 04:40:59.681559: step: 1468/526, loss: 2.8228761948412284e-05
2023-01-23 04:41:00.819575: step: 1472/526, loss: 0.06143951416015625
2023-01-23 04:41:01.954942: step: 1476/526, loss: 8.587837510276586e-05
2023-01-23 04:41:03.089005: step: 1480/526, loss: 0.0020687102805823088
2023-01-23 04:41:04.219157: step: 1484/526, loss: 0.007953548803925514
2023-01-23 04:41:05.375382: step: 1488/526, loss: 3.070831371587701e-05
2023-01-23 04:41:06.537500: step: 1492/526, loss: 6.542206392623484e-05
2023-01-23 04:41:07.681442: step: 1496/526, loss: 0.014448165893554688
2023-01-23 04:41:08.814222: step: 1500/526, loss: 0.0014653205871582031
2023-01-23 04:41:09.951272: step: 1504/526, loss: 1.945495569088962e-05
2023-01-23 04:41:11.082502: step: 1508/526, loss: 0.00021057129197288305
2023-01-23 04:41:12.231355: step: 1512/526, loss: 0.010966873727738857
2023-01-23 04:41:13.353524: step: 1516/526, loss: 4.19616708313697e-06
2023-01-23 04:41:14.513494: step: 1520/526, loss: 0.03119640424847603
2023-01-23 04:41:15.644524: step: 1524/526, loss: 3.24249276673072e-06
2023-01-23 04:41:16.762533: step: 1528/526, loss: 0.0028587342239916325
2023-01-23 04:41:17.917392: step: 1532/526, loss: 0.0004125595442019403
2023-01-23 04:41:19.066737: step: 1536/526, loss: 0.05422992631793022
2023-01-23 04:41:20.204577: step: 1540/526, loss: 2.174377368646674e-05
2023-01-23 04:41:21.346200: step: 1544/526, loss: 0.00015163421630859375
2023-01-23 04:41:22.457444: step: 1548/526, loss: 7.247925168485381e-06
2023-01-23 04:41:23.619466: step: 1552/526, loss: 0.002633476397022605
2023-01-23 04:41:24.768127: step: 1556/526, loss: 7.26699799997732e-05
2023-01-23 04:41:25.899179: step: 1560/526, loss: 0.0002200603485107422
2023-01-23 04:41:27.063796: step: 1564/526, loss: 0.0009292602771893144
2023-01-23 04:41:28.198484: step: 1568/526, loss: 0.009453201666474342
2023-01-23 04:41:29.337874: step: 1572/526, loss: 0.08656969666481018
2023-01-23 04:41:30.460991: step: 1576/526, loss: 1.33514404296875e-05
2023-01-23 04:41:31.584393: step: 1580/526, loss: 0.0017705917125567794
2023-01-23 04:41:32.689249: step: 1584/526, loss: 0.02142944373190403
2023-01-23 04:41:33.824041: step: 1588/526, loss: 0.007173466961830854
2023-01-23 04:41:34.952838: step: 1592/526, loss: 3.776550147449598e-05
2023-01-23 04:41:36.080341: step: 1596/526, loss: 0.0007255554082803428
2023-01-23 04:41:37.235112: step: 1600/526, loss: 0.001608562539331615
2023-01-23 04:41:38.384380: step: 1604/526, loss: 0.024193763732910156
2023-01-23 04:41:39.507463: step: 1608/526, loss: 0.0002079010009765625
2023-01-23 04:41:40.669295: step: 1612/526, loss: 6.732940528308973e-05
2023-01-23 04:41:41.783058: step: 1616/526, loss: 0.0003525734064169228
2023-01-23 04:41:42.916849: step: 1620/526, loss: 3.070831371587701e-05
2023-01-23 04:41:44.036287: step: 1624/526, loss: 1.7452241081628017e-05
2023-01-23 04:41:45.160184: step: 1628/526, loss: 2.002716064453125e-05
2023-01-23 04:41:46.288162: step: 1632/526, loss: 7.63893112889491e-05
2023-01-23 04:41:47.433563: step: 1636/526, loss: 2.6702882678364404e-06
2023-01-23 04:41:48.615856: step: 1640/526, loss: 0.017107296735048294
2023-01-23 04:41:49.753059: step: 1644/526, loss: 0.0029172897338867188
2023-01-23 04:41:50.865487: step: 1648/526, loss: 0.09816054999828339
2023-01-23 04:41:51.991733: step: 1652/526, loss: -2.6226043701171875e-06
2023-01-23 04:41:53.115527: step: 1656/526, loss: 0.0005792618030682206
2023-01-23 04:41:54.231359: step: 1660/526, loss: 5.53131121705519e-06
2023-01-23 04:41:55.378887: step: 1664/526, loss: 0.00031843187753111124
2023-01-23 04:41:56.505354: step: 1668/526, loss: 0.027492905035614967
2023-01-23 04:41:57.674306: step: 1672/526, loss: 1.2588501704158261e-05
2023-01-23 04:41:58.831159: step: 1676/526, loss: 1.277923547604587e-05
2023-01-23 04:41:59.971272: step: 1680/526, loss: 8.583069188716763e-07
2023-01-23 04:42:01.081692: step: 1684/526, loss: 9.860993304755539e-05
2023-01-23 04:42:02.220080: step: 1688/526, loss: 0.0006062507745809853
2023-01-23 04:42:03.352627: step: 1692/526, loss: 8.964539119915571e-06
2023-01-23 04:42:04.512784: step: 1696/526, loss: 0.004302597139030695
2023-01-23 04:42:05.646455: step: 1700/526, loss: 0.005199909675866365
2023-01-23 04:42:06.802026: step: 1704/526, loss: 0.007496881298720837
2023-01-23 04:42:07.943174: step: 1708/526, loss: 6.732941255904734e-05
2023-01-23 04:42:09.102100: step: 1712/526, loss: 0.47811076045036316
2023-01-23 04:42:10.242566: step: 1716/526, loss: 0.0004191398620605469
2023-01-23 04:42:11.377691: step: 1720/526, loss: 0.0011436461936682463
2023-01-23 04:42:12.501658: step: 1724/526, loss: 0.02382030338048935
2023-01-23 04:42:13.628581: step: 1728/526, loss: 2.441406286379788e-05
2023-01-23 04:42:14.760895: step: 1732/526, loss: 6.680488877464086e-05
2023-01-23 04:42:15.887637: step: 1736/526, loss: 6.561279587913305e-05
2023-01-23 04:42:17.043174: step: 1740/526, loss: 2.2220612663659267e-05
2023-01-23 04:42:18.200243: step: 1744/526, loss: 0.0026401046197861433
2023-01-23 04:42:19.337605: step: 1748/526, loss: 0.2119217813014984
2023-01-23 04:42:20.465174: step: 1752/526, loss: 0.009987641125917435
2023-01-23 04:42:21.587125: step: 1756/526, loss: 0.023770714178681374
2023-01-23 04:42:22.715209: step: 1760/526, loss: 0.0011073113419115543
2023-01-23 04:42:23.865806: step: 1764/526, loss: 0.00010299683344783261
2023-01-23 04:42:24.981411: step: 1768/526, loss: 4.2629242670955136e-05
2023-01-23 04:42:26.133724: step: 1772/526, loss: 0.00466079730540514
2023-01-23 04:42:27.307010: step: 1776/526, loss: 0.0020397186744958162
2023-01-23 04:42:28.461301: step: 1780/526, loss: 0.0014230727683752775
2023-01-23 04:42:29.603061: step: 1784/526, loss: 0.0004172325134277344
2023-01-23 04:42:30.722198: step: 1788/526, loss: 0.0006271362653933465
2023-01-23 04:42:31.838847: step: 1792/526, loss: 0.011373710818588734
2023-01-23 04:42:33.045323: step: 1796/526, loss: 0.005287742707878351
2023-01-23 04:42:34.170411: step: 1800/526, loss: -2.19345088225964e-06
2023-01-23 04:42:35.317337: step: 1804/526, loss: 2.6845931643038057e-05
2023-01-23 04:42:36.444856: step: 1808/526, loss: 0.0015560149913653731
2023-01-23 04:42:37.566845: step: 1812/526, loss: 0.06823697686195374
2023-01-23 04:42:38.692044: step: 1816/526, loss: 0.0019278526306152344
2023-01-23 04:42:39.794946: step: 1820/526, loss: 0.07867280393838882
2023-01-23 04:42:40.907557: step: 1824/526, loss: 0.00042743684025481343
2023-01-23 04:42:42.039623: step: 1828/526, loss: 0.0008561611175537109
2023-01-23 04:42:43.188353: step: 1832/526, loss: 0.00011920928955078125
2023-01-23 04:42:44.324276: step: 1836/526, loss: 0.0020898820366710424
2023-01-23 04:42:45.483076: step: 1840/526, loss: 0.019743727520108223
2023-01-23 04:42:46.606247: step: 1844/526, loss: 0.035468123853206635
2023-01-23 04:42:47.779870: step: 1848/526, loss: 0.015892982482910156
2023-01-23 04:42:48.901863: step: 1852/526, loss: 0.0007521629449911416
2023-01-23 04:42:50.060267: step: 1856/526, loss: 1.4495850336970761e-05
2023-01-23 04:42:51.231167: step: 1860/526, loss: 5.207061622058973e-05
2023-01-23 04:42:52.368701: step: 1864/526, loss: 2.6702882678364404e-06
2023-01-23 04:42:53.520638: step: 1868/526, loss: 0.0014774323208257556
2023-01-23 04:42:54.649214: step: 1872/526, loss: 0.011353207752108574
2023-01-23 04:42:55.808703: step: 1876/526, loss: 0.014170932583510876
2023-01-23 04:42:56.949333: step: 1880/526, loss: 4.487037949729711e-05
2023-01-23 04:42:58.075411: step: 1884/526, loss: 0.00039768218994140625
2023-01-23 04:42:59.237572: step: 1888/526, loss: 0.04080944135785103
2023-01-23 04:43:00.330049: step: 1892/526, loss: 0.02029399946331978
2023-01-23 04:43:01.497888: step: 1896/526, loss: 0.00759277306497097
2023-01-23 04:43:02.666422: step: 1900/526, loss: 0.002919864607974887
2023-01-23 04:43:03.780380: step: 1904/526, loss: 0.002685165498405695
2023-01-23 04:43:04.929635: step: 1908/526, loss: 1.3089180356473662e-05
2023-01-23 04:43:06.093192: step: 1912/526, loss: 0.00036067963810637593
2023-01-23 04:43:07.217186: step: 1916/526, loss: 0.00090112688485533
2023-01-23 04:43:08.345095: step: 1920/526, loss: 0.019569776952266693
2023-01-23 04:43:09.478130: step: 1924/526, loss: 0.00111732492223382
2023-01-23 04:43:10.641026: step: 1928/526, loss: 0.00013151168241165578
2023-01-23 04:43:11.805688: step: 1932/526, loss: 1.5258792700478807e-06
2023-01-23 04:43:12.982330: step: 1936/526, loss: 0.006577968131750822
2023-01-23 04:43:14.161526: step: 1940/526, loss: 2.269744800287299e-05
2023-01-23 04:43:15.286341: step: 1944/526, loss: 0.0001729965297272429
2023-01-23 04:43:16.461643: step: 1948/526, loss: 0.005018198397010565
2023-01-23 04:43:17.608720: step: 1952/526, loss: 0.0008781657088547945
2023-01-23 04:43:18.772847: step: 1956/526, loss: 1.4495850336970761e-05
2023-01-23 04:43:19.932799: step: 1960/526, loss: 0.007883788086473942
2023-01-23 04:43:21.091032: step: 1964/526, loss: 3.128051685052924e-05
2023-01-23 04:43:22.287260: step: 1968/526, loss: 0.06362781673669815
2023-01-23 04:43:23.440546: step: 1972/526, loss: 4.76837158203125e-06
2023-01-23 04:43:24.570751: step: 1976/526, loss: 0.005054474342614412
2023-01-23 04:43:25.720635: step: 1980/526, loss: 0.00013132095045875758
2023-01-23 04:43:26.841668: step: 1984/526, loss: 0.0284791961312294
2023-01-23 04:43:27.964651: step: 1988/526, loss: 7.295608520507812e-05
2023-01-23 04:43:29.116276: step: 1992/526, loss: 2.5558472771081142e-05
2023-01-23 04:43:30.249798: step: 1996/526, loss: 0.00021972657123114914
2023-01-23 04:43:31.405665: step: 2000/526, loss: 0.0012958527076989412
2023-01-23 04:43:32.543398: step: 2004/526, loss: 0.01424627285450697
2023-01-23 04:43:33.643498: step: 2008/526, loss: 6.175041198730469e-05
2023-01-23 04:43:34.803668: step: 2012/526, loss: 0.008519649505615234
2023-01-23 04:43:35.938986: step: 2016/526, loss: 0.019211864098906517
2023-01-23 04:43:37.067642: step: 2020/526, loss: 0.009011078625917435
2023-01-23 04:43:38.208444: step: 2024/526, loss: 0.002674675080925226
2023-01-23 04:43:39.345719: step: 2028/526, loss: 0.0013034821022301912
2023-01-23 04:43:40.483356: step: 2032/526, loss: 0.0012968461960554123
2023-01-23 04:43:41.616416: step: 2036/526, loss: 0.018309593200683594
2023-01-23 04:43:42.755355: step: 2040/526, loss: 0.011711501516401768
2023-01-23 04:43:43.891658: step: 2044/526, loss: 7.171630568336695e-05
2023-01-23 04:43:45.058917: step: 2048/526, loss: 6.408691842807457e-05
2023-01-23 04:43:46.197953: step: 2052/526, loss: 0.012289238162338734
2023-01-23 04:43:47.340040: step: 2056/526, loss: 0.08432511985301971
2023-01-23 04:43:48.490159: step: 2060/526, loss: 0.005443572998046875
2023-01-23 04:43:49.632406: step: 2064/526, loss: 0.04935331642627716
2023-01-23 04:43:50.757944: step: 2068/526, loss: 1.087188684323337e-05
2023-01-23 04:43:51.892150: step: 2072/526, loss: 0.0004212379571981728
2023-01-23 04:43:53.014952: step: 2076/526, loss: 1.296997106692288e-05
2023-01-23 04:43:54.151770: step: 2080/526, loss: 0.03268766403198242
2023-01-23 04:43:55.303615: step: 2084/526, loss: 0.022002030164003372
2023-01-23 04:43:56.455583: step: 2088/526, loss: 0.02983837202191353
2023-01-23 04:43:57.613789: step: 2092/526, loss: 0.003565883729606867
2023-01-23 04:43:58.738603: step: 2096/526, loss: 0.00304336566478014
2023-01-23 04:43:59.882011: step: 2100/526, loss: 0.013535975478589535
2023-01-23 04:44:01.086778: step: 2104/526, loss: 0.0045476434752345085
==================================================
Loss: 0.014
--------------------
Dev: {'event': {'p': 0.5856573705179283, 'r': 0.7829560585885486, 'f1': 0.67008547008547}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 29}
Test: {'event': {'p': 0.6119463632669646, 'r': 0.7860125260960334, 'f1': 0.6881425633995888}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 29}
Chinese: {'event': {'p': 0.5714285714285714, 'r': 0.8888888888888888, 'f1': 0.6956521739130435}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 29}
Korean: {'event': {'p': 0.6226415094339622, 'r': 0.5238095238095238, 'f1': 0.5689655172413793}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 29}
Russian: {'event': {'p': 0.4772727272727273, 'r': 0.5833333333333334, 'f1': 0.5250000000000001}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 29}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6266519823788547, 'r': 0.7576564580559254, 'f1': 0.6859553948161543}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Eng Test for Chinese: {'event': {'p': 0.6313522825150732, 'r': 0.7651356993736952, 'f1': 0.6918357715903728}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Sample Chinese: {'event': {'p': 0.6621621621621622, 'r': 0.9074074074074074, 'f1': 0.765625}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6257995735607675, 'r': 0.7816245006657789, 'f1': 0.6950858496151568}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Eng Test for Korean: {'event': {'p': 0.623113410952997, 'r': 0.7541753653444676, 'f1': 0.6824085005903188}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Sample Korean: {'event': {'p': 0.7446808510638298, 'r': 0.5555555555555556, 'f1': 0.6363636363636364}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6266519823788547, 'r': 0.7576564580559254, 'f1': 0.6859553948161543}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Eng Test for Russian: {'event': {'p': 0.6313522825150732, 'r': 0.7651356993736952, 'f1': 0.6918357715903728}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Sample Russian: {'event': {'p': 0.5384615384615384, 'r': 0.5833333333333334, 'f1': 0.5599999999999999}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}