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 23:22:51.845142: step: 4/530, loss: 3.600830554962158
2023-01-22 23:22:52.999773: step: 8/530, loss: 11.446001052856445
2023-01-22 23:22:54.151824: step: 12/530, loss: 5.477788925170898
2023-01-22 23:22:55.266665: step: 16/530, loss: 3.1343941688537598
2023-01-22 23:22:56.425363: step: 20/530, loss: 3.854640007019043
2023-01-22 23:22:57.532257: step: 24/530, loss: 3.0547313690185547
2023-01-22 23:22:58.692346: step: 28/530, loss: 11.198469161987305
2023-01-22 23:22:59.818492: step: 32/530, loss: 10.628847122192383
2023-01-22 23:23:00.951187: step: 36/530, loss: 19.666278839111328
2023-01-22 23:23:02.093343: step: 40/530, loss: 4.534551620483398
2023-01-22 23:23:03.231568: step: 44/530, loss: 3.983240842819214
2023-01-22 23:23:04.358859: step: 48/530, loss: 5.397889137268066
2023-01-22 23:23:05.488358: step: 52/530, loss: 5.041791915893555
2023-01-22 23:23:06.622337: step: 56/530, loss: 2.1729354858398438
2023-01-22 23:23:07.743169: step: 60/530, loss: 3.4424490928649902
2023-01-22 23:23:08.920574: step: 64/530, loss: 22.45005989074707
2023-01-22 23:23:10.066470: step: 68/530, loss: 30.6683349609375
2023-01-22 23:23:11.181018: step: 72/530, loss: 3.5177664756774902
2023-01-22 23:23:12.320455: step: 76/530, loss: 4.0421295166015625
2023-01-22 23:23:13.422183: step: 80/530, loss: 3.200045108795166
2023-01-22 23:23:14.525181: step: 84/530, loss: 3.304994583129883
2023-01-22 23:23:15.664183: step: 88/530, loss: 19.04894256591797
2023-01-22 23:23:16.770027: step: 92/530, loss: 3.5746703147888184
2023-01-22 23:23:17.886604: step: 96/530, loss: 11.587350845336914
2023-01-22 23:23:18.991316: step: 100/530, loss: 3.2992119789123535
2023-01-22 23:23:20.095077: step: 104/530, loss: 13.409751892089844
2023-01-22 23:23:21.214479: step: 108/530, loss: 9.834317207336426
2023-01-22 23:23:22.354616: step: 112/530, loss: 5.219486236572266
2023-01-22 23:23:23.472662: step: 116/530, loss: 2.659261703491211
2023-01-22 23:23:24.576367: step: 120/530, loss: 21.642410278320312
2023-01-22 23:23:25.708981: step: 124/530, loss: 2.6457650661468506
2023-01-22 23:23:26.830060: step: 128/530, loss: 7.287134170532227
2023-01-22 23:23:27.927213: step: 132/530, loss: 10.075141906738281
2023-01-22 23:23:29.034994: step: 136/530, loss: 9.616050720214844
2023-01-22 23:23:30.161372: step: 140/530, loss: 10.84445858001709
2023-01-22 23:23:31.280969: step: 144/530, loss: 19.43450164794922
2023-01-22 23:23:32.418968: step: 148/530, loss: 2.7353615760803223
2023-01-22 23:23:33.553585: step: 152/530, loss: 3.719870090484619
2023-01-22 23:23:34.687008: step: 156/530, loss: 11.29328441619873
2023-01-22 23:23:35.798929: step: 160/530, loss: 8.982820510864258
2023-01-22 23:23:36.912185: step: 164/530, loss: 4.201029300689697
2023-01-22 23:23:38.045124: step: 168/530, loss: 14.721243858337402
2023-01-22 23:23:39.160884: step: 172/530, loss: 20.664798736572266
2023-01-22 23:23:40.268115: step: 176/530, loss: 6.335413932800293
2023-01-22 23:23:41.380076: step: 180/530, loss: 3.3321621417999268
2023-01-22 23:23:42.494863: step: 184/530, loss: 16.395395278930664
2023-01-22 23:23:43.614538: step: 188/530, loss: 2.9829115867614746
2023-01-22 23:23:44.761203: step: 192/530, loss: 3.75447940826416
2023-01-22 23:23:45.886400: step: 196/530, loss: 3.3201072216033936
2023-01-22 23:23:47.028665: step: 200/530, loss: 16.67919158935547
2023-01-22 23:23:48.176448: step: 204/530, loss: 12.394281387329102
2023-01-22 23:23:49.281167: step: 208/530, loss: 22.63667106628418
2023-01-22 23:23:50.416083: step: 212/530, loss: 21.802249908447266
2023-01-22 23:23:51.566116: step: 216/530, loss: 17.718791961669922
2023-01-22 23:23:52.692615: step: 220/530, loss: 7.292086124420166
2023-01-22 23:23:53.790670: step: 224/530, loss: 9.311068534851074
2023-01-22 23:23:54.881051: step: 228/530, loss: 8.232246398925781
2023-01-22 23:23:56.001821: step: 232/530, loss: 3.0800533294677734
2023-01-22 23:23:57.174931: step: 236/530, loss: 5.678860664367676
2023-01-22 23:23:58.303546: step: 240/530, loss: 12.479248046875
2023-01-22 23:23:59.412159: step: 244/530, loss: 14.88258171081543
2023-01-22 23:24:00.537130: step: 248/530, loss: 3.3008227348327637
2023-01-22 23:24:01.643046: step: 252/530, loss: 1.9073622226715088
2023-01-22 23:24:02.795287: step: 256/530, loss: 3.8980636596679688
2023-01-22 23:24:03.952655: step: 260/530, loss: 20.849109649658203
2023-01-22 23:24:05.079962: step: 264/530, loss: 12.183300018310547
2023-01-22 23:24:06.216615: step: 268/530, loss: 3.017989158630371
2023-01-22 23:24:07.396598: step: 272/530, loss: 4.457563400268555
2023-01-22 23:24:08.500556: step: 276/530, loss: 3.3766024112701416
2023-01-22 23:24:09.616172: step: 280/530, loss: 2.2874879837036133
2023-01-22 23:24:10.728880: step: 284/530, loss: 13.350345611572266
2023-01-22 23:24:11.870316: step: 288/530, loss: 4.229209899902344
2023-01-22 23:24:12.981393: step: 292/530, loss: 30.592504501342773
2023-01-22 23:24:14.137968: step: 296/530, loss: 3.621605157852173
2023-01-22 23:24:15.229544: step: 300/530, loss: 2.939500570297241
2023-01-22 23:24:16.356668: step: 304/530, loss: 11.074926376342773
2023-01-22 23:24:17.458354: step: 308/530, loss: 16.21042823791504
2023-01-22 23:24:18.599705: step: 312/530, loss: 32.711097717285156
2023-01-22 23:24:19.716678: step: 316/530, loss: 2.7682790756225586
2023-01-22 23:24:20.868109: step: 320/530, loss: 19.118976593017578
2023-01-22 23:24:22.013699: step: 324/530, loss: 10.407299995422363
2023-01-22 23:24:23.143873: step: 328/530, loss: 2.090254068374634
2023-01-22 23:24:24.284927: step: 332/530, loss: 4.193398475646973
2023-01-22 23:24:25.423132: step: 336/530, loss: 20.624755859375
2023-01-22 23:24:26.537984: step: 340/530, loss: 3.584094524383545
2023-01-22 23:24:27.673076: step: 344/530, loss: 11.230154037475586
2023-01-22 23:24:28.792957: step: 348/530, loss: 10.490753173828125
2023-01-22 23:24:29.939767: step: 352/530, loss: 29.088909149169922
2023-01-22 23:24:31.056628: step: 356/530, loss: 2.8673999309539795
2023-01-22 23:24:32.210381: step: 360/530, loss: 9.16180419921875
2023-01-22 23:24:33.330423: step: 364/530, loss: 7.584294319152832
2023-01-22 23:24:34.444828: step: 368/530, loss: 2.8562428951263428
2023-01-22 23:24:35.567576: step: 372/530, loss: 2.784353733062744
2023-01-22 23:24:36.725460: step: 376/530, loss: 23.008869171142578
2023-01-22 23:24:37.847068: step: 380/530, loss: 8.876879692077637
2023-01-22 23:24:39.021094: step: 384/530, loss: 8.077498435974121
2023-01-22 23:24:40.135299: step: 388/530, loss: 3.9711127281188965
2023-01-22 23:24:41.255793: step: 392/530, loss: 9.134020805358887
2023-01-22 23:24:42.385541: step: 396/530, loss: 25.49004364013672
2023-01-22 23:24:43.535435: step: 400/530, loss: 4.108882427215576
2023-01-22 23:24:44.645058: step: 404/530, loss: 7.861549377441406
2023-01-22 23:24:45.805071: step: 408/530, loss: 7.5175461769104
2023-01-22 23:24:46.966505: step: 412/530, loss: 9.480937004089355
2023-01-22 23:24:48.117956: step: 416/530, loss: 10.70997428894043
2023-01-22 23:24:49.242355: step: 420/530, loss: 2.3260340690612793
2023-01-22 23:24:50.380673: step: 424/530, loss: 3.471595287322998
2023-01-22 23:24:51.500908: step: 428/530, loss: 3.711090087890625
2023-01-22 23:24:52.667598: step: 432/530, loss: 3.251601219177246
2023-01-22 23:24:53.801666: step: 436/530, loss: 3.768089771270752
2023-01-22 23:24:54.941512: step: 440/530, loss: 2.9075162410736084
2023-01-22 23:24:56.068175: step: 444/530, loss: 2.0615603923797607
2023-01-22 23:24:57.178981: step: 448/530, loss: 11.910271644592285
2023-01-22 23:24:58.311623: step: 452/530, loss: 7.101742744445801
2023-01-22 23:24:59.444317: step: 456/530, loss: 7.715378761291504
2023-01-22 23:25:00.594307: step: 460/530, loss: 1.998674988746643
2023-01-22 23:25:01.756335: step: 464/530, loss: 14.214048385620117
2023-01-22 23:25:02.912423: step: 468/530, loss: 8.028645515441895
2023-01-22 23:25:04.041425: step: 472/530, loss: 2.282589912414551
2023-01-22 23:25:05.163810: step: 476/530, loss: 5.238405227661133
2023-01-22 23:25:06.294020: step: 480/530, loss: 2.1900508403778076
2023-01-22 23:25:07.421379: step: 484/530, loss: 7.375765800476074
2023-01-22 23:25:08.536830: step: 488/530, loss: 4.8053765296936035
2023-01-22 23:25:09.687321: step: 492/530, loss: 7.305607795715332
2023-01-22 23:25:10.842079: step: 496/530, loss: 13.81304931640625
2023-01-22 23:25:12.001805: step: 500/530, loss: 5.6990556716918945
2023-01-22 23:25:13.116439: step: 504/530, loss: 3.9752540588378906
2023-01-22 23:25:14.232822: step: 508/530, loss: 1.5550434589385986
2023-01-22 23:25:15.374826: step: 512/530, loss: 1.7749539613723755
2023-01-22 23:25:16.497363: step: 516/530, loss: 1.4538006782531738
2023-01-22 23:25:17.639233: step: 520/530, loss: 3.191053867340088
2023-01-22 23:25:18.769950: step: 524/530, loss: 1.3320629596710205
2023-01-22 23:25:19.916680: step: 528/530, loss: 2.291764736175537
2023-01-22 23:25:21.014455: step: 532/530, loss: 3.120242118835449
2023-01-22 23:25:22.144914: step: 536/530, loss: 4.4088945388793945
2023-01-22 23:25:23.234785: step: 540/530, loss: 4.373464584350586
2023-01-22 23:25:24.361783: step: 544/530, loss: 2.950277805328369
2023-01-22 23:25:25.489396: step: 548/530, loss: 6.946873188018799
2023-01-22 23:25:26.609788: step: 552/530, loss: 8.5263090133667
2023-01-22 23:25:27.750224: step: 556/530, loss: 2.9757401943206787
2023-01-22 23:25:28.863230: step: 560/530, loss: 0.8556032180786133
2023-01-22 23:25:29.991388: step: 564/530, loss: 2.5542051792144775
2023-01-22 23:25:31.112614: step: 568/530, loss: 8.050448417663574
2023-01-22 23:25:32.221647: step: 572/530, loss: 1.2285194396972656
2023-01-22 23:25:33.360787: step: 576/530, loss: 3.2618823051452637
2023-01-22 23:25:34.470773: step: 580/530, loss: 1.3381786346435547
2023-01-22 23:25:35.585020: step: 584/530, loss: 0.6971803307533264
2023-01-22 23:25:36.718285: step: 588/530, loss: 4.007962226867676
2023-01-22 23:25:37.837884: step: 592/530, loss: 1.5476454496383667
2023-01-22 23:25:38.945889: step: 596/530, loss: 0.6741154193878174
2023-01-22 23:25:40.056507: step: 600/530, loss: 4.426174163818359
2023-01-22 23:25:41.189559: step: 604/530, loss: 1.5493625402450562
2023-01-22 23:25:42.323975: step: 608/530, loss: 4.625621318817139
2023-01-22 23:25:43.446398: step: 612/530, loss: 1.687483549118042
2023-01-22 23:25:44.538919: step: 616/530, loss: 4.624767303466797
2023-01-22 23:25:45.677518: step: 620/530, loss: 4.724775314331055
2023-01-22 23:25:46.785887: step: 624/530, loss: 0.7202094793319702
2023-01-22 23:25:47.897583: step: 628/530, loss: 1.3630282878875732
2023-01-22 23:25:49.023377: step: 632/530, loss: 1.2366769313812256
2023-01-22 23:25:50.145175: step: 636/530, loss: 0.607374370098114
2023-01-22 23:25:51.288981: step: 640/530, loss: 3.485468864440918
2023-01-22 23:25:52.400210: step: 644/530, loss: 1.0302376747131348
2023-01-22 23:25:53.522081: step: 648/530, loss: 0.8324732184410095
2023-01-22 23:25:54.657701: step: 652/530, loss: 3.657708168029785
2023-01-22 23:25:55.778367: step: 656/530, loss: 2.873729705810547
2023-01-22 23:25:56.937552: step: 660/530, loss: 7.555106163024902
2023-01-22 23:25:58.021734: step: 664/530, loss: 0.5502809286117554
2023-01-22 23:25:59.145891: step: 668/530, loss: 2.3129308223724365
2023-01-22 23:26:00.265007: step: 672/530, loss: 1.891132116317749
2023-01-22 23:26:01.389788: step: 676/530, loss: 9.392467498779297
2023-01-22 23:26:02.517505: step: 680/530, loss: 1.7686702013015747
2023-01-22 23:26:03.618421: step: 684/530, loss: 2.2616591453552246
2023-01-22 23:26:04.716924: step: 688/530, loss: 2.5172009468078613
2023-01-22 23:26:05.839508: step: 692/530, loss: 1.1885987520217896
2023-01-22 23:26:06.966497: step: 696/530, loss: 0.6277967691421509
2023-01-22 23:26:08.123258: step: 700/530, loss: 0.45983749628067017
2023-01-22 23:26:09.238137: step: 704/530, loss: 3.198279857635498
2023-01-22 23:26:10.342185: step: 708/530, loss: 0.674511194229126
2023-01-22 23:26:11.453493: step: 712/530, loss: 0.8145885467529297
2023-01-22 23:26:12.607485: step: 716/530, loss: 1.9764336347579956
2023-01-22 23:26:13.754289: step: 720/530, loss: 3.313617706298828
2023-01-22 23:26:14.879583: step: 724/530, loss: 0.6266363263130188
2023-01-22 23:26:15.982854: step: 728/530, loss: 0.5607494115829468
2023-01-22 23:26:17.120526: step: 732/530, loss: 0.5683830976486206
2023-01-22 23:26:18.261398: step: 736/530, loss: 5.060230255126953
2023-01-22 23:26:19.409486: step: 740/530, loss: 0.6281356811523438
2023-01-22 23:26:20.511003: step: 744/530, loss: 0.637123703956604
2023-01-22 23:26:21.634781: step: 748/530, loss: 0.6059290170669556
2023-01-22 23:26:22.764459: step: 752/530, loss: 4.053745746612549
2023-01-22 23:26:23.887624: step: 756/530, loss: 2.8495497703552246
2023-01-22 23:26:25.003771: step: 760/530, loss: 2.016963481903076
2023-01-22 23:26:26.136900: step: 764/530, loss: 1.4283347129821777
2023-01-22 23:26:27.253161: step: 768/530, loss: 2.5355424880981445
2023-01-22 23:26:28.386767: step: 772/530, loss: 2.572380781173706
2023-01-22 23:26:29.500431: step: 776/530, loss: 2.76509690284729
2023-01-22 23:26:30.620682: step: 780/530, loss: 3.676267623901367
2023-01-22 23:26:31.779790: step: 784/530, loss: 2.0123727321624756
2023-01-22 23:26:32.938498: step: 788/530, loss: 3.093647003173828
2023-01-22 23:26:34.076548: step: 792/530, loss: 1.3893589973449707
2023-01-22 23:26:35.191442: step: 796/530, loss: 0.5670020580291748
2023-01-22 23:26:36.291956: step: 800/530, loss: 1.9091811180114746
2023-01-22 23:26:37.387039: step: 804/530, loss: 1.1956661939620972
2023-01-22 23:26:38.491031: step: 808/530, loss: 0.33247166872024536
2023-01-22 23:26:39.635111: step: 812/530, loss: 2.714752197265625
2023-01-22 23:26:40.761733: step: 816/530, loss: 2.7602460384368896
2023-01-22 23:26:41.893148: step: 820/530, loss: 1.389080286026001
2023-01-22 23:26:42.995909: step: 824/530, loss: 1.6229441165924072
2023-01-22 23:26:44.119023: step: 828/530, loss: 0.9028524160385132
2023-01-22 23:26:45.248860: step: 832/530, loss: 2.3566911220550537
2023-01-22 23:26:46.381302: step: 836/530, loss: 1.0580787658691406
2023-01-22 23:26:47.496598: step: 840/530, loss: 1.3911709785461426
2023-01-22 23:26:48.622360: step: 844/530, loss: 1.1588531732559204
2023-01-22 23:26:49.743973: step: 848/530, loss: 0.7124577760696411
2023-01-22 23:26:50.859786: step: 852/530, loss: 0.46316224336624146
2023-01-22 23:26:52.002944: step: 856/530, loss: 0.675922691822052
2023-01-22 23:26:53.134633: step: 860/530, loss: 0.7243403196334839
2023-01-22 23:26:54.277911: step: 864/530, loss: 0.27582770586013794
2023-01-22 23:26:55.379979: step: 868/530, loss: 3.4991581439971924
2023-01-22 23:26:56.512718: step: 872/530, loss: 0.9697194695472717
2023-01-22 23:26:57.623083: step: 876/530, loss: 1.0417035818099976
2023-01-22 23:26:58.751997: step: 880/530, loss: 0.7541743516921997
2023-01-22 23:26:59.858336: step: 884/530, loss: 0.46459466218948364
2023-01-22 23:27:00.983672: step: 888/530, loss: 1.741030216217041
2023-01-22 23:27:02.168958: step: 892/530, loss: 0.4115075170993805
2023-01-22 23:27:03.288751: step: 896/530, loss: 0.5463149547576904
2023-01-22 23:27:04.407009: step: 900/530, loss: 0.6377755403518677
2023-01-22 23:27:05.526876: step: 904/530, loss: 2.4856197834014893
2023-01-22 23:27:06.691522: step: 908/530, loss: 3.756301164627075
2023-01-22 23:27:07.826662: step: 912/530, loss: 0.4391940236091614
2023-01-22 23:27:08.938850: step: 916/530, loss: 1.045654058456421
2023-01-22 23:27:10.061483: step: 920/530, loss: 1.518012523651123
2023-01-22 23:27:11.182777: step: 924/530, loss: 3.4010565280914307
2023-01-22 23:27:12.317352: step: 928/530, loss: 0.46121102571487427
2023-01-22 23:27:13.439629: step: 932/530, loss: 7.733952045440674
2023-01-22 23:27:14.557993: step: 936/530, loss: 0.608338475227356
2023-01-22 23:27:15.665136: step: 940/530, loss: 2.4491991996765137
2023-01-22 23:27:16.801143: step: 944/530, loss: 1.2341818809509277
2023-01-22 23:27:17.924996: step: 948/530, loss: 0.30906087160110474
2023-01-22 23:27:19.031491: step: 952/530, loss: 2.2727456092834473
2023-01-22 23:27:20.168039: step: 956/530, loss: 3.5723812580108643
2023-01-22 23:27:21.280829: step: 960/530, loss: 0.5487877130508423
2023-01-22 23:27:22.406428: step: 964/530, loss: 1.386991024017334
2023-01-22 23:27:23.546427: step: 968/530, loss: 0.4014175534248352
2023-01-22 23:27:24.667798: step: 972/530, loss: 0.33909910917282104
2023-01-22 23:27:25.778153: step: 976/530, loss: 1.0264865159988403
2023-01-22 23:27:26.912135: step: 980/530, loss: 0.48007574677467346
2023-01-22 23:27:28.058368: step: 984/530, loss: 0.5306209325790405
2023-01-22 23:27:29.181414: step: 988/530, loss: 1.0716761350631714
2023-01-22 23:27:30.332854: step: 992/530, loss: 0.5828955769538879
2023-01-22 23:27:31.443703: step: 996/530, loss: 0.685972273349762
2023-01-22 23:27:32.610934: step: 1000/530, loss: 0.412115216255188
2023-01-22 23:27:33.747961: step: 1004/530, loss: 0.29873672127723694
2023-01-22 23:27:34.872264: step: 1008/530, loss: 8.87093734741211
2023-01-22 23:27:35.999556: step: 1012/530, loss: 1.144291877746582
2023-01-22 23:27:37.121702: step: 1016/530, loss: 0.43664783239364624
2023-01-22 23:27:38.248093: step: 1020/530, loss: 1.815722942352295
2023-01-22 23:27:39.398507: step: 1024/530, loss: 1.0974397659301758
2023-01-22 23:27:40.571342: step: 1028/530, loss: 2.252948522567749
2023-01-22 23:27:41.675680: step: 1032/530, loss: 0.3966113030910492
2023-01-22 23:27:42.789088: step: 1036/530, loss: 2.0770246982574463
2023-01-22 23:27:43.894196: step: 1040/530, loss: 0.345125675201416
2023-01-22 23:27:45.019403: step: 1044/530, loss: 0.523857593536377
2023-01-22 23:27:46.151938: step: 1048/530, loss: 1.4699203968048096
2023-01-22 23:27:47.293014: step: 1052/530, loss: 2.2116103172302246
2023-01-22 23:27:48.420014: step: 1056/530, loss: 2.7866392135620117
2023-01-22 23:27:49.532988: step: 1060/530, loss: 1.5094499588012695
2023-01-22 23:27:50.664900: step: 1064/530, loss: 2.090209722518921
2023-01-22 23:27:51.793630: step: 1068/530, loss: 0.44535475969314575
2023-01-22 23:27:52.918436: step: 1072/530, loss: 3.7799086570739746
2023-01-22 23:27:54.072823: step: 1076/530, loss: 2.126986503601074
2023-01-22 23:27:55.190174: step: 1080/530, loss: 2.398672580718994
2023-01-22 23:27:56.338728: step: 1084/530, loss: 1.9506633281707764
2023-01-22 23:27:57.448096: step: 1088/530, loss: 2.201355457305908
2023-01-22 23:27:58.578315: step: 1092/530, loss: 0.6073480248451233
2023-01-22 23:27:59.691159: step: 1096/530, loss: 1.36834716796875
2023-01-22 23:28:00.856885: step: 1100/530, loss: 2.315734386444092
2023-01-22 23:28:02.032429: step: 1104/530, loss: 0.33206498622894287
2023-01-22 23:28:03.153824: step: 1108/530, loss: 2.451411485671997
2023-01-22 23:28:04.274332: step: 1112/530, loss: 2.069584846496582
2023-01-22 23:28:05.438919: step: 1116/530, loss: 1.9682148694992065
2023-01-22 23:28:06.554783: step: 1120/530, loss: 0.3384386897087097
2023-01-22 23:28:07.714962: step: 1124/530, loss: 1.7715543508529663
2023-01-22 23:28:08.852923: step: 1128/530, loss: 1.2660282850265503
2023-01-22 23:28:09.949508: step: 1132/530, loss: 1.1928772926330566
2023-01-22 23:28:11.044098: step: 1136/530, loss: 1.8105182647705078
2023-01-22 23:28:12.146757: step: 1140/530, loss: 0.5496821403503418
2023-01-22 23:28:13.337855: step: 1144/530, loss: 0.6329587697982788
2023-01-22 23:28:14.443333: step: 1148/530, loss: 1.0937938690185547
2023-01-22 23:28:15.586779: step: 1152/530, loss: 0.43902474641799927
2023-01-22 23:28:16.712381: step: 1156/530, loss: 2.580002546310425
2023-01-22 23:28:17.829160: step: 1160/530, loss: 0.3949740529060364
2023-01-22 23:28:18.960058: step: 1164/530, loss: 2.565321683883667
2023-01-22 23:28:20.063599: step: 1168/530, loss: 0.32813262939453125
2023-01-22 23:28:21.205222: step: 1172/530, loss: 0.47925710678100586
2023-01-22 23:28:22.329198: step: 1176/530, loss: 0.6064233779907227
2023-01-22 23:28:23.471789: step: 1180/530, loss: 1.4329512119293213
2023-01-22 23:28:24.595453: step: 1184/530, loss: 0.5150305032730103
2023-01-22 23:28:25.741525: step: 1188/530, loss: 0.5031442642211914
2023-01-22 23:28:26.872940: step: 1192/530, loss: 2.933885335922241
2023-01-22 23:28:27.987488: step: 1196/530, loss: 2.081019163131714
2023-01-22 23:28:29.106228: step: 1200/530, loss: 1.5043662786483765
2023-01-22 23:28:30.203698: step: 1204/530, loss: 2.3235888481140137
2023-01-22 23:28:31.347989: step: 1208/530, loss: 1.176701545715332
2023-01-22 23:28:32.479325: step: 1212/530, loss: 0.944574236869812
2023-01-22 23:28:33.610162: step: 1216/530, loss: 0.4637095630168915
2023-01-22 23:28:34.795487: step: 1220/530, loss: 0.64052414894104
2023-01-22 23:28:35.917683: step: 1224/530, loss: 0.8622530102729797
2023-01-22 23:28:37.046883: step: 1228/530, loss: 1.340064525604248
2023-01-22 23:28:38.181979: step: 1232/530, loss: 0.9074380397796631
2023-01-22 23:28:39.293817: step: 1236/530, loss: 0.9914621710777283
2023-01-22 23:28:40.410167: step: 1240/530, loss: 1.7066187858581543
2023-01-22 23:28:41.502887: step: 1244/530, loss: 0.4488796293735504
2023-01-22 23:28:42.628929: step: 1248/530, loss: 1.4746979475021362
2023-01-22 23:28:43.759372: step: 1252/530, loss: 1.0657771825790405
2023-01-22 23:28:44.936736: step: 1256/530, loss: 0.5082967281341553
2023-01-22 23:28:46.097952: step: 1260/530, loss: 0.9484478831291199
2023-01-22 23:28:47.211178: step: 1264/530, loss: 0.5143436789512634
2023-01-22 23:28:48.358567: step: 1268/530, loss: 4.903132438659668
2023-01-22 23:28:49.495275: step: 1272/530, loss: 1.4742833375930786
2023-01-22 23:28:50.618517: step: 1276/530, loss: 0.49241095781326294
2023-01-22 23:28:51.732911: step: 1280/530, loss: 1.8619345426559448
2023-01-22 23:28:52.861734: step: 1284/530, loss: 0.46827393770217896
2023-01-22 23:28:53.982029: step: 1288/530, loss: 2.9534099102020264
2023-01-22 23:28:55.091934: step: 1292/530, loss: 8.42802906036377
2023-01-22 23:28:56.196176: step: 1296/530, loss: 1.7902815341949463
2023-01-22 23:28:57.329983: step: 1300/530, loss: 1.2165833711624146
2023-01-22 23:28:58.478729: step: 1304/530, loss: 1.3490514755249023
2023-01-22 23:28:59.574321: step: 1308/530, loss: 1.2527767419815063
2023-01-22 23:29:00.693379: step: 1312/530, loss: 0.5281668305397034
2023-01-22 23:29:01.824460: step: 1316/530, loss: 1.4810662269592285
2023-01-22 23:29:02.947454: step: 1320/530, loss: 0.4196866750717163
2023-01-22 23:29:04.048056: step: 1324/530, loss: 0.3975706696510315
2023-01-22 23:29:05.209922: step: 1328/530, loss: 0.5328815579414368
2023-01-22 23:29:06.322901: step: 1332/530, loss: 2.9793622493743896
2023-01-22 23:29:07.464746: step: 1336/530, loss: 1.081673502922058
2023-01-22 23:29:08.583659: step: 1340/530, loss: 0.2754342555999756
2023-01-22 23:29:09.678330: step: 1344/530, loss: 0.7935055494308472
2023-01-22 23:29:10.807673: step: 1348/530, loss: 0.4227084517478943
2023-01-22 23:29:11.923547: step: 1352/530, loss: 8.243891716003418
2023-01-22 23:29:13.021028: step: 1356/530, loss: 1.0183504819869995
2023-01-22 23:29:14.127016: step: 1360/530, loss: 0.6033120155334473
2023-01-22 23:29:15.251253: step: 1364/530, loss: 2.24267578125
2023-01-22 23:29:16.396702: step: 1368/530, loss: 0.4645126461982727
2023-01-22 23:29:17.523346: step: 1372/530, loss: 0.8822733163833618
2023-01-22 23:29:18.615280: step: 1376/530, loss: 1.4328054189682007
2023-01-22 23:29:19.718267: step: 1380/530, loss: 1.7444825172424316
2023-01-22 23:29:20.823632: step: 1384/530, loss: 0.9913070201873779
2023-01-22 23:29:21.970545: step: 1388/530, loss: 0.8182525634765625
2023-01-22 23:29:23.113770: step: 1392/530, loss: 1.2500710487365723
2023-01-22 23:29:24.245249: step: 1396/530, loss: 0.6330999732017517
2023-01-22 23:29:25.353207: step: 1400/530, loss: 0.25191688537597656
2023-01-22 23:29:26.486778: step: 1404/530, loss: 3.7340052127838135
2023-01-22 23:29:27.647384: step: 1408/530, loss: 1.532026767730713
2023-01-22 23:29:28.775041: step: 1412/530, loss: 1.451857566833496
2023-01-22 23:29:29.873183: step: 1416/530, loss: 1.818490982055664
2023-01-22 23:29:31.027942: step: 1420/530, loss: 0.36859849095344543
2023-01-22 23:29:32.156934: step: 1424/530, loss: 0.3752859830856323
2023-01-22 23:29:33.276499: step: 1428/530, loss: 0.6991058588027954
2023-01-22 23:29:34.423509: step: 1432/530, loss: 0.27190127968788147
2023-01-22 23:29:35.563143: step: 1436/530, loss: 0.6830970048904419
2023-01-22 23:29:36.681623: step: 1440/530, loss: 0.22408531606197357
2023-01-22 23:29:37.851722: step: 1444/530, loss: 2.056386709213257
2023-01-22 23:29:38.970040: step: 1448/530, loss: 0.5733118057250977
2023-01-22 23:29:40.120400: step: 1452/530, loss: 0.3968283534049988
2023-01-22 23:29:41.247172: step: 1456/530, loss: 1.7949159145355225
2023-01-22 23:29:42.353834: step: 1460/530, loss: 0.3667941987514496
2023-01-22 23:29:43.455296: step: 1464/530, loss: 0.46869271993637085
2023-01-22 23:29:44.573064: step: 1468/530, loss: 1.4501781463623047
2023-01-22 23:29:45.681060: step: 1472/530, loss: 2.5580124855041504
2023-01-22 23:29:46.815131: step: 1476/530, loss: 2.118748903274536
2023-01-22 23:29:47.914671: step: 1480/530, loss: 1.0308361053466797
2023-01-22 23:29:49.011185: step: 1484/530, loss: 0.5159183740615845
2023-01-22 23:29:50.129838: step: 1488/530, loss: 1.057452917098999
2023-01-22 23:29:51.225840: step: 1492/530, loss: 1.4485530853271484
2023-01-22 23:29:52.361136: step: 1496/530, loss: 3.538574457168579
2023-01-22 23:29:53.487916: step: 1500/530, loss: 0.667655348777771
2023-01-22 23:29:54.571505: step: 1504/530, loss: 0.2334914207458496
2023-01-22 23:29:55.687715: step: 1508/530, loss: 0.23393484950065613
2023-01-22 23:29:56.842355: step: 1512/530, loss: 0.31054389476776123
2023-01-22 23:29:57.970388: step: 1516/530, loss: 0.23938751220703125
2023-01-22 23:29:59.122543: step: 1520/530, loss: 1.1196620464324951
2023-01-22 23:30:00.225618: step: 1524/530, loss: 0.8583744168281555
2023-01-22 23:30:01.362260: step: 1528/530, loss: 1.2071545124053955
2023-01-22 23:30:02.508407: step: 1532/530, loss: 1.1557931900024414
2023-01-22 23:30:03.633318: step: 1536/530, loss: 1.8818198442459106
2023-01-22 23:30:04.749934: step: 1540/530, loss: 0.255204975605011
2023-01-22 23:30:05.887585: step: 1544/530, loss: 2.2218806743621826
2023-01-22 23:30:06.996979: step: 1548/530, loss: 0.23186376690864563
2023-01-22 23:30:08.096519: step: 1552/530, loss: 0.2523016929626465
2023-01-22 23:30:09.215905: step: 1556/530, loss: 1.8257893323898315
2023-01-22 23:30:10.338463: step: 1560/530, loss: 0.3640386462211609
2023-01-22 23:30:11.479783: step: 1564/530, loss: 0.3130548298358917
2023-01-22 23:30:12.606244: step: 1568/530, loss: 0.3681375980377197
2023-01-22 23:30:13.708204: step: 1572/530, loss: 0.4442242383956909
2023-01-22 23:30:14.831285: step: 1576/530, loss: 0.25453662872314453
2023-01-22 23:30:15.947584: step: 1580/530, loss: 3.7313971519470215
2023-01-22 23:30:17.065913: step: 1584/530, loss: 0.3674551248550415
2023-01-22 23:30:18.194434: step: 1588/530, loss: 1.8774027824401855
2023-01-22 23:30:19.317869: step: 1592/530, loss: 0.42305582761764526
2023-01-22 23:30:20.457827: step: 1596/530, loss: 2.530494213104248
2023-01-22 23:30:21.617662: step: 1600/530, loss: 0.4066914916038513
2023-01-22 23:30:22.774861: step: 1604/530, loss: 1.1537199020385742
2023-01-22 23:30:23.894344: step: 1608/530, loss: 1.0986946821212769
2023-01-22 23:30:25.019915: step: 1612/530, loss: 1.5892796516418457
2023-01-22 23:30:26.137566: step: 1616/530, loss: 0.6171531677246094
2023-01-22 23:30:27.259827: step: 1620/530, loss: 1.014963150024414
2023-01-22 23:30:28.364545: step: 1624/530, loss: 0.37272512912750244
2023-01-22 23:30:29.505500: step: 1628/530, loss: 0.7471286058425903
2023-01-22 23:30:30.623577: step: 1632/530, loss: 0.21901212632656097
2023-01-22 23:30:31.707307: step: 1636/530, loss: 1.7878408432006836
2023-01-22 23:30:32.852716: step: 1640/530, loss: 0.9727045893669128
2023-01-22 23:30:33.971412: step: 1644/530, loss: 0.7920225262641907
2023-01-22 23:30:35.121657: step: 1648/530, loss: 1.2238308191299438
2023-01-22 23:30:36.237786: step: 1652/530, loss: 0.2008354663848877
2023-01-22 23:30:37.364741: step: 1656/530, loss: 0.6294609308242798
2023-01-22 23:30:38.504290: step: 1660/530, loss: 1.1559182405471802
2023-01-22 23:30:39.645335: step: 1664/530, loss: 0.186271071434021
2023-01-22 23:30:40.758326: step: 1668/530, loss: 1.243440866470337
2023-01-22 23:30:41.897636: step: 1672/530, loss: 0.3269496560096741
2023-01-22 23:30:43.030465: step: 1676/530, loss: 0.1378132402896881
2023-01-22 23:30:44.142967: step: 1680/530, loss: 0.5146986842155457
2023-01-22 23:30:45.219753: step: 1684/530, loss: 0.28378400206565857
2023-01-22 23:30:46.313312: step: 1688/530, loss: 0.15652476251125336
2023-01-22 23:30:47.435403: step: 1692/530, loss: 0.5861271023750305
2023-01-22 23:30:48.553047: step: 1696/530, loss: 1.3331334590911865
2023-01-22 23:30:49.664568: step: 1700/530, loss: 8.364970207214355
2023-01-22 23:30:50.804238: step: 1704/530, loss: 0.8491256237030029
2023-01-22 23:30:51.934204: step: 1708/530, loss: 0.36198320984840393
2023-01-22 23:30:53.032938: step: 1712/530, loss: 0.5336839556694031
2023-01-22 23:30:54.143591: step: 1716/530, loss: 0.5477591156959534
2023-01-22 23:30:55.291004: step: 1720/530, loss: 1.49003267288208
2023-01-22 23:30:56.395717: step: 1724/530, loss: 1.797303557395935
2023-01-22 23:30:57.512147: step: 1728/530, loss: 1.4529967308044434
2023-01-22 23:30:58.641973: step: 1732/530, loss: 1.5711355209350586
2023-01-22 23:30:59.756026: step: 1736/530, loss: 0.17998333275318146
2023-01-22 23:31:00.877197: step: 1740/530, loss: 3.067667007446289
2023-01-22 23:31:01.980386: step: 1744/530, loss: 0.27986735105514526
2023-01-22 23:31:03.125416: step: 1748/530, loss: 0.4771209955215454
2023-01-22 23:31:04.237583: step: 1752/530, loss: 0.4389764070510864
2023-01-22 23:31:05.339771: step: 1756/530, loss: 1.14346444606781
2023-01-22 23:31:06.465409: step: 1760/530, loss: 0.43427371978759766
2023-01-22 23:31:07.606174: step: 1764/530, loss: 2.199627161026001
2023-01-22 23:31:08.698088: step: 1768/530, loss: 3.8894827365875244
2023-01-22 23:31:09.841712: step: 1772/530, loss: 0.24031981825828552
2023-01-22 23:31:10.936006: step: 1776/530, loss: 0.8863033056259155
2023-01-22 23:31:12.049503: step: 1780/530, loss: 0.6817730069160461
2023-01-22 23:31:13.175538: step: 1784/530, loss: 2.9836671352386475
2023-01-22 23:31:14.276343: step: 1788/530, loss: 0.2790653705596924
2023-01-22 23:31:15.414223: step: 1792/530, loss: 0.39870119094848633
2023-01-22 23:31:16.561206: step: 1796/530, loss: 1.2312772274017334
2023-01-22 23:31:17.667471: step: 1800/530, loss: 0.4943826198577881
2023-01-22 23:31:18.759284: step: 1804/530, loss: 0.14156588912010193
2023-01-22 23:31:19.891164: step: 1808/530, loss: 1.042165756225586
2023-01-22 23:31:21.003877: step: 1812/530, loss: 0.2378344088792801
2023-01-22 23:31:22.128855: step: 1816/530, loss: 1.5827640295028687
2023-01-22 23:31:23.248176: step: 1820/530, loss: 0.9896622896194458
2023-01-22 23:31:24.381024: step: 1824/530, loss: 0.5366732478141785
2023-01-22 23:31:25.470099: step: 1828/530, loss: 0.29550257325172424
2023-01-22 23:31:26.580802: step: 1832/530, loss: 0.6661741137504578
2023-01-22 23:31:27.716794: step: 1836/530, loss: 1.6965742111206055
2023-01-22 23:31:28.820695: step: 1840/530, loss: 2.8654441833496094
2023-01-22 23:31:29.942574: step: 1844/530, loss: 0.9360326528549194
2023-01-22 23:31:31.073390: step: 1848/530, loss: 0.48728516697883606
2023-01-22 23:31:32.196567: step: 1852/530, loss: 0.7745282649993896
2023-01-22 23:31:33.299710: step: 1856/530, loss: 0.5575208067893982
2023-01-22 23:31:34.410452: step: 1860/530, loss: 1.5983372926712036
2023-01-22 23:31:35.509449: step: 1864/530, loss: 1.5419771671295166
2023-01-22 23:31:36.626621: step: 1868/530, loss: 0.3139318525791168
2023-01-22 23:31:37.735143: step: 1872/530, loss: 1.8479645252227783
2023-01-22 23:31:38.869721: step: 1876/530, loss: 1.23250412940979
2023-01-22 23:31:39.999995: step: 1880/530, loss: 0.8113978505134583
2023-01-22 23:31:41.122855: step: 1884/530, loss: 0.8430125117301941
2023-01-22 23:31:42.256740: step: 1888/530, loss: 0.31167298555374146
2023-01-22 23:31:43.376365: step: 1892/530, loss: 0.47321024537086487
2023-01-22 23:31:44.514316: step: 1896/530, loss: 0.2288370132446289
2023-01-22 23:31:45.653449: step: 1900/530, loss: 0.3992019593715668
2023-01-22 23:31:46.787472: step: 1904/530, loss: 2.973729372024536
2023-01-22 23:31:47.899427: step: 1908/530, loss: 0.29276227951049805
2023-01-22 23:31:49.039741: step: 1912/530, loss: 0.3745533227920532
2023-01-22 23:31:50.157434: step: 1916/530, loss: 0.6668537259101868
2023-01-22 23:31:51.256608: step: 1920/530, loss: 1.711925983428955
2023-01-22 23:31:52.389106: step: 1924/530, loss: 3.0173497200012207
2023-01-22 23:31:53.510450: step: 1928/530, loss: 2.8242077827453613
2023-01-22 23:31:54.633518: step: 1932/530, loss: 0.4657968580722809
2023-01-22 23:31:55.761492: step: 1936/530, loss: 2.0983266830444336
2023-01-22 23:31:56.937404: step: 1940/530, loss: 0.4327394366264343
2023-01-22 23:31:58.027502: step: 1944/530, loss: 0.8828244209289551
2023-01-22 23:31:59.128660: step: 1948/530, loss: 0.3461621403694153
2023-01-22 23:32:00.272439: step: 1952/530, loss: 0.9902653694152832
2023-01-22 23:32:01.427003: step: 1956/530, loss: 0.6558536887168884
2023-01-22 23:32:02.590810: step: 1960/530, loss: 0.2337017059326172
2023-01-22 23:32:03.748630: step: 1964/530, loss: 0.8781980276107788
2023-01-22 23:32:04.877825: step: 1968/530, loss: 2.319739580154419
2023-01-22 23:32:05.976160: step: 1972/530, loss: 0.8620238900184631
2023-01-22 23:32:07.109433: step: 1976/530, loss: 0.28784117102622986
2023-01-22 23:32:08.250659: step: 1980/530, loss: 2.2409591674804688
2023-01-22 23:32:09.343049: step: 1984/530, loss: 0.3111709654331207
2023-01-22 23:32:10.482369: step: 1988/530, loss: 1.2188161611557007
2023-01-22 23:32:11.641628: step: 1992/530, loss: 1.1012210845947266
2023-01-22 23:32:12.735681: step: 1996/530, loss: 1.094132423400879
2023-01-22 23:32:13.852868: step: 2000/530, loss: 0.4319194555282593
2023-01-22 23:32:14.959553: step: 2004/530, loss: 1.8047986030578613
2023-01-22 23:32:16.110623: step: 2008/530, loss: 0.2863107919692993
2023-01-22 23:32:17.232848: step: 2012/530, loss: 0.5039840936660767
2023-01-22 23:32:18.366636: step: 2016/530, loss: 0.37399351596832275
2023-01-22 23:32:19.486903: step: 2020/530, loss: 0.7118241786956787
2023-01-22 23:32:20.612630: step: 2024/530, loss: 0.4375157356262207
2023-01-22 23:32:21.711510: step: 2028/530, loss: 0.0410003662109375
2023-01-22 23:32:22.863445: step: 2032/530, loss: 2.3981244564056396
2023-01-22 23:32:23.982879: step: 2036/530, loss: 0.5573617815971375
2023-01-22 23:32:25.113082: step: 2040/530, loss: 0.2811049520969391
2023-01-22 23:32:26.245176: step: 2044/530, loss: 0.4849625527858734
2023-01-22 23:32:27.349313: step: 2048/530, loss: 0.9386671781539917
2023-01-22 23:32:28.477316: step: 2052/530, loss: 0.6929950714111328
2023-01-22 23:32:29.604918: step: 2056/530, loss: 0.18222494423389435
2023-01-22 23:32:30.722170: step: 2060/530, loss: 0.5865623950958252
2023-01-22 23:32:31.865528: step: 2064/530, loss: 1.2626607418060303
2023-01-22 23:32:32.979842: step: 2068/530, loss: 0.10001854598522186
2023-01-22 23:32:34.125186: step: 2072/530, loss: 0.15827837586402893
2023-01-22 23:32:35.280791: step: 2076/530, loss: 0.6684004664421082
2023-01-22 23:32:36.423174: step: 2080/530, loss: 0.6001387238502502
2023-01-22 23:32:37.576940: step: 2084/530, loss: 0.3209933340549469
2023-01-22 23:32:38.698424: step: 2088/530, loss: 0.7773169279098511
2023-01-22 23:32:39.826364: step: 2092/530, loss: 0.2292274534702301
2023-01-22 23:32:40.944453: step: 2096/530, loss: 0.19434042274951935
2023-01-22 23:32:42.082254: step: 2100/530, loss: 1.7122278213500977
2023-01-22 23:32:43.209105: step: 2104/530, loss: 2.20381498336792
2023-01-22 23:32:44.314741: step: 2108/530, loss: 0.38788869976997375
2023-01-22 23:32:45.463807: step: 2112/530, loss: 0.4826367497444153
2023-01-22 23:32:46.615366: step: 2116/530, loss: 1.1367560625076294
2023-01-22 23:32:47.751808: step: 2120/530, loss: 0.21407929062843323
==================================================
Loss: 3.221
--------------------
Dev: {'event': {'p': 0.5620736698499318, 'r': 0.5486018641810919, 'f1': 0.555256064690027}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Test: {'event': {'p': 0.4576822916666667, 'r': 0.4017142857142857, 'f1': 0.4278758368837492}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Chinese: {'event': {'p': 0.55, 'r': 0.4074074074074074, 'f1': 0.46808510638297873}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Korean: {'event': {'p': 0.9444444444444444, 'r': 0.2698412698412698, 'f1': 0.41975308641975306}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Russian: {'event': {'p': 0.5625, 'r': 0.25, 'f1': 0.34615384615384615}, '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': 0.5620736698499318, 'r': 0.5486018641810919, 'f1': 0.555256064690027}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Eng Test for Chinese: {'event': {'p': 0.4576822916666667, 'r': 0.4017142857142857, 'f1': 0.4278758368837492}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Sample Chinese: {'event': {'p': 0.55, 'r': 0.4074074074074074, 'f1': 0.46808510638297873}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5620736698499318, 'r': 0.5486018641810919, 'f1': 0.555256064690027}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Eng Test for Korean: {'event': {'p': 0.4576822916666667, 'r': 0.4017142857142857, 'f1': 0.4278758368837492}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Sample Korean: {'event': {'p': 0.9444444444444444, 'r': 0.2698412698412698, 'f1': 0.41975308641975306}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5620736698499318, 'r': 0.5486018641810919, 'f1': 0.555256064690027}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Eng Test for Russian: {'event': {'p': 0.4576822916666667, 'r': 0.4017142857142857, 'f1': 0.4278758368837492}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Sample Russian: {'event': {'p': 0.5625, 'r': 0.25, 'f1': 0.34615384615384615}, '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 23:33:49.806064: step: 4/530, loss: 0.3566058278083801
2023-01-22 23:33:50.923484: step: 8/530, loss: 0.4130827784538269
2023-01-22 23:33:52.024832: step: 12/530, loss: 0.3445383608341217
2023-01-22 23:33:53.142505: step: 16/530, loss: 1.0949736833572388
2023-01-22 23:33:54.301918: step: 20/530, loss: 0.4339710474014282
2023-01-22 23:33:55.456029: step: 24/530, loss: 0.42941704392433167
2023-01-22 23:33:56.609695: step: 28/530, loss: 0.13230538368225098
2023-01-22 23:33:57.749672: step: 32/530, loss: 0.5876734256744385
2023-01-22 23:33:58.861289: step: 36/530, loss: 1.8525090217590332
2023-01-22 23:33:59.981066: step: 40/530, loss: 1.193851113319397
2023-01-22 23:34:01.078663: step: 44/530, loss: 0.409809410572052
2023-01-22 23:34:02.208047: step: 48/530, loss: 1.872848629951477
2023-01-22 23:34:03.302078: step: 52/530, loss: 1.0504995584487915
2023-01-22 23:34:04.433056: step: 56/530, loss: 1.1709342002868652
2023-01-22 23:34:05.585179: step: 60/530, loss: 0.2039329558610916
2023-01-22 23:34:06.718293: step: 64/530, loss: 0.4649409353733063
2023-01-22 23:34:07.879918: step: 68/530, loss: 0.29313212633132935
2023-01-22 23:34:08.990465: step: 72/530, loss: 2.413440704345703
2023-01-22 23:34:10.126375: step: 76/530, loss: 0.2135639190673828
2023-01-22 23:34:11.231573: step: 80/530, loss: 1.319648265838623
2023-01-22 23:34:12.378113: step: 84/530, loss: 0.764073371887207
2023-01-22 23:34:13.506223: step: 88/530, loss: 0.8711465001106262
2023-01-22 23:34:14.610572: step: 92/530, loss: 0.2745100259780884
2023-01-22 23:34:15.724246: step: 96/530, loss: 0.3904329836368561
2023-01-22 23:34:16.837144: step: 100/530, loss: 0.20956841111183167
2023-01-22 23:34:17.970234: step: 104/530, loss: 0.5658622980117798
2023-01-22 23:34:19.088779: step: 108/530, loss: 0.30235034227371216
2023-01-22 23:34:20.216473: step: 112/530, loss: 0.3002249598503113
2023-01-22 23:34:21.337222: step: 116/530, loss: 0.6919804811477661
2023-01-22 23:34:22.446350: step: 120/530, loss: 0.6587099432945251
2023-01-22 23:34:23.582394: step: 124/530, loss: 0.3840743601322174
2023-01-22 23:34:24.724619: step: 128/530, loss: 0.5738978385925293
2023-01-22 23:34:25.844267: step: 132/530, loss: 0.7326037287712097
2023-01-22 23:34:26.979814: step: 136/530, loss: 3.655930280685425
2023-01-22 23:34:28.120072: step: 140/530, loss: 0.5548944473266602
2023-01-22 23:34:29.237628: step: 144/530, loss: 0.7589792609214783
2023-01-22 23:34:30.375288: step: 148/530, loss: 0.5321389436721802
2023-01-22 23:34:31.474935: step: 152/530, loss: 1.2859963178634644
2023-01-22 23:34:32.590903: step: 156/530, loss: 1.2933050394058228
2023-01-22 23:34:33.717740: step: 160/530, loss: 0.23951034247875214
2023-01-22 23:34:34.835872: step: 164/530, loss: 7.642308712005615
2023-01-22 23:34:35.944085: step: 168/530, loss: 0.3990862965583801
2023-01-22 23:34:37.068900: step: 172/530, loss: 10.411173820495605
2023-01-22 23:34:38.211688: step: 176/530, loss: 0.4032111167907715
2023-01-22 23:34:39.350501: step: 180/530, loss: 2.958904266357422
2023-01-22 23:34:40.495427: step: 184/530, loss: 0.7786664962768555
2023-01-22 23:34:41.617622: step: 188/530, loss: 1.576459288597107
2023-01-22 23:34:42.727444: step: 192/530, loss: 3.7912445068359375
2023-01-22 23:34:43.825028: step: 196/530, loss: 1.166519045829773
2023-01-22 23:34:44.935942: step: 200/530, loss: 0.9358481168746948
2023-01-22 23:34:46.070398: step: 204/530, loss: 0.36315298080444336
2023-01-22 23:34:47.186730: step: 208/530, loss: 0.2807299494743347
2023-01-22 23:34:48.283107: step: 212/530, loss: 0.5661808252334595
2023-01-22 23:34:49.396454: step: 216/530, loss: 1.0351403951644897
2023-01-22 23:34:50.529186: step: 220/530, loss: 0.40887367725372314
2023-01-22 23:34:51.665431: step: 224/530, loss: 0.671779990196228
2023-01-22 23:34:52.773163: step: 228/530, loss: 0.10804577171802521
2023-01-22 23:34:53.887077: step: 232/530, loss: 0.350119024515152
2023-01-22 23:34:55.045613: step: 236/530, loss: 0.3751036822795868
2023-01-22 23:34:56.190552: step: 240/530, loss: 7.320432186126709
2023-01-22 23:34:57.326279: step: 244/530, loss: 0.41650259494781494
2023-01-22 23:34:58.433687: step: 248/530, loss: 0.4484068751335144
2023-01-22 23:34:59.566361: step: 252/530, loss: 0.6989626884460449
2023-01-22 23:35:00.684272: step: 256/530, loss: 0.5099005103111267
2023-01-22 23:35:01.822856: step: 260/530, loss: 0.90438312292099
2023-01-22 23:35:02.970946: step: 264/530, loss: 0.9393069744110107
2023-01-22 23:35:04.084801: step: 268/530, loss: 0.49958059191703796
2023-01-22 23:35:05.211772: step: 272/530, loss: 1.126135230064392
2023-01-22 23:35:06.330205: step: 276/530, loss: 0.4600154161453247
2023-01-22 23:35:07.447298: step: 280/530, loss: 0.7101521492004395
2023-01-22 23:35:08.576197: step: 284/530, loss: 3.1613001823425293
2023-01-22 23:35:09.723236: step: 288/530, loss: 0.2667194902896881
2023-01-22 23:35:10.861135: step: 292/530, loss: 0.669231653213501
2023-01-22 23:35:11.946050: step: 296/530, loss: 1.1442652940750122
2023-01-22 23:35:13.099730: step: 300/530, loss: 0.16563892364501953
2023-01-22 23:35:14.204904: step: 304/530, loss: 0.6221114993095398
2023-01-22 23:35:15.319119: step: 308/530, loss: 1.3496848344802856
2023-01-22 23:35:16.436270: step: 312/530, loss: 0.448622465133667
2023-01-22 23:35:17.568021: step: 316/530, loss: 2.4301681518554688
2023-01-22 23:35:18.673443: step: 320/530, loss: 2.4049713611602783
2023-01-22 23:35:19.786039: step: 324/530, loss: 0.6371944546699524
2023-01-22 23:35:20.898790: step: 328/530, loss: 1.4824625253677368
2023-01-22 23:35:22.031684: step: 332/530, loss: 0.36765578389167786
2023-01-22 23:35:23.174980: step: 336/530, loss: 3.296193838119507
2023-01-22 23:35:24.321643: step: 340/530, loss: 0.6682201623916626
2023-01-22 23:35:25.448661: step: 344/530, loss: 0.8573024868965149
2023-01-22 23:35:26.575320: step: 348/530, loss: 0.14986252784729004
2023-01-22 23:35:27.684220: step: 352/530, loss: 1.0312409400939941
2023-01-22 23:35:28.804878: step: 356/530, loss: 0.5645427703857422
2023-01-22 23:35:29.916730: step: 360/530, loss: 0.588174045085907
2023-01-22 23:35:31.051712: step: 364/530, loss: 0.23256036639213562
2023-01-22 23:35:32.163224: step: 368/530, loss: 0.5504868030548096
2023-01-22 23:35:33.267413: step: 372/530, loss: 0.16431033611297607
2023-01-22 23:35:34.420932: step: 376/530, loss: 0.3678847849369049
2023-01-22 23:35:35.544583: step: 380/530, loss: 0.7806366682052612
2023-01-22 23:35:36.649946: step: 384/530, loss: 0.11238108575344086
2023-01-22 23:35:37.779517: step: 388/530, loss: 1.022740364074707
2023-01-22 23:35:38.898476: step: 392/530, loss: 0.21687498688697815
2023-01-22 23:35:40.010204: step: 396/530, loss: 0.23517140746116638
2023-01-22 23:35:41.137194: step: 400/530, loss: 1.8847451210021973
2023-01-22 23:35:42.238932: step: 404/530, loss: 0.7515870332717896
2023-01-22 23:35:43.382673: step: 408/530, loss: 0.922863245010376
2023-01-22 23:35:44.508270: step: 412/530, loss: 0.2927433252334595
2023-01-22 23:35:45.632513: step: 416/530, loss: 1.2556331157684326
2023-01-22 23:35:46.753130: step: 420/530, loss: 1.6767101287841797
2023-01-22 23:35:47.857461: step: 424/530, loss: 0.2748070955276489
2023-01-22 23:35:48.959652: step: 428/530, loss: 0.15707266330718994
2023-01-22 23:35:50.110229: step: 432/530, loss: 1.6101641654968262
2023-01-22 23:35:51.204707: step: 436/530, loss: 1.7438379526138306
2023-01-22 23:35:52.322483: step: 440/530, loss: 0.57662034034729
2023-01-22 23:35:53.473539: step: 444/530, loss: 0.5762401819229126
2023-01-22 23:35:54.603968: step: 448/530, loss: 0.1595286875963211
2023-01-22 23:35:55.734639: step: 452/530, loss: 0.30400657653808594
2023-01-22 23:35:56.869062: step: 456/530, loss: 1.4402575492858887
2023-01-22 23:35:57.966000: step: 460/530, loss: 0.2760410010814667
2023-01-22 23:35:59.086217: step: 464/530, loss: 0.7937334179878235
2023-01-22 23:36:00.197387: step: 468/530, loss: 1.8473342657089233
2023-01-22 23:36:01.342649: step: 472/530, loss: 1.0623207092285156
2023-01-22 23:36:02.501500: step: 476/530, loss: 0.625682532787323
2023-01-22 23:36:03.627226: step: 480/530, loss: 0.9409477710723877
2023-01-22 23:36:04.733863: step: 484/530, loss: 0.8266118764877319
2023-01-22 23:36:05.836094: step: 488/530, loss: 0.19022828340530396
2023-01-22 23:36:06.912424: step: 492/530, loss: 1.2855019569396973
2023-01-22 23:36:08.032530: step: 496/530, loss: 0.14154188334941864
2023-01-22 23:36:09.157617: step: 500/530, loss: 0.314447820186615
2023-01-22 23:36:10.311552: step: 504/530, loss: 0.9460071921348572
2023-01-22 23:36:11.434766: step: 508/530, loss: 0.6269891858100891
2023-01-22 23:36:12.573433: step: 512/530, loss: 1.5256773233413696
2023-01-22 23:36:13.708870: step: 516/530, loss: 0.515169084072113
2023-01-22 23:36:14.822086: step: 520/530, loss: 1.4351682662963867
2023-01-22 23:36:15.942853: step: 524/530, loss: 0.6430720090866089
2023-01-22 23:36:17.052458: step: 528/530, loss: 0.9238367080688477
2023-01-22 23:36:18.160665: step: 532/530, loss: 0.38574808835983276
2023-01-22 23:36:19.278423: step: 536/530, loss: 0.3678542971611023
2023-01-22 23:36:20.428680: step: 540/530, loss: 0.2950584888458252
2023-01-22 23:36:21.585094: step: 544/530, loss: 0.9912084341049194
2023-01-22 23:36:22.702194: step: 548/530, loss: 0.49688720703125
2023-01-22 23:36:23.818972: step: 552/530, loss: 0.21537886559963226
2023-01-22 23:36:24.959959: step: 556/530, loss: 0.28884661197662354
2023-01-22 23:36:26.094700: step: 560/530, loss: 0.9238185286521912
2023-01-22 23:36:27.223923: step: 564/530, loss: 0.3266097903251648
2023-01-22 23:36:28.358889: step: 568/530, loss: 0.9632443189620972
2023-01-22 23:36:29.481707: step: 572/530, loss: 0.3264654874801636
2023-01-22 23:36:30.608801: step: 576/530, loss: 1.3379392623901367
2023-01-22 23:36:31.742909: step: 580/530, loss: 0.9528099298477173
2023-01-22 23:36:32.848553: step: 584/530, loss: 0.7141236066818237
2023-01-22 23:36:33.975282: step: 588/530, loss: 0.506945013999939
2023-01-22 23:36:35.076049: step: 592/530, loss: 1.045934796333313
2023-01-22 23:36:36.195898: step: 596/530, loss: 0.34235143661499023
2023-01-22 23:36:37.313792: step: 600/530, loss: 1.2318871021270752
2023-01-22 23:36:38.431065: step: 604/530, loss: 0.4056874215602875
2023-01-22 23:36:39.566564: step: 608/530, loss: 0.413580060005188
2023-01-22 23:36:40.700786: step: 612/530, loss: 0.2892702519893646
2023-01-22 23:36:41.818005: step: 616/530, loss: 6.976891994476318
2023-01-22 23:36:42.941886: step: 620/530, loss: 0.27013903856277466
2023-01-22 23:36:44.080704: step: 624/530, loss: 0.21309155225753784
2023-01-22 23:36:45.213051: step: 628/530, loss: 1.6618425846099854
2023-01-22 23:36:46.331824: step: 632/530, loss: 0.07346592098474503
2023-01-22 23:36:47.469293: step: 636/530, loss: 1.146353006362915
2023-01-22 23:36:48.629875: step: 640/530, loss: 0.20191031694412231
2023-01-22 23:36:49.758407: step: 644/530, loss: 1.1306957006454468
2023-01-22 23:36:50.883155: step: 648/530, loss: 0.23944978415966034
2023-01-22 23:36:52.000899: step: 652/530, loss: 0.7822617888450623
2023-01-22 23:36:53.129368: step: 656/530, loss: 0.7542898654937744
2023-01-22 23:36:54.254488: step: 660/530, loss: 0.17951121926307678
2023-01-22 23:36:55.414068: step: 664/530, loss: 0.44017887115478516
2023-01-22 23:36:56.549507: step: 668/530, loss: 0.6335656642913818
2023-01-22 23:36:57.650005: step: 672/530, loss: 0.22563424706459045
2023-01-22 23:36:58.767957: step: 676/530, loss: 0.09069471806287766
2023-01-22 23:36:59.879781: step: 680/530, loss: 0.3064506947994232
2023-01-22 23:37:01.017650: step: 684/530, loss: 1.5548375844955444
2023-01-22 23:37:02.174322: step: 688/530, loss: 0.16918258368968964
2023-01-22 23:37:03.294375: step: 692/530, loss: 0.2627032995223999
2023-01-22 23:37:04.426591: step: 696/530, loss: 0.2972683906555176
2023-01-22 23:37:05.571157: step: 700/530, loss: 0.8079271912574768
2023-01-22 23:37:06.671869: step: 704/530, loss: 0.21016903221607208
2023-01-22 23:37:07.792764: step: 708/530, loss: 0.5566600561141968
2023-01-22 23:37:08.921219: step: 712/530, loss: 2.9727137088775635
2023-01-22 23:37:10.043477: step: 716/530, loss: 0.8868815898895264
2023-01-22 23:37:11.153573: step: 720/530, loss: 0.6727351546287537
2023-01-22 23:37:12.285338: step: 724/530, loss: 0.41052961349487305
2023-01-22 23:37:13.380586: step: 728/530, loss: 0.15838566422462463
2023-01-22 23:37:14.524036: step: 732/530, loss: 1.1593433618545532
2023-01-22 23:37:15.636728: step: 736/530, loss: 1.0618622303009033
2023-01-22 23:37:16.775753: step: 740/530, loss: 2.73171329498291
2023-01-22 23:37:17.920532: step: 744/530, loss: 0.6454010009765625
2023-01-22 23:37:19.051500: step: 748/530, loss: 0.18166008591651917
2023-01-22 23:37:20.166814: step: 752/530, loss: 0.12550459802150726
2023-01-22 23:37:21.312793: step: 756/530, loss: 0.36531150341033936
2023-01-22 23:37:22.448125: step: 760/530, loss: 0.14516229927539825
2023-01-22 23:37:23.580390: step: 764/530, loss: 0.8672568202018738
2023-01-22 23:37:24.703803: step: 768/530, loss: 0.24750952422618866
2023-01-22 23:37:25.830880: step: 772/530, loss: 0.6645693778991699
2023-01-22 23:37:26.946541: step: 776/530, loss: 0.8205047249794006
2023-01-22 23:37:28.075742: step: 780/530, loss: 0.36898624897003174
2023-01-22 23:37:29.181067: step: 784/530, loss: 0.25122299790382385
2023-01-22 23:37:30.319343: step: 788/530, loss: 1.738002061843872
2023-01-22 23:37:31.448388: step: 792/530, loss: 0.47999632358551025
2023-01-22 23:37:32.617935: step: 796/530, loss: 0.3370702266693115
2023-01-22 23:37:33.755683: step: 800/530, loss: 0.26940375566482544
2023-01-22 23:37:34.875646: step: 804/530, loss: 0.5166050791740417
2023-01-22 23:37:36.003453: step: 808/530, loss: 0.2013622224330902
2023-01-22 23:37:37.141573: step: 812/530, loss: 1.0816948413848877
2023-01-22 23:37:38.254012: step: 816/530, loss: 0.7672421932220459
2023-01-22 23:37:39.389474: step: 820/530, loss: 0.4618135392665863
2023-01-22 23:37:40.497857: step: 824/530, loss: 2.2708003520965576
2023-01-22 23:37:41.603511: step: 828/530, loss: 1.307183027267456
2023-01-22 23:37:42.706013: step: 832/530, loss: 6.292883396148682
2023-01-22 23:37:43.825621: step: 836/530, loss: 0.23577895760536194
2023-01-22 23:37:44.971444: step: 840/530, loss: 1.5875312089920044
2023-01-22 23:37:46.131046: step: 844/530, loss: 0.20029973983764648
2023-01-22 23:37:47.247054: step: 848/530, loss: 0.14980784058570862
2023-01-22 23:37:48.368546: step: 852/530, loss: 0.9651031494140625
2023-01-22 23:37:49.552819: step: 856/530, loss: 0.24396952986717224
2023-01-22 23:37:50.669345: step: 860/530, loss: 1.1361064910888672
2023-01-22 23:37:51.811818: step: 864/530, loss: 0.1594073325395584
2023-01-22 23:37:52.920148: step: 868/530, loss: 0.048084452748298645
2023-01-22 23:37:54.061708: step: 872/530, loss: 0.3147246539592743
2023-01-22 23:37:55.179216: step: 876/530, loss: 0.7524187564849854
2023-01-22 23:37:56.309415: step: 880/530, loss: 0.5513640642166138
2023-01-22 23:37:57.459971: step: 884/530, loss: 2.0146548748016357
2023-01-22 23:37:58.573341: step: 888/530, loss: 0.17148466408252716
2023-01-22 23:37:59.709031: step: 892/530, loss: 0.2688533067703247
2023-01-22 23:38:00.814145: step: 896/530, loss: 0.1653767228126526
2023-01-22 23:38:01.948195: step: 900/530, loss: 0.31855255365371704
2023-01-22 23:38:03.099768: step: 904/530, loss: 0.7202506065368652
2023-01-22 23:38:04.239856: step: 908/530, loss: 0.46812745928764343
2023-01-22 23:38:05.389670: step: 912/530, loss: 1.197242259979248
2023-01-22 23:38:06.510531: step: 916/530, loss: 0.20905455946922302
2023-01-22 23:38:07.661323: step: 920/530, loss: 1.059620976448059
2023-01-22 23:38:08.784625: step: 924/530, loss: 0.14065943658351898
2023-01-22 23:38:09.912463: step: 928/530, loss: 0.7345306873321533
2023-01-22 23:38:11.050355: step: 932/530, loss: 0.2738502621650696
2023-01-22 23:38:12.184359: step: 936/530, loss: 0.9302751421928406
2023-01-22 23:38:13.317263: step: 940/530, loss: 1.3788981437683105
2023-01-22 23:38:14.478827: step: 944/530, loss: 0.2821890711784363
2023-01-22 23:38:15.572613: step: 948/530, loss: 0.26237952709198
2023-01-22 23:38:16.686207: step: 952/530, loss: 0.2008712887763977
2023-01-22 23:38:17.854571: step: 956/530, loss: 0.35614025592803955
2023-01-22 23:38:18.992596: step: 960/530, loss: 0.3039717674255371
2023-01-22 23:38:20.121199: step: 964/530, loss: 0.13932275772094727
2023-01-22 23:38:21.249970: step: 968/530, loss: 0.7154656648635864
2023-01-22 23:38:22.397859: step: 972/530, loss: 0.14186687767505646
2023-01-22 23:38:23.509480: step: 976/530, loss: 0.23681649565696716
2023-01-22 23:38:24.642971: step: 980/530, loss: 0.8003570437431335
2023-01-22 23:38:25.738280: step: 984/530, loss: 0.5427683591842651
2023-01-22 23:38:26.877690: step: 988/530, loss: 0.4901230037212372
2023-01-22 23:38:27.995272: step: 992/530, loss: 0.3047858476638794
2023-01-22 23:38:29.086164: step: 996/530, loss: 0.536281406879425
2023-01-22 23:38:30.252358: step: 1000/530, loss: 1.6701381206512451
2023-01-22 23:38:31.354996: step: 1004/530, loss: 0.19230122864246368
2023-01-22 23:38:32.472759: step: 1008/530, loss: 0.22382239997386932
2023-01-22 23:38:33.581609: step: 1012/530, loss: 0.1477527618408203
2023-01-22 23:38:34.676964: step: 1016/530, loss: 0.5205669403076172
2023-01-22 23:38:35.790846: step: 1020/530, loss: 0.19983796775341034
2023-01-22 23:38:36.918443: step: 1024/530, loss: 1.0030394792556763
2023-01-22 23:38:38.054924: step: 1028/530, loss: 1.1196682453155518
2023-01-22 23:38:39.178218: step: 1032/530, loss: 0.47917041182518005
2023-01-22 23:38:40.299203: step: 1036/530, loss: 1.2454583644866943
2023-01-22 23:38:41.428129: step: 1040/530, loss: 1.2044823169708252
2023-01-22 23:38:42.538820: step: 1044/530, loss: 0.7468950748443604
2023-01-22 23:38:43.647758: step: 1048/530, loss: 0.7009557485580444
2023-01-22 23:38:44.781803: step: 1052/530, loss: 0.2177600860595703
2023-01-22 23:38:45.957742: step: 1056/530, loss: 0.47021159529685974
2023-01-22 23:38:47.093543: step: 1060/530, loss: 6.791146755218506
2023-01-22 23:38:48.215890: step: 1064/530, loss: 1.4735078811645508
2023-01-22 23:38:49.359918: step: 1068/530, loss: 1.6379945278167725
2023-01-22 23:38:50.474579: step: 1072/530, loss: 0.7927103638648987
2023-01-22 23:38:51.583008: step: 1076/530, loss: 1.2895610332489014
2023-01-22 23:38:52.727661: step: 1080/530, loss: 0.5735262036323547
2023-01-22 23:38:53.875919: step: 1084/530, loss: 0.44888830184936523
2023-01-22 23:38:54.994140: step: 1088/530, loss: 0.14473238587379456
2023-01-22 23:38:56.132930: step: 1092/530, loss: 0.1704268604516983
2023-01-22 23:38:57.257037: step: 1096/530, loss: 0.2278425395488739
2023-01-22 23:38:58.353017: step: 1100/530, loss: 0.16720008850097656
2023-01-22 23:38:59.499116: step: 1104/530, loss: 1.661759376525879
2023-01-22 23:39:00.608308: step: 1108/530, loss: 1.5906410217285156
2023-01-22 23:39:01.770212: step: 1112/530, loss: 1.7449020147323608
2023-01-22 23:39:02.878389: step: 1116/530, loss: 0.3117155134677887
2023-01-22 23:39:04.037580: step: 1120/530, loss: 0.16042709350585938
2023-01-22 23:39:05.178960: step: 1124/530, loss: 1.4187798500061035
2023-01-22 23:39:06.335204: step: 1128/530, loss: 1.6446759700775146
2023-01-22 23:39:07.445993: step: 1132/530, loss: 0.4482409358024597
2023-01-22 23:39:08.548701: step: 1136/530, loss: 0.2240900695323944
2023-01-22 23:39:09.659214: step: 1140/530, loss: 0.3433306813240051
2023-01-22 23:39:10.783176: step: 1144/530, loss: 6.444187641143799
2023-01-22 23:39:11.897053: step: 1148/530, loss: 0.23748381435871124
2023-01-22 23:39:13.048785: step: 1152/530, loss: 0.2018374353647232
2023-01-22 23:39:14.195368: step: 1156/530, loss: 0.30465179681777954
2023-01-22 23:39:15.316523: step: 1160/530, loss: 0.5044019818305969
2023-01-22 23:39:16.448865: step: 1164/530, loss: 1.08774733543396
2023-01-22 23:39:17.549428: step: 1168/530, loss: 0.6293907761573792
2023-01-22 23:39:18.662290: step: 1172/530, loss: 0.15773901343345642
2023-01-22 23:39:19.796117: step: 1176/530, loss: 0.20408979058265686
2023-01-22 23:39:20.918083: step: 1180/530, loss: 0.6606953144073486
2023-01-22 23:39:22.037700: step: 1184/530, loss: 0.8491404056549072
2023-01-22 23:39:23.181250: step: 1188/530, loss: 0.9160614013671875
2023-01-22 23:39:24.280400: step: 1192/530, loss: 0.3279854357242584
2023-01-22 23:39:25.403215: step: 1196/530, loss: 0.37932348251342773
2023-01-22 23:39:26.540271: step: 1200/530, loss: 0.19620972871780396
2023-01-22 23:39:27.674721: step: 1204/530, loss: 1.3911794424057007
2023-01-22 23:39:28.822742: step: 1208/530, loss: 0.45618483424186707
2023-01-22 23:39:29.948153: step: 1212/530, loss: 0.5725933909416199
2023-01-22 23:39:31.048586: step: 1216/530, loss: 0.2683318555355072
2023-01-22 23:39:32.162950: step: 1220/530, loss: 0.9543277025222778
2023-01-22 23:39:33.285321: step: 1224/530, loss: 0.19767579436302185
2023-01-22 23:39:34.437837: step: 1228/530, loss: 0.31375494599342346
2023-01-22 23:39:35.574492: step: 1232/530, loss: 0.24461689591407776
2023-01-22 23:39:36.667592: step: 1236/530, loss: 0.8889716267585754
2023-01-22 23:39:37.770245: step: 1240/530, loss: 0.293101966381073
2023-01-22 23:39:38.906083: step: 1244/530, loss: 1.2730488777160645
2023-01-22 23:39:40.050211: step: 1248/530, loss: 0.3960801064968109
2023-01-22 23:39:41.194033: step: 1252/530, loss: 0.2290855497121811
2023-01-22 23:39:42.324756: step: 1256/530, loss: 0.20648488402366638
2023-01-22 23:39:43.438083: step: 1260/530, loss: 0.10601487010717392
2023-01-22 23:39:44.550968: step: 1264/530, loss: 0.536906361579895
2023-01-22 23:39:45.689765: step: 1268/530, loss: 0.3468421995639801
2023-01-22 23:39:46.834897: step: 1272/530, loss: 0.24444961547851562
2023-01-22 23:39:47.935586: step: 1276/530, loss: 0.08144369721412659
2023-01-22 23:39:49.033241: step: 1280/530, loss: 0.5225187540054321
2023-01-22 23:39:50.173915: step: 1284/530, loss: 0.411137193441391
2023-01-22 23:39:51.302735: step: 1288/530, loss: 0.7633897066116333
2023-01-22 23:39:52.424535: step: 1292/530, loss: 0.4491537809371948
2023-01-22 23:39:53.539999: step: 1296/530, loss: 0.5478394627571106
2023-01-22 23:39:54.675204: step: 1300/530, loss: 0.5223590135574341
2023-01-22 23:39:55.803851: step: 1304/530, loss: 0.19366580247879028
2023-01-22 23:39:56.958711: step: 1308/530, loss: 1.493715763092041
2023-01-22 23:39:58.108050: step: 1312/530, loss: 0.7926374673843384
2023-01-22 23:39:59.228356: step: 1316/530, loss: 0.2620566487312317
2023-01-22 23:40:00.366160: step: 1320/530, loss: 0.2101770043373108
2023-01-22 23:40:01.542764: step: 1324/530, loss: 0.36574631929397583
2023-01-22 23:40:02.673500: step: 1328/530, loss: 1.2851864099502563
2023-01-22 23:40:03.799049: step: 1332/530, loss: 0.334254652261734
2023-01-22 23:40:04.912571: step: 1336/530, loss: 0.13697519898414612
2023-01-22 23:40:06.048497: step: 1340/530, loss: 0.9536935687065125
2023-01-22 23:40:07.163871: step: 1344/530, loss: 1.5413018465042114
2023-01-22 23:40:08.354619: step: 1348/530, loss: 0.7670227289199829
2023-01-22 23:40:09.479815: step: 1352/530, loss: 0.2627897262573242
2023-01-22 23:40:10.588968: step: 1356/530, loss: 0.34195834398269653
2023-01-22 23:40:11.689827: step: 1360/530, loss: 0.1234525665640831
2023-01-22 23:40:12.837831: step: 1364/530, loss: 0.24544048309326172
2023-01-22 23:40:13.941535: step: 1368/530, loss: 0.7134837508201599
2023-01-22 23:40:15.054271: step: 1372/530, loss: 0.1867872178554535
2023-01-22 23:40:16.202566: step: 1376/530, loss: 0.20178325474262238
2023-01-22 23:40:17.316503: step: 1380/530, loss: 0.7981695532798767
2023-01-22 23:40:18.465748: step: 1384/530, loss: 0.12979841232299805
2023-01-22 23:40:19.661014: step: 1388/530, loss: 0.8277761340141296
2023-01-22 23:40:20.798251: step: 1392/530, loss: 0.08861684799194336
2023-01-22 23:40:21.937686: step: 1396/530, loss: 0.4481843113899231
2023-01-22 23:40:23.168136: step: 1400/530, loss: 6.67739200592041
2023-01-22 23:40:24.291084: step: 1404/530, loss: 0.3434179425239563
2023-01-22 23:40:25.412336: step: 1408/530, loss: 0.3478502035140991
2023-01-22 23:40:26.512046: step: 1412/530, loss: 0.21788367629051208
2023-01-22 23:40:27.643333: step: 1416/530, loss: 0.4262528717517853
2023-01-22 23:40:28.779378: step: 1420/530, loss: 0.17025771737098694
2023-01-22 23:40:29.895770: step: 1424/530, loss: 0.8870526552200317
2023-01-22 23:40:31.045893: step: 1428/530, loss: 0.9154606461524963
2023-01-22 23:40:32.165429: step: 1432/530, loss: 0.12415867298841476
2023-01-22 23:40:33.287760: step: 1436/530, loss: 0.21688851714134216
2023-01-22 23:40:34.417927: step: 1440/530, loss: 0.7055283188819885
2023-01-22 23:40:35.553188: step: 1444/530, loss: 0.25743627548217773
2023-01-22 23:40:36.687462: step: 1448/530, loss: 1.9429590702056885
2023-01-22 23:40:37.821394: step: 1452/530, loss: 0.21187180280685425
2023-01-22 23:40:38.940210: step: 1456/530, loss: 0.5164682269096375
2023-01-22 23:40:40.037847: step: 1460/530, loss: 0.09471134841442108
2023-01-22 23:40:41.148837: step: 1464/530, loss: 2.2872867584228516
2023-01-22 23:40:42.269918: step: 1468/530, loss: 0.5719640851020813
2023-01-22 23:40:43.395816: step: 1472/530, loss: 1.6966402530670166
2023-01-22 23:40:44.504352: step: 1476/530, loss: 1.3545782566070557
2023-01-22 23:40:45.621795: step: 1480/530, loss: 0.636709451675415
2023-01-22 23:40:46.776020: step: 1484/530, loss: 0.7344902157783508
2023-01-22 23:40:47.908514: step: 1488/530, loss: 0.48277369141578674
2023-01-22 23:40:49.038602: step: 1492/530, loss: 0.24266642332077026
2023-01-22 23:40:50.162345: step: 1496/530, loss: 0.3556075096130371
2023-01-22 23:40:51.272063: step: 1500/530, loss: 0.23602394759655
2023-01-22 23:40:52.388012: step: 1504/530, loss: 1.1088502407073975
2023-01-22 23:40:53.515558: step: 1508/530, loss: 1.6270503997802734
2023-01-22 23:40:54.655815: step: 1512/530, loss: 0.0618162639439106
2023-01-22 23:40:55.768747: step: 1516/530, loss: 0.0733531042933464
2023-01-22 23:40:56.903470: step: 1520/530, loss: 1.8814818859100342
2023-01-22 23:40:58.030396: step: 1524/530, loss: 7.419620990753174
2023-01-22 23:40:59.185130: step: 1528/530, loss: 1.6803817749023438
2023-01-22 23:41:00.295312: step: 1532/530, loss: 0.1288263350725174
2023-01-22 23:41:01.435729: step: 1536/530, loss: 0.8849203586578369
2023-01-22 23:41:02.591349: step: 1540/530, loss: 0.36991938948631287
2023-01-22 23:41:03.722891: step: 1544/530, loss: 0.1908399611711502
2023-01-22 23:41:04.843719: step: 1548/530, loss: 0.19451384246349335
2023-01-22 23:41:05.974533: step: 1552/530, loss: 0.5053917765617371
2023-01-22 23:41:07.079820: step: 1556/530, loss: 1.2861690521240234
2023-01-22 23:41:08.232522: step: 1560/530, loss: 0.3923514485359192
2023-01-22 23:41:09.356836: step: 1564/530, loss: 0.6893815994262695
2023-01-22 23:41:10.482580: step: 1568/530, loss: 0.6902713775634766
2023-01-22 23:41:11.622594: step: 1572/530, loss: 0.4286918640136719
2023-01-22 23:41:12.751959: step: 1576/530, loss: 0.07515612244606018
2023-01-22 23:41:13.874035: step: 1580/530, loss: 0.39479684829711914
2023-01-22 23:41:14.998016: step: 1584/530, loss: 0.6350180506706238
2023-01-22 23:41:16.125427: step: 1588/530, loss: 0.2779053747653961
2023-01-22 23:41:17.232992: step: 1592/530, loss: 0.13090582191944122
2023-01-22 23:41:18.356814: step: 1596/530, loss: 0.9883217811584473
2023-01-22 23:41:19.485001: step: 1600/530, loss: 0.09409274905920029
2023-01-22 23:41:20.595173: step: 1604/530, loss: 0.2982763648033142
2023-01-22 23:41:21.696762: step: 1608/530, loss: 0.2672467827796936
2023-01-22 23:41:22.858939: step: 1612/530, loss: 1.5939741134643555
2023-01-22 23:41:23.978345: step: 1616/530, loss: 0.8672860860824585
2023-01-22 23:41:25.083978: step: 1620/530, loss: 0.8958872556686401
2023-01-22 23:41:26.190489: step: 1624/530, loss: 0.0984601080417633
2023-01-22 23:41:27.314053: step: 1628/530, loss: 2.789956569671631
2023-01-22 23:41:28.449421: step: 1632/530, loss: 0.2605394124984741
2023-01-22 23:41:29.561892: step: 1636/530, loss: 0.15066084265708923
2023-01-22 23:41:30.686200: step: 1640/530, loss: 1.1546671390533447
2023-01-22 23:41:31.805148: step: 1644/530, loss: 0.2743123173713684
2023-01-22 23:41:32.944061: step: 1648/530, loss: 0.8997188210487366
2023-01-22 23:41:34.092978: step: 1652/530, loss: 0.24478493630886078
2023-01-22 23:41:35.222690: step: 1656/530, loss: 0.8704109191894531
2023-01-22 23:41:36.341264: step: 1660/530, loss: 1.2081955671310425
2023-01-22 23:41:37.452950: step: 1664/530, loss: 0.16584762930870056
2023-01-22 23:41:38.594442: step: 1668/530, loss: 0.42290323972702026
2023-01-22 23:41:39.720794: step: 1672/530, loss: 1.1843347549438477
2023-01-22 23:41:40.856154: step: 1676/530, loss: 0.18201667070388794
2023-01-22 23:41:42.001263: step: 1680/530, loss: 0.1348247528076172
2023-01-22 23:41:43.146576: step: 1684/530, loss: 0.3566984236240387
2023-01-22 23:41:44.286652: step: 1688/530, loss: 2.0272209644317627
2023-01-22 23:41:45.432730: step: 1692/530, loss: 0.1784757673740387
2023-01-22 23:41:46.540363: step: 1696/530, loss: 1.0046180486679077
2023-01-22 23:41:47.667857: step: 1700/530, loss: 0.30544471740722656
2023-01-22 23:41:48.785755: step: 1704/530, loss: 0.2551521360874176
2023-01-22 23:41:49.915136: step: 1708/530, loss: 1.7154011726379395
2023-01-22 23:41:51.040995: step: 1712/530, loss: 0.2702065706253052
2023-01-22 23:41:52.159660: step: 1716/530, loss: 0.194538414478302
2023-01-22 23:41:53.298442: step: 1720/530, loss: 0.5195850133895874
2023-01-22 23:41:54.437332: step: 1724/530, loss: 0.5444344282150269
2023-01-22 23:41:55.551749: step: 1728/530, loss: 0.45696118474006653
2023-01-22 23:41:56.704673: step: 1732/530, loss: 0.6724588871002197
2023-01-22 23:41:57.838132: step: 1736/530, loss: 0.6436266899108887
2023-01-22 23:41:58.980737: step: 1740/530, loss: 0.06118364259600639
2023-01-22 23:42:00.100386: step: 1744/530, loss: 0.4872073531150818
2023-01-22 23:42:01.232126: step: 1748/530, loss: 0.5396503806114197
2023-01-22 23:42:02.352290: step: 1752/530, loss: 0.13950863480567932
2023-01-22 23:42:03.456731: step: 1756/530, loss: 1.0801059007644653
2023-01-22 23:42:04.589737: step: 1760/530, loss: 1.0713865756988525
2023-01-22 23:42:05.743934: step: 1764/530, loss: 1.0806747674942017
2023-01-22 23:42:06.864091: step: 1768/530, loss: 0.27925539016723633
2023-01-22 23:42:07.979880: step: 1772/530, loss: 0.8207964301109314
2023-01-22 23:42:09.084542: step: 1776/530, loss: 0.07673411071300507
2023-01-22 23:42:10.200314: step: 1780/530, loss: 1.3512283563613892
2023-01-22 23:42:11.323965: step: 1784/530, loss: 1.031259536743164
2023-01-22 23:42:12.454482: step: 1788/530, loss: 0.7698662281036377
2023-01-22 23:42:13.560692: step: 1792/530, loss: 0.2016758918762207
2023-01-22 23:42:14.673775: step: 1796/530, loss: 0.8086709976196289
2023-01-22 23:42:15.799697: step: 1800/530, loss: 0.2249886691570282
2023-01-22 23:42:16.932510: step: 1804/530, loss: 0.7650534510612488
2023-01-22 23:42:18.038162: step: 1808/530, loss: 0.15870437026023865
2023-01-22 23:42:19.154862: step: 1812/530, loss: 0.7360981702804565
2023-01-22 23:42:20.284524: step: 1816/530, loss: 6.378812789916992
2023-01-22 23:42:21.405873: step: 1820/530, loss: 0.358445942401886
2023-01-22 23:42:22.567153: step: 1824/530, loss: 0.812828779220581
2023-01-22 23:42:23.717696: step: 1828/530, loss: 1.0967357158660889
2023-01-22 23:42:24.853391: step: 1832/530, loss: 0.40618619322776794
2023-01-22 23:42:25.992427: step: 1836/530, loss: 2.38862681388855
2023-01-22 23:42:27.131100: step: 1840/530, loss: 2.1479198932647705
2023-01-22 23:42:28.262874: step: 1844/530, loss: 0.85140061378479
2023-01-22 23:42:29.380376: step: 1848/530, loss: 0.7551918625831604
2023-01-22 23:42:30.483371: step: 1852/530, loss: 0.5966693162918091
2023-01-22 23:42:31.633176: step: 1856/530, loss: 2.546915054321289
2023-01-22 23:42:32.752873: step: 1860/530, loss: 1.9478868246078491
2023-01-22 23:42:33.930567: step: 1864/530, loss: 0.26968422532081604
2023-01-22 23:42:35.059633: step: 1868/530, loss: 0.7457396984100342
2023-01-22 23:42:36.157753: step: 1872/530, loss: 0.7320360541343689
2023-01-22 23:42:37.277760: step: 1876/530, loss: 0.14077992737293243
2023-01-22 23:42:38.401266: step: 1880/530, loss: 0.09402614086866379
2023-01-22 23:42:39.505881: step: 1884/530, loss: 0.1349850594997406
2023-01-22 23:42:40.615589: step: 1888/530, loss: 0.693934977054596
2023-01-22 23:42:41.743720: step: 1892/530, loss: 0.30236172676086426
2023-01-22 23:42:42.882051: step: 1896/530, loss: 1.1149325370788574
2023-01-22 23:42:43.995082: step: 1900/530, loss: 0.27901583909988403
2023-01-22 23:42:45.122858: step: 1904/530, loss: 0.19165612757205963
2023-01-22 23:42:46.251657: step: 1908/530, loss: 0.06629457324743271
2023-01-22 23:42:47.375752: step: 1912/530, loss: 0.8024194240570068
2023-01-22 23:42:48.490960: step: 1916/530, loss: 0.7966238260269165
2023-01-22 23:42:49.606873: step: 1920/530, loss: 0.06974106281995773
2023-01-22 23:42:50.726988: step: 1924/530, loss: 0.7855917811393738
2023-01-22 23:42:51.829623: step: 1928/530, loss: 0.7097975015640259
2023-01-22 23:42:52.956541: step: 1932/530, loss: 0.6111996173858643
2023-01-22 23:42:54.080176: step: 1936/530, loss: 2.051295757293701
2023-01-22 23:42:55.186431: step: 1940/530, loss: 0.26898786425590515
2023-01-22 23:42:56.347684: step: 1944/530, loss: 1.0412803888320923
2023-01-22 23:42:57.446177: step: 1948/530, loss: 0.9236189126968384
2023-01-22 23:42:58.545367: step: 1952/530, loss: 0.5727674961090088
2023-01-22 23:42:59.656947: step: 1956/530, loss: 0.08463945984840393
2023-01-22 23:43:00.796959: step: 1960/530, loss: 0.2254650592803955
2023-01-22 23:43:01.909658: step: 1964/530, loss: 0.19339652359485626
2023-01-22 23:43:03.028567: step: 1968/530, loss: 0.7773427963256836
2023-01-22 23:43:04.149385: step: 1972/530, loss: 0.14954176545143127
2023-01-22 23:43:05.282883: step: 1976/530, loss: 0.5910944938659668
2023-01-22 23:43:06.406438: step: 1980/530, loss: 0.22116994857788086
2023-01-22 23:43:07.534836: step: 1984/530, loss: 0.1570582389831543
2023-01-22 23:43:08.672573: step: 1988/530, loss: 0.07202224433422089
2023-01-22 23:43:09.804693: step: 1992/530, loss: 0.14000225067138672
2023-01-22 23:43:10.907931: step: 1996/530, loss: 0.4157206118106842
2023-01-22 23:43:11.998334: step: 2000/530, loss: 0.6648862361907959
2023-01-22 23:43:13.109239: step: 2004/530, loss: 0.286368727684021
2023-01-22 23:43:14.225251: step: 2008/530, loss: 0.15232335031032562
2023-01-22 23:43:15.354266: step: 2012/530, loss: 0.6181201934814453
2023-01-22 23:43:16.477072: step: 2016/530, loss: 0.09782581776380539
2023-01-22 23:43:17.571376: step: 2020/530, loss: 0.17981024086475372
2023-01-22 23:43:18.726682: step: 2024/530, loss: 1.29769766330719
2023-01-22 23:43:19.851783: step: 2028/530, loss: 0.22478684782981873
2023-01-22 23:43:20.979530: step: 2032/530, loss: 0.07622937858104706
2023-01-22 23:43:22.106753: step: 2036/530, loss: 0.1252705603837967
2023-01-22 23:43:23.254858: step: 2040/530, loss: 0.3433162569999695
2023-01-22 23:43:24.391158: step: 2044/530, loss: 0.19063769280910492
2023-01-22 23:43:25.531703: step: 2048/530, loss: 0.22122856974601746
2023-01-22 23:43:26.660901: step: 2052/530, loss: 0.14650268852710724
2023-01-22 23:43:27.782398: step: 2056/530, loss: 1.1723874807357788
2023-01-22 23:43:28.889061: step: 2060/530, loss: 0.198953777551651
2023-01-22 23:43:30.021901: step: 2064/530, loss: 1.712605595588684
2023-01-22 23:43:31.171829: step: 2068/530, loss: 0.22792960703372955
2023-01-22 23:43:32.308488: step: 2072/530, loss: 0.6539992094039917
2023-01-22 23:43:33.418657: step: 2076/530, loss: 0.7947683930397034
2023-01-22 23:43:34.546476: step: 2080/530, loss: 1.8783246278762817
2023-01-22 23:43:35.683543: step: 2084/530, loss: 0.20687751471996307
2023-01-22 23:43:36.803940: step: 2088/530, loss: 0.1786704957485199
2023-01-22 23:43:37.942686: step: 2092/530, loss: 1.5413072109222412
2023-01-22 23:43:39.092288: step: 2096/530, loss: 0.2419353425502777
2023-01-22 23:43:40.217368: step: 2100/530, loss: 0.17813606560230255
2023-01-22 23:43:41.349048: step: 2104/530, loss: 0.14032870531082153
2023-01-22 23:43:42.478910: step: 2108/530, loss: 0.0925634428858757
2023-01-22 23:43:43.604732: step: 2112/530, loss: 0.45660123229026794
2023-01-22 23:43:44.736404: step: 2116/530, loss: 0.2844177484512329
2023-01-22 23:43:45.879043: step: 2120/530, loss: 0.36299824714660645
==================================================
Loss: 0.794
--------------------
Dev: {'event': {'p': 0.6436170212765957, 'r': 0.644474034620506, 'f1': 0.6440452428476381}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Test: {'event': {'p': 0.6642728904847397, 'r': 0.6342857142857142, 'f1': 0.6489330605086231}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Chinese: {'event': {'p': 0.5932203389830508, 'r': 0.6481481481481481, 'f1': 0.6194690265486725}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Korean: {'event': {'p': 0.75, 'r': 0.3333333333333333, 'f1': 0.46153846153846156}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Russian: {'event': {'p': 0.64, 'r': 0.4444444444444444, 'f1': 0.5245901639344263}, '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': 0.6436170212765957, 'r': 0.644474034620506, 'f1': 0.6440452428476381}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Eng Test for Chinese: {'event': {'p': 0.6642728904847397, 'r': 0.6342857142857142, 'f1': 0.6489330605086231}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Sample Chinese: {'event': {'p': 0.5932203389830508, 'r': 0.6481481481481481, 'f1': 0.6194690265486725}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6436170212765957, 'r': 0.644474034620506, 'f1': 0.6440452428476381}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Eng Test for Korean: {'event': {'p': 0.6642728904847397, 'r': 0.6342857142857142, 'f1': 0.6489330605086231}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Sample Korean: {'event': {'p': 0.75, 'r': 0.3333333333333333, 'f1': 0.46153846153846156}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6436170212765957, 'r': 0.644474034620506, 'f1': 0.6440452428476381}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Eng Test for Russian: {'event': {'p': 0.6642728904847397, 'r': 0.6342857142857142, 'f1': 0.6489330605086231}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Sample Russian: {'event': {'p': 0.64, 'r': 0.4444444444444444, 'f1': 0.5245901639344263}, '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 23:44:47.272265: step: 4/530, loss: 0.2549871802330017
2023-01-22 23:44:48.455281: step: 8/530, loss: 1.7303869724273682
2023-01-22 23:44:49.563774: step: 12/530, loss: 1.153725266456604
2023-01-22 23:44:50.693578: step: 16/530, loss: 0.5541088581085205
2023-01-22 23:44:51.817880: step: 20/530, loss: 0.07219181209802628
2023-01-22 23:44:52.939242: step: 24/530, loss: 0.11997681111097336
2023-01-22 23:44:54.079452: step: 28/530, loss: 0.6570150256156921
2023-01-22 23:44:55.202835: step: 32/530, loss: 1.6036723852157593
2023-01-22 23:44:56.357039: step: 36/530, loss: 0.1650841385126114
2023-01-22 23:44:57.493995: step: 40/530, loss: 0.8205879330635071
2023-01-22 23:44:58.635333: step: 44/530, loss: 1.344017505645752
2023-01-22 23:44:59.739214: step: 48/530, loss: 0.4052448272705078
2023-01-22 23:45:00.876572: step: 52/530, loss: 0.28544116020202637
2023-01-22 23:45:02.002711: step: 56/530, loss: 0.22886408865451813
2023-01-22 23:45:03.138033: step: 60/530, loss: 0.12092933803796768
2023-01-22 23:45:04.246585: step: 64/530, loss: 0.1983252614736557
2023-01-22 23:45:05.373540: step: 68/530, loss: 1.4818247556686401
2023-01-22 23:45:06.465715: step: 72/530, loss: 0.15928326547145844
2023-01-22 23:45:07.569240: step: 76/530, loss: 0.3694389760494232
2023-01-22 23:45:08.682464: step: 80/530, loss: 0.4056609869003296
2023-01-22 23:45:09.806354: step: 84/530, loss: 0.26151764392852783
2023-01-22 23:45:10.899275: step: 88/530, loss: 0.1126493439078331
2023-01-22 23:45:12.008221: step: 92/530, loss: 0.2248607724905014
2023-01-22 23:45:13.102963: step: 96/530, loss: 0.33363789319992065
2023-01-22 23:45:14.236820: step: 100/530, loss: 0.11394501477479935
2023-01-22 23:45:15.364570: step: 104/530, loss: 0.18549376726150513
2023-01-22 23:45:16.494705: step: 108/530, loss: 0.7846215963363647
2023-01-22 23:45:17.601572: step: 112/530, loss: 1.0464065074920654
2023-01-22 23:45:18.715156: step: 116/530, loss: 0.18868285417556763
2023-01-22 23:45:19.817854: step: 120/530, loss: 0.7378286123275757
2023-01-22 23:45:20.935418: step: 124/530, loss: 0.3399714529514313
2023-01-22 23:45:22.045960: step: 128/530, loss: 0.23601636290550232
2023-01-22 23:45:23.187357: step: 132/530, loss: 0.16574101150035858
2023-01-22 23:45:24.298569: step: 136/530, loss: 0.9829902648925781
2023-01-22 23:45:25.403577: step: 140/530, loss: 0.7383224368095398
2023-01-22 23:45:26.556748: step: 144/530, loss: 1.2845613956451416
2023-01-22 23:45:27.697665: step: 148/530, loss: 0.938347578048706
2023-01-22 23:45:28.818734: step: 152/530, loss: 0.18910598754882812
2023-01-22 23:45:29.934493: step: 156/530, loss: 0.05874957889318466
2023-01-22 23:45:31.082773: step: 160/530, loss: 0.9890762567520142
2023-01-22 23:45:32.224141: step: 164/530, loss: 1.5207116603851318
2023-01-22 23:45:33.369704: step: 168/530, loss: 0.5067645907402039
2023-01-22 23:45:34.502113: step: 172/530, loss: 0.6130468845367432
2023-01-22 23:45:35.646571: step: 176/530, loss: 0.08087359368801117
2023-01-22 23:45:36.759732: step: 180/530, loss: 0.4731321632862091
2023-01-22 23:45:37.908200: step: 184/530, loss: 0.2755403518676758
2023-01-22 23:45:39.034777: step: 188/530, loss: 0.3389209806919098
2023-01-22 23:45:40.186659: step: 192/530, loss: 0.247080996632576
2023-01-22 23:45:41.315858: step: 196/530, loss: 0.1220521479845047
2023-01-22 23:45:42.465486: step: 200/530, loss: 0.7505062222480774
2023-01-22 23:45:43.588704: step: 204/530, loss: 0.13835224509239197
2023-01-22 23:45:44.688606: step: 208/530, loss: 0.08297586441040039
2023-01-22 23:45:45.836465: step: 212/530, loss: 0.47152671217918396
2023-01-22 23:45:46.994819: step: 216/530, loss: 0.4521659016609192
2023-01-22 23:45:48.101855: step: 220/530, loss: 0.058286383748054504
2023-01-22 23:45:49.227620: step: 224/530, loss: 0.569999635219574
2023-01-22 23:45:50.332883: step: 228/530, loss: 0.1763368546962738
2023-01-22 23:45:51.485865: step: 232/530, loss: 0.7132700681686401
2023-01-22 23:45:52.597735: step: 236/530, loss: 0.7418447732925415
2023-01-22 23:45:53.737243: step: 240/530, loss: 0.151699498295784
2023-01-22 23:45:54.860743: step: 244/530, loss: 0.21459513902664185
2023-01-22 23:45:56.010484: step: 248/530, loss: 0.1821517050266266
2023-01-22 23:45:57.131384: step: 252/530, loss: 0.4466073513031006
2023-01-22 23:45:58.244656: step: 256/530, loss: 0.161688432097435
2023-01-22 23:45:59.372095: step: 260/530, loss: 0.8341001868247986
2023-01-22 23:46:00.502111: step: 264/530, loss: 0.5594701766967773
2023-01-22 23:46:01.612645: step: 268/530, loss: 0.8592886924743652
2023-01-22 23:46:02.762716: step: 272/530, loss: 0.36857423186302185
2023-01-22 23:46:03.891101: step: 276/530, loss: 0.11693410575389862
2023-01-22 23:46:05.003634: step: 280/530, loss: 0.4446922838687897
2023-01-22 23:46:06.118348: step: 284/530, loss: 0.6469581723213196
2023-01-22 23:46:07.247178: step: 288/530, loss: 0.2586190104484558
2023-01-22 23:46:08.387499: step: 292/530, loss: 0.4812266528606415
2023-01-22 23:46:09.506496: step: 296/530, loss: 0.7611778974533081
2023-01-22 23:46:10.623296: step: 300/530, loss: 1.189784049987793
2023-01-22 23:46:11.733664: step: 304/530, loss: 0.5434539318084717
2023-01-22 23:46:12.858196: step: 308/530, loss: 0.6020355224609375
2023-01-22 23:46:13.980789: step: 312/530, loss: 1.158416748046875
2023-01-22 23:46:15.136019: step: 316/530, loss: 0.16148415207862854
2023-01-22 23:46:16.263413: step: 320/530, loss: 0.40499603748321533
2023-01-22 23:46:17.355942: step: 324/530, loss: 0.12176743149757385
2023-01-22 23:46:18.475884: step: 328/530, loss: 1.566463828086853
2023-01-22 23:46:19.596759: step: 332/530, loss: 0.18461808562278748
2023-01-22 23:46:20.720492: step: 336/530, loss: 0.6959921717643738
2023-01-22 23:46:21.868095: step: 340/530, loss: 0.8371450304985046
2023-01-22 23:46:22.988508: step: 344/530, loss: 1.0187971591949463
2023-01-22 23:46:24.152797: step: 348/530, loss: 0.3670177459716797
2023-01-22 23:46:25.269500: step: 352/530, loss: 0.41727352142333984
2023-01-22 23:46:26.390294: step: 356/530, loss: 0.17567510902881622
2023-01-22 23:46:27.510839: step: 360/530, loss: 0.757550835609436
2023-01-22 23:46:28.630391: step: 364/530, loss: 0.06790180504322052
2023-01-22 23:46:29.735634: step: 368/530, loss: 0.13106070458889008
2023-01-22 23:46:30.845520: step: 372/530, loss: 0.1412394940853119
2023-01-22 23:46:31.982272: step: 376/530, loss: 0.2952960133552551
2023-01-22 23:46:33.133923: step: 380/530, loss: 0.6557536125183105
2023-01-22 23:46:34.268971: step: 384/530, loss: 0.9003782868385315
2023-01-22 23:46:35.432470: step: 388/530, loss: 0.099893718957901
2023-01-22 23:46:36.569437: step: 392/530, loss: 0.1825265884399414
2023-01-22 23:46:37.704714: step: 396/530, loss: 0.2066102921962738
2023-01-22 23:46:38.826623: step: 400/530, loss: 0.43238189816474915
2023-01-22 23:46:39.970541: step: 404/530, loss: 0.14483137428760529
2023-01-22 23:46:41.094335: step: 408/530, loss: 0.39697813987731934
2023-01-22 23:46:42.233926: step: 412/530, loss: 0.7833611369132996
2023-01-22 23:46:43.354694: step: 416/530, loss: 0.8130244016647339
2023-01-22 23:46:44.498317: step: 420/530, loss: 0.26998642086982727
2023-01-22 23:46:45.624650: step: 424/530, loss: 0.45044320821762085
2023-01-22 23:46:46.754169: step: 428/530, loss: 1.0882318019866943
2023-01-22 23:46:47.879707: step: 432/530, loss: 0.10300693660974503
2023-01-22 23:46:48.981384: step: 436/530, loss: 0.41531428694725037
2023-01-22 23:46:50.097306: step: 440/530, loss: 0.027932167053222656
2023-01-22 23:46:51.217796: step: 444/530, loss: 0.20370645821094513
2023-01-22 23:46:52.335765: step: 448/530, loss: 0.9263323545455933
2023-01-22 23:46:53.513769: step: 452/530, loss: 0.445218563079834
2023-01-22 23:46:54.622572: step: 456/530, loss: 0.7113152146339417
2023-01-22 23:46:55.754530: step: 460/530, loss: 0.5523746609687805
2023-01-22 23:46:56.867600: step: 464/530, loss: 0.21276822686195374
2023-01-22 23:46:57.961201: step: 468/530, loss: 0.15584564208984375
2023-01-22 23:46:59.074169: step: 472/530, loss: 0.20984001457691193
2023-01-22 23:47:00.187640: step: 476/530, loss: 0.2754071354866028
2023-01-22 23:47:01.312354: step: 480/530, loss: 0.17370755970478058
2023-01-22 23:47:02.435628: step: 484/530, loss: 0.176835834980011
2023-01-22 23:47:03.566157: step: 488/530, loss: 0.2124270498752594
2023-01-22 23:47:04.709982: step: 492/530, loss: 0.1323350965976715
2023-01-22 23:47:05.818036: step: 496/530, loss: 1.0380834341049194
2023-01-22 23:47:06.933977: step: 500/530, loss: 6.5939741134643555
2023-01-22 23:47:08.050795: step: 504/530, loss: 0.21367189288139343
2023-01-22 23:47:09.190827: step: 508/530, loss: 0.6519832015037537
2023-01-22 23:47:10.325916: step: 512/530, loss: 0.3971001207828522
2023-01-22 23:47:11.441894: step: 516/530, loss: 0.2099950760602951
2023-01-22 23:47:12.567644: step: 520/530, loss: 0.6482779383659363
2023-01-22 23:47:13.681595: step: 524/530, loss: 0.036852024495601654
2023-01-22 23:47:14.832618: step: 528/530, loss: 1.981764793395996
2023-01-22 23:47:16.025021: step: 532/530, loss: 0.2899623513221741
2023-01-22 23:47:17.164661: step: 536/530, loss: 0.7923697233200073
2023-01-22 23:47:18.302809: step: 540/530, loss: 0.36124134063720703
2023-01-22 23:47:19.404131: step: 544/530, loss: 0.16855287551879883
2023-01-22 23:47:20.514174: step: 548/530, loss: 0.6073692440986633
2023-01-22 23:47:21.647754: step: 552/530, loss: 1.2224150896072388
2023-01-22 23:47:22.737688: step: 556/530, loss: 1.0469428300857544
2023-01-22 23:47:23.887658: step: 560/530, loss: 0.1363590508699417
2023-01-22 23:47:25.020210: step: 564/530, loss: 0.3859992027282715
2023-01-22 23:47:26.159344: step: 568/530, loss: 0.14113959670066833
2023-01-22 23:47:27.292719: step: 572/530, loss: 0.3557610511779785
2023-01-22 23:47:28.416575: step: 576/530, loss: 0.09070573002099991
2023-01-22 23:47:29.568214: step: 580/530, loss: 0.08663950115442276
2023-01-22 23:47:30.688212: step: 584/530, loss: 0.3012918531894684
2023-01-22 23:47:31.817779: step: 588/530, loss: 0.7022686004638672
2023-01-22 23:47:32.971176: step: 592/530, loss: 0.7342543601989746
2023-01-22 23:47:34.111497: step: 596/530, loss: 2.139040470123291
2023-01-22 23:47:35.214951: step: 600/530, loss: 0.9770023822784424
2023-01-22 23:47:36.328992: step: 604/530, loss: 0.20111560821533203
2023-01-22 23:47:37.456242: step: 608/530, loss: 1.280655860900879
2023-01-22 23:47:38.582652: step: 612/530, loss: 0.22764426469802856
2023-01-22 23:47:39.690032: step: 616/530, loss: 0.5092660188674927
2023-01-22 23:47:40.823483: step: 620/530, loss: 0.08441576361656189
2023-01-22 23:47:41.944805: step: 624/530, loss: 0.41629570722579956
2023-01-22 23:47:43.059445: step: 628/530, loss: 1.22637140750885
2023-01-22 23:47:44.183796: step: 632/530, loss: 1.4531912803649902
2023-01-22 23:47:45.314769: step: 636/530, loss: 0.45081931352615356
2023-01-22 23:47:46.459038: step: 640/530, loss: 0.39078283309936523
2023-01-22 23:47:47.573604: step: 644/530, loss: 0.3018566966056824
2023-01-22 23:47:48.691294: step: 648/530, loss: 0.829871654510498
2023-01-22 23:47:49.828127: step: 652/530, loss: 0.5401266813278198
2023-01-22 23:47:50.953562: step: 656/530, loss: 6.142358303070068
2023-01-22 23:47:52.052491: step: 660/530, loss: 0.8059202432632446
2023-01-22 23:47:53.173229: step: 664/530, loss: 0.14764243364334106
2023-01-22 23:47:54.322301: step: 668/530, loss: 0.2622183859348297
2023-01-22 23:47:55.433460: step: 672/530, loss: 7.544880390167236
2023-01-22 23:47:56.551872: step: 676/530, loss: 0.8880947828292847
2023-01-22 23:47:57.682708: step: 680/530, loss: 0.14731311798095703
2023-01-22 23:47:58.789517: step: 684/530, loss: 0.5059198141098022
2023-01-22 23:47:59.905284: step: 688/530, loss: 0.26448696851730347
2023-01-22 23:48:01.042500: step: 692/530, loss: 1.2483859062194824
2023-01-22 23:48:02.156347: step: 696/530, loss: 0.08068018406629562
2023-01-22 23:48:03.281944: step: 700/530, loss: 0.14242082834243774
2023-01-22 23:48:04.415723: step: 704/530, loss: 0.32842761278152466
2023-01-22 23:48:05.528832: step: 708/530, loss: 0.08093119412660599
2023-01-22 23:48:06.650432: step: 712/530, loss: 0.03687271848320961
2023-01-22 23:48:07.766015: step: 716/530, loss: 0.18993185460567474
2023-01-22 23:48:08.878919: step: 720/530, loss: 0.37675780057907104
2023-01-22 23:48:10.012608: step: 724/530, loss: 0.24144478142261505
2023-01-22 23:48:11.111117: step: 728/530, loss: 1.2489759922027588
2023-01-22 23:48:12.222613: step: 732/530, loss: 0.64762943983078
2023-01-22 23:48:13.350105: step: 736/530, loss: 0.22054243087768555
2023-01-22 23:48:14.457782: step: 740/530, loss: 0.7320102453231812
2023-01-22 23:48:15.549927: step: 744/530, loss: 0.18115448951721191
2023-01-22 23:48:16.651233: step: 748/530, loss: 0.18425212800502777
2023-01-22 23:48:17.780628: step: 752/530, loss: 0.1290455311536789
2023-01-22 23:48:18.894654: step: 756/530, loss: 0.22215071320533752
2023-01-22 23:48:19.976776: step: 760/530, loss: 0.9888249039649963
2023-01-22 23:48:21.063057: step: 764/530, loss: 0.12373016029596329
2023-01-22 23:48:22.201007: step: 768/530, loss: 0.15127182006835938
2023-01-22 23:48:23.332232: step: 772/530, loss: 0.3780156970024109
2023-01-22 23:48:24.475767: step: 776/530, loss: 0.17230844497680664
2023-01-22 23:48:25.604765: step: 780/530, loss: 0.800753116607666
2023-01-22 23:48:26.745187: step: 784/530, loss: 1.518019676208496
2023-01-22 23:48:27.886207: step: 788/530, loss: 0.1791977435350418
2023-01-22 23:48:29.007480: step: 792/530, loss: 0.3912786543369293
2023-01-22 23:48:30.159017: step: 796/530, loss: 0.3245595097541809
2023-01-22 23:48:31.256152: step: 800/530, loss: 0.7361921072006226
2023-01-22 23:48:32.404592: step: 804/530, loss: 0.3055207133293152
2023-01-22 23:48:33.536267: step: 808/530, loss: 0.2662474513053894
2023-01-22 23:48:34.646009: step: 812/530, loss: 0.05306663364171982
2023-01-22 23:48:35.763193: step: 816/530, loss: 1.3680143356323242
2023-01-22 23:48:36.859131: step: 820/530, loss: 0.06519480049610138
2023-01-22 23:48:37.981840: step: 824/530, loss: 0.180962473154068
2023-01-22 23:48:39.087331: step: 828/530, loss: 0.07015037536621094
2023-01-22 23:48:40.190005: step: 832/530, loss: 0.7355828881263733
2023-01-22 23:48:41.305945: step: 836/530, loss: 0.5996140241622925
2023-01-22 23:48:42.422012: step: 840/530, loss: 0.15328168869018555
2023-01-22 23:48:43.557284: step: 844/530, loss: 0.042687609791755676
2023-01-22 23:48:44.658840: step: 848/530, loss: 0.16516882181167603
2023-01-22 23:48:45.780123: step: 852/530, loss: 0.6940152645111084
2023-01-22 23:48:46.878014: step: 856/530, loss: 0.7352458834648132
2023-01-22 23:48:48.021363: step: 860/530, loss: 0.47857657074928284
2023-01-22 23:48:49.136562: step: 864/530, loss: 1.603176474571228
2023-01-22 23:48:50.253551: step: 868/530, loss: 0.7686771154403687
2023-01-22 23:48:51.382444: step: 872/530, loss: 0.24088802933692932
2023-01-22 23:48:52.504776: step: 876/530, loss: 0.11938619613647461
2023-01-22 23:48:53.659013: step: 880/530, loss: 0.04923210293054581
2023-01-22 23:48:54.809924: step: 884/530, loss: 0.14917898178100586
2023-01-22 23:48:55.913833: step: 888/530, loss: 0.061806872487068176
2023-01-22 23:48:57.018277: step: 892/530, loss: 0.1656983494758606
2023-01-22 23:48:58.140019: step: 896/530, loss: 1.5073906183242798
2023-01-22 23:48:59.246457: step: 900/530, loss: 0.26584750413894653
2023-01-22 23:49:00.366168: step: 904/530, loss: 0.1944114714860916
2023-01-22 23:49:01.494474: step: 908/530, loss: 0.26362448930740356
2023-01-22 23:49:02.638668: step: 912/530, loss: 0.38007867336273193
2023-01-22 23:49:03.745546: step: 916/530, loss: 0.4378413259983063
2023-01-22 23:49:04.849411: step: 920/530, loss: 1.208674669265747
2023-01-22 23:49:05.978055: step: 924/530, loss: 0.175586998462677
2023-01-22 23:49:07.107969: step: 928/530, loss: 0.6227144598960876
2023-01-22 23:49:08.244512: step: 932/530, loss: 1.5765175819396973
2023-01-22 23:49:09.381245: step: 936/530, loss: 0.1888962835073471
2023-01-22 23:49:10.549807: step: 940/530, loss: 0.09631138294935226
2023-01-22 23:49:11.677685: step: 944/530, loss: 0.2614017426967621
2023-01-22 23:49:12.787147: step: 948/530, loss: 0.055631544440984726
2023-01-22 23:49:13.925261: step: 952/530, loss: 0.32814350724220276
2023-01-22 23:49:15.045927: step: 956/530, loss: 1.0186214447021484
2023-01-22 23:49:16.195951: step: 960/530, loss: 0.41222620010375977
2023-01-22 23:49:17.313473: step: 964/530, loss: 0.06350564956665039
2023-01-22 23:49:18.451006: step: 968/530, loss: 0.12357597053050995
2023-01-22 23:49:19.560638: step: 972/530, loss: 0.3315253257751465
2023-01-22 23:49:20.658388: step: 976/530, loss: 0.9720466732978821
2023-01-22 23:49:21.759162: step: 980/530, loss: 0.06506018340587616
2023-01-22 23:49:22.883611: step: 984/530, loss: 0.3916108310222626
2023-01-22 23:49:24.037559: step: 988/530, loss: 0.861648678779602
2023-01-22 23:49:25.133993: step: 992/530, loss: 0.08412675559520721
2023-01-22 23:49:26.330009: step: 996/530, loss: 0.23973016440868378
2023-01-22 23:49:27.465079: step: 1000/530, loss: 0.8282028436660767
2023-01-22 23:49:28.581453: step: 1004/530, loss: 0.7034934759140015
2023-01-22 23:49:29.688902: step: 1008/530, loss: 0.29350337386131287
2023-01-22 23:49:30.837161: step: 1012/530, loss: 0.3190247714519501
2023-01-22 23:49:31.968007: step: 1016/530, loss: 0.7765703797340393
2023-01-22 23:49:33.123862: step: 1020/530, loss: 0.28241467475891113
2023-01-22 23:49:34.241176: step: 1024/530, loss: 0.5483298301696777
2023-01-22 23:49:35.377478: step: 1028/530, loss: 0.515511691570282
2023-01-22 23:49:36.510495: step: 1032/530, loss: 0.12958142161369324
2023-01-22 23:49:37.628612: step: 1036/530, loss: 6.191729545593262
2023-01-22 23:49:38.756372: step: 1040/530, loss: 0.7704676985740662
2023-01-22 23:49:39.886171: step: 1044/530, loss: 0.10454535484313965
2023-01-22 23:49:41.002537: step: 1048/530, loss: 0.09000349044799805
2023-01-22 23:49:42.113900: step: 1052/530, loss: 0.7896023988723755
2023-01-22 23:49:43.224026: step: 1056/530, loss: 0.6158335208892822
2023-01-22 23:49:44.341119: step: 1060/530, loss: 0.6221862435340881
2023-01-22 23:49:45.444563: step: 1064/530, loss: 0.5899291634559631
2023-01-22 23:49:46.594209: step: 1068/530, loss: 0.8752052187919617
2023-01-22 23:49:47.709250: step: 1072/530, loss: 0.4298314154148102
2023-01-22 23:49:48.876963: step: 1076/530, loss: 0.13121899962425232
2023-01-22 23:49:50.001192: step: 1080/530, loss: 0.1385403871536255
2023-01-22 23:49:51.125490: step: 1084/530, loss: 0.23179060220718384
2023-01-22 23:49:52.272949: step: 1088/530, loss: 1.016118049621582
2023-01-22 23:49:53.423255: step: 1092/530, loss: 0.10098409652709961
2023-01-22 23:49:54.597288: step: 1096/530, loss: 0.4687042236328125
2023-01-22 23:49:55.716739: step: 1100/530, loss: 2.1217658519744873
2023-01-22 23:49:56.866069: step: 1104/530, loss: 0.12036685645580292
2023-01-22 23:49:57.979026: step: 1108/530, loss: 0.34987831115722656
2023-01-22 23:49:59.081133: step: 1112/530, loss: 0.052722882479429245
2023-01-22 23:50:00.199314: step: 1116/530, loss: 0.06628718972206116
2023-01-22 23:50:01.327138: step: 1120/530, loss: 0.6652696132659912
2023-01-22 23:50:02.439171: step: 1124/530, loss: 0.15781469643115997
2023-01-22 23:50:03.559481: step: 1128/530, loss: 0.6451373100280762
2023-01-22 23:50:04.698823: step: 1132/530, loss: 1.2718219757080078
2023-01-22 23:50:05.829351: step: 1136/530, loss: 0.24527369439601898
2023-01-22 23:50:06.960455: step: 1140/530, loss: 0.22603583335876465
2023-01-22 23:50:08.071857: step: 1144/530, loss: 1.5129776000976562
2023-01-22 23:50:09.196118: step: 1148/530, loss: 0.10716376453638077
2023-01-22 23:50:10.311599: step: 1152/530, loss: 0.185224249958992
2023-01-22 23:50:11.425594: step: 1156/530, loss: 0.12649841606616974
2023-01-22 23:50:12.568235: step: 1160/530, loss: 0.14966841042041779
2023-01-22 23:50:13.713972: step: 1164/530, loss: 0.7400844693183899
2023-01-22 23:50:14.824992: step: 1168/530, loss: 0.08268282562494278
2023-01-22 23:50:15.980724: step: 1172/530, loss: 0.7513513565063477
2023-01-22 23:50:17.108253: step: 1176/530, loss: 0.45528754591941833
2023-01-22 23:50:18.275405: step: 1180/530, loss: 0.449070543050766
2023-01-22 23:50:19.416653: step: 1184/530, loss: 0.09797721356153488
2023-01-22 23:50:20.540711: step: 1188/530, loss: 0.24434785544872284
2023-01-22 23:50:21.640591: step: 1192/530, loss: 0.184340238571167
2023-01-22 23:50:22.762511: step: 1196/530, loss: 1.1998863220214844
2023-01-22 23:50:23.899712: step: 1200/530, loss: 0.210282564163208
2023-01-22 23:50:24.996191: step: 1204/530, loss: 1.3139013051986694
2023-01-22 23:50:26.141810: step: 1208/530, loss: 0.5444134473800659
2023-01-22 23:50:27.239402: step: 1212/530, loss: 0.29207244515419006
2023-01-22 23:50:28.351665: step: 1216/530, loss: 0.09406566619873047
2023-01-22 23:50:29.487020: step: 1220/530, loss: 0.4249807596206665
2023-01-22 23:50:30.631463: step: 1224/530, loss: 0.2517785131931305
2023-01-22 23:50:31.762463: step: 1228/530, loss: 0.37605181336402893
2023-01-22 23:50:32.952183: step: 1232/530, loss: 0.1841794103384018
2023-01-22 23:50:34.077365: step: 1236/530, loss: 0.7708064317703247
2023-01-22 23:50:35.196297: step: 1240/530, loss: 1.9997828006744385
2023-01-22 23:50:36.311682: step: 1244/530, loss: 0.16339293122291565
2023-01-22 23:50:37.444796: step: 1248/530, loss: 0.49651604890823364
2023-01-22 23:50:38.571970: step: 1252/530, loss: 1.6021158695220947
2023-01-22 23:50:39.683574: step: 1256/530, loss: 0.1506500244140625
2023-01-22 23:50:40.788764: step: 1260/530, loss: 0.05822458490729332
2023-01-22 23:50:41.909095: step: 1264/530, loss: 0.09736347198486328
2023-01-22 23:50:43.023049: step: 1268/530, loss: 0.0550776943564415
2023-01-22 23:50:44.127835: step: 1272/530, loss: 0.2136070728302002
2023-01-22 23:50:45.274514: step: 1276/530, loss: 0.09297418594360352
2023-01-22 23:50:46.386804: step: 1280/530, loss: 0.16149863600730896
2023-01-22 23:50:47.499025: step: 1284/530, loss: 0.46872490644454956
2023-01-22 23:50:48.625913: step: 1288/530, loss: 0.32695770263671875
2023-01-22 23:50:49.751227: step: 1292/530, loss: 0.08009135723114014
2023-01-22 23:50:50.883431: step: 1296/530, loss: 0.6113733053207397
2023-01-22 23:50:52.009111: step: 1300/530, loss: 0.5991030931472778
2023-01-22 23:50:53.116915: step: 1304/530, loss: 0.5400673151016235
2023-01-22 23:50:54.236230: step: 1308/530, loss: 1.7407561540603638
2023-01-22 23:50:55.356459: step: 1312/530, loss: 0.222305029630661
2023-01-22 23:50:56.508851: step: 1316/530, loss: 0.11263298988342285
2023-01-22 23:50:57.654420: step: 1320/530, loss: 0.14874425530433655
2023-01-22 23:50:58.796581: step: 1324/530, loss: 0.2534072995185852
2023-01-22 23:50:59.908500: step: 1328/530, loss: 0.08204689621925354
2023-01-22 23:51:01.032642: step: 1332/530, loss: 0.22871409356594086
2023-01-22 23:51:02.156768: step: 1336/530, loss: 0.070670947432518
2023-01-22 23:51:03.290599: step: 1340/530, loss: 0.4729039669036865
2023-01-22 23:51:04.412498: step: 1344/530, loss: 0.22761201858520508
2023-01-22 23:51:05.510794: step: 1348/530, loss: 0.17169252038002014
2023-01-22 23:51:06.592080: step: 1352/530, loss: 0.21530741453170776
2023-01-22 23:51:07.728835: step: 1356/530, loss: 1.4356058835983276
2023-01-22 23:51:08.848016: step: 1360/530, loss: 0.37823906540870667
2023-01-22 23:51:10.010912: step: 1364/530, loss: 0.7812243700027466
2023-01-22 23:51:11.138017: step: 1368/530, loss: 1.2373443841934204
2023-01-22 23:51:12.233858: step: 1372/530, loss: 0.10183171927928925
2023-01-22 23:51:13.376310: step: 1376/530, loss: 0.8201669454574585
2023-01-22 23:51:14.466852: step: 1380/530, loss: 0.24404993653297424
2023-01-22 23:51:15.602807: step: 1384/530, loss: 0.1608392298221588
2023-01-22 23:51:16.742560: step: 1388/530, loss: 0.7014926075935364
2023-01-22 23:51:17.900569: step: 1392/530, loss: 0.45869407057762146
2023-01-22 23:51:19.024662: step: 1396/530, loss: 6.414951801300049
2023-01-22 23:51:20.173641: step: 1400/530, loss: 0.027323007583618164
2023-01-22 23:51:21.318590: step: 1404/530, loss: 0.5884970426559448
2023-01-22 23:51:22.446084: step: 1408/530, loss: 0.2120293825864792
2023-01-22 23:51:23.573271: step: 1412/530, loss: 0.0824156254529953
2023-01-22 23:51:24.718044: step: 1416/530, loss: 0.19473476707935333
2023-01-22 23:51:25.843820: step: 1420/530, loss: 0.37752535939216614
2023-01-22 23:51:26.960026: step: 1424/530, loss: 0.12089991569519043
2023-01-22 23:51:28.061933: step: 1428/530, loss: 6.326498508453369
2023-01-22 23:51:29.190498: step: 1432/530, loss: 0.4065941870212555
2023-01-22 23:51:30.311976: step: 1436/530, loss: 1.898832082748413
2023-01-22 23:51:31.438825: step: 1440/530, loss: 6.559451103210449
2023-01-22 23:51:32.610723: step: 1444/530, loss: 1.0750842094421387
2023-01-22 23:51:33.714079: step: 1448/530, loss: 0.08206968754529953
2023-01-22 23:51:34.785605: step: 1452/530, loss: 1.6692469120025635
2023-01-22 23:51:35.891694: step: 1456/530, loss: 0.08275580406188965
2023-01-22 23:51:37.035409: step: 1460/530, loss: 0.29534482955932617
2023-01-22 23:51:38.165335: step: 1464/530, loss: 0.12534990906715393
2023-01-22 23:51:39.307061: step: 1468/530, loss: 0.07975426316261292
2023-01-22 23:51:40.452934: step: 1472/530, loss: 0.7868443727493286
2023-01-22 23:51:41.576267: step: 1476/530, loss: 0.28463783860206604
2023-01-22 23:51:42.732107: step: 1480/530, loss: 1.543434739112854
2023-01-22 23:51:43.854007: step: 1484/530, loss: 0.5127757787704468
2023-01-22 23:51:44.985064: step: 1488/530, loss: 0.11634526401758194
2023-01-22 23:51:46.116391: step: 1492/530, loss: 0.1346220076084137
2023-01-22 23:51:47.274628: step: 1496/530, loss: 0.2461404800415039
2023-01-22 23:51:48.417912: step: 1500/530, loss: 0.3611830770969391
2023-01-22 23:51:49.608478: step: 1504/530, loss: 0.42270898818969727
2023-01-22 23:51:50.757877: step: 1508/530, loss: 0.2460983395576477
2023-01-22 23:51:51.856350: step: 1512/530, loss: 0.2051871418952942
2023-01-22 23:51:52.989631: step: 1516/530, loss: 1.3063852787017822
2023-01-22 23:51:54.086680: step: 1520/530, loss: 0.2958106994628906
2023-01-22 23:51:55.206208: step: 1524/530, loss: 0.5070406198501587
2023-01-22 23:51:56.323724: step: 1528/530, loss: 0.20924854278564453
2023-01-22 23:51:57.454028: step: 1532/530, loss: 0.15202771127223969
2023-01-22 23:51:58.567279: step: 1536/530, loss: 2.326475143432617
2023-01-22 23:51:59.676776: step: 1540/530, loss: 0.08757729828357697
2023-01-22 23:52:00.827403: step: 1544/530, loss: 1.299591064453125
2023-01-22 23:52:01.953722: step: 1548/530, loss: 0.3828961253166199
2023-01-22 23:52:03.114871: step: 1552/530, loss: 0.2863673269748688
2023-01-22 23:52:04.209730: step: 1556/530, loss: 0.07447466999292374
2023-01-22 23:52:05.339518: step: 1560/530, loss: 7.14508581161499
2023-01-22 23:52:06.474011: step: 1564/530, loss: 0.14088097214698792
2023-01-22 23:52:07.647702: step: 1568/530, loss: 1.9876673221588135
2023-01-22 23:52:08.768311: step: 1572/530, loss: 0.4182295799255371
2023-01-22 23:52:09.896251: step: 1576/530, loss: 0.8177449703216553
2023-01-22 23:52:11.016715: step: 1580/530, loss: 0.3151237368583679
2023-01-22 23:52:12.132856: step: 1584/530, loss: 1.5390770435333252
2023-01-22 23:52:13.275588: step: 1588/530, loss: 1.0214335918426514
2023-01-22 23:52:14.372389: step: 1592/530, loss: 0.09614195674657822
2023-01-22 23:52:15.502817: step: 1596/530, loss: 0.11271438747644424
2023-01-22 23:52:16.635611: step: 1600/530, loss: 0.5496959686279297
2023-01-22 23:52:17.757138: step: 1604/530, loss: 0.8033367991447449
2023-01-22 23:52:18.887929: step: 1608/530, loss: 0.6044737100601196
2023-01-22 23:52:19.993674: step: 1612/530, loss: 1.9274663925170898
2023-01-22 23:52:21.126039: step: 1616/530, loss: 0.25484132766723633
2023-01-22 23:52:22.243768: step: 1620/530, loss: 0.3882312476634979
2023-01-22 23:52:23.337211: step: 1624/530, loss: 7.3641357421875
2023-01-22 23:52:24.453912: step: 1628/530, loss: 1.288686990737915
2023-01-22 23:52:25.587735: step: 1632/530, loss: 0.08786025643348694
2023-01-22 23:52:26.705185: step: 1636/530, loss: 0.1812223494052887
2023-01-22 23:52:27.874291: step: 1640/530, loss: 1.2615675926208496
2023-01-22 23:52:28.984100: step: 1644/530, loss: 0.05477505177259445
2023-01-22 23:52:30.106264: step: 1648/530, loss: 0.10191360116004944
2023-01-22 23:52:31.230516: step: 1652/530, loss: 0.6886259317398071
2023-01-22 23:52:32.366683: step: 1656/530, loss: 1.9948408603668213
2023-01-22 23:52:33.485958: step: 1660/530, loss: 0.30972665548324585
2023-01-22 23:52:34.616880: step: 1664/530, loss: 0.048215627670288086
2023-01-22 23:52:35.745283: step: 1668/530, loss: 0.9507412910461426
2023-01-22 23:52:36.892318: step: 1672/530, loss: 1.0865137577056885
2023-01-22 23:52:38.041659: step: 1676/530, loss: 0.8738133907318115
2023-01-22 23:52:39.156879: step: 1680/530, loss: 0.23672696948051453
2023-01-22 23:52:40.291149: step: 1684/530, loss: 0.24212399125099182
2023-01-22 23:52:41.418680: step: 1688/530, loss: 0.23320885002613068
2023-01-22 23:52:42.564969: step: 1692/530, loss: 1.0013595819473267
2023-01-22 23:52:43.703490: step: 1696/530, loss: 0.15325136482715607
2023-01-22 23:52:44.828439: step: 1700/530, loss: 0.2142990529537201
2023-01-22 23:52:45.953421: step: 1704/530, loss: 0.22104549407958984
2023-01-22 23:52:47.048286: step: 1708/530, loss: 0.11247821152210236
2023-01-22 23:52:48.168347: step: 1712/530, loss: 0.6389761567115784
2023-01-22 23:52:49.276273: step: 1716/530, loss: 0.09800930321216583
2023-01-22 23:52:50.447466: step: 1720/530, loss: 0.30935680866241455
2023-01-22 23:52:51.626474: step: 1724/530, loss: 0.25702953338623047
2023-01-22 23:52:52.732600: step: 1728/530, loss: 0.06217360496520996
2023-01-22 23:52:53.857317: step: 1732/530, loss: 0.09047393500804901
2023-01-22 23:52:54.986306: step: 1736/530, loss: 0.1336732804775238
2023-01-22 23:52:56.162728: step: 1740/530, loss: 0.5340733528137207
2023-01-22 23:52:57.287172: step: 1744/530, loss: 0.531393826007843
2023-01-22 23:52:58.395625: step: 1748/530, loss: 0.5154545307159424
2023-01-22 23:52:59.533814: step: 1752/530, loss: 0.14974327385425568
2023-01-22 23:53:00.635740: step: 1756/530, loss: 0.053351547569036484
2023-01-22 23:53:01.757298: step: 1760/530, loss: 0.16407376527786255
2023-01-22 23:53:02.890004: step: 1764/530, loss: 0.08765693008899689
2023-01-22 23:53:04.037934: step: 1768/530, loss: 0.499778151512146
2023-01-22 23:53:05.171518: step: 1772/530, loss: 0.46413174271583557
2023-01-22 23:53:06.272416: step: 1776/530, loss: 0.11247333884239197
2023-01-22 23:53:07.403176: step: 1780/530, loss: 0.37716227769851685
2023-01-22 23:53:08.520842: step: 1784/530, loss: 2.129530906677246
2023-01-22 23:53:09.637643: step: 1788/530, loss: 0.6678089499473572
2023-01-22 23:53:10.782727: step: 1792/530, loss: 0.16081924736499786
2023-01-22 23:53:11.888738: step: 1796/530, loss: 0.3812602162361145
2023-01-22 23:53:13.018510: step: 1800/530, loss: 0.6328672170639038
2023-01-22 23:53:14.133038: step: 1804/530, loss: 0.6405184864997864
2023-01-22 23:53:15.267896: step: 1808/530, loss: 0.6990206837654114
2023-01-22 23:53:16.409158: step: 1812/530, loss: 0.352647602558136
2023-01-22 23:53:17.560583: step: 1816/530, loss: 0.10947147011756897
2023-01-22 23:53:18.693392: step: 1820/530, loss: 0.16661424934864044
2023-01-22 23:53:19.821710: step: 1824/530, loss: 0.10155987739562988
2023-01-22 23:53:20.965454: step: 1828/530, loss: 0.8162501454353333
2023-01-22 23:53:22.089743: step: 1832/530, loss: 0.2598547041416168
2023-01-22 23:53:23.223944: step: 1836/530, loss: 0.1784307062625885
2023-01-22 23:53:24.332607: step: 1840/530, loss: 0.7863420248031616
2023-01-22 23:53:25.441027: step: 1844/530, loss: 0.22834280133247375
2023-01-22 23:53:26.584394: step: 1848/530, loss: 0.7989018559455872
2023-01-22 23:53:27.722174: step: 1852/530, loss: 0.7019374966621399
2023-01-22 23:53:28.836485: step: 1856/530, loss: 0.19690647721290588
2023-01-22 23:53:29.955992: step: 1860/530, loss: 0.0850774273276329
2023-01-22 23:53:31.084087: step: 1864/530, loss: 0.9399198293685913
2023-01-22 23:53:32.219057: step: 1868/530, loss: 1.9015846252441406
2023-01-22 23:53:33.338926: step: 1872/530, loss: 0.16511507332324982
2023-01-22 23:53:34.466513: step: 1876/530, loss: 0.5228404998779297
2023-01-22 23:53:35.621513: step: 1880/530, loss: 0.41082051396369934
2023-01-22 23:53:36.779641: step: 1884/530, loss: 0.8720858693122864
2023-01-22 23:53:37.912666: step: 1888/530, loss: 0.05514850839972496
2023-01-22 23:53:39.038361: step: 1892/530, loss: 0.604894757270813
2023-01-22 23:53:40.177370: step: 1896/530, loss: 0.5620167851448059
2023-01-22 23:53:41.286005: step: 1900/530, loss: 0.8447092771530151
2023-01-22 23:53:42.397653: step: 1904/530, loss: 0.9962377548217773
2023-01-22 23:53:43.514677: step: 1908/530, loss: 0.23509721457958221
2023-01-22 23:53:44.646687: step: 1912/530, loss: 0.8576667308807373
2023-01-22 23:53:45.752382: step: 1916/530, loss: 0.349565327167511
2023-01-22 23:53:46.893759: step: 1920/530, loss: 0.18940743803977966
2023-01-22 23:53:48.061342: step: 1924/530, loss: 0.6548725366592407
2023-01-22 23:53:49.195252: step: 1928/530, loss: 1.9670281410217285
2023-01-22 23:53:50.299750: step: 1932/530, loss: 0.6714258193969727
2023-01-22 23:53:51.426846: step: 1936/530, loss: 0.04806642606854439
2023-01-22 23:53:52.565442: step: 1940/530, loss: 0.10305114090442657
2023-01-22 23:53:53.710227: step: 1944/530, loss: 0.422593891620636
2023-01-22 23:53:54.824791: step: 1948/530, loss: 0.7131737470626831
2023-01-22 23:53:55.926622: step: 1952/530, loss: 0.15087327361106873
2023-01-22 23:53:57.073537: step: 1956/530, loss: 0.7676081657409668
2023-01-22 23:53:58.214314: step: 1960/530, loss: 0.023475931957364082
2023-01-22 23:53:59.357032: step: 1964/530, loss: 1.2449216842651367
2023-01-22 23:54:00.473632: step: 1968/530, loss: 0.05243687331676483
2023-01-22 23:54:01.631961: step: 1972/530, loss: 0.22005577385425568
2023-01-22 23:54:02.756910: step: 1976/530, loss: 0.7210884094238281
2023-01-22 23:54:03.907775: step: 1980/530, loss: 0.15306778252124786
2023-01-22 23:54:05.052692: step: 1984/530, loss: 0.13331422209739685
2023-01-22 23:54:06.207342: step: 1988/530, loss: 0.18127784132957458
2023-01-22 23:54:07.373209: step: 1992/530, loss: 0.23089894652366638
2023-01-22 23:54:08.481317: step: 1996/530, loss: 0.7111529111862183
2023-01-22 23:54:09.608164: step: 2000/530, loss: 0.21061024069786072
2023-01-22 23:54:10.695298: step: 2004/530, loss: 0.4544907510280609
2023-01-22 23:54:11.794376: step: 2008/530, loss: 0.43710020184516907
2023-01-22 23:54:12.930121: step: 2012/530, loss: 0.3562057912349701
2023-01-22 23:54:14.033077: step: 2016/530, loss: 0.14166541397571564
2023-01-22 23:54:15.154073: step: 2020/530, loss: 0.19112272560596466
2023-01-22 23:54:16.287630: step: 2024/530, loss: 0.4822103977203369
2023-01-22 23:54:17.410012: step: 2028/530, loss: 0.515457272529602
2023-01-22 23:54:18.529273: step: 2032/530, loss: 0.195018008351326
2023-01-22 23:54:19.659796: step: 2036/530, loss: 0.9606984257698059
2023-01-22 23:54:20.789382: step: 2040/530, loss: 1.847872257232666
2023-01-22 23:54:21.914670: step: 2044/530, loss: 0.9115325212478638
2023-01-22 23:54:23.097944: step: 2048/530, loss: 1.8556472063064575
2023-01-22 23:54:24.212505: step: 2052/530, loss: 0.3390215039253235
2023-01-22 23:54:25.319800: step: 2056/530, loss: 0.32991498708724976
2023-01-22 23:54:26.469793: step: 2060/530, loss: 0.22730664908885956
2023-01-22 23:54:27.613523: step: 2064/530, loss: 0.16781559586524963
2023-01-22 23:54:28.758447: step: 2068/530, loss: 0.10911817848682404
2023-01-22 23:54:29.904845: step: 2072/530, loss: 1.1823575496673584
2023-01-22 23:54:31.049781: step: 2076/530, loss: 0.3871402442455292
2023-01-22 23:54:32.190524: step: 2080/530, loss: 0.12795454263687134
2023-01-22 23:54:33.313503: step: 2084/530, loss: 0.4788084030151367
2023-01-22 23:54:34.426983: step: 2088/530, loss: 0.45576614141464233
2023-01-22 23:54:35.565170: step: 2092/530, loss: 0.18033123016357422
2023-01-22 23:54:36.689267: step: 2096/530, loss: 0.8473040461540222
2023-01-22 23:54:37.781557: step: 2100/530, loss: 0.7381426692008972
2023-01-22 23:54:38.921514: step: 2104/530, loss: 1.4058525562286377
2023-01-22 23:54:40.043709: step: 2108/530, loss: 0.013858843594789505
2023-01-22 23:54:41.172588: step: 2112/530, loss: 0.75736004114151
2023-01-22 23:54:42.307420: step: 2116/530, loss: 0.3479897379875183
2023-01-22 23:54:43.432995: step: 2120/530, loss: 0.08949537575244904
==================================================
Loss: 0.599
--------------------
Dev: {'event': {'p': 0.569593147751606, 'r': 0.7083888149134487, 'f1': 0.631454005934718}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Test: {'event': {'p': 0.605787476280835, 'r': 0.7297142857142858, 'f1': 0.6620010368066357}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Chinese: {'event': {'p': 0.5774647887323944, 'r': 0.7592592592592593, 'f1': 0.656}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Korean: {'event': {'p': 0.7105263157894737, 'r': 0.42857142857142855, 'f1': 0.5346534653465346}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Russian: {'event': {'p': 0.5625, 'r': 0.5, 'f1': 0.5294117647058824}, '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': 0.569593147751606, 'r': 0.7083888149134487, 'f1': 0.631454005934718}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Eng Test for Chinese: {'event': {'p': 0.605787476280835, 'r': 0.7297142857142858, 'f1': 0.6620010368066357}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Sample Chinese: {'event': {'p': 0.5774647887323944, 'r': 0.7592592592592593, 'f1': 0.656}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
--------------------
Eng Dev for Korean: {'event': {'p': 0.569593147751606, 'r': 0.7083888149134487, 'f1': 0.631454005934718}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Eng Test for Korean: {'event': {'p': 0.605787476280835, 'r': 0.7297142857142858, 'f1': 0.6620010368066357}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Sample Korean: {'event': {'p': 0.7105263157894737, 'r': 0.42857142857142855, 'f1': 0.5346534653465346}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6436170212765957, 'r': 0.644474034620506, 'f1': 0.6440452428476381}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Eng Test for Russian: {'event': {'p': 0.6642728904847397, 'r': 0.6342857142857142, 'f1': 0.6489330605086231}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Sample Russian: {'event': {'p': 0.64, 'r': 0.4444444444444444, 'f1': 0.5245901639344263}, '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 23:55:40.192469: step: 4/530, loss: 0.17036724090576172
2023-01-22 23:55:41.308120: step: 8/530, loss: 0.16642971336841583
2023-01-22 23:55:42.458005: step: 12/530, loss: 0.34728074073791504
2023-01-22 23:55:43.559537: step: 16/530, loss: 0.23984479904174805
2023-01-22 23:55:44.698026: step: 20/530, loss: 1.1788955926895142
2023-01-22 23:55:45.846176: step: 24/530, loss: 0.1517195701599121
2023-01-22 23:55:46.982045: step: 28/530, loss: 0.9309684038162231
2023-01-22 23:55:48.114149: step: 32/530, loss: 0.027128791436553
2023-01-22 23:55:49.304483: step: 36/530, loss: 0.20915785431861877
2023-01-22 23:55:50.429129: step: 40/530, loss: 0.23358076810836792
2023-01-22 23:55:51.535802: step: 44/530, loss: 1.2669751644134521
2023-01-22 23:55:52.632156: step: 48/530, loss: 0.21642929315567017
2023-01-22 23:55:53.778389: step: 52/530, loss: 0.46964895725250244
2023-01-22 23:55:54.897890: step: 56/530, loss: 0.08487287163734436
2023-01-22 23:55:56.027175: step: 60/530, loss: 0.0885734111070633
2023-01-22 23:55:57.154607: step: 64/530, loss: 1.2772128582000732
2023-01-22 23:55:58.259021: step: 68/530, loss: 0.21787281334400177
2023-01-22 23:55:59.380253: step: 72/530, loss: 0.45431509613990784
2023-01-22 23:56:00.510958: step: 76/530, loss: 0.3456558585166931
2023-01-22 23:56:01.630270: step: 80/530, loss: 0.11414603888988495
2023-01-22 23:56:02.801106: step: 84/530, loss: 0.762995719909668
2023-01-22 23:56:03.923800: step: 88/530, loss: 0.17691020667552948
2023-01-22 23:56:05.038151: step: 92/530, loss: 0.4836730360984802
2023-01-22 23:56:06.158764: step: 96/530, loss: 7.069892883300781
2023-01-22 23:56:07.290008: step: 100/530, loss: 0.3584449887275696
2023-01-22 23:56:08.406049: step: 104/530, loss: 0.4535992741584778
2023-01-22 23:56:09.508732: step: 108/530, loss: 0.06003322824835777
2023-01-22 23:56:10.635139: step: 112/530, loss: 0.2212258279323578
2023-01-22 23:56:11.781728: step: 116/530, loss: 0.19721660017967224
2023-01-22 23:56:12.945525: step: 120/530, loss: 0.7173643112182617
2023-01-22 23:56:14.087309: step: 124/530, loss: 0.2072695791721344
2023-01-22 23:56:15.222364: step: 128/530, loss: 0.07194796204566956
2023-01-22 23:56:16.339449: step: 132/530, loss: 0.04120960459113121
2023-01-22 23:56:17.445749: step: 136/530, loss: 0.5953636765480042
2023-01-22 23:56:18.581276: step: 140/530, loss: 0.45882779359817505
2023-01-22 23:56:19.710426: step: 144/530, loss: 0.8287956118583679
2023-01-22 23:56:20.811079: step: 148/530, loss: 0.6020979881286621
2023-01-22 23:56:21.927248: step: 152/530, loss: 0.2859021723270416
2023-01-22 23:56:23.047349: step: 156/530, loss: 0.7586717009544373
2023-01-22 23:56:24.154362: step: 160/530, loss: 0.433019757270813
2023-01-22 23:56:25.254588: step: 164/530, loss: 0.09717945754528046
2023-01-22 23:56:26.386124: step: 168/530, loss: 0.0967007651925087
2023-01-22 23:56:27.508562: step: 172/530, loss: 1.19929039478302
2023-01-22 23:56:28.656038: step: 176/530, loss: 0.6184322237968445
2023-01-22 23:56:29.756264: step: 180/530, loss: 0.12002047896385193
2023-01-22 23:56:30.908889: step: 184/530, loss: 0.12334775924682617
2023-01-22 23:56:32.038508: step: 188/530, loss: 0.12159624695777893
2023-01-22 23:56:33.198181: step: 192/530, loss: 0.47953665256500244
2023-01-22 23:56:34.305396: step: 196/530, loss: 0.4455191195011139
2023-01-22 23:56:35.457956: step: 200/530, loss: 0.0381779670715332
2023-01-22 23:56:36.589480: step: 204/530, loss: 0.0698336586356163
2023-01-22 23:56:37.723820: step: 208/530, loss: 0.9178913235664368
2023-01-22 23:56:38.845201: step: 212/530, loss: 0.6019262671470642
2023-01-22 23:56:39.980837: step: 216/530, loss: 0.7543321847915649
2023-01-22 23:56:41.110139: step: 220/530, loss: 0.39735376834869385
2023-01-22 23:56:42.225917: step: 224/530, loss: 0.13671712577342987
2023-01-22 23:56:43.398399: step: 228/530, loss: 0.09299878776073456
2023-01-22 23:56:44.529006: step: 232/530, loss: 0.2131734937429428
2023-01-22 23:56:45.650133: step: 236/530, loss: 0.2404012829065323
2023-01-22 23:56:46.824682: step: 240/530, loss: 0.30490607023239136
2023-01-22 23:56:47.951723: step: 244/530, loss: 0.5144624710083008
2023-01-22 23:56:49.102491: step: 248/530, loss: 7.687002182006836
2023-01-22 23:56:50.264340: step: 252/530, loss: 0.1485731601715088
2023-01-22 23:56:51.393074: step: 256/530, loss: 0.7885928153991699
2023-01-22 23:56:52.543490: step: 260/530, loss: 0.8743067383766174
2023-01-22 23:56:53.688296: step: 264/530, loss: 0.1159951239824295
2023-01-22 23:56:54.783251: step: 268/530, loss: 0.08031110465526581
2023-01-22 23:56:55.898501: step: 272/530, loss: 6.587563991546631
2023-01-22 23:56:57.013253: step: 276/530, loss: 0.47947150468826294
2023-01-22 23:56:58.137778: step: 280/530, loss: 0.16153354942798615
2023-01-22 23:56:59.242152: step: 284/530, loss: 0.14447660744190216
2023-01-22 23:57:00.331588: step: 288/530, loss: 0.7117495536804199
2023-01-22 23:57:01.455313: step: 292/530, loss: 0.6613510847091675
2023-01-22 23:57:02.599643: step: 296/530, loss: 0.3186551034450531
2023-01-22 23:57:03.711360: step: 300/530, loss: 0.07023553550243378
2023-01-22 23:57:04.829183: step: 304/530, loss: 0.6561623811721802
2023-01-22 23:57:05.967121: step: 308/530, loss: 0.11302366107702255
2023-01-22 23:57:07.104362: step: 312/530, loss: 0.1771559715270996
2023-01-22 23:57:08.229912: step: 316/530, loss: 0.17372578382492065
2023-01-22 23:57:09.380237: step: 320/530, loss: 0.15440569818019867
2023-01-22 23:57:10.528351: step: 324/530, loss: 0.11930026859045029
2023-01-22 23:57:11.670848: step: 328/530, loss: 0.8409977555274963
2023-01-22 23:57:12.789788: step: 332/530, loss: 0.054646775126457214
2023-01-22 23:57:13.921727: step: 336/530, loss: 1.5318517684936523
2023-01-22 23:57:15.042867: step: 340/530, loss: 0.28302761912345886
2023-01-22 23:57:16.150762: step: 344/530, loss: 0.3082978129386902
2023-01-22 23:57:17.334284: step: 348/530, loss: 0.6703676581382751
2023-01-22 23:57:18.438635: step: 352/530, loss: 0.6897979378700256
2023-01-22 23:57:19.578536: step: 356/530, loss: 0.13538876175880432
2023-01-22 23:57:20.732825: step: 360/530, loss: 0.31450697779655457
2023-01-22 23:57:21.850071: step: 364/530, loss: 0.8024132251739502
2023-01-22 23:57:23.043111: step: 368/530, loss: 0.02173762395977974
2023-01-22 23:57:24.192131: step: 372/530, loss: 0.1503484696149826
2023-01-22 23:57:25.314111: step: 376/530, loss: 0.3332023620605469
2023-01-22 23:57:26.439818: step: 380/530, loss: 0.1747463196516037
2023-01-22 23:57:27.555991: step: 384/530, loss: 1.2421914339065552
2023-01-22 23:57:28.690202: step: 388/530, loss: 0.26384490728378296
2023-01-22 23:57:29.835537: step: 392/530, loss: 0.11498914659023285
2023-01-22 23:57:30.962578: step: 396/530, loss: 0.08179517090320587
2023-01-22 23:57:32.098966: step: 400/530, loss: 0.8759828209877014
2023-01-22 23:57:33.257045: step: 404/530, loss: 0.13246408104896545
2023-01-22 23:57:34.389883: step: 408/530, loss: 1.139804482460022
2023-01-22 23:57:35.518132: step: 412/530, loss: 0.08743028342723846
2023-01-22 23:57:36.627087: step: 416/530, loss: 0.7635576725006104
2023-01-22 23:57:37.748416: step: 420/530, loss: 0.9492528438568115
2023-01-22 23:57:38.889568: step: 424/530, loss: 0.03791513666510582
2023-01-22 23:57:40.026050: step: 428/530, loss: 0.0655418410897255
2023-01-22 23:57:41.155630: step: 432/530, loss: 0.17578358948230743
2023-01-22 23:57:42.292006: step: 436/530, loss: 0.11343555152416229
2023-01-22 23:57:43.370393: step: 440/530, loss: 0.6295663714408875
2023-01-22 23:57:44.506124: step: 444/530, loss: 1.0501545667648315
2023-01-22 23:57:45.653646: step: 448/530, loss: 0.004906797781586647
2023-01-22 23:57:46.782934: step: 452/530, loss: 0.17903494834899902
2023-01-22 23:57:47.913106: step: 456/530, loss: 0.14512687921524048
2023-01-22 23:57:49.025967: step: 460/530, loss: 0.039325617253780365
2023-01-22 23:57:50.172605: step: 464/530, loss: 0.09596538543701172
2023-01-22 23:57:51.300176: step: 468/530, loss: 5.930542469024658
2023-01-22 23:57:52.423894: step: 472/530, loss: 0.06485719978809357
2023-01-22 23:57:53.551000: step: 476/530, loss: 0.595467746257782
2023-01-22 23:57:54.667499: step: 480/530, loss: 0.07808828353881836
2023-01-22 23:57:55.781890: step: 484/530, loss: 0.4855794906616211
2023-01-22 23:57:56.894227: step: 488/530, loss: 0.7745007872581482
2023-01-22 23:57:58.031459: step: 492/530, loss: 0.05012564733624458
2023-01-22 23:57:59.167310: step: 496/530, loss: 0.05086483806371689
2023-01-22 23:58:00.311363: step: 500/530, loss: 1.30084228515625
2023-01-22 23:58:01.416163: step: 504/530, loss: 0.31470975279808044
2023-01-22 23:58:02.575337: step: 508/530, loss: 0.2153313159942627
2023-01-22 23:58:03.694720: step: 512/530, loss: 0.3217411935329437
2023-01-22 23:58:04.799228: step: 516/530, loss: 0.08524914085865021
2023-01-22 23:58:05.917814: step: 520/530, loss: 0.7159448266029358
2023-01-22 23:58:07.030850: step: 524/530, loss: 6.960169315338135
2023-01-22 23:58:08.173488: step: 528/530, loss: 0.1907837986946106
2023-01-22 23:58:09.292305: step: 532/530, loss: 0.8664283156394958
2023-01-22 23:58:10.399556: step: 536/530, loss: 0.3343973755836487
2023-01-22 23:58:11.519441: step: 540/530, loss: 0.36517515778541565
2023-01-22 23:58:12.633585: step: 544/530, loss: 0.47974395751953125
2023-01-22 23:58:13.743995: step: 548/530, loss: 0.6829677224159241
2023-01-22 23:58:14.878001: step: 552/530, loss: 0.15357132256031036
2023-01-22 23:58:15.998238: step: 556/530, loss: 1.2117977142333984
2023-01-22 23:58:17.125966: step: 560/530, loss: 0.11820311099290848
2023-01-22 23:58:18.242865: step: 564/530, loss: 0.11121435463428497
2023-01-22 23:58:19.385372: step: 568/530, loss: 0.14728155732154846
2023-01-22 23:58:20.513983: step: 572/530, loss: 0.22958365082740784
2023-01-22 23:58:21.651523: step: 576/530, loss: 0.14843511581420898
2023-01-22 23:58:22.755485: step: 580/530, loss: 0.03653326258063316
2023-01-22 23:58:23.915747: step: 584/530, loss: 0.7637840509414673
2023-01-22 23:58:25.018716: step: 588/530, loss: 0.7900869250297546
2023-01-22 23:58:26.139984: step: 592/530, loss: 0.6163390278816223
2023-01-22 23:58:27.238928: step: 596/530, loss: 0.16181430220603943
2023-01-22 23:58:28.364528: step: 600/530, loss: 0.05414404720067978
2023-01-22 23:58:29.502434: step: 604/530, loss: 0.424004465341568
2023-01-22 23:58:30.657839: step: 608/530, loss: 0.055150412023067474
2023-01-22 23:58:31.782763: step: 612/530, loss: 0.20257851481437683
2023-01-22 23:58:32.910873: step: 616/530, loss: 1.4594733715057373
2023-01-22 23:58:34.030864: step: 620/530, loss: 0.28739339113235474
2023-01-22 23:58:35.206724: step: 624/530, loss: 0.40655574202537537
2023-01-22 23:58:36.300488: step: 628/530, loss: 0.7748737335205078
2023-01-22 23:58:37.425728: step: 632/530, loss: 0.08959989249706268
2023-01-22 23:58:38.515657: step: 636/530, loss: 0.031038235872983932
2023-01-22 23:58:39.614770: step: 640/530, loss: 0.08690023422241211
2023-01-22 23:58:40.745074: step: 644/530, loss: 0.1289418339729309
2023-01-22 23:58:41.880751: step: 648/530, loss: 0.12941542267799377
2023-01-22 23:58:42.996360: step: 652/530, loss: 0.039647866040468216
2023-01-22 23:58:44.145599: step: 656/530, loss: 0.20582933723926544
2023-01-22 23:58:45.259215: step: 660/530, loss: 0.19206447899341583
2023-01-22 23:58:46.413493: step: 664/530, loss: 1.1911507844924927
2023-01-22 23:58:47.535966: step: 668/530, loss: 0.2263558804988861
2023-01-22 23:58:48.660784: step: 672/530, loss: 0.3241848647594452
2023-01-22 23:58:49.764252: step: 676/530, loss: 0.12599745392799377
2023-01-22 23:58:50.877574: step: 680/530, loss: 0.1579577475786209
2023-01-22 23:58:52.003416: step: 684/530, loss: 0.17495307326316833
2023-01-22 23:58:53.157449: step: 688/530, loss: 0.12659373879432678
2023-01-22 23:58:54.289741: step: 692/530, loss: 0.29097747802734375
2023-01-22 23:58:55.432755: step: 696/530, loss: 0.3467721939086914
2023-01-22 23:58:56.525884: step: 700/530, loss: 0.1125221773982048
2023-01-22 23:58:57.634167: step: 704/530, loss: 0.13981495797634125
2023-01-22 23:58:58.757385: step: 708/530, loss: 0.41114577651023865
2023-01-22 23:58:59.896099: step: 712/530, loss: 0.11268831044435501
2023-01-22 23:59:01.017812: step: 716/530, loss: 0.6382874250411987
2023-01-22 23:59:02.156490: step: 720/530, loss: 0.13899879157543182
2023-01-22 23:59:03.288652: step: 724/530, loss: 0.29497337341308594
2023-01-22 23:59:04.426537: step: 728/530, loss: 0.1831246018409729
2023-01-22 23:59:05.593473: step: 732/530, loss: 0.6397929191589355
2023-01-22 23:59:06.737187: step: 736/530, loss: 0.14032816886901855
2023-01-22 23:59:07.864114: step: 740/530, loss: 0.12659473717212677
2023-01-22 23:59:08.999249: step: 744/530, loss: 0.2427208125591278
2023-01-22 23:59:10.118473: step: 748/530, loss: 0.13204193115234375
2023-01-22 23:59:11.244245: step: 752/530, loss: 0.18585357069969177
2023-01-22 23:59:12.358730: step: 756/530, loss: 0.046698667109012604
2023-01-22 23:59:13.477272: step: 760/530, loss: 0.05091409757733345
2023-01-22 23:59:14.598061: step: 764/530, loss: 0.31775951385498047
2023-01-22 23:59:15.725810: step: 768/530, loss: 0.24497456848621368
2023-01-22 23:59:16.861119: step: 772/530, loss: 0.34144461154937744
2023-01-22 23:59:17.996996: step: 776/530, loss: 0.2530684471130371
2023-01-22 23:59:19.111998: step: 780/530, loss: 0.6524829268455505
2023-01-22 23:59:20.262008: step: 784/530, loss: 0.5054017901420593
2023-01-22 23:59:21.413063: step: 788/530, loss: 0.3866092562675476
2023-01-22 23:59:22.540196: step: 792/530, loss: 0.3562334179878235
2023-01-22 23:59:23.665191: step: 796/530, loss: 0.2593211233615875
2023-01-22 23:59:24.783330: step: 800/530, loss: 0.05630688741803169
2023-01-22 23:59:25.897662: step: 804/530, loss: 0.5241835117340088
2023-01-22 23:59:27.029503: step: 808/530, loss: 1.4336533546447754
2023-01-22 23:59:28.217326: step: 812/530, loss: 0.25675326585769653
2023-01-22 23:59:29.336099: step: 816/530, loss: 0.2492874264717102
2023-01-22 23:59:30.446619: step: 820/530, loss: 0.3151586651802063
2023-01-22 23:59:31.552754: step: 824/530, loss: 0.09283819794654846
2023-01-22 23:59:32.689028: step: 828/530, loss: 0.11414463818073273
2023-01-22 23:59:33.839065: step: 832/530, loss: 0.7769097089767456
2023-01-22 23:59:34.989421: step: 836/530, loss: 0.20338688790798187
2023-01-22 23:59:36.141145: step: 840/530, loss: 0.9682126045227051
2023-01-22 23:59:37.279788: step: 844/530, loss: 0.4638552665710449
2023-01-22 23:59:38.429657: step: 848/530, loss: 0.7936142683029175
2023-01-22 23:59:39.536187: step: 852/530, loss: 0.16188031435012817
2023-01-22 23:59:40.634451: step: 856/530, loss: 0.07353615760803223
2023-01-22 23:59:41.765418: step: 860/530, loss: 0.10312461853027344
2023-01-22 23:59:42.869185: step: 864/530, loss: 0.10354427993297577
2023-01-22 23:59:43.980484: step: 868/530, loss: 0.23886442184448242
2023-01-22 23:59:45.084592: step: 872/530, loss: 0.31222569942474365
2023-01-22 23:59:46.195185: step: 876/530, loss: 0.08500252664089203
2023-01-22 23:59:47.355964: step: 880/530, loss: 0.30035269260406494
2023-01-22 23:59:48.466683: step: 884/530, loss: 0.28802254796028137
2023-01-22 23:59:49.532095: step: 888/530, loss: 0.04839920997619629
2023-01-22 23:59:50.654517: step: 892/530, loss: 0.539877712726593
2023-01-22 23:59:51.785793: step: 896/530, loss: 0.710597813129425
2023-01-22 23:59:52.908431: step: 900/530, loss: 0.21863803267478943
2023-01-22 23:59:54.018026: step: 904/530, loss: 1.9587645530700684
2023-01-22 23:59:55.154130: step: 908/530, loss: 0.23699207603931427
2023-01-22 23:59:56.271446: step: 912/530, loss: 0.7093230485916138
2023-01-22 23:59:57.399213: step: 916/530, loss: 0.6573853492736816
2023-01-22 23:59:58.510428: step: 920/530, loss: 0.19469384849071503
2023-01-22 23:59:59.611812: step: 924/530, loss: 0.5714029669761658
2023-01-23 00:00:00.760023: step: 928/530, loss: 0.25678300857543945
2023-01-23 00:00:01.890691: step: 932/530, loss: 0.1119375228881836
2023-01-23 00:00:03.021880: step: 936/530, loss: 0.0706668347120285
2023-01-23 00:00:04.144045: step: 940/530, loss: 0.2677582800388336
2023-01-23 00:00:05.235957: step: 944/530, loss: 0.10434536635875702
2023-01-23 00:00:06.354911: step: 948/530, loss: 0.35396918654441833
2023-01-23 00:00:07.516322: step: 952/530, loss: 0.7816277742385864
2023-01-23 00:00:08.631582: step: 956/530, loss: 6.337296962738037
2023-01-23 00:00:09.745075: step: 960/530, loss: 0.04668422043323517
2023-01-23 00:00:10.900033: step: 964/530, loss: 0.2845540940761566
2023-01-23 00:00:12.021312: step: 968/530, loss: 0.11601004749536514
2023-01-23 00:00:13.154332: step: 972/530, loss: 0.869560718536377
2023-01-23 00:00:14.264041: step: 976/530, loss: 0.18167667090892792
2023-01-23 00:00:15.411355: step: 980/530, loss: 0.4020606279373169
2023-01-23 00:00:16.524588: step: 984/530, loss: 0.12131624668836594
2023-01-23 00:00:17.659958: step: 988/530, loss: 0.2102939486503601
2023-01-23 00:00:18.814431: step: 992/530, loss: 0.44801560044288635
2023-01-23 00:00:19.934756: step: 996/530, loss: 0.13658258318901062
2023-01-23 00:00:21.075242: step: 1000/530, loss: 0.3587406873703003
2023-01-23 00:00:22.197459: step: 1004/530, loss: 0.16822342574596405
2023-01-23 00:00:23.355771: step: 1008/530, loss: 0.24062567949295044
2023-01-23 00:00:24.504026: step: 1012/530, loss: 0.12505730986595154
2023-01-23 00:00:25.677524: step: 1016/530, loss: 0.5557454228401184
2023-01-23 00:00:26.804637: step: 1020/530, loss: 0.693396270275116
2023-01-23 00:00:27.917764: step: 1024/530, loss: 0.1114506721496582
2023-01-23 00:00:29.053312: step: 1028/530, loss: 0.21157866716384888
2023-01-23 00:00:30.185049: step: 1032/530, loss: 0.4216056764125824
2023-01-23 00:00:31.320780: step: 1036/530, loss: 0.32248449325561523
2023-01-23 00:00:32.456795: step: 1040/530, loss: 0.1275119185447693
2023-01-23 00:00:33.568311: step: 1044/530, loss: 0.142400324344635
2023-01-23 00:00:34.692440: step: 1048/530, loss: 0.7415033578872681
2023-01-23 00:00:35.802153: step: 1052/530, loss: 0.2202221006155014
2023-01-23 00:00:36.924066: step: 1056/530, loss: 0.0769352912902832
2023-01-23 00:00:38.065784: step: 1060/530, loss: 0.42288094758987427
2023-01-23 00:00:39.171654: step: 1064/530, loss: 0.09324227273464203
2023-01-23 00:00:40.291115: step: 1068/530, loss: 1.3253374099731445
2023-01-23 00:00:41.423836: step: 1072/530, loss: 0.7777339220046997
2023-01-23 00:00:42.546789: step: 1076/530, loss: 0.08843765407800674
2023-01-23 00:00:43.690489: step: 1080/530, loss: 0.4438443183898926
2023-01-23 00:00:44.819859: step: 1084/530, loss: 0.2560030519962311
2023-01-23 00:00:45.910878: step: 1088/530, loss: 0.06521987915039062
2023-01-23 00:00:47.041960: step: 1092/530, loss: 0.739310085773468
2023-01-23 00:00:48.145235: step: 1096/530, loss: 0.13745641708374023
2023-01-23 00:00:49.267148: step: 1100/530, loss: 1.1782341003417969
2023-01-23 00:00:50.391166: step: 1104/530, loss: 0.16865158081054688
2023-01-23 00:00:51.512402: step: 1108/530, loss: 0.1872844696044922
2023-01-23 00:00:52.661333: step: 1112/530, loss: 0.6049100160598755
2023-01-23 00:00:53.808946: step: 1116/530, loss: 0.6019338369369507
2023-01-23 00:00:54.932815: step: 1120/530, loss: 0.42210477590560913
2023-01-23 00:00:56.045506: step: 1124/530, loss: 0.28427088260650635
2023-01-23 00:00:57.196470: step: 1128/530, loss: 0.08407735824584961
2023-01-23 00:00:58.366371: step: 1132/530, loss: 0.6136186718940735
2023-01-23 00:00:59.507637: step: 1136/530, loss: 0.11276464909315109
2023-01-23 00:01:00.626348: step: 1140/530, loss: 0.4786517024040222
2023-01-23 00:01:01.757036: step: 1144/530, loss: 0.3155521750450134
2023-01-23 00:01:02.887053: step: 1148/530, loss: 1.332437515258789
2023-01-23 00:01:03.980112: step: 1152/530, loss: 0.38677850365638733
2023-01-23 00:01:05.121897: step: 1156/530, loss: 0.19574908912181854
2023-01-23 00:01:06.235094: step: 1160/530, loss: 0.1790851205587387
2023-01-23 00:01:07.379664: step: 1164/530, loss: 0.3607296943664551
2023-01-23 00:01:08.522929: step: 1168/530, loss: 0.8320285081863403
2023-01-23 00:01:09.634685: step: 1172/530, loss: 0.1929721236228943
2023-01-23 00:01:10.757574: step: 1176/530, loss: 1.0880717039108276
2023-01-23 00:01:11.885475: step: 1180/530, loss: 0.17029863595962524
2023-01-23 00:01:13.013852: step: 1184/530, loss: 0.30269670486450195
2023-01-23 00:01:14.127935: step: 1188/530, loss: 0.36966878175735474
2023-01-23 00:01:15.277616: step: 1192/530, loss: 0.09792809933423996
2023-01-23 00:01:16.425441: step: 1196/530, loss: 0.13636694848537445
2023-01-23 00:01:17.537224: step: 1200/530, loss: 0.3022838830947876
2023-01-23 00:01:18.644741: step: 1204/530, loss: 0.34465765953063965
2023-01-23 00:01:19.771943: step: 1208/530, loss: 0.4255351126194
2023-01-23 00:01:20.891843: step: 1212/530, loss: 0.07824020087718964
2023-01-23 00:01:22.031514: step: 1216/530, loss: 0.9964789748191833
2023-01-23 00:01:23.164678: step: 1220/530, loss: 0.047849610447883606
2023-01-23 00:01:24.266322: step: 1224/530, loss: 0.15184727311134338
2023-01-23 00:01:25.386941: step: 1228/530, loss: 0.1626778542995453
2023-01-23 00:01:26.538074: step: 1232/530, loss: 0.10159101337194443
2023-01-23 00:01:27.648964: step: 1236/530, loss: 0.10504229366779327
2023-01-23 00:01:28.787743: step: 1240/530, loss: 0.5259441137313843
2023-01-23 00:01:29.901925: step: 1244/530, loss: 8.02356243133545
2023-01-23 00:01:31.020734: step: 1248/530, loss: 0.21302662789821625
2023-01-23 00:01:32.160796: step: 1252/530, loss: 0.3146812319755554
2023-01-23 00:01:33.266697: step: 1256/530, loss: 0.11408501118421555
2023-01-23 00:01:34.387794: step: 1260/530, loss: 0.7517045736312866
2023-01-23 00:01:35.505370: step: 1264/530, loss: 0.7985848188400269
2023-01-23 00:01:36.618801: step: 1268/530, loss: 0.27232933044433594
2023-01-23 00:01:37.729996: step: 1272/530, loss: 0.31952157616615295
2023-01-23 00:01:38.861609: step: 1276/530, loss: 0.21916276216506958
2023-01-23 00:01:39.979056: step: 1280/530, loss: 0.04496030882000923
2023-01-23 00:01:41.123452: step: 1284/530, loss: 0.11020383983850479
2023-01-23 00:01:42.223317: step: 1288/530, loss: 0.18361882865428925
2023-01-23 00:01:43.348809: step: 1292/530, loss: 0.4127759039402008
2023-01-23 00:01:44.459970: step: 1296/530, loss: 0.16507530212402344
2023-01-23 00:01:45.592018: step: 1300/530, loss: 0.19806194305419922
2023-01-23 00:01:46.680449: step: 1304/530, loss: 0.04165811464190483
2023-01-23 00:01:47.795260: step: 1308/530, loss: 0.1296827346086502
2023-01-23 00:01:48.929491: step: 1312/530, loss: 0.1720447540283203
2023-01-23 00:01:50.068287: step: 1316/530, loss: 0.9106971621513367
2023-01-23 00:01:51.227416: step: 1320/530, loss: 0.2494775801897049
2023-01-23 00:01:52.345520: step: 1324/530, loss: 0.38870009779930115
2023-01-23 00:01:53.445766: step: 1328/530, loss: 0.13143309950828552
2023-01-23 00:01:54.559743: step: 1332/530, loss: 0.3807516098022461
2023-01-23 00:01:55.691008: step: 1336/530, loss: 0.43951416015625
2023-01-23 00:01:56.824848: step: 1340/530, loss: 0.8405409455299377
2023-01-23 00:01:57.939431: step: 1344/530, loss: 0.142801433801651
2023-01-23 00:01:59.012191: step: 1348/530, loss: 0.1895488202571869
2023-01-23 00:02:00.146876: step: 1352/530, loss: 0.2847919464111328
2023-01-23 00:02:01.238158: step: 1356/530, loss: 0.07428627461194992
2023-01-23 00:02:02.364138: step: 1360/530, loss: 0.07416939735412598
2023-01-23 00:02:03.505569: step: 1364/530, loss: 0.11670255661010742
2023-01-23 00:02:04.618918: step: 1368/530, loss: 0.2198708951473236
2023-01-23 00:02:05.764150: step: 1372/530, loss: 0.08131561428308487
2023-01-23 00:02:06.896722: step: 1376/530, loss: 0.208016499876976
2023-01-23 00:02:08.008694: step: 1380/530, loss: 0.08762387931346893
2023-01-23 00:02:09.139259: step: 1384/530, loss: 0.3269149661064148
2023-01-23 00:02:10.287028: step: 1388/530, loss: 0.2431713044643402
2023-01-23 00:02:11.422538: step: 1392/530, loss: 0.6110830307006836
2023-01-23 00:02:12.546950: step: 1396/530, loss: 0.0643744021654129
2023-01-23 00:02:13.692212: step: 1400/530, loss: 1.9066836833953857
2023-01-23 00:02:14.815661: step: 1404/530, loss: 0.514267086982727
2023-01-23 00:02:15.937502: step: 1408/530, loss: 0.16873283684253693
2023-01-23 00:02:17.078905: step: 1412/530, loss: 0.2858301103115082
2023-01-23 00:02:18.211996: step: 1416/530, loss: 0.19447803497314453
2023-01-23 00:02:19.331953: step: 1420/530, loss: 0.7655235528945923
2023-01-23 00:02:20.463226: step: 1424/530, loss: 0.9057453274726868
2023-01-23 00:02:21.582788: step: 1428/530, loss: 0.2897835969924927
2023-01-23 00:02:22.723681: step: 1432/530, loss: 0.18510980904102325
2023-01-23 00:02:23.853051: step: 1436/530, loss: 0.11482544243335724
2023-01-23 00:02:24.972557: step: 1440/530, loss: 0.07887572795152664
2023-01-23 00:02:26.097784: step: 1444/530, loss: 0.20164881646633148
2023-01-23 00:02:27.225812: step: 1448/530, loss: 0.48689284920692444
2023-01-23 00:02:28.350633: step: 1452/530, loss: 0.045612335205078125
2023-01-23 00:02:29.477509: step: 1456/530, loss: 0.677822470664978
2023-01-23 00:02:30.581798: step: 1460/530, loss: 0.8919574022293091
2023-01-23 00:02:31.699196: step: 1464/530, loss: 0.160923570394516
2023-01-23 00:02:32.857974: step: 1468/530, loss: 0.14006395637989044
2023-01-23 00:02:33.956649: step: 1472/530, loss: 0.1263522207736969
2023-01-23 00:02:35.113401: step: 1476/530, loss: 0.04875602945685387
2023-01-23 00:02:36.235294: step: 1480/530, loss: 0.11507539451122284
2023-01-23 00:02:37.334437: step: 1484/530, loss: 0.4592326283454895
2023-01-23 00:02:38.453005: step: 1488/530, loss: 0.9233525395393372
2023-01-23 00:02:39.573451: step: 1492/530, loss: 0.21476107835769653
2023-01-23 00:02:40.681694: step: 1496/530, loss: 0.05584440380334854
2023-01-23 00:02:41.783635: step: 1500/530, loss: 0.05728616937994957
2023-01-23 00:02:42.888032: step: 1504/530, loss: 0.9771144390106201
2023-01-23 00:02:44.007335: step: 1508/530, loss: 0.3630111515522003
2023-01-23 00:02:45.122092: step: 1512/530, loss: 0.12333698570728302
2023-01-23 00:02:46.279903: step: 1516/530, loss: 0.2548215985298157
2023-01-23 00:02:47.417407: step: 1520/530, loss: 0.6190086603164673
2023-01-23 00:02:48.552460: step: 1524/530, loss: 0.2342969924211502
2023-01-23 00:02:49.671492: step: 1528/530, loss: 0.34411242604255676
2023-01-23 00:02:50.783592: step: 1532/530, loss: 0.21410337090492249
2023-01-23 00:02:51.912764: step: 1536/530, loss: 1.0242745876312256
2023-01-23 00:02:53.036641: step: 1540/530, loss: 0.13568997383117676
2023-01-23 00:02:54.140261: step: 1544/530, loss: 0.2209858000278473
2023-01-23 00:02:55.256491: step: 1548/530, loss: 0.026560211554169655
2023-01-23 00:02:56.402839: step: 1552/530, loss: 0.23429393768310547
2023-01-23 00:02:57.493326: step: 1556/530, loss: 0.04659919813275337
2023-01-23 00:02:58.634708: step: 1560/530, loss: 0.9354751706123352
2023-01-23 00:02:59.766064: step: 1564/530, loss: 0.5804479122161865
2023-01-23 00:03:00.892593: step: 1568/530, loss: 0.36770325899124146
2023-01-23 00:03:02.010074: step: 1572/530, loss: 0.09268569946289062
2023-01-23 00:03:03.105540: step: 1576/530, loss: 0.07004991173744202
2023-01-23 00:03:04.227729: step: 1580/530, loss: 0.48980700969696045
2023-01-23 00:03:05.363576: step: 1584/530, loss: 0.585756778717041
2023-01-23 00:03:06.485754: step: 1588/530, loss: 0.09195587784051895
2023-01-23 00:03:07.604301: step: 1592/530, loss: 0.32577866315841675
2023-01-23 00:03:08.716096: step: 1596/530, loss: 0.04666896164417267
2023-01-23 00:03:09.884585: step: 1600/530, loss: 6.151769161224365
2023-01-23 00:03:11.006217: step: 1604/530, loss: 0.13677054643630981
2023-01-23 00:03:12.135142: step: 1608/530, loss: 0.7264582514762878
2023-01-23 00:03:13.258297: step: 1612/530, loss: 0.44529154896736145
2023-01-23 00:03:14.422338: step: 1616/530, loss: 0.26551979780197144
2023-01-23 00:03:15.554377: step: 1620/530, loss: 0.18485456705093384
2023-01-23 00:03:16.690230: step: 1624/530, loss: 0.5798535346984863
2023-01-23 00:03:17.818842: step: 1628/530, loss: 0.13767534494400024
2023-01-23 00:03:18.964553: step: 1632/530, loss: 1.4618440866470337
2023-01-23 00:03:20.078655: step: 1636/530, loss: 0.06379413604736328
2023-01-23 00:03:21.211974: step: 1640/530, loss: 0.12085109204053879
2023-01-23 00:03:22.334101: step: 1644/530, loss: 0.5972986221313477
2023-01-23 00:03:23.445799: step: 1648/530, loss: 0.17446888983249664
2023-01-23 00:03:24.544117: step: 1652/530, loss: 0.7446853518486023
2023-01-23 00:03:25.702014: step: 1656/530, loss: 0.1470375657081604
2023-01-23 00:03:26.810191: step: 1660/530, loss: 0.5677639842033386
2023-01-23 00:03:27.939067: step: 1664/530, loss: 0.28879988193511963
2023-01-23 00:03:29.054554: step: 1668/530, loss: 0.1233987808227539
2023-01-23 00:03:30.185072: step: 1672/530, loss: 0.36274638772010803
2023-01-23 00:03:31.306082: step: 1676/530, loss: 0.13657522201538086
2023-01-23 00:03:32.423774: step: 1680/530, loss: 0.8815388679504395
2023-01-23 00:03:33.533573: step: 1684/530, loss: 0.33287304639816284
2023-01-23 00:03:34.640659: step: 1688/530, loss: 0.5164784789085388
2023-01-23 00:03:35.785380: step: 1692/530, loss: 0.42818278074264526
2023-01-23 00:03:36.903347: step: 1696/530, loss: 0.035449910908937454
2023-01-23 00:03:38.029496: step: 1700/530, loss: 0.2492295801639557
2023-01-23 00:03:39.169094: step: 1704/530, loss: 0.16623243689537048
2023-01-23 00:03:40.297755: step: 1708/530, loss: 1.0236146450042725
2023-01-23 00:03:41.428734: step: 1712/530, loss: 0.1681804656982422
2023-01-23 00:03:42.544205: step: 1716/530, loss: 0.3860305845737457
2023-01-23 00:03:43.650606: step: 1720/530, loss: 0.2120051383972168
2023-01-23 00:03:44.750967: step: 1724/530, loss: 0.7842609286308289
2023-01-23 00:03:45.869710: step: 1728/530, loss: 1.6515214443206787
2023-01-23 00:03:46.992705: step: 1732/530, loss: 0.13141250610351562
2023-01-23 00:03:48.092285: step: 1736/530, loss: 0.08918621391057968
2023-01-23 00:03:49.185365: step: 1740/530, loss: 0.16304850578308105
2023-01-23 00:03:50.323948: step: 1744/530, loss: 2.0773239135742188
2023-01-23 00:03:51.469757: step: 1748/530, loss: 1.048683524131775
2023-01-23 00:03:52.591517: step: 1752/530, loss: 0.17725367844104767
2023-01-23 00:03:53.675870: step: 1756/530, loss: 0.6948029398918152
2023-01-23 00:03:54.802289: step: 1760/530, loss: 1.403632640838623
2023-01-23 00:03:55.910284: step: 1764/530, loss: 0.21824435889720917
2023-01-23 00:03:57.035037: step: 1768/530, loss: 0.7054895162582397
2023-01-23 00:03:58.141437: step: 1772/530, loss: 0.22495470941066742
2023-01-23 00:03:59.266085: step: 1776/530, loss: 0.49282923340797424
2023-01-23 00:04:00.385935: step: 1780/530, loss: 0.18711167573928833
2023-01-23 00:04:01.504747: step: 1784/530, loss: 0.07118716835975647
2023-01-23 00:04:02.665488: step: 1788/530, loss: 0.45792192220687866
2023-01-23 00:04:03.790537: step: 1792/530, loss: 0.11594811081886292
2023-01-23 00:04:04.921938: step: 1796/530, loss: 0.5197655558586121
2023-01-23 00:04:06.043255: step: 1800/530, loss: 0.7505996823310852
2023-01-23 00:04:07.170919: step: 1804/530, loss: 0.8414021730422974
2023-01-23 00:04:08.307002: step: 1808/530, loss: 1.1111630201339722
2023-01-23 00:04:09.440490: step: 1812/530, loss: 0.25381165742874146
2023-01-23 00:04:10.545378: step: 1816/530, loss: 0.32689225673675537
2023-01-23 00:04:11.661758: step: 1820/530, loss: 0.1935802400112152
2023-01-23 00:04:12.804441: step: 1824/530, loss: 0.08370056003332138
2023-01-23 00:04:13.888977: step: 1828/530, loss: 0.21775542199611664
2023-01-23 00:04:15.018995: step: 1832/530, loss: 0.29918763041496277
2023-01-23 00:04:16.155166: step: 1836/530, loss: 0.12295322120189667
2023-01-23 00:04:17.286034: step: 1840/530, loss: 0.7260211706161499
2023-01-23 00:04:18.403544: step: 1844/530, loss: 0.1619025319814682
2023-01-23 00:04:19.515200: step: 1848/530, loss: 0.06291775405406952
2023-01-23 00:04:20.622996: step: 1852/530, loss: 0.2906424105167389
2023-01-23 00:04:21.744350: step: 1856/530, loss: 0.23726846277713776
2023-01-23 00:04:22.880640: step: 1860/530, loss: 0.5974012613296509
2023-01-23 00:04:23.974648: step: 1864/530, loss: 0.6490985155105591
2023-01-23 00:04:25.086003: step: 1868/530, loss: 0.51610267162323
2023-01-23 00:04:26.208694: step: 1872/530, loss: 0.10148139297962189
2023-01-23 00:04:27.322771: step: 1876/530, loss: 0.5994809865951538
2023-01-23 00:04:28.437477: step: 1880/530, loss: 0.09673991054296494
2023-01-23 00:04:29.543926: step: 1884/530, loss: 0.6247178912162781
2023-01-23 00:04:30.676688: step: 1888/530, loss: 0.1039685308933258
2023-01-23 00:04:31.820384: step: 1892/530, loss: 0.4099477529525757
2023-01-23 00:04:32.944239: step: 1896/530, loss: 0.8992904424667358
2023-01-23 00:04:34.054531: step: 1900/530, loss: 0.583234965801239
2023-01-23 00:04:35.172086: step: 1904/530, loss: 0.3806690275669098
2023-01-23 00:04:36.283161: step: 1908/530, loss: 0.5566908121109009
2023-01-23 00:04:37.439564: step: 1912/530, loss: 0.11651559919118881
2023-01-23 00:04:38.558449: step: 1916/530, loss: 1.0576083660125732
2023-01-23 00:04:39.719388: step: 1920/530, loss: 0.16118082404136658
2023-01-23 00:04:40.853729: step: 1924/530, loss: 0.12736625969409943
2023-01-23 00:04:41.956572: step: 1928/530, loss: 0.13824300467967987
2023-01-23 00:04:43.070984: step: 1932/530, loss: 0.41821566224098206
2023-01-23 00:04:44.189220: step: 1936/530, loss: 0.7704918384552002
2023-01-23 00:04:45.337564: step: 1940/530, loss: 0.7969303131103516
2023-01-23 00:04:46.459593: step: 1944/530, loss: 0.08521604537963867
2023-01-23 00:04:47.594818: step: 1948/530, loss: 0.07951287925243378
2023-01-23 00:04:48.702196: step: 1952/530, loss: 0.17035618424415588
2023-01-23 00:04:49.803343: step: 1956/530, loss: 0.10889606177806854
2023-01-23 00:04:50.947632: step: 1960/530, loss: 6.4887003898620605
2023-01-23 00:04:52.080028: step: 1964/530, loss: 0.046761225908994675
2023-01-23 00:04:53.204755: step: 1968/530, loss: 0.006165886297821999
2023-01-23 00:04:54.322490: step: 1972/530, loss: 0.035973500460386276
2023-01-23 00:04:55.402675: step: 1976/530, loss: 0.04148568958044052
2023-01-23 00:04:56.497135: step: 1980/530, loss: 2.423964500427246
2023-01-23 00:04:57.664746: step: 1984/530, loss: 1.4673709869384766
2023-01-23 00:04:58.790067: step: 1988/530, loss: 2.032862663269043
2023-01-23 00:04:59.899550: step: 1992/530, loss: 1.201643466949463
2023-01-23 00:05:01.030278: step: 1996/530, loss: 0.1756226122379303
2023-01-23 00:05:02.211293: step: 2000/530, loss: 0.24756136536598206
2023-01-23 00:05:03.336225: step: 2004/530, loss: 0.26147061586380005
2023-01-23 00:05:04.491912: step: 2008/530, loss: 0.5023872256278992
2023-01-23 00:05:05.601913: step: 2012/530, loss: 0.18697504699230194
2023-01-23 00:05:06.759440: step: 2016/530, loss: 0.7710103988647461
2023-01-23 00:05:07.882933: step: 2020/530, loss: 0.4787195324897766
2023-01-23 00:05:09.010980: step: 2024/530, loss: 0.5848315358161926
2023-01-23 00:05:10.139420: step: 2028/530, loss: 0.27945375442504883
2023-01-23 00:05:11.260726: step: 2032/530, loss: 0.25259438157081604
2023-01-23 00:05:12.378060: step: 2036/530, loss: 0.5716609954833984
2023-01-23 00:05:13.508907: step: 2040/530, loss: 0.053400229662656784
2023-01-23 00:05:14.612861: step: 2044/530, loss: 1.0147889852523804
2023-01-23 00:05:15.745844: step: 2048/530, loss: 0.07517776638269424
2023-01-23 00:05:16.894489: step: 2052/530, loss: 0.2517591714859009
2023-01-23 00:05:18.003164: step: 2056/530, loss: 0.17578890919685364
2023-01-23 00:05:19.145950: step: 2060/530, loss: 0.3270758390426636
2023-01-23 00:05:20.273462: step: 2064/530, loss: 0.8309615850448608
2023-01-23 00:05:21.399734: step: 2068/530, loss: 3.2110702991485596
2023-01-23 00:05:22.532358: step: 2072/530, loss: 0.05585131794214249
2023-01-23 00:05:23.642881: step: 2076/530, loss: 0.1288878470659256
2023-01-23 00:05:24.795227: step: 2080/530, loss: 0.3452204167842865
2023-01-23 00:05:25.898096: step: 2084/530, loss: 0.13798275589942932
2023-01-23 00:05:27.002899: step: 2088/530, loss: 0.08709807693958282
2023-01-23 00:05:28.117099: step: 2092/530, loss: 0.25586891174316406
2023-01-23 00:05:29.264706: step: 2096/530, loss: 0.08041448891162872
2023-01-23 00:05:30.368662: step: 2100/530, loss: 0.39065685868263245
2023-01-23 00:05:31.507824: step: 2104/530, loss: 0.19825562834739685
2023-01-23 00:05:32.643210: step: 2108/530, loss: 0.626522421836853
2023-01-23 00:05:33.777626: step: 2112/530, loss: 0.08409452438354492
2023-01-23 00:05:34.932999: step: 2116/530, loss: 0.12319669872522354
2023-01-23 00:05:36.067079: step: 2120/530, loss: 0.44887515902519226
==================================================
Loss: 0.493
--------------------
Dev: {'event': {'p': 0.5832471561530507, 'r': 0.7509986684420772, 'f1': 0.6565774155995343}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Test: {'event': {'p': 0.603579418344519, 'r': 0.7708571428571429, 'f1': 0.6770388958594731}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Chinese: {'event': {'p': 0.575, 'r': 0.8518518518518519, 'f1': 0.6865671641791045}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Korean: {'event': {'p': 0.6470588235294118, 'r': 0.5238095238095238, 'f1': 0.5789473684210527}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Russian: {'event': {'p': 0.43243243243243246, 'r': 0.4444444444444444, 'f1': 0.4383561643835616}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
New best chinese model...
New best korean model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.5832471561530507, 'r': 0.7509986684420772, 'f1': 0.6565774155995343}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Chinese: {'event': {'p': 0.603579418344519, 'r': 0.7708571428571429, 'f1': 0.6770388958594731}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Chinese: {'event': {'p': 0.575, 'r': 0.8518518518518519, 'f1': 0.6865671641791045}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5832471561530507, 'r': 0.7509986684420772, 'f1': 0.6565774155995343}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Korean: {'event': {'p': 0.603579418344519, 'r': 0.7708571428571429, 'f1': 0.6770388958594731}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Korean: {'event': {'p': 0.6470588235294118, 'r': 0.5238095238095238, 'f1': 0.5789473684210527}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6436170212765957, 'r': 0.644474034620506, 'f1': 0.6440452428476381}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Eng Test for Russian: {'event': {'p': 0.6642728904847397, 'r': 0.6342857142857142, 'f1': 0.6489330605086231}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Sample Russian: {'event': {'p': 0.64, 'r': 0.4444444444444444, 'f1': 0.5245901639344263}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
******************************
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 00:06:32.331944: step: 4/530, loss: 0.2426898032426834
2023-01-23 00:06:33.485661: step: 8/530, loss: 0.20357075333595276
2023-01-23 00:06:34.624468: step: 12/530, loss: 0.07590899616479874
2023-01-23 00:06:35.725137: step: 16/530, loss: 0.09386958926916122
2023-01-23 00:06:36.827376: step: 20/530, loss: 0.14798539876937866
2023-01-23 00:06:37.946957: step: 24/530, loss: 0.7234320640563965
2023-01-23 00:06:39.059431: step: 28/530, loss: 0.10331859439611435
2023-01-23 00:06:40.169283: step: 32/530, loss: 0.10128088295459747
2023-01-23 00:06:41.306923: step: 36/530, loss: 0.6619992256164551
2023-01-23 00:06:42.438025: step: 40/530, loss: 0.1277463436126709
2023-01-23 00:06:43.557720: step: 44/530, loss: 0.07528219372034073
2023-01-23 00:06:44.700620: step: 48/530, loss: 0.9066574573516846
2023-01-23 00:06:45.803559: step: 52/530, loss: 0.059286929666996
2023-01-23 00:06:46.950361: step: 56/530, loss: 0.3750576972961426
2023-01-23 00:06:48.076759: step: 60/530, loss: 0.21866169571876526
2023-01-23 00:06:49.193734: step: 64/530, loss: 0.19564051926136017
2023-01-23 00:06:50.297058: step: 68/530, loss: 0.651627242565155
2023-01-23 00:06:51.403274: step: 72/530, loss: 0.7306483387947083
2023-01-23 00:06:52.524431: step: 76/530, loss: 0.0267396941781044
2023-01-23 00:06:53.617922: step: 80/530, loss: 0.09535031765699387
2023-01-23 00:06:54.739388: step: 84/530, loss: 0.3563896417617798
2023-01-23 00:06:55.853360: step: 88/530, loss: 0.6136549711227417
2023-01-23 00:06:57.004520: step: 92/530, loss: 0.09629111737012863
2023-01-23 00:06:58.131876: step: 96/530, loss: 1.346459150314331
2023-01-23 00:06:59.258272: step: 100/530, loss: 0.1783783882856369
2023-01-23 00:07:00.395474: step: 104/530, loss: 0.28856849670410156
2023-01-23 00:07:01.531668: step: 108/530, loss: 0.11380644142627716
2023-01-23 00:07:02.674952: step: 112/530, loss: 1.292015552520752
2023-01-23 00:07:03.802448: step: 116/530, loss: 0.08938512951135635
2023-01-23 00:07:04.917126: step: 120/530, loss: 1.0643033981323242
2023-01-23 00:07:06.075755: step: 124/530, loss: 0.1515856683254242
2023-01-23 00:07:07.202877: step: 128/530, loss: 0.5604331493377686
2023-01-23 00:07:08.333507: step: 132/530, loss: 0.08894267678260803
2023-01-23 00:07:09.460039: step: 136/530, loss: 0.13017530739307404
2023-01-23 00:07:10.610869: step: 140/530, loss: 0.09927596896886826
2023-01-23 00:07:11.755072: step: 144/530, loss: 0.09744873642921448
2023-01-23 00:07:12.915080: step: 148/530, loss: 0.19730836153030396
2023-01-23 00:07:14.024326: step: 152/530, loss: 0.7384673357009888
2023-01-23 00:07:15.142324: step: 156/530, loss: 0.2800275683403015
2023-01-23 00:07:16.247498: step: 160/530, loss: 0.12046681344509125
2023-01-23 00:07:17.371205: step: 164/530, loss: 0.02410411834716797
2023-01-23 00:07:18.526681: step: 168/530, loss: 0.02486124075949192
2023-01-23 00:07:19.668537: step: 172/530, loss: 0.09562597423791885
2023-01-23 00:07:20.751723: step: 176/530, loss: 0.08392749726772308
2023-01-23 00:07:21.878734: step: 180/530, loss: 0.07321682572364807
2023-01-23 00:07:23.047807: step: 184/530, loss: 0.15812483429908752
2023-01-23 00:07:24.163938: step: 188/530, loss: 0.37360915541648865
2023-01-23 00:07:25.296423: step: 192/530, loss: 0.5706270337104797
2023-01-23 00:07:26.428509: step: 196/530, loss: 1.1458741426467896
2023-01-23 00:07:27.541218: step: 200/530, loss: 0.15156421065330505
2023-01-23 00:07:28.648834: step: 204/530, loss: 0.3389979898929596
2023-01-23 00:07:29.760491: step: 208/530, loss: 0.10417509078979492
2023-01-23 00:07:30.866697: step: 212/530, loss: 0.09341412037611008
2023-01-23 00:07:32.019299: step: 216/530, loss: 1.0482102632522583
2023-01-23 00:07:33.150913: step: 220/530, loss: 0.12351961433887482
2023-01-23 00:07:34.322850: step: 224/530, loss: 0.4129384160041809
2023-01-23 00:07:35.451715: step: 228/530, loss: 0.2869279086589813
2023-01-23 00:07:36.598815: step: 232/530, loss: 0.19159956276416779
2023-01-23 00:07:37.725007: step: 236/530, loss: 0.09985899925231934
2023-01-23 00:07:38.844830: step: 240/530, loss: 1.044792890548706
2023-01-23 00:07:39.985556: step: 244/530, loss: 0.6497471928596497
2023-01-23 00:07:41.092220: step: 248/530, loss: 0.0644163116812706
2023-01-23 00:07:42.205703: step: 252/530, loss: 0.12396059185266495
2023-01-23 00:07:43.342136: step: 256/530, loss: 0.125981867313385
2023-01-23 00:07:44.481490: step: 260/530, loss: 0.1220371276140213
2023-01-23 00:07:45.603947: step: 264/530, loss: 0.32602912187576294
2023-01-23 00:07:46.739949: step: 268/530, loss: 1.0321238040924072
2023-01-23 00:07:47.893569: step: 272/530, loss: 0.1178189292550087
2023-01-23 00:07:49.067150: step: 276/530, loss: 0.16814814507961273
2023-01-23 00:07:50.210024: step: 280/530, loss: 0.14084625244140625
2023-01-23 00:07:51.311852: step: 284/530, loss: 0.0956568717956543
2023-01-23 00:07:52.426696: step: 288/530, loss: 0.5914638638496399
2023-01-23 00:07:53.562013: step: 292/530, loss: 0.16256102919578552
2023-01-23 00:07:54.690647: step: 296/530, loss: 0.410400390625
2023-01-23 00:07:55.825016: step: 300/530, loss: 0.05446135997772217
2023-01-23 00:07:57.010008: step: 304/530, loss: 0.37062549591064453
2023-01-23 00:07:58.190739: step: 308/530, loss: 0.25865477323532104
2023-01-23 00:07:59.325784: step: 312/530, loss: 0.21905192732810974
2023-01-23 00:08:00.444867: step: 316/530, loss: 0.08423290401697159
2023-01-23 00:08:01.552095: step: 320/530, loss: 0.40526628494262695
2023-01-23 00:08:02.667707: step: 324/530, loss: 0.5596331357955933
2023-01-23 00:08:03.803965: step: 328/530, loss: 0.057629965245723724
2023-01-23 00:08:04.924921: step: 332/530, loss: 0.07920923829078674
2023-01-23 00:08:06.047013: step: 336/530, loss: 0.28068098425865173
2023-01-23 00:08:07.178177: step: 340/530, loss: 0.12315788865089417
2023-01-23 00:08:08.281210: step: 344/530, loss: 0.04610776901245117
2023-01-23 00:08:09.403505: step: 348/530, loss: 0.10983829945325851
2023-01-23 00:08:10.543080: step: 352/530, loss: 0.13707371056079865
2023-01-23 00:08:11.658754: step: 356/530, loss: 0.04855484887957573
2023-01-23 00:08:12.781713: step: 360/530, loss: 0.15080510079860687
2023-01-23 00:08:13.905799: step: 364/530, loss: 0.2960459887981415
2023-01-23 00:08:15.019833: step: 368/530, loss: 0.38567107915878296
2023-01-23 00:08:16.136302: step: 372/530, loss: 0.8939532041549683
2023-01-23 00:08:17.261098: step: 376/530, loss: 0.016727160662412643
2023-01-23 00:08:18.362629: step: 380/530, loss: 0.24768222868442535
2023-01-23 00:08:19.503323: step: 384/530, loss: 0.7668226957321167
2023-01-23 00:08:20.645435: step: 388/530, loss: 0.7150883674621582
2023-01-23 00:08:21.780203: step: 392/530, loss: 1.1176691055297852
2023-01-23 00:08:22.931747: step: 396/530, loss: 0.05874443054199219
2023-01-23 00:08:24.071355: step: 400/530, loss: 0.03908901289105415
2023-01-23 00:08:25.213811: step: 404/530, loss: 0.9112390279769897
2023-01-23 00:08:26.358200: step: 408/530, loss: 0.09809088706970215
2023-01-23 00:08:27.581657: step: 412/530, loss: 0.631411612033844
2023-01-23 00:08:29.041701: step: 416/530, loss: 0.18457326292991638
2023-01-23 00:08:30.139147: step: 420/530, loss: 0.11251892894506454
2023-01-23 00:08:31.257973: step: 424/530, loss: 0.09046631306409836
2023-01-23 00:08:32.346043: step: 428/530, loss: 0.03998565673828125
2023-01-23 00:08:33.480061: step: 432/530, loss: 0.09033947438001633
2023-01-23 00:08:34.580306: step: 436/530, loss: 0.08593063801527023
2023-01-23 00:08:35.704697: step: 440/530, loss: 0.29131969809532166
2023-01-23 00:08:36.856228: step: 444/530, loss: 0.11450796574354172
2023-01-23 00:08:37.985051: step: 448/530, loss: 0.025425339117646217
2023-01-23 00:08:39.120450: step: 452/530, loss: 0.10331273078918457
2023-01-23 00:08:40.243879: step: 456/530, loss: 0.5864859223365784
2023-01-23 00:08:41.359061: step: 460/530, loss: 0.6186594367027283
2023-01-23 00:08:42.457257: step: 464/530, loss: 0.1444006860256195
2023-01-23 00:08:43.564960: step: 468/530, loss: 0.04403819888830185
2023-01-23 00:08:44.704156: step: 472/530, loss: 0.46927422285079956
2023-01-23 00:08:45.838855: step: 476/530, loss: 0.12903137505054474
2023-01-23 00:08:46.963758: step: 480/530, loss: 1.112038016319275
2023-01-23 00:08:48.075925: step: 484/530, loss: 0.08306923508644104
2023-01-23 00:08:49.240219: step: 488/530, loss: 0.19161853194236755
2023-01-23 00:08:50.359549: step: 492/530, loss: 0.518001914024353
2023-01-23 00:08:51.481890: step: 496/530, loss: 0.06959342956542969
2023-01-23 00:08:52.573503: step: 500/530, loss: 0.06137733533978462
2023-01-23 00:08:53.709667: step: 504/530, loss: 0.3269311785697937
2023-01-23 00:08:54.842488: step: 508/530, loss: 0.5023454427719116
2023-01-23 00:08:55.970242: step: 512/530, loss: 0.13778051733970642
2023-01-23 00:08:57.118405: step: 516/530, loss: 0.9450715184211731
2023-01-23 00:08:58.238507: step: 520/530, loss: 0.08117542415857315
2023-01-23 00:08:59.374609: step: 524/530, loss: 0.13776007294654846
2023-01-23 00:09:00.470603: step: 528/530, loss: 0.07911749184131622
2023-01-23 00:09:01.591761: step: 532/530, loss: 0.32076358795166016
2023-01-23 00:09:02.700247: step: 536/530, loss: 0.2454909384250641
2023-01-23 00:09:03.839536: step: 540/530, loss: 0.22251597046852112
2023-01-23 00:09:04.980475: step: 544/530, loss: 0.17575788497924805
2023-01-23 00:09:06.122566: step: 548/530, loss: 0.05004005506634712
2023-01-23 00:09:07.240335: step: 552/530, loss: 0.32304298877716064
2023-01-23 00:09:08.352367: step: 556/530, loss: 0.3375406265258789
2023-01-23 00:09:09.452341: step: 560/530, loss: 0.00990219134837389
2023-01-23 00:09:10.571101: step: 564/530, loss: 0.0975489616394043
2023-01-23 00:09:11.684540: step: 568/530, loss: 0.13485947251319885
2023-01-23 00:09:12.803173: step: 572/530, loss: 0.3519957363605499
2023-01-23 00:09:13.928405: step: 576/530, loss: 0.3879193365573883
2023-01-23 00:09:15.051386: step: 580/530, loss: 0.39379578828811646
2023-01-23 00:09:16.169488: step: 584/530, loss: 0.14923697710037231
2023-01-23 00:09:17.286456: step: 588/530, loss: 0.19109030067920685
2023-01-23 00:09:18.401079: step: 592/530, loss: 0.24350671470165253
2023-01-23 00:09:19.516131: step: 596/530, loss: 0.029885293915867805
2023-01-23 00:09:20.643941: step: 600/530, loss: 0.9649703502655029
2023-01-23 00:09:21.750054: step: 604/530, loss: 0.7610010504722595
2023-01-23 00:09:22.891014: step: 608/530, loss: 0.03967934101819992
2023-01-23 00:09:24.008836: step: 612/530, loss: 0.02753724902868271
2023-01-23 00:09:25.118872: step: 616/530, loss: 0.7964020371437073
2023-01-23 00:09:26.250424: step: 620/530, loss: 0.5280997157096863
2023-01-23 00:09:27.385367: step: 624/530, loss: 0.5744256973266602
2023-01-23 00:09:28.482142: step: 628/530, loss: 0.7409168481826782
2023-01-23 00:09:29.558677: step: 632/530, loss: 0.3102342188358307
2023-01-23 00:09:30.684660: step: 636/530, loss: 0.13078069686889648
2023-01-23 00:09:31.803771: step: 640/530, loss: 0.044184159487485886
2023-01-23 00:09:32.925208: step: 644/530, loss: 0.07325520366430283
2023-01-23 00:09:34.095544: step: 648/530, loss: 0.8813309669494629
2023-01-23 00:09:35.245478: step: 652/530, loss: 0.2608141005039215
2023-01-23 00:09:36.401133: step: 656/530, loss: 0.11824913322925568
2023-01-23 00:09:37.502380: step: 660/530, loss: 0.11784043163061142
2023-01-23 00:09:38.618809: step: 664/530, loss: 0.13362941145896912
2023-01-23 00:09:39.759594: step: 668/530, loss: 0.2579174041748047
2023-01-23 00:09:40.873058: step: 672/530, loss: 0.1547134518623352
2023-01-23 00:09:41.974631: step: 676/530, loss: 0.37035951018333435
2023-01-23 00:09:43.099575: step: 680/530, loss: 0.2700921893119812
2023-01-23 00:09:44.216271: step: 684/530, loss: 0.2412181943655014
2023-01-23 00:09:45.359577: step: 688/530, loss: 0.19370746612548828
2023-01-23 00:09:46.486309: step: 692/530, loss: 0.7111555337905884
2023-01-23 00:09:47.612896: step: 696/530, loss: 0.47564518451690674
2023-01-23 00:09:48.739822: step: 700/530, loss: 0.12684603035449982
2023-01-23 00:09:49.850942: step: 704/530, loss: 0.06669716536998749
2023-01-23 00:09:50.963382: step: 708/530, loss: 0.47259649634361267
2023-01-23 00:09:52.060932: step: 712/530, loss: 0.20346832275390625
2023-01-23 00:09:53.188405: step: 716/530, loss: 0.20383216440677643
2023-01-23 00:09:54.306262: step: 720/530, loss: 0.4766809344291687
2023-01-23 00:09:55.440566: step: 724/530, loss: 0.04410247504711151
2023-01-23 00:09:56.573877: step: 728/530, loss: 0.14399266242980957
2023-01-23 00:09:57.715247: step: 732/530, loss: 0.15260982513427734
2023-01-23 00:09:58.831921: step: 736/530, loss: 0.16811323165893555
2023-01-23 00:09:59.944432: step: 740/530, loss: 0.10209040343761444
2023-01-23 00:10:01.104099: step: 744/530, loss: 0.12906968593597412
2023-01-23 00:10:02.215699: step: 748/530, loss: 0.05279877036809921
2023-01-23 00:10:03.343865: step: 752/530, loss: 0.6425662636756897
2023-01-23 00:10:04.450834: step: 756/530, loss: 0.3395642042160034
2023-01-23 00:10:05.600831: step: 760/530, loss: 0.2783685624599457
2023-01-23 00:10:06.711876: step: 764/530, loss: 0.04553408548235893
2023-01-23 00:10:07.833369: step: 768/530, loss: 0.11670637130737305
2023-01-23 00:10:08.968539: step: 772/530, loss: 0.46865376830101013
2023-01-23 00:10:10.109478: step: 776/530, loss: 0.7218046188354492
2023-01-23 00:10:11.262560: step: 780/530, loss: 1.0530325174331665
2023-01-23 00:10:12.396965: step: 784/530, loss: 0.17734013497829437
2023-01-23 00:10:13.547012: step: 788/530, loss: 0.3175069987773895
2023-01-23 00:10:14.686704: step: 792/530, loss: 0.08610615134239197
2023-01-23 00:10:15.811027: step: 796/530, loss: 0.06858482956886292
2023-01-23 00:10:16.953401: step: 800/530, loss: 0.7775834202766418
2023-01-23 00:10:18.059541: step: 804/530, loss: 0.6047054529190063
2023-01-23 00:10:19.159461: step: 808/530, loss: 0.10581164062023163
2023-01-23 00:10:20.330209: step: 812/530, loss: 0.0590825080871582
2023-01-23 00:10:21.440792: step: 816/530, loss: 0.16704817116260529
2023-01-23 00:10:22.556190: step: 820/530, loss: 0.6027072072029114
2023-01-23 00:10:23.662199: step: 824/530, loss: 0.06710748374462128
2023-01-23 00:10:24.777531: step: 828/530, loss: 0.17862224578857422
2023-01-23 00:10:25.896916: step: 832/530, loss: 0.08034076541662216
2023-01-23 00:10:27.034233: step: 836/530, loss: 0.14182758331298828
2023-01-23 00:10:28.160450: step: 840/530, loss: 5.561537742614746
2023-01-23 00:10:29.279405: step: 844/530, loss: 0.8769439458847046
2023-01-23 00:10:30.401655: step: 848/530, loss: 0.19149112701416016
2023-01-23 00:10:31.521940: step: 852/530, loss: 0.12649592757225037
2023-01-23 00:10:32.664838: step: 856/530, loss: 0.8606684803962708
2023-01-23 00:10:33.805586: step: 860/530, loss: 0.0691070556640625
2023-01-23 00:10:34.926455: step: 864/530, loss: 0.18118353188037872
2023-01-23 00:10:36.035146: step: 868/530, loss: 0.11194916069507599
2023-01-23 00:10:37.147686: step: 872/530, loss: 0.3001757562160492
2023-01-23 00:10:38.297765: step: 876/530, loss: 0.7367363572120667
2023-01-23 00:10:39.440824: step: 880/530, loss: 0.11703381687402725
2023-01-23 00:10:40.564676: step: 884/530, loss: 0.596276581287384
2023-01-23 00:10:41.699788: step: 888/530, loss: 0.0638425350189209
2023-01-23 00:10:42.831313: step: 892/530, loss: 0.12961846590042114
2023-01-23 00:10:44.006263: step: 896/530, loss: 0.13920792937278748
2023-01-23 00:10:45.128487: step: 900/530, loss: 0.09304087609052658
2023-01-23 00:10:46.219035: step: 904/530, loss: 0.6309574246406555
2023-01-23 00:10:47.350883: step: 908/530, loss: 0.2951746881008148
2023-01-23 00:10:48.475742: step: 912/530, loss: 0.12824681401252747
2023-01-23 00:10:49.600431: step: 916/530, loss: 0.5646584033966064
2023-01-23 00:10:50.753848: step: 920/530, loss: 5.596519947052002
2023-01-23 00:10:51.886478: step: 924/530, loss: 0.04315061867237091
2023-01-23 00:10:53.013812: step: 928/530, loss: 0.3209080100059509
2023-01-23 00:10:54.136531: step: 932/530, loss: 0.09496760368347168
2023-01-23 00:10:55.260196: step: 936/530, loss: 0.197357177734375
2023-01-23 00:10:56.398057: step: 940/530, loss: 0.7305237054824829
2023-01-23 00:10:57.529762: step: 944/530, loss: 0.06873271614313126
2023-01-23 00:10:58.699933: step: 948/530, loss: 0.37570440769195557
2023-01-23 00:10:59.852097: step: 952/530, loss: 0.27637261152267456
2023-01-23 00:11:00.997665: step: 956/530, loss: 0.061997607350349426
2023-01-23 00:11:02.156328: step: 960/530, loss: 1.0024683475494385
2023-01-23 00:11:03.289029: step: 964/530, loss: 0.13721580803394318
2023-01-23 00:11:04.425499: step: 968/530, loss: 0.1336839199066162
2023-01-23 00:11:05.542069: step: 972/530, loss: 0.15640544891357422
2023-01-23 00:11:06.679602: step: 976/530, loss: 0.14638696610927582
2023-01-23 00:11:07.794495: step: 980/530, loss: 0.23668193817138672
2023-01-23 00:11:08.893282: step: 984/530, loss: 0.2937930226325989
2023-01-23 00:11:10.006054: step: 988/530, loss: 0.2170475870370865
2023-01-23 00:11:11.125815: step: 992/530, loss: 0.631024956703186
2023-01-23 00:11:12.211082: step: 996/530, loss: 0.10520673543214798
2023-01-23 00:11:13.346675: step: 1000/530, loss: 0.18981638550758362
2023-01-23 00:11:14.468864: step: 1004/530, loss: 0.4293762445449829
2023-01-23 00:11:15.658578: step: 1008/530, loss: 0.2915140986442566
2023-01-23 00:11:16.770569: step: 1012/530, loss: 0.05743970721960068
2023-01-23 00:11:17.906368: step: 1016/530, loss: 0.04022722318768501
2023-01-23 00:11:19.028521: step: 1020/530, loss: 0.03130464628338814
2023-01-23 00:11:20.153732: step: 1024/530, loss: 0.12952327728271484
2023-01-23 00:11:21.247055: step: 1028/530, loss: 0.2634626030921936
2023-01-23 00:11:22.374998: step: 1032/530, loss: 0.09073200821876526
2023-01-23 00:11:23.524361: step: 1036/530, loss: 0.16730089485645294
2023-01-23 00:11:24.633100: step: 1040/530, loss: 0.21579104661941528
2023-01-23 00:11:25.757808: step: 1044/530, loss: 0.10871829837560654
2023-01-23 00:11:26.877848: step: 1048/530, loss: 0.5240617990493774
2023-01-23 00:11:27.992691: step: 1052/530, loss: 0.1836831122636795
2023-01-23 00:11:29.112268: step: 1056/530, loss: 0.14211492240428925
2023-01-23 00:11:30.225990: step: 1060/530, loss: 1.059338927268982
2023-01-23 00:11:31.388835: step: 1064/530, loss: 6.697022438049316
2023-01-23 00:11:32.553063: step: 1068/530, loss: 0.11243682354688644
2023-01-23 00:11:33.666637: step: 1072/530, loss: 0.03249311447143555
2023-01-23 00:11:34.789093: step: 1076/530, loss: 0.02041592448949814
2023-01-23 00:11:35.921621: step: 1080/530, loss: 0.06910476833581924
2023-01-23 00:11:37.030223: step: 1084/530, loss: 0.5682775378227234
2023-01-23 00:11:38.154733: step: 1088/530, loss: 0.11185060441493988
2023-01-23 00:11:39.296835: step: 1092/530, loss: 1.2662150859832764
2023-01-23 00:11:40.389954: step: 1096/530, loss: 0.2531459927558899
2023-01-23 00:11:41.530329: step: 1100/530, loss: 0.1688491851091385
2023-01-23 00:11:42.674280: step: 1104/530, loss: 0.0957394614815712
2023-01-23 00:11:43.825421: step: 1108/530, loss: 0.14809615910053253
2023-01-23 00:11:44.949900: step: 1112/530, loss: 0.15989232063293457
2023-01-23 00:11:46.098255: step: 1116/530, loss: 1.0009489059448242
2023-01-23 00:11:47.204621: step: 1120/530, loss: 0.07803960144519806
2023-01-23 00:11:48.285896: step: 1124/530, loss: 0.03127622604370117
2023-01-23 00:11:49.412141: step: 1128/530, loss: 0.1130366325378418
2023-01-23 00:11:50.526645: step: 1132/530, loss: 0.12404890358448029
2023-01-23 00:11:51.681819: step: 1136/530, loss: 0.4977996051311493
2023-01-23 00:11:52.808316: step: 1140/530, loss: 0.9116091728210449
2023-01-23 00:11:53.898808: step: 1144/530, loss: 0.028257369995117188
2023-01-23 00:11:55.022345: step: 1148/530, loss: 0.7959879636764526
2023-01-23 00:11:56.131215: step: 1152/530, loss: 0.09358659386634827
2023-01-23 00:11:57.287887: step: 1156/530, loss: 0.034700918942689896
2023-01-23 00:11:58.394818: step: 1160/530, loss: 0.20606566965579987
2023-01-23 00:11:59.514042: step: 1164/530, loss: 0.37286311388015747
2023-01-23 00:12:00.626272: step: 1168/530, loss: 0.3449724316596985
2023-01-23 00:12:01.778938: step: 1172/530, loss: 0.17827215790748596
2023-01-23 00:12:02.963195: step: 1176/530, loss: 0.13285665214061737
2023-01-23 00:12:04.070112: step: 1180/530, loss: 0.13569337129592896
2023-01-23 00:12:05.165308: step: 1184/530, loss: 0.09818144142627716
2023-01-23 00:12:06.282828: step: 1188/530, loss: 0.15180349349975586
2023-01-23 00:12:07.418625: step: 1192/530, loss: 0.7923673391342163
2023-01-23 00:12:08.549999: step: 1196/530, loss: 0.7085750102996826
2023-01-23 00:12:09.675789: step: 1200/530, loss: 0.9579010605812073
2023-01-23 00:12:10.794189: step: 1204/530, loss: 0.4816337525844574
2023-01-23 00:12:11.940425: step: 1208/530, loss: 0.4566114544868469
2023-01-23 00:12:13.053029: step: 1212/530, loss: 4.5486979484558105
2023-01-23 00:12:14.184111: step: 1216/530, loss: 0.076572947204113
2023-01-23 00:12:15.315517: step: 1220/530, loss: 0.15429744124412537
2023-01-23 00:12:16.450018: step: 1224/530, loss: 0.7346298694610596
2023-01-23 00:12:17.633161: step: 1228/530, loss: 0.1368391066789627
2023-01-23 00:12:18.752777: step: 1232/530, loss: 0.18241462111473083
2023-01-23 00:12:19.890977: step: 1236/530, loss: 0.12973624467849731
2023-01-23 00:12:21.032173: step: 1240/530, loss: 0.11317090690135956
2023-01-23 00:12:22.157935: step: 1244/530, loss: 1.0910747051239014
2023-01-23 00:12:23.272553: step: 1248/530, loss: 1.8710020780563354
2023-01-23 00:12:24.361879: step: 1252/530, loss: 0.11874990165233612
2023-01-23 00:12:25.461746: step: 1256/530, loss: 0.14404550194740295
2023-01-23 00:12:26.616512: step: 1260/530, loss: 0.48172688484191895
2023-01-23 00:12:27.748834: step: 1264/530, loss: 0.6925452351570129
2023-01-23 00:12:28.865807: step: 1268/530, loss: 0.005505752749741077
2023-01-23 00:12:29.990865: step: 1272/530, loss: 0.12491970509290695
2023-01-23 00:12:31.123428: step: 1276/530, loss: 0.21732720732688904
2023-01-23 00:12:32.253161: step: 1280/530, loss: 0.6931290030479431
2023-01-23 00:12:33.377528: step: 1284/530, loss: 0.12014809250831604
2023-01-23 00:12:34.514584: step: 1288/530, loss: 3.9107110500335693
2023-01-23 00:12:35.622835: step: 1292/530, loss: 0.23418594896793365
2023-01-23 00:12:36.734222: step: 1296/530, loss: 0.43575289845466614
2023-01-23 00:12:37.849659: step: 1300/530, loss: 0.3126988410949707
2023-01-23 00:12:38.970385: step: 1304/530, loss: 0.029483510181307793
2023-01-23 00:12:40.123364: step: 1308/530, loss: 0.44991618394851685
2023-01-23 00:12:41.278046: step: 1312/530, loss: 0.5220819711685181
2023-01-23 00:12:42.442065: step: 1316/530, loss: 0.8805736303329468
2023-01-23 00:12:43.580605: step: 1320/530, loss: 0.09765376895666122
2023-01-23 00:12:44.718547: step: 1324/530, loss: 0.3835306763648987
2023-01-23 00:12:45.854249: step: 1328/530, loss: 0.7068468928337097
2023-01-23 00:12:46.987817: step: 1332/530, loss: 0.5412137508392334
2023-01-23 00:12:48.102181: step: 1336/530, loss: 0.5303499102592468
2023-01-23 00:12:49.207881: step: 1340/530, loss: 0.0532391332089901
2023-01-23 00:12:50.338872: step: 1344/530, loss: 0.0699133425951004
2023-01-23 00:12:51.473741: step: 1348/530, loss: 0.11602401733398438
2023-01-23 00:12:52.597557: step: 1352/530, loss: 0.11507931351661682
2023-01-23 00:12:53.703628: step: 1356/530, loss: 0.08576121181249619
2023-01-23 00:12:54.815939: step: 1360/530, loss: 1.2977372407913208
2023-01-23 00:12:55.984107: step: 1364/530, loss: 0.13552981615066528
2023-01-23 00:12:57.107062: step: 1368/530, loss: 0.15410995483398438
2023-01-23 00:12:58.257905: step: 1372/530, loss: 0.12532921135425568
2023-01-23 00:12:59.376562: step: 1376/530, loss: 0.9345909357070923
2023-01-23 00:13:00.499485: step: 1380/530, loss: 0.10559320449829102
2023-01-23 00:13:01.616324: step: 1384/530, loss: 0.5648598670959473
2023-01-23 00:13:02.779822: step: 1388/530, loss: 0.05499105527997017
2023-01-23 00:13:03.926863: step: 1392/530, loss: 1.5131492614746094
2023-01-23 00:13:05.032533: step: 1396/530, loss: 0.30266791582107544
2023-01-23 00:13:06.178529: step: 1400/530, loss: 0.36107635498046875
2023-01-23 00:13:07.297125: step: 1404/530, loss: 0.08211131393909454
2023-01-23 00:13:08.437334: step: 1408/530, loss: 0.1853996217250824
2023-01-23 00:13:09.553333: step: 1412/530, loss: 3.913877010345459
2023-01-23 00:13:10.657784: step: 1416/530, loss: 0.3650156855583191
2023-01-23 00:13:11.780543: step: 1420/530, loss: 0.07907247543334961
2023-01-23 00:13:12.913370: step: 1424/530, loss: 0.46418002247810364
2023-01-23 00:13:14.038300: step: 1428/530, loss: 0.34937965869903564
2023-01-23 00:13:15.152231: step: 1432/530, loss: 0.251691997051239
2023-01-23 00:13:16.307171: step: 1436/530, loss: 0.1269761621952057
2023-01-23 00:13:17.413799: step: 1440/530, loss: 0.3294636607170105
2023-01-23 00:13:18.537573: step: 1444/530, loss: 0.1376476287841797
2023-01-23 00:13:19.672018: step: 1448/530, loss: 0.0502413734793663
2023-01-23 00:13:20.776889: step: 1452/530, loss: 0.2584006190299988
2023-01-23 00:13:21.885672: step: 1456/530, loss: 0.06424055248498917
2023-01-23 00:13:23.028322: step: 1460/530, loss: 0.8068082928657532
2023-01-23 00:13:24.124689: step: 1464/530, loss: 0.4949599504470825
2023-01-23 00:13:25.221487: step: 1468/530, loss: 0.0526403933763504
2023-01-23 00:13:26.323321: step: 1472/530, loss: 2.772021532058716
2023-01-23 00:13:27.456885: step: 1476/530, loss: 0.029606152325868607
2023-01-23 00:13:28.541680: step: 1480/530, loss: 0.09204654395580292
2023-01-23 00:13:29.660506: step: 1484/530, loss: 0.04686170071363449
2023-01-23 00:13:30.770319: step: 1488/530, loss: 0.4500100910663605
2023-01-23 00:13:31.897949: step: 1492/530, loss: 0.10053558647632599
2023-01-23 00:13:33.026183: step: 1496/530, loss: 1.4256826639175415
2023-01-23 00:13:34.178196: step: 1500/530, loss: 0.15307369828224182
2023-01-23 00:13:35.288500: step: 1504/530, loss: 0.32327374815940857
2023-01-23 00:13:36.426356: step: 1508/530, loss: 0.10572662204504013
2023-01-23 00:13:37.556099: step: 1512/530, loss: 0.18129916489124298
2023-01-23 00:13:38.668017: step: 1516/530, loss: 0.10050592571496964
2023-01-23 00:13:39.808988: step: 1520/530, loss: 0.021743012592196465
2023-01-23 00:13:40.928034: step: 1524/530, loss: 0.05757313221693039
2023-01-23 00:13:42.070037: step: 1528/530, loss: 1.483445644378662
2023-01-23 00:13:43.195830: step: 1532/530, loss: 0.05383338779211044
2023-01-23 00:13:44.323984: step: 1536/530, loss: 2.020174741744995
2023-01-23 00:13:45.446837: step: 1540/530, loss: 0.038916923105716705
2023-01-23 00:13:46.546629: step: 1544/530, loss: 0.8860012292861938
2023-01-23 00:13:47.678594: step: 1548/530, loss: 0.13376203179359436
2023-01-23 00:13:48.836958: step: 1552/530, loss: 2.292222499847412
2023-01-23 00:13:49.983910: step: 1556/530, loss: 0.8194613456726074
2023-01-23 00:13:51.159965: step: 1560/530, loss: 0.1855698674917221
2023-01-23 00:13:52.309059: step: 1564/530, loss: 0.2875831723213196
2023-01-23 00:13:53.455883: step: 1568/530, loss: 2.010491132736206
2023-01-23 00:13:54.588445: step: 1572/530, loss: 0.25376319885253906
2023-01-23 00:13:55.718684: step: 1576/530, loss: 0.08488493412733078
2023-01-23 00:13:56.853695: step: 1580/530, loss: 0.5695492625236511
2023-01-23 00:13:57.971453: step: 1584/530, loss: 0.32643136382102966
2023-01-23 00:13:59.114138: step: 1588/530, loss: 0.021935129538178444
2023-01-23 00:14:00.244943: step: 1592/530, loss: 0.168484628200531
2023-01-23 00:14:01.349629: step: 1596/530, loss: 0.7492960691452026
2023-01-23 00:14:02.462435: step: 1600/530, loss: 0.28280019760131836
2023-01-23 00:14:03.590955: step: 1604/530, loss: 0.713383674621582
2023-01-23 00:14:04.731093: step: 1608/530, loss: 0.5585966110229492
2023-01-23 00:14:05.863807: step: 1612/530, loss: 0.3293589651584625
2023-01-23 00:14:06.974345: step: 1616/530, loss: 0.10880356281995773
2023-01-23 00:14:08.097406: step: 1620/530, loss: 0.5849825739860535
2023-01-23 00:14:09.219421: step: 1624/530, loss: 0.8764529228210449
2023-01-23 00:14:10.343390: step: 1628/530, loss: 0.06115712970495224
2023-01-23 00:14:11.507935: step: 1632/530, loss: 0.14915533363819122
2023-01-23 00:14:12.634949: step: 1636/530, loss: 0.09380646049976349
2023-01-23 00:14:13.762546: step: 1640/530, loss: 0.1113104298710823
2023-01-23 00:14:14.873171: step: 1644/530, loss: 0.1281011998653412
2023-01-23 00:14:15.977858: step: 1648/530, loss: 0.20835809409618378
2023-01-23 00:14:17.085591: step: 1652/530, loss: 0.07434120029211044
2023-01-23 00:14:18.193168: step: 1656/530, loss: 0.05488395690917969
2023-01-23 00:14:19.312157: step: 1660/530, loss: 0.049842022359371185
2023-01-23 00:14:20.425494: step: 1664/530, loss: 0.2538219392299652
2023-01-23 00:14:21.549194: step: 1668/530, loss: 0.058594606816768646
2023-01-23 00:14:22.684850: step: 1672/530, loss: 0.05866451561450958
2023-01-23 00:14:23.796787: step: 1676/530, loss: 0.22145463526248932
2023-01-23 00:14:24.922664: step: 1680/530, loss: 0.17822200059890747
2023-01-23 00:14:26.051448: step: 1684/530, loss: 0.7184593677520752
2023-01-23 00:14:27.158423: step: 1688/530, loss: 0.10963602364063263
2023-01-23 00:14:28.293503: step: 1692/530, loss: 0.807685911655426
2023-01-23 00:14:29.417164: step: 1696/530, loss: 0.08288630843162537
2023-01-23 00:14:30.529234: step: 1700/530, loss: 0.242415189743042
2023-01-23 00:14:31.654662: step: 1704/530, loss: 0.10757341235876083
2023-01-23 00:14:32.776185: step: 1708/530, loss: 0.02465801313519478
2023-01-23 00:14:33.944807: step: 1712/530, loss: 0.13817119598388672
2023-01-23 00:14:35.058712: step: 1716/530, loss: 0.28537243604660034
2023-01-23 00:14:36.177534: step: 1720/530, loss: 0.7142650485038757
2023-01-23 00:14:37.309722: step: 1724/530, loss: 0.2754554748535156
2023-01-23 00:14:38.416179: step: 1728/530, loss: 0.4273221790790558
2023-01-23 00:14:39.542930: step: 1732/530, loss: 0.8859471678733826
2023-01-23 00:14:40.702660: step: 1736/530, loss: 0.33142802119255066
2023-01-23 00:14:41.829837: step: 1740/530, loss: 0.12461915612220764
2023-01-23 00:14:42.966820: step: 1744/530, loss: 0.3007735311985016
2023-01-23 00:14:44.092732: step: 1748/530, loss: 0.5511849522590637
2023-01-23 00:14:45.234353: step: 1752/530, loss: 0.16630326211452484
2023-01-23 00:14:46.376230: step: 1756/530, loss: 0.12402570992708206
2023-01-23 00:14:47.484667: step: 1760/530, loss: 1.3395030498504639
2023-01-23 00:14:48.600455: step: 1764/530, loss: 0.23198625445365906
2023-01-23 00:14:49.708803: step: 1768/530, loss: 0.11191582679748535
2023-01-23 00:14:50.807730: step: 1772/530, loss: 0.10320186614990234
2023-01-23 00:14:51.950732: step: 1776/530, loss: 0.29644688963890076
2023-01-23 00:14:53.062478: step: 1780/530, loss: 0.1512923240661621
2023-01-23 00:14:54.204018: step: 1784/530, loss: 0.4369129538536072
2023-01-23 00:14:55.337102: step: 1788/530, loss: 0.1335986852645874
2023-01-23 00:14:56.444206: step: 1792/530, loss: 0.09932279586791992
2023-01-23 00:14:57.586243: step: 1796/530, loss: 0.24840280413627625
2023-01-23 00:14:58.702499: step: 1800/530, loss: 0.5166805386543274
2023-01-23 00:14:59.873785: step: 1804/530, loss: 1.2183558940887451
2023-01-23 00:15:00.985162: step: 1808/530, loss: 0.23145313560962677
2023-01-23 00:15:02.156225: step: 1812/530, loss: 0.5459344983100891
2023-01-23 00:15:03.300515: step: 1816/530, loss: 0.4104844927787781
2023-01-23 00:15:04.427647: step: 1820/530, loss: 0.3828395903110504
2023-01-23 00:15:05.561036: step: 1824/530, loss: 0.11716604232788086
2023-01-23 00:15:06.694874: step: 1828/530, loss: 0.5799517631530762
2023-01-23 00:15:07.826039: step: 1832/530, loss: 0.5515645742416382
2023-01-23 00:15:08.981389: step: 1836/530, loss: 0.07434368133544922
2023-01-23 00:15:10.086791: step: 1840/530, loss: 0.2095049023628235
2023-01-23 00:15:11.237035: step: 1844/530, loss: 0.16163387894630432
2023-01-23 00:15:12.353194: step: 1848/530, loss: 0.09525775909423828
2023-01-23 00:15:13.474133: step: 1852/530, loss: 0.6529601812362671
2023-01-23 00:15:14.582610: step: 1856/530, loss: 0.15268835425376892
2023-01-23 00:15:15.689086: step: 1860/530, loss: 0.15811890363693237
2023-01-23 00:15:16.783372: step: 1864/530, loss: 0.01988091506063938
2023-01-23 00:15:17.916750: step: 1868/530, loss: 0.10967741161584854
2023-01-23 00:15:19.017927: step: 1872/530, loss: 0.09564152359962463
2023-01-23 00:15:20.132563: step: 1876/530, loss: 2.1743366718292236
2023-01-23 00:15:21.297234: step: 1880/530, loss: 0.7197198867797852
2023-01-23 00:15:22.435163: step: 1884/530, loss: 0.11725623905658722
2023-01-23 00:15:23.571768: step: 1888/530, loss: 0.11699095368385315
2023-01-23 00:15:24.715968: step: 1892/530, loss: 0.12567205727100372
2023-01-23 00:15:25.844791: step: 1896/530, loss: 0.11940484493970871
2023-01-23 00:15:26.995914: step: 1900/530, loss: 0.5074408650398254
2023-01-23 00:15:28.137391: step: 1904/530, loss: 0.28615647554397583
2023-01-23 00:15:29.268955: step: 1908/530, loss: 0.11127553135156631
2023-01-23 00:15:30.436920: step: 1912/530, loss: 0.2144385278224945
2023-01-23 00:15:31.554655: step: 1916/530, loss: 0.19051532447338104
2023-01-23 00:15:32.690676: step: 1920/530, loss: 0.36019372940063477
2023-01-23 00:15:33.813589: step: 1924/530, loss: 0.2777508795261383
2023-01-23 00:15:34.933110: step: 1928/530, loss: 0.2543220520019531
2023-01-23 00:15:36.032477: step: 1932/530, loss: 0.40941813588142395
2023-01-23 00:15:37.148337: step: 1936/530, loss: 0.7665479183197021
2023-01-23 00:15:38.283823: step: 1940/530, loss: 0.1408340483903885
2023-01-23 00:15:39.414048: step: 1944/530, loss: 0.04568493366241455
2023-01-23 00:15:40.533215: step: 1948/530, loss: 0.07039077579975128
2023-01-23 00:15:41.671422: step: 1952/530, loss: 0.03977060317993164
2023-01-23 00:15:42.831182: step: 1956/530, loss: 0.7270016670227051
2023-01-23 00:15:43.952242: step: 1960/530, loss: 0.48939552903175354
2023-01-23 00:15:45.077760: step: 1964/530, loss: 3.0228066444396973
2023-01-23 00:15:46.209001: step: 1968/530, loss: 0.31307584047317505
2023-01-23 00:15:47.327531: step: 1972/530, loss: 0.11756334453821182
2023-01-23 00:15:48.429081: step: 1976/530, loss: 0.30105704069137573
2023-01-23 00:15:49.545025: step: 1980/530, loss: 0.02498607523739338
2023-01-23 00:15:50.704670: step: 1984/530, loss: 0.17753076553344727
2023-01-23 00:15:51.827088: step: 1988/530, loss: 0.16538485884666443
2023-01-23 00:15:52.973520: step: 1992/530, loss: 0.34773874282836914
2023-01-23 00:15:54.118182: step: 1996/530, loss: 0.45388665795326233
2023-01-23 00:15:55.228152: step: 2000/530, loss: 0.14956659078598022
2023-01-23 00:15:56.386773: step: 2004/530, loss: 0.11129655689001083
2023-01-23 00:15:57.496321: step: 2008/530, loss: 0.17294436693191528
2023-01-23 00:15:58.608216: step: 2012/530, loss: 0.09069366753101349
2023-01-23 00:15:59.710274: step: 2016/530, loss: 0.08433127403259277
2023-01-23 00:16:00.839555: step: 2020/530, loss: 0.4764396846294403
2023-01-23 00:16:01.989654: step: 2024/530, loss: 0.12009716033935547
2023-01-23 00:16:03.119202: step: 2028/530, loss: 0.315599262714386
2023-01-23 00:16:04.208674: step: 2032/530, loss: 0.5425676107406616
2023-01-23 00:16:05.343897: step: 2036/530, loss: 0.08703804016113281
2023-01-23 00:16:06.488669: step: 2040/530, loss: 0.2610679864883423
2023-01-23 00:16:07.595261: step: 2044/530, loss: 0.12227936089038849
2023-01-23 00:16:08.702460: step: 2048/530, loss: 0.012537575326859951
2023-01-23 00:16:09.822742: step: 2052/530, loss: 0.07939349114894867
2023-01-23 00:16:10.953597: step: 2056/530, loss: 0.2578169107437134
2023-01-23 00:16:12.097777: step: 2060/530, loss: 0.15415841341018677
2023-01-23 00:16:13.207675: step: 2064/530, loss: 0.8681615591049194
2023-01-23 00:16:14.370530: step: 2068/530, loss: 0.1851181983947754
2023-01-23 00:16:15.506572: step: 2072/530, loss: 0.3306097984313965
2023-01-23 00:16:16.634323: step: 2076/530, loss: 0.08711384236812592
2023-01-23 00:16:17.735047: step: 2080/530, loss: 0.7476381659507751
2023-01-23 00:16:18.862355: step: 2084/530, loss: 0.7445141673088074
2023-01-23 00:16:19.983787: step: 2088/530, loss: 0.12560033798217773
2023-01-23 00:16:21.105433: step: 2092/530, loss: 0.17096364498138428
2023-01-23 00:16:22.250516: step: 2096/530, loss: 0.10149335861206055
2023-01-23 00:16:23.358882: step: 2100/530, loss: 0.08993730694055557
2023-01-23 00:16:24.490984: step: 2104/530, loss: 1.4990428686141968
2023-01-23 00:16:25.620486: step: 2108/530, loss: 0.13334588706493378
2023-01-23 00:16:26.772612: step: 2112/530, loss: 0.36022433638572693
2023-01-23 00:16:27.880176: step: 2116/530, loss: 0.807364284992218
2023-01-23 00:16:28.996887: step: 2120/530, loss: 0.2485140860080719
==================================================
Loss: 0.386
--------------------
Dev: {'event': {'p': 0.6534653465346535, 'r': 0.7030625832223701, 'f1': 0.6773572803078897}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Test: {'event': {'p': 0.6715481171548117, 'r': 0.7337142857142858, 'f1': 0.7012561441835063}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Chinese: {'event': {'p': 0.6111111111111112, 'r': 0.8148148148148148, 'f1': 0.6984126984126984}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Korean: {'event': {'p': 0.625, 'r': 0.3968253968253968, 'f1': 0.4854368932038835}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Russian: {'event': {'p': 0.5405405405405406, 'r': 0.5555555555555556, 'f1': 0.547945205479452}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
New best chinese model...
New best russian model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6534653465346535, 'r': 0.7030625832223701, 'f1': 0.6773572803078897}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Eng Test for Chinese: {'event': {'p': 0.6715481171548117, 'r': 0.7337142857142858, 'f1': 0.7012561441835063}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Sample Chinese: {'event': {'p': 0.6111111111111112, 'r': 0.8148148148148148, 'f1': 0.6984126984126984}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5832471561530507, 'r': 0.7509986684420772, 'f1': 0.6565774155995343}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Korean: {'event': {'p': 0.603579418344519, 'r': 0.7708571428571429, 'f1': 0.6770388958594731}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Korean: {'event': {'p': 0.6470588235294118, 'r': 0.5238095238095238, 'f1': 0.5789473684210527}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6534653465346535, 'r': 0.7030625832223701, 'f1': 0.6773572803078897}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Eng Test for Russian: {'event': {'p': 0.6715481171548117, 'r': 0.7337142857142858, 'f1': 0.7012561441835063}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Sample Russian: {'event': {'p': 0.5405405405405406, 'r': 0.5555555555555556, 'f1': 0.547945205479452}, '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 00:17:20.553075: step: 4/530, loss: 0.3328391909599304
2023-01-23 00:17:21.653059: step: 8/530, loss: 0.2161366492509842
2023-01-23 00:17:22.758676: step: 12/530, loss: 2.3184242248535156
2023-01-23 00:17:23.859556: step: 16/530, loss: 1.0192146301269531
2023-01-23 00:17:24.982928: step: 20/530, loss: 0.08197665214538574
2023-01-23 00:17:26.119863: step: 24/530, loss: 0.23187074065208435
2023-01-23 00:17:27.223792: step: 28/530, loss: 0.1261003464460373
2023-01-23 00:17:28.359017: step: 32/530, loss: 0.13355597853660583
2023-01-23 00:17:29.478330: step: 36/530, loss: 0.1482105255126953
2023-01-23 00:17:30.619695: step: 40/530, loss: 0.3279067873954773
2023-01-23 00:17:31.747420: step: 44/530, loss: 0.5191739797592163
2023-01-23 00:17:32.887418: step: 48/530, loss: 0.2949063181877136
2023-01-23 00:17:34.024404: step: 52/530, loss: 0.22519607841968536
2023-01-23 00:17:35.155370: step: 56/530, loss: 0.03790559992194176
2023-01-23 00:17:36.267747: step: 60/530, loss: 0.05702982097864151
2023-01-23 00:17:37.385726: step: 64/530, loss: 0.1355874091386795
2023-01-23 00:17:38.499489: step: 68/530, loss: 0.2908710837364197
2023-01-23 00:17:39.611433: step: 72/530, loss: 0.4064415991306305
2023-01-23 00:17:40.760483: step: 76/530, loss: 0.13113364577293396
2023-01-23 00:17:41.906975: step: 80/530, loss: 0.0589747428894043
2023-01-23 00:17:43.028380: step: 84/530, loss: 0.10074613243341446
2023-01-23 00:17:44.151524: step: 88/530, loss: 0.14747628569602966
2023-01-23 00:17:45.361498: step: 92/530, loss: 0.10192590206861496
2023-01-23 00:17:46.493713: step: 96/530, loss: 0.35114815831184387
2023-01-23 00:17:47.621125: step: 100/530, loss: 0.21711650490760803
2023-01-23 00:17:48.766646: step: 104/530, loss: 0.06990785896778107
2023-01-23 00:17:49.923462: step: 108/530, loss: 0.09487934410572052
2023-01-23 00:17:51.039593: step: 112/530, loss: 0.04557361453771591
2023-01-23 00:17:52.157493: step: 116/530, loss: 0.10987591743469238
2023-01-23 00:17:53.299596: step: 120/530, loss: 0.2561771273612976
2023-01-23 00:17:54.427809: step: 124/530, loss: 0.27180272340774536
2023-01-23 00:17:55.549295: step: 128/530, loss: 0.5598156452178955
2023-01-23 00:17:56.647730: step: 132/530, loss: 0.1672348976135254
2023-01-23 00:17:57.754886: step: 136/530, loss: 0.12120304256677628
2023-01-23 00:17:58.885910: step: 140/530, loss: 0.27204322814941406
2023-01-23 00:18:00.009082: step: 144/530, loss: 0.1415904015302658
2023-01-23 00:18:01.117147: step: 148/530, loss: 0.028807926923036575
2023-01-23 00:18:02.238198: step: 152/530, loss: 0.08358936756849289
2023-01-23 00:18:03.347083: step: 156/530, loss: 0.02778015099465847
2023-01-23 00:18:04.476712: step: 160/530, loss: 0.11728544533252716
2023-01-23 00:18:05.592618: step: 164/530, loss: 0.1509249210357666
2023-01-23 00:18:06.727812: step: 168/530, loss: 0.16300678253173828
2023-01-23 00:18:07.875740: step: 172/530, loss: 0.10371866822242737
2023-01-23 00:18:08.999299: step: 176/530, loss: 0.15409621596336365
2023-01-23 00:18:10.131377: step: 180/530, loss: 0.09803777188062668
2023-01-23 00:18:11.270660: step: 184/530, loss: 0.07412414252758026
2023-01-23 00:18:12.403066: step: 188/530, loss: 0.24671994149684906
2023-01-23 00:18:13.514184: step: 192/530, loss: 0.19809454679489136
2023-01-23 00:18:14.638242: step: 196/530, loss: 0.10713253170251846
2023-01-23 00:18:15.739162: step: 200/530, loss: 0.12279417365789413
2023-01-23 00:18:16.874098: step: 204/530, loss: 0.22239446640014648
2023-01-23 00:18:18.009898: step: 208/530, loss: 0.03668703883886337
2023-01-23 00:18:19.152307: step: 212/530, loss: 0.18285083770751953
2023-01-23 00:18:20.290939: step: 216/530, loss: 0.20613804459571838
2023-01-23 00:18:21.413459: step: 220/530, loss: 0.12802791595458984
2023-01-23 00:18:22.558209: step: 224/530, loss: 0.4143645465373993
2023-01-23 00:18:23.669488: step: 228/530, loss: 0.40455740690231323
2023-01-23 00:18:24.778499: step: 232/530, loss: 0.2410842627286911
2023-01-23 00:18:25.904750: step: 236/530, loss: 0.1660003662109375
2023-01-23 00:18:27.058564: step: 240/530, loss: 0.21147093176841736
2023-01-23 00:18:28.184867: step: 244/530, loss: 0.5502294301986694
2023-01-23 00:18:29.288592: step: 248/530, loss: 0.2317015826702118
2023-01-23 00:18:30.397145: step: 252/530, loss: 0.48736143112182617
2023-01-23 00:18:31.525633: step: 256/530, loss: 1.1992590427398682
2023-01-23 00:18:32.687167: step: 260/530, loss: 0.049887944012880325
2023-01-23 00:18:33.800038: step: 264/530, loss: 0.5157423615455627
2023-01-23 00:18:34.926584: step: 268/530, loss: 0.1872878074645996
2023-01-23 00:18:36.050108: step: 272/530, loss: 0.06069578975439072
2023-01-23 00:18:37.175981: step: 276/530, loss: 0.09013481438159943
2023-01-23 00:18:38.271662: step: 280/530, loss: 0.19185668230056763
2023-01-23 00:18:39.375912: step: 284/530, loss: 0.24523791670799255
2023-01-23 00:18:40.513605: step: 288/530, loss: 0.1333208680152893
2023-01-23 00:18:41.647695: step: 292/530, loss: 0.19570809602737427
2023-01-23 00:18:42.752596: step: 296/530, loss: 0.09879980236291885
2023-01-23 00:18:43.882508: step: 300/530, loss: 0.33673810958862305
2023-01-23 00:18:44.994189: step: 304/530, loss: 0.16912536323070526
2023-01-23 00:18:46.108546: step: 308/530, loss: 1.130427598953247
2023-01-23 00:18:47.239686: step: 312/530, loss: 0.4088205397129059
2023-01-23 00:18:48.368467: step: 316/530, loss: 0.1219671294093132
2023-01-23 00:18:49.505666: step: 320/530, loss: 1.049168348312378
2023-01-23 00:18:50.639004: step: 324/530, loss: 0.16328278183937073
2023-01-23 00:18:51.765874: step: 328/530, loss: 0.2961302697658539
2023-01-23 00:18:52.904586: step: 332/530, loss: 0.06673374027013779
2023-01-23 00:18:54.047219: step: 336/530, loss: 0.20635861158370972
2023-01-23 00:18:55.186984: step: 340/530, loss: 0.1278267353773117
2023-01-23 00:18:56.329070: step: 344/530, loss: 0.06825017929077148
2023-01-23 00:18:57.505340: step: 348/530, loss: 0.5643631219863892
2023-01-23 00:18:58.624880: step: 352/530, loss: 2.377779006958008
2023-01-23 00:18:59.736182: step: 356/530, loss: 0.1623862385749817
2023-01-23 00:19:00.871810: step: 360/530, loss: 0.14190712571144104
2023-01-23 00:19:01.981671: step: 364/530, loss: 0.1083555743098259
2023-01-23 00:19:03.111639: step: 368/530, loss: 0.04416332393884659
2023-01-23 00:19:04.255141: step: 372/530, loss: 0.08700676262378693
2023-01-23 00:19:05.410563: step: 376/530, loss: 0.3626858592033386
2023-01-23 00:19:06.540257: step: 380/530, loss: 0.1521831452846527
2023-01-23 00:19:07.655807: step: 384/530, loss: 0.26257649064064026
2023-01-23 00:19:08.818918: step: 388/530, loss: 0.3938552439212799
2023-01-23 00:19:09.965408: step: 392/530, loss: 0.1368224322795868
2023-01-23 00:19:11.112502: step: 396/530, loss: 0.5392426252365112
2023-01-23 00:19:12.237291: step: 400/530, loss: 0.5867196321487427
2023-01-23 00:19:13.357169: step: 404/530, loss: 0.08044548332691193
2023-01-23 00:19:14.471163: step: 408/530, loss: 0.490561842918396
2023-01-23 00:19:15.602828: step: 412/530, loss: 0.10304884612560272
2023-01-23 00:19:16.748356: step: 416/530, loss: 0.052866749465465546
2023-01-23 00:19:17.867918: step: 420/530, loss: 0.18571040034294128
2023-01-23 00:19:18.975325: step: 424/530, loss: 0.1016283631324768
2023-01-23 00:19:20.096434: step: 428/530, loss: 0.32809171080589294
2023-01-23 00:19:21.229382: step: 432/530, loss: 0.43588322401046753
2023-01-23 00:19:22.353308: step: 436/530, loss: 0.18912430107593536
2023-01-23 00:19:23.466312: step: 440/530, loss: 0.15097761154174805
2023-01-23 00:19:24.589487: step: 444/530, loss: 0.671211838722229
2023-01-23 00:19:25.724823: step: 448/530, loss: 1.5963035821914673
2023-01-23 00:19:26.876266: step: 452/530, loss: 0.1866540014743805
2023-01-23 00:19:28.059658: step: 456/530, loss: 0.24476033449172974
2023-01-23 00:19:29.195975: step: 460/530, loss: 0.12629517912864685
2023-01-23 00:19:30.321723: step: 464/530, loss: 0.1475435197353363
2023-01-23 00:19:31.438473: step: 468/530, loss: 0.1469893455505371
2023-01-23 00:19:32.615018: step: 472/530, loss: 0.23201203346252441
2023-01-23 00:19:33.765342: step: 476/530, loss: 0.07769317924976349
2023-01-23 00:19:34.890617: step: 480/530, loss: 0.14647254347801208
2023-01-23 00:19:36.003599: step: 484/530, loss: 0.1238466277718544
2023-01-23 00:19:37.124590: step: 488/530, loss: 0.0988299548625946
2023-01-23 00:19:38.224544: step: 492/530, loss: 0.3083796501159668
2023-01-23 00:19:39.359651: step: 496/530, loss: 0.4444504976272583
2023-01-23 00:19:40.483920: step: 500/530, loss: 0.2293771207332611
2023-01-23 00:19:41.622586: step: 504/530, loss: 0.3313515782356262
2023-01-23 00:19:42.749228: step: 508/530, loss: 0.19626016914844513
2023-01-23 00:19:43.865473: step: 512/530, loss: 0.08703222125768661
2023-01-23 00:19:44.991409: step: 516/530, loss: 0.09193181991577148
2023-01-23 00:19:46.116616: step: 520/530, loss: 0.13546772301197052
2023-01-23 00:19:47.231985: step: 524/530, loss: 0.044866085052490234
2023-01-23 00:19:48.346702: step: 528/530, loss: 0.040330030024051666
2023-01-23 00:19:49.488613: step: 532/530, loss: 0.6278777122497559
2023-01-23 00:19:50.603510: step: 536/530, loss: 0.16063614189624786
2023-01-23 00:19:51.740838: step: 540/530, loss: 0.2526487112045288
2023-01-23 00:19:52.872538: step: 544/530, loss: 0.10354487597942352
2023-01-23 00:19:53.976268: step: 548/530, loss: 0.06830969452857971
2023-01-23 00:19:55.098714: step: 552/530, loss: 0.10166035592556
2023-01-23 00:19:56.240574: step: 556/530, loss: 0.5175685882568359
2023-01-23 00:19:57.337683: step: 560/530, loss: 0.5365087389945984
2023-01-23 00:19:58.515825: step: 564/530, loss: 0.0465024933218956
2023-01-23 00:19:59.637228: step: 568/530, loss: 0.15384580194950104
2023-01-23 00:20:00.776884: step: 572/530, loss: 0.07074346393346786
2023-01-23 00:20:01.909577: step: 576/530, loss: 0.5204747319221497
2023-01-23 00:20:03.056084: step: 580/530, loss: 0.17314299941062927
2023-01-23 00:20:04.234546: step: 584/530, loss: 1.2452647686004639
2023-01-23 00:20:05.363239: step: 588/530, loss: 0.207940012216568
2023-01-23 00:20:06.484921: step: 592/530, loss: 0.019712068140506744
2023-01-23 00:20:07.587324: step: 596/530, loss: 0.08395443856716156
2023-01-23 00:20:08.704312: step: 600/530, loss: 0.24348679184913635
2023-01-23 00:20:09.835056: step: 604/530, loss: 0.10326090455055237
2023-01-23 00:20:10.976133: step: 608/530, loss: 0.43974122405052185
2023-01-23 00:20:12.095884: step: 612/530, loss: 0.1816503405570984
2023-01-23 00:20:13.254707: step: 616/530, loss: 0.1156463623046875
2023-01-23 00:20:14.370914: step: 620/530, loss: 0.10953550040721893
2023-01-23 00:20:15.506712: step: 624/530, loss: 0.03271923214197159
2023-01-23 00:20:16.614270: step: 628/530, loss: 0.3760426640510559
2023-01-23 00:20:17.701418: step: 632/530, loss: 0.17508994042873383
2023-01-23 00:20:18.843474: step: 636/530, loss: 0.09670362621545792
2023-01-23 00:20:20.004815: step: 640/530, loss: 0.21797600388526917
2023-01-23 00:20:21.132579: step: 644/530, loss: 0.3582476079463959
2023-01-23 00:20:22.254706: step: 648/530, loss: 0.06395077705383301
2023-01-23 00:20:23.375575: step: 652/530, loss: 0.05302887409925461
2023-01-23 00:20:24.492992: step: 656/530, loss: 0.038953591138124466
2023-01-23 00:20:25.634983: step: 660/530, loss: 0.13032856583595276
2023-01-23 00:20:26.745756: step: 664/530, loss: 0.1422923058271408
2023-01-23 00:20:27.820426: step: 668/530, loss: 0.5913253426551819
2023-01-23 00:20:28.941051: step: 672/530, loss: 0.5791007280349731
2023-01-23 00:20:30.091251: step: 676/530, loss: 0.09437239170074463
2023-01-23 00:20:31.220780: step: 680/530, loss: 0.1497097909450531
2023-01-23 00:20:32.374732: step: 684/530, loss: 0.19355785846710205
2023-01-23 00:20:33.483270: step: 688/530, loss: 0.13408851623535156
2023-01-23 00:20:34.601397: step: 692/530, loss: 0.3380964398384094
2023-01-23 00:20:35.711790: step: 696/530, loss: 0.19491642713546753
2023-01-23 00:20:36.844688: step: 700/530, loss: 0.19311437010765076
2023-01-23 00:20:37.986665: step: 704/530, loss: 0.1483035534620285
2023-01-23 00:20:39.107970: step: 708/530, loss: 0.3194564878940582
2023-01-23 00:20:40.227098: step: 712/530, loss: 0.08179903030395508
2023-01-23 00:20:41.353202: step: 716/530, loss: 0.2908279597759247
2023-01-23 00:20:42.480314: step: 720/530, loss: 0.10363516956567764
2023-01-23 00:20:43.596480: step: 724/530, loss: 0.07589159905910492
2023-01-23 00:20:44.735283: step: 728/530, loss: 0.09766826778650284
2023-01-23 00:20:45.861060: step: 732/530, loss: 0.2257830798625946
2023-01-23 00:20:46.985727: step: 736/530, loss: 0.5136715173721313
2023-01-23 00:20:48.126073: step: 740/530, loss: 0.12021151185035706
2023-01-23 00:20:49.274522: step: 744/530, loss: 0.17326650023460388
2023-01-23 00:20:50.401545: step: 748/530, loss: 0.04267315939068794
2023-01-23 00:20:51.553380: step: 752/530, loss: 0.10617952048778534
2023-01-23 00:20:52.714775: step: 756/530, loss: 0.2369038611650467
2023-01-23 00:20:53.853878: step: 760/530, loss: 0.05305519327521324
2023-01-23 00:20:54.999417: step: 764/530, loss: 0.24194279313087463
2023-01-23 00:20:56.118842: step: 768/530, loss: 1.0865648984909058
2023-01-23 00:20:57.244617: step: 772/530, loss: 0.14510604739189148
2023-01-23 00:20:58.343518: step: 776/530, loss: 0.15307465195655823
2023-01-23 00:20:59.474361: step: 780/530, loss: 0.04640016704797745
2023-01-23 00:21:00.637003: step: 784/530, loss: 0.34444141387939453
2023-01-23 00:21:01.754682: step: 788/530, loss: 0.11877629160881042
2023-01-23 00:21:02.872764: step: 792/530, loss: 0.07700634002685547
2023-01-23 00:21:03.988388: step: 796/530, loss: 0.3511069118976593
2023-01-23 00:21:05.134422: step: 800/530, loss: 0.41715505719184875
2023-01-23 00:21:06.262989: step: 804/530, loss: 0.13137730956077576
2023-01-23 00:21:07.366546: step: 808/530, loss: 0.12022048234939575
2023-01-23 00:21:08.507684: step: 812/530, loss: 0.13441486656665802
2023-01-23 00:21:09.640189: step: 816/530, loss: 0.2620023787021637
2023-01-23 00:21:10.807996: step: 820/530, loss: 0.06594095379114151
2023-01-23 00:21:11.918819: step: 824/530, loss: 0.17283029854297638
2023-01-23 00:21:13.033469: step: 828/530, loss: 0.14289219677448273
2023-01-23 00:21:14.139059: step: 832/530, loss: 1.140893816947937
2023-01-23 00:21:15.259984: step: 836/530, loss: 0.5993806719779968
2023-01-23 00:21:16.366577: step: 840/530, loss: 0.09278631210327148
2023-01-23 00:21:17.501777: step: 844/530, loss: 0.10381016880273819
2023-01-23 00:21:18.615332: step: 848/530, loss: 0.5966172218322754
2023-01-23 00:21:19.754043: step: 852/530, loss: 0.26500165462493896
2023-01-23 00:21:20.881763: step: 856/530, loss: 0.15709298849105835
2023-01-23 00:21:21.992453: step: 860/530, loss: 0.08998998999595642
2023-01-23 00:21:23.107450: step: 864/530, loss: 0.09043969959020615
2023-01-23 00:21:24.234810: step: 868/530, loss: 0.22988061606884003
2023-01-23 00:21:25.343761: step: 872/530, loss: 0.15304259955883026
2023-01-23 00:21:26.450108: step: 876/530, loss: 0.05835294723510742
2023-01-23 00:21:27.581584: step: 880/530, loss: 0.5869282484054565
2023-01-23 00:21:28.705512: step: 884/530, loss: 0.06869509816169739
2023-01-23 00:21:29.837787: step: 888/530, loss: 0.5883738398551941
2023-01-23 00:21:31.020477: step: 892/530, loss: 0.13258734345436096
2023-01-23 00:21:32.156851: step: 896/530, loss: 0.25757285952568054
2023-01-23 00:21:33.283711: step: 900/530, loss: 0.074462890625
2023-01-23 00:21:34.400279: step: 904/530, loss: 0.22323136031627655
2023-01-23 00:21:35.519241: step: 908/530, loss: 0.08468742668628693
2023-01-23 00:21:36.651180: step: 912/530, loss: 0.10809478908777237
2023-01-23 00:21:37.828427: step: 916/530, loss: 0.7821671962738037
2023-01-23 00:21:38.979610: step: 920/530, loss: 0.1058753952383995
2023-01-23 00:21:40.136799: step: 924/530, loss: 0.07042007148265839
2023-01-23 00:21:41.250145: step: 928/530, loss: 0.26982536911964417
2023-01-23 00:21:42.351596: step: 932/530, loss: 0.09188766777515411
2023-01-23 00:21:43.516657: step: 936/530, loss: 0.35422927141189575
2023-01-23 00:21:44.667167: step: 940/530, loss: 0.7445580959320068
2023-01-23 00:21:45.798666: step: 944/530, loss: 0.04747777059674263
2023-01-23 00:21:46.921409: step: 948/530, loss: 0.09176960587501526
2023-01-23 00:21:48.048028: step: 952/530, loss: 0.06079930067062378
2023-01-23 00:21:49.197882: step: 956/530, loss: 0.0665692389011383
2023-01-23 00:21:50.313529: step: 960/530, loss: 0.11003494262695312
2023-01-23 00:21:51.463763: step: 964/530, loss: 0.1225917860865593
2023-01-23 00:21:52.615707: step: 968/530, loss: 0.057576559484004974
2023-01-23 00:21:53.735170: step: 972/530, loss: 0.9640516042709351
2023-01-23 00:21:54.908635: step: 976/530, loss: 0.13804513216018677
2023-01-23 00:21:56.010120: step: 980/530, loss: 0.05690355598926544
2023-01-23 00:21:57.137545: step: 984/530, loss: 0.11256230622529984
2023-01-23 00:21:58.295415: step: 988/530, loss: 0.312844455242157
2023-01-23 00:21:59.416927: step: 992/530, loss: 0.06485471874475479
2023-01-23 00:22:00.556585: step: 996/530, loss: 0.24370832741260529
2023-01-23 00:22:01.677641: step: 1000/530, loss: 0.1107872948050499
2023-01-23 00:22:02.807116: step: 1004/530, loss: 0.18152594566345215
2023-01-23 00:22:03.911805: step: 1008/530, loss: 0.3008895814418793
2023-01-23 00:22:05.012446: step: 1012/530, loss: 0.10740160942077637
2023-01-23 00:22:06.168206: step: 1016/530, loss: 0.1232067197561264
2023-01-23 00:22:07.296525: step: 1020/530, loss: 0.11176462471485138
2023-01-23 00:22:08.412178: step: 1024/530, loss: 0.05635805055499077
2023-01-23 00:22:09.525948: step: 1028/530, loss: 0.13475151360034943
2023-01-23 00:22:10.665919: step: 1032/530, loss: 0.4001826345920563
2023-01-23 00:22:11.808076: step: 1036/530, loss: 0.18724600970745087
2023-01-23 00:22:12.918547: step: 1040/530, loss: 0.05257861688733101
2023-01-23 00:22:14.061984: step: 1044/530, loss: 0.4860478341579437
2023-01-23 00:22:15.177293: step: 1048/530, loss: 0.2075042724609375
2023-01-23 00:22:16.300721: step: 1052/530, loss: 0.1154942512512207
2023-01-23 00:22:17.421938: step: 1056/530, loss: 0.06639137119054794
2023-01-23 00:22:18.538210: step: 1060/530, loss: 0.9118468761444092
2023-01-23 00:22:19.697660: step: 1064/530, loss: 0.08206520974636078
2023-01-23 00:22:20.814902: step: 1068/530, loss: 0.16710948944091797
2023-01-23 00:22:21.937542: step: 1072/530, loss: 0.20957517623901367
2023-01-23 00:22:23.060019: step: 1076/530, loss: 0.4679213762283325
2023-01-23 00:22:24.180070: step: 1080/530, loss: 0.1396736204624176
2023-01-23 00:22:25.305217: step: 1084/530, loss: 0.05888848751783371
2023-01-23 00:22:26.426377: step: 1088/530, loss: 0.09545326232910156
2023-01-23 00:22:27.569266: step: 1092/530, loss: 0.044793032109737396
2023-01-23 00:22:28.697318: step: 1096/530, loss: 0.16030049324035645
2023-01-23 00:22:29.823805: step: 1100/530, loss: 0.3537948727607727
2023-01-23 00:22:30.935469: step: 1104/530, loss: 0.05103006213903427
2023-01-23 00:22:32.092845: step: 1108/530, loss: 0.047654539346694946
2023-01-23 00:22:33.228335: step: 1112/530, loss: 0.19664603471755981
2023-01-23 00:22:34.339311: step: 1116/530, loss: 0.4600929319858551
2023-01-23 00:22:35.474279: step: 1120/530, loss: 0.08519162982702255
2023-01-23 00:22:36.623878: step: 1124/530, loss: 0.44426119327545166
2023-01-23 00:22:37.784419: step: 1128/530, loss: 0.19597744941711426
2023-01-23 00:22:38.889820: step: 1132/530, loss: 0.04792299121618271
2023-01-23 00:22:39.988646: step: 1136/530, loss: 0.11004962772130966
2023-01-23 00:22:41.126683: step: 1140/530, loss: 0.1282147467136383
2023-01-23 00:22:42.262258: step: 1144/530, loss: 0.23563870787620544
2023-01-23 00:22:43.380142: step: 1148/530, loss: 0.1534150093793869
2023-01-23 00:22:44.495560: step: 1152/530, loss: 0.014919042587280273
2023-01-23 00:22:45.631038: step: 1156/530, loss: 0.3591992259025574
2023-01-23 00:22:46.753766: step: 1160/530, loss: 0.2913808822631836
2023-01-23 00:22:47.874171: step: 1164/530, loss: 0.37747278809547424
2023-01-23 00:22:49.012258: step: 1168/530, loss: 0.4004940986633301
2023-01-23 00:22:50.189296: step: 1172/530, loss: 0.08267870545387268
2023-01-23 00:22:51.332918: step: 1176/530, loss: 0.25983744859695435
2023-01-23 00:22:52.467230: step: 1180/530, loss: 0.14484748244285583
2023-01-23 00:22:53.571411: step: 1184/530, loss: 0.08454503864049911
2023-01-23 00:22:54.686216: step: 1188/530, loss: 0.12518340349197388
2023-01-23 00:22:55.818573: step: 1192/530, loss: 0.16108350455760956
2023-01-23 00:22:56.929903: step: 1196/530, loss: 0.07637319713830948
2023-01-23 00:22:58.050119: step: 1200/530, loss: 0.05120735242962837
2023-01-23 00:22:59.165682: step: 1204/530, loss: 0.6247413754463196
2023-01-23 00:23:00.262182: step: 1208/530, loss: 0.44350355863571167
2023-01-23 00:23:01.376112: step: 1212/530, loss: 0.20133991539478302
2023-01-23 00:23:02.482164: step: 1216/530, loss: 0.09835930168628693
2023-01-23 00:23:03.630509: step: 1220/530, loss: 0.15910738706588745
2023-01-23 00:23:04.804058: step: 1224/530, loss: 0.0912107527256012
2023-01-23 00:23:05.905336: step: 1228/530, loss: 0.09170942008495331
2023-01-23 00:23:06.967352: step: 1232/530, loss: 0.03578028827905655
2023-01-23 00:23:08.122220: step: 1236/530, loss: 0.5063158869743347
2023-01-23 00:23:09.245627: step: 1240/530, loss: 0.03750190883874893
2023-01-23 00:23:10.392233: step: 1244/530, loss: 0.4150182008743286
2023-01-23 00:23:11.509628: step: 1248/530, loss: 0.10190348327159882
2023-01-23 00:23:12.632158: step: 1252/530, loss: 0.08628308773040771
2023-01-23 00:23:13.736385: step: 1256/530, loss: 0.010641051456332207
2023-01-23 00:23:14.872163: step: 1260/530, loss: 0.4293396770954132
2023-01-23 00:23:15.991535: step: 1264/530, loss: 0.1042017936706543
2023-01-23 00:23:17.126746: step: 1268/530, loss: 0.40181973576545715
2023-01-23 00:23:18.243552: step: 1272/530, loss: 0.4539757966995239
2023-01-23 00:23:19.380456: step: 1276/530, loss: 0.04647216945886612
2023-01-23 00:23:20.503248: step: 1280/530, loss: 0.103580042719841
2023-01-23 00:23:21.615332: step: 1284/530, loss: 0.6041619181632996
2023-01-23 00:23:22.699552: step: 1288/530, loss: 0.23835164308547974
2023-01-23 00:23:23.850676: step: 1292/530, loss: 0.1521662473678589
2023-01-23 00:23:24.974792: step: 1296/530, loss: 0.14514799416065216
2023-01-23 00:23:26.089803: step: 1300/530, loss: 0.07047128677368164
2023-01-23 00:23:27.219838: step: 1304/530, loss: 0.2801291048526764
2023-01-23 00:23:28.368398: step: 1308/530, loss: 0.3373778462409973
2023-01-23 00:23:29.482034: step: 1312/530, loss: 0.8691965937614441
2023-01-23 00:23:30.582475: step: 1316/530, loss: 0.06026478111743927
2023-01-23 00:23:31.719954: step: 1320/530, loss: 0.18016988039016724
2023-01-23 00:23:32.851341: step: 1324/530, loss: 0.07727446407079697
2023-01-23 00:23:33.959919: step: 1328/530, loss: 0.15874509513378143
2023-01-23 00:23:35.080097: step: 1332/530, loss: 0.06604871898889542
2023-01-23 00:23:36.238290: step: 1336/530, loss: 0.19367733597755432
2023-01-23 00:23:37.366600: step: 1340/530, loss: 0.10540228337049484
2023-01-23 00:23:38.469342: step: 1344/530, loss: 0.4208540916442871
2023-01-23 00:23:39.603970: step: 1348/530, loss: 0.20355644822120667
2023-01-23 00:23:40.728425: step: 1352/530, loss: 0.31035566329956055
2023-01-23 00:23:41.841644: step: 1356/530, loss: 0.2901880741119385
2023-01-23 00:23:42.954073: step: 1360/530, loss: 0.09144363552331924
2023-01-23 00:23:44.082291: step: 1364/530, loss: 0.014129210263490677
2023-01-23 00:23:45.235777: step: 1368/530, loss: 0.7443875074386597
2023-01-23 00:23:46.354375: step: 1372/530, loss: 0.11810608208179474
2023-01-23 00:23:47.446131: step: 1376/530, loss: 0.5168406963348389
2023-01-23 00:23:48.573895: step: 1380/530, loss: 0.16402606666088104
2023-01-23 00:23:49.693563: step: 1384/530, loss: 0.08584009110927582
2023-01-23 00:23:50.833522: step: 1388/530, loss: 0.23799744248390198
2023-01-23 00:23:51.955576: step: 1392/530, loss: 0.23348312079906464
2023-01-23 00:23:53.101195: step: 1396/530, loss: 0.823794424533844
2023-01-23 00:23:54.226613: step: 1400/530, loss: 0.1546565145254135
2023-01-23 00:23:55.367900: step: 1404/530, loss: 0.2717716693878174
2023-01-23 00:23:56.480144: step: 1408/530, loss: 0.2602858543395996
2023-01-23 00:23:57.604755: step: 1412/530, loss: 0.9619173407554626
2023-01-23 00:23:58.730588: step: 1416/530, loss: 0.5547990202903748
2023-01-23 00:23:59.852067: step: 1420/530, loss: 0.13050489127635956
2023-01-23 00:24:00.974665: step: 1424/530, loss: 0.14009436964988708
2023-01-23 00:24:02.148799: step: 1428/530, loss: 0.03670034185051918
2023-01-23 00:24:03.251038: step: 1432/530, loss: 0.06494155526161194
2023-01-23 00:24:04.384420: step: 1436/530, loss: 0.27621030807495117
2023-01-23 00:24:05.562020: step: 1440/530, loss: 0.6529596447944641
2023-01-23 00:24:06.693303: step: 1444/530, loss: 0.0682094544172287
2023-01-23 00:24:07.822471: step: 1448/530, loss: 0.3881278932094574
2023-01-23 00:24:08.954478: step: 1452/530, loss: 0.9283435344696045
2023-01-23 00:24:10.063701: step: 1456/530, loss: 0.08008800446987152
2023-01-23 00:24:11.186887: step: 1460/530, loss: 0.10517697036266327
2023-01-23 00:24:12.323785: step: 1464/530, loss: 0.3689754605293274
2023-01-23 00:24:13.412689: step: 1468/530, loss: 1.9221255779266357
2023-01-23 00:24:14.554075: step: 1472/530, loss: 0.16830691695213318
2023-01-23 00:24:15.652039: step: 1476/530, loss: 0.07905427366495132
2023-01-23 00:24:16.777939: step: 1480/530, loss: 0.1761879026889801
2023-01-23 00:24:17.906201: step: 1484/530, loss: 1.4609920978546143
2023-01-23 00:24:19.048104: step: 1488/530, loss: 0.22796781361103058
2023-01-23 00:24:20.156555: step: 1492/530, loss: 0.18301787972450256
2023-01-23 00:24:21.278011: step: 1496/530, loss: 0.7601524591445923
2023-01-23 00:24:22.384645: step: 1500/530, loss: 1.4826362133026123
2023-01-23 00:24:23.502819: step: 1504/530, loss: 0.07959934324026108
2023-01-23 00:24:24.616158: step: 1508/530, loss: 0.2915472984313965
2023-01-23 00:24:25.739342: step: 1512/530, loss: 0.03482165187597275
2023-01-23 00:24:26.834755: step: 1516/530, loss: 0.2605397403240204
2023-01-23 00:24:27.982753: step: 1520/530, loss: 0.12189693748950958
2023-01-23 00:24:29.129895: step: 1524/530, loss: 0.18373775482177734
2023-01-23 00:24:30.262607: step: 1528/530, loss: 0.18816213309764862
2023-01-23 00:24:31.390900: step: 1532/530, loss: 0.10893383622169495
2023-01-23 00:24:32.531693: step: 1536/530, loss: 0.08929157257080078
2023-01-23 00:24:33.670854: step: 1540/530, loss: 0.3500238060951233
2023-01-23 00:24:34.791137: step: 1544/530, loss: 0.02064676210284233
2023-01-23 00:24:35.881404: step: 1548/530, loss: 0.04589357599616051
2023-01-23 00:24:36.983668: step: 1552/530, loss: 0.1696067750453949
2023-01-23 00:24:38.115721: step: 1556/530, loss: 0.16545256972312927
2023-01-23 00:24:39.232858: step: 1560/530, loss: 0.0654686912894249
2023-01-23 00:24:40.362343: step: 1564/530, loss: 0.6287447810173035
2023-01-23 00:24:41.482942: step: 1568/530, loss: 0.1089734137058258
2023-01-23 00:24:42.594752: step: 1572/530, loss: 0.06013832241296768
2023-01-23 00:24:43.724375: step: 1576/530, loss: 0.07506036758422852
2023-01-23 00:24:44.854066: step: 1580/530, loss: 0.5531541109085083
2023-01-23 00:24:45.969112: step: 1584/530, loss: 0.06878586113452911
2023-01-23 00:24:47.086933: step: 1588/530, loss: 0.1207190528512001
2023-01-23 00:24:48.219308: step: 1592/530, loss: 0.278353214263916
2023-01-23 00:24:49.329098: step: 1596/530, loss: 0.05043058469891548
2023-01-23 00:24:50.450698: step: 1600/530, loss: 0.1797867715358734
2023-01-23 00:24:51.549615: step: 1604/530, loss: 0.0501859188079834
2023-01-23 00:24:52.686415: step: 1608/530, loss: 0.8419907689094543
2023-01-23 00:24:53.858158: step: 1612/530, loss: 0.09508943557739258
2023-01-23 00:24:54.985013: step: 1616/530, loss: 0.14453211426734924
2023-01-23 00:24:56.110377: step: 1620/530, loss: 0.05309171974658966
2023-01-23 00:24:57.244986: step: 1624/530, loss: 0.08540558815002441
2023-01-23 00:24:58.372072: step: 1628/530, loss: 0.3839705288410187
2023-01-23 00:24:59.493775: step: 1632/530, loss: 0.2065594643354416
2023-01-23 00:25:00.630055: step: 1636/530, loss: 1.3691645860671997
2023-01-23 00:25:01.773343: step: 1640/530, loss: 0.4003581404685974
2023-01-23 00:25:02.926721: step: 1644/530, loss: 0.7048473954200745
2023-01-23 00:25:04.051655: step: 1648/530, loss: 0.24850665032863617
2023-01-23 00:25:05.186219: step: 1652/530, loss: 0.02414698526263237
2023-01-23 00:25:06.319784: step: 1656/530, loss: 0.08642005920410156
2023-01-23 00:25:07.465434: step: 1660/530, loss: 0.6366859674453735
2023-01-23 00:25:08.604222: step: 1664/530, loss: 0.1102198138833046
2023-01-23 00:25:09.761965: step: 1668/530, loss: 0.06933679431676865
2023-01-23 00:25:10.880604: step: 1672/530, loss: 0.2849675714969635
2023-01-23 00:25:12.005199: step: 1676/530, loss: 0.31922245025634766
2023-01-23 00:25:13.138770: step: 1680/530, loss: 0.42438358068466187
2023-01-23 00:25:14.250949: step: 1684/530, loss: 0.10104990005493164
2023-01-23 00:25:15.358778: step: 1688/530, loss: 0.08451852947473526
2023-01-23 00:25:16.500383: step: 1692/530, loss: 0.32380664348602295
2023-01-23 00:25:17.622731: step: 1696/530, loss: 0.2716783583164215
2023-01-23 00:25:18.767138: step: 1700/530, loss: 0.14854370057582855
2023-01-23 00:25:19.876922: step: 1704/530, loss: 0.07838621735572815
2023-01-23 00:25:21.001903: step: 1708/530, loss: 0.30359622836112976
2023-01-23 00:25:22.138948: step: 1712/530, loss: 0.29104965925216675
2023-01-23 00:25:23.256290: step: 1716/530, loss: 0.17394447326660156
2023-01-23 00:25:24.380910: step: 1720/530, loss: 0.20211371779441833
2023-01-23 00:25:25.521732: step: 1724/530, loss: 0.09822969883680344
2023-01-23 00:25:26.615915: step: 1728/530, loss: 0.09604644775390625
2023-01-23 00:25:27.762028: step: 1732/530, loss: 0.042954444885253906
2023-01-23 00:25:28.868830: step: 1736/530, loss: 0.4413073658943176
2023-01-23 00:25:29.959626: step: 1740/530, loss: 0.15138083696365356
2023-01-23 00:25:31.099893: step: 1744/530, loss: 0.2657526135444641
2023-01-23 00:25:32.232147: step: 1748/530, loss: 0.709804356098175
2023-01-23 00:25:33.377193: step: 1752/530, loss: 0.06254644691944122
2023-01-23 00:25:34.502209: step: 1756/530, loss: 0.13190633058547974
2023-01-23 00:25:35.634225: step: 1760/530, loss: 0.04444608837366104
2023-01-23 00:25:36.749210: step: 1764/530, loss: 0.09217515587806702
2023-01-23 00:25:37.932532: step: 1768/530, loss: 0.3437265455722809
2023-01-23 00:25:39.081107: step: 1772/530, loss: 0.40223953127861023
2023-01-23 00:25:40.198721: step: 1776/530, loss: 0.8026493787765503
2023-01-23 00:25:41.315904: step: 1780/530, loss: 0.15695348381996155
2023-01-23 00:25:42.477794: step: 1784/530, loss: 0.11650065332651138
2023-01-23 00:25:43.604917: step: 1788/530, loss: 0.36791807413101196
2023-01-23 00:25:44.728134: step: 1792/530, loss: 0.02191222831606865
2023-01-23 00:25:45.871303: step: 1796/530, loss: 0.5840681791305542
2023-01-23 00:25:46.999182: step: 1800/530, loss: 0.0982985571026802
2023-01-23 00:25:48.125519: step: 1804/530, loss: 0.11985808610916138
2023-01-23 00:25:49.238681: step: 1808/530, loss: 0.16817140579223633
2023-01-23 00:25:50.398580: step: 1812/530, loss: 0.1982143521308899
2023-01-23 00:25:51.548937: step: 1816/530, loss: 0.23344996571540833
2023-01-23 00:25:52.696873: step: 1820/530, loss: 0.09022513031959534
2023-01-23 00:25:53.834510: step: 1824/530, loss: 0.5485559105873108
2023-01-23 00:25:54.933342: step: 1828/530, loss: 0.19541864097118378
2023-01-23 00:25:56.062190: step: 1832/530, loss: 0.568931519985199
2023-01-23 00:25:57.198295: step: 1836/530, loss: 0.26919302344322205
2023-01-23 00:25:58.305155: step: 1840/530, loss: 0.08027572929859161
2023-01-23 00:25:59.428188: step: 1844/530, loss: 0.06768160313367844
2023-01-23 00:26:00.575694: step: 1848/530, loss: 0.45090949535369873
2023-01-23 00:26:01.722520: step: 1852/530, loss: 0.23631440103054047
2023-01-23 00:26:02.858634: step: 1856/530, loss: 1.2236262559890747
2023-01-23 00:26:03.955937: step: 1860/530, loss: 0.13902024924755096
2023-01-23 00:26:05.100918: step: 1864/530, loss: 0.6208492517471313
2023-01-23 00:26:06.233713: step: 1868/530, loss: 0.07035932689905167
2023-01-23 00:26:07.361523: step: 1872/530, loss: 0.4000682830810547
2023-01-23 00:26:08.483535: step: 1876/530, loss: 0.21575576066970825
2023-01-23 00:26:09.648873: step: 1880/530, loss: 0.0999719649553299
2023-01-23 00:26:10.789242: step: 1884/530, loss: 0.2011333405971527
2023-01-23 00:26:11.940156: step: 1888/530, loss: 0.5587990880012512
2023-01-23 00:26:13.063189: step: 1892/530, loss: 0.5708900690078735
2023-01-23 00:26:14.206976: step: 1896/530, loss: 0.08642025291919708
2023-01-23 00:26:15.321440: step: 1900/530, loss: 0.11000652611255646
2023-01-23 00:26:16.467310: step: 1904/530, loss: 0.09740067273378372
2023-01-23 00:26:17.583995: step: 1908/530, loss: 0.11247525364160538
2023-01-23 00:26:18.710772: step: 1912/530, loss: 0.10732746124267578
2023-01-23 00:26:19.835999: step: 1916/530, loss: 0.0624576136469841
2023-01-23 00:26:20.972948: step: 1920/530, loss: 0.48494482040405273
2023-01-23 00:26:22.108518: step: 1924/530, loss: 0.27472057938575745
2023-01-23 00:26:23.222542: step: 1928/530, loss: 0.39347752928733826
2023-01-23 00:26:24.338239: step: 1932/530, loss: 0.1965927630662918
2023-01-23 00:26:25.442083: step: 1936/530, loss: 0.10447807610034943
2023-01-23 00:26:26.602525: step: 1940/530, loss: 0.17233189940452576
2023-01-23 00:26:27.704354: step: 1944/530, loss: 0.125209242105484
2023-01-23 00:26:28.834850: step: 1948/530, loss: 0.04891815409064293
2023-01-23 00:26:29.949585: step: 1952/530, loss: 0.14031849801540375
2023-01-23 00:26:31.104206: step: 1956/530, loss: 0.13968229293823242
2023-01-23 00:26:32.248225: step: 1960/530, loss: 0.19782835245132446
2023-01-23 00:26:33.364608: step: 1964/530, loss: 0.23898521065711975
2023-01-23 00:26:34.543922: step: 1968/530, loss: 0.10926322638988495
2023-01-23 00:26:35.673921: step: 1972/530, loss: 0.18810200691223145
2023-01-23 00:26:36.816365: step: 1976/530, loss: 0.06363999843597412
2023-01-23 00:26:37.926590: step: 1980/530, loss: 0.08606290817260742
2023-01-23 00:26:39.110698: step: 1984/530, loss: 0.07819166034460068
2023-01-23 00:26:40.214729: step: 1988/530, loss: 0.07699299603700638
2023-01-23 00:26:41.377358: step: 1992/530, loss: 0.18645472824573517
2023-01-23 00:26:42.487492: step: 1996/530, loss: 0.04337611421942711
2023-01-23 00:26:43.624111: step: 2000/530, loss: 0.2782968580722809
2023-01-23 00:26:44.747087: step: 2004/530, loss: 0.9622762203216553
2023-01-23 00:26:45.856723: step: 2008/530, loss: 0.010148381814360619
2023-01-23 00:26:46.979404: step: 2012/530, loss: 0.05298314243555069
2023-01-23 00:26:48.099801: step: 2016/530, loss: 0.8698732852935791
2023-01-23 00:26:49.206602: step: 2020/530, loss: 0.42634153366088867
2023-01-23 00:26:50.331393: step: 2024/530, loss: 0.10237999260425568
2023-01-23 00:26:51.472138: step: 2028/530, loss: 0.3417743742465973
2023-01-23 00:26:52.621758: step: 2032/530, loss: 0.17312544584274292
2023-01-23 00:26:53.778075: step: 2036/530, loss: 0.03941159322857857
2023-01-23 00:26:54.919236: step: 2040/530, loss: 0.11214208602905273
2023-01-23 00:26:56.040764: step: 2044/530, loss: 0.5566015839576721
2023-01-23 00:26:57.155796: step: 2048/530, loss: 0.18551188707351685
2023-01-23 00:26:58.262014: step: 2052/530, loss: 0.04253873974084854
2023-01-23 00:26:59.395553: step: 2056/530, loss: 0.10253920406103134
2023-01-23 00:27:00.536427: step: 2060/530, loss: 1.281870722770691
2023-01-23 00:27:01.666387: step: 2064/530, loss: 0.2358206957578659
2023-01-23 00:27:02.785640: step: 2068/530, loss: 0.07573598623275757
2023-01-23 00:27:03.900116: step: 2072/530, loss: 0.30315670371055603
2023-01-23 00:27:05.038752: step: 2076/530, loss: 0.3258075714111328
2023-01-23 00:27:06.165573: step: 2080/530, loss: 0.11895184218883514
2023-01-23 00:27:07.273899: step: 2084/530, loss: 0.06229085847735405
2023-01-23 00:27:08.384821: step: 2088/530, loss: 0.08908441662788391
2023-01-23 00:27:09.510434: step: 2092/530, loss: 0.11622504889965057
2023-01-23 00:27:10.635095: step: 2096/530, loss: 0.1601143777370453
2023-01-23 00:27:11.757532: step: 2100/530, loss: 0.087957963347435
2023-01-23 00:27:12.864088: step: 2104/530, loss: 0.08399859070777893
2023-01-23 00:27:13.999379: step: 2108/530, loss: 0.09608087688684464
2023-01-23 00:27:15.151540: step: 2112/530, loss: 0.20828914642333984
2023-01-23 00:27:16.280221: step: 2116/530, loss: 1.5464457273483276
2023-01-23 00:27:17.425800: step: 2120/530, loss: 0.41183242201805115
==================================================
Loss: 0.257
--------------------
Dev: {'event': {'p': 0.5623781676413255, 'r': 0.7683089214380826, 'f1': 0.6494091164884638}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Test: {'event': {'p': 0.6135852451641925, 'r': 0.7794285714285715, 'f1': 0.6866347847973824}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
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': 5}
Korean: {'event': {'p': 0.6458333333333334, 'r': 0.49206349206349204, 'f1': 0.5585585585585586}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Russian: {'event': {'p': 0.5, 'r': 0.6388888888888888, 'f1': 0.5609756097560975}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6534653465346535, 'r': 0.7030625832223701, 'f1': 0.6773572803078897}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Eng Test for Chinese: {'event': {'p': 0.6715481171548117, 'r': 0.7337142857142858, 'f1': 0.7012561441835063}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Sample Chinese: {'event': {'p': 0.6111111111111112, 'r': 0.8148148148148148, 'f1': 0.6984126984126984}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5832471561530507, 'r': 0.7509986684420772, 'f1': 0.6565774155995343}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Korean: {'event': {'p': 0.603579418344519, 'r': 0.7708571428571429, 'f1': 0.6770388958594731}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Korean: {'event': {'p': 0.6470588235294118, 'r': 0.5238095238095238, 'f1': 0.5789473684210527}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6534653465346535, 'r': 0.7030625832223701, 'f1': 0.6773572803078897}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Eng Test for Russian: {'event': {'p': 0.6715481171548117, 'r': 0.7337142857142858, 'f1': 0.7012561441835063}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Sample Russian: {'event': {'p': 0.5405405405405406, 'r': 0.5555555555555556, 'f1': 0.547945205479452}, '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 00:27:58.506548: step: 4/530, loss: 0.11194248497486115
2023-01-23 00:27:59.628013: step: 8/530, loss: 0.049623921513557434
2023-01-23 00:28:00.737645: step: 12/530, loss: 0.2674240171909332
2023-01-23 00:28:01.886005: step: 16/530, loss: 0.4016891419887543
2023-01-23 00:28:02.985443: step: 20/530, loss: 0.08837618678808212
2023-01-23 00:28:04.121876: step: 24/530, loss: 0.1961146891117096
2023-01-23 00:28:05.264060: step: 28/530, loss: 0.5754033923149109
2023-01-23 00:28:06.396048: step: 32/530, loss: 0.07500315457582474
2023-01-23 00:28:07.517799: step: 36/530, loss: 0.28617429733276367
2023-01-23 00:28:08.645212: step: 40/530, loss: 0.11771003901958466
2023-01-23 00:28:09.766799: step: 44/530, loss: 0.10080128163099289
2023-01-23 00:28:10.899015: step: 48/530, loss: 0.07413606345653534
2023-01-23 00:28:12.004219: step: 52/530, loss: 0.1635688841342926
2023-01-23 00:28:13.115455: step: 56/530, loss: 1.0997036695480347
2023-01-23 00:28:14.227878: step: 60/530, loss: 0.060564424842596054
2023-01-23 00:28:15.343502: step: 64/530, loss: 0.0589059442281723
2023-01-23 00:28:16.442973: step: 68/530, loss: 0.1011110320687294
2023-01-23 00:28:17.563180: step: 72/530, loss: 0.05460335314273834
2023-01-23 00:28:18.673853: step: 76/530, loss: 0.019150162115693092
2023-01-23 00:28:19.795688: step: 80/530, loss: 0.10857105255126953
2023-01-23 00:28:20.952555: step: 84/530, loss: 0.1468132585287094
2023-01-23 00:28:22.070556: step: 88/530, loss: 0.20085926353931427
2023-01-23 00:28:23.220221: step: 92/530, loss: 0.03862953186035156
2023-01-23 00:28:24.339151: step: 96/530, loss: 0.14193525910377502
2023-01-23 00:28:25.443727: step: 100/530, loss: 0.053687430918216705
2023-01-23 00:28:26.544007: step: 104/530, loss: 0.21082444489002228
2023-01-23 00:28:27.688459: step: 108/530, loss: 0.3369824290275574
2023-01-23 00:28:28.829092: step: 112/530, loss: 0.09846735000610352
2023-01-23 00:28:29.952472: step: 116/530, loss: 0.06406798213720322
2023-01-23 00:28:31.062412: step: 120/530, loss: 0.06315302848815918
2023-01-23 00:28:32.173088: step: 124/530, loss: 0.14239558577537537
2023-01-23 00:28:33.313520: step: 128/530, loss: 0.09159211814403534
2023-01-23 00:28:34.431382: step: 132/530, loss: 0.16498985886573792
2023-01-23 00:28:35.567441: step: 136/530, loss: 0.39249420166015625
2023-01-23 00:28:36.693455: step: 140/530, loss: 0.24727730453014374
2023-01-23 00:28:37.819336: step: 144/530, loss: 0.08183468878269196
2023-01-23 00:28:38.952296: step: 148/530, loss: 0.18683281540870667
2023-01-23 00:28:40.083788: step: 152/530, loss: 0.2134561687707901
2023-01-23 00:28:41.166682: step: 156/530, loss: 0.11397352814674377
2023-01-23 00:28:42.270514: step: 160/530, loss: 0.1358993500471115
2023-01-23 00:28:43.403671: step: 164/530, loss: 0.6313165426254272
2023-01-23 00:28:44.510181: step: 168/530, loss: 0.16857090592384338
2023-01-23 00:28:45.661026: step: 172/530, loss: 0.29583850502967834
2023-01-23 00:28:46.783224: step: 176/530, loss: 0.12963418662548065
2023-01-23 00:28:47.920964: step: 180/530, loss: 0.04939279705286026
2023-01-23 00:28:49.049659: step: 184/530, loss: 0.17047253251075745
2023-01-23 00:28:50.172765: step: 188/530, loss: 0.4329880475997925
2023-01-23 00:28:51.311598: step: 192/530, loss: 1.1938530206680298
2023-01-23 00:28:52.466894: step: 196/530, loss: 0.0672723799943924
2023-01-23 00:28:53.570328: step: 200/530, loss: 0.15000496804714203
2023-01-23 00:28:54.715326: step: 204/530, loss: 0.010749245062470436
2023-01-23 00:28:55.849429: step: 208/530, loss: 0.08671312034130096
2023-01-23 00:28:56.990959: step: 212/530, loss: 0.13785028457641602
2023-01-23 00:28:58.129688: step: 216/530, loss: 0.09297370910644531
2023-01-23 00:28:59.236002: step: 220/530, loss: 0.7623798251152039
2023-01-23 00:29:00.361953: step: 224/530, loss: 0.33997198939323425
2023-01-23 00:29:01.489460: step: 228/530, loss: 0.20066604018211365
2023-01-23 00:29:02.608242: step: 232/530, loss: 0.22781620919704437
2023-01-23 00:29:03.730269: step: 236/530, loss: 0.12429914623498917
2023-01-23 00:29:04.851287: step: 240/530, loss: 0.0406736359000206
2023-01-23 00:29:05.972306: step: 244/530, loss: 0.1048862487077713
2023-01-23 00:29:07.105144: step: 248/530, loss: 0.26026782393455505
2023-01-23 00:29:08.236317: step: 252/530, loss: 0.11861743777990341
2023-01-23 00:29:09.341923: step: 256/530, loss: 0.17957691848278046
2023-01-23 00:29:10.481786: step: 260/530, loss: 0.6569564342498779
2023-01-23 00:29:11.588644: step: 264/530, loss: 0.3405083119869232
2023-01-23 00:29:12.743644: step: 268/530, loss: 0.21052753925323486
2023-01-23 00:29:13.857706: step: 272/530, loss: 0.3186979591846466
2023-01-23 00:29:14.974609: step: 276/530, loss: 0.03326263278722763
2023-01-23 00:29:16.092618: step: 280/530, loss: 0.020763732492923737
2023-01-23 00:29:17.209283: step: 284/530, loss: 0.1216953694820404
2023-01-23 00:29:18.321694: step: 288/530, loss: 0.13241548836231232
2023-01-23 00:29:19.457449: step: 292/530, loss: 0.3040769696235657
2023-01-23 00:29:20.589818: step: 296/530, loss: 0.4823044538497925
2023-01-23 00:29:21.752810: step: 300/530, loss: 0.12489767372608185
2023-01-23 00:29:22.860608: step: 304/530, loss: 0.12295909225940704
2023-01-23 00:29:24.014411: step: 308/530, loss: 0.042694948613643646
2023-01-23 00:29:25.120004: step: 312/530, loss: 0.14850598573684692
2023-01-23 00:29:26.213398: step: 316/530, loss: 0.10556916892528534
2023-01-23 00:29:27.291050: step: 320/530, loss: 0.11462660133838654
2023-01-23 00:29:28.408532: step: 324/530, loss: 0.08037600666284561
2023-01-23 00:29:29.521558: step: 328/530, loss: 0.16339492797851562
2023-01-23 00:29:30.622104: step: 332/530, loss: 0.08692774921655655
2023-01-23 00:29:31.759648: step: 336/530, loss: 0.10949669778347015
2023-01-23 00:29:32.884614: step: 340/530, loss: 0.12452287971973419
2023-01-23 00:29:34.028371: step: 344/530, loss: 0.01850919798016548
2023-01-23 00:29:35.174317: step: 348/530, loss: 0.03559465333819389
2023-01-23 00:29:36.283828: step: 352/530, loss: 0.060702040791511536
2023-01-23 00:29:37.407985: step: 356/530, loss: 0.11019151657819748
2023-01-23 00:29:38.537877: step: 360/530, loss: 0.047522544860839844
2023-01-23 00:29:39.653898: step: 364/530, loss: 0.15981540083885193
2023-01-23 00:29:40.755519: step: 368/530, loss: 0.021494578570127487
2023-01-23 00:29:41.873051: step: 372/530, loss: 0.1744919866323471
2023-01-23 00:29:42.997702: step: 376/530, loss: 0.11825066059827805
2023-01-23 00:29:44.134831: step: 380/530, loss: 0.08242321014404297
2023-01-23 00:29:45.255176: step: 384/530, loss: 0.08118505775928497
2023-01-23 00:29:46.360619: step: 388/530, loss: 0.027975846081972122
2023-01-23 00:29:47.517291: step: 392/530, loss: 0.044190309941768646
2023-01-23 00:29:48.644593: step: 396/530, loss: 0.0552341490983963
2023-01-23 00:29:49.798566: step: 400/530, loss: 0.6174713373184204
2023-01-23 00:29:50.953234: step: 404/530, loss: 0.6127270460128784
2023-01-23 00:29:52.070011: step: 408/530, loss: 0.06541475653648376
2023-01-23 00:29:53.179688: step: 412/530, loss: 0.18652623891830444
2023-01-23 00:29:54.330372: step: 416/530, loss: 0.28773394227027893
2023-01-23 00:29:55.483782: step: 420/530, loss: 0.47584548592567444
2023-01-23 00:29:56.634389: step: 424/530, loss: 0.10230350494384766
2023-01-23 00:29:57.834703: step: 428/530, loss: 0.12202253192663193
2023-01-23 00:29:58.967945: step: 432/530, loss: 0.11746470630168915
2023-01-23 00:30:00.095360: step: 436/530, loss: 0.08739033341407776
2023-01-23 00:30:01.257419: step: 440/530, loss: 0.3817031979560852
2023-01-23 00:30:02.363505: step: 444/530, loss: 0.08086929470300674
2023-01-23 00:30:03.508109: step: 448/530, loss: 0.009555435739457607
2023-01-23 00:30:04.656078: step: 452/530, loss: 0.13949918746948242
2023-01-23 00:30:05.780649: step: 456/530, loss: 0.0866062194108963
2023-01-23 00:30:06.898207: step: 460/530, loss: 0.06560106575489044
2023-01-23 00:30:08.009016: step: 464/530, loss: 0.384586900472641
2023-01-23 00:30:09.107096: step: 468/530, loss: 0.3166958689689636
2023-01-23 00:30:10.232215: step: 472/530, loss: 0.019094564020633698
2023-01-23 00:30:11.345799: step: 476/530, loss: 0.1679706871509552
2023-01-23 00:30:12.444743: step: 480/530, loss: 0.03817443549633026
2023-01-23 00:30:13.597146: step: 484/530, loss: 0.2168036550283432
2023-01-23 00:30:14.753437: step: 488/530, loss: 0.11938080936670303
2023-01-23 00:30:15.875356: step: 492/530, loss: 0.15857356786727905
2023-01-23 00:30:17.003850: step: 496/530, loss: 0.08879127353429794
2023-01-23 00:30:18.123598: step: 500/530, loss: 0.03689851611852646
2023-01-23 00:30:19.224937: step: 504/530, loss: 0.13657721877098083
2023-01-23 00:30:20.359906: step: 508/530, loss: 0.04713382571935654
2023-01-23 00:30:21.489002: step: 512/530, loss: 0.054463766515254974
2023-01-23 00:30:22.601538: step: 516/530, loss: 0.17969933152198792
2023-01-23 00:30:23.768694: step: 520/530, loss: 0.017021656036376953
2023-01-23 00:30:24.893021: step: 524/530, loss: 0.26531982421875
2023-01-23 00:30:26.011733: step: 528/530, loss: 0.07258759438991547
2023-01-23 00:30:27.160002: step: 532/530, loss: 0.3317708969116211
2023-01-23 00:30:28.292611: step: 536/530, loss: 0.147942915558815
2023-01-23 00:30:29.419057: step: 540/530, loss: 0.08274231106042862
2023-01-23 00:30:30.551865: step: 544/530, loss: 0.14594116806983948
2023-01-23 00:30:31.629423: step: 548/530, loss: 0.24725544452667236
2023-01-23 00:30:32.741011: step: 552/530, loss: 0.3674476742744446
2023-01-23 00:30:33.872723: step: 556/530, loss: 0.01938924938440323
2023-01-23 00:30:34.986727: step: 560/530, loss: 0.13125286996364594
2023-01-23 00:30:36.106836: step: 564/530, loss: 0.060601044446229935
2023-01-23 00:30:37.249738: step: 568/530, loss: 0.0606420524418354
2023-01-23 00:30:38.391062: step: 572/530, loss: 0.11411742866039276
2023-01-23 00:30:39.527470: step: 576/530, loss: 0.04862036556005478
2023-01-23 00:30:40.685087: step: 580/530, loss: 0.09410410374403
2023-01-23 00:30:41.806897: step: 584/530, loss: 0.22315135598182678
2023-01-23 00:30:42.918246: step: 588/530, loss: 0.3560633659362793
2023-01-23 00:30:44.066483: step: 592/530, loss: 0.1942174881696701
2023-01-23 00:30:45.168139: step: 596/530, loss: 0.07413597404956818
2023-01-23 00:30:46.318234: step: 600/530, loss: 0.30392590165138245
2023-01-23 00:30:47.431419: step: 604/530, loss: 0.18566074967384338
2023-01-23 00:30:48.577009: step: 608/530, loss: 0.08718490600585938
2023-01-23 00:30:49.696438: step: 612/530, loss: 0.04963655769824982
2023-01-23 00:30:50.852867: step: 616/530, loss: 0.024406051263213158
2023-01-23 00:30:51.969377: step: 620/530, loss: 0.16222438216209412
2023-01-23 00:30:53.087336: step: 624/530, loss: 0.2591068744659424
2023-01-23 00:30:54.209565: step: 628/530, loss: 0.08294692635536194
2023-01-23 00:30:55.346664: step: 632/530, loss: 0.20426569879055023
2023-01-23 00:30:56.488014: step: 636/530, loss: 0.29253149032592773
2023-01-23 00:30:57.614026: step: 640/530, loss: 0.10060005635023117
2023-01-23 00:30:58.737520: step: 644/530, loss: 0.09808759391307831
2023-01-23 00:30:59.851194: step: 648/530, loss: 0.13261820375919342
2023-01-23 00:31:00.952929: step: 652/530, loss: 0.23392906785011292
2023-01-23 00:31:02.092729: step: 656/530, loss: 0.07397551834583282
2023-01-23 00:31:03.205082: step: 660/530, loss: 0.17286443710327148
2023-01-23 00:31:04.298531: step: 664/530, loss: 0.0275329127907753
2023-01-23 00:31:05.408575: step: 668/530, loss: 0.07778511196374893
2023-01-23 00:31:06.556378: step: 672/530, loss: 0.1746256798505783
2023-01-23 00:31:07.678100: step: 676/530, loss: 0.25683510303497314
2023-01-23 00:31:08.813833: step: 680/530, loss: 0.07895040512084961
2023-01-23 00:31:09.947216: step: 684/530, loss: 0.17074833810329437
2023-01-23 00:31:11.093293: step: 688/530, loss: 0.3005863130092621
2023-01-23 00:31:12.207545: step: 692/530, loss: 0.13454914093017578
2023-01-23 00:31:13.314467: step: 696/530, loss: 0.18390029668807983
2023-01-23 00:31:14.452684: step: 700/530, loss: 0.2685925364494324
2023-01-23 00:31:15.567798: step: 704/530, loss: 0.06342411041259766
2023-01-23 00:31:16.688598: step: 708/530, loss: 0.07591047137975693
2023-01-23 00:31:17.816387: step: 712/530, loss: 0.15268459916114807
2023-01-23 00:31:18.957843: step: 716/530, loss: 0.07096538692712784
2023-01-23 00:31:20.064069: step: 720/530, loss: 0.22825470566749573
2023-01-23 00:31:21.222225: step: 724/530, loss: 0.04830455780029297
2023-01-23 00:31:22.381373: step: 728/530, loss: 0.1716753989458084
2023-01-23 00:31:23.490358: step: 732/530, loss: 0.08199730515480042
2023-01-23 00:31:24.612682: step: 736/530, loss: 0.042665187269449234
2023-01-23 00:31:25.753614: step: 740/530, loss: 0.4883585572242737
2023-01-23 00:31:26.880482: step: 744/530, loss: 0.1581067144870758
2023-01-23 00:31:27.991887: step: 748/530, loss: 0.06403084099292755
2023-01-23 00:31:29.097799: step: 752/530, loss: 0.1654316782951355
2023-01-23 00:31:30.192674: step: 756/530, loss: 0.0798945426940918
2023-01-23 00:31:31.316868: step: 760/530, loss: 0.06621751934289932
2023-01-23 00:31:32.434846: step: 764/530, loss: 0.053577519953250885
2023-01-23 00:31:33.626586: step: 768/530, loss: 0.11058750748634338
2023-01-23 00:31:34.774776: step: 772/530, loss: 0.017936183139681816
2023-01-23 00:31:35.917042: step: 776/530, loss: 0.04355302080512047
2023-01-23 00:31:37.046585: step: 780/530, loss: 0.36495158076286316
2023-01-23 00:31:38.142498: step: 784/530, loss: 0.43934112787246704
2023-01-23 00:31:39.266328: step: 788/530, loss: 0.07102146744728088
2023-01-23 00:31:40.391179: step: 792/530, loss: 0.21190303564071655
2023-01-23 00:31:41.524335: step: 796/530, loss: 0.29780712723731995
2023-01-23 00:31:42.638455: step: 800/530, loss: 0.34278467297554016
2023-01-23 00:31:43.782093: step: 804/530, loss: 0.15146255493164062
2023-01-23 00:31:44.915951: step: 808/530, loss: 0.19004635512828827
2023-01-23 00:31:46.006493: step: 812/530, loss: 0.05664868652820587
2023-01-23 00:31:47.141178: step: 816/530, loss: 0.05887401103973389
2023-01-23 00:31:48.272972: step: 820/530, loss: 0.08248929679393768
2023-01-23 00:31:49.382948: step: 824/530, loss: 0.06411056965589523
2023-01-23 00:31:50.521524: step: 828/530, loss: 0.5204371213912964
2023-01-23 00:31:51.644980: step: 832/530, loss: 0.05493386089801788
2023-01-23 00:31:52.784363: step: 836/530, loss: 1.2070831060409546
2023-01-23 00:31:53.921295: step: 840/530, loss: 0.6121943593025208
2023-01-23 00:31:55.030647: step: 844/530, loss: 0.23101691901683807
2023-01-23 00:31:56.154453: step: 848/530, loss: 0.09901097416877747
2023-01-23 00:31:57.296184: step: 852/530, loss: 0.39380624890327454
2023-01-23 00:31:58.414824: step: 856/530, loss: 0.01799907721579075
2023-01-23 00:31:59.524442: step: 860/530, loss: 0.08131790161132812
2023-01-23 00:32:00.626952: step: 864/530, loss: 0.020610427483916283
2023-01-23 00:32:01.733416: step: 868/530, loss: 0.1006801575422287
2023-01-23 00:32:02.866217: step: 872/530, loss: 0.08300866931676865
2023-01-23 00:32:03.996882: step: 876/530, loss: 0.038166143000125885
2023-01-23 00:32:05.109280: step: 880/530, loss: 0.0500035285949707
2023-01-23 00:32:06.221629: step: 884/530, loss: 0.05715980380773544
2023-01-23 00:32:07.370558: step: 888/530, loss: 0.3410232663154602
2023-01-23 00:32:08.473654: step: 892/530, loss: 0.2113526463508606
2023-01-23 00:32:09.588078: step: 896/530, loss: 0.06199474260210991
2023-01-23 00:32:10.710231: step: 900/530, loss: 0.19418449699878693
2023-01-23 00:32:11.832579: step: 904/530, loss: 0.4718639552593231
2023-01-23 00:32:12.996805: step: 908/530, loss: 0.20216770470142365
2023-01-23 00:32:14.112522: step: 912/530, loss: 0.26844674348831177
2023-01-23 00:32:15.224165: step: 916/530, loss: 0.058798979967832565
2023-01-23 00:32:16.358441: step: 920/530, loss: 0.15817013382911682
2023-01-23 00:32:17.469202: step: 924/530, loss: 0.29059523344039917
2023-01-23 00:32:18.563812: step: 928/530, loss: 0.1474754363298416
2023-01-23 00:32:19.662742: step: 932/530, loss: 0.11966433376073837
2023-01-23 00:32:20.787367: step: 936/530, loss: 0.07209692895412445
2023-01-23 00:32:21.911326: step: 940/530, loss: 0.06701042503118515
2023-01-23 00:32:23.022910: step: 944/530, loss: 0.04705529287457466
2023-01-23 00:32:24.129210: step: 948/530, loss: 0.05824854224920273
2023-01-23 00:32:25.221020: step: 952/530, loss: 0.20646142959594727
2023-01-23 00:32:26.326377: step: 956/530, loss: 0.1423918604850769
2023-01-23 00:32:27.454501: step: 960/530, loss: 0.296003133058548
2023-01-23 00:32:28.593921: step: 964/530, loss: 0.08810319751501083
2023-01-23 00:32:29.742740: step: 968/530, loss: 0.7253124713897705
2023-01-23 00:32:30.876138: step: 972/530, loss: 1.5166828632354736
2023-01-23 00:32:32.014389: step: 976/530, loss: 0.0873604267835617
2023-01-23 00:32:33.129301: step: 980/530, loss: 0.9824960231781006
2023-01-23 00:32:34.273402: step: 984/530, loss: 0.013598823919892311
2023-01-23 00:32:35.392352: step: 988/530, loss: 0.7239496111869812
2023-01-23 00:32:36.512929: step: 992/530, loss: 0.12836608290672302
2023-01-23 00:32:37.638123: step: 996/530, loss: 0.08518409729003906
2023-01-23 00:32:38.761037: step: 1000/530, loss: 0.01154622994363308
2023-01-23 00:32:39.895567: step: 1004/530, loss: 0.4631291925907135
2023-01-23 00:32:41.026226: step: 1008/530, loss: 0.08600912243127823
2023-01-23 00:32:42.142176: step: 1012/530, loss: 0.01753721386194229
2023-01-23 00:32:43.253759: step: 1016/530, loss: 0.3470671772956848
2023-01-23 00:32:44.375919: step: 1020/530, loss: 0.5096868276596069
2023-01-23 00:32:45.513399: step: 1024/530, loss: 0.3036513030529022
2023-01-23 00:32:46.659012: step: 1028/530, loss: 0.13549338281154633
2023-01-23 00:32:47.799785: step: 1032/530, loss: 0.2141742706298828
2023-01-23 00:32:48.950811: step: 1036/530, loss: 0.1712675392627716
2023-01-23 00:32:50.110173: step: 1040/530, loss: 0.14944756031036377
2023-01-23 00:32:51.219092: step: 1044/530, loss: 0.05993552505970001
2023-01-23 00:32:52.346318: step: 1048/530, loss: 0.7211365103721619
2023-01-23 00:32:53.487429: step: 1052/530, loss: 0.0779966413974762
2023-01-23 00:32:54.608511: step: 1056/530, loss: 0.06341171264648438
2023-01-23 00:32:55.716045: step: 1060/530, loss: 0.13384047150611877
2023-01-23 00:32:56.849659: step: 1064/530, loss: 0.06296498328447342
2023-01-23 00:32:57.982845: step: 1068/530, loss: 0.2466968595981598
2023-01-23 00:32:59.096436: step: 1072/530, loss: 0.09526863694190979
2023-01-23 00:33:00.217594: step: 1076/530, loss: 0.014645003713667393
2023-01-23 00:33:01.322456: step: 1080/530, loss: 0.21385088562965393
2023-01-23 00:33:02.457271: step: 1084/530, loss: 0.3780633807182312
2023-01-23 00:33:03.593663: step: 1088/530, loss: 0.3160451054573059
2023-01-23 00:33:04.745199: step: 1092/530, loss: 0.32387468218803406
2023-01-23 00:33:05.868979: step: 1096/530, loss: 0.04341869428753853
2023-01-23 00:33:07.004148: step: 1100/530, loss: 0.07547321915626526
2023-01-23 00:33:08.141819: step: 1104/530, loss: 0.26678380370140076
2023-01-23 00:33:09.283779: step: 1108/530, loss: 0.2126132994890213
2023-01-23 00:33:10.423787: step: 1112/530, loss: 0.07048411667346954
2023-01-23 00:33:11.550844: step: 1116/530, loss: 0.08048667758703232
2023-01-23 00:33:12.642947: step: 1120/530, loss: 0.012352370657026768
2023-01-23 00:33:13.776194: step: 1124/530, loss: 0.06429357826709747
2023-01-23 00:33:14.946412: step: 1128/530, loss: 0.031514931470155716
2023-01-23 00:33:16.084906: step: 1132/530, loss: 1.2397717237472534
2023-01-23 00:33:17.210737: step: 1136/530, loss: 0.028403710573911667
2023-01-23 00:33:18.358675: step: 1140/530, loss: 0.10085955262184143
2023-01-23 00:33:19.505997: step: 1144/530, loss: 0.1403471976518631
2023-01-23 00:33:20.638938: step: 1148/530, loss: 0.7042710185050964
2023-01-23 00:33:21.801484: step: 1152/530, loss: 0.09390640258789062
2023-01-23 00:33:22.941153: step: 1156/530, loss: 0.09355869889259338
2023-01-23 00:33:24.067852: step: 1160/530, loss: 0.007473087403923273
2023-01-23 00:33:25.201822: step: 1164/530, loss: 0.27679768204689026
2023-01-23 00:33:26.365585: step: 1168/530, loss: 0.11187019944190979
2023-01-23 00:33:27.484545: step: 1172/530, loss: 0.053135111927986145
2023-01-23 00:33:28.585541: step: 1176/530, loss: 0.08385889232158661
2023-01-23 00:33:29.694948: step: 1180/530, loss: 0.17480221390724182
2023-01-23 00:33:30.822931: step: 1184/530, loss: 2.046238422393799
2023-01-23 00:33:31.933452: step: 1188/530, loss: 0.02764158323407173
2023-01-23 00:33:33.068955: step: 1192/530, loss: 0.0494568832218647
2023-01-23 00:33:34.214788: step: 1196/530, loss: 0.06500430405139923
2023-01-23 00:33:35.337396: step: 1200/530, loss: 0.12212173640727997
2023-01-23 00:33:36.476057: step: 1204/530, loss: 0.19683972001075745
2023-01-23 00:33:37.597939: step: 1208/530, loss: 0.06458806991577148
2023-01-23 00:33:38.735861: step: 1212/530, loss: 0.11424527317285538
2023-01-23 00:33:39.860357: step: 1216/530, loss: 0.19803999364376068
2023-01-23 00:33:40.990946: step: 1220/530, loss: 0.04700913652777672
2023-01-23 00:33:42.129621: step: 1224/530, loss: 0.048827171325683594
2023-01-23 00:33:43.247171: step: 1228/530, loss: 0.05452003329992294
2023-01-23 00:33:44.390747: step: 1232/530, loss: 0.21613922715187073
2023-01-23 00:33:45.515407: step: 1236/530, loss: 0.24322834610939026
2023-01-23 00:33:46.638460: step: 1240/530, loss: 0.04457903280854225
2023-01-23 00:33:47.752110: step: 1244/530, loss: 0.0448366180062294
2023-01-23 00:33:48.884768: step: 1248/530, loss: 0.09091325104236603
2023-01-23 00:33:50.001916: step: 1252/530, loss: 0.09748277813196182
2023-01-23 00:33:51.143892: step: 1256/530, loss: 0.12203522026538849
2023-01-23 00:33:52.285017: step: 1260/530, loss: 0.335780531167984
2023-01-23 00:33:53.415123: step: 1264/530, loss: 0.22614207863807678
2023-01-23 00:33:54.524845: step: 1268/530, loss: 0.2030268758535385
2023-01-23 00:33:55.628961: step: 1272/530, loss: 0.22400760650634766
2023-01-23 00:33:56.772388: step: 1276/530, loss: 0.08141575008630753
2023-01-23 00:33:57.922306: step: 1280/530, loss: 0.5172402858734131
2023-01-23 00:33:59.059302: step: 1284/530, loss: 0.22656220197677612
2023-01-23 00:34:00.197296: step: 1288/530, loss: 0.11657829582691193
2023-01-23 00:34:01.338458: step: 1292/530, loss: 0.06654205173254013
2023-01-23 00:34:02.468041: step: 1296/530, loss: 0.015016365796327591
2023-01-23 00:34:03.590699: step: 1300/530, loss: 0.4473293423652649
2023-01-23 00:34:04.726940: step: 1304/530, loss: 0.2816286087036133
2023-01-23 00:34:05.836336: step: 1308/530, loss: 0.2372780740261078
2023-01-23 00:34:06.944994: step: 1312/530, loss: 0.13489703834056854
2023-01-23 00:34:08.078480: step: 1316/530, loss: 0.052164364606142044
2023-01-23 00:34:09.176511: step: 1320/530, loss: 0.20643702149391174
2023-01-23 00:34:10.294935: step: 1324/530, loss: 0.2209964245557785
2023-01-23 00:34:11.399795: step: 1328/530, loss: 0.16489094495773315
2023-01-23 00:34:12.527171: step: 1332/530, loss: 0.23755799233913422
2023-01-23 00:34:13.685392: step: 1336/530, loss: 0.10670223087072372
2023-01-23 00:34:14.788897: step: 1340/530, loss: 0.0945381224155426
2023-01-23 00:34:15.895229: step: 1344/530, loss: 0.44866687059402466
2023-01-23 00:34:17.022637: step: 1348/530, loss: 0.21802903711795807
2023-01-23 00:34:18.140744: step: 1352/530, loss: 0.08314695209264755
2023-01-23 00:34:19.267044: step: 1356/530, loss: 0.1375287026166916
2023-01-23 00:34:20.425253: step: 1360/530, loss: 0.33060723543167114
2023-01-23 00:34:21.540205: step: 1364/530, loss: 0.11901453137397766
2023-01-23 00:34:22.669651: step: 1368/530, loss: 0.03996272385120392
2023-01-23 00:34:23.769635: step: 1372/530, loss: 0.05270390585064888
2023-01-23 00:34:24.873701: step: 1376/530, loss: 0.1120242103934288
2023-01-23 00:34:25.978338: step: 1380/530, loss: 0.11558208614587784
2023-01-23 00:34:27.085298: step: 1384/530, loss: 0.10492321848869324
2023-01-23 00:34:28.210819: step: 1388/530, loss: 0.01764545403420925
2023-01-23 00:34:29.324761: step: 1392/530, loss: 0.2943659722805023
2023-01-23 00:34:30.444108: step: 1396/530, loss: 0.10658684372901917
2023-01-23 00:34:31.542186: step: 1400/530, loss: 0.06164398044347763
2023-01-23 00:34:32.685585: step: 1404/530, loss: 0.09172210842370987
2023-01-23 00:34:33.811038: step: 1408/530, loss: 0.11529102176427841
2023-01-23 00:34:34.931753: step: 1412/530, loss: 0.36260128021240234
2023-01-23 00:34:36.067141: step: 1416/530, loss: 0.11755562573671341
2023-01-23 00:34:37.212576: step: 1420/530, loss: 0.1664118766784668
2023-01-23 00:34:38.351537: step: 1424/530, loss: 0.09763488918542862
2023-01-23 00:34:39.477906: step: 1428/530, loss: 0.16853809356689453
2023-01-23 00:34:40.628241: step: 1432/530, loss: 0.26410362124443054
2023-01-23 00:34:41.738816: step: 1436/530, loss: 0.1288415938615799
2023-01-23 00:34:42.889458: step: 1440/530, loss: 0.050049737095832825
2023-01-23 00:34:44.009532: step: 1444/530, loss: 0.24375152587890625
2023-01-23 00:34:45.124188: step: 1448/530, loss: 0.10457730293273926
2023-01-23 00:34:46.227227: step: 1452/530, loss: 0.3700190484523773
2023-01-23 00:34:47.358615: step: 1456/530, loss: 0.2309008538722992
2023-01-23 00:34:48.504578: step: 1460/530, loss: 0.0939367339015007
2023-01-23 00:34:49.616059: step: 1464/530, loss: 0.04740658402442932
2023-01-23 00:34:50.739765: step: 1468/530, loss: 0.03651466593146324
2023-01-23 00:34:51.912567: step: 1472/530, loss: 0.5056043267250061
2023-01-23 00:34:53.036666: step: 1476/530, loss: 0.12814083695411682
2023-01-23 00:34:54.147049: step: 1480/530, loss: 0.06132626533508301
2023-01-23 00:34:55.275685: step: 1484/530, loss: 0.021965885534882545
2023-01-23 00:34:56.363870: step: 1488/530, loss: 0.14142721891403198
2023-01-23 00:34:57.461717: step: 1492/530, loss: 0.042731285095214844
2023-01-23 00:34:58.578780: step: 1496/530, loss: 0.037416670471429825
2023-01-23 00:34:59.702799: step: 1500/530, loss: 0.02287759818136692
2023-01-23 00:35:00.827469: step: 1504/530, loss: 0.2768389582633972
2023-01-23 00:35:01.942916: step: 1508/530, loss: 0.4945589303970337
2023-01-23 00:35:03.115019: step: 1512/530, loss: 0.033917855471372604
2023-01-23 00:35:04.278372: step: 1516/530, loss: 1.3697296380996704
2023-01-23 00:35:05.430068: step: 1520/530, loss: 0.043160442262887955
2023-01-23 00:35:06.549174: step: 1524/530, loss: 0.07813435047864914
2023-01-23 00:35:07.661206: step: 1528/530, loss: 0.10764770954847336
2023-01-23 00:35:08.802854: step: 1532/530, loss: 0.2389325201511383
2023-01-23 00:35:09.907628: step: 1536/530, loss: 0.3503111004829407
2023-01-23 00:35:11.008726: step: 1540/530, loss: 0.06169404834508896
2023-01-23 00:35:12.135860: step: 1544/530, loss: 0.7213138341903687
2023-01-23 00:35:13.254073: step: 1548/530, loss: 0.1807718276977539
2023-01-23 00:35:14.352074: step: 1552/530, loss: 0.10531444847583771
2023-01-23 00:35:15.481897: step: 1556/530, loss: 0.2628301680088043
2023-01-23 00:35:16.589658: step: 1560/530, loss: 0.13537092506885529
2023-01-23 00:35:17.750609: step: 1564/530, loss: 0.091173455119133
2023-01-23 00:35:18.892720: step: 1568/530, loss: 0.050329022109508514
2023-01-23 00:35:20.008570: step: 1572/530, loss: 0.20693665742874146
2023-01-23 00:35:21.123824: step: 1576/530, loss: 0.0497838519513607
2023-01-23 00:35:22.241483: step: 1580/530, loss: 0.06012783199548721
2023-01-23 00:35:23.334971: step: 1584/530, loss: 0.2369484007358551
2023-01-23 00:35:24.448482: step: 1588/530, loss: 0.0898078978061676
2023-01-23 00:35:25.577747: step: 1592/530, loss: 0.0971534252166748
2023-01-23 00:35:26.698502: step: 1596/530, loss: 0.32569846510887146
2023-01-23 00:35:27.816427: step: 1600/530, loss: 0.1363188773393631
2023-01-23 00:35:28.904229: step: 1604/530, loss: 0.3215019106864929
2023-01-23 00:35:30.057807: step: 1608/530, loss: 0.19120875000953674
2023-01-23 00:35:31.190924: step: 1612/530, loss: 0.07800846546888351
2023-01-23 00:35:32.328460: step: 1616/530, loss: 0.31955671310424805
2023-01-23 00:35:33.482831: step: 1620/530, loss: 0.13016024231910706
2023-01-23 00:35:34.643793: step: 1624/530, loss: 0.140536367893219
2023-01-23 00:35:35.767359: step: 1628/530, loss: 0.01799945905804634
2023-01-23 00:35:36.888429: step: 1632/530, loss: 0.5441030263900757
2023-01-23 00:35:38.023720: step: 1636/530, loss: 0.01740856282413006
2023-01-23 00:35:39.159806: step: 1640/530, loss: 0.866162121295929
2023-01-23 00:35:40.274127: step: 1644/530, loss: 0.5128917098045349
2023-01-23 00:35:41.418816: step: 1648/530, loss: 0.08527746051549911
2023-01-23 00:35:42.584807: step: 1652/530, loss: 0.038887977600097656
2023-01-23 00:35:43.688503: step: 1656/530, loss: 0.300466924905777
2023-01-23 00:35:44.839737: step: 1660/530, loss: 0.08356447517871857
2023-01-23 00:35:45.974137: step: 1664/530, loss: 0.047193050384521484
2023-01-23 00:35:47.085338: step: 1668/530, loss: 0.04196572303771973
2023-01-23 00:35:48.231104: step: 1672/530, loss: 0.22638550400733948
2023-01-23 00:35:49.377415: step: 1676/530, loss: 0.060697294771671295
2023-01-23 00:35:50.515709: step: 1680/530, loss: 0.029040971770882607
2023-01-23 00:35:51.643103: step: 1684/530, loss: 0.32494333386421204
2023-01-23 00:35:52.747731: step: 1688/530, loss: 0.2050762176513672
2023-01-23 00:35:53.844287: step: 1692/530, loss: 0.15073424577713013
2023-01-23 00:35:54.949346: step: 1696/530, loss: 0.021234560757875443
2023-01-23 00:35:56.070059: step: 1700/530, loss: 0.22772693634033203
2023-01-23 00:35:57.174892: step: 1704/530, loss: 0.2048051953315735
2023-01-23 00:35:58.283470: step: 1708/530, loss: 1.229255199432373
2023-01-23 00:35:59.388343: step: 1712/530, loss: 0.07519569247961044
2023-01-23 00:36:00.488662: step: 1716/530, loss: 0.3553768992424011
2023-01-23 00:36:01.606233: step: 1720/530, loss: 0.31177273392677307
2023-01-23 00:36:02.726833: step: 1724/530, loss: 0.07540798932313919
2023-01-23 00:36:03.852439: step: 1728/530, loss: 0.4778037965297699
2023-01-23 00:36:05.006446: step: 1732/530, loss: 0.10925769805908203
2023-01-23 00:36:06.114820: step: 1736/530, loss: 0.1518394500017166
2023-01-23 00:36:07.250771: step: 1740/530, loss: 0.09637327492237091
2023-01-23 00:36:08.395864: step: 1744/530, loss: 0.2500007748603821
2023-01-23 00:36:09.540827: step: 1748/530, loss: 0.04216470569372177
2023-01-23 00:36:10.675718: step: 1752/530, loss: 0.3958495855331421
2023-01-23 00:36:11.809062: step: 1756/530, loss: 0.34370705485343933
2023-01-23 00:36:12.940579: step: 1760/530, loss: 0.16984349489212036
2023-01-23 00:36:14.068518: step: 1764/530, loss: 0.2212836742401123
2023-01-23 00:36:15.186775: step: 1768/530, loss: 0.1221095621585846
2023-01-23 00:36:16.286036: step: 1772/530, loss: 0.16367921233177185
2023-01-23 00:36:17.394109: step: 1776/530, loss: 0.09126263111829758
2023-01-23 00:36:18.525873: step: 1780/530, loss: 0.18614892661571503
2023-01-23 00:36:19.663358: step: 1784/530, loss: 0.14096757769584656
2023-01-23 00:36:20.796106: step: 1788/530, loss: 0.22768375277519226
2023-01-23 00:36:21.943675: step: 1792/530, loss: 0.4420034885406494
2023-01-23 00:36:23.064631: step: 1796/530, loss: 0.6020099520683289
2023-01-23 00:36:24.185001: step: 1800/530, loss: 0.013664103113114834
2023-01-23 00:36:25.282178: step: 1804/530, loss: 0.03677663952112198
2023-01-23 00:36:26.427005: step: 1808/530, loss: 0.1266801357269287
2023-01-23 00:36:27.560099: step: 1812/530, loss: 0.23877553641796112
2023-01-23 00:36:28.690383: step: 1816/530, loss: 0.06793355941772461
2023-01-23 00:36:29.825995: step: 1820/530, loss: 0.18614837527275085
2023-01-23 00:36:30.962336: step: 1824/530, loss: 0.052790261805057526
2023-01-23 00:36:32.096494: step: 1828/530, loss: 0.2922162115573883
2023-01-23 00:36:33.221443: step: 1832/530, loss: 0.07311079651117325
2023-01-23 00:36:34.326879: step: 1836/530, loss: 0.3650810420513153
2023-01-23 00:36:35.450882: step: 1840/530, loss: 0.01961350440979004
2023-01-23 00:36:36.547118: step: 1844/530, loss: 0.08485154807567596
2023-01-23 00:36:37.679023: step: 1848/530, loss: 0.4292561709880829
2023-01-23 00:36:38.849095: step: 1852/530, loss: 0.18198230862617493
2023-01-23 00:36:39.974410: step: 1856/530, loss: 0.08973255008459091
2023-01-23 00:36:41.128586: step: 1860/530, loss: 0.12911725044250488
2023-01-23 00:36:42.264175: step: 1864/530, loss: 0.0540163516998291
2023-01-23 00:36:43.421564: step: 1868/530, loss: 0.20200799405574799
2023-01-23 00:36:44.569723: step: 1872/530, loss: 0.09971609711647034
2023-01-23 00:36:45.683088: step: 1876/530, loss: 0.03512759506702423
2023-01-23 00:36:46.805889: step: 1880/530, loss: 0.09538641571998596
2023-01-23 00:36:47.925614: step: 1884/530, loss: 0.12151136249303818
2023-01-23 00:36:49.056756: step: 1888/530, loss: 0.20381908118724823
2023-01-23 00:36:50.194474: step: 1892/530, loss: 0.46223753690719604
2023-01-23 00:36:51.313382: step: 1896/530, loss: 0.027243424206972122
2023-01-23 00:36:52.451732: step: 1900/530, loss: 0.10899010300636292
2023-01-23 00:36:53.536138: step: 1904/530, loss: 0.153279110789299
2023-01-23 00:36:54.654792: step: 1908/530, loss: 0.6745237112045288
2023-01-23 00:36:55.780570: step: 1912/530, loss: 0.500869870185852
2023-01-23 00:36:56.927574: step: 1916/530, loss: 0.5899769067764282
2023-01-23 00:36:58.084500: step: 1920/530, loss: 0.07409355789422989
2023-01-23 00:36:59.200054: step: 1924/530, loss: 0.15016856789588928
2023-01-23 00:37:00.350462: step: 1928/530, loss: 0.21908608078956604
2023-01-23 00:37:01.461991: step: 1932/530, loss: 0.07517699897289276
2023-01-23 00:37:02.591159: step: 1936/530, loss: 0.09788842499256134
2023-01-23 00:37:03.694692: step: 1940/530, loss: 0.09046149253845215
2023-01-23 00:37:04.837751: step: 1944/530, loss: 0.17099237442016602
2023-01-23 00:37:05.967966: step: 1948/530, loss: 0.11549048870801926
2023-01-23 00:37:07.110783: step: 1952/530, loss: 0.17608605325222015
2023-01-23 00:37:08.235800: step: 1956/530, loss: 0.10070304572582245
2023-01-23 00:37:09.358702: step: 1960/530, loss: 0.13738679885864258
2023-01-23 00:37:10.485960: step: 1964/530, loss: 0.22463731467723846
2023-01-23 00:37:11.690920: step: 1968/530, loss: 0.6038355827331543
2023-01-23 00:37:12.790112: step: 1972/530, loss: 0.6044832468032837
2023-01-23 00:37:13.914793: step: 1976/530, loss: 0.12859220802783966
2023-01-23 00:37:15.022448: step: 1980/530, loss: 0.08989968150854111
2023-01-23 00:37:16.133302: step: 1984/530, loss: 0.12805600464344025
2023-01-23 00:37:17.243830: step: 1988/530, loss: 0.0669550895690918
2023-01-23 00:37:18.358709: step: 1992/530, loss: 0.04595589637756348
2023-01-23 00:37:19.472614: step: 1996/530, loss: 0.07101660221815109
2023-01-23 00:37:20.587825: step: 2000/530, loss: 0.16647876799106598
2023-01-23 00:37:21.696785: step: 2004/530, loss: 0.09565702080726624
2023-01-23 00:37:22.805880: step: 2008/530, loss: 0.1197698637843132
2023-01-23 00:37:23.947242: step: 2012/530, loss: 0.21390505135059357
2023-01-23 00:37:25.057507: step: 2016/530, loss: 0.17323322594165802
2023-01-23 00:37:26.161548: step: 2020/530, loss: 0.04296598583459854
2023-01-23 00:37:27.317667: step: 2024/530, loss: 0.06947288662195206
2023-01-23 00:37:28.467665: step: 2028/530, loss: 0.15835817158222198
2023-01-23 00:37:29.636948: step: 2032/530, loss: 0.0697358176112175
2023-01-23 00:37:30.764623: step: 2036/530, loss: 0.13951721787452698
2023-01-23 00:37:31.891760: step: 2040/530, loss: 0.12837333977222443
2023-01-23 00:37:33.024101: step: 2044/530, loss: 0.20212160050868988
2023-01-23 00:37:34.170043: step: 2048/530, loss: 0.14614444971084595
2023-01-23 00:37:35.290237: step: 2052/530, loss: 0.007374191656708717
2023-01-23 00:37:36.410607: step: 2056/530, loss: 0.08166094124317169
2023-01-23 00:37:37.540470: step: 2060/530, loss: 0.06730890274047852
2023-01-23 00:37:38.660647: step: 2064/530, loss: 0.05676688998937607
2023-01-23 00:37:39.798201: step: 2068/530, loss: 0.23960915207862854
2023-01-23 00:37:40.922648: step: 2072/530, loss: 0.8756664395332336
2023-01-23 00:37:42.061924: step: 2076/530, loss: 0.6012828946113586
2023-01-23 00:37:43.174170: step: 2080/530, loss: 0.1297682374715805
2023-01-23 00:37:44.285031: step: 2084/530, loss: 0.47456806898117065
2023-01-23 00:37:45.399465: step: 2088/530, loss: 0.05200080946087837
2023-01-23 00:37:46.516115: step: 2092/530, loss: 0.4557887613773346
2023-01-23 00:37:47.632277: step: 2096/530, loss: 0.011409521102905273
2023-01-23 00:37:48.758370: step: 2100/530, loss: 0.02104482613503933
2023-01-23 00:37:49.908024: step: 2104/530, loss: 0.18514509499073029
2023-01-23 00:37:51.003628: step: 2108/530, loss: 0.8774241209030151
2023-01-23 00:37:52.121869: step: 2112/530, loss: 0.4231996536254883
2023-01-23 00:37:53.267211: step: 2116/530, loss: 0.2420537918806076
2023-01-23 00:37:54.377271: step: 2120/530, loss: 0.7077285051345825
==================================================
Loss: 0.195
--------------------
Dev: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Test: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Chinese: {'event': {'p': 0.6190476190476191, 'r': 0.9629629629629629, 'f1': 0.7536231884057971}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Korean: {'event': {'p': 0.609375, 'r': 0.6190476190476191, 'f1': 0.6141732283464567}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Russian: {'event': {'p': 0.5319148936170213, 'r': 0.6944444444444444, 'f1': 0.6024096385542169}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
New best chinese model...
New best korean model...
New best russian model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Chinese: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Chinese: {'event': {'p': 0.6190476190476191, 'r': 0.9629629629629629, 'f1': 0.7536231884057971}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Korean: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Korean: {'event': {'p': 0.609375, 'r': 0.6190476190476191, 'f1': 0.6141732283464567}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5319148936170213, 'r': 0.6944444444444444, 'f1': 0.6024096385542169}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
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 00:38:52.958613: step: 4/530, loss: 1.2680834531784058
2023-01-23 00:38:54.090725: step: 8/530, loss: 0.11628742516040802
2023-01-23 00:38:55.231087: step: 12/530, loss: 0.10035018622875214
2023-01-23 00:38:56.325012: step: 16/530, loss: 0.07771806418895721
2023-01-23 00:38:57.432656: step: 20/530, loss: 0.0396575927734375
2023-01-23 00:38:58.559056: step: 24/530, loss: 0.07201176136732101
2023-01-23 00:38:59.679373: step: 28/530, loss: 0.345685750246048
2023-01-23 00:39:00.804815: step: 32/530, loss: 0.18685273826122284
2023-01-23 00:39:01.923878: step: 36/530, loss: 0.11074590682983398
2023-01-23 00:39:03.026853: step: 40/530, loss: 0.036945439875125885
2023-01-23 00:39:04.128829: step: 44/530, loss: 0.019988251850008965
2023-01-23 00:39:05.249993: step: 48/530, loss: 0.10782280564308167
2023-01-23 00:39:06.372540: step: 52/530, loss: 0.043553560972213745
2023-01-23 00:39:07.491132: step: 56/530, loss: 0.03478240966796875
2023-01-23 00:39:08.638818: step: 60/530, loss: 0.3675309121608734
2023-01-23 00:39:09.766702: step: 64/530, loss: 0.12756377458572388
2023-01-23 00:39:10.857934: step: 68/530, loss: 0.04408903047442436
2023-01-23 00:39:12.005564: step: 72/530, loss: 0.06789093464612961
2023-01-23 00:39:13.135901: step: 76/530, loss: 0.2024621069431305
2023-01-23 00:39:14.255878: step: 80/530, loss: 0.07582321763038635
2023-01-23 00:39:15.375034: step: 84/530, loss: 0.08279547095298767
2023-01-23 00:39:16.508188: step: 88/530, loss: 0.11244364082813263
2023-01-23 00:39:17.643350: step: 92/530, loss: 0.6770861744880676
2023-01-23 00:39:18.756609: step: 96/530, loss: 0.17271490395069122
2023-01-23 00:39:19.900834: step: 100/530, loss: 0.2672789692878723
2023-01-23 00:39:21.016955: step: 104/530, loss: 0.03359966352581978
2023-01-23 00:39:22.170748: step: 108/530, loss: 0.15161657333374023
2023-01-23 00:39:23.285431: step: 112/530, loss: 0.04416675865650177
2023-01-23 00:39:24.429770: step: 116/530, loss: 0.05272217094898224
2023-01-23 00:39:25.559674: step: 120/530, loss: 0.07752113789319992
2023-01-23 00:39:26.693569: step: 124/530, loss: 0.04306497797369957
2023-01-23 00:39:27.812811: step: 128/530, loss: 0.08245506137609482
2023-01-23 00:39:28.917312: step: 132/530, loss: 0.693924069404602
2023-01-23 00:39:30.043411: step: 136/530, loss: 0.07675180584192276
2023-01-23 00:39:31.163578: step: 140/530, loss: 0.1386013627052307
2023-01-23 00:39:32.319670: step: 144/530, loss: 0.10035989433526993
2023-01-23 00:39:33.429351: step: 148/530, loss: 0.024668170139193535
2023-01-23 00:39:34.567066: step: 152/530, loss: 0.06383457034826279
2023-01-23 00:39:35.732009: step: 156/530, loss: 0.11973152309656143
2023-01-23 00:39:36.823790: step: 160/530, loss: 0.042676351964473724
2023-01-23 00:39:37.987567: step: 164/530, loss: 0.15362448990345
2023-01-23 00:39:39.090884: step: 168/530, loss: 0.14505767822265625
2023-01-23 00:39:40.213914: step: 172/530, loss: 0.13315200805664062
2023-01-23 00:39:41.333730: step: 176/530, loss: 0.2832792103290558
2023-01-23 00:39:42.444180: step: 180/530, loss: 0.17722105979919434
2023-01-23 00:39:43.577149: step: 184/530, loss: 0.15194718539714813
2023-01-23 00:39:44.723459: step: 188/530, loss: 0.150286003947258
2023-01-23 00:39:45.844055: step: 192/530, loss: 0.09859780967235565
2023-01-23 00:39:46.973352: step: 196/530, loss: 0.11405744403600693
2023-01-23 00:39:48.111554: step: 200/530, loss: 0.009566117078065872
2023-01-23 00:39:49.241510: step: 204/530, loss: 0.27399322390556335
2023-01-23 00:39:50.346619: step: 208/530, loss: 0.0459321029484272
2023-01-23 00:39:51.458518: step: 212/530, loss: 0.031373072415590286
2023-01-23 00:39:52.580703: step: 216/530, loss: 0.08388862758874893
2023-01-23 00:39:53.694973: step: 220/530, loss: 0.17334657907485962
2023-01-23 00:39:54.829760: step: 224/530, loss: 0.01612100750207901
2023-01-23 00:39:55.952310: step: 228/530, loss: 0.05114307254552841
2023-01-23 00:39:57.051802: step: 232/530, loss: 0.023565197363495827
2023-01-23 00:39:58.177119: step: 236/530, loss: 0.06466398388147354
2023-01-23 00:39:59.291764: step: 240/530, loss: 0.127864271402359
2023-01-23 00:40:00.405005: step: 244/530, loss: 0.015131901949644089
2023-01-23 00:40:01.522656: step: 248/530, loss: 0.2220287322998047
2023-01-23 00:40:02.678664: step: 252/530, loss: 0.06713638454675674
2023-01-23 00:40:03.798856: step: 256/530, loss: 0.05299339070916176
2023-01-23 00:40:04.918803: step: 260/530, loss: 0.21844425797462463
2023-01-23 00:40:06.024237: step: 264/530, loss: 0.027155732735991478
2023-01-23 00:40:07.156122: step: 268/530, loss: 0.1889164000749588
2023-01-23 00:40:08.275102: step: 272/530, loss: 0.08978307247161865
2023-01-23 00:40:09.381630: step: 276/530, loss: 0.2027631253004074
2023-01-23 00:40:10.503481: step: 280/530, loss: 0.3179045617580414
2023-01-23 00:40:11.637955: step: 284/530, loss: 0.17387732863426208
2023-01-23 00:40:12.742492: step: 288/530, loss: 0.11703416705131531
2023-01-23 00:40:13.911582: step: 292/530, loss: 0.05413389205932617
2023-01-23 00:40:15.051685: step: 296/530, loss: 0.16706986725330353
2023-01-23 00:40:16.217768: step: 300/530, loss: 0.20405225455760956
2023-01-23 00:40:17.329954: step: 304/530, loss: 0.12181229889392853
2023-01-23 00:40:18.459085: step: 308/530, loss: 0.04867248609662056
2023-01-23 00:40:19.607211: step: 312/530, loss: 0.024172592908143997
2023-01-23 00:40:20.725035: step: 316/530, loss: 0.05715160816907883
2023-01-23 00:40:21.857584: step: 320/530, loss: 0.299630343914032
2023-01-23 00:40:23.016850: step: 324/530, loss: 0.23877058923244476
2023-01-23 00:40:24.137896: step: 328/530, loss: 0.05015774071216583
2023-01-23 00:40:25.263466: step: 332/530, loss: 0.10128937661647797
2023-01-23 00:40:26.404638: step: 336/530, loss: 0.3304719924926758
2023-01-23 00:40:27.559033: step: 340/530, loss: 0.2882063090801239
2023-01-23 00:40:28.709343: step: 344/530, loss: 0.007085896097123623
2023-01-23 00:40:29.828564: step: 348/530, loss: 0.11631961166858673
2023-01-23 00:40:31.006627: step: 352/530, loss: 0.2977229952812195
2023-01-23 00:40:32.158859: step: 356/530, loss: 0.3813876211643219
2023-01-23 00:40:33.296736: step: 360/530, loss: 0.4327712059020996
2023-01-23 00:40:34.427782: step: 364/530, loss: 0.036438848823308945
2023-01-23 00:40:35.563754: step: 368/530, loss: 0.07077427208423615
2023-01-23 00:40:36.691625: step: 372/530, loss: 0.12200746685266495
2023-01-23 00:40:37.831551: step: 376/530, loss: 0.02948732301592827
2023-01-23 00:40:38.956296: step: 380/530, loss: 0.1491079330444336
2023-01-23 00:40:40.078297: step: 384/530, loss: 0.02601945400238037
2023-01-23 00:40:41.214450: step: 388/530, loss: 0.37616854906082153
2023-01-23 00:40:42.334531: step: 392/530, loss: 0.06340713798999786
2023-01-23 00:40:43.444698: step: 396/530, loss: 1.1876200437545776
2023-01-23 00:40:44.546838: step: 400/530, loss: 0.08074913173913956
2023-01-23 00:40:45.668459: step: 404/530, loss: 0.08615941554307938
2023-01-23 00:40:46.790705: step: 408/530, loss: 0.027387047186493874
2023-01-23 00:40:47.945248: step: 412/530, loss: 0.061334848403930664
2023-01-23 00:40:49.061378: step: 416/530, loss: 0.1527661383152008
2023-01-23 00:40:50.206962: step: 420/530, loss: 0.041491247713565826
2023-01-23 00:40:51.321667: step: 424/530, loss: 0.04295506700873375
2023-01-23 00:40:52.447867: step: 428/530, loss: 0.19950208067893982
2023-01-23 00:40:53.559076: step: 432/530, loss: 0.030297422781586647
2023-01-23 00:40:54.714995: step: 436/530, loss: 0.09364042431116104
2023-01-23 00:40:55.879029: step: 440/530, loss: 0.030904626473784447
2023-01-23 00:40:57.040751: step: 444/530, loss: 0.23721298575401306
2023-01-23 00:40:58.158573: step: 448/530, loss: 0.04982786253094673
2023-01-23 00:40:59.274874: step: 452/530, loss: 0.2451189011335373
2023-01-23 00:41:00.388038: step: 456/530, loss: 0.16009148955345154
2023-01-23 00:41:01.509821: step: 460/530, loss: 1.979337453842163
2023-01-23 00:41:02.643242: step: 464/530, loss: 0.13183872401714325
2023-01-23 00:41:03.777807: step: 468/530, loss: 0.1537894308567047
2023-01-23 00:41:04.910116: step: 472/530, loss: 0.013261795043945312
2023-01-23 00:41:06.030067: step: 476/530, loss: 0.007299757096916437
2023-01-23 00:41:07.184525: step: 480/530, loss: 0.07049300521612167
2023-01-23 00:41:08.304645: step: 484/530, loss: 0.03040905110538006
2023-01-23 00:41:09.441612: step: 488/530, loss: 0.22414608299732208
2023-01-23 00:41:10.555771: step: 492/530, loss: 0.13880681991577148
2023-01-23 00:41:11.685410: step: 496/530, loss: 0.08127718418836594
2023-01-23 00:41:12.790025: step: 500/530, loss: 0.0580902099609375
2023-01-23 00:41:13.914736: step: 504/530, loss: 0.35004082322120667
2023-01-23 00:41:15.059121: step: 508/530, loss: 0.024770833551883698
2023-01-23 00:41:16.211018: step: 512/530, loss: 0.16093240678310394
2023-01-23 00:41:17.338922: step: 516/530, loss: 0.15723609924316406
2023-01-23 00:41:18.464311: step: 520/530, loss: 0.04057464376091957
2023-01-23 00:41:19.575505: step: 524/530, loss: 0.09470286965370178
2023-01-23 00:41:20.729293: step: 528/530, loss: 0.16625729203224182
2023-01-23 00:41:21.886329: step: 532/530, loss: 0.3267606794834137
2023-01-23 00:41:23.008278: step: 536/530, loss: 0.1564989537000656
2023-01-23 00:41:24.161791: step: 540/530, loss: 0.1945013552904129
2023-01-23 00:41:25.326182: step: 544/530, loss: 0.0932827964425087
2023-01-23 00:41:26.461641: step: 548/530, loss: 0.25178176164627075
2023-01-23 00:41:27.562215: step: 552/530, loss: 0.06794595718383789
2023-01-23 00:41:28.702232: step: 556/530, loss: 0.025017166510224342
2023-01-23 00:41:29.859265: step: 560/530, loss: 0.17379188537597656
2023-01-23 00:41:30.963429: step: 564/530, loss: 0.22268112003803253
2023-01-23 00:41:32.113957: step: 568/530, loss: 0.124933622777462
2023-01-23 00:41:33.205946: step: 572/530, loss: 0.1330583542585373
2023-01-23 00:41:34.336488: step: 576/530, loss: 0.3112865388393402
2023-01-23 00:41:35.437341: step: 580/530, loss: 0.044574640691280365
2023-01-23 00:41:36.569834: step: 584/530, loss: 0.08824305236339569
2023-01-23 00:41:37.712711: step: 588/530, loss: 0.05356311798095703
2023-01-23 00:41:38.835372: step: 592/530, loss: 0.19820280373096466
2023-01-23 00:41:39.978863: step: 596/530, loss: 0.26677417755126953
2023-01-23 00:41:41.137016: step: 600/530, loss: 0.09618616104125977
2023-01-23 00:41:42.281931: step: 604/530, loss: 0.03541979566216469
2023-01-23 00:41:43.389100: step: 608/530, loss: 0.011844397522509098
2023-01-23 00:41:44.506184: step: 612/530, loss: 0.12447986751794815
2023-01-23 00:41:45.616364: step: 616/530, loss: 0.02741217613220215
2023-01-23 00:41:46.734620: step: 620/530, loss: 0.0318482406437397
2023-01-23 00:41:47.846482: step: 624/530, loss: 0.03936829790472984
2023-01-23 00:41:48.979216: step: 628/530, loss: 0.08939743041992188
2023-01-23 00:41:50.097120: step: 632/530, loss: 0.39468926191329956
2023-01-23 00:41:51.224349: step: 636/530, loss: 0.08065292984247208
2023-01-23 00:41:52.376903: step: 640/530, loss: 0.019866371527314186
2023-01-23 00:41:53.495112: step: 644/530, loss: 0.02760334126651287
2023-01-23 00:41:54.605741: step: 648/530, loss: 0.1017528548836708
2023-01-23 00:41:55.712299: step: 652/530, loss: 0.054642342031002045
2023-01-23 00:41:56.827075: step: 656/530, loss: 0.1251974105834961
2023-01-23 00:41:57.944349: step: 660/530, loss: 0.13237157464027405
2023-01-23 00:41:59.081686: step: 664/530, loss: 0.023891830816864967
2023-01-23 00:42:00.234622: step: 668/530, loss: 0.031920768320560455
2023-01-23 00:42:01.367511: step: 672/530, loss: 0.5596164464950562
2023-01-23 00:42:02.468087: step: 676/530, loss: 0.1701713502407074
2023-01-23 00:42:03.577433: step: 680/530, loss: 0.322089821100235
2023-01-23 00:42:04.712041: step: 684/530, loss: 0.3374071717262268
2023-01-23 00:42:05.835937: step: 688/530, loss: 0.03748607635498047
2023-01-23 00:42:06.950604: step: 692/530, loss: 0.08294196426868439
2023-01-23 00:42:08.095543: step: 696/530, loss: 0.036841683089733124
2023-01-23 00:42:09.201071: step: 700/530, loss: 0.5671392679214478
2023-01-23 00:42:10.327952: step: 704/530, loss: 0.12063626945018768
2023-01-23 00:42:11.416037: step: 708/530, loss: 0.03777356445789337
2023-01-23 00:42:12.526765: step: 712/530, loss: 0.05540013313293457
2023-01-23 00:42:13.677903: step: 716/530, loss: 1.0611423254013062
2023-01-23 00:42:14.810274: step: 720/530, loss: 0.14903612434864044
2023-01-23 00:42:15.941107: step: 724/530, loss: 0.06801829487085342
2023-01-23 00:42:17.062144: step: 728/530, loss: 0.1702050268650055
2023-01-23 00:42:18.167266: step: 732/530, loss: 0.06455488502979279
2023-01-23 00:42:19.269641: step: 736/530, loss: 0.039522647857666016
2023-01-23 00:42:20.376717: step: 740/530, loss: 0.013491058722138405
2023-01-23 00:42:21.517635: step: 744/530, loss: 0.013341330923140049
2023-01-23 00:42:22.618776: step: 748/530, loss: 0.008408689871430397
2023-01-23 00:42:23.739207: step: 752/530, loss: 0.10313113033771515
2023-01-23 00:42:24.865637: step: 756/530, loss: 0.12600445747375488
2023-01-23 00:42:26.006489: step: 760/530, loss: 0.10465564578771591
2023-01-23 00:42:27.158413: step: 764/530, loss: 0.7691822052001953
2023-01-23 00:42:28.277275: step: 768/530, loss: 0.13884945213794708
2023-01-23 00:42:29.435079: step: 772/530, loss: 0.5772150158882141
2023-01-23 00:42:30.573455: step: 776/530, loss: 0.011269379407167435
2023-01-23 00:42:31.683563: step: 780/530, loss: 0.019548512995243073
2023-01-23 00:42:32.836979: step: 784/530, loss: 0.02127857133746147
2023-01-23 00:42:33.976452: step: 788/530, loss: 0.05510329082608223
2023-01-23 00:42:35.103977: step: 792/530, loss: 0.2115684449672699
2023-01-23 00:42:36.243374: step: 796/530, loss: 0.08806119114160538
2023-01-23 00:42:37.356602: step: 800/530, loss: 0.08503551036119461
2023-01-23 00:42:38.478142: step: 804/530, loss: 0.14497795701026917
2023-01-23 00:42:39.611886: step: 808/530, loss: 0.5076913237571716
2023-01-23 00:42:40.762585: step: 812/530, loss: 0.049543194472789764
2023-01-23 00:42:41.921037: step: 816/530, loss: 0.03858156502246857
2023-01-23 00:42:43.022221: step: 820/530, loss: 0.6613465547561646
2023-01-23 00:42:44.158028: step: 824/530, loss: 0.08955249935388565
2023-01-23 00:42:45.307211: step: 828/530, loss: 0.07663831859827042
2023-01-23 00:42:46.437100: step: 832/530, loss: 0.876922607421875
2023-01-23 00:42:47.550876: step: 836/530, loss: 0.4619845449924469
2023-01-23 00:42:48.678289: step: 840/530, loss: 1.1741057634353638
2023-01-23 00:42:49.783297: step: 844/530, loss: 0.20487356185913086
2023-01-23 00:42:50.902044: step: 848/530, loss: 0.04862041771411896
2023-01-23 00:42:52.026351: step: 852/530, loss: 0.0805690735578537
2023-01-23 00:42:53.167473: step: 856/530, loss: 0.13526864349842072
2023-01-23 00:42:54.313361: step: 860/530, loss: 0.2602815628051758
2023-01-23 00:42:55.431399: step: 864/530, loss: 0.15856361389160156
2023-01-23 00:42:56.560919: step: 868/530, loss: 0.060231827199459076
2023-01-23 00:42:57.691838: step: 872/530, loss: 0.1310029923915863
2023-01-23 00:42:58.795890: step: 876/530, loss: 0.2046949416399002
2023-01-23 00:42:59.922139: step: 880/530, loss: 0.007313728332519531
2023-01-23 00:43:01.069207: step: 884/530, loss: 0.13419418036937714
2023-01-23 00:43:02.199788: step: 888/530, loss: 0.0949595496058464
2023-01-23 00:43:03.304863: step: 892/530, loss: 0.33237114548683167
2023-01-23 00:43:04.448979: step: 896/530, loss: 0.022608280181884766
2023-01-23 00:43:05.578621: step: 900/530, loss: 1.4238147735595703
2023-01-23 00:43:06.743107: step: 904/530, loss: 0.061098575592041016
2023-01-23 00:43:07.876334: step: 908/530, loss: 0.11682215332984924
2023-01-23 00:43:08.983079: step: 912/530, loss: 0.5803439021110535
2023-01-23 00:43:10.104187: step: 916/530, loss: 0.0573551207780838
2023-01-23 00:43:11.217715: step: 920/530, loss: 0.05730133131146431
2023-01-23 00:43:12.348546: step: 924/530, loss: 0.2132701873779297
2023-01-23 00:43:13.500040: step: 928/530, loss: 0.06581659615039825
2023-01-23 00:43:14.613154: step: 932/530, loss: 0.025093458592891693
2023-01-23 00:43:15.737570: step: 936/530, loss: 0.021825648844242096
2023-01-23 00:43:16.859838: step: 940/530, loss: 0.11853313446044922
2023-01-23 00:43:17.988997: step: 944/530, loss: 0.16185303032398224
2023-01-23 00:43:19.106115: step: 948/530, loss: 0.09925565868616104
2023-01-23 00:43:20.208528: step: 952/530, loss: 0.08460798114538193
2023-01-23 00:43:21.338956: step: 956/530, loss: 0.24478113651275635
2023-01-23 00:43:22.441127: step: 960/530, loss: 0.0432397834956646
2023-01-23 00:43:23.552320: step: 964/530, loss: 0.05497493967413902
2023-01-23 00:43:24.689005: step: 968/530, loss: 0.23973789811134338
2023-01-23 00:43:25.805711: step: 972/530, loss: 0.01343536376953125
2023-01-23 00:43:26.933010: step: 976/530, loss: 0.435263454914093
2023-01-23 00:43:28.071348: step: 980/530, loss: 0.19541878998279572
2023-01-23 00:43:29.216653: step: 984/530, loss: 0.2850082516670227
2023-01-23 00:43:30.329915: step: 988/530, loss: 0.1438342034816742
2023-01-23 00:43:31.448102: step: 992/530, loss: 0.28700196743011475
2023-01-23 00:43:32.574831: step: 996/530, loss: 0.005561149213463068
2023-01-23 00:43:33.695470: step: 1000/530, loss: 0.396655410528183
2023-01-23 00:43:34.826462: step: 1004/530, loss: 0.04499969631433487
2023-01-23 00:43:35.996288: step: 1008/530, loss: 0.09269142150878906
2023-01-23 00:43:37.155228: step: 1012/530, loss: 0.16717949509620667
2023-01-23 00:43:38.295888: step: 1016/530, loss: 0.08923578262329102
2023-01-23 00:43:39.435302: step: 1020/530, loss: 0.12078352272510529
2023-01-23 00:43:40.548837: step: 1024/530, loss: 0.16229376196861267
2023-01-23 00:43:41.683771: step: 1028/530, loss: 0.0274245273321867
2023-01-23 00:43:42.825765: step: 1032/530, loss: 0.024878215044736862
2023-01-23 00:43:43.971725: step: 1036/530, loss: 0.07197790592908859
2023-01-23 00:43:45.091625: step: 1040/530, loss: 0.0647188201546669
2023-01-23 00:43:46.225758: step: 1044/530, loss: 0.1187833845615387
2023-01-23 00:43:47.366896: step: 1048/530, loss: 0.14217329025268555
2023-01-23 00:43:48.488191: step: 1052/530, loss: 0.07880067825317383
2023-01-23 00:43:49.635637: step: 1056/530, loss: 0.1424035131931305
2023-01-23 00:43:50.747394: step: 1060/530, loss: 0.02519674226641655
2023-01-23 00:43:51.865490: step: 1064/530, loss: 0.041162874549627304
2023-01-23 00:43:52.977593: step: 1068/530, loss: 0.050572872161865234
2023-01-23 00:43:54.118929: step: 1072/530, loss: 0.16051027178764343
2023-01-23 00:43:55.239486: step: 1076/530, loss: 0.11720800399780273
2023-01-23 00:43:56.347201: step: 1080/530, loss: 0.06875353306531906
2023-01-23 00:43:57.493294: step: 1084/530, loss: 0.032303810119628906
2023-01-23 00:43:58.603305: step: 1088/530, loss: 0.6615206003189087
2023-01-23 00:43:59.733553: step: 1092/530, loss: 0.0618986152112484
2023-01-23 00:44:00.899156: step: 1096/530, loss: 0.08714609593153
2023-01-23 00:44:02.025082: step: 1100/530, loss: 0.10588884353637695
2023-01-23 00:44:03.176954: step: 1104/530, loss: 0.05422933027148247
2023-01-23 00:44:04.359749: step: 1108/530, loss: 0.08528108149766922
2023-01-23 00:44:05.482013: step: 1112/530, loss: 0.04613494873046875
2023-01-23 00:44:06.623265: step: 1116/530, loss: 0.06508312374353409
2023-01-23 00:44:07.716833: step: 1120/530, loss: 0.0842016190290451
2023-01-23 00:44:08.844326: step: 1124/530, loss: 0.17549681663513184
2023-01-23 00:44:09.950122: step: 1128/530, loss: 0.021941518411040306
2023-01-23 00:44:11.074983: step: 1132/530, loss: 0.732150673866272
2023-01-23 00:44:12.184384: step: 1136/530, loss: 0.017777252942323685
2023-01-23 00:44:13.340110: step: 1140/530, loss: 0.26571425795555115
2023-01-23 00:44:14.457595: step: 1144/530, loss: 1.4252564907073975
2023-01-23 00:44:15.543707: step: 1148/530, loss: 0.057390954345464706
2023-01-23 00:44:16.664418: step: 1152/530, loss: 0.22549590468406677
2023-01-23 00:44:17.758563: step: 1156/530, loss: 0.15741194784641266
2023-01-23 00:44:18.918942: step: 1160/530, loss: 0.39007800817489624
2023-01-23 00:44:20.038966: step: 1164/530, loss: 0.07414837181568146
2023-01-23 00:44:21.163886: step: 1168/530, loss: 0.26224347949028015
2023-01-23 00:44:22.294000: step: 1172/530, loss: 0.1373356729745865
2023-01-23 00:44:23.431891: step: 1176/530, loss: 0.05471067875623703
2023-01-23 00:44:24.564158: step: 1180/530, loss: 0.11634416878223419
2023-01-23 00:44:25.711562: step: 1184/530, loss: 0.22966629266738892
2023-01-23 00:44:26.825676: step: 1188/530, loss: 0.0383848175406456
2023-01-23 00:44:27.916625: step: 1192/530, loss: 0.03922059386968613
2023-01-23 00:44:29.045434: step: 1196/530, loss: 0.04711313545703888
2023-01-23 00:44:30.160772: step: 1200/530, loss: 0.12867765128612518
2023-01-23 00:44:31.302879: step: 1204/530, loss: 0.20471186935901642
2023-01-23 00:44:32.441096: step: 1208/530, loss: 0.19581404328346252
2023-01-23 00:44:33.552902: step: 1212/530, loss: 0.07948637008666992
2023-01-23 00:44:34.670447: step: 1216/530, loss: 0.05376477539539337
2023-01-23 00:44:35.813215: step: 1220/530, loss: 0.036206819117069244
2023-01-23 00:44:36.916120: step: 1224/530, loss: 0.19651050865650177
2023-01-23 00:44:38.031825: step: 1228/530, loss: 0.033911801874637604
2023-01-23 00:44:39.145932: step: 1232/530, loss: 0.15604406595230103
2023-01-23 00:44:40.261898: step: 1236/530, loss: 0.0981866866350174
2023-01-23 00:44:41.385073: step: 1240/530, loss: 0.035298824310302734
2023-01-23 00:44:42.539903: step: 1244/530, loss: 0.13226062059402466
2023-01-23 00:44:43.676727: step: 1248/530, loss: 0.1768416464328766
2023-01-23 00:44:44.773609: step: 1252/530, loss: 0.16594401001930237
2023-01-23 00:44:45.893745: step: 1256/530, loss: 0.07306098937988281
2023-01-23 00:44:47.030271: step: 1260/530, loss: 0.09872972965240479
2023-01-23 00:44:48.156827: step: 1264/530, loss: 0.016474151983857155
2023-01-23 00:44:49.280033: step: 1268/530, loss: 0.10059785842895508
2023-01-23 00:44:50.386854: step: 1272/530, loss: 0.07504215091466904
2023-01-23 00:44:51.501779: step: 1276/530, loss: 0.02240929752588272
2023-01-23 00:44:52.642317: step: 1280/530, loss: 0.24671754240989685
2023-01-23 00:44:53.782294: step: 1284/530, loss: 0.06925249099731445
2023-01-23 00:44:54.879109: step: 1288/530, loss: 0.05390463024377823
2023-01-23 00:44:55.977809: step: 1292/530, loss: 0.25257396697998047
2023-01-23 00:44:57.107975: step: 1296/530, loss: 0.2731453776359558
2023-01-23 00:44:58.239426: step: 1300/530, loss: 0.04899749904870987
2023-01-23 00:44:59.357437: step: 1304/530, loss: 0.017156029120087624
2023-01-23 00:45:00.480030: step: 1308/530, loss: 0.05664246156811714
2023-01-23 00:45:01.599906: step: 1312/530, loss: 0.205424502491951
2023-01-23 00:45:02.726762: step: 1316/530, loss: 0.04082925245165825
2023-01-23 00:45:03.826464: step: 1320/530, loss: 0.2498483955860138
2023-01-23 00:45:04.957468: step: 1324/530, loss: 1.0341918468475342
2023-01-23 00:45:06.085423: step: 1328/530, loss: 0.02234964445233345
2023-01-23 00:45:07.297236: step: 1332/530, loss: 0.11992769688367844
2023-01-23 00:45:08.424697: step: 1336/530, loss: 0.12890520691871643
2023-01-23 00:45:09.538729: step: 1340/530, loss: 0.0451996810734272
2023-01-23 00:45:10.668387: step: 1344/530, loss: 0.12387257069349289
2023-01-23 00:45:11.801420: step: 1348/530, loss: 0.026116086170077324
2023-01-23 00:45:12.926382: step: 1352/530, loss: 0.233127623796463
2023-01-23 00:45:14.054437: step: 1356/530, loss: 0.12263259291648865
2023-01-23 00:45:15.156743: step: 1360/530, loss: 0.057888224720954895
2023-01-23 00:45:16.310531: step: 1364/530, loss: 0.12071923911571503
2023-01-23 00:45:17.445323: step: 1368/530, loss: 0.14103765785694122
2023-01-23 00:45:18.562905: step: 1372/530, loss: 0.19510279595851898
2023-01-23 00:45:19.670597: step: 1376/530, loss: 0.3639591932296753
2023-01-23 00:45:20.792602: step: 1380/530, loss: 0.08072170615196228
2023-01-23 00:45:21.903045: step: 1384/530, loss: 0.08210192620754242
2023-01-23 00:45:23.023056: step: 1388/530, loss: 0.03093853034079075
2023-01-23 00:45:24.159291: step: 1392/530, loss: 0.10535440593957901
2023-01-23 00:45:25.286568: step: 1396/530, loss: 0.01924286037683487
2023-01-23 00:45:26.390035: step: 1400/530, loss: 0.041249942034482956
2023-01-23 00:45:27.523617: step: 1404/530, loss: 0.11865682899951935
2023-01-23 00:45:28.631282: step: 1408/530, loss: 0.013319588266313076
2023-01-23 00:45:29.753205: step: 1412/530, loss: 0.022849559783935547
2023-01-23 00:45:30.869455: step: 1416/530, loss: 0.17736944556236267
2023-01-23 00:45:31.987719: step: 1420/530, loss: 0.6939536929130554
2023-01-23 00:45:33.131053: step: 1424/530, loss: 0.1634509116411209
2023-01-23 00:45:34.249924: step: 1428/530, loss: 0.09280534088611603
2023-01-23 00:45:35.388514: step: 1432/530, loss: 0.13037090003490448
2023-01-23 00:45:36.511892: step: 1436/530, loss: 0.17189759016036987
2023-01-23 00:45:37.639791: step: 1440/530, loss: 0.17920485138893127
2023-01-23 00:45:38.755726: step: 1444/530, loss: 0.08363771438598633
2023-01-23 00:45:39.852684: step: 1448/530, loss: 0.2847312092781067
2023-01-23 00:45:40.974075: step: 1452/530, loss: 0.07989463955163956
2023-01-23 00:45:42.098167: step: 1456/530, loss: 0.10486698150634766
2023-01-23 00:45:43.223017: step: 1460/530, loss: 0.12657156586647034
2023-01-23 00:45:44.381981: step: 1464/530, loss: 0.15494680404663086
2023-01-23 00:45:45.515487: step: 1468/530, loss: 0.01230688113719225
2023-01-23 00:45:46.645966: step: 1472/530, loss: 0.05029625818133354
2023-01-23 00:45:47.776004: step: 1476/530, loss: 0.032521724700927734
2023-01-23 00:45:48.906040: step: 1480/530, loss: 0.14653682708740234
2023-01-23 00:45:50.027227: step: 1484/530, loss: 0.09010009467601776
2023-01-23 00:45:51.157919: step: 1488/530, loss: 0.12466501444578171
2023-01-23 00:45:52.327548: step: 1492/530, loss: 0.05337543413043022
2023-01-23 00:45:53.454128: step: 1496/530, loss: 0.04406700283288956
2023-01-23 00:45:54.584130: step: 1500/530, loss: 0.2210375815629959
2023-01-23 00:45:55.711998: step: 1504/530, loss: 0.18387623131275177
2023-01-23 00:45:56.847797: step: 1508/530, loss: 0.12805165350437164
2023-01-23 00:45:57.979696: step: 1512/530, loss: 0.0774141326546669
2023-01-23 00:45:59.097764: step: 1516/530, loss: 0.10437707602977753
2023-01-23 00:46:00.235966: step: 1520/530, loss: 0.14396977424621582
2023-01-23 00:46:01.349203: step: 1524/530, loss: 0.05496826022863388
2023-01-23 00:46:02.476438: step: 1528/530, loss: 0.11916399002075195
2023-01-23 00:46:03.605447: step: 1532/530, loss: 0.1935289204120636
2023-01-23 00:46:04.716010: step: 1536/530, loss: 0.42479172348976135
2023-01-23 00:46:05.881592: step: 1540/530, loss: 0.36505621671676636
2023-01-23 00:46:06.989319: step: 1544/530, loss: 0.16534185409545898
2023-01-23 00:46:08.119644: step: 1548/530, loss: 0.03631606325507164
2023-01-23 00:46:09.230948: step: 1552/530, loss: 0.10368328541517258
2023-01-23 00:46:10.406790: step: 1556/530, loss: 0.68121337890625
2023-01-23 00:46:11.552331: step: 1560/530, loss: 0.13818788528442383
2023-01-23 00:46:12.670071: step: 1564/530, loss: 0.7915406823158264
2023-01-23 00:46:13.789998: step: 1568/530, loss: 0.06029238551855087
2023-01-23 00:46:14.924424: step: 1572/530, loss: 0.13905592262744904
2023-01-23 00:46:16.061642: step: 1576/530, loss: 0.10436001420021057
2023-01-23 00:46:17.164057: step: 1580/530, loss: 0.22023090720176697
2023-01-23 00:46:18.272523: step: 1584/530, loss: 0.05080080404877663
2023-01-23 00:46:19.382539: step: 1588/530, loss: 0.06474848091602325
2023-01-23 00:46:20.537781: step: 1592/530, loss: 0.14199644327163696
2023-01-23 00:46:21.660354: step: 1596/530, loss: 0.05756683275103569
2023-01-23 00:46:22.774273: step: 1600/530, loss: 0.13492439687252045
2023-01-23 00:46:23.856934: step: 1604/530, loss: 0.02302999421954155
2023-01-23 00:46:24.994066: step: 1608/530, loss: 0.16538085043430328
2023-01-23 00:46:26.111912: step: 1612/530, loss: 0.0825202465057373
2023-01-23 00:46:27.222215: step: 1616/530, loss: 0.05481024086475372
2023-01-23 00:46:28.338208: step: 1620/530, loss: 0.08377237617969513
2023-01-23 00:46:29.452043: step: 1624/530, loss: 0.009915542788803577
2023-01-23 00:46:30.596635: step: 1628/530, loss: 0.07840323448181152
2023-01-23 00:46:31.760067: step: 1632/530, loss: 0.06298070400953293
2023-01-23 00:46:32.846175: step: 1636/530, loss: 0.07393121719360352
2023-01-23 00:46:33.967609: step: 1640/530, loss: 0.13563385605812073
2023-01-23 00:46:35.100176: step: 1644/530, loss: 0.168226957321167
2023-01-23 00:46:36.254759: step: 1648/530, loss: 0.04362669214606285
2023-01-23 00:46:37.386819: step: 1652/530, loss: 0.054886434227228165
2023-01-23 00:46:38.503450: step: 1656/530, loss: 1.4837015867233276
2023-01-23 00:46:39.622784: step: 1660/530, loss: 0.06503525376319885
2023-01-23 00:46:40.767375: step: 1664/530, loss: 0.06147126853466034
2023-01-23 00:46:41.866920: step: 1668/530, loss: 0.08744516223669052
2023-01-23 00:46:43.045546: step: 1672/530, loss: 0.3688690662384033
2023-01-23 00:46:44.142612: step: 1676/530, loss: 0.024454019963741302
2023-01-23 00:46:45.275287: step: 1680/530, loss: 0.010876060463488102
2023-01-23 00:46:46.411139: step: 1684/530, loss: 0.11532311141490936
2023-01-23 00:46:47.520045: step: 1688/530, loss: 0.0986049622297287
2023-01-23 00:46:48.644884: step: 1692/530, loss: 0.07453000545501709
2023-01-23 00:46:49.762407: step: 1696/530, loss: 0.09139471501111984
2023-01-23 00:46:50.862062: step: 1700/530, loss: 0.05962200090289116
2023-01-23 00:46:51.998430: step: 1704/530, loss: 0.17260321974754333
2023-01-23 00:46:53.129741: step: 1708/530, loss: 0.06605947017669678
2023-01-23 00:46:54.241888: step: 1712/530, loss: 0.1656384915113449
2023-01-23 00:46:55.368444: step: 1716/530, loss: 0.35463786125183105
2023-01-23 00:46:56.528795: step: 1720/530, loss: 0.16194772720336914
2023-01-23 00:46:57.641047: step: 1724/530, loss: 0.06718187779188156
2023-01-23 00:46:58.762999: step: 1728/530, loss: 0.2318398505449295
2023-01-23 00:46:59.900242: step: 1732/530, loss: 0.07556295394897461
2023-01-23 00:47:01.009281: step: 1736/530, loss: 0.02566538006067276
2023-01-23 00:47:02.163561: step: 1740/530, loss: 0.09393348544836044
2023-01-23 00:47:03.283336: step: 1744/530, loss: 0.04976792261004448
2023-01-23 00:47:04.437547: step: 1748/530, loss: 0.07157669216394424
2023-01-23 00:47:05.605381: step: 1752/530, loss: 0.0800900012254715
2023-01-23 00:47:06.719043: step: 1756/530, loss: 0.019009782001376152
2023-01-23 00:47:07.833187: step: 1760/530, loss: 0.7311533689498901
2023-01-23 00:47:08.933573: step: 1764/530, loss: 0.13898307085037231
2023-01-23 00:47:10.034544: step: 1768/530, loss: 0.05152168869972229
2023-01-23 00:47:11.160693: step: 1772/530, loss: 0.055876828730106354
2023-01-23 00:47:12.293300: step: 1776/530, loss: 0.05248122289776802
2023-01-23 00:47:13.408506: step: 1780/530, loss: 0.07632989436388016
2023-01-23 00:47:14.532344: step: 1784/530, loss: 0.6406081318855286
2023-01-23 00:47:15.677992: step: 1788/530, loss: 0.6238624453544617
2023-01-23 00:47:16.785643: step: 1792/530, loss: 0.17739373445510864
2023-01-23 00:47:17.931865: step: 1796/530, loss: 0.06013917922973633
2023-01-23 00:47:19.083211: step: 1800/530, loss: 0.12412300705909729
2023-01-23 00:47:20.208827: step: 1804/530, loss: 0.07818011939525604
2023-01-23 00:47:21.303660: step: 1808/530, loss: 0.5141303539276123
2023-01-23 00:47:22.441777: step: 1812/530, loss: 0.2001221626996994
2023-01-23 00:47:23.568467: step: 1816/530, loss: 0.15150794386863708
2023-01-23 00:47:24.682264: step: 1820/530, loss: 0.13091126084327698
2023-01-23 00:47:25.807673: step: 1824/530, loss: 0.018029015511274338
2023-01-23 00:47:26.933401: step: 1828/530, loss: 0.13202953338623047
2023-01-23 00:47:28.085300: step: 1832/530, loss: 0.033278465270996094
2023-01-23 00:47:29.238488: step: 1836/530, loss: 0.02139580436050892
2023-01-23 00:47:30.350129: step: 1840/530, loss: 0.10722912102937698
2023-01-23 00:47:31.453635: step: 1844/530, loss: 0.1031157523393631
2023-01-23 00:47:32.614892: step: 1848/530, loss: 0.3295229971408844
2023-01-23 00:47:33.726020: step: 1852/530, loss: 0.06683597713708878
2023-01-23 00:47:34.861233: step: 1856/530, loss: 0.5251230001449585
2023-01-23 00:47:35.959325: step: 1860/530, loss: 0.07481712847948074
2023-01-23 00:47:37.102250: step: 1864/530, loss: 0.04296443611383438
2023-01-23 00:47:38.226835: step: 1868/530, loss: 0.10067825019359589
2023-01-23 00:47:39.342796: step: 1872/530, loss: 0.31604501605033875
2023-01-23 00:47:40.478167: step: 1876/530, loss: 0.17540818452835083
2023-01-23 00:47:41.628470: step: 1880/530, loss: 0.056783199310302734
2023-01-23 00:47:42.739004: step: 1884/530, loss: 0.06674452126026154
2023-01-23 00:47:43.888416: step: 1888/530, loss: 0.018225669860839844
2023-01-23 00:47:45.002783: step: 1892/530, loss: 0.09129539132118225
2023-01-23 00:47:46.100060: step: 1896/530, loss: 0.06556501239538193
2023-01-23 00:47:47.215987: step: 1900/530, loss: 0.08240365982055664
2023-01-23 00:47:48.328556: step: 1904/530, loss: 0.15672054886817932
2023-01-23 00:47:49.485982: step: 1908/530, loss: 0.07845965027809143
2023-01-23 00:47:50.598210: step: 1912/530, loss: 0.0674038901925087
2023-01-23 00:47:51.708611: step: 1916/530, loss: 0.17329376935958862
2023-01-23 00:47:52.885148: step: 1920/530, loss: 0.3830658793449402
2023-01-23 00:47:54.003969: step: 1924/530, loss: 0.017481040209531784
2023-01-23 00:47:55.154656: step: 1928/530, loss: 0.4208986759185791
2023-01-23 00:47:56.268542: step: 1932/530, loss: 0.08931312710046768
2023-01-23 00:47:57.410980: step: 1936/530, loss: 0.10816283524036407
2023-01-23 00:47:58.523865: step: 1940/530, loss: 0.04626784473657608
2023-01-23 00:47:59.642942: step: 1944/530, loss: 0.1099090576171875
2023-01-23 00:48:00.771342: step: 1948/530, loss: 0.02344541624188423
2023-01-23 00:48:01.922504: step: 1952/530, loss: 0.15743452310562134
2023-01-23 00:48:03.038596: step: 1956/530, loss: 0.1801835000514984
2023-01-23 00:48:04.210554: step: 1960/530, loss: 0.15383490920066833
2023-01-23 00:48:05.333530: step: 1964/530, loss: 0.2860403060913086
2023-01-23 00:48:06.462892: step: 1968/530, loss: 0.22299738228321075
2023-01-23 00:48:07.591296: step: 1972/530, loss: 0.07216902077198029
2023-01-23 00:48:08.716047: step: 1976/530, loss: 0.39765453338623047
2023-01-23 00:48:09.859313: step: 1980/530, loss: 0.03186450153589249
2023-01-23 00:48:10.986087: step: 1984/530, loss: 0.055449869483709335
2023-01-23 00:48:12.114530: step: 1988/530, loss: 0.11690497398376465
2023-01-23 00:48:13.234911: step: 1992/530, loss: 0.024784088134765625
2023-01-23 00:48:14.351762: step: 1996/530, loss: 0.005114507861435413
2023-01-23 00:48:15.462754: step: 2000/530, loss: 0.10327720642089844
2023-01-23 00:48:16.645343: step: 2004/530, loss: 0.016121864318847656
2023-01-23 00:48:17.797441: step: 2008/530, loss: 0.09388083964586258
2023-01-23 00:48:18.913251: step: 2012/530, loss: 0.3490671217441559
2023-01-23 00:48:20.044953: step: 2016/530, loss: 0.06737031787633896
2023-01-23 00:48:21.165834: step: 2020/530, loss: 0.10140247642993927
2023-01-23 00:48:22.293244: step: 2024/530, loss: 0.0574406161904335
2023-01-23 00:48:23.412321: step: 2028/530, loss: 0.25454071164131165
2023-01-23 00:48:24.564373: step: 2032/530, loss: 0.09743957221508026
2023-01-23 00:48:25.698314: step: 2036/530, loss: 0.08753442764282227
2023-01-23 00:48:26.841501: step: 2040/530, loss: 0.4302801191806793
2023-01-23 00:48:27.975523: step: 2044/530, loss: 0.0899573341012001
2023-01-23 00:48:29.143216: step: 2048/530, loss: 0.2613717019557953
2023-01-23 00:48:30.294884: step: 2052/530, loss: 0.08410835266113281
2023-01-23 00:48:31.437804: step: 2056/530, loss: 0.06310901790857315
2023-01-23 00:48:32.588367: step: 2060/530, loss: 0.06670618057250977
2023-01-23 00:48:33.742242: step: 2064/530, loss: 0.1709795892238617
2023-01-23 00:48:34.893546: step: 2068/530, loss: 0.8651343584060669
2023-01-23 00:48:36.012124: step: 2072/530, loss: 0.25615906715393066
2023-01-23 00:48:37.129757: step: 2076/530, loss: 0.1450739949941635
2023-01-23 00:48:38.243816: step: 2080/530, loss: 0.03266597166657448
2023-01-23 00:48:39.388071: step: 2084/530, loss: 0.12448253482580185
2023-01-23 00:48:40.510563: step: 2088/530, loss: 0.02251415327191353
2023-01-23 00:48:41.621263: step: 2092/530, loss: 0.09509305655956268
2023-01-23 00:48:42.756651: step: 2096/530, loss: 0.03014073520898819
2023-01-23 00:48:43.856811: step: 2100/530, loss: 0.10166730731725693
2023-01-23 00:48:45.022301: step: 2104/530, loss: 0.017941810190677643
2023-01-23 00:48:46.148727: step: 2108/530, loss: 0.01709207333624363
2023-01-23 00:48:47.270493: step: 2112/530, loss: 0.14904442429542542
2023-01-23 00:48:48.373755: step: 2116/530, loss: 0.03419847786426544
2023-01-23 00:48:49.498511: step: 2120/530, loss: 0.10788088291883469
==================================================
Loss: 0.160
--------------------
Dev: {'event': {'p': 0.5693215339233039, 'r': 0.7709720372836218, 'f1': 0.6549773755656109}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Test: {'event': {'p': 0.6194531600179292, 'r': 0.7897142857142857, 'f1': 0.6942979150967095}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
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': 7}
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': 7}
Russian: {'event': {'p': 0.5111111111111111, 'r': 0.6388888888888888, 'f1': 0.5679012345679012}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Chinese: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Chinese: {'event': {'p': 0.6190476190476191, 'r': 0.9629629629629629, 'f1': 0.7536231884057971}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Korean: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Korean: {'event': {'p': 0.609375, 'r': 0.6190476190476191, 'f1': 0.6141732283464567}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5319148936170213, 'r': 0.6944444444444444, 'f1': 0.6024096385542169}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
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 00:49:30.282788: step: 4/530, loss: 0.03088674508035183
2023-01-23 00:49:31.406875: step: 8/530, loss: 0.0714973509311676
2023-01-23 00:49:32.524599: step: 12/530, loss: 0.03342180326581001
2023-01-23 00:49:33.646624: step: 16/530, loss: 0.08557090163230896
2023-01-23 00:49:34.772516: step: 20/530, loss: 0.11828122287988663
2023-01-23 00:49:35.879378: step: 24/530, loss: 0.02834930457174778
2023-01-23 00:49:37.003764: step: 28/530, loss: 0.09843587875366211
2023-01-23 00:49:38.098076: step: 32/530, loss: 0.10048885643482208
2023-01-23 00:49:39.211244: step: 36/530, loss: 0.7323719263076782
2023-01-23 00:49:40.355208: step: 40/530, loss: 0.15236178040504456
2023-01-23 00:49:41.496634: step: 44/530, loss: 0.08092904090881348
2023-01-23 00:49:42.632564: step: 48/530, loss: 0.007445144932717085
2023-01-23 00:49:43.744363: step: 52/530, loss: 0.06854166835546494
2023-01-23 00:49:44.880650: step: 56/530, loss: 0.11754970252513885
2023-01-23 00:49:46.019484: step: 60/530, loss: 0.32558268308639526
2023-01-23 00:49:47.107388: step: 64/530, loss: 0.023315954953432083
2023-01-23 00:49:48.211935: step: 68/530, loss: 0.8472309112548828
2023-01-23 00:49:49.306550: step: 72/530, loss: 0.07725968956947327
2023-01-23 00:49:50.453188: step: 76/530, loss: 0.08451500535011292
2023-01-23 00:49:51.581753: step: 80/530, loss: 0.025615310296416283
2023-01-23 00:49:52.693892: step: 84/530, loss: 0.06845617294311523
2023-01-23 00:49:53.814515: step: 88/530, loss: 0.005445909686386585
2023-01-23 00:49:54.948581: step: 92/530, loss: 0.01611170917749405
2023-01-23 00:49:56.096059: step: 96/530, loss: 0.14182491600513458
2023-01-23 00:49:57.227217: step: 100/530, loss: 0.03151226043701172
2023-01-23 00:49:58.373402: step: 104/530, loss: 0.14596061408519745
2023-01-23 00:49:59.472368: step: 108/530, loss: 0.13791608810424805
2023-01-23 00:50:00.592284: step: 112/530, loss: 0.0609862320125103
2023-01-23 00:50:01.715620: step: 116/530, loss: 0.1532306671142578
2023-01-23 00:50:02.863931: step: 120/530, loss: 0.1373240053653717
2023-01-23 00:50:03.966221: step: 124/530, loss: 0.09173421561717987
2023-01-23 00:50:05.070841: step: 128/530, loss: 0.3763471245765686
2023-01-23 00:50:06.176123: step: 132/530, loss: 0.12174288928508759
2023-01-23 00:50:07.261988: step: 136/530, loss: 0.06933148205280304
2023-01-23 00:50:08.357204: step: 140/530, loss: 0.014846229925751686
2023-01-23 00:50:09.539074: step: 144/530, loss: 0.034085944294929504
2023-01-23 00:50:10.665575: step: 148/530, loss: 0.04126236215233803
2023-01-23 00:50:11.792082: step: 152/530, loss: 0.10013517737388611
2023-01-23 00:50:12.929492: step: 156/530, loss: 0.07507873326539993
2023-01-23 00:50:14.042357: step: 160/530, loss: 0.09161396324634552
2023-01-23 00:50:15.145338: step: 164/530, loss: 0.009203052148222923
2023-01-23 00:50:16.262946: step: 168/530, loss: 0.312895268201828
2023-01-23 00:50:17.403194: step: 172/530, loss: 0.009002065286040306
2023-01-23 00:50:18.489394: step: 176/530, loss: 0.07059097290039062
2023-01-23 00:50:19.642640: step: 180/530, loss: 0.12018217146396637
2023-01-23 00:50:20.791454: step: 184/530, loss: 0.11672301590442657
2023-01-23 00:50:21.927027: step: 188/530, loss: 0.11591462790966034
2023-01-23 00:50:23.052466: step: 192/530, loss: 0.0751151591539383
2023-01-23 00:50:24.166761: step: 196/530, loss: 0.9985004663467407
2023-01-23 00:50:25.282353: step: 200/530, loss: 0.037081051617860794
2023-01-23 00:50:26.420463: step: 204/530, loss: 0.12355313450098038
2023-01-23 00:50:27.580763: step: 208/530, loss: 0.06885853409767151
2023-01-23 00:50:28.698507: step: 212/530, loss: 0.09651784598827362
2023-01-23 00:50:29.805008: step: 216/530, loss: 0.12591969966888428
2023-01-23 00:50:30.919941: step: 220/530, loss: 0.08783884346485138
2023-01-23 00:50:32.037855: step: 224/530, loss: 0.025673963129520416
2023-01-23 00:50:33.174425: step: 228/530, loss: 0.08829168975353241
2023-01-23 00:50:34.334901: step: 232/530, loss: 0.28565704822540283
2023-01-23 00:50:35.469423: step: 236/530, loss: 0.09349632263183594
2023-01-23 00:50:36.592578: step: 240/530, loss: 0.021793222054839134
2023-01-23 00:50:37.734317: step: 244/530, loss: 0.09603968262672424
2023-01-23 00:50:38.876936: step: 248/530, loss: 0.04812202602624893
2023-01-23 00:50:39.999916: step: 252/530, loss: 0.12237548828125
2023-01-23 00:50:41.125020: step: 256/530, loss: 0.04396219179034233
2023-01-23 00:50:42.237089: step: 260/530, loss: 0.05063905939459801
2023-01-23 00:50:43.396553: step: 264/530, loss: 0.18561352789402008
2023-01-23 00:50:44.536347: step: 268/530, loss: 0.06180925294756889
2023-01-23 00:50:45.674250: step: 272/530, loss: 0.07270612567663193
2023-01-23 00:50:46.827969: step: 276/530, loss: 0.06297808140516281
2023-01-23 00:50:47.925672: step: 280/530, loss: 0.09719981998205185
2023-01-23 00:50:49.049011: step: 284/530, loss: 0.12755441665649414
2023-01-23 00:50:50.192159: step: 288/530, loss: 0.40275105834007263
2023-01-23 00:50:51.316387: step: 292/530, loss: 0.07438831776380539
2023-01-23 00:50:52.438846: step: 296/530, loss: 0.030213166028261185
2023-01-23 00:50:53.542718: step: 300/530, loss: 0.04804039001464844
2023-01-23 00:50:54.715506: step: 304/530, loss: 0.5731737613677979
2023-01-23 00:50:55.854747: step: 308/530, loss: 0.053475238382816315
2023-01-23 00:50:56.979528: step: 312/530, loss: 0.09966201335191727
2023-01-23 00:50:58.081212: step: 316/530, loss: 0.09093177318572998
2023-01-23 00:50:59.232623: step: 320/530, loss: 0.004211616702377796
2023-01-23 00:51:00.353858: step: 324/530, loss: 0.09737997502088547
2023-01-23 00:51:01.477619: step: 328/530, loss: 0.043309975415468216
2023-01-23 00:51:02.599510: step: 332/530, loss: 0.022772599011659622
2023-01-23 00:51:03.756244: step: 336/530, loss: 0.033370498567819595
2023-01-23 00:51:04.899986: step: 340/530, loss: 0.050402261316776276
2023-01-23 00:51:06.010867: step: 344/530, loss: 0.043215371668338776
2023-01-23 00:51:07.123906: step: 348/530, loss: 0.27151376008987427
2023-01-23 00:51:08.287663: step: 352/530, loss: 0.1773693561553955
2023-01-23 00:51:09.403600: step: 356/530, loss: 0.04150247573852539
2023-01-23 00:51:10.535830: step: 360/530, loss: 0.15407544374465942
2023-01-23 00:51:11.656867: step: 364/530, loss: 0.054289959371089935
2023-01-23 00:51:12.793486: step: 368/530, loss: 0.029505252838134766
2023-01-23 00:51:13.914567: step: 372/530, loss: 0.0939764529466629
2023-01-23 00:51:15.045301: step: 376/530, loss: 0.4697422385215759
2023-01-23 00:51:16.160989: step: 380/530, loss: 0.05170917510986328
2023-01-23 00:51:17.304864: step: 384/530, loss: 0.4505559802055359
2023-01-23 00:51:18.459987: step: 388/530, loss: 0.12265956401824951
2023-01-23 00:51:19.558118: step: 392/530, loss: 0.0273679718375206
2023-01-23 00:51:20.695109: step: 396/530, loss: 0.3489646017551422
2023-01-23 00:51:21.835483: step: 400/530, loss: 0.014752007089555264
2023-01-23 00:51:22.971389: step: 404/530, loss: 0.03730654716491699
2023-01-23 00:51:24.104469: step: 408/530, loss: 0.050646115094423294
2023-01-23 00:51:25.229046: step: 412/530, loss: 0.012432193383574486
2023-01-23 00:51:26.354289: step: 416/530, loss: 0.07271060347557068
2023-01-23 00:51:27.480810: step: 420/530, loss: 0.03569746017456055
2023-01-23 00:51:28.614365: step: 424/530, loss: 0.2065838873386383
2023-01-23 00:51:29.742813: step: 428/530, loss: 0.04082994535565376
2023-01-23 00:51:30.864100: step: 432/530, loss: 0.043137550354003906
2023-01-23 00:51:31.972650: step: 436/530, loss: 0.09850387275218964
2023-01-23 00:51:33.127272: step: 440/530, loss: 0.03089609369635582
2023-01-23 00:51:34.235790: step: 444/530, loss: 0.009991872124373913
2023-01-23 00:51:35.348718: step: 448/530, loss: 0.12180376797914505
2023-01-23 00:51:36.490625: step: 452/530, loss: 0.14681577682495117
2023-01-23 00:51:37.599866: step: 456/530, loss: 0.0652797669172287
2023-01-23 00:51:38.750544: step: 460/530, loss: 0.03833465650677681
2023-01-23 00:51:39.880400: step: 464/530, loss: 0.06378021836280823
2023-01-23 00:51:40.997414: step: 468/530, loss: 0.03038034401834011
2023-01-23 00:51:42.133334: step: 472/530, loss: 0.06567096710205078
2023-01-23 00:51:43.264562: step: 476/530, loss: 0.07855186611413956
2023-01-23 00:51:44.403773: step: 480/530, loss: 0.18243679404258728
2023-01-23 00:51:45.526399: step: 484/530, loss: 0.1372160017490387
2023-01-23 00:51:46.654138: step: 488/530, loss: 0.11994900554418564
2023-01-23 00:51:47.802887: step: 492/530, loss: 0.15050125122070312
2023-01-23 00:51:48.936211: step: 496/530, loss: 0.11551618576049805
2023-01-23 00:51:50.073051: step: 500/530, loss: 0.04369340091943741
2023-01-23 00:51:51.191805: step: 504/530, loss: 0.06640468537807465
2023-01-23 00:51:52.311914: step: 508/530, loss: 0.007361006923019886
2023-01-23 00:51:53.449642: step: 512/530, loss: 0.048218343406915665
2023-01-23 00:51:54.550183: step: 516/530, loss: 0.060860682278871536
2023-01-23 00:51:55.709171: step: 520/530, loss: 0.08113536983728409
2023-01-23 00:51:56.851208: step: 524/530, loss: 0.14440375566482544
2023-01-23 00:51:57.982933: step: 528/530, loss: 0.022012807428836823
2023-01-23 00:51:59.106645: step: 532/530, loss: 0.14495879411697388
2023-01-23 00:52:00.216061: step: 536/530, loss: 0.0418274886906147
2023-01-23 00:52:01.339165: step: 540/530, loss: 0.09153890609741211
2023-01-23 00:52:02.474215: step: 544/530, loss: 0.13710197806358337
2023-01-23 00:52:03.583235: step: 548/530, loss: 0.04768846184015274
2023-01-23 00:52:04.724379: step: 552/530, loss: 0.0736326202750206
2023-01-23 00:52:05.851518: step: 556/530, loss: 1.2957487106323242
2023-01-23 00:52:06.970114: step: 560/530, loss: 0.042452335357666016
2023-01-23 00:52:08.116996: step: 564/530, loss: 0.08253307640552521
2023-01-23 00:52:09.239079: step: 568/530, loss: 0.1243891716003418
2023-01-23 00:52:10.358750: step: 572/530, loss: 0.08163681626319885
2023-01-23 00:52:11.494701: step: 576/530, loss: 0.02335796318948269
2023-01-23 00:52:12.642466: step: 580/530, loss: 0.06467590481042862
2023-01-23 00:52:13.763478: step: 584/530, loss: 0.05988512188196182
2023-01-23 00:52:14.876757: step: 588/530, loss: 0.09767093509435654
2023-01-23 00:52:15.998950: step: 592/530, loss: 0.1100701317191124
2023-01-23 00:52:17.099797: step: 596/530, loss: 0.29908645153045654
2023-01-23 00:52:18.253713: step: 600/530, loss: 0.015368079766631126
2023-01-23 00:52:19.367344: step: 604/530, loss: 0.08268795162439346
2023-01-23 00:52:20.487962: step: 608/530, loss: 0.018003465607762337
2023-01-23 00:52:21.620595: step: 612/530, loss: 0.08078031986951828
2023-01-23 00:52:22.756809: step: 616/530, loss: 0.027094364166259766
2023-01-23 00:52:23.878048: step: 620/530, loss: 0.04923610761761665
2023-01-23 00:52:24.984716: step: 624/530, loss: 0.07506600022315979
2023-01-23 00:52:26.096785: step: 628/530, loss: 0.024556400254368782
2023-01-23 00:52:27.200060: step: 632/530, loss: 0.05791368708014488
2023-01-23 00:52:28.324447: step: 636/530, loss: 0.08215484768152237
2023-01-23 00:52:29.450351: step: 640/530, loss: 0.041934773325920105
2023-01-23 00:52:30.562773: step: 644/530, loss: 0.05976295471191406
2023-01-23 00:52:31.703851: step: 648/530, loss: 0.32400768995285034
2023-01-23 00:52:32.871356: step: 652/530, loss: 0.03439519554376602
2023-01-23 00:52:33.994285: step: 656/530, loss: 0.2925798296928406
2023-01-23 00:52:35.119190: step: 660/530, loss: 0.027838896960020065
2023-01-23 00:52:36.234581: step: 664/530, loss: 0.07512311637401581
2023-01-23 00:52:37.355506: step: 668/530, loss: 0.09839363396167755
2023-01-23 00:52:38.486075: step: 672/530, loss: 0.07456064224243164
2023-01-23 00:52:39.641083: step: 676/530, loss: 0.035246849060058594
2023-01-23 00:52:40.755895: step: 680/530, loss: 0.07092466950416565
2023-01-23 00:52:41.865578: step: 684/530, loss: 0.2112814038991928
2023-01-23 00:52:42.997246: step: 688/530, loss: 0.05242948234081268
2023-01-23 00:52:44.141835: step: 692/530, loss: 0.07309255748987198
2023-01-23 00:52:45.254227: step: 696/530, loss: 0.07162085175514221
2023-01-23 00:52:46.387494: step: 700/530, loss: 0.06522292643785477
2023-01-23 00:52:47.527794: step: 704/530, loss: 0.09814925491809845
2023-01-23 00:52:48.647913: step: 708/530, loss: 0.16781044006347656
2023-01-23 00:52:49.760610: step: 712/530, loss: 0.055739592760801315
2023-01-23 00:52:50.840649: step: 716/530, loss: 0.04203863441944122
2023-01-23 00:52:51.996631: step: 720/530, loss: 0.05915536731481552
2023-01-23 00:52:53.141744: step: 724/530, loss: 0.19279813766479492
2023-01-23 00:52:54.288452: step: 728/530, loss: 0.34922534227371216
2023-01-23 00:52:55.448928: step: 732/530, loss: 0.1728130280971527
2023-01-23 00:52:56.592365: step: 736/530, loss: 0.12764176726341248
2023-01-23 00:52:57.730445: step: 740/530, loss: 0.20023518800735474
2023-01-23 00:52:58.900948: step: 744/530, loss: 0.019550751894712448
2023-01-23 00:52:59.999287: step: 748/530, loss: 0.4400915205478668
2023-01-23 00:53:01.127020: step: 752/530, loss: 0.23120427131652832
2023-01-23 00:53:02.241727: step: 756/530, loss: 0.019921613857150078
2023-01-23 00:53:03.342654: step: 760/530, loss: 0.06383663415908813
2023-01-23 00:53:04.497398: step: 764/530, loss: 0.08591480553150177
2023-01-23 00:53:05.630804: step: 768/530, loss: 0.13027562201023102
2023-01-23 00:53:06.751820: step: 772/530, loss: 0.07488145679235458
2023-01-23 00:53:07.859245: step: 776/530, loss: 0.044815681874752045
2023-01-23 00:53:09.012633: step: 780/530, loss: 0.11078119277954102
2023-01-23 00:53:10.126197: step: 784/530, loss: 0.12994547188282013
2023-01-23 00:53:11.252421: step: 788/530, loss: 0.08993014693260193
2023-01-23 00:53:12.367560: step: 792/530, loss: 0.21433153748512268
2023-01-23 00:53:13.480143: step: 796/530, loss: 0.014615010470151901
2023-01-23 00:53:14.640790: step: 800/530, loss: 0.019059086218476295
2023-01-23 00:53:15.745269: step: 804/530, loss: 0.09029875695705414
2023-01-23 00:53:16.877013: step: 808/530, loss: 0.032218173146247864
2023-01-23 00:53:18.014332: step: 812/530, loss: 0.03984851762652397
2023-01-23 00:53:19.141132: step: 816/530, loss: 0.127696231007576
2023-01-23 00:53:20.255152: step: 820/530, loss: 0.06995301693677902
2023-01-23 00:53:21.380569: step: 824/530, loss: 0.10436270385980606
2023-01-23 00:53:22.515831: step: 828/530, loss: 0.12582284212112427
2023-01-23 00:53:23.653821: step: 832/530, loss: 0.025069715455174446
2023-01-23 00:53:24.771792: step: 836/530, loss: 0.01713085174560547
2023-01-23 00:53:25.885608: step: 840/530, loss: 0.03806161880493164
2023-01-23 00:53:26.995805: step: 844/530, loss: 0.022437002509832382
2023-01-23 00:53:28.158792: step: 848/530, loss: 0.1250888854265213
2023-01-23 00:53:29.304845: step: 852/530, loss: 0.028609706088900566
2023-01-23 00:53:30.434547: step: 856/530, loss: 0.029798317700624466
2023-01-23 00:53:31.525047: step: 860/530, loss: 0.08777026832103729
2023-01-23 00:53:32.697431: step: 864/530, loss: 0.20468302071094513
2023-01-23 00:53:33.808380: step: 868/530, loss: 0.03855018690228462
2023-01-23 00:53:34.951031: step: 872/530, loss: 0.08856801688671112
2023-01-23 00:53:36.076228: step: 876/530, loss: 0.023838140070438385
2023-01-23 00:53:37.184281: step: 880/530, loss: 0.29989421367645264
2023-01-23 00:53:38.294193: step: 884/530, loss: 0.41837263107299805
2023-01-23 00:53:39.431157: step: 888/530, loss: 0.16151557862758636
2023-01-23 00:53:40.579226: step: 892/530, loss: 0.05406970903277397
2023-01-23 00:53:41.723227: step: 896/530, loss: 0.5375280380249023
2023-01-23 00:53:42.852087: step: 900/530, loss: 0.34047988057136536
2023-01-23 00:53:43.985532: step: 904/530, loss: 0.03292236477136612
2023-01-23 00:53:45.111298: step: 908/530, loss: 0.09112946689128876
2023-01-23 00:53:46.230106: step: 912/530, loss: 0.1620519608259201
2023-01-23 00:53:47.379414: step: 916/530, loss: 0.04178342968225479
2023-01-23 00:53:48.509181: step: 920/530, loss: 0.01404571533203125
2023-01-23 00:53:49.623059: step: 924/530, loss: 3.9763343334198
2023-01-23 00:53:50.758719: step: 928/530, loss: 0.035802461206912994
2023-01-23 00:53:51.906913: step: 932/530, loss: 0.26478224992752075
2023-01-23 00:53:53.027896: step: 936/530, loss: 0.03883552551269531
2023-01-23 00:53:54.165194: step: 940/530, loss: 0.0029333115089684725
2023-01-23 00:53:55.288750: step: 944/530, loss: 0.3648069500923157
2023-01-23 00:53:56.444087: step: 948/530, loss: 0.08199644088745117
2023-01-23 00:53:57.567042: step: 952/530, loss: 0.19840264320373535
2023-01-23 00:53:58.734912: step: 956/530, loss: 0.16729974746704102
2023-01-23 00:53:59.888503: step: 960/530, loss: 0.05994696915149689
2023-01-23 00:54:00.997545: step: 964/530, loss: 0.07341411709785461
2023-01-23 00:54:02.156199: step: 968/530, loss: 0.08187513053417206
2023-01-23 00:54:03.267856: step: 972/530, loss: 0.049796007573604584
2023-01-23 00:54:04.395554: step: 976/530, loss: 0.09649428725242615
2023-01-23 00:54:05.548969: step: 980/530, loss: 0.07598339766263962
2023-01-23 00:54:06.683376: step: 984/530, loss: 0.07876968383789062
2023-01-23 00:54:07.794885: step: 988/530, loss: 0.030896425247192383
2023-01-23 00:54:08.910633: step: 992/530, loss: 0.05377402529120445
2023-01-23 00:54:10.045701: step: 996/530, loss: 0.0895547866821289
2023-01-23 00:54:11.181633: step: 1000/530, loss: 0.046038150787353516
2023-01-23 00:54:12.371526: step: 1004/530, loss: 0.07872681319713593
2023-01-23 00:54:13.461072: step: 1008/530, loss: 0.09826698154211044
2023-01-23 00:54:14.595874: step: 1012/530, loss: 0.0428282730281353
2023-01-23 00:54:15.699819: step: 1016/530, loss: 0.6448582410812378
2023-01-23 00:54:16.823665: step: 1020/530, loss: 0.046166516840457916
2023-01-23 00:54:17.966826: step: 1024/530, loss: 0.19410762190818787
2023-01-23 00:54:19.181733: step: 1028/530, loss: 0.11003265529870987
2023-01-23 00:54:20.329997: step: 1032/530, loss: 0.1165589839220047
2023-01-23 00:54:21.453980: step: 1036/530, loss: 0.02948169782757759
2023-01-23 00:54:22.547278: step: 1040/530, loss: 0.3134117126464844
2023-01-23 00:54:23.697704: step: 1044/530, loss: 0.5719877481460571
2023-01-23 00:54:24.784814: step: 1048/530, loss: 0.11576595157384872
2023-01-23 00:54:25.903065: step: 1052/530, loss: 0.0035792351700365543
2023-01-23 00:54:27.030271: step: 1056/530, loss: 0.05913562700152397
2023-01-23 00:54:28.179079: step: 1060/530, loss: 0.06444358825683594
2023-01-23 00:54:29.283911: step: 1064/530, loss: 0.23844031989574432
2023-01-23 00:54:30.406260: step: 1068/530, loss: 0.1456901580095291
2023-01-23 00:54:31.537162: step: 1072/530, loss: 0.01520471554249525
2023-01-23 00:54:32.707744: step: 1076/530, loss: 0.09892044216394424
2023-01-23 00:54:33.834518: step: 1080/530, loss: 0.14753571152687073
2023-01-23 00:54:34.988485: step: 1084/530, loss: 0.0640416145324707
2023-01-23 00:54:36.124413: step: 1088/530, loss: 0.04655437543988228
2023-01-23 00:54:37.251185: step: 1092/530, loss: 0.04622550308704376
2023-01-23 00:54:38.403153: step: 1096/530, loss: 0.2176496684551239
2023-01-23 00:54:39.545988: step: 1100/530, loss: 0.06824783980846405
2023-01-23 00:54:40.655536: step: 1104/530, loss: 0.179981529712677
2023-01-23 00:54:41.781574: step: 1108/530, loss: 0.03285665810108185
2023-01-23 00:54:42.931974: step: 1112/530, loss: 0.03740978240966797
2023-01-23 00:54:44.058565: step: 1116/530, loss: 0.04311180114746094
2023-01-23 00:54:45.184560: step: 1120/530, loss: 0.08397160470485687
2023-01-23 00:54:46.297418: step: 1124/530, loss: 0.1097785085439682
2023-01-23 00:54:47.415298: step: 1128/530, loss: 0.06077098846435547
2023-01-23 00:54:48.532788: step: 1132/530, loss: 0.13154879212379456
2023-01-23 00:54:49.694490: step: 1136/530, loss: 0.11111602932214737
2023-01-23 00:54:50.815492: step: 1140/530, loss: 0.032245635986328125
2023-01-23 00:54:51.960319: step: 1144/530, loss: 0.08708296716213226
2023-01-23 00:54:53.109373: step: 1148/530, loss: 0.08207712322473526
2023-01-23 00:54:54.217197: step: 1152/530, loss: 0.08362355828285217
2023-01-23 00:54:55.341262: step: 1156/530, loss: 0.13088122010231018
2023-01-23 00:54:56.462739: step: 1160/530, loss: 0.4110361933708191
2023-01-23 00:54:57.614487: step: 1164/530, loss: 0.11537876725196838
2023-01-23 00:54:58.723985: step: 1168/530, loss: 0.04328203201293945
2023-01-23 00:54:59.832434: step: 1172/530, loss: 0.0701117068529129
2023-01-23 00:55:00.957022: step: 1176/530, loss: 0.1302386373281479
2023-01-23 00:55:02.104957: step: 1180/530, loss: 0.04262809827923775
2023-01-23 00:55:03.222407: step: 1184/530, loss: 0.010998058132827282
2023-01-23 00:55:04.343922: step: 1188/530, loss: 0.07971601188182831
2023-01-23 00:55:05.460342: step: 1192/530, loss: 0.00440636882558465
2023-01-23 00:55:06.596352: step: 1196/530, loss: 0.1615658700466156
2023-01-23 00:55:07.714567: step: 1200/530, loss: 0.10765416920185089
2023-01-23 00:55:08.822112: step: 1204/530, loss: 0.12520912289619446
2023-01-23 00:55:09.938569: step: 1208/530, loss: 0.08215294033288956
2023-01-23 00:55:11.034643: step: 1212/530, loss: 0.03524074703454971
2023-01-23 00:55:12.195160: step: 1216/530, loss: 0.023448754101991653
2023-01-23 00:55:13.319112: step: 1220/530, loss: 0.02454409748315811
2023-01-23 00:55:14.438352: step: 1224/530, loss: 0.0606236457824707
2023-01-23 00:55:15.574227: step: 1228/530, loss: 0.03665647655725479
2023-01-23 00:55:16.696222: step: 1232/530, loss: 0.018143273890018463
2023-01-23 00:55:17.775850: step: 1236/530, loss: 0.1944512277841568
2023-01-23 00:55:18.941200: step: 1240/530, loss: 0.0617918036878109
2023-01-23 00:55:20.145765: step: 1244/530, loss: 0.03439726680517197
2023-01-23 00:55:21.262373: step: 1248/530, loss: 0.2308807373046875
2023-01-23 00:55:22.385094: step: 1252/530, loss: 0.0649634376168251
2023-01-23 00:55:23.529851: step: 1256/530, loss: 0.10017891228199005
2023-01-23 00:55:24.658602: step: 1260/530, loss: 0.11726336181163788
2023-01-23 00:55:25.814202: step: 1264/530, loss: 0.10373449325561523
2023-01-23 00:55:26.928836: step: 1268/530, loss: 0.017322350293397903
2023-01-23 00:55:28.060055: step: 1272/530, loss: 0.11629681289196014
2023-01-23 00:55:29.184522: step: 1276/530, loss: 0.020702313631772995
2023-01-23 00:55:30.313259: step: 1280/530, loss: 0.05313124507665634
2023-01-23 00:55:31.409390: step: 1284/530, loss: 0.6437771320343018
2023-01-23 00:55:32.573939: step: 1288/530, loss: 0.07526913285255432
2023-01-23 00:55:33.711619: step: 1292/530, loss: 0.013522911816835403
2023-01-23 00:55:34.846969: step: 1296/530, loss: 0.06642293930053711
2023-01-23 00:55:35.952275: step: 1300/530, loss: 0.034535981714725494
2023-01-23 00:55:37.054936: step: 1304/530, loss: 0.006374877877533436
2023-01-23 00:55:38.192739: step: 1308/530, loss: 1.2615207433700562
2023-01-23 00:55:39.300655: step: 1312/530, loss: 0.04376354068517685
2023-01-23 00:55:40.435760: step: 1316/530, loss: 0.048059988766908646
2023-01-23 00:55:41.582196: step: 1320/530, loss: 0.21942730247974396
2023-01-23 00:55:42.684642: step: 1324/530, loss: 0.10523892194032669
2023-01-23 00:55:43.806544: step: 1328/530, loss: 0.3994571566581726
2023-01-23 00:55:44.949782: step: 1332/530, loss: 0.06274890899658203
2023-01-23 00:55:46.064955: step: 1336/530, loss: 0.16639643907546997
2023-01-23 00:55:47.179756: step: 1340/530, loss: 0.0745050460100174
2023-01-23 00:55:48.334806: step: 1344/530, loss: 0.020218467339873314
2023-01-23 00:55:49.486505: step: 1348/530, loss: 0.06965980678796768
2023-01-23 00:55:50.640490: step: 1352/530, loss: 0.07142181694507599
2023-01-23 00:55:51.743550: step: 1356/530, loss: 0.05727948993444443
2023-01-23 00:55:52.863838: step: 1360/530, loss: 0.06587830185890198
2023-01-23 00:55:53.959074: step: 1364/530, loss: 0.1136774942278862
2023-01-23 00:55:55.059611: step: 1368/530, loss: 0.045653726905584335
2023-01-23 00:55:56.164146: step: 1372/530, loss: 0.039304353296756744
2023-01-23 00:55:57.265731: step: 1376/530, loss: 0.07658644020557404
2023-01-23 00:55:58.380670: step: 1380/530, loss: 0.018712997436523438
2023-01-23 00:55:59.497186: step: 1384/530, loss: 0.03401937335729599
2023-01-23 00:56:00.614656: step: 1388/530, loss: 0.11538667976856232
2023-01-23 00:56:01.731349: step: 1392/530, loss: 0.13676157593727112
2023-01-23 00:56:02.853401: step: 1396/530, loss: 0.15297982096672058
2023-01-23 00:56:03.968927: step: 1400/530, loss: 0.018097544088959694
2023-01-23 00:56:05.103205: step: 1404/530, loss: 0.0774068832397461
2023-01-23 00:56:06.236947: step: 1408/530, loss: 0.07601775974035263
2023-01-23 00:56:07.375695: step: 1412/530, loss: 0.19643695652484894
2023-01-23 00:56:08.511965: step: 1416/530, loss: 0.0519014336168766
2023-01-23 00:56:09.641817: step: 1420/530, loss: 0.03080177493393421
2023-01-23 00:56:10.726631: step: 1424/530, loss: 0.0715765729546547
2023-01-23 00:56:11.845405: step: 1428/530, loss: 0.06904315948486328
2023-01-23 00:56:12.943981: step: 1432/530, loss: 0.03958840295672417
2023-01-23 00:56:14.088271: step: 1436/530, loss: 0.04114561155438423
2023-01-23 00:56:15.211486: step: 1440/530, loss: 0.06859956681728363
2023-01-23 00:56:16.360015: step: 1444/530, loss: 0.042545415461063385
2023-01-23 00:56:17.474288: step: 1448/530, loss: 0.06447849422693253
2023-01-23 00:56:18.605862: step: 1452/530, loss: 0.14115557074546814
2023-01-23 00:56:19.720960: step: 1456/530, loss: 0.15271377563476562
2023-01-23 00:56:20.877801: step: 1460/530, loss: 0.09959983825683594
2023-01-23 00:56:22.047038: step: 1464/530, loss: 0.05774059519171715
2023-01-23 00:56:23.229221: step: 1468/530, loss: 0.8459482192993164
2023-01-23 00:56:24.335684: step: 1472/530, loss: 0.1214621514081955
2023-01-23 00:56:25.467366: step: 1476/530, loss: 0.17651471495628357
2023-01-23 00:56:26.590447: step: 1480/530, loss: 0.036165524274110794
2023-01-23 00:56:27.696121: step: 1484/530, loss: 0.027136903256177902
2023-01-23 00:56:28.797179: step: 1488/530, loss: 0.02073807641863823
2023-01-23 00:56:29.912326: step: 1492/530, loss: 0.07076302915811539
2023-01-23 00:56:31.045202: step: 1496/530, loss: 0.03808724880218506
2023-01-23 00:56:32.156521: step: 1500/530, loss: 0.5862589478492737
2023-01-23 00:56:33.273191: step: 1504/530, loss: 0.04045257717370987
2023-01-23 00:56:34.378857: step: 1508/530, loss: 0.05408668518066406
2023-01-23 00:56:35.498493: step: 1512/530, loss: 0.8601412773132324
2023-01-23 00:56:36.619243: step: 1516/530, loss: 0.2603822648525238
2023-01-23 00:56:37.744238: step: 1520/530, loss: 0.1986106038093567
2023-01-23 00:56:38.868391: step: 1524/530, loss: 0.0456884391605854
2023-01-23 00:56:39.992114: step: 1528/530, loss: 0.07586565613746643
2023-01-23 00:56:41.090431: step: 1532/530, loss: 0.2109348326921463
2023-01-23 00:56:42.224337: step: 1536/530, loss: 0.2524593472480774
2023-01-23 00:56:43.396698: step: 1540/530, loss: 0.09041347354650497
2023-01-23 00:56:44.519409: step: 1544/530, loss: 0.027682732790708542
2023-01-23 00:56:45.666306: step: 1548/530, loss: 0.04460182413458824
2023-01-23 00:56:46.767602: step: 1552/530, loss: 0.06576766818761826
2023-01-23 00:56:47.876174: step: 1556/530, loss: 0.04151410982012749
2023-01-23 00:56:49.048060: step: 1560/530, loss: 0.03367156907916069
2023-01-23 00:56:50.164807: step: 1564/530, loss: 0.0012005805037915707
2023-01-23 00:56:51.274053: step: 1568/530, loss: 0.020243704319000244
2023-01-23 00:56:52.392852: step: 1572/530, loss: 0.07041990756988525
2023-01-23 00:56:53.512150: step: 1576/530, loss: 0.0623898059129715
2023-01-23 00:56:54.644224: step: 1580/530, loss: 0.08070193231105804
2023-01-23 00:56:55.765225: step: 1584/530, loss: 0.08670344948768616
2023-01-23 00:56:56.899614: step: 1588/530, loss: 0.09154634922742844
2023-01-23 00:56:58.005502: step: 1592/530, loss: 0.011732817627489567
2023-01-23 00:56:59.136037: step: 1596/530, loss: 0.08833663165569305
2023-01-23 00:57:00.276240: step: 1600/530, loss: 0.11914139986038208
2023-01-23 00:57:01.396774: step: 1604/530, loss: 0.09477101266384125
2023-01-23 00:57:02.509622: step: 1608/530, loss: 0.23316669464111328
2023-01-23 00:57:03.647382: step: 1612/530, loss: 0.03017454221844673
2023-01-23 00:57:04.773982: step: 1616/530, loss: 0.14386683702468872
2023-01-23 00:57:05.903002: step: 1620/530, loss: 0.08940906822681427
2023-01-23 00:57:07.036334: step: 1624/530, loss: 0.02055530622601509
2023-01-23 00:57:08.166962: step: 1628/530, loss: 0.10598006844520569
2023-01-23 00:57:09.283752: step: 1632/530, loss: 0.04440479353070259
2023-01-23 00:57:10.415514: step: 1636/530, loss: 0.09307155758142471
2023-01-23 00:57:11.560891: step: 1640/530, loss: 0.11901766061782837
2023-01-23 00:57:12.713226: step: 1644/530, loss: 0.09626798331737518
2023-01-23 00:57:13.842286: step: 1648/530, loss: 0.0802789255976677
2023-01-23 00:57:14.955771: step: 1652/530, loss: 0.2961452305316925
2023-01-23 00:57:16.092940: step: 1656/530, loss: 0.09225402027368546
2023-01-23 00:57:17.230471: step: 1660/530, loss: 0.12265992164611816
2023-01-23 00:57:18.363758: step: 1664/530, loss: 0.0021490096114575863
2023-01-23 00:57:19.481544: step: 1668/530, loss: 0.09488850086927414
2023-01-23 00:57:20.578930: step: 1672/530, loss: 0.07696390151977539
2023-01-23 00:57:21.708018: step: 1676/530, loss: 0.07524547725915909
2023-01-23 00:57:22.864985: step: 1680/530, loss: 0.04918060451745987
2023-01-23 00:57:24.014454: step: 1684/530, loss: 0.012505482882261276
2023-01-23 00:57:25.133570: step: 1688/530, loss: 0.04604711756110191
2023-01-23 00:57:26.248424: step: 1692/530, loss: 0.051996562629938126
2023-01-23 00:57:27.391211: step: 1696/530, loss: 0.01409225445240736
2023-01-23 00:57:28.532753: step: 1700/530, loss: 0.060300350189208984
2023-01-23 00:57:29.664689: step: 1704/530, loss: 0.18855877220630646
2023-01-23 00:57:30.772838: step: 1708/530, loss: 0.11008048057556152
2023-01-23 00:57:31.899217: step: 1712/530, loss: 0.04119386896491051
2023-01-23 00:57:33.024427: step: 1716/530, loss: 0.06107797846198082
2023-01-23 00:57:34.125347: step: 1720/530, loss: 0.27596521377563477
2023-01-23 00:57:35.230848: step: 1724/530, loss: 0.08460140228271484
2023-01-23 00:57:36.358134: step: 1728/530, loss: 0.11772172898054123
2023-01-23 00:57:37.511396: step: 1732/530, loss: 0.014800453558564186
2023-01-23 00:57:38.640231: step: 1736/530, loss: 0.02242593839764595
2023-01-23 00:57:39.785580: step: 1740/530, loss: 0.15692806243896484
2023-01-23 00:57:40.918682: step: 1744/530, loss: 0.06582526862621307
2023-01-23 00:57:42.030766: step: 1748/530, loss: 0.04527602344751358
2023-01-23 00:57:43.197082: step: 1752/530, loss: 0.07914133369922638
2023-01-23 00:57:44.321385: step: 1756/530, loss: 0.13442236185073853
2023-01-23 00:57:45.461239: step: 1760/530, loss: 0.5814440846443176
2023-01-23 00:57:46.572022: step: 1764/530, loss: 0.34597188234329224
2023-01-23 00:57:47.701560: step: 1768/530, loss: 0.5466675758361816
2023-01-23 00:57:48.802995: step: 1772/530, loss: 0.03274974972009659
2023-01-23 00:57:49.944586: step: 1776/530, loss: 0.10324878245592117
2023-01-23 00:57:51.065832: step: 1780/530, loss: 0.25266528129577637
2023-01-23 00:57:52.204134: step: 1784/530, loss: 0.04500222206115723
2023-01-23 00:57:53.348991: step: 1788/530, loss: 0.1351356953382492
2023-01-23 00:57:54.471323: step: 1792/530, loss: 0.031963445246219635
2023-01-23 00:57:55.588927: step: 1796/530, loss: 0.40441760420799255
2023-01-23 00:57:56.715837: step: 1800/530, loss: 0.2764412462711334
2023-01-23 00:57:57.853079: step: 1804/530, loss: 0.0966092124581337
2023-01-23 00:57:58.986823: step: 1808/530, loss: 0.048938751220703125
2023-01-23 00:58:00.099957: step: 1812/530, loss: 0.14263038337230682
2023-01-23 00:58:01.228724: step: 1816/530, loss: 0.08984461426734924
2023-01-23 00:58:02.343047: step: 1820/530, loss: 0.1023816168308258
2023-01-23 00:58:03.474883: step: 1824/530, loss: 0.050203923135995865
2023-01-23 00:58:04.620440: step: 1828/530, loss: 0.22512884438037872
2023-01-23 00:58:05.746138: step: 1832/530, loss: 0.2169717401266098
2023-01-23 00:58:06.871833: step: 1836/530, loss: 0.10818032920360565
2023-01-23 00:58:07.989709: step: 1840/530, loss: 0.013808537274599075
2023-01-23 00:58:09.128248: step: 1844/530, loss: 0.08203835785388947
2023-01-23 00:58:10.255290: step: 1848/530, loss: 0.09792857617139816
2023-01-23 00:58:11.384555: step: 1852/530, loss: 0.1966841220855713
2023-01-23 00:58:12.522284: step: 1856/530, loss: 0.05021515116095543
2023-01-23 00:58:13.644788: step: 1860/530, loss: 0.13389775156974792
2023-01-23 00:58:14.783501: step: 1864/530, loss: 0.16585904359817505
2023-01-23 00:58:15.885827: step: 1868/530, loss: 0.3613828420639038
2023-01-23 00:58:17.026638: step: 1872/530, loss: 0.08053598552942276
2023-01-23 00:58:18.135870: step: 1876/530, loss: 0.04160032421350479
2023-01-23 00:58:19.275350: step: 1880/530, loss: 0.041875626891851425
2023-01-23 00:58:20.401019: step: 1884/530, loss: 0.11476331204175949
2023-01-23 00:58:21.507156: step: 1888/530, loss: 0.10922642052173615
2023-01-23 00:58:22.617631: step: 1892/530, loss: 0.05841970443725586
2023-01-23 00:58:23.779420: step: 1896/530, loss: 0.05351386219263077
2023-01-23 00:58:24.939903: step: 1900/530, loss: 0.024054670706391335
2023-01-23 00:58:26.044305: step: 1904/530, loss: 0.06838121265172958
2023-01-23 00:58:27.166768: step: 1908/530, loss: 0.11356105655431747
2023-01-23 00:58:28.287333: step: 1912/530, loss: 0.03153543546795845
2023-01-23 00:58:29.423760: step: 1916/530, loss: 0.016533851623535156
2023-01-23 00:58:30.539618: step: 1920/530, loss: 0.056430913507938385
2023-01-23 00:58:31.693591: step: 1924/530, loss: 0.1042516678571701
2023-01-23 00:58:32.849178: step: 1928/530, loss: 0.09258913993835449
2023-01-23 00:58:33.947969: step: 1932/530, loss: 0.09291648864746094
2023-01-23 00:58:35.076507: step: 1936/530, loss: 0.049272727221250534
2023-01-23 00:58:36.201368: step: 1940/530, loss: 0.0884493887424469
2023-01-23 00:58:37.322855: step: 1944/530, loss: 0.14059877395629883
2023-01-23 00:58:38.461434: step: 1948/530, loss: 0.21385231614112854
2023-01-23 00:58:39.595900: step: 1952/530, loss: 0.11460743099451065
2023-01-23 00:58:40.700431: step: 1956/530, loss: 0.43515080213546753
2023-01-23 00:58:41.802710: step: 1960/530, loss: 0.07509736716747284
2023-01-23 00:58:42.923622: step: 1964/530, loss: 0.14917536079883575
2023-01-23 00:58:44.053754: step: 1968/530, loss: 0.08783073723316193
2023-01-23 00:58:45.194821: step: 1972/530, loss: 0.06715182960033417
2023-01-23 00:58:46.309099: step: 1976/530, loss: 0.3167229890823364
2023-01-23 00:58:47.461195: step: 1980/530, loss: 0.022747136652469635
2023-01-23 00:58:48.589647: step: 1984/530, loss: 0.014326667413115501
2023-01-23 00:58:49.734332: step: 1988/530, loss: 0.07179916650056839
2023-01-23 00:58:50.863978: step: 1992/530, loss: 0.06716380268335342
2023-01-23 00:58:52.032224: step: 1996/530, loss: 0.16477961838245392
2023-01-23 00:58:53.196558: step: 2000/530, loss: 0.033688828349113464
2023-01-23 00:58:54.349328: step: 2004/530, loss: 0.2741049826145172
2023-01-23 00:58:55.486239: step: 2008/530, loss: 0.09658517688512802
2023-01-23 00:58:56.600520: step: 2012/530, loss: 0.9274341464042664
2023-01-23 00:58:57.725509: step: 2016/530, loss: 0.004947471432387829
2023-01-23 00:58:58.841620: step: 2020/530, loss: 0.057419776916503906
2023-01-23 00:58:59.949536: step: 2024/530, loss: 0.01900796964764595
2023-01-23 00:59:01.057824: step: 2028/530, loss: 0.16491250693798065
2023-01-23 00:59:02.178058: step: 2032/530, loss: 0.09365349262952805
2023-01-23 00:59:03.294745: step: 2036/530, loss: 0.046285200864076614
2023-01-23 00:59:04.443134: step: 2040/530, loss: 0.06361713260412216
2023-01-23 00:59:05.568197: step: 2044/530, loss: 0.06339231133460999
2023-01-23 00:59:06.722467: step: 2048/530, loss: 0.10045404732227325
2023-01-23 00:59:07.837554: step: 2052/530, loss: 0.051396798342466354
2023-01-23 00:59:08.976043: step: 2056/530, loss: 0.09863011538982391
2023-01-23 00:59:10.130208: step: 2060/530, loss: 0.8275082111358643
2023-01-23 00:59:11.285988: step: 2064/530, loss: 0.11857318878173828
2023-01-23 00:59:12.408975: step: 2068/530, loss: 0.09697838127613068
2023-01-23 00:59:13.541852: step: 2072/530, loss: 0.1563989222049713
2023-01-23 00:59:14.674411: step: 2076/530, loss: 0.10821013152599335
2023-01-23 00:59:15.766125: step: 2080/530, loss: 0.049179743975400925
2023-01-23 00:59:16.899268: step: 2084/530, loss: 0.0793735533952713
2023-01-23 00:59:18.033898: step: 2088/530, loss: 0.011032676324248314
2023-01-23 00:59:19.148719: step: 2092/530, loss: 0.19795528054237366
2023-01-23 00:59:20.264053: step: 2096/530, loss: 0.08164076507091522
2023-01-23 00:59:21.383840: step: 2100/530, loss: 0.058263204991817474
2023-01-23 00:59:22.507958: step: 2104/530, loss: 0.013590408489108086
2023-01-23 00:59:23.619237: step: 2108/530, loss: 0.05726051330566406
2023-01-23 00:59:24.788498: step: 2112/530, loss: 0.5535554885864258
2023-01-23 00:59:25.907561: step: 2116/530, loss: 0.010237693786621094
2023-01-23 00:59:27.027097: step: 2120/530, loss: 0.1349318027496338
==================================================
Loss: 0.126
--------------------
Dev: {'event': {'p': 0.5679611650485437, 'r': 0.7789613848202397, 'f1': 0.656934306569343}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Test: {'event': {'p': 0.609845031905196, 'r': 0.7645714285714286, 'f1': 0.6784989858012171}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
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': 8}
Korean: {'event': {'p': 0.5967741935483871, 'r': 0.5873015873015873, 'f1': 0.592}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Russian: {'event': {'p': 0.34782608695652173, 'r': 0.4444444444444444, 'f1': 0.3902439024390244}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Chinese: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Chinese: {'event': {'p': 0.6190476190476191, 'r': 0.9629629629629629, 'f1': 0.7536231884057971}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Korean: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Korean: {'event': {'p': 0.609375, 'r': 0.6190476190476191, 'f1': 0.6141732283464567}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5319148936170213, 'r': 0.6944444444444444, 'f1': 0.6024096385542169}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
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 01:00:07.709296: step: 4/530, loss: 0.0790146216750145
2023-01-23 01:00:08.821986: step: 8/530, loss: 0.3121567368507385
2023-01-23 01:00:09.965449: step: 12/530, loss: 0.005270957946777344
2023-01-23 01:00:11.091624: step: 16/530, loss: 0.10345049202442169
2023-01-23 01:00:12.193242: step: 20/530, loss: 0.026897288858890533
2023-01-23 01:00:13.366884: step: 24/530, loss: 0.06734971702098846
2023-01-23 01:00:14.514373: step: 28/530, loss: 0.028751563280820847
2023-01-23 01:00:15.643575: step: 32/530, loss: 0.019435979425907135
2023-01-23 01:00:16.746389: step: 36/530, loss: 0.02271575853228569
2023-01-23 01:00:17.868147: step: 40/530, loss: 0.10955947637557983
2023-01-23 01:00:18.996776: step: 44/530, loss: 0.06370868533849716
2023-01-23 01:00:20.139032: step: 48/530, loss: 0.05016279220581055
2023-01-23 01:00:21.251849: step: 52/530, loss: 0.026475906372070312
2023-01-23 01:00:22.389720: step: 56/530, loss: 0.08268547058105469
2023-01-23 01:00:23.510425: step: 60/530, loss: 0.10631771385669708
2023-01-23 01:00:24.628278: step: 64/530, loss: 0.062207892537117004
2023-01-23 01:00:25.739138: step: 68/530, loss: 0.05992469936609268
2023-01-23 01:00:26.867365: step: 72/530, loss: 0.044905029237270355
2023-01-23 01:00:27.979133: step: 76/530, loss: 0.018973970785737038
2023-01-23 01:00:29.089852: step: 80/530, loss: 0.03886954486370087
2023-01-23 01:00:30.215684: step: 84/530, loss: 0.05941829830408096
2023-01-23 01:00:31.319193: step: 88/530, loss: 0.23195838928222656
2023-01-23 01:00:32.438327: step: 92/530, loss: 0.11491012573242188
2023-01-23 01:00:33.552046: step: 96/530, loss: 0.09214534610509872
2023-01-23 01:00:34.656625: step: 100/530, loss: 0.09660749137401581
2023-01-23 01:00:35.754865: step: 104/530, loss: 0.02130107954144478
2023-01-23 01:00:36.860419: step: 108/530, loss: 0.029286576434969902
2023-01-23 01:00:37.988221: step: 112/530, loss: 0.19082216918468475
2023-01-23 01:00:39.134575: step: 116/530, loss: 0.1164407730102539
2023-01-23 01:00:40.281893: step: 120/530, loss: 0.8564645648002625
2023-01-23 01:00:41.408529: step: 124/530, loss: 0.19386176764965057
2023-01-23 01:00:42.576397: step: 128/530, loss: 0.1229085922241211
2023-01-23 01:00:43.707070: step: 132/530, loss: 0.007953834719955921
2023-01-23 01:00:44.823723: step: 136/530, loss: 0.031861402094364166
2023-01-23 01:00:45.933042: step: 140/530, loss: 0.020019937306642532
2023-01-23 01:00:47.065398: step: 144/530, loss: 0.07812432199716568
2023-01-23 01:00:48.199475: step: 148/530, loss: 0.05324859917163849
2023-01-23 01:00:49.336887: step: 152/530, loss: 0.48522549867630005
2023-01-23 01:00:50.494212: step: 156/530, loss: 0.13192281126976013
2023-01-23 01:00:51.610102: step: 160/530, loss: 0.017609406262636185
2023-01-23 01:00:52.720385: step: 164/530, loss: 0.03794679790735245
2023-01-23 01:00:53.839573: step: 168/530, loss: 0.07091084122657776
2023-01-23 01:00:54.980974: step: 172/530, loss: 0.08146214485168457
2023-01-23 01:00:56.089967: step: 176/530, loss: 0.0790490135550499
2023-01-23 01:00:57.197947: step: 180/530, loss: 0.10353999584913254
2023-01-23 01:00:58.314209: step: 184/530, loss: 0.1889912188053131
2023-01-23 01:00:59.432493: step: 188/530, loss: 0.06240663677453995
2023-01-23 01:01:00.541302: step: 192/530, loss: 0.182064488530159
2023-01-23 01:01:01.656942: step: 196/530, loss: 0.042807579040527344
2023-01-23 01:01:02.809685: step: 200/530, loss: 0.16158857941627502
2023-01-23 01:01:03.938933: step: 204/530, loss: 0.053696535527706146
2023-01-23 01:01:05.067058: step: 208/530, loss: 0.2970302700996399
2023-01-23 01:01:06.193956: step: 212/530, loss: 0.027089547365903854
2023-01-23 01:01:07.333791: step: 216/530, loss: 0.15973377227783203
2023-01-23 01:01:08.438097: step: 220/530, loss: 0.2062583863735199
2023-01-23 01:01:09.569775: step: 224/530, loss: 0.07543697953224182
2023-01-23 01:01:10.722567: step: 228/530, loss: 0.057195283472537994
2023-01-23 01:01:11.859786: step: 232/530, loss: 0.11635017395019531
2023-01-23 01:01:13.024873: step: 236/530, loss: 0.7904821634292603
2023-01-23 01:01:14.147890: step: 240/530, loss: 0.1256381869316101
2023-01-23 01:01:15.278314: step: 244/530, loss: 0.14440707862377167
2023-01-23 01:01:16.395799: step: 248/530, loss: 0.049249935895204544
2023-01-23 01:01:17.520997: step: 252/530, loss: 0.0046364786103367805
2023-01-23 01:01:18.663753: step: 256/530, loss: 0.020391464233398438
2023-01-23 01:01:19.771951: step: 260/530, loss: 0.032820604741573334
2023-01-23 01:01:20.909382: step: 264/530, loss: 0.08701248466968536
2023-01-23 01:01:22.034366: step: 268/530, loss: 0.09363818168640137
2023-01-23 01:01:23.175947: step: 272/530, loss: 0.022823764011263847
2023-01-23 01:01:24.325871: step: 276/530, loss: 0.08607196807861328
2023-01-23 01:01:25.430630: step: 280/530, loss: 0.08581342548131943
2023-01-23 01:01:26.580341: step: 284/530, loss: 0.02920222282409668
2023-01-23 01:01:27.701998: step: 288/530, loss: 0.021055985242128372
2023-01-23 01:01:28.828663: step: 292/530, loss: 0.9731878638267517
2023-01-23 01:01:29.954765: step: 296/530, loss: 0.06904873996973038
2023-01-23 01:01:31.064654: step: 300/530, loss: 0.06195984035730362
2023-01-23 01:01:32.161398: step: 304/530, loss: 0.16180315613746643
2023-01-23 01:01:33.307929: step: 308/530, loss: 0.06663952022790909
2023-01-23 01:01:34.447198: step: 312/530, loss: 0.060877226293087006
2023-01-23 01:01:35.571570: step: 316/530, loss: 0.03636179119348526
2023-01-23 01:01:36.686031: step: 320/530, loss: 0.04690727964043617
2023-01-23 01:01:37.799991: step: 324/530, loss: 0.447091668844223
2023-01-23 01:01:38.951966: step: 328/530, loss: 0.10942287743091583
2023-01-23 01:01:40.101954: step: 332/530, loss: 0.06489335000514984
2023-01-23 01:01:41.211582: step: 336/530, loss: 0.07269497215747833
2023-01-23 01:01:42.317932: step: 340/530, loss: 0.2644649147987366
2023-01-23 01:01:43.445822: step: 344/530, loss: 0.10777568817138672
2023-01-23 01:01:44.583849: step: 348/530, loss: 0.026566505432128906
2023-01-23 01:01:45.680505: step: 352/530, loss: 0.034213267266750336
2023-01-23 01:01:46.810484: step: 356/530, loss: 0.4147357940673828
2023-01-23 01:01:47.923946: step: 360/530, loss: 0.07547035813331604
2023-01-23 01:01:49.057955: step: 364/530, loss: 0.3082072138786316
2023-01-23 01:01:50.193236: step: 368/530, loss: 0.5564893484115601
2023-01-23 01:01:51.313066: step: 372/530, loss: 0.06938190758228302
2023-01-23 01:01:52.433620: step: 376/530, loss: 0.05175306648015976
2023-01-23 01:01:53.561806: step: 380/530, loss: 0.06000519171357155
2023-01-23 01:01:54.679879: step: 384/530, loss: 0.34796857833862305
2023-01-23 01:01:55.779699: step: 388/530, loss: 0.0763828307390213
2023-01-23 01:01:56.886644: step: 392/530, loss: 0.016621733084321022
2023-01-23 01:01:57.984484: step: 396/530, loss: 0.12110351771116257
2023-01-23 01:01:59.115828: step: 400/530, loss: 0.06852512806653976
2023-01-23 01:02:00.262263: step: 404/530, loss: 0.03708639368414879
2023-01-23 01:02:01.362720: step: 408/530, loss: 0.2687458097934723
2023-01-23 01:02:02.525505: step: 412/530, loss: 0.057169344276189804
2023-01-23 01:02:03.679667: step: 416/530, loss: 0.0790010541677475
2023-01-23 01:02:04.791681: step: 420/530, loss: 0.11381244659423828
2023-01-23 01:02:05.929551: step: 424/530, loss: 0.0247865691781044
2023-01-23 01:02:07.037253: step: 428/530, loss: 0.032341957092285156
2023-01-23 01:02:08.129939: step: 432/530, loss: 0.037595055997371674
2023-01-23 01:02:09.257023: step: 436/530, loss: 0.06516475975513458
2023-01-23 01:02:10.381308: step: 440/530, loss: 0.03413037955760956
2023-01-23 01:02:11.511661: step: 444/530, loss: 0.07497907429933548
2023-01-23 01:02:12.635943: step: 448/530, loss: 0.08353137969970703
2023-01-23 01:02:13.777180: step: 452/530, loss: 0.05254316329956055
2023-01-23 01:02:14.916361: step: 456/530, loss: 0.8278747200965881
2023-01-23 01:02:16.038912: step: 460/530, loss: 0.09874637424945831
2023-01-23 01:02:17.143996: step: 464/530, loss: 0.6914241909980774
2023-01-23 01:02:18.258612: step: 468/530, loss: 0.05763216316699982
2023-01-23 01:02:19.395142: step: 472/530, loss: 0.15036840736865997
2023-01-23 01:02:20.520340: step: 476/530, loss: 0.24840950965881348
2023-01-23 01:02:21.679495: step: 480/530, loss: 0.03926057741045952
2023-01-23 01:02:22.794125: step: 484/530, loss: 0.07835254818201065
2023-01-23 01:02:23.910795: step: 488/530, loss: 0.4250585436820984
2023-01-23 01:02:25.045934: step: 492/530, loss: 0.04335727542638779
2023-01-23 01:02:26.181898: step: 496/530, loss: 0.0035352229606360197
2023-01-23 01:02:27.307396: step: 500/530, loss: 0.03633260726928711
2023-01-23 01:02:28.414819: step: 504/530, loss: 0.05147905275225639
2023-01-23 01:02:29.537493: step: 508/530, loss: 0.0861385390162468
2023-01-23 01:02:30.646269: step: 512/530, loss: 0.1566476821899414
2023-01-23 01:02:31.745447: step: 516/530, loss: 0.005314636509865522
2023-01-23 01:02:32.866680: step: 520/530, loss: 0.08648806065320969
2023-01-23 01:02:34.026050: step: 524/530, loss: 0.07566585391759872
2023-01-23 01:02:35.184190: step: 528/530, loss: 0.18203648924827576
2023-01-23 01:02:36.289100: step: 532/530, loss: 0.13507795333862305
2023-01-23 01:02:37.397552: step: 536/530, loss: 0.20587468147277832
2023-01-23 01:02:38.585507: step: 540/530, loss: 0.055060386657714844
2023-01-23 01:02:39.678547: step: 544/530, loss: 0.010841942392289639
2023-01-23 01:02:40.806112: step: 548/530, loss: 0.679426372051239
2023-01-23 01:02:41.916437: step: 552/530, loss: 0.0229357723146677
2023-01-23 01:02:43.059396: step: 556/530, loss: 0.058355141431093216
2023-01-23 01:02:44.212087: step: 560/530, loss: 0.18925486505031586
2023-01-23 01:02:45.324762: step: 564/530, loss: 0.06875462830066681
2023-01-23 01:02:46.468188: step: 568/530, loss: 0.1131775826215744
2023-01-23 01:02:47.592064: step: 572/530, loss: 0.11294879764318466
2023-01-23 01:02:48.755145: step: 576/530, loss: 0.043291714042425156
2023-01-23 01:02:49.880682: step: 580/530, loss: 0.0644916519522667
2023-01-23 01:02:50.997250: step: 584/530, loss: 0.024523068219423294
2023-01-23 01:02:52.107654: step: 588/530, loss: 0.021272946149110794
2023-01-23 01:02:53.253597: step: 592/530, loss: 0.1397315114736557
2023-01-23 01:02:54.399656: step: 596/530, loss: 0.044266462326049805
2023-01-23 01:02:55.522088: step: 600/530, loss: 0.0054864888079464436
2023-01-23 01:02:56.639715: step: 604/530, loss: 0.01130599994212389
2023-01-23 01:02:57.742166: step: 608/530, loss: 0.031546689569950104
2023-01-23 01:02:58.862333: step: 612/530, loss: 0.06674909591674805
2023-01-23 01:03:00.004228: step: 616/530, loss: 0.027262020856142044
2023-01-23 01:03:01.137679: step: 620/530, loss: 0.27579402923583984
2023-01-23 01:03:02.246371: step: 624/530, loss: 0.04268636554479599
2023-01-23 01:03:03.379409: step: 628/530, loss: 0.05083026736974716
2023-01-23 01:03:04.499969: step: 632/530, loss: 0.23850193619728088
2023-01-23 01:03:05.644939: step: 636/530, loss: 0.05563812702894211
2023-01-23 01:03:06.784354: step: 640/530, loss: 0.0673486739397049
2023-01-23 01:03:07.922938: step: 644/530, loss: 0.37997251749038696
2023-01-23 01:03:09.044712: step: 648/530, loss: 0.06310577690601349
2023-01-23 01:03:10.165551: step: 652/530, loss: 0.030410468578338623
2023-01-23 01:03:11.302096: step: 656/530, loss: 0.3537307679653168
2023-01-23 01:03:12.384614: step: 660/530, loss: 0.08765874058008194
2023-01-23 01:03:13.541633: step: 664/530, loss: 0.09160985797643661
2023-01-23 01:03:14.674809: step: 668/530, loss: 0.09218783676624298
2023-01-23 01:03:15.779679: step: 672/530, loss: 0.01848459243774414
2023-01-23 01:03:16.946903: step: 676/530, loss: 0.009665966033935547
2023-01-23 01:03:18.086418: step: 680/530, loss: 0.02227923832833767
2023-01-23 01:03:19.195728: step: 684/530, loss: 0.018256057053804398
2023-01-23 01:03:20.316794: step: 688/530, loss: 0.05286731943488121
2023-01-23 01:03:21.452687: step: 692/530, loss: 0.007831496186554432
2023-01-23 01:03:22.574268: step: 696/530, loss: 0.28025922179222107
2023-01-23 01:03:23.703218: step: 700/530, loss: 0.032499026507139206
2023-01-23 01:03:24.836443: step: 704/530, loss: 0.3166576027870178
2023-01-23 01:03:26.001871: step: 708/530, loss: 0.05491609498858452
2023-01-23 01:03:27.106544: step: 712/530, loss: 0.08305530995130539
2023-01-23 01:03:28.231537: step: 716/530, loss: 0.053624916821718216
2023-01-23 01:03:29.366384: step: 720/530, loss: 0.060971833765506744
2023-01-23 01:03:30.482835: step: 724/530, loss: 0.06447964161634445
2023-01-23 01:03:31.608280: step: 728/530, loss: 0.03336534649133682
2023-01-23 01:03:32.751166: step: 732/530, loss: 0.09625549614429474
2023-01-23 01:03:33.862583: step: 736/530, loss: 0.5622841119766235
2023-01-23 01:03:34.988671: step: 740/530, loss: 0.05314350128173828
2023-01-23 01:03:36.113064: step: 744/530, loss: 0.06232508644461632
2023-01-23 01:03:37.252803: step: 748/530, loss: 0.0464634895324707
2023-01-23 01:03:38.380401: step: 752/530, loss: 0.15146788954734802
2023-01-23 01:03:39.503576: step: 756/530, loss: 0.09412975609302521
2023-01-23 01:03:40.639005: step: 760/530, loss: 0.024077225476503372
2023-01-23 01:03:41.763808: step: 764/530, loss: 0.04605092853307724
2023-01-23 01:03:42.914256: step: 768/530, loss: 0.03228297084569931
2023-01-23 01:03:44.049036: step: 772/530, loss: 0.019731711596250534
2023-01-23 01:03:45.167569: step: 776/530, loss: 0.07025881111621857
2023-01-23 01:03:46.323339: step: 780/530, loss: 0.04610424116253853
2023-01-23 01:03:47.479742: step: 784/530, loss: 0.04086361080408096
2023-01-23 01:03:48.615502: step: 788/530, loss: 0.02827739715576172
2023-01-23 01:03:49.737765: step: 792/530, loss: 0.03472556918859482
2023-01-23 01:03:50.871835: step: 796/530, loss: 0.056482698768377304
2023-01-23 01:03:51.975828: step: 800/530, loss: 0.03596235811710358
2023-01-23 01:03:53.099773: step: 804/530, loss: 0.10903110355138779
2023-01-23 01:03:54.239717: step: 808/530, loss: 0.0865020751953125
2023-01-23 01:03:55.366687: step: 812/530, loss: 0.04447140917181969
2023-01-23 01:03:56.498931: step: 816/530, loss: 0.06706170737743378
2023-01-23 01:03:57.604981: step: 820/530, loss: 0.01953282207250595
2023-01-23 01:03:58.751499: step: 824/530, loss: 0.11724953353404999
2023-01-23 01:03:59.865132: step: 828/530, loss: 0.056803420186042786
2023-01-23 01:04:01.009755: step: 832/530, loss: 0.7149471640586853
2023-01-23 01:04:02.185347: step: 836/530, loss: 0.122760109603405
2023-01-23 01:04:03.302500: step: 840/530, loss: 0.014964200556278229
2023-01-23 01:04:04.460990: step: 844/530, loss: 0.05737876892089844
2023-01-23 01:04:05.570196: step: 848/530, loss: 0.0651622787117958
2023-01-23 01:04:06.703248: step: 852/530, loss: 0.13405953347682953
2023-01-23 01:04:07.805262: step: 856/530, loss: 0.07202019542455673
2023-01-23 01:04:08.965644: step: 860/530, loss: 0.09511547535657883
2023-01-23 01:04:10.072724: step: 864/530, loss: 0.06167984381318092
2023-01-23 01:04:11.180539: step: 868/530, loss: 0.14603640139102936
2023-01-23 01:04:12.340843: step: 872/530, loss: 0.10600428283214569
2023-01-23 01:04:13.477592: step: 876/530, loss: 0.03459315747022629
2023-01-23 01:04:14.602610: step: 880/530, loss: 0.047760773450136185
2023-01-23 01:04:15.715657: step: 884/530, loss: 0.07533969730138779
2023-01-23 01:04:16.859817: step: 888/530, loss: 0.07903270423412323
2023-01-23 01:04:17.981807: step: 892/530, loss: 0.03886070474982262
2023-01-23 01:04:19.125813: step: 896/530, loss: 0.0925288200378418
2023-01-23 01:04:20.265104: step: 900/530, loss: 0.027315188199281693
2023-01-23 01:04:21.391417: step: 904/530, loss: 0.06365995109081268
2023-01-23 01:04:22.560665: step: 908/530, loss: 0.05195145308971405
2023-01-23 01:04:23.720360: step: 912/530, loss: 0.09089546650648117
2023-01-23 01:04:24.881574: step: 916/530, loss: 0.11439648270606995
2023-01-23 01:04:26.007658: step: 920/530, loss: 0.026868630200624466
2023-01-23 01:04:27.130576: step: 924/530, loss: 0.05828814208507538
2023-01-23 01:04:28.254093: step: 928/530, loss: 0.21288034319877625
2023-01-23 01:04:29.385975: step: 932/530, loss: 0.060282520949840546
2023-01-23 01:04:30.507307: step: 936/530, loss: 0.025718022137880325
2023-01-23 01:04:31.619864: step: 940/530, loss: 0.03839864581823349
2023-01-23 01:04:32.735691: step: 944/530, loss: 0.10771417617797852
2023-01-23 01:04:33.877911: step: 948/530, loss: 0.013860464096069336
2023-01-23 01:04:35.003385: step: 952/530, loss: 0.018464185297489166
2023-01-23 01:04:36.124597: step: 956/530, loss: 0.0586027130484581
2023-01-23 01:04:37.263778: step: 960/530, loss: 0.03533783182501793
2023-01-23 01:04:38.385743: step: 964/530, loss: 0.0895792543888092
2023-01-23 01:04:39.521212: step: 968/530, loss: 0.02761068381369114
2023-01-23 01:04:40.690861: step: 972/530, loss: 6.560903549194336
2023-01-23 01:04:41.843310: step: 976/530, loss: 0.14062567055225372
2023-01-23 01:04:42.975773: step: 980/530, loss: 0.04823312908411026
2023-01-23 01:04:44.106186: step: 984/530, loss: 0.06727972626686096
2023-01-23 01:04:45.237096: step: 988/530, loss: 0.10017089545726776
2023-01-23 01:04:46.345765: step: 992/530, loss: 0.08516636490821838
2023-01-23 01:04:47.510001: step: 996/530, loss: 0.02323278784751892
2023-01-23 01:04:48.640222: step: 1000/530, loss: 0.8687888383865356
2023-01-23 01:04:49.725518: step: 1004/530, loss: 0.027425337582826614
2023-01-23 01:04:50.856618: step: 1008/530, loss: 0.05602312088012695
2023-01-23 01:04:51.969214: step: 1012/530, loss: 0.01217279490083456
2023-01-23 01:04:53.087442: step: 1016/530, loss: 0.08596086502075195
2023-01-23 01:04:54.201032: step: 1020/530, loss: 0.14333610236644745
2023-01-23 01:04:55.310513: step: 1024/530, loss: 0.16926316916942596
2023-01-23 01:04:56.416366: step: 1028/530, loss: 0.01046838704496622
2023-01-23 01:04:57.550235: step: 1032/530, loss: 0.03778515011072159
2023-01-23 01:04:58.656682: step: 1036/530, loss: 0.01136159896850586
2023-01-23 01:04:59.777509: step: 1040/530, loss: 0.02363138273358345
2023-01-23 01:05:00.912480: step: 1044/530, loss: 0.013595771975815296
2023-01-23 01:05:02.032218: step: 1048/530, loss: 0.03186054527759552
2023-01-23 01:05:03.179876: step: 1052/530, loss: 0.011513233184814453
2023-01-23 01:05:04.361540: step: 1056/530, loss: 0.02689356915652752
2023-01-23 01:05:05.483069: step: 1060/530, loss: 0.09482517838478088
2023-01-23 01:05:06.630996: step: 1064/530, loss: 0.12446188926696777
2023-01-23 01:05:07.751475: step: 1068/530, loss: 0.12660154700279236
2023-01-23 01:05:08.873149: step: 1072/530, loss: 0.10044154524803162
2023-01-23 01:05:10.004791: step: 1076/530, loss: 0.00036978721618652344
2023-01-23 01:05:11.119909: step: 1080/530, loss: 0.01193382777273655
2023-01-23 01:05:12.272593: step: 1084/530, loss: 0.09958532452583313
2023-01-23 01:05:13.417156: step: 1088/530, loss: 0.06786270439624786
2023-01-23 01:05:14.555546: step: 1092/530, loss: 0.0034145356621593237
2023-01-23 01:05:15.672992: step: 1096/530, loss: 0.07294435799121857
2023-01-23 01:05:16.809627: step: 1100/530, loss: 0.09617061913013458
2023-01-23 01:05:17.946361: step: 1104/530, loss: 0.07037369906902313
2023-01-23 01:05:19.059118: step: 1108/530, loss: 0.01848287507891655
2023-01-23 01:05:20.197691: step: 1112/530, loss: 0.07685699313879013
2023-01-23 01:05:21.340380: step: 1116/530, loss: 0.03291606903076172
2023-01-23 01:05:22.471811: step: 1120/530, loss: 0.08798322826623917
2023-01-23 01:05:23.608032: step: 1124/530, loss: 0.18928633630275726
2023-01-23 01:05:24.783984: step: 1128/530, loss: 0.03708620369434357
2023-01-23 01:05:25.909962: step: 1132/530, loss: 0.183427631855011
2023-01-23 01:05:27.053589: step: 1136/530, loss: 0.24276676774024963
2023-01-23 01:05:28.152854: step: 1140/530, loss: 0.028408052399754524
2023-01-23 01:05:29.272801: step: 1144/530, loss: 0.028786754235625267
2023-01-23 01:05:30.427350: step: 1148/530, loss: 0.2041950225830078
2023-01-23 01:05:31.532176: step: 1152/530, loss: 0.038805197924375534
2023-01-23 01:05:32.692169: step: 1156/530, loss: 0.05086822435259819
2023-01-23 01:05:33.822379: step: 1160/530, loss: 0.03743095323443413
2023-01-23 01:05:34.969095: step: 1164/530, loss: 0.024446584284305573
2023-01-23 01:05:36.076062: step: 1168/530, loss: 0.09873976558446884
2023-01-23 01:05:37.222791: step: 1172/530, loss: 0.04134741052985191
2023-01-23 01:05:38.383750: step: 1176/530, loss: 0.6849942207336426
2023-01-23 01:05:39.502094: step: 1180/530, loss: 0.13051578402519226
2023-01-23 01:05:40.658655: step: 1184/530, loss: 0.06943130493164062
2023-01-23 01:05:41.794817: step: 1188/530, loss: 0.04057817906141281
2023-01-23 01:05:42.946931: step: 1192/530, loss: 0.011747789569199085
2023-01-23 01:05:44.120753: step: 1196/530, loss: 0.4016820788383484
2023-01-23 01:05:45.248939: step: 1200/530, loss: 0.05502305179834366
2023-01-23 01:05:46.419247: step: 1204/530, loss: 0.02045278623700142
2023-01-23 01:05:47.541418: step: 1208/530, loss: 0.09430789947509766
2023-01-23 01:05:48.659658: step: 1212/530, loss: 0.07636761665344238
2023-01-23 01:05:49.771151: step: 1216/530, loss: 0.10635528713464737
2023-01-23 01:05:50.885589: step: 1220/530, loss: 0.010033512488007545
2023-01-23 01:05:52.001215: step: 1224/530, loss: 0.07806424796581268
2023-01-23 01:05:53.110838: step: 1228/530, loss: 0.008599281311035156
2023-01-23 01:05:54.227646: step: 1232/530, loss: 0.018236923962831497
2023-01-23 01:05:55.341620: step: 1236/530, loss: 0.08666108548641205
2023-01-23 01:05:56.474042: step: 1240/530, loss: 0.17101651430130005
2023-01-23 01:05:57.606679: step: 1244/530, loss: 0.08385143429040909
2023-01-23 01:05:58.759863: step: 1248/530, loss: 0.036004066467285156
2023-01-23 01:05:59.872404: step: 1252/530, loss: 0.04186706244945526
2023-01-23 01:06:01.026378: step: 1256/530, loss: 0.08961105346679688
2023-01-23 01:06:02.156662: step: 1260/530, loss: 0.029230643063783646
2023-01-23 01:06:03.286893: step: 1264/530, loss: 0.04703674465417862
2023-01-23 01:06:04.425426: step: 1268/530, loss: 0.522025465965271
2023-01-23 01:06:05.557755: step: 1272/530, loss: 0.1514565497636795
2023-01-23 01:06:06.685182: step: 1276/530, loss: 0.13386401534080505
2023-01-23 01:06:07.806873: step: 1280/530, loss: 0.17071080207824707
2023-01-23 01:06:08.939562: step: 1284/530, loss: 0.07503719627857208
2023-01-23 01:06:10.061901: step: 1288/530, loss: 0.5004467368125916
2023-01-23 01:06:11.191952: step: 1292/530, loss: 0.061617374420166016
2023-01-23 01:06:12.324261: step: 1296/530, loss: 0.10591130703687668
2023-01-23 01:06:13.458826: step: 1300/530, loss: 0.07752017676830292
2023-01-23 01:06:14.573163: step: 1304/530, loss: 0.011450815945863724
2023-01-23 01:06:15.695201: step: 1308/530, loss: 0.07293599098920822
2023-01-23 01:06:16.792318: step: 1312/530, loss: 0.04488656297326088
2023-01-23 01:06:17.928659: step: 1316/530, loss: 0.0789724811911583
2023-01-23 01:06:19.056060: step: 1320/530, loss: 0.027509786188602448
2023-01-23 01:06:20.184203: step: 1324/530, loss: 0.12159271538257599
2023-01-23 01:06:21.307181: step: 1328/530, loss: 0.03311128914356232
2023-01-23 01:06:22.461175: step: 1332/530, loss: 0.02288665808737278
2023-01-23 01:06:23.567602: step: 1336/530, loss: 0.10609426349401474
2023-01-23 01:06:24.687256: step: 1340/530, loss: 0.043726157397031784
2023-01-23 01:06:25.799706: step: 1344/530, loss: 0.006451750174164772
2023-01-23 01:06:26.914283: step: 1348/530, loss: 0.12351807951927185
2023-01-23 01:06:28.020026: step: 1352/530, loss: 0.16189061105251312
2023-01-23 01:06:29.133184: step: 1356/530, loss: 0.007510089781135321
2023-01-23 01:06:30.275895: step: 1360/530, loss: 0.04030637815594673
2023-01-23 01:06:31.416845: step: 1364/530, loss: 0.08193626254796982
2023-01-23 01:06:32.579871: step: 1368/530, loss: 0.1276511251926422
2023-01-23 01:06:33.713187: step: 1372/530, loss: 0.037912726402282715
2023-01-23 01:06:34.838820: step: 1376/530, loss: 0.06471309065818787
2023-01-23 01:06:35.983260: step: 1380/530, loss: 0.0040777684189379215
2023-01-23 01:06:37.097797: step: 1384/530, loss: 0.03407859802246094
2023-01-23 01:06:38.216489: step: 1388/530, loss: 0.09845371544361115
2023-01-23 01:06:39.342039: step: 1392/530, loss: 0.3267652690410614
2023-01-23 01:06:40.455616: step: 1396/530, loss: 0.11281280964612961
2023-01-23 01:06:41.584878: step: 1400/530, loss: 0.04188718646764755
2023-01-23 01:06:42.700419: step: 1404/530, loss: 0.49927303194999695
2023-01-23 01:06:43.839674: step: 1408/530, loss: 0.026709843426942825
2023-01-23 01:06:45.003851: step: 1412/530, loss: 0.1442207396030426
2023-01-23 01:06:46.116903: step: 1416/530, loss: 0.16683274507522583
2023-01-23 01:06:47.244712: step: 1420/530, loss: 0.014535332098603249
2023-01-23 01:06:48.329806: step: 1424/530, loss: 0.05050954967737198
2023-01-23 01:06:49.427316: step: 1428/530, loss: 0.06561928242444992
2023-01-23 01:06:50.582662: step: 1432/530, loss: 0.027131270617246628
2023-01-23 01:06:51.706541: step: 1436/530, loss: 0.011635875329375267
2023-01-23 01:06:52.825823: step: 1440/530, loss: 0.058353424072265625
2023-01-23 01:06:53.933101: step: 1444/530, loss: 0.06147165223956108
2023-01-23 01:06:55.047352: step: 1448/530, loss: 0.05459146574139595
2023-01-23 01:06:56.182855: step: 1452/530, loss: 0.063715361058712
2023-01-23 01:06:57.316328: step: 1456/530, loss: 0.025348853319883347
2023-01-23 01:06:58.407810: step: 1460/530, loss: 0.0006513595581054688
2023-01-23 01:06:59.539614: step: 1464/530, loss: 0.1258711814880371
2023-01-23 01:07:00.668051: step: 1468/530, loss: 0.06794948875904083
2023-01-23 01:07:01.788565: step: 1472/530, loss: 0.12003631889820099
2023-01-23 01:07:02.942243: step: 1476/530, loss: 0.1690683811903
2023-01-23 01:07:04.071554: step: 1480/530, loss: 0.017186546698212624
2023-01-23 01:07:05.217413: step: 1484/530, loss: 0.05246248468756676
2023-01-23 01:07:06.342952: step: 1488/530, loss: 0.053032875061035156
2023-01-23 01:07:07.460574: step: 1492/530, loss: 0.004847431555390358
2023-01-23 01:07:08.593376: step: 1496/530, loss: 0.06122569739818573
2023-01-23 01:07:09.699241: step: 1500/530, loss: 0.19184602797031403
2023-01-23 01:07:10.845888: step: 1504/530, loss: 0.07328452914953232
2023-01-23 01:07:11.955596: step: 1508/530, loss: 0.03860063850879669
2023-01-23 01:07:13.079028: step: 1512/530, loss: 0.07141876220703125
2023-01-23 01:07:14.215634: step: 1516/530, loss: 0.07593289017677307
2023-01-23 01:07:15.342692: step: 1520/530, loss: 0.18136702477931976
2023-01-23 01:07:16.460559: step: 1524/530, loss: 0.17930598556995392
2023-01-23 01:07:17.576236: step: 1528/530, loss: 0.0016337871784344316
2023-01-23 01:07:18.671389: step: 1532/530, loss: 0.0418432243168354
2023-01-23 01:07:19.808197: step: 1536/530, loss: 0.0071582794189453125
2023-01-23 01:07:20.934119: step: 1540/530, loss: 0.05998706817626953
2023-01-23 01:07:22.049251: step: 1544/530, loss: 0.0076999664306640625
2023-01-23 01:07:23.173743: step: 1548/530, loss: 0.025150299072265625
2023-01-23 01:07:24.310932: step: 1552/530, loss: 0.04065189138054848
2023-01-23 01:07:25.423620: step: 1556/530, loss: 0.09578075259923935
2023-01-23 01:07:26.572669: step: 1560/530, loss: 0.19159050285816193
2023-01-23 01:07:27.687627: step: 1564/530, loss: 0.1180192232131958
2023-01-23 01:07:28.809879: step: 1568/530, loss: 0.09115500003099442
2023-01-23 01:07:29.995903: step: 1572/530, loss: 0.2018662989139557
2023-01-23 01:07:31.126028: step: 1576/530, loss: 0.011330699548125267
2023-01-23 01:07:32.255272: step: 1580/530, loss: 0.03448767587542534
2023-01-23 01:07:33.380554: step: 1584/530, loss: 0.05008220672607422
2023-01-23 01:07:34.532753: step: 1588/530, loss: 0.10126900672912598
2023-01-23 01:07:35.665817: step: 1592/530, loss: 0.056223392486572266
2023-01-23 01:07:36.788891: step: 1596/530, loss: 0.11051645874977112
2023-01-23 01:07:37.940096: step: 1600/530, loss: 0.09102821350097656
2023-01-23 01:07:39.066595: step: 1604/530, loss: 0.16616077721118927
2023-01-23 01:07:40.213864: step: 1608/530, loss: 0.09570388495922089
2023-01-23 01:07:41.306757: step: 1612/530, loss: 0.00036115647526457906
2023-01-23 01:07:42.418960: step: 1616/530, loss: 0.06224660947918892
2023-01-23 01:07:43.532054: step: 1620/530, loss: 0.07185105979442596
2023-01-23 01:07:44.631817: step: 1624/530, loss: 0.06093177944421768
2023-01-23 01:07:45.737205: step: 1628/530, loss: 0.10062961280345917
2023-01-23 01:07:46.826884: step: 1632/530, loss: 0.0170472152531147
2023-01-23 01:07:47.937793: step: 1636/530, loss: 0.5759602785110474
2023-01-23 01:07:49.047413: step: 1640/530, loss: 0.07380161434412003
2023-01-23 01:07:50.179389: step: 1644/530, loss: 0.1147991195321083
2023-01-23 01:07:51.308990: step: 1648/530, loss: 0.09085425734519958
2023-01-23 01:07:52.445514: step: 1652/530, loss: 0.04240245744585991
2023-01-23 01:07:53.568233: step: 1656/530, loss: 0.032878972589969635
2023-01-23 01:07:54.708568: step: 1660/530, loss: 0.11079893261194229
2023-01-23 01:07:55.848255: step: 1664/530, loss: 0.4983340799808502
2023-01-23 01:07:56.983868: step: 1668/530, loss: 0.1105494499206543
2023-01-23 01:07:58.100283: step: 1672/530, loss: 0.10265432298183441
2023-01-23 01:07:59.221709: step: 1676/530, loss: 0.33097267150878906
2023-01-23 01:08:00.335829: step: 1680/530, loss: 0.00038557054358534515
2023-01-23 01:08:01.469392: step: 1684/530, loss: 0.014426374807953835
2023-01-23 01:08:02.617521: step: 1688/530, loss: 0.022704387083649635
2023-01-23 01:08:03.750720: step: 1692/530, loss: 0.1082952469587326
2023-01-23 01:08:04.854185: step: 1696/530, loss: 0.06152687221765518
2023-01-23 01:08:05.982387: step: 1700/530, loss: 0.01396484300494194
2023-01-23 01:08:07.130959: step: 1704/530, loss: 0.13204509019851685
2023-01-23 01:08:08.235437: step: 1708/530, loss: 0.16111384332180023
2023-01-23 01:08:09.394738: step: 1712/530, loss: 0.07105598598718643
2023-01-23 01:08:10.527175: step: 1716/530, loss: 0.044014930725097656
2023-01-23 01:08:11.658136: step: 1720/530, loss: 0.07751598209142685
2023-01-23 01:08:12.783291: step: 1724/530, loss: 0.013644028455018997
2023-01-23 01:08:13.902458: step: 1728/530, loss: 0.4771810472011566
2023-01-23 01:08:15.041331: step: 1732/530, loss: 0.08296814560890198
2023-01-23 01:08:16.161514: step: 1736/530, loss: 0.20678111910820007
2023-01-23 01:08:17.275272: step: 1740/530, loss: 0.08969905972480774
2023-01-23 01:08:18.400536: step: 1744/530, loss: 0.020624350756406784
2023-01-23 01:08:19.529983: step: 1748/530, loss: 0.18946728110313416
2023-01-23 01:08:20.649823: step: 1752/530, loss: 0.01571216620504856
2023-01-23 01:08:21.762893: step: 1756/530, loss: 0.07748472690582275
2023-01-23 01:08:22.878207: step: 1760/530, loss: 0.1304752379655838
2023-01-23 01:08:24.028853: step: 1764/530, loss: 0.020856570452451706
2023-01-23 01:08:25.168095: step: 1768/530, loss: 0.008144760504364967
2023-01-23 01:08:26.277070: step: 1772/530, loss: 0.1670517921447754
2023-01-23 01:08:27.370917: step: 1776/530, loss: 0.04218435287475586
2023-01-23 01:08:28.500888: step: 1780/530, loss: 0.09137530624866486
2023-01-23 01:08:29.643225: step: 1784/530, loss: 0.2485300600528717
2023-01-23 01:08:30.795977: step: 1788/530, loss: 0.12017574906349182
2023-01-23 01:08:31.884529: step: 1792/530, loss: 0.21962089836597443
2023-01-23 01:08:33.038421: step: 1796/530, loss: 0.004981517791748047
2023-01-23 01:08:34.145283: step: 1800/530, loss: 0.199933260679245
2023-01-23 01:08:35.293370: step: 1804/530, loss: 0.04714103043079376
2023-01-23 01:08:36.459581: step: 1808/530, loss: 0.004731369204819202
2023-01-23 01:08:37.579122: step: 1812/530, loss: 0.0011181235313415527
2023-01-23 01:08:38.705005: step: 1816/530, loss: 0.07350564002990723
2023-01-23 01:08:39.805955: step: 1820/530, loss: 0.41598719358444214
2023-01-23 01:08:40.912483: step: 1824/530, loss: 0.06858482211828232
2023-01-23 01:08:42.014970: step: 1828/530, loss: 0.1664014756679535
2023-01-23 01:08:43.128537: step: 1832/530, loss: 0.06379032135009766
2023-01-23 01:08:44.250715: step: 1836/530, loss: 0.12418480217456818
2023-01-23 01:08:45.408397: step: 1840/530, loss: 0.14654946327209473
2023-01-23 01:08:46.533410: step: 1844/530, loss: 0.037153054028749466
2023-01-23 01:08:47.644857: step: 1848/530, loss: 0.08995561301708221
2023-01-23 01:08:48.768802: step: 1852/530, loss: 0.06575407832860947
2023-01-23 01:08:49.905684: step: 1856/530, loss: 0.10117187350988388
2023-01-23 01:08:51.078717: step: 1860/530, loss: 0.24815022945404053
2023-01-23 01:08:52.194790: step: 1864/530, loss: 0.010378074832260609
2023-01-23 01:08:53.320122: step: 1868/530, loss: 0.08951392024755478
2023-01-23 01:08:54.457020: step: 1872/530, loss: 0.07183942943811417
2023-01-23 01:08:55.573298: step: 1876/530, loss: 0.061238862574100494
2023-01-23 01:08:56.688285: step: 1880/530, loss: 0.09973859786987305
2023-01-23 01:08:57.800427: step: 1884/530, loss: 0.04124307632446289
2023-01-23 01:08:58.928876: step: 1888/530, loss: 0.09564247727394104
2023-01-23 01:09:00.030967: step: 1892/530, loss: 0.013436890207231045
2023-01-23 01:09:01.167388: step: 1896/530, loss: 0.049610041081905365
2023-01-23 01:09:02.323398: step: 1900/530, loss: 0.12335586547851562
2023-01-23 01:09:03.435100: step: 1904/530, loss: 0.014607524499297142
2023-01-23 01:09:04.550750: step: 1908/530, loss: 0.15633372962474823
2023-01-23 01:09:05.644038: step: 1912/530, loss: 0.04107208177447319
2023-01-23 01:09:06.777060: step: 1916/530, loss: 0.03873138502240181
2023-01-23 01:09:07.911879: step: 1920/530, loss: 0.0539851188659668
2023-01-23 01:09:09.022581: step: 1924/530, loss: 0.9264144897460938
2023-01-23 01:09:10.150802: step: 1928/530, loss: 0.10763807594776154
2023-01-23 01:09:11.297343: step: 1932/530, loss: 0.05523405224084854
2023-01-23 01:09:12.442586: step: 1936/530, loss: 0.0531252846121788
2023-01-23 01:09:13.596302: step: 1940/530, loss: 0.1844370812177658
2023-01-23 01:09:14.700041: step: 1944/530, loss: 0.03949160501360893
2023-01-23 01:09:15.823083: step: 1948/530, loss: 0.027771569788455963
2023-01-23 01:09:16.953257: step: 1952/530, loss: 0.017905663698911667
2023-01-23 01:09:18.075137: step: 1956/530, loss: 0.010768735781311989
2023-01-23 01:09:19.165040: step: 1960/530, loss: 0.00064849853515625
2023-01-23 01:09:20.278775: step: 1964/530, loss: 0.08890162408351898
2023-01-23 01:09:21.438318: step: 1968/530, loss: 0.051820896565914154
2023-01-23 01:09:22.582999: step: 1972/530, loss: 0.015370655804872513
2023-01-23 01:09:23.743274: step: 1976/530, loss: 0.1209191381931305
2023-01-23 01:09:24.895735: step: 1980/530, loss: 0.09295487403869629
2023-01-23 01:09:26.021323: step: 1984/530, loss: 0.20483312010765076
2023-01-23 01:09:27.158572: step: 1988/530, loss: 0.19505666196346283
2023-01-23 01:09:28.339264: step: 1992/530, loss: 0.08865413069725037
2023-01-23 01:09:29.474748: step: 1996/530, loss: 0.19149601459503174
2023-01-23 01:09:30.615694: step: 2000/530, loss: 0.14197130501270294
2023-01-23 01:09:31.758648: step: 2004/530, loss: 0.05966319888830185
2023-01-23 01:09:32.894416: step: 2008/530, loss: 0.041666317731142044
2023-01-23 01:09:34.016975: step: 2012/530, loss: 0.08533763885498047
2023-01-23 01:09:35.151683: step: 2016/530, loss: 0.2117973417043686
2023-01-23 01:09:36.288395: step: 2020/530, loss: 0.02915506437420845
2023-01-23 01:09:37.441832: step: 2024/530, loss: 0.14061832427978516
2023-01-23 01:09:38.572931: step: 2028/530, loss: 0.1348496377468109
2023-01-23 01:09:39.692466: step: 2032/530, loss: 0.005411624908447266
2023-01-23 01:09:40.845991: step: 2036/530, loss: 0.02037353441119194
2023-01-23 01:09:41.948486: step: 2040/530, loss: 0.04704036936163902
2023-01-23 01:09:43.064128: step: 2044/530, loss: 0.012836170382797718
2023-01-23 01:09:44.178974: step: 2048/530, loss: 0.07903461903333664
2023-01-23 01:09:45.306525: step: 2052/530, loss: 0.09906673431396484
2023-01-23 01:09:46.425183: step: 2056/530, loss: 0.02335362508893013
2023-01-23 01:09:47.544972: step: 2060/530, loss: 0.015564728528261185
2023-01-23 01:09:48.680448: step: 2064/530, loss: 0.015874575823545456
2023-01-23 01:09:49.775936: step: 2068/530, loss: 0.030770661309361458
2023-01-23 01:09:50.888733: step: 2072/530, loss: 0.04608564451336861
2023-01-23 01:09:52.012989: step: 2076/530, loss: 0.015005970373749733
2023-01-23 01:09:53.165241: step: 2080/530, loss: 0.05450630187988281
2023-01-23 01:09:54.316165: step: 2084/530, loss: 0.11551046371459961
2023-01-23 01:09:55.443261: step: 2088/530, loss: 0.16853152215480804
2023-01-23 01:09:56.586962: step: 2092/530, loss: 0.12096138298511505
2023-01-23 01:09:57.670926: step: 2096/530, loss: 0.02918987348675728
2023-01-23 01:09:58.762726: step: 2100/530, loss: 0.0818575918674469
2023-01-23 01:09:59.892069: step: 2104/530, loss: 0.013566303066909313
2023-01-23 01:10:01.003940: step: 2108/530, loss: 0.16752614080905914
2023-01-23 01:10:02.156797: step: 2112/530, loss: 0.024146415293216705
2023-01-23 01:10:03.290768: step: 2116/530, loss: 0.04718070104718208
2023-01-23 01:10:04.400952: step: 2120/530, loss: 0.10455741733312607
==================================================
Loss: 0.115
--------------------
Dev: {'event': {'p': 0.5877016129032258, 'r': 0.7762982689747004, 'f1': 0.6689615605278255}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Test: {'event': {'p': 0.6539923954372624, 'r': 0.7862857142857143, 'f1': 0.7140633108458745}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Chinese: {'event': {'p': 0.5604395604395604, 'r': 0.9444444444444444, 'f1': 0.7034482758620689}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Korean: {'event': {'p': 0.6666666666666666, 'r': 0.6349206349206349, 'f1': 0.6504065040650407}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
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': 9}
New best korean model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Chinese: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Chinese: {'event': {'p': 0.6190476190476191, 'r': 0.9629629629629629, 'f1': 0.7536231884057971}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5877016129032258, 'r': 0.7762982689747004, 'f1': 0.6689615605278255}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Korean: {'event': {'p': 0.6539923954372624, 'r': 0.7862857142857143, 'f1': 0.7140633108458745}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Korean: {'event': {'p': 0.6666666666666666, 'r': 0.6349206349206349, 'f1': 0.6504065040650407}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5319148936170213, 'r': 0.6944444444444444, 'f1': 0.6024096385542169}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
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 01:10:53.825739: step: 4/530, loss: 0.10765113681554794
2023-01-23 01:10:54.948517: step: 8/530, loss: 0.039498232305049896
2023-01-23 01:10:56.095301: step: 12/530, loss: 0.02771434746682644
2023-01-23 01:10:57.208204: step: 16/530, loss: 0.08857274055480957
2023-01-23 01:10:58.308371: step: 20/530, loss: 0.08839455246925354
2023-01-23 01:10:59.442861: step: 24/530, loss: 0.031239032745361328
2023-01-23 01:11:00.555661: step: 28/530, loss: 0.011895323172211647
2023-01-23 01:11:01.665161: step: 32/530, loss: 0.03530006483197212
2023-01-23 01:11:02.779007: step: 36/530, loss: 0.044904425740242004
2023-01-23 01:11:03.903960: step: 40/530, loss: 0.42820852994918823
2023-01-23 01:11:05.029752: step: 44/530, loss: 0.04303331300616264
2023-01-23 01:11:06.129870: step: 48/530, loss: 0.02294302172958851
2023-01-23 01:11:07.210609: step: 52/530, loss: 0.03592471405863762
2023-01-23 01:11:08.325212: step: 56/530, loss: 0.04403352737426758
2023-01-23 01:11:09.416397: step: 60/530, loss: 0.08497639000415802
2023-01-23 01:11:10.556006: step: 64/530, loss: 0.14726601541042328
2023-01-23 01:11:11.694931: step: 68/530, loss: 0.05775437504053116
2023-01-23 01:11:12.821406: step: 72/530, loss: 0.024156952276825905
2023-01-23 01:11:13.983574: step: 76/530, loss: 0.11047402024269104
2023-01-23 01:11:15.121514: step: 80/530, loss: 0.11057644337415695
2023-01-23 01:11:16.239168: step: 84/530, loss: 0.05052890628576279
2023-01-23 01:11:17.356057: step: 88/530, loss: 0.049050286412239075
2023-01-23 01:11:18.495825: step: 92/530, loss: 0.01645517349243164
2023-01-23 01:11:19.622611: step: 96/530, loss: 0.09989142417907715
2023-01-23 01:11:20.715886: step: 100/530, loss: 0.01087045669555664
2023-01-23 01:11:21.835925: step: 104/530, loss: 0.02903604507446289
2023-01-23 01:11:22.952108: step: 108/530, loss: 0.17633160948753357
2023-01-23 01:11:24.077119: step: 112/530, loss: 0.01232614554464817
2023-01-23 01:11:25.179666: step: 116/530, loss: 0.01432571467012167
2023-01-23 01:11:26.312844: step: 120/530, loss: 0.04102649912238121
2023-01-23 01:11:27.439923: step: 124/530, loss: 0.07410211861133575
2023-01-23 01:11:28.588572: step: 128/530, loss: 0.22276869416236877
2023-01-23 01:11:29.705261: step: 132/530, loss: 0.01596832275390625
2023-01-23 01:11:30.816446: step: 136/530, loss: 0.06610021740198135
2023-01-23 01:11:31.945497: step: 140/530, loss: 0.05329170823097229
2023-01-23 01:11:33.104042: step: 144/530, loss: 0.019696855917572975
2023-01-23 01:11:34.245304: step: 148/530, loss: 0.26527518033981323
2023-01-23 01:11:35.379673: step: 152/530, loss: 0.10803528130054474
2023-01-23 01:11:36.504257: step: 156/530, loss: 0.07411766052246094
2023-01-23 01:11:37.635558: step: 160/530, loss: 0.045439720153808594
2023-01-23 01:11:38.769842: step: 164/530, loss: 0.3324577808380127
2023-01-23 01:11:39.914420: step: 168/530, loss: 0.062174275517463684
2023-01-23 01:11:41.054117: step: 172/530, loss: 0.018614387139678
2023-01-23 01:11:42.167989: step: 176/530, loss: 0.04056167975068092
2023-01-23 01:11:43.322623: step: 180/530, loss: 0.12621356546878815
2023-01-23 01:11:44.456860: step: 184/530, loss: 0.12509211897850037
2023-01-23 01:11:45.584653: step: 188/530, loss: 0.0927850753068924
2023-01-23 01:11:46.741902: step: 192/530, loss: 0.07804946601390839
2023-01-23 01:11:47.887546: step: 196/530, loss: 0.10279674828052521
2023-01-23 01:11:49.017554: step: 200/530, loss: 0.08590393513441086
2023-01-23 01:11:50.129224: step: 204/530, loss: 0.023784827440977097
2023-01-23 01:11:51.257169: step: 208/530, loss: 0.05802679434418678
2023-01-23 01:11:52.402134: step: 212/530, loss: 0.0005128383636474609
2023-01-23 01:11:53.514230: step: 216/530, loss: 0.05874624103307724
2023-01-23 01:11:54.622606: step: 220/530, loss: 0.02341618575155735
2023-01-23 01:11:55.729076: step: 224/530, loss: 0.05245189741253853
2023-01-23 01:11:56.863802: step: 228/530, loss: 0.08626270294189453
2023-01-23 01:11:57.970064: step: 232/530, loss: 0.2873474061489105
2023-01-23 01:11:59.082938: step: 236/530, loss: 0.01621522754430771
2023-01-23 01:12:00.223475: step: 240/530, loss: 0.1179172545671463
2023-01-23 01:12:01.344769: step: 244/530, loss: 0.00968389492481947
2023-01-23 01:12:02.474697: step: 248/530, loss: 0.05039501190185547
2023-01-23 01:12:03.593649: step: 252/530, loss: 0.022718237712979317
2023-01-23 01:12:04.728537: step: 256/530, loss: 0.027546310797333717
2023-01-23 01:12:05.841878: step: 260/530, loss: 0.03861560672521591
2023-01-23 01:12:06.959542: step: 264/530, loss: 0.04481859132647514
2023-01-23 01:12:08.109765: step: 268/530, loss: 0.0638696700334549
2023-01-23 01:12:09.261164: step: 272/530, loss: 0.05806942284107208
2023-01-23 01:12:10.394843: step: 276/530, loss: 0.023115921765565872
2023-01-23 01:12:11.503131: step: 280/530, loss: 0.02539529837667942
2023-01-23 01:12:12.618853: step: 284/530, loss: 0.14105892181396484
2023-01-23 01:12:13.767215: step: 288/530, loss: 0.015781689435243607
2023-01-23 01:12:14.919666: step: 292/530, loss: 0.010963821783661842
2023-01-23 01:12:16.062566: step: 296/530, loss: 0.12178449332714081
2023-01-23 01:12:17.188834: step: 300/530, loss: 0.028708267956972122
2023-01-23 01:12:18.305271: step: 304/530, loss: 0.08935517817735672
2023-01-23 01:12:19.448758: step: 308/530, loss: 0.06159505993127823
2023-01-23 01:12:20.585886: step: 312/530, loss: 0.013109494000673294
2023-01-23 01:12:21.705655: step: 316/530, loss: 0.1577167510986328
2023-01-23 01:12:22.838445: step: 320/530, loss: 0.041231490671634674
2023-01-23 01:12:23.970695: step: 324/530, loss: 1.474432349205017
2023-01-23 01:12:25.089850: step: 328/530, loss: 0.05310077965259552
2023-01-23 01:12:26.277789: step: 332/530, loss: 0.011202669702470303
2023-01-23 01:12:27.367490: step: 336/530, loss: 0.10677547752857208
2023-01-23 01:12:28.508814: step: 340/530, loss: 0.12843990325927734
2023-01-23 01:12:29.645861: step: 344/530, loss: 0.0025238990783691406
2023-01-23 01:12:30.747517: step: 348/530, loss: 0.028189469128847122
2023-01-23 01:12:31.855759: step: 352/530, loss: 0.03873257711529732
2023-01-23 01:12:32.970792: step: 356/530, loss: 0.0664127916097641
2023-01-23 01:12:34.098518: step: 360/530, loss: 0.052901364862918854
2023-01-23 01:12:35.231717: step: 364/530, loss: 0.042401909828186035
2023-01-23 01:12:36.372287: step: 368/530, loss: 0.016837596893310547
2023-01-23 01:12:37.519292: step: 372/530, loss: 0.07129593193531036
2023-01-23 01:12:38.683048: step: 376/530, loss: 0.014962482266128063
2023-01-23 01:12:39.823677: step: 380/530, loss: 0.06429004669189453
2023-01-23 01:12:40.939940: step: 384/530, loss: 0.00642662076279521
2023-01-23 01:12:42.059614: step: 388/530, loss: 0.16434498131275177
2023-01-23 01:12:43.201108: step: 392/530, loss: 0.05184169113636017
2023-01-23 01:12:44.324255: step: 396/530, loss: 0.046453237533569336
2023-01-23 01:12:45.437174: step: 400/530, loss: 0.024739742279052734
2023-01-23 01:12:46.561823: step: 404/530, loss: 0.0801876112818718
2023-01-23 01:12:47.690464: step: 408/530, loss: 0.03692302852869034
2023-01-23 01:12:48.821776: step: 412/530, loss: 0.058938123285770416
2023-01-23 01:12:49.986648: step: 416/530, loss: 0.07724404335021973
2023-01-23 01:12:51.170424: step: 420/530, loss: 0.07342529296875
2023-01-23 01:12:52.268356: step: 424/530, loss: 0.02885305881500244
2023-01-23 01:12:53.414889: step: 428/530, loss: 0.1588561087846756
2023-01-23 01:12:54.528361: step: 432/530, loss: 0.17054371535778046
2023-01-23 01:12:55.668008: step: 436/530, loss: 0.08053378760814667
2023-01-23 01:12:56.778005: step: 440/530, loss: 0.7874759435653687
2023-01-23 01:12:57.895053: step: 444/530, loss: 0.011628913693130016
2023-01-23 01:12:59.028499: step: 448/530, loss: 0.018297767266631126
2023-01-23 01:13:00.144284: step: 452/530, loss: 0.021543312817811966
2023-01-23 01:13:01.271016: step: 456/530, loss: 0.005405521485954523
2023-01-23 01:13:02.419312: step: 460/530, loss: 0.16249045729637146
2023-01-23 01:13:03.544826: step: 464/530, loss: 0.02071523666381836
2023-01-23 01:13:04.657038: step: 468/530, loss: 0.1479371041059494
2023-01-23 01:13:05.811945: step: 472/530, loss: 0.6006187200546265
2023-01-23 01:13:06.912992: step: 476/530, loss: 0.08663597702980042
2023-01-23 01:13:08.015095: step: 480/530, loss: 0.11022194474935532
2023-01-23 01:13:09.131259: step: 484/530, loss: 0.07298507541418076
2023-01-23 01:13:10.275945: step: 488/530, loss: 0.22021742165088654
2023-01-23 01:13:11.391963: step: 492/530, loss: 0.11701764911413193
2023-01-23 01:13:12.537975: step: 496/530, loss: 0.25930604338645935
2023-01-23 01:13:13.653187: step: 500/530, loss: 0.09067802876234055
2023-01-23 01:13:14.798896: step: 504/530, loss: 0.008562088012695312
2023-01-23 01:13:15.957847: step: 508/530, loss: 0.027094651013612747
2023-01-23 01:13:17.073909: step: 512/530, loss: 0.1402035653591156
2023-01-23 01:13:18.191293: step: 516/530, loss: 0.02455282211303711
2023-01-23 01:13:19.304184: step: 520/530, loss: 0.07938452064990997
2023-01-23 01:13:20.441668: step: 524/530, loss: 0.07965602725744247
2023-01-23 01:13:21.577274: step: 528/530, loss: 0.018642330542206764
2023-01-23 01:13:22.732047: step: 532/530, loss: 0.10618558526039124
2023-01-23 01:13:23.877319: step: 536/530, loss: 0.028895283117890358
2023-01-23 01:13:25.040021: step: 540/530, loss: 0.026750946417450905
2023-01-23 01:13:26.171608: step: 544/530, loss: 0.024262618273496628
2023-01-23 01:13:27.297299: step: 548/530, loss: 0.003574943635612726
2023-01-23 01:13:28.411944: step: 552/530, loss: 0.05119892582297325
2023-01-23 01:13:29.552784: step: 556/530, loss: 0.35329532623291016
2023-01-23 01:13:30.701339: step: 560/530, loss: 0.10245752334594727
2023-01-23 01:13:31.820684: step: 564/530, loss: 0.07935552299022675
2023-01-23 01:13:32.953965: step: 568/530, loss: 0.08759871125221252
2023-01-23 01:13:34.048402: step: 572/530, loss: 0.058500003069639206
2023-01-23 01:13:35.156402: step: 576/530, loss: 0.020183134824037552
2023-01-23 01:13:36.264187: step: 580/530, loss: 0.036687564104795456
2023-01-23 01:13:37.392820: step: 584/530, loss: 0.035057827830314636
2023-01-23 01:13:38.534701: step: 588/530, loss: 0.05998945236206055
2023-01-23 01:13:39.677272: step: 592/530, loss: 0.004501724615693092
2023-01-23 01:13:40.816048: step: 596/530, loss: 0.013484383001923561
2023-01-23 01:13:41.923766: step: 600/530, loss: 0.011657047085464
2023-01-23 01:13:43.015874: step: 604/530, loss: 0.014903879724442959
2023-01-23 01:13:44.132309: step: 608/530, loss: 0.060456182807683945
2023-01-23 01:13:45.251852: step: 612/530, loss: 0.08970329165458679
2023-01-23 01:13:46.356836: step: 616/530, loss: 0.07361546158790588
2023-01-23 01:13:47.494500: step: 620/530, loss: 0.07196168601512909
2023-01-23 01:13:48.639618: step: 624/530, loss: 0.010826683603227139
2023-01-23 01:13:49.757677: step: 628/530, loss: 0.42353326082229614
2023-01-23 01:13:50.865011: step: 632/530, loss: 0.01778816059231758
2023-01-23 01:13:52.025949: step: 636/530, loss: 0.05257253721356392
2023-01-23 01:13:53.153395: step: 640/530, loss: 0.022453976795077324
2023-01-23 01:13:54.258742: step: 644/530, loss: 0.025582171976566315
2023-01-23 01:13:55.365832: step: 648/530, loss: 0.006249523255974054
2023-01-23 01:13:56.488190: step: 652/530, loss: 0.0723206102848053
2023-01-23 01:13:57.614633: step: 656/530, loss: 0.00969839096069336
2023-01-23 01:13:58.758868: step: 660/530, loss: 0.040892697870731354
2023-01-23 01:13:59.891973: step: 664/530, loss: 0.07451563328504562
2023-01-23 01:14:00.996938: step: 668/530, loss: 0.11151543259620667
2023-01-23 01:14:02.146477: step: 672/530, loss: 0.033945560455322266
2023-01-23 01:14:03.253634: step: 676/530, loss: 0.05096454918384552
2023-01-23 01:14:04.378643: step: 680/530, loss: 0.16975107789039612
2023-01-23 01:14:05.471958: step: 684/530, loss: 0.0540614128112793
2023-01-23 01:14:06.575299: step: 688/530, loss: 0.03207254409790039
2023-01-23 01:14:07.693319: step: 692/530, loss: 0.10302925109863281
2023-01-23 01:14:08.826005: step: 696/530, loss: 0.05581269413232803
2023-01-23 01:14:09.956083: step: 700/530, loss: 0.07609835267066956
2023-01-23 01:14:11.058605: step: 704/530, loss: 0.011246967129409313
2023-01-23 01:14:12.176865: step: 708/530, loss: 0.09025593101978302
2023-01-23 01:14:13.320261: step: 712/530, loss: 0.039476778358221054
2023-01-23 01:14:14.427878: step: 716/530, loss: 0.031519606709480286
2023-01-23 01:14:15.535887: step: 720/530, loss: 0.032343242317438126
2023-01-23 01:14:16.652743: step: 724/530, loss: 0.04513416439294815
2023-01-23 01:14:17.793806: step: 728/530, loss: 0.060396961867809296
2023-01-23 01:14:18.923288: step: 732/530, loss: 0.12892360985279083
2023-01-23 01:14:20.031992: step: 736/530, loss: 0.04455604404211044
2023-01-23 01:14:21.139764: step: 740/530, loss: 0.016609765589237213
2023-01-23 01:14:22.254686: step: 744/530, loss: 0.039734650403261185
2023-01-23 01:14:23.375870: step: 748/530, loss: 0.04650592803955078
2023-01-23 01:14:24.514201: step: 752/530, loss: 0.04336996003985405
2023-01-23 01:14:25.632064: step: 756/530, loss: 0.08165951073169708
2023-01-23 01:14:26.722620: step: 760/530, loss: 0.24136991798877716
2023-01-23 01:14:27.872289: step: 764/530, loss: 0.013903426937758923
2023-01-23 01:14:29.012683: step: 768/530, loss: 0.012473011389374733
2023-01-23 01:14:30.132443: step: 772/530, loss: 0.033951569348573685
2023-01-23 01:14:31.245336: step: 776/530, loss: 0.256072998046875
2023-01-23 01:14:32.363663: step: 780/530, loss: 0.03144855424761772
2023-01-23 01:14:33.460484: step: 784/530, loss: 0.06555668264627457
2023-01-23 01:14:34.583647: step: 788/530, loss: 0.1716821938753128
2023-01-23 01:14:35.730196: step: 792/530, loss: 0.1999543160200119
2023-01-23 01:14:36.864044: step: 796/530, loss: 0.18226367235183716
2023-01-23 01:14:37.992473: step: 800/530, loss: 0.0015272140735760331
2023-01-23 01:14:39.094219: step: 804/530, loss: 0.01624884642660618
2023-01-23 01:14:40.246235: step: 808/530, loss: 0.11577749252319336
2023-01-23 01:14:41.398284: step: 812/530, loss: 0.05146780237555504
2023-01-23 01:14:42.510527: step: 816/530, loss: 0.4820139408111572
2023-01-23 01:14:43.633094: step: 820/530, loss: 0.07320301234722137
2023-01-23 01:14:44.756832: step: 824/530, loss: 0.1259758025407791
2023-01-23 01:14:45.857858: step: 828/530, loss: 0.08337679505348206
2023-01-23 01:14:46.984460: step: 832/530, loss: 0.10451727360486984
2023-01-23 01:14:48.100950: step: 836/530, loss: 0.03495025634765625
2023-01-23 01:14:49.234137: step: 840/530, loss: 0.01575026474893093
2023-01-23 01:14:50.356487: step: 844/530, loss: 0.03577547147870064
2023-01-23 01:14:51.470219: step: 848/530, loss: 0.04008970409631729
2023-01-23 01:14:52.619935: step: 852/530, loss: 0.12645407021045685
2023-01-23 01:14:53.719939: step: 856/530, loss: 0.10761023312807083
2023-01-23 01:14:54.858184: step: 860/530, loss: 0.02683563157916069
2023-01-23 01:14:55.974656: step: 864/530, loss: 0.0854131281375885
2023-01-23 01:14:57.099874: step: 868/530, loss: 0.011182595044374466
2023-01-23 01:14:58.215552: step: 872/530, loss: 0.09581577777862549
2023-01-23 01:14:59.335633: step: 876/530, loss: 0.04635629802942276
2023-01-23 01:15:00.456150: step: 880/530, loss: 0.2457302063703537
2023-01-23 01:15:01.579471: step: 884/530, loss: 0.12046680599451065
2023-01-23 01:15:02.712493: step: 888/530, loss: 0.06635294109582901
2023-01-23 01:15:03.832377: step: 892/530, loss: 0.012544631958007812
2023-01-23 01:15:04.932033: step: 896/530, loss: 0.03818855434656143
2023-01-23 01:15:06.038881: step: 900/530, loss: 0.04055233299732208
2023-01-23 01:15:07.145752: step: 904/530, loss: 0.07662753760814667
2023-01-23 01:15:08.304879: step: 908/530, loss: 0.12469349056482315
2023-01-23 01:15:09.438084: step: 912/530, loss: 0.0028290273621678352
2023-01-23 01:15:10.566924: step: 916/530, loss: 0.04923210293054581
2023-01-23 01:15:11.719652: step: 920/530, loss: 0.10410775989294052
2023-01-23 01:15:12.884568: step: 924/530, loss: 0.1359046995639801
2023-01-23 01:15:14.020950: step: 928/530, loss: 0.07372274994850159
2023-01-23 01:15:15.124654: step: 932/530, loss: 0.09040529280900955
2023-01-23 01:15:16.253956: step: 936/530, loss: 0.11561093479394913
2023-01-23 01:15:17.376795: step: 940/530, loss: 0.27289941906929016
2023-01-23 01:15:18.511537: step: 944/530, loss: 0.02662224881350994
2023-01-23 01:15:19.631318: step: 948/530, loss: 0.056172944605350494
2023-01-23 01:15:20.736846: step: 952/530, loss: 0.035030364990234375
2023-01-23 01:15:21.848905: step: 956/530, loss: 0.01123189926147461
2023-01-23 01:15:22.959725: step: 960/530, loss: 0.054741762578487396
2023-01-23 01:15:24.104552: step: 964/530, loss: 0.05325598642230034
2023-01-23 01:15:25.226749: step: 968/530, loss: 0.13110850751399994
2023-01-23 01:15:26.395179: step: 972/530, loss: 0.033997632563114166
2023-01-23 01:15:27.523512: step: 976/530, loss: 0.005642128176987171
2023-01-23 01:15:28.697881: step: 980/530, loss: 0.020025063306093216
2023-01-23 01:15:29.829494: step: 984/530, loss: 0.03479595482349396
2023-01-23 01:15:30.955933: step: 988/530, loss: 0.21435566246509552
2023-01-23 01:15:32.104492: step: 992/530, loss: 0.10434789955615997
2023-01-23 01:15:33.231518: step: 996/530, loss: 0.06803098320960999
2023-01-23 01:15:34.349893: step: 1000/530, loss: 0.09369244426488876
2023-01-23 01:15:35.484001: step: 1004/530, loss: 0.01654071733355522
2023-01-23 01:15:36.610533: step: 1008/530, loss: 0.052614498883485794
2023-01-23 01:15:37.758770: step: 1012/530, loss: 0.12027569115161896
2023-01-23 01:15:38.878209: step: 1016/530, loss: 0.0188356414437294
2023-01-23 01:15:40.038371: step: 1020/530, loss: 0.4954391419887543
2023-01-23 01:15:41.176788: step: 1024/530, loss: 0.09468240290880203
2023-01-23 01:15:42.311534: step: 1028/530, loss: 0.09825067967176437
2023-01-23 01:15:43.449343: step: 1032/530, loss: 0.05871162563562393
2023-01-23 01:15:44.582866: step: 1036/530, loss: 0.05405168607831001
2023-01-23 01:15:45.731438: step: 1040/530, loss: 0.08131580054759979
2023-01-23 01:15:46.856247: step: 1044/530, loss: 0.0037410736549645662
2023-01-23 01:15:47.969166: step: 1048/530, loss: 0.05062122642993927
2023-01-23 01:15:49.102391: step: 1052/530, loss: 0.03069133684039116
2023-01-23 01:15:50.214327: step: 1056/530, loss: 0.1147225871682167
2023-01-23 01:15:51.360237: step: 1060/530, loss: 0.09318237006664276
2023-01-23 01:15:52.456680: step: 1064/530, loss: 0.2423088103532791
2023-01-23 01:15:53.571851: step: 1068/530, loss: 0.03568211942911148
2023-01-23 01:15:54.684798: step: 1072/530, loss: 0.012611103244125843
2023-01-23 01:15:55.816056: step: 1076/530, loss: 0.05418844148516655
2023-01-23 01:15:56.964429: step: 1080/530, loss: 0.04475107416510582
2023-01-23 01:15:58.061327: step: 1084/530, loss: 0.3632713258266449
2023-01-23 01:15:59.166108: step: 1088/530, loss: 0.024009324610233307
2023-01-23 01:16:00.258443: step: 1092/530, loss: 0.005177688784897327
2023-01-23 01:16:01.355315: step: 1096/530, loss: 0.09368596225976944
2023-01-23 01:16:02.490836: step: 1100/530, loss: 0.05512266233563423
2023-01-23 01:16:03.635446: step: 1104/530, loss: 0.011346627026796341
2023-01-23 01:16:04.740145: step: 1108/530, loss: 0.029341697692871094
2023-01-23 01:16:05.880491: step: 1112/530, loss: 0.03827638924121857
2023-01-23 01:16:07.002461: step: 1116/530, loss: 0.06597843021154404
2023-01-23 01:16:08.119254: step: 1120/530, loss: 0.006766128353774548
2023-01-23 01:16:09.264000: step: 1124/530, loss: 0.05839795991778374
2023-01-23 01:16:10.399173: step: 1128/530, loss: 0.04410533979535103
2023-01-23 01:16:11.534269: step: 1132/530, loss: 0.12106069922447205
2023-01-23 01:16:12.653381: step: 1136/530, loss: 0.03493161126971245
2023-01-23 01:16:13.767752: step: 1140/530, loss: 0.02443847618997097
2023-01-23 01:16:14.909943: step: 1144/530, loss: 0.035881903022527695
2023-01-23 01:16:16.066085: step: 1148/530, loss: 0.113833948969841
2023-01-23 01:16:17.182280: step: 1152/530, loss: 0.07648496329784393
2023-01-23 01:16:18.338538: step: 1156/530, loss: 0.0863349586725235
2023-01-23 01:16:19.480297: step: 1160/530, loss: 0.6466966867446899
2023-01-23 01:16:20.614158: step: 1164/530, loss: 0.06250123679637909
2023-01-23 01:16:21.736606: step: 1168/530, loss: 0.11098838597536087
2023-01-23 01:16:22.880563: step: 1172/530, loss: 0.07459316402673721
2023-01-23 01:16:23.984959: step: 1176/530, loss: 0.05114293098449707
2023-01-23 01:16:25.111021: step: 1180/530, loss: 1.2644160985946655
2023-01-23 01:16:26.231244: step: 1184/530, loss: 0.06528482586145401
2023-01-23 01:16:27.324404: step: 1188/530, loss: 0.08628320693969727
2023-01-23 01:16:28.427945: step: 1192/530, loss: 0.02360553853213787
2023-01-23 01:16:29.579293: step: 1196/530, loss: 0.014839936047792435
2023-01-23 01:16:30.725570: step: 1200/530, loss: 0.07058839499950409
2023-01-23 01:16:31.845559: step: 1204/530, loss: 0.0026111602783203125
2023-01-23 01:16:32.971298: step: 1208/530, loss: 0.04411683231592178
2023-01-23 01:16:34.101361: step: 1212/530, loss: 0.199140265583992
2023-01-23 01:16:35.238625: step: 1216/530, loss: 0.080120749771595
2023-01-23 01:16:36.368688: step: 1220/530, loss: 0.005340576637536287
2023-01-23 01:16:37.504155: step: 1224/530, loss: 0.01398096140474081
2023-01-23 01:16:38.602950: step: 1228/530, loss: 0.09265422821044922
2023-01-23 01:16:39.713348: step: 1232/530, loss: 0.09217549860477448
2023-01-23 01:16:40.845754: step: 1236/530, loss: 0.7396581172943115
2023-01-23 01:16:41.971560: step: 1240/530, loss: 0.16215386986732483
2023-01-23 01:16:43.094204: step: 1244/530, loss: 0.03207864984869957
2023-01-23 01:16:44.248245: step: 1248/530, loss: 0.1976570188999176
2023-01-23 01:16:45.400890: step: 1252/530, loss: 0.029663659632205963
2023-01-23 01:16:46.521897: step: 1256/530, loss: 0.05139150470495224
2023-01-23 01:16:47.652472: step: 1260/530, loss: 0.31529468297958374
2023-01-23 01:16:48.748866: step: 1264/530, loss: 0.09567108005285263
2023-01-23 01:16:49.919781: step: 1268/530, loss: 0.5147698521614075
2023-01-23 01:16:51.057064: step: 1272/530, loss: 0.06492443382740021
2023-01-23 01:16:52.191853: step: 1276/530, loss: 0.27599087357521057
2023-01-23 01:16:53.327327: step: 1280/530, loss: 0.07113823294639587
2023-01-23 01:16:54.420130: step: 1284/530, loss: 0.04100165516138077
2023-01-23 01:16:55.538179: step: 1288/530, loss: 0.01410763245075941
2023-01-23 01:16:56.659085: step: 1292/530, loss: 0.010512733832001686
2023-01-23 01:16:57.819194: step: 1296/530, loss: 0.0069130901247262955
2023-01-23 01:16:58.921144: step: 1300/530, loss: 0.05699882656335831
2023-01-23 01:17:00.084106: step: 1304/530, loss: 0.025124359875917435
2023-01-23 01:17:01.244063: step: 1308/530, loss: 0.013685036450624466
2023-01-23 01:17:02.407314: step: 1312/530, loss: 0.014512252993881702
2023-01-23 01:17:03.507181: step: 1316/530, loss: 0.04087622091174126
2023-01-23 01:17:04.658764: step: 1320/530, loss: 0.06798171997070312
2023-01-23 01:17:05.789951: step: 1324/530, loss: 0.10997334122657776
2023-01-23 01:17:06.902688: step: 1328/530, loss: 0.039987754076719284
2023-01-23 01:17:08.032798: step: 1332/530, loss: 0.027688980102539062
2023-01-23 01:17:09.176705: step: 1336/530, loss: 0.11296100914478302
2023-01-23 01:17:10.282701: step: 1340/530, loss: 0.01258707046508789
2023-01-23 01:17:11.381391: step: 1344/530, loss: 0.010766697116196156
2023-01-23 01:17:12.510102: step: 1348/530, loss: 0.009875917807221413
2023-01-23 01:17:13.644945: step: 1352/530, loss: 0.009843206033110619
2023-01-23 01:17:14.779203: step: 1356/530, loss: 0.056551504880189896
2023-01-23 01:17:15.921427: step: 1360/530, loss: 0.19640818238258362
2023-01-23 01:17:17.109715: step: 1364/530, loss: 0.1295129805803299
2023-01-23 01:17:18.234438: step: 1368/530, loss: 0.13788118958473206
2023-01-23 01:17:19.369974: step: 1372/530, loss: 0.020614244043827057
2023-01-23 01:17:20.491808: step: 1376/530, loss: 0.25282496213912964
2023-01-23 01:17:21.625654: step: 1380/530, loss: 0.03530731052160263
2023-01-23 01:17:22.738056: step: 1384/530, loss: 0.18435411155223846
2023-01-23 01:17:23.849398: step: 1388/530, loss: 0.10940217971801758
2023-01-23 01:17:25.036614: step: 1392/530, loss: 0.11272287368774414
2023-01-23 01:17:26.151268: step: 1396/530, loss: 0.1318398416042328
2023-01-23 01:17:27.296711: step: 1400/530, loss: 0.03157520294189453
2023-01-23 01:17:28.425936: step: 1404/530, loss: 0.008353996090590954
2023-01-23 01:17:29.570353: step: 1408/530, loss: 0.4283823072910309
2023-01-23 01:17:30.716045: step: 1412/530, loss: 0.10291337966918945
2023-01-23 01:17:31.824224: step: 1416/530, loss: 0.05410919338464737
2023-01-23 01:17:32.961085: step: 1420/530, loss: 0.04996194690465927
2023-01-23 01:17:34.066983: step: 1424/530, loss: 0.0653717964887619
2023-01-23 01:17:35.213263: step: 1428/530, loss: 0.06787414848804474
2023-01-23 01:17:36.325877: step: 1432/530, loss: 0.00700192479416728
2023-01-23 01:17:37.467419: step: 1436/530, loss: 0.1161777526140213
2023-01-23 01:17:38.611070: step: 1440/530, loss: 0.07731761783361435
2023-01-23 01:17:39.722894: step: 1444/530, loss: 0.07756614685058594
2023-01-23 01:17:40.865836: step: 1448/530, loss: 0.0411500446498394
2023-01-23 01:17:42.003447: step: 1452/530, loss: 0.1718452423810959
2023-01-23 01:17:43.122029: step: 1456/530, loss: 0.035085584968328476
2023-01-23 01:17:44.250490: step: 1460/530, loss: 0.002965736435726285
2023-01-23 01:17:45.398388: step: 1464/530, loss: 0.04071469232439995
2023-01-23 01:17:46.546602: step: 1468/530, loss: 0.07147331535816193
2023-01-23 01:17:47.684613: step: 1472/530, loss: 0.026366807520389557
2023-01-23 01:17:48.822955: step: 1476/530, loss: 0.06166896969079971
2023-01-23 01:17:49.961071: step: 1480/530, loss: 0.16291895508766174
2023-01-23 01:17:51.076936: step: 1484/530, loss: 0.07217002660036087
2023-01-23 01:17:52.204275: step: 1488/530, loss: 0.07616110146045685
2023-01-23 01:17:53.340965: step: 1492/530, loss: 0.04465656355023384
2023-01-23 01:17:54.457278: step: 1496/530, loss: 0.042730093002319336
2023-01-23 01:17:55.582793: step: 1500/530, loss: 0.008275412954390049
2023-01-23 01:17:56.701826: step: 1504/530, loss: 0.014320563524961472
2023-01-23 01:17:57.837908: step: 1508/530, loss: 0.022402573376893997
2023-01-23 01:17:58.936597: step: 1512/530, loss: 0.02273428626358509
2023-01-23 01:18:00.077204: step: 1516/530, loss: 0.07801590114831924
2023-01-23 01:18:01.196559: step: 1520/530, loss: 0.660473644733429
2023-01-23 01:18:02.329446: step: 1524/530, loss: 0.062969870865345
2023-01-23 01:18:03.460985: step: 1528/530, loss: 0.04149813577532768
2023-01-23 01:18:04.576675: step: 1532/530, loss: 0.534745991230011
2023-01-23 01:18:05.667990: step: 1536/530, loss: 0.04747038334608078
2023-01-23 01:18:06.789937: step: 1540/530, loss: 0.041450027376413345
2023-01-23 01:18:07.910760: step: 1544/530, loss: 0.002290964126586914
2023-01-23 01:18:09.041944: step: 1548/530, loss: 0.003115034196525812
2023-01-23 01:18:10.155276: step: 1552/530, loss: 0.0901481881737709
2023-01-23 01:18:11.287415: step: 1556/530, loss: 0.04049034044146538
2023-01-23 01:18:12.395803: step: 1560/530, loss: 0.06399927288293839
2023-01-23 01:18:13.518595: step: 1564/530, loss: 0.04926738888025284
2023-01-23 01:18:14.664082: step: 1568/530, loss: 0.06774749606847763
2023-01-23 01:18:15.848524: step: 1572/530, loss: 0.0345122329890728
2023-01-23 01:18:16.993346: step: 1576/530, loss: 0.004068565554916859
2023-01-23 01:18:18.125998: step: 1580/530, loss: 0.02066836506128311
2023-01-23 01:18:19.255715: step: 1584/530, loss: 0.0838892012834549
2023-01-23 01:18:20.393261: step: 1588/530, loss: 0.018881987780332565
2023-01-23 01:18:21.511536: step: 1592/530, loss: 0.09250137954950333
2023-01-23 01:18:22.657851: step: 1596/530, loss: 0.05074882507324219
2023-01-23 01:18:23.808813: step: 1600/530, loss: 0.00616983138024807
2023-01-23 01:18:24.939764: step: 1604/530, loss: 0.09350337833166122
2023-01-23 01:18:26.053982: step: 1608/530, loss: 0.024193860590457916
2023-01-23 01:18:27.179395: step: 1612/530, loss: 0.055021002888679504
2023-01-23 01:18:28.295718: step: 1616/530, loss: 0.6724486351013184
2023-01-23 01:18:29.417823: step: 1620/530, loss: 0.016064025461673737
2023-01-23 01:18:30.536078: step: 1624/530, loss: 0.05892963334918022
2023-01-23 01:18:31.649775: step: 1628/530, loss: 0.05799455568194389
2023-01-23 01:18:32.769809: step: 1632/530, loss: 0.09745702892541885
2023-01-23 01:18:33.874610: step: 1636/530, loss: 0.0015552043914794922
2023-01-23 01:18:35.029282: step: 1640/530, loss: 0.05822935327887535
2023-01-23 01:18:36.122235: step: 1644/530, loss: 0.025290869176387787
2023-01-23 01:18:37.249907: step: 1648/530, loss: 0.05255603790283203
2023-01-23 01:18:38.378705: step: 1652/530, loss: 0.020556354895234108
2023-01-23 01:18:39.504188: step: 1656/530, loss: 0.4559013247489929
2023-01-23 01:18:40.638455: step: 1660/530, loss: 0.02525482140481472
2023-01-23 01:18:41.763469: step: 1664/530, loss: 0.06422662734985352
2023-01-23 01:18:42.880369: step: 1668/530, loss: 0.12644276022911072
2023-01-23 01:18:44.001853: step: 1672/530, loss: 0.17926025390625
2023-01-23 01:18:45.142060: step: 1676/530, loss: 0.05211496353149414
2023-01-23 01:18:46.264595: step: 1680/530, loss: 0.16344602406024933
2023-01-23 01:18:47.387904: step: 1684/530, loss: 0.0701485201716423
2023-01-23 01:18:48.518721: step: 1688/530, loss: 0.043615687638521194
2023-01-23 01:18:49.680258: step: 1692/530, loss: 0.0025273323990404606
2023-01-23 01:18:50.816416: step: 1696/530, loss: 0.05736789479851723
2023-01-23 01:18:51.945697: step: 1700/530, loss: 0.04317808151245117
2023-01-23 01:18:53.070709: step: 1704/530, loss: 0.2833509147167206
2023-01-23 01:18:54.208796: step: 1708/530, loss: 0.07659697532653809
2023-01-23 01:18:55.322471: step: 1712/530, loss: 0.041161250323057175
2023-01-23 01:18:56.434942: step: 1716/530, loss: 0.06974592804908752
2023-01-23 01:18:57.540262: step: 1720/530, loss: 0.06852450221776962
2023-01-23 01:18:58.695617: step: 1724/530, loss: 0.0031832694076001644
2023-01-23 01:18:59.820494: step: 1728/530, loss: 0.020217228680849075
2023-01-23 01:19:00.993918: step: 1732/530, loss: 0.1470022201538086
2023-01-23 01:19:02.130140: step: 1736/530, loss: 0.011029482819139957
2023-01-23 01:19:03.230883: step: 1740/530, loss: 0.06349734216928482
2023-01-23 01:19:04.371873: step: 1744/530, loss: 0.08026114106178284
2023-01-23 01:19:05.490991: step: 1748/530, loss: 0.0418119877576828
2023-01-23 01:19:06.626494: step: 1752/530, loss: 0.04265284538269043
2023-01-23 01:19:07.740839: step: 1756/530, loss: 0.0036739350762218237
2023-01-23 01:19:08.883355: step: 1760/530, loss: 0.11331792175769806
2023-01-23 01:19:10.020615: step: 1764/530, loss: 0.14771810173988342
2023-01-23 01:19:11.187368: step: 1768/530, loss: 0.02606639824807644
2023-01-23 01:19:12.323612: step: 1772/530, loss: 0.05151662603020668
2023-01-23 01:19:13.478813: step: 1776/530, loss: 0.010968590155243874
2023-01-23 01:19:14.604648: step: 1780/530, loss: 0.029538821429014206
2023-01-23 01:19:15.703136: step: 1784/530, loss: 0.06696148216724396
2023-01-23 01:19:16.822491: step: 1788/530, loss: 0.051369860768318176
2023-01-23 01:19:17.976161: step: 1792/530, loss: 0.6859917044639587
2023-01-23 01:19:19.116099: step: 1796/530, loss: 0.06786274909973145
2023-01-23 01:19:20.254148: step: 1800/530, loss: 0.059851549565792084
2023-01-23 01:19:21.377584: step: 1804/530, loss: 0.044039536267519
2023-01-23 01:19:22.514530: step: 1808/530, loss: 0.009844970889389515
2023-01-23 01:19:23.618002: step: 1812/530, loss: 0.6420565843582153
2023-01-23 01:19:24.749873: step: 1816/530, loss: 0.04098225012421608
2023-01-23 01:19:25.883546: step: 1820/530, loss: 0.15927332639694214
2023-01-23 01:19:27.014288: step: 1824/530, loss: 0.160509392619133
2023-01-23 01:19:28.168836: step: 1828/530, loss: 0.12359962612390518
2023-01-23 01:19:29.292080: step: 1832/530, loss: 0.04187892749905586
2023-01-23 01:19:30.423027: step: 1836/530, loss: 0.016002655029296875
2023-01-23 01:19:31.552954: step: 1840/530, loss: 0.021069765090942383
2023-01-23 01:19:32.711048: step: 1844/530, loss: 0.1635255664587021
2023-01-23 01:19:33.841236: step: 1848/530, loss: 0.10742644965648651
2023-01-23 01:19:34.962609: step: 1852/530, loss: 0.10360260307788849
2023-01-23 01:19:36.080913: step: 1856/530, loss: 0.01583815924823284
2023-01-23 01:19:37.188067: step: 1860/530, loss: 0.012880707159638405
2023-01-23 01:19:38.303999: step: 1864/530, loss: 0.10445842891931534
2023-01-23 01:19:39.414919: step: 1868/530, loss: 0.027312923222780228
2023-01-23 01:19:40.526669: step: 1872/530, loss: 0.02525165118277073
2023-01-23 01:19:41.654675: step: 1876/530, loss: 0.22788628935813904
2023-01-23 01:19:42.754445: step: 1880/530, loss: 0.00774993933737278
2023-01-23 01:19:43.880542: step: 1884/530, loss: 0.04043865203857422
2023-01-23 01:19:44.997115: step: 1888/530, loss: 0.0032260895241051912
2023-01-23 01:19:46.147008: step: 1892/530, loss: 0.01276698149740696
2023-01-23 01:19:47.261673: step: 1896/530, loss: 0.08284330368041992
2023-01-23 01:19:48.389151: step: 1900/530, loss: 0.014325236901640892
2023-01-23 01:19:49.511413: step: 1904/530, loss: 0.07284488528966904
2023-01-23 01:19:50.619308: step: 1908/530, loss: 0.3223952353000641
2023-01-23 01:19:51.719948: step: 1912/530, loss: 0.06291351467370987
2023-01-23 01:19:52.851699: step: 1916/530, loss: 0.00580178527161479
2023-01-23 01:19:54.011732: step: 1920/530, loss: 0.0956028550863266
2023-01-23 01:19:55.159155: step: 1924/530, loss: 0.21865883469581604
2023-01-23 01:19:56.304291: step: 1928/530, loss: 0.08705687522888184
2023-01-23 01:19:57.451287: step: 1932/530, loss: 0.023654038086533546
2023-01-23 01:19:58.588032: step: 1936/530, loss: 0.29416608810424805
2023-01-23 01:19:59.727536: step: 1940/530, loss: 0.05245485529303551
2023-01-23 01:20:00.874064: step: 1944/530, loss: 0.08622479438781738
2023-01-23 01:20:02.010133: step: 1948/530, loss: 0.05781688541173935
2023-01-23 01:20:03.150756: step: 1952/530, loss: 0.06407561153173447
2023-01-23 01:20:04.288125: step: 1956/530, loss: 0.1016550064086914
2023-01-23 01:20:05.443703: step: 1960/530, loss: 0.04599037021398544
2023-01-23 01:20:06.603375: step: 1964/530, loss: 0.0449918732047081
2023-01-23 01:20:07.714284: step: 1968/530, loss: 0.025324631482362747
2023-01-23 01:20:08.806833: step: 1972/530, loss: 0.020659398287534714
2023-01-23 01:20:09.921738: step: 1976/530, loss: 0.07957782596349716
2023-01-23 01:20:11.030818: step: 1980/530, loss: 0.2930607497692108
2023-01-23 01:20:12.147634: step: 1984/530, loss: 0.0812654048204422
2023-01-23 01:20:13.307011: step: 1988/530, loss: 0.015449953265488148
2023-01-23 01:20:14.426687: step: 1992/530, loss: 0.09924278408288956
2023-01-23 01:20:15.536812: step: 1996/530, loss: 0.09803356975317001
2023-01-23 01:20:16.655638: step: 2000/530, loss: 0.8872809410095215
2023-01-23 01:20:17.780273: step: 2004/530, loss: 0.2716556489467621
2023-01-23 01:20:18.922636: step: 2008/530, loss: 0.15356646478176117
2023-01-23 01:20:20.047889: step: 2012/530, loss: 0.020653152838349342
2023-01-23 01:20:21.176969: step: 2016/530, loss: 0.08149471133947372
2023-01-23 01:20:22.296423: step: 2020/530, loss: 0.0851578414440155
2023-01-23 01:20:23.407899: step: 2024/530, loss: 0.032738495618104935
2023-01-23 01:20:24.539213: step: 2028/530, loss: 0.051030635833740234
2023-01-23 01:20:25.651993: step: 2032/530, loss: 0.011017322540283203
2023-01-23 01:20:26.784496: step: 2036/530, loss: 0.0707957074046135
2023-01-23 01:20:27.907139: step: 2040/530, loss: 0.01657099649310112
2023-01-23 01:20:29.071570: step: 2044/530, loss: 0.04788494110107422
2023-01-23 01:20:30.212827: step: 2048/530, loss: 0.058371927589178085
2023-01-23 01:20:31.362763: step: 2052/530, loss: 0.09562435746192932
2023-01-23 01:20:32.515107: step: 2056/530, loss: 0.10337600857019424
2023-01-23 01:20:33.642664: step: 2060/530, loss: 0.06824488937854767
2023-01-23 01:20:34.771135: step: 2064/530, loss: 0.037090301513671875
2023-01-23 01:20:35.913633: step: 2068/530, loss: 0.2514505386352539
2023-01-23 01:20:37.032262: step: 2072/530, loss: 0.07868289947509766
2023-01-23 01:20:38.165822: step: 2076/530, loss: 0.09531764686107635
2023-01-23 01:20:39.301252: step: 2080/530, loss: 0.08204317837953568
2023-01-23 01:20:40.423181: step: 2084/530, loss: 0.03345184400677681
2023-01-23 01:20:41.571573: step: 2088/530, loss: 0.158244326710701
2023-01-23 01:20:42.702811: step: 2092/530, loss: 0.024426650255918503
2023-01-23 01:20:43.798495: step: 2096/530, loss: 0.05949068069458008
2023-01-23 01:20:44.909358: step: 2100/530, loss: 0.6813151836395264
2023-01-23 01:20:46.034288: step: 2104/530, loss: 0.011803055182099342
2023-01-23 01:20:47.178797: step: 2108/530, loss: 0.053340815007686615
2023-01-23 01:20:48.307527: step: 2112/530, loss: 0.017792940139770508
2023-01-23 01:20:49.447193: step: 2116/530, loss: 0.0037843226455152035
2023-01-23 01:20:50.579912: step: 2120/530, loss: 1.2282586097717285
==================================================
Loss: 0.095
--------------------
Dev: {'event': {'p': 0.5675675675675675, 'r': 0.7829560585885486, 'f1': 0.6580861779518746}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Test: {'event': {'p': 0.6069438491213031, 'r': 0.8091428571428572, 'f1': 0.6936076414401176}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Chinese: {'event': {'p': 0.5340909090909091, 'r': 0.8703703703703703, 'f1': 0.6619718309859154}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Korean: {'event': {'p': 0.5671641791044776, 'r': 0.6031746031746031, 'f1': 0.5846153846153845}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
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': 10}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Chinese: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Chinese: {'event': {'p': 0.6190476190476191, 'r': 0.9629629629629629, 'f1': 0.7536231884057971}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5877016129032258, 'r': 0.7762982689747004, 'f1': 0.6689615605278255}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Korean: {'event': {'p': 0.6539923954372624, 'r': 0.7862857142857143, 'f1': 0.7140633108458745}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Korean: {'event': {'p': 0.6666666666666666, 'r': 0.6349206349206349, 'f1': 0.6504065040650407}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5319148936170213, 'r': 0.6944444444444444, 'f1': 0.6024096385542169}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
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 01:21:31.552617: step: 4/530, loss: 0.01445770263671875
2023-01-23 01:21:32.699651: step: 8/530, loss: 0.03450345993041992
2023-01-23 01:21:33.833481: step: 12/530, loss: 0.07936783134937286
2023-01-23 01:21:34.947555: step: 16/530, loss: 0.012303435243666172
2023-01-23 01:21:36.098211: step: 20/530, loss: 0.02600078471004963
2023-01-23 01:21:37.212130: step: 24/530, loss: 0.039287663996219635
2023-01-23 01:21:38.323548: step: 28/530, loss: 0.08217611163854599
2023-01-23 01:21:39.454699: step: 32/530, loss: 0.0037899017333984375
2023-01-23 01:21:40.613067: step: 36/530, loss: 0.06696641445159912
2023-01-23 01:21:41.747707: step: 40/530, loss: 0.02762126922607422
2023-01-23 01:21:42.852677: step: 44/530, loss: 0.1270473450422287
2023-01-23 01:21:44.002527: step: 48/530, loss: 0.0277539249509573
2023-01-23 01:21:45.162497: step: 52/530, loss: 0.006583213806152344
2023-01-23 01:21:46.315870: step: 56/530, loss: 0.027288246899843216
2023-01-23 01:21:47.413878: step: 60/530, loss: 0.033304356038570404
2023-01-23 01:21:48.550881: step: 64/530, loss: 0.046938780695199966
2023-01-23 01:21:49.690302: step: 68/530, loss: 0.023034095764160156
2023-01-23 01:21:50.829284: step: 72/530, loss: 0.07793130725622177
2023-01-23 01:21:51.954276: step: 76/530, loss: 0.024054337292909622
2023-01-23 01:21:53.076964: step: 80/530, loss: 0.07088327407836914
2023-01-23 01:21:54.195339: step: 84/530, loss: 0.005694866180419922
2023-01-23 01:21:55.322454: step: 88/530, loss: 0.048822835087776184
2023-01-23 01:21:56.445037: step: 92/530, loss: 0.02551422268152237
2023-01-23 01:21:57.583921: step: 96/530, loss: 0.12112608551979065
2023-01-23 01:21:58.721254: step: 100/530, loss: 0.06975698471069336
2023-01-23 01:21:59.810552: step: 104/530, loss: 0.028263188898563385
2023-01-23 01:22:00.944204: step: 108/530, loss: 0.008280182257294655
2023-01-23 01:22:02.048536: step: 112/530, loss: 0.1454872041940689
2023-01-23 01:22:03.194220: step: 116/530, loss: 0.024723529815673828
2023-01-23 01:22:04.314990: step: 120/530, loss: 0.4002692997455597
2023-01-23 01:22:05.427010: step: 124/530, loss: 0.29019662737846375
2023-01-23 01:22:06.537003: step: 128/530, loss: 0.025742197409272194
2023-01-23 01:22:07.654759: step: 132/530, loss: 0.003211552044376731
2023-01-23 01:22:08.777566: step: 136/530, loss: 0.018715573474764824
2023-01-23 01:22:09.878809: step: 140/530, loss: 0.2575494945049286
2023-01-23 01:22:11.018000: step: 144/530, loss: 0.14548683166503906
2023-01-23 01:22:12.146480: step: 148/530, loss: 0.03913545608520508
2023-01-23 01:22:13.281233: step: 152/530, loss: 0.019583702087402344
2023-01-23 01:22:14.437235: step: 156/530, loss: 0.21997728943824768
2023-01-23 01:22:15.578549: step: 160/530, loss: 0.011895847506821156
2023-01-23 01:22:16.682892: step: 164/530, loss: 0.2892166078090668
2023-01-23 01:22:17.774878: step: 168/530, loss: 0.05348362773656845
2023-01-23 01:22:18.908029: step: 172/530, loss: 0.06256003677845001
2023-01-23 01:22:20.024525: step: 176/530, loss: 0.018559932708740234
2023-01-23 01:22:21.124633: step: 180/530, loss: 0.0371706523001194
2023-01-23 01:22:22.242901: step: 184/530, loss: 0.9415879249572754
2023-01-23 01:22:23.373146: step: 188/530, loss: 0.081817626953125
2023-01-23 01:22:24.510876: step: 192/530, loss: 0.019884299486875534
2023-01-23 01:22:25.641803: step: 196/530, loss: 0.05709486082196236
2023-01-23 01:22:26.766279: step: 200/530, loss: 0.07249286025762558
2023-01-23 01:22:27.860869: step: 204/530, loss: 0.011102485470473766
2023-01-23 01:22:28.974183: step: 208/530, loss: 0.1096406951546669
2023-01-23 01:22:30.145301: step: 212/530, loss: 0.08910264819860458
2023-01-23 01:22:31.260930: step: 216/530, loss: 0.2910998463630676
2023-01-23 01:22:32.397773: step: 220/530, loss: 0.05775747448205948
2023-01-23 01:22:33.507254: step: 224/530, loss: 0.0006633758312091231
2023-01-23 01:22:34.613401: step: 228/530, loss: 0.0011505603324621916
2023-01-23 01:22:35.727297: step: 232/530, loss: 0.09911108762025833
2023-01-23 01:22:36.854035: step: 236/530, loss: 0.06554313004016876
2023-01-23 01:22:38.000301: step: 240/530, loss: 0.02504882961511612
2023-01-23 01:22:39.111069: step: 244/530, loss: 0.10207463055849075
2023-01-23 01:22:40.210751: step: 248/530, loss: 0.04125576093792915
2023-01-23 01:22:41.341341: step: 252/530, loss: 0.08495473861694336
2023-01-23 01:22:42.462716: step: 256/530, loss: 0.04540920630097389
2023-01-23 01:22:43.601356: step: 260/530, loss: 0.1420988142490387
2023-01-23 01:22:44.765199: step: 264/530, loss: 0.03118143044412136
2023-01-23 01:22:45.872595: step: 268/530, loss: 0.10663948208093643
2023-01-23 01:22:47.009306: step: 272/530, loss: 0.011132621206343174
2023-01-23 01:22:48.145678: step: 276/530, loss: 0.027394961565732956
2023-01-23 01:22:49.263987: step: 280/530, loss: 0.07532797008752823
2023-01-23 01:22:50.374170: step: 284/530, loss: 0.13033714890480042
2023-01-23 01:22:51.523574: step: 288/530, loss: 0.051958370953798294
2023-01-23 01:22:52.638784: step: 292/530, loss: 0.009131526574492455
2023-01-23 01:22:53.772880: step: 296/530, loss: 0.0011385917896404862
2023-01-23 01:22:54.895702: step: 300/530, loss: 0.013597488403320312
2023-01-23 01:22:56.031420: step: 304/530, loss: 0.04292549937963486
2023-01-23 01:22:57.174895: step: 308/530, loss: 0.05222950130701065
2023-01-23 01:22:58.280159: step: 312/530, loss: 0.03021574206650257
2023-01-23 01:22:59.411127: step: 316/530, loss: 0.0709286704659462
2023-01-23 01:23:00.574369: step: 320/530, loss: 0.06238918378949165
2023-01-23 01:23:01.703743: step: 324/530, loss: 0.025046350434422493
2023-01-23 01:23:02.870971: step: 328/530, loss: 0.031374216079711914
2023-01-23 01:23:03.985876: step: 332/530, loss: 0.015353584662079811
2023-01-23 01:23:05.077354: step: 336/530, loss: 0.22220002114772797
2023-01-23 01:23:06.218507: step: 340/530, loss: 0.13547106087207794
2023-01-23 01:23:07.340915: step: 344/530, loss: 0.012132836505770683
2023-01-23 01:23:08.454134: step: 348/530, loss: 0.0672733336687088
2023-01-23 01:23:09.620923: step: 352/530, loss: 0.05815630033612251
2023-01-23 01:23:10.752398: step: 356/530, loss: 0.006888675503432751
2023-01-23 01:23:11.873546: step: 360/530, loss: 0.07691159844398499
2023-01-23 01:23:13.007573: step: 364/530, loss: 0.14771157503128052
2023-01-23 01:23:14.128883: step: 368/530, loss: 0.038546372205019
2023-01-23 01:23:15.267358: step: 372/530, loss: 0.02037830278277397
2023-01-23 01:23:16.389326: step: 376/530, loss: 0.013608884997665882
2023-01-23 01:23:17.516411: step: 380/530, loss: 0.16843700408935547
2023-01-23 01:23:18.630804: step: 384/530, loss: 0.016086386516690254
2023-01-23 01:23:19.737717: step: 388/530, loss: 0.013777637854218483
2023-01-23 01:23:20.864585: step: 392/530, loss: 0.003441238310188055
2023-01-23 01:23:21.988306: step: 396/530, loss: 0.07063465565443039
2023-01-23 01:23:23.102718: step: 400/530, loss: 0.207781121134758
2023-01-23 01:23:24.227642: step: 404/530, loss: 0.08404732495546341
2023-01-23 01:23:25.395318: step: 408/530, loss: 0.0668419897556305
2023-01-23 01:23:26.515130: step: 412/530, loss: 0.06274401396512985
2023-01-23 01:23:27.650213: step: 416/530, loss: 0.006211805157363415
2023-01-23 01:23:28.760524: step: 420/530, loss: 0.01486311573535204
2023-01-23 01:23:29.893224: step: 424/530, loss: 0.12865057587623596
2023-01-23 01:23:31.007209: step: 428/530, loss: 0.1546918898820877
2023-01-23 01:23:32.152628: step: 432/530, loss: 0.004378318786621094
2023-01-23 01:23:33.280382: step: 436/530, loss: 0.11989402770996094
2023-01-23 01:23:34.409476: step: 440/530, loss: 0.026608657091856003
2023-01-23 01:23:35.536430: step: 444/530, loss: 0.018164968118071556
2023-01-23 01:23:36.651310: step: 448/530, loss: 0.04957571253180504
2023-01-23 01:23:37.759770: step: 452/530, loss: 0.03682751581072807
2023-01-23 01:23:38.867813: step: 456/530, loss: 0.02497081831097603
2023-01-23 01:23:39.996777: step: 460/530, loss: 0.018630720674991608
2023-01-23 01:23:41.134524: step: 464/530, loss: 0.06690549850463867
2023-01-23 01:23:42.264590: step: 468/530, loss: 0.038674164563417435
2023-01-23 01:23:43.380731: step: 472/530, loss: 0.014288758859038353
2023-01-23 01:23:44.525886: step: 476/530, loss: 0.06731200218200684
2023-01-23 01:23:45.663103: step: 480/530, loss: 0.17412835359573364
2023-01-23 01:23:46.804657: step: 484/530, loss: 0.023894120007753372
2023-01-23 01:23:47.940370: step: 488/530, loss: 0.05509471893310547
2023-01-23 01:23:49.072427: step: 492/530, loss: 0.27944415807724
2023-01-23 01:23:50.219750: step: 496/530, loss: 0.051247790455818176
2023-01-23 01:23:51.331115: step: 500/530, loss: 0.1640431433916092
2023-01-23 01:23:52.461422: step: 504/530, loss: 0.020304251462221146
2023-01-23 01:23:53.573483: step: 508/530, loss: 0.009315062314271927
2023-01-23 01:23:54.713673: step: 512/530, loss: 0.03766131401062012
2023-01-23 01:23:55.805186: step: 516/530, loss: 0.03255338966846466
2023-01-23 01:23:56.918987: step: 520/530, loss: 0.019003022462129593
2023-01-23 01:23:58.049672: step: 524/530, loss: 0.00856394786387682
2023-01-23 01:23:59.148305: step: 528/530, loss: 0.08291111141443253
2023-01-23 01:24:00.258032: step: 532/530, loss: 0.0517425537109375
2023-01-23 01:24:01.374697: step: 536/530, loss: 0.0063506606966257095
2023-01-23 01:24:02.484771: step: 540/530, loss: 0.02998046949505806
2023-01-23 01:24:03.612025: step: 544/530, loss: 0.014499855227768421
2023-01-23 01:24:04.726033: step: 548/530, loss: 0.025513364002108574
2023-01-23 01:24:05.872996: step: 552/530, loss: 0.0032840727362781763
2023-01-23 01:24:07.037367: step: 556/530, loss: 0.06379013508558273
2023-01-23 01:24:08.156367: step: 560/530, loss: 0.027318669483065605
2023-01-23 01:24:09.325030: step: 564/530, loss: 0.18331317603588104
2023-01-23 01:24:10.457079: step: 568/530, loss: 0.0556914322078228
2023-01-23 01:24:11.586751: step: 572/530, loss: 0.01944875717163086
2023-01-23 01:24:12.707934: step: 576/530, loss: 0.05487499386072159
2023-01-23 01:24:13.832128: step: 580/530, loss: 0.01848888397216797
2023-01-23 01:24:14.982170: step: 584/530, loss: 0.10216408222913742
2023-01-23 01:24:16.066130: step: 588/530, loss: 0.03553037717938423
2023-01-23 01:24:17.207105: step: 592/530, loss: 0.026528263464570045
2023-01-23 01:24:18.303007: step: 596/530, loss: 0.0061918264254927635
2023-01-23 01:24:19.456384: step: 600/530, loss: 0.0188235305249691
2023-01-23 01:24:20.562667: step: 604/530, loss: 0.0622439831495285
2023-01-23 01:24:21.695361: step: 608/530, loss: 0.02280578576028347
2023-01-23 01:24:22.801758: step: 612/530, loss: 0.04630870744585991
2023-01-23 01:24:23.934083: step: 616/530, loss: 0.046742819249629974
2023-01-23 01:24:25.084012: step: 620/530, loss: 0.0693449079990387
2023-01-23 01:24:26.221667: step: 624/530, loss: 0.09341659396886826
2023-01-23 01:24:27.334308: step: 628/530, loss: 0.02776651456952095
2023-01-23 01:24:28.470851: step: 632/530, loss: 0.1390846222639084
2023-01-23 01:24:29.606434: step: 636/530, loss: 0.6937339901924133
2023-01-23 01:24:30.738587: step: 640/530, loss: 0.03495540842413902
2023-01-23 01:24:31.920646: step: 644/530, loss: 0.03575325012207031
2023-01-23 01:24:33.061699: step: 648/530, loss: 0.5459203720092773
2023-01-23 01:24:34.187700: step: 652/530, loss: 0.006506538018584251
2023-01-23 01:24:35.335763: step: 656/530, loss: 0.2865927517414093
2023-01-23 01:24:36.449038: step: 660/530, loss: 0.037972450256347656
2023-01-23 01:24:37.592710: step: 664/530, loss: 0.03791651874780655
2023-01-23 01:24:38.715596: step: 668/530, loss: 0.13957729935646057
2023-01-23 01:24:39.832118: step: 672/530, loss: 0.02175619639456272
2023-01-23 01:24:40.941303: step: 676/530, loss: 0.04468078538775444
2023-01-23 01:24:42.073733: step: 680/530, loss: 0.012370586395263672
2023-01-23 01:24:43.209173: step: 684/530, loss: 0.0033576965797692537
2023-01-23 01:24:44.320568: step: 688/530, loss: 0.019021224230527878
2023-01-23 01:24:45.459077: step: 692/530, loss: 0.013133621774613857
2023-01-23 01:24:46.622418: step: 696/530, loss: 0.1058053970336914
2023-01-23 01:24:47.741735: step: 700/530, loss: 0.062140658497810364
2023-01-23 01:24:48.859125: step: 704/530, loss: 0.02763814851641655
2023-01-23 01:24:49.983879: step: 708/530, loss: 0.03821153566241264
2023-01-23 01:24:51.100966: step: 712/530, loss: 0.07512583583593369
2023-01-23 01:24:52.238084: step: 716/530, loss: 0.12789902091026306
2023-01-23 01:24:53.341644: step: 720/530, loss: 0.019373273476958275
2023-01-23 01:24:54.466649: step: 724/530, loss: 0.025617599487304688
2023-01-23 01:24:55.595415: step: 728/530, loss: 0.011046218685805798
2023-01-23 01:24:56.725623: step: 732/530, loss: 0.039710428565740585
2023-01-23 01:24:57.857507: step: 736/530, loss: 0.00010223221033811569
2023-01-23 01:24:58.967547: step: 740/530, loss: 0.02292652055621147
2023-01-23 01:25:00.113699: step: 744/530, loss: 0.032210540026426315
2023-01-23 01:25:01.232236: step: 748/530, loss: 0.14425086975097656
2023-01-23 01:25:02.363779: step: 752/530, loss: 0.007232856936752796
2023-01-23 01:25:03.478874: step: 756/530, loss: 0.08457297831773758
2023-01-23 01:25:04.616708: step: 760/530, loss: 0.011852837167680264
2023-01-23 01:25:05.769345: step: 764/530, loss: 0.09369754791259766
2023-01-23 01:25:06.903328: step: 768/530, loss: 0.03629627078771591
2023-01-23 01:25:08.055959: step: 772/530, loss: 0.43800267577171326
2023-01-23 01:25:09.169809: step: 776/530, loss: 0.05042581632733345
2023-01-23 01:25:10.294630: step: 780/530, loss: 0.026218559592962265
2023-01-23 01:25:11.413333: step: 784/530, loss: 0.030567217618227005
2023-01-23 01:25:12.541233: step: 788/530, loss: 0.6515905261039734
2023-01-23 01:25:13.673981: step: 792/530, loss: 0.02814474143087864
2023-01-23 01:25:14.799644: step: 796/530, loss: 0.04781952127814293
2023-01-23 01:25:15.926718: step: 800/530, loss: 0.08095154166221619
2023-01-23 01:25:17.043739: step: 804/530, loss: 0.04170503839850426
2023-01-23 01:25:18.176739: step: 808/530, loss: 0.04887457191944122
2023-01-23 01:25:19.317802: step: 812/530, loss: 0.101282499730587
2023-01-23 01:25:20.441777: step: 816/530, loss: 0.0029612542130053043
2023-01-23 01:25:21.565388: step: 820/530, loss: 0.0007656335947103798
2023-01-23 01:25:22.682260: step: 824/530, loss: 0.10248041152954102
2023-01-23 01:25:23.798932: step: 828/530, loss: 0.06279736012220383
2023-01-23 01:25:24.942847: step: 832/530, loss: 0.01447677705436945
2023-01-23 01:25:26.033292: step: 836/530, loss: 0.03201131895184517
2023-01-23 01:25:27.145491: step: 840/530, loss: 0.014046764001250267
2023-01-23 01:25:28.283121: step: 844/530, loss: 0.0996561050415039
2023-01-23 01:25:29.390920: step: 848/530, loss: 0.03612957149744034
2023-01-23 01:25:30.482552: step: 852/530, loss: 0.020800210535526276
2023-01-23 01:25:31.671963: step: 856/530, loss: 0.00274581927806139
2023-01-23 01:25:32.805474: step: 860/530, loss: 0.030065441504120827
2023-01-23 01:25:33.929139: step: 864/530, loss: 0.0040302276611328125
2023-01-23 01:25:35.040220: step: 868/530, loss: 0.00771408062428236
2023-01-23 01:25:36.159228: step: 872/530, loss: 0.12622594833374023
2023-01-23 01:25:37.291942: step: 876/530, loss: 0.007862758822739124
2023-01-23 01:25:38.410839: step: 880/530, loss: 0.2506319284439087
2023-01-23 01:25:39.565071: step: 884/530, loss: 0.10726174712181091
2023-01-23 01:25:40.664534: step: 888/530, loss: 0.04552764818072319
2023-01-23 01:25:41.773521: step: 892/530, loss: 0.018457986414432526
2023-01-23 01:25:42.892395: step: 896/530, loss: 0.0013124465476721525
2023-01-23 01:25:44.003540: step: 900/530, loss: 0.2510325312614441
2023-01-23 01:25:45.117499: step: 904/530, loss: 0.04855804517865181
2023-01-23 01:25:46.238548: step: 908/530, loss: 0.09022665023803711
2023-01-23 01:25:47.338179: step: 912/530, loss: 0.0936279296875
2023-01-23 01:25:48.446570: step: 916/530, loss: 0.07424610108137131
2023-01-23 01:25:49.546903: step: 920/530, loss: 0.03892498090863228
2023-01-23 01:25:50.656305: step: 924/530, loss: 0.05424042046070099
2023-01-23 01:25:51.768055: step: 928/530, loss: 0.016835279762744904
2023-01-23 01:25:52.915630: step: 932/530, loss: 0.009508704766631126
2023-01-23 01:25:54.028282: step: 936/530, loss: 0.11599965393543243
2023-01-23 01:25:55.178581: step: 940/530, loss: 0.020278453826904297
2023-01-23 01:25:56.324549: step: 944/530, loss: 0.036522772163152695
2023-01-23 01:25:57.441152: step: 948/530, loss: 0.07682456821203232
2023-01-23 01:25:58.579691: step: 952/530, loss: 0.1798015534877777
2023-01-23 01:25:59.682107: step: 956/530, loss: 0.01995849795639515
2023-01-23 01:26:00.810299: step: 960/530, loss: 0.10105772316455841
2023-01-23 01:26:01.949053: step: 964/530, loss: 0.15047797560691833
2023-01-23 01:26:03.164994: step: 968/530, loss: 0.09532566368579865
2023-01-23 01:26:04.325418: step: 972/530, loss: 0.030692197382450104
2023-01-23 01:26:05.429600: step: 976/530, loss: 0.05657653883099556
2023-01-23 01:26:06.560902: step: 980/530, loss: 0.06002149358391762
2023-01-23 01:26:07.661769: step: 984/530, loss: 0.02169513702392578
2023-01-23 01:26:08.787341: step: 988/530, loss: 0.038320064544677734
2023-01-23 01:26:09.898386: step: 992/530, loss: 0.08170090615749359
2023-01-23 01:26:11.040122: step: 996/530, loss: 0.0005859375232830644
2023-01-23 01:26:12.175156: step: 1000/530, loss: 0.009829336777329445
2023-01-23 01:26:13.292263: step: 1004/530, loss: 0.00011296272714389488
2023-01-23 01:26:14.400419: step: 1008/530, loss: 0.016820382326841354
2023-01-23 01:26:15.514915: step: 1012/530, loss: 0.0171248447149992
2023-01-23 01:26:16.659917: step: 1016/530, loss: 0.10330505669116974
2023-01-23 01:26:17.778141: step: 1020/530, loss: 0.02688894420862198
2023-01-23 01:26:18.923317: step: 1024/530, loss: 0.003786420915275812
2023-01-23 01:26:20.058469: step: 1028/530, loss: 0.0174394603818655
2023-01-23 01:26:21.181434: step: 1032/530, loss: 0.011028338223695755
2023-01-23 01:26:22.314144: step: 1036/530, loss: 0.018026208505034447
2023-01-23 01:26:23.436579: step: 1040/530, loss: 0.07739534974098206
2023-01-23 01:26:24.582934: step: 1044/530, loss: 0.01706256903707981
2023-01-23 01:26:25.711581: step: 1048/530, loss: 0.0266692154109478
2023-01-23 01:26:26.860851: step: 1052/530, loss: 0.07829628139734268
2023-01-23 01:26:28.013532: step: 1056/530, loss: 0.019511796534061432
2023-01-23 01:26:29.138086: step: 1060/530, loss: 0.002972221467643976
2023-01-23 01:26:30.254852: step: 1064/530, loss: 0.03808288648724556
2023-01-23 01:26:31.386889: step: 1068/530, loss: 0.40817755460739136
2023-01-23 01:26:32.494928: step: 1072/530, loss: 0.08213977515697479
2023-01-23 01:26:33.619736: step: 1076/530, loss: 0.14943495392799377
2023-01-23 01:26:34.761041: step: 1080/530, loss: 0.0157381072640419
2023-01-23 01:26:35.886779: step: 1084/530, loss: 0.004616069607436657
2023-01-23 01:26:37.009440: step: 1088/530, loss: 0.07865428924560547
2023-01-23 01:26:38.137692: step: 1092/530, loss: 0.11023406684398651
2023-01-23 01:26:39.274877: step: 1096/530, loss: 0.07896137237548828
2023-01-23 01:26:40.405143: step: 1100/530, loss: 0.193163201212883
2023-01-23 01:26:41.508331: step: 1104/530, loss: 0.21725492179393768
2023-01-23 01:26:42.624334: step: 1108/530, loss: 0.01814866065979004
2023-01-23 01:26:43.749413: step: 1112/530, loss: 0.0029195784591138363
2023-01-23 01:26:44.845254: step: 1116/530, loss: 0.0165436752140522
2023-01-23 01:26:45.986035: step: 1120/530, loss: 0.02433796040713787
2023-01-23 01:26:47.130680: step: 1124/530, loss: 0.01960843987762928
2023-01-23 01:26:48.293198: step: 1128/530, loss: 0.028461933135986328
2023-01-23 01:26:49.416701: step: 1132/530, loss: 0.05832348018884659
2023-01-23 01:26:50.547364: step: 1136/530, loss: 0.0003609657287597656
2023-01-23 01:26:51.669108: step: 1140/530, loss: 0.008929729461669922
2023-01-23 01:26:52.799791: step: 1144/530, loss: 0.07246923446655273
2023-01-23 01:26:53.946341: step: 1148/530, loss: 0.010180855169892311
2023-01-23 01:26:55.073032: step: 1152/530, loss: 0.05389556661248207
2023-01-23 01:26:56.199726: step: 1156/530, loss: 0.011961890384554863
2023-01-23 01:26:57.366419: step: 1160/530, loss: 0.0748300552368164
2023-01-23 01:26:58.462921: step: 1164/530, loss: 0.0465640053153038
2023-01-23 01:26:59.564878: step: 1168/530, loss: 0.10560932010412216
2023-01-23 01:27:00.684744: step: 1172/530, loss: 0.03892073780298233
2023-01-23 01:27:01.826152: step: 1176/530, loss: 0.031076718121767044
2023-01-23 01:27:02.960402: step: 1180/530, loss: 0.02347918599843979
2023-01-23 01:27:04.082618: step: 1184/530, loss: 0.07828617095947266
2023-01-23 01:27:05.290911: step: 1188/530, loss: 0.1742088347673416
2023-01-23 01:27:06.459338: step: 1192/530, loss: 0.035913847386837006
2023-01-23 01:27:07.605587: step: 1196/530, loss: 0.006459998898208141
2023-01-23 01:27:08.738212: step: 1200/530, loss: 0.024181175976991653
2023-01-23 01:27:09.883587: step: 1204/530, loss: 0.042345236986875534
2023-01-23 01:27:11.034093: step: 1208/530, loss: 0.003262949176132679
2023-01-23 01:27:12.137628: step: 1212/530, loss: 0.11211252212524414
2023-01-23 01:27:13.285149: step: 1216/530, loss: 0.02284984663128853
2023-01-23 01:27:14.401170: step: 1220/530, loss: 0.04695471376180649
2023-01-23 01:27:15.515482: step: 1224/530, loss: 0.012668800540268421
2023-01-23 01:27:16.644663: step: 1228/530, loss: 0.1259150505065918
2023-01-23 01:27:17.771863: step: 1232/530, loss: 0.09182815998792648
2023-01-23 01:27:18.874231: step: 1236/530, loss: 0.030479764565825462
2023-01-23 01:27:20.000199: step: 1240/530, loss: 0.0050123692490160465
2023-01-23 01:27:21.111986: step: 1244/530, loss: 0.0282166488468647
2023-01-23 01:27:22.224318: step: 1248/530, loss: 0.0700405165553093
2023-01-23 01:27:23.366274: step: 1252/530, loss: 0.009382152929902077
2023-01-23 01:27:24.506183: step: 1256/530, loss: 0.030722713097929955
2023-01-23 01:27:25.659240: step: 1260/530, loss: 0.06939296424388885
2023-01-23 01:27:26.787167: step: 1264/530, loss: 0.047120094299316406
2023-01-23 01:27:27.900156: step: 1268/530, loss: 0.05680961534380913
2023-01-23 01:27:29.028062: step: 1272/530, loss: 0.06423606723546982
2023-01-23 01:27:30.145785: step: 1276/530, loss: 0.06578169018030167
2023-01-23 01:27:31.297916: step: 1280/530, loss: 0.008302784524857998
2023-01-23 01:27:32.410128: step: 1284/530, loss: 0.006422996520996094
2023-01-23 01:27:33.591210: step: 1288/530, loss: 0.025800514966249466
2023-01-23 01:27:34.725183: step: 1292/530, loss: 0.04233236610889435
2023-01-23 01:27:35.855642: step: 1296/530, loss: 0.00080194475594908
2023-01-23 01:27:36.976742: step: 1300/530, loss: 0.017215585336089134
2023-01-23 01:27:38.122329: step: 1304/530, loss: 0.049330711364746094
2023-01-23 01:27:39.269607: step: 1308/530, loss: 0.042549800127744675
2023-01-23 01:27:40.408143: step: 1312/530, loss: 0.052066802978515625
2023-01-23 01:27:41.544519: step: 1316/530, loss: 0.04202727973461151
2023-01-23 01:27:42.681690: step: 1320/530, loss: 0.06000897288322449
2023-01-23 01:27:43.797366: step: 1324/530, loss: 0.20177088677883148
2023-01-23 01:27:44.910050: step: 1328/530, loss: 0.051516056060791016
2023-01-23 01:27:46.035403: step: 1332/530, loss: 0.021866250783205032
2023-01-23 01:27:47.160701: step: 1336/530, loss: 0.02463226579129696
2023-01-23 01:27:48.283716: step: 1340/530, loss: 0.03839721903204918
2023-01-23 01:27:49.446859: step: 1344/530, loss: 0.03847694396972656
2023-01-23 01:27:50.574372: step: 1348/530, loss: 0.06000366061925888
2023-01-23 01:27:51.709699: step: 1352/530, loss: 0.0593835823237896
2023-01-23 01:27:52.846779: step: 1356/530, loss: 0.050646498799324036
2023-01-23 01:27:53.989284: step: 1360/530, loss: 0.009618950076401234
2023-01-23 01:27:55.158378: step: 1364/530, loss: 0.05122070387005806
2023-01-23 01:27:56.263213: step: 1368/530, loss: 0.028808213770389557
2023-01-23 01:27:57.393118: step: 1372/530, loss: 0.17811298370361328
2023-01-23 01:27:58.517199: step: 1376/530, loss: 0.03187117353081703
2023-01-23 01:27:59.635843: step: 1380/530, loss: 0.040517520159482956
2023-01-23 01:28:00.782633: step: 1384/530, loss: 0.640001654624939
2023-01-23 01:28:01.926132: step: 1388/530, loss: 0.044702719897031784
2023-01-23 01:28:03.044164: step: 1392/530, loss: 0.05064759403467178
2023-01-23 01:28:04.174712: step: 1396/530, loss: 0.06525421142578125
2023-01-23 01:28:05.292250: step: 1400/530, loss: 0.046235181391239166
2023-01-23 01:28:06.419452: step: 1404/530, loss: 0.024970628321170807
2023-01-23 01:28:07.538021: step: 1408/530, loss: 0.019870664924383163
2023-01-23 01:28:08.666685: step: 1412/530, loss: 0.1729743927717209
2023-01-23 01:28:09.781071: step: 1416/530, loss: 0.05711031332612038
2023-01-23 01:28:10.903063: step: 1420/530, loss: 0.07533387839794159
2023-01-23 01:28:12.004950: step: 1424/530, loss: 0.030455783009529114
2023-01-23 01:28:13.144783: step: 1428/530, loss: 0.0289122574031353
2023-01-23 01:28:14.289536: step: 1432/530, loss: 0.10187626630067825
2023-01-23 01:28:15.427910: step: 1436/530, loss: 0.03603868559002876
2023-01-23 01:28:16.560564: step: 1440/530, loss: 0.03162336349487305
2023-01-23 01:28:17.702257: step: 1444/530, loss: 0.020629405975341797
2023-01-23 01:28:18.833446: step: 1448/530, loss: 0.12042804062366486
2023-01-23 01:28:19.941776: step: 1452/530, loss: 0.03444423899054527
2023-01-23 01:28:21.064918: step: 1456/530, loss: 0.0018639564514160156
2023-01-23 01:28:22.201077: step: 1460/530, loss: 0.058011531829833984
2023-01-23 01:28:23.345831: step: 1464/530, loss: 0.276532918214798
2023-01-23 01:28:24.521175: step: 1468/530, loss: 0.145494282245636
2023-01-23 01:28:25.637351: step: 1472/530, loss: 0.03534507751464844
2023-01-23 01:28:26.764341: step: 1476/530, loss: 0.05287494510412216
2023-01-23 01:28:27.878689: step: 1480/530, loss: 0.04884395748376846
2023-01-23 01:28:29.003050: step: 1484/530, loss: 0.011091279797255993
2023-01-23 01:28:30.137857: step: 1488/530, loss: 0.010197639465332031
2023-01-23 01:28:31.275177: step: 1492/530, loss: 0.06927052140235901
2023-01-23 01:28:32.413313: step: 1496/530, loss: 0.05755405128002167
2023-01-23 01:28:33.576768: step: 1500/530, loss: 0.02384796179831028
2023-01-23 01:28:34.697689: step: 1504/530, loss: 0.5944212079048157
2023-01-23 01:28:35.828171: step: 1508/530, loss: 0.060752034187316895
2023-01-23 01:28:36.963083: step: 1512/530, loss: 0.10176029801368713
2023-01-23 01:28:38.082592: step: 1516/530, loss: 0.00897760409861803
2023-01-23 01:28:39.194067: step: 1520/530, loss: 0.096531942486763
2023-01-23 01:28:40.335982: step: 1524/530, loss: 0.02178940922021866
2023-01-23 01:28:41.475540: step: 1528/530, loss: 0.14092516899108887
2023-01-23 01:28:42.603719: step: 1532/530, loss: 0.04464459419250488
2023-01-23 01:28:43.712973: step: 1536/530, loss: 0.05871257930994034
2023-01-23 01:28:44.839698: step: 1540/530, loss: 0.008302975445985794
2023-01-23 01:28:45.967272: step: 1544/530, loss: 0.19416749477386475
2023-01-23 01:28:47.092195: step: 1548/530, loss: 0.027652930468320847
2023-01-23 01:28:48.259584: step: 1552/530, loss: 0.02328796312212944
2023-01-23 01:28:49.374132: step: 1556/530, loss: 0.0266539566218853
2023-01-23 01:28:50.488548: step: 1560/530, loss: 0.03760109096765518
2023-01-23 01:28:51.605536: step: 1564/530, loss: 0.11218070983886719
2023-01-23 01:28:52.718673: step: 1568/530, loss: 0.10916433483362198
2023-01-23 01:28:53.836334: step: 1572/530, loss: 0.03420887142419815
2023-01-23 01:28:54.971001: step: 1576/530, loss: 0.021595347672700882
2023-01-23 01:28:56.099921: step: 1580/530, loss: 0.06901824474334717
2023-01-23 01:28:57.241321: step: 1584/530, loss: 0.02319660224020481
2023-01-23 01:28:58.359621: step: 1588/530, loss: 0.02566986158490181
2023-01-23 01:28:59.474407: step: 1592/530, loss: 0.04655332863330841
2023-01-23 01:29:00.598017: step: 1596/530, loss: 0.031061720103025436
2023-01-23 01:29:01.699907: step: 1600/530, loss: 0.2984463572502136
2023-01-23 01:29:02.867184: step: 1604/530, loss: 0.04659252241253853
2023-01-23 01:29:03.985363: step: 1608/530, loss: 0.015270424075424671
2023-01-23 01:29:05.116858: step: 1612/530, loss: 0.024371527135372162
2023-01-23 01:29:06.237123: step: 1616/530, loss: 0.15676327049732208
2023-01-23 01:29:07.339853: step: 1620/530, loss: 0.17237024009227753
2023-01-23 01:29:08.471966: step: 1624/530, loss: 0.05896444618701935
2023-01-23 01:29:09.611644: step: 1628/530, loss: 0.10925626754760742
2023-01-23 01:29:10.734641: step: 1632/530, loss: 0.06329164654016495
2023-01-23 01:29:11.879364: step: 1636/530, loss: 0.13272634148597717
2023-01-23 01:29:12.983602: step: 1640/530, loss: 0.01004729326814413
2023-01-23 01:29:14.122679: step: 1644/530, loss: 0.10683955997228622
2023-01-23 01:29:15.262789: step: 1648/530, loss: 0.02809314802289009
2023-01-23 01:29:16.385254: step: 1652/530, loss: 0.01524581853300333
2023-01-23 01:29:17.554098: step: 1656/530, loss: 0.10205049812793732
2023-01-23 01:29:18.664039: step: 1660/530, loss: 0.09389620274305344
2023-01-23 01:29:19.792461: step: 1664/530, loss: 0.06841736286878586
2023-01-23 01:29:20.922804: step: 1668/530, loss: 0.022959517315030098
2023-01-23 01:29:22.063135: step: 1672/530, loss: 0.07232954353094101
2023-01-23 01:29:23.184750: step: 1676/530, loss: 0.06563596427440643
2023-01-23 01:29:24.289042: step: 1680/530, loss: 0.05518674850463867
2023-01-23 01:29:25.418584: step: 1684/530, loss: 0.05053729936480522
2023-01-23 01:29:26.534428: step: 1688/530, loss: 0.1637769639492035
2023-01-23 01:29:27.632810: step: 1692/530, loss: 0.03731890022754669
2023-01-23 01:29:28.773423: step: 1696/530, loss: 0.06530562043190002
2023-01-23 01:29:29.891696: step: 1700/530, loss: 0.01639573462307453
2023-01-23 01:29:31.014125: step: 1704/530, loss: 0.99970543384552
2023-01-23 01:29:32.160684: step: 1708/530, loss: 0.03499565273523331
2023-01-23 01:29:33.277598: step: 1712/530, loss: 0.0360812172293663
2023-01-23 01:29:34.389016: step: 1716/530, loss: 0.02043433114886284
2023-01-23 01:29:35.503734: step: 1720/530, loss: 0.04056520760059357
2023-01-23 01:29:36.656991: step: 1724/530, loss: 0.06651439517736435
2023-01-23 01:29:37.772515: step: 1728/530, loss: 0.020090769976377487
2023-01-23 01:29:38.887293: step: 1732/530, loss: 0.021418048068881035
2023-01-23 01:29:40.013283: step: 1736/530, loss: 0.06156749650835991
2023-01-23 01:29:41.129787: step: 1740/530, loss: 0.10172872990369797
2023-01-23 01:29:42.256150: step: 1744/530, loss: 0.16617614030838013
2023-01-23 01:29:43.426966: step: 1748/530, loss: 0.4521685838699341
2023-01-23 01:29:44.563015: step: 1752/530, loss: 0.09275803714990616
2023-01-23 01:29:45.712693: step: 1756/530, loss: 0.12140293419361115
2023-01-23 01:29:46.855843: step: 1760/530, loss: 0.12638473510742188
2023-01-23 01:29:47.979194: step: 1764/530, loss: 0.07202653586864471
2023-01-23 01:29:49.109883: step: 1768/530, loss: 0.6037311553955078
2023-01-23 01:29:50.246851: step: 1772/530, loss: 0.021046781912446022
2023-01-23 01:29:51.383587: step: 1776/530, loss: 0.019855499267578125
2023-01-23 01:29:52.527685: step: 1780/530, loss: 0.27081823348999023
2023-01-23 01:29:53.668767: step: 1784/530, loss: 0.0345311164855957
2023-01-23 01:29:54.777215: step: 1788/530, loss: 0.3245789706707001
2023-01-23 01:29:55.897202: step: 1792/530, loss: 0.04525794833898544
2023-01-23 01:29:57.023533: step: 1796/530, loss: 0.11900676786899567
2023-01-23 01:29:58.152990: step: 1800/530, loss: 0.09945344924926758
2023-01-23 01:29:59.292747: step: 1804/530, loss: 0.04015503078699112
2023-01-23 01:30:00.431496: step: 1808/530, loss: 0.030086733400821686
2023-01-23 01:30:01.540113: step: 1812/530, loss: 0.05636558309197426
2023-01-23 01:30:02.706253: step: 1816/530, loss: 0.013280868530273438
2023-01-23 01:30:03.841942: step: 1820/530, loss: 0.00011157989501953125
2023-01-23 01:30:04.952137: step: 1824/530, loss: 0.10377340018749237
2023-01-23 01:30:06.083870: step: 1828/530, loss: 0.024784373119473457
2023-01-23 01:30:07.236597: step: 1832/530, loss: 0.08820071071386337
2023-01-23 01:30:08.353784: step: 1836/530, loss: 0.03144865110516548
2023-01-23 01:30:09.480022: step: 1840/530, loss: 0.00724840210750699
2023-01-23 01:30:10.610275: step: 1844/530, loss: 0.10830254852771759
2023-01-23 01:30:11.730346: step: 1848/530, loss: 0.066503144800663
2023-01-23 01:30:12.850783: step: 1852/530, loss: 0.02907257154583931
2023-01-23 01:30:13.973413: step: 1856/530, loss: 0.04058127477765083
2023-01-23 01:30:15.105433: step: 1860/530, loss: 0.09039421379566193
2023-01-23 01:30:16.252273: step: 1864/530, loss: 0.07128114253282547
2023-01-23 01:30:17.375559: step: 1868/530, loss: 1.153980016708374
2023-01-23 01:30:18.557706: step: 1872/530, loss: 0.08205990493297577
2023-01-23 01:30:19.684121: step: 1876/530, loss: 0.02853412739932537
2023-01-23 01:30:20.796871: step: 1880/530, loss: 0.0814666748046875
2023-01-23 01:30:21.915925: step: 1884/530, loss: 0.02749776840209961
2023-01-23 01:30:23.057634: step: 1888/530, loss: 0.07677202671766281
2023-01-23 01:30:24.177701: step: 1892/530, loss: 0.04359283670783043
2023-01-23 01:30:25.288478: step: 1896/530, loss: 0.043320465832948685
2023-01-23 01:30:26.416801: step: 1900/530, loss: 0.0574478916823864
2023-01-23 01:30:27.552482: step: 1904/530, loss: 0.03754854202270508
2023-01-23 01:30:28.699285: step: 1908/530, loss: 0.0698099136352539
2023-01-23 01:30:29.841029: step: 1912/530, loss: 0.01396979484707117
2023-01-23 01:30:30.975146: step: 1916/530, loss: 0.02376404032111168
2023-01-23 01:30:32.154716: step: 1920/530, loss: 0.08164024353027344
2023-01-23 01:30:33.262400: step: 1924/530, loss: 0.05492382124066353
2023-01-23 01:30:34.400134: step: 1928/530, loss: 0.02073955535888672
2023-01-23 01:30:35.528765: step: 1932/530, loss: 0.001667881035245955
2023-01-23 01:30:36.648512: step: 1936/530, loss: 0.041443921625614166
2023-01-23 01:30:37.767276: step: 1940/530, loss: 0.3478538393974304
2023-01-23 01:30:38.861272: step: 1944/530, loss: 0.10430584102869034
2023-01-23 01:30:39.965803: step: 1948/530, loss: 0.281054824590683
2023-01-23 01:30:41.105998: step: 1952/530, loss: 0.034300997853279114
2023-01-23 01:30:42.232965: step: 1956/530, loss: 0.03845549002289772
2023-01-23 01:30:43.354658: step: 1960/530, loss: 3.0636723041534424
2023-01-23 01:30:44.464674: step: 1964/530, loss: 0.08521699905395508
2023-01-23 01:30:45.590749: step: 1968/530, loss: 0.036104965955019
2023-01-23 01:30:46.702291: step: 1972/530, loss: 0.12650585174560547
2023-01-23 01:30:47.866432: step: 1976/530, loss: 0.0829019546508789
2023-01-23 01:30:49.033259: step: 1980/530, loss: 0.1659226417541504
2023-01-23 01:30:50.163178: step: 1984/530, loss: 0.04490480571985245
2023-01-23 01:30:51.269986: step: 1988/530, loss: 0.23819756507873535
2023-01-23 01:30:52.393667: step: 1992/530, loss: 0.08589334785938263
2023-01-23 01:30:53.487211: step: 1996/530, loss: 0.01590270921587944
2023-01-23 01:30:54.623860: step: 2000/530, loss: 0.4315044581890106
2023-01-23 01:30:55.751299: step: 2004/530, loss: 0.051927998661994934
2023-01-23 01:30:56.870582: step: 2008/530, loss: 0.028842829167842865
2023-01-23 01:30:58.008766: step: 2012/530, loss: 0.02912616729736328
2023-01-23 01:30:59.122658: step: 2016/530, loss: 0.04855956882238388
2023-01-23 01:31:00.255630: step: 2020/530, loss: 0.04493856430053711
2023-01-23 01:31:01.387982: step: 2024/530, loss: 0.010172081179916859
2023-01-23 01:31:02.587700: step: 2028/530, loss: 0.12167644500732422
2023-01-23 01:31:03.750911: step: 2032/530, loss: 0.019178105518221855
2023-01-23 01:31:04.848029: step: 2036/530, loss: 0.05155201256275177
2023-01-23 01:31:05.972194: step: 2040/530, loss: 0.0021677971817553043
2023-01-23 01:31:07.116820: step: 2044/530, loss: 0.06638431549072266
2023-01-23 01:31:08.288532: step: 2048/530, loss: 0.01248855609446764
2023-01-23 01:31:09.405526: step: 2052/530, loss: 0.13607816398143768
2023-01-23 01:31:10.510541: step: 2056/530, loss: 0.03781623765826225
2023-01-23 01:31:11.654831: step: 2060/530, loss: 0.03121051751077175
2023-01-23 01:31:12.807914: step: 2064/530, loss: 0.036220550537109375
2023-01-23 01:31:13.937066: step: 2068/530, loss: 0.03292284160852432
2023-01-23 01:31:15.039144: step: 2072/530, loss: 7.696151442360133e-05
2023-01-23 01:31:16.178699: step: 2076/530, loss: 0.17656850814819336
2023-01-23 01:31:17.296547: step: 2080/530, loss: 0.012176895514130592
2023-01-23 01:31:18.419471: step: 2084/530, loss: 0.10169430077075958
2023-01-23 01:31:19.534297: step: 2088/530, loss: 0.07025375217199326
2023-01-23 01:31:20.677784: step: 2092/530, loss: 0.07257194817066193
2023-01-23 01:31:21.783645: step: 2096/530, loss: 0.011845779605209827
2023-01-23 01:31:22.910170: step: 2100/530, loss: 0.019803810864686966
2023-01-23 01:31:24.030688: step: 2104/530, loss: 0.023592090234160423
2023-01-23 01:31:25.177217: step: 2108/530, loss: 0.024277402088046074
2023-01-23 01:31:26.305815: step: 2112/530, loss: 0.015037250705063343
2023-01-23 01:31:27.434397: step: 2116/530, loss: 0.03745584562420845
2023-01-23 01:31:28.542602: step: 2120/530, loss: 0.09587268531322479
==================================================
Loss: 0.081
--------------------
Dev: {'event': {'p': 0.6010471204188481, 'r': 0.7643142476697736, 'f1': 0.6729191090269636}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 11}
Test: {'event': {'p': 0.645933014354067, 'r': 0.7714285714285715, 'f1': 0.7031250000000001}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 11}
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': 11}
Korean: {'event': {'p': 0.6538461538461539, 'r': 0.5396825396825397, 'f1': 0.5913043478260869}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 11}
Russian: {'event': {'p': 0.46153846153846156, 'r': 0.5, 'f1': 0.48000000000000004}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 11}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Chinese: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Chinese: {'event': {'p': 0.6190476190476191, 'r': 0.9629629629629629, 'f1': 0.7536231884057971}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5877016129032258, 'r': 0.7762982689747004, 'f1': 0.6689615605278255}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Korean: {'event': {'p': 0.6539923954372624, 'r': 0.7862857142857143, 'f1': 0.7140633108458745}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Korean: {'event': {'p': 0.6666666666666666, 'r': 0.6349206349206349, 'f1': 0.6504065040650407}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5319148936170213, 'r': 0.6944444444444444, 'f1': 0.6024096385542169}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
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 01:32:09.168034: step: 4/530, loss: 0.04146585613489151
2023-01-23 01:32:10.302041: step: 8/530, loss: 0.0164960864931345
2023-01-23 01:32:11.462146: step: 12/530, loss: 0.03456135094165802
2023-01-23 01:32:12.581574: step: 16/530, loss: 0.18468494713306427
2023-01-23 01:32:13.684902: step: 20/530, loss: 0.09135501831769943
2023-01-23 01:32:14.809312: step: 24/530, loss: 0.027293110266327858
2023-01-23 01:32:15.938821: step: 28/530, loss: 0.04382496327161789
2023-01-23 01:32:17.036915: step: 32/530, loss: 0.12391787022352219
2023-01-23 01:32:18.203138: step: 36/530, loss: 0.06755166500806808
2023-01-23 01:32:19.335459: step: 40/530, loss: 0.007240963168442249
2023-01-23 01:32:20.433346: step: 44/530, loss: 0.0015702247619628906
2023-01-23 01:32:21.553676: step: 48/530, loss: 0.06069831922650337
2023-01-23 01:32:22.669149: step: 52/530, loss: 0.06297197192907333
2023-01-23 01:32:23.777626: step: 56/530, loss: 0.14973267912864685
2023-01-23 01:32:24.897673: step: 60/530, loss: 0.0063460348173975945
2023-01-23 01:32:26.014399: step: 64/530, loss: 0.2561872601509094
2023-01-23 01:32:27.125053: step: 68/530, loss: 0.03596191480755806
2023-01-23 01:32:28.246620: step: 72/530, loss: 0.0290814395993948
2023-01-23 01:32:29.397299: step: 76/530, loss: 0.049086377024650574
2023-01-23 01:32:30.501151: step: 80/530, loss: 0.0009068489307537675
2023-01-23 01:32:31.631449: step: 84/530, loss: 0.09232454001903534
2023-01-23 01:32:32.760570: step: 88/530, loss: 0.0063554286025464535
2023-01-23 01:32:33.904023: step: 92/530, loss: 0.10055732727050781
2023-01-23 01:32:35.007325: step: 96/530, loss: 0.08032207190990448
2023-01-23 01:32:36.116403: step: 100/530, loss: 0.03787975385785103
2023-01-23 01:32:37.257103: step: 104/530, loss: 0.009539986029267311
2023-01-23 01:32:38.396885: step: 108/530, loss: 0.022919846698641777
2023-01-23 01:32:39.538017: step: 112/530, loss: 0.0420568473637104
2023-01-23 01:32:40.671218: step: 116/530, loss: 0.024195099249482155
2023-01-23 01:32:41.795731: step: 120/530, loss: 0.02817096747457981
2023-01-23 01:32:42.926896: step: 124/530, loss: 0.05008964613080025
2023-01-23 01:32:44.043592: step: 128/530, loss: 0.13800200819969177
2023-01-23 01:32:45.165876: step: 132/530, loss: 0.0007683277362957597
2023-01-23 01:32:46.292198: step: 136/530, loss: 0.04119687154889107
2023-01-23 01:32:47.420339: step: 140/530, loss: 0.4442861080169678
2023-01-23 01:32:48.507598: step: 144/530, loss: 0.07509423047304153
2023-01-23 01:32:49.616454: step: 148/530, loss: 0.05681591108441353
2023-01-23 01:32:50.728469: step: 152/530, loss: 0.005243396852165461
2023-01-23 01:32:51.816702: step: 156/530, loss: 0.05020580440759659
2023-01-23 01:32:52.956950: step: 160/530, loss: 0.08720698952674866
2023-01-23 01:32:54.111054: step: 164/530, loss: 0.07956667244434357
2023-01-23 01:32:55.240880: step: 168/530, loss: 0.06377530097961426
2023-01-23 01:32:56.368001: step: 172/530, loss: 0.016119956970214844
2023-01-23 01:32:57.505316: step: 176/530, loss: 0.017048906534910202
2023-01-23 01:32:58.631981: step: 180/530, loss: 0.05277865007519722
2023-01-23 01:32:59.767030: step: 184/530, loss: 0.0050366404466331005
2023-01-23 01:33:00.925417: step: 188/530, loss: 0.05620727688074112
2023-01-23 01:33:02.087390: step: 192/530, loss: 0.05632200092077255
2023-01-23 01:33:03.201604: step: 196/530, loss: 0.15684758126735687
2023-01-23 01:33:04.315874: step: 200/530, loss: 0.0258638858795166
2023-01-23 01:33:05.443686: step: 204/530, loss: 0.029148291796445847
2023-01-23 01:33:06.590149: step: 208/530, loss: 0.01912403106689453
2023-01-23 01:33:07.712684: step: 212/530, loss: 0.011973000131547451
2023-01-23 01:33:08.812273: step: 216/530, loss: 0.04125671461224556
2023-01-23 01:33:09.914931: step: 220/530, loss: 0.09170989692211151
2023-01-23 01:33:11.065981: step: 224/530, loss: 0.040692903101444244
2023-01-23 01:33:12.186302: step: 228/530, loss: 0.014829372987151146
2023-01-23 01:33:13.295500: step: 232/530, loss: 0.025092124938964844
2023-01-23 01:33:14.417324: step: 236/530, loss: 0.0481724739074707
2023-01-23 01:33:15.547470: step: 240/530, loss: 0.06974754482507706
2023-01-23 01:33:16.677153: step: 244/530, loss: 0.06489360332489014
2023-01-23 01:33:17.806322: step: 248/530, loss: 0.018863869830965996
2023-01-23 01:33:18.921802: step: 252/530, loss: 0.003004169324412942
2023-01-23 01:33:20.024954: step: 256/530, loss: 0.008741474710404873
2023-01-23 01:33:21.161563: step: 260/530, loss: 0.023272132501006126
2023-01-23 01:33:22.276785: step: 264/530, loss: 0.8038443922996521
2023-01-23 01:33:23.428505: step: 268/530, loss: 0.004899454303085804
2023-01-23 01:33:24.565223: step: 272/530, loss: 0.04940157011151314
2023-01-23 01:33:25.673479: step: 276/530, loss: 0.07593349367380142
2023-01-23 01:33:26.813705: step: 280/530, loss: 0.008756637573242188
2023-01-23 01:33:27.941458: step: 284/530, loss: 0.04515376314520836
2023-01-23 01:33:29.121845: step: 288/530, loss: 0.024807455018162727
2023-01-23 01:33:30.277275: step: 292/530, loss: 0.1753520965576172
2023-01-23 01:33:31.421514: step: 296/530, loss: 0.012975931167602539
2023-01-23 01:33:32.566908: step: 300/530, loss: 0.0167604461312294
2023-01-23 01:33:33.731271: step: 304/530, loss: 0.004330158233642578
2023-01-23 01:33:34.862984: step: 308/530, loss: 6.226780414581299
2023-01-23 01:33:35.980559: step: 312/530, loss: 0.034804344177246094
2023-01-23 01:33:37.087107: step: 316/530, loss: 0.005957412999123335
2023-01-23 01:33:38.215990: step: 320/530, loss: 0.04643554985523224
2023-01-23 01:33:39.335920: step: 324/530, loss: 0.04254427179694176
2023-01-23 01:33:40.454348: step: 328/530, loss: 0.09731712937355042
2023-01-23 01:33:41.583340: step: 332/530, loss: 0.008234405890107155
2023-01-23 01:33:42.684956: step: 336/530, loss: 0.07836703956127167
2023-01-23 01:33:43.803972: step: 340/530, loss: 0.032621145248413086
2023-01-23 01:33:44.928342: step: 344/530, loss: 0.031035710126161575
2023-01-23 01:33:46.083780: step: 348/530, loss: 0.0398748405277729
2023-01-23 01:33:47.247096: step: 352/530, loss: 0.07766761630773544
2023-01-23 01:33:48.339031: step: 356/530, loss: 0.03663988411426544
2023-01-23 01:33:49.453951: step: 360/530, loss: 0.005725192837417126
2023-01-23 01:33:50.553605: step: 364/530, loss: 0.03603353351354599
2023-01-23 01:33:51.685834: step: 368/530, loss: 0.05004243552684784
2023-01-23 01:33:52.773552: step: 372/530, loss: 0.16664715111255646
2023-01-23 01:33:53.908430: step: 376/530, loss: 0.08054390549659729
2023-01-23 01:33:55.011607: step: 380/530, loss: 0.08258800953626633
2023-01-23 01:33:56.137102: step: 384/530, loss: 0.0011554717784747481
2023-01-23 01:33:57.246592: step: 388/530, loss: 0.0006314754718914628
2023-01-23 01:33:58.383075: step: 392/530, loss: 0.009018135257065296
2023-01-23 01:33:59.522207: step: 396/530, loss: 0.045431043952703476
2023-01-23 01:34:00.634695: step: 400/530, loss: 0.008813095279037952
2023-01-23 01:34:01.796254: step: 404/530, loss: 0.018123149871826172
2023-01-23 01:34:02.969965: step: 408/530, loss: 0.12108249962329865
2023-01-23 01:34:04.124084: step: 412/530, loss: 0.06378650665283203
2023-01-23 01:34:05.256926: step: 416/530, loss: 0.048793695867061615
2023-01-23 01:34:06.419632: step: 420/530, loss: 0.017655229195952415
2023-01-23 01:34:07.567625: step: 424/530, loss: 0.012522506527602673
2023-01-23 01:34:08.717459: step: 428/530, loss: 0.06374216079711914
2023-01-23 01:34:09.845867: step: 432/530, loss: 0.10491828620433807
2023-01-23 01:34:11.003200: step: 436/530, loss: 0.0975012332201004
2023-01-23 01:34:12.120322: step: 440/530, loss: 0.0031029225792735815
2023-01-23 01:34:13.262761: step: 444/530, loss: 0.09400520473718643
2023-01-23 01:34:14.384770: step: 448/530, loss: 0.013028335757553577
2023-01-23 01:34:15.527758: step: 452/530, loss: 0.045618344098329544
2023-01-23 01:34:16.671036: step: 456/530, loss: 0.03030386008322239
2023-01-23 01:34:17.805812: step: 460/530, loss: 0.02246379852294922
2023-01-23 01:34:18.910334: step: 464/530, loss: 0.012247848324477673
2023-01-23 01:34:20.009820: step: 468/530, loss: 0.016779230907559395
2023-01-23 01:34:21.114898: step: 472/530, loss: 0.0005039215320721269
2023-01-23 01:34:22.226119: step: 476/530, loss: 0.009072018787264824
2023-01-23 01:34:23.367869: step: 480/530, loss: 0.03471393510699272
2023-01-23 01:34:24.487422: step: 484/530, loss: 0.017095565795898438
2023-01-23 01:34:25.583380: step: 488/530, loss: 0.04830913990736008
2023-01-23 01:34:26.724809: step: 492/530, loss: 0.007652092259377241
2023-01-23 01:34:27.851024: step: 496/530, loss: 0.02378563955426216
2023-01-23 01:34:28.961515: step: 500/530, loss: 0.026201438158750534
2023-01-23 01:34:30.086384: step: 504/530, loss: 0.03820495679974556
2023-01-23 01:34:31.219825: step: 508/530, loss: 0.023201845586299896
2023-01-23 01:34:32.354968: step: 512/530, loss: 0.015618515200912952
2023-01-23 01:34:33.457165: step: 516/530, loss: 0.008405590429902077
2023-01-23 01:34:34.575795: step: 520/530, loss: 0.013255024328827858
2023-01-23 01:34:35.737369: step: 524/530, loss: 0.36251935362815857
2023-01-23 01:34:36.860805: step: 528/530, loss: 0.0015875815879553556
2023-01-23 01:34:37.988793: step: 532/530, loss: 0.015517806634306908
2023-01-23 01:34:39.133062: step: 536/530, loss: 0.12606608867645264
2023-01-23 01:34:40.257164: step: 540/530, loss: 0.010173225775361061
2023-01-23 01:34:41.417724: step: 544/530, loss: 0.006377696990966797
2023-01-23 01:34:42.510299: step: 548/530, loss: 0.05588836595416069
2023-01-23 01:34:43.630149: step: 552/530, loss: 0.06918372958898544
2023-01-23 01:34:44.756958: step: 556/530, loss: 0.09663286805152893
2023-01-23 01:34:45.913717: step: 560/530, loss: 0.06582470238208771
2023-01-23 01:34:47.043988: step: 564/530, loss: 0.025864887982606888
2023-01-23 01:34:48.178075: step: 568/530, loss: 0.053361132740974426
2023-01-23 01:34:49.288187: step: 572/530, loss: 0.016445159912109375
2023-01-23 01:34:50.434809: step: 576/530, loss: 0.12411890178918839
2023-01-23 01:34:51.571165: step: 580/530, loss: 0.021427059546113014
2023-01-23 01:34:52.708533: step: 584/530, loss: 0.06904029846191406
2023-01-23 01:34:53.819970: step: 588/530, loss: 0.13493481278419495
2023-01-23 01:34:54.937669: step: 592/530, loss: 0.029292868450284004
2023-01-23 01:34:56.056657: step: 596/530, loss: 0.009181786328554153
2023-01-23 01:34:57.196747: step: 600/530, loss: 0.05648374557495117
2023-01-23 01:34:58.319455: step: 604/530, loss: 0.038665641099214554
2023-01-23 01:34:59.455010: step: 608/530, loss: 0.009718894958496094
2023-01-23 01:35:00.592857: step: 612/530, loss: 0.008212280459702015
2023-01-23 01:35:01.716750: step: 616/530, loss: 0.08202342689037323
2023-01-23 01:35:02.861366: step: 620/530, loss: 0.005619812291115522
2023-01-23 01:35:04.012208: step: 624/530, loss: 0.054976511746644974
2023-01-23 01:35:05.105566: step: 628/530, loss: 0.03801391273736954
2023-01-23 01:35:06.244168: step: 632/530, loss: 0.016525745391845703
2023-01-23 01:35:07.370410: step: 636/530, loss: 0.08721990883350372
2023-01-23 01:35:08.511161: step: 640/530, loss: 0.02155628241598606
2023-01-23 01:35:09.631102: step: 644/530, loss: 0.09035935997962952
2023-01-23 01:35:10.759560: step: 648/530, loss: 0.029609205201268196
2023-01-23 01:35:11.877924: step: 652/530, loss: 0.019499968737363815
2023-01-23 01:35:13.011909: step: 656/530, loss: 0.03985252603888512
2023-01-23 01:35:14.138894: step: 660/530, loss: 0.087981678545475
2023-01-23 01:35:15.286825: step: 664/530, loss: 0.059149932116270065
2023-01-23 01:35:16.392790: step: 668/530, loss: 0.06220431625843048
2023-01-23 01:35:17.513010: step: 672/530, loss: 0.002528381533920765
2023-01-23 01:35:18.655613: step: 676/530, loss: 0.028195716440677643
2023-01-23 01:35:19.787724: step: 680/530, loss: 0.024074697867035866
2023-01-23 01:35:20.891623: step: 684/530, loss: 0.0861758217215538
2023-01-23 01:35:22.024447: step: 688/530, loss: 0.09414668381214142
2023-01-23 01:35:23.155170: step: 692/530, loss: 0.024211978539824486
2023-01-23 01:35:24.274351: step: 696/530, loss: 0.02629375457763672
2023-01-23 01:35:25.427755: step: 700/530, loss: 0.0645742416381836
2023-01-23 01:35:26.583592: step: 704/530, loss: 0.027009274810552597
2023-01-23 01:35:27.719755: step: 708/530, loss: 0.07800912857055664
2023-01-23 01:35:28.806604: step: 712/530, loss: 0.014352703467011452
2023-01-23 01:35:29.924173: step: 716/530, loss: 0.04800605773925781
2023-01-23 01:35:31.024581: step: 720/530, loss: 0.08245086669921875
2023-01-23 01:35:32.156549: step: 724/530, loss: 0.01673748530447483
2023-01-23 01:35:33.316677: step: 728/530, loss: 0.07929801940917969
2023-01-23 01:35:34.451477: step: 732/530, loss: 0.002699923701584339
2023-01-23 01:35:35.584780: step: 736/530, loss: 0.07265863567590714
2023-01-23 01:35:36.709041: step: 740/530, loss: 0.028813553974032402
2023-01-23 01:35:37.807769: step: 744/530, loss: 0.04370279610157013
2023-01-23 01:35:38.960079: step: 748/530, loss: 0.00019559860811568797
2023-01-23 01:35:40.093768: step: 752/530, loss: 0.031233882531523705
2023-01-23 01:35:41.226737: step: 756/530, loss: 0.00712242117151618
2023-01-23 01:35:42.352223: step: 760/530, loss: 0.009337044321000576
2023-01-23 01:35:43.468727: step: 764/530, loss: 0.8297949433326721
2023-01-23 01:35:44.571392: step: 768/530, loss: 0.027551794424653053
2023-01-23 01:35:45.707840: step: 772/530, loss: 0.05590534210205078
2023-01-23 01:35:46.811088: step: 776/530, loss: 0.043745994567871094
2023-01-23 01:35:47.925535: step: 780/530, loss: 0.010922812856733799
2023-01-23 01:35:49.084126: step: 784/530, loss: 0.04017524793744087
2023-01-23 01:35:50.204961: step: 788/530, loss: 0.039598654955625534
2023-01-23 01:35:51.319806: step: 792/530, loss: 0.007432460784912109
2023-01-23 01:35:52.469670: step: 796/530, loss: 0.007860946469008923
2023-01-23 01:35:53.630608: step: 800/530, loss: 0.016886234283447266
2023-01-23 01:35:54.765394: step: 804/530, loss: 0.03184347227215767
2023-01-23 01:35:55.895200: step: 808/530, loss: 0.02033214643597603
2023-01-23 01:35:57.000732: step: 812/530, loss: 0.03039254993200302
2023-01-23 01:35:58.144096: step: 816/530, loss: 0.07868233323097229
2023-01-23 01:35:59.303291: step: 820/530, loss: 0.010586929507553577
2023-01-23 01:36:00.448796: step: 824/530, loss: 0.4011600613594055
2023-01-23 01:36:01.571748: step: 828/530, loss: 0.0167218204587698
2023-01-23 01:36:02.692477: step: 832/530, loss: 0.16747525334358215
2023-01-23 01:36:03.812859: step: 836/530, loss: 0.04014711454510689
2023-01-23 01:36:04.933018: step: 840/530, loss: 0.0198395736515522
2023-01-23 01:36:06.053837: step: 844/530, loss: 0.0016194343334063888
2023-01-23 01:36:07.165773: step: 848/530, loss: 0.05386009067296982
2023-01-23 01:36:08.289998: step: 852/530, loss: 0.035674382001161575
2023-01-23 01:36:09.401678: step: 856/530, loss: 0.02274188958108425
2023-01-23 01:36:10.545825: step: 860/530, loss: 0.030316829681396484
2023-01-23 01:36:11.673835: step: 864/530, loss: 0.0369170680642128
2023-01-23 01:36:12.778333: step: 868/530, loss: 0.027235697954893112
2023-01-23 01:36:13.907363: step: 872/530, loss: 0.031687356531620026
2023-01-23 01:36:14.988230: step: 876/530, loss: 0.006474614143371582
2023-01-23 01:36:16.112862: step: 880/530, loss: 0.02765359915792942
2023-01-23 01:36:17.254492: step: 884/530, loss: 0.11171627789735794
2023-01-23 01:36:18.373417: step: 888/530, loss: 0.026321982964873314
2023-01-23 01:36:19.502842: step: 892/530, loss: 0.0026480676606297493
2023-01-23 01:36:20.653569: step: 896/530, loss: 0.01588573306798935
2023-01-23 01:36:21.771463: step: 900/530, loss: 0.07487421482801437
2023-01-23 01:36:22.863305: step: 904/530, loss: 0.040831565856933594
2023-01-23 01:36:23.985073: step: 908/530, loss: 0.41110649704933167
2023-01-23 01:36:25.089821: step: 912/530, loss: 0.03103947825729847
2023-01-23 01:36:26.220693: step: 916/530, loss: 0.1822216659784317
2023-01-23 01:36:27.345844: step: 920/530, loss: 0.01214895211160183
2023-01-23 01:36:28.428076: step: 924/530, loss: 0.015990495681762695
2023-01-23 01:36:29.562723: step: 928/530, loss: 0.5049837827682495
2023-01-23 01:36:30.682340: step: 932/530, loss: 0.008755683898925781
2023-01-23 01:36:31.821822: step: 936/530, loss: 0.05490703508257866
2023-01-23 01:36:32.935967: step: 940/530, loss: 0.019974518567323685
2023-01-23 01:36:34.044985: step: 944/530, loss: 0.016568278893828392
2023-01-23 01:36:35.170544: step: 948/530, loss: 0.004858541768044233
2023-01-23 01:36:36.297817: step: 952/530, loss: 0.0048694610595703125
2023-01-23 01:36:37.426293: step: 956/530, loss: 0.060088206082582474
2023-01-23 01:36:38.550810: step: 960/530, loss: 0.004809761419892311
2023-01-23 01:36:39.680370: step: 964/530, loss: 0.04707353189587593
2023-01-23 01:36:40.802528: step: 968/530, loss: 0.03624153137207031
2023-01-23 01:36:41.953124: step: 972/530, loss: 0.020730018615722656
2023-01-23 01:36:43.077384: step: 976/530, loss: 0.03426048532128334
2023-01-23 01:36:44.224527: step: 980/530, loss: 0.025171946734189987
2023-01-23 01:36:45.372495: step: 984/530, loss: 0.009561729617416859
2023-01-23 01:36:46.524985: step: 988/530, loss: 0.07763605564832687
2023-01-23 01:36:47.660078: step: 992/530, loss: 0.027331778779625893
2023-01-23 01:36:48.777812: step: 996/530, loss: 0.7535378932952881
2023-01-23 01:36:49.890706: step: 1000/530, loss: 0.0663982480764389
2023-01-23 01:36:51.006681: step: 1004/530, loss: 0.03893308714032173
2023-01-23 01:36:52.111588: step: 1008/530, loss: 0.011975526809692383
2023-01-23 01:36:53.224304: step: 1012/530, loss: 0.09670901298522949
2023-01-23 01:36:54.343519: step: 1016/530, loss: 0.016979694366455078
2023-01-23 01:36:55.485984: step: 1020/530, loss: 0.019005490466952324
2023-01-23 01:36:56.609027: step: 1024/530, loss: 0.04517097398638725
2023-01-23 01:36:57.751354: step: 1028/530, loss: 0.011025047861039639
2023-01-23 01:36:58.889176: step: 1032/530, loss: 0.1146320328116417
2023-01-23 01:37:00.038931: step: 1036/530, loss: 0.06828584522008896
2023-01-23 01:37:01.145971: step: 1040/530, loss: 0.1598796844482422
2023-01-23 01:37:02.246543: step: 1044/530, loss: 0.10229549556970596
2023-01-23 01:37:03.371677: step: 1048/530, loss: 0.017337609082460403
2023-01-23 01:37:04.534052: step: 1052/530, loss: 0.036089349538087845
2023-01-23 01:37:05.656976: step: 1056/530, loss: 0.0346127524971962
2023-01-23 01:37:06.754836: step: 1060/530, loss: 0.007623481564223766
2023-01-23 01:37:07.861353: step: 1064/530, loss: 0.050319671630859375
2023-01-23 01:37:09.012895: step: 1068/530, loss: 0.01645965501666069
2023-01-23 01:37:10.123524: step: 1072/530, loss: 0.04982910305261612
2023-01-23 01:37:11.274956: step: 1076/530, loss: 0.024080883711576462
2023-01-23 01:37:12.387280: step: 1080/530, loss: 0.02354259416460991
2023-01-23 01:37:13.495372: step: 1084/530, loss: 0.03885345533490181
2023-01-23 01:37:14.625638: step: 1088/530, loss: 0.05298004299402237
2023-01-23 01:37:15.748838: step: 1092/530, loss: 0.02705850638449192
2023-01-23 01:37:16.898290: step: 1096/530, loss: 0.04123878479003906
2023-01-23 01:37:18.001590: step: 1100/530, loss: 0.10094118118286133
2023-01-23 01:37:19.134308: step: 1104/530, loss: 0.029483605176210403
2023-01-23 01:37:20.260265: step: 1108/530, loss: 0.11217517405748367
2023-01-23 01:37:21.361395: step: 1112/530, loss: 0.17927446961402893
2023-01-23 01:37:22.486006: step: 1116/530, loss: 0.07067833095788956
2023-01-23 01:37:23.637746: step: 1120/530, loss: 0.1162746399641037
2023-01-23 01:37:24.764959: step: 1124/530, loss: 0.0340668186545372
2023-01-23 01:37:25.881833: step: 1128/530, loss: 0.007141590118408203
2023-01-23 01:37:27.006634: step: 1132/530, loss: 0.03126878663897514
2023-01-23 01:37:28.119581: step: 1136/530, loss: 0.03748369216918945
2023-01-23 01:37:29.255791: step: 1140/530, loss: 0.001227092812769115
2023-01-23 01:37:30.361899: step: 1144/530, loss: 0.02130298689007759
2023-01-23 01:37:31.505832: step: 1148/530, loss: 0.012703514657914639
2023-01-23 01:37:32.618448: step: 1152/530, loss: 0.2367529422044754
2023-01-23 01:37:33.723503: step: 1156/530, loss: 0.0236591175198555
2023-01-23 01:37:34.847460: step: 1160/530, loss: 0.0019272805657237768
2023-01-23 01:37:35.985723: step: 1164/530, loss: 0.052582789212465286
2023-01-23 01:37:37.175475: step: 1168/530, loss: 0.12448345124721527
2023-01-23 01:37:38.288113: step: 1172/530, loss: 0.2623058259487152
2023-01-23 01:37:39.414281: step: 1176/530, loss: 0.03934812545776367
2023-01-23 01:37:40.520081: step: 1180/530, loss: 0.05309572443366051
2023-01-23 01:37:41.634967: step: 1184/530, loss: 0.03446225821971893
2023-01-23 01:37:42.761813: step: 1188/530, loss: 0.0435122586786747
2023-01-23 01:37:43.900213: step: 1192/530, loss: 0.0553533099591732
2023-01-23 01:37:45.022072: step: 1196/530, loss: 0.013289928436279297
2023-01-23 01:37:46.149082: step: 1200/530, loss: 0.013298642821609974
2023-01-23 01:37:47.310881: step: 1204/530, loss: 0.02317214012145996
2023-01-23 01:37:48.474692: step: 1208/530, loss: 0.058649253100156784
2023-01-23 01:37:49.619325: step: 1212/530, loss: 1.4833146333694458
2023-01-23 01:37:50.744094: step: 1216/530, loss: 0.025757789611816406
2023-01-23 01:37:51.857070: step: 1220/530, loss: 0.041926003992557526
2023-01-23 01:37:52.979282: step: 1224/530, loss: 0.11770649254322052
2023-01-23 01:37:54.094626: step: 1228/530, loss: 0.0029358863830566406
2023-01-23 01:37:55.225819: step: 1232/530, loss: 0.9838047027587891
2023-01-23 01:37:56.330131: step: 1236/530, loss: 0.04121103510260582
2023-01-23 01:37:57.487265: step: 1240/530, loss: 0.05901211500167847
2023-01-23 01:37:58.637631: step: 1244/530, loss: 0.0799943059682846
2023-01-23 01:37:59.782957: step: 1248/530, loss: 0.09362554550170898
2023-01-23 01:38:00.905853: step: 1252/530, loss: 1.3456366062164307
2023-01-23 01:38:02.089477: step: 1256/530, loss: 0.030677413567900658
2023-01-23 01:38:03.233707: step: 1260/530, loss: 0.09209322929382324
2023-01-23 01:38:04.348097: step: 1264/530, loss: 0.031025506556034088
2023-01-23 01:38:05.450362: step: 1268/530, loss: 0.008028984069824219
2023-01-23 01:38:06.568355: step: 1272/530, loss: 0.06793183833360672
2023-01-23 01:38:07.711884: step: 1276/530, loss: 0.030474090948700905
2023-01-23 01:38:08.816127: step: 1280/530, loss: 0.007448864169418812
2023-01-23 01:38:09.955592: step: 1284/530, loss: 0.027852153405547142
2023-01-23 01:38:11.087260: step: 1288/530, loss: 0.10311603546142578
2023-01-23 01:38:12.221526: step: 1292/530, loss: 0.07385721057653427
2023-01-23 01:38:13.370732: step: 1296/530, loss: 0.0898863822221756
2023-01-23 01:38:14.501183: step: 1300/530, loss: 0.3169923722743988
2023-01-23 01:38:15.611696: step: 1304/530, loss: 0.09978704154491425
2023-01-23 01:38:16.735274: step: 1308/530, loss: 0.06102476269006729
2023-01-23 01:38:17.854966: step: 1312/530, loss: 0.030858777463436127
2023-01-23 01:38:18.986670: step: 1316/530, loss: 0.015398884192109108
2023-01-23 01:38:20.122569: step: 1320/530, loss: 0.08353858441114426
2023-01-23 01:38:21.270895: step: 1324/530, loss: 0.07359378039836884
2023-01-23 01:38:22.363755: step: 1328/530, loss: 0.046921443194150925
2023-01-23 01:38:23.467727: step: 1332/530, loss: 0.0617523193359375
2023-01-23 01:38:24.581591: step: 1336/530, loss: 0.04049711301922798
2023-01-23 01:38:25.747075: step: 1340/530, loss: 0.012983131222426891
2023-01-23 01:38:26.896289: step: 1344/530, loss: 0.01473617646843195
2023-01-23 01:38:28.019690: step: 1348/530, loss: 0.007877158932387829
2023-01-23 01:38:29.130329: step: 1352/530, loss: 0.3036857545375824
2023-01-23 01:38:30.293386: step: 1356/530, loss: 0.040499210357666016
2023-01-23 01:38:31.435619: step: 1360/530, loss: 0.05816479027271271
2023-01-23 01:38:32.602322: step: 1364/530, loss: 0.09076805412769318
2023-01-23 01:38:33.710895: step: 1368/530, loss: 0.0436735637485981
2023-01-23 01:38:34.820171: step: 1372/530, loss: 0.011147355660796165
2023-01-23 01:38:35.930816: step: 1376/530, loss: 0.023430967703461647
2023-01-23 01:38:37.021762: step: 1380/530, loss: 0.017697811126708984
2023-01-23 01:38:38.142837: step: 1384/530, loss: 0.22648115456104279
2023-01-23 01:38:39.264398: step: 1388/530, loss: 0.005888843908905983
2023-01-23 01:38:40.395086: step: 1392/530, loss: 0.0368773490190506
2023-01-23 01:38:41.578830: step: 1396/530, loss: 0.0022420408204197884
2023-01-23 01:38:42.697495: step: 1400/530, loss: 0.0013060569763183594
2023-01-23 01:38:43.838758: step: 1404/530, loss: 0.3281448483467102
2023-01-23 01:38:44.981052: step: 1408/530, loss: 0.03287963941693306
2023-01-23 01:38:46.110740: step: 1412/530, loss: 0.015015030279755592
2023-01-23 01:38:47.249173: step: 1416/530, loss: 0.1252155303955078
2023-01-23 01:38:48.368375: step: 1420/530, loss: 0.016002941876649857
2023-01-23 01:38:49.486902: step: 1424/530, loss: 0.0055599212646484375
2023-01-23 01:38:50.627103: step: 1428/530, loss: 0.004454612731933594
2023-01-23 01:38:51.737665: step: 1432/530, loss: 0.1563817262649536
2023-01-23 01:38:52.868355: step: 1436/530, loss: 0.019991589710116386
2023-01-23 01:38:53.986503: step: 1440/530, loss: 0.03615932539105415
2023-01-23 01:38:55.106160: step: 1444/530, loss: 0.04416370391845703
2023-01-23 01:38:56.236827: step: 1448/530, loss: 0.02237873151898384
2023-01-23 01:38:57.373334: step: 1452/530, loss: 0.004031658172607422
2023-01-23 01:38:58.488450: step: 1456/530, loss: 0.10543432831764221
2023-01-23 01:38:59.608928: step: 1460/530, loss: 0.04476146772503853
2023-01-23 01:39:00.709236: step: 1464/530, loss: 0.013064957223832607
2023-01-23 01:39:01.838398: step: 1468/530, loss: 0.07537870109081268
2023-01-23 01:39:02.969927: step: 1472/530, loss: 0.19609889388084412
2023-01-23 01:39:04.110874: step: 1476/530, loss: 0.022807884961366653
2023-01-23 01:39:05.240302: step: 1480/530, loss: 0.00527267437428236
2023-01-23 01:39:06.371142: step: 1484/530, loss: 0.11423645913600922
2023-01-23 01:39:07.537379: step: 1488/530, loss: 0.041696835309267044
2023-01-23 01:39:08.650131: step: 1492/530, loss: 0.008644675835967064
2023-01-23 01:39:09.797481: step: 1496/530, loss: 0.02127685584127903
2023-01-23 01:39:10.929215: step: 1500/530, loss: 0.010269737802445889
2023-01-23 01:39:12.054412: step: 1504/530, loss: 0.12578992545604706
2023-01-23 01:39:13.162529: step: 1508/530, loss: 0.1257183998823166
2023-01-23 01:39:14.270263: step: 1512/530, loss: 0.061166100203990936
2023-01-23 01:39:15.380074: step: 1516/530, loss: 0.09761114418506622
2023-01-23 01:39:16.523174: step: 1520/530, loss: 0.05430469661951065
2023-01-23 01:39:17.658959: step: 1524/530, loss: 0.0682094544172287
2023-01-23 01:39:18.804732: step: 1528/530, loss: 0.08745650947093964
2023-01-23 01:39:19.912506: step: 1532/530, loss: 0.03851308673620224
2023-01-23 01:39:21.034416: step: 1536/530, loss: 0.13264040648937225
2023-01-23 01:39:22.178464: step: 1540/530, loss: 0.023351669311523438
2023-01-23 01:39:23.317800: step: 1544/530, loss: 0.010625744238495827
2023-01-23 01:39:24.436082: step: 1548/530, loss: 0.0032019615173339844
2023-01-23 01:39:25.543924: step: 1552/530, loss: 0.002635193057358265
2023-01-23 01:39:26.666344: step: 1556/530, loss: 0.03500928729772568
2023-01-23 01:39:27.788076: step: 1560/530, loss: 0.0467713363468647
2023-01-23 01:39:28.931621: step: 1564/530, loss: 0.05844561383128166
2023-01-23 01:39:30.068282: step: 1568/530, loss: 0.08722095191478729
2023-01-23 01:39:31.201163: step: 1572/530, loss: 0.06287989765405655
2023-01-23 01:39:32.332414: step: 1576/530, loss: 0.031231213361024857
2023-01-23 01:39:33.495429: step: 1580/530, loss: 0.05687766149640083
2023-01-23 01:39:34.624606: step: 1584/530, loss: 0.01974515989422798
2023-01-23 01:39:35.727974: step: 1588/530, loss: 0.004370022099465132
2023-01-23 01:39:36.835651: step: 1592/530, loss: 0.0794130340218544
2023-01-23 01:39:37.955191: step: 1596/530, loss: 0.040224839001894
2023-01-23 01:39:39.096994: step: 1600/530, loss: 0.013759803958237171
2023-01-23 01:39:40.207791: step: 1604/530, loss: 0.04306211322546005
2023-01-23 01:39:41.336498: step: 1608/530, loss: 0.03336386755108833
2023-01-23 01:39:42.454310: step: 1612/530, loss: 0.01677856408059597
2023-01-23 01:39:43.568542: step: 1616/530, loss: 0.013958167284727097
2023-01-23 01:39:44.699385: step: 1620/530, loss: 0.07066164910793304
2023-01-23 01:39:45.835441: step: 1624/530, loss: 0.019552230834960938
2023-01-23 01:39:46.943131: step: 1628/530, loss: 0.3767172396183014
2023-01-23 01:39:48.083956: step: 1632/530, loss: 0.16153717041015625
2023-01-23 01:39:49.244097: step: 1636/530, loss: 0.008396911434829235
2023-01-23 01:39:50.353733: step: 1640/530, loss: 0.11108437180519104
2023-01-23 01:39:51.522979: step: 1644/530, loss: 0.10089760273694992
2023-01-23 01:39:52.655442: step: 1648/530, loss: 0.08596020191907883
2023-01-23 01:39:53.826463: step: 1652/530, loss: 0.006371689029037952
2023-01-23 01:39:54.998898: step: 1656/530, loss: 0.0012007714249193668
2023-01-23 01:39:56.136367: step: 1660/530, loss: 0.14213065803050995
2023-01-23 01:39:57.264081: step: 1664/530, loss: 0.14099007844924927
2023-01-23 01:39:58.443088: step: 1668/530, loss: 0.08927521854639053
2023-01-23 01:39:59.557633: step: 1672/530, loss: 0.017639046534895897
2023-01-23 01:40:00.677216: step: 1676/530, loss: 0.02323169820010662
2023-01-23 01:40:01.855801: step: 1680/530, loss: 0.025168299674987793
2023-01-23 01:40:02.995447: step: 1684/530, loss: 0.014221000485122204
2023-01-23 01:40:04.109001: step: 1688/530, loss: 0.04615669324994087
2023-01-23 01:40:05.224314: step: 1692/530, loss: 0.019794845953583717
2023-01-23 01:40:06.347315: step: 1696/530, loss: 0.0795656219124794
2023-01-23 01:40:07.452283: step: 1700/530, loss: 0.02145867422223091
2023-01-23 01:40:08.608398: step: 1704/530, loss: 0.010657120496034622
2023-01-23 01:40:09.739028: step: 1708/530, loss: 0.02896442450582981
2023-01-23 01:40:10.876876: step: 1712/530, loss: 0.12802210450172424
2023-01-23 01:40:11.996011: step: 1716/530, loss: 0.044201187789440155
2023-01-23 01:40:13.115060: step: 1720/530, loss: 0.04937968775629997
2023-01-23 01:40:14.221780: step: 1724/530, loss: 0.0014869689475744963
2023-01-23 01:40:15.331999: step: 1728/530, loss: 0.1193552017211914
2023-01-23 01:40:16.455319: step: 1732/530, loss: 0.02165224589407444
2023-01-23 01:40:17.562493: step: 1736/530, loss: 0.015211200341582298
2023-01-23 01:40:18.681413: step: 1740/530, loss: 0.041077326983213425
2023-01-23 01:40:19.814410: step: 1744/530, loss: 0.06702794879674911
2023-01-23 01:40:20.926075: step: 1748/530, loss: 0.059510041028261185
2023-01-23 01:40:22.052236: step: 1752/530, loss: 0.07804689556360245
2023-01-23 01:40:23.192421: step: 1756/530, loss: 0.06708774715662003
2023-01-23 01:40:24.307059: step: 1760/530, loss: 0.2416139543056488
2023-01-23 01:40:25.427778: step: 1764/530, loss: 0.04386806860566139
2023-01-23 01:40:26.582741: step: 1768/530, loss: 0.0035983086563646793
2023-01-23 01:40:27.680605: step: 1772/530, loss: 0.05683918297290802
2023-01-23 01:40:28.806742: step: 1776/530, loss: 0.026645852252840996
2023-01-23 01:40:29.917856: step: 1780/530, loss: 0.010800170712172985
2023-01-23 01:40:31.058679: step: 1784/530, loss: 0.024897005409002304
2023-01-23 01:40:32.193454: step: 1788/530, loss: 0.03249054029583931
2023-01-23 01:40:33.330786: step: 1792/530, loss: 0.44863295555114746
2023-01-23 01:40:34.474155: step: 1796/530, loss: 0.03138303756713867
2023-01-23 01:40:35.605426: step: 1800/530, loss: 0.020154381170868874
2023-01-23 01:40:36.729691: step: 1804/530, loss: 0.00490570068359375
2023-01-23 01:40:37.868605: step: 1808/530, loss: 0.056840136647224426
2023-01-23 01:40:39.006908: step: 1812/530, loss: 0.014387797564268112
2023-01-23 01:40:40.117515: step: 1816/530, loss: 0.011014366522431374
2023-01-23 01:40:41.250073: step: 1820/530, loss: 0.034049034118652344
2023-01-23 01:40:42.385488: step: 1824/530, loss: 1.1494110822677612
2023-01-23 01:40:43.492054: step: 1828/530, loss: 0.04215068742632866
2023-01-23 01:40:44.660542: step: 1832/530, loss: 0.014886761084198952
2023-01-23 01:40:45.798750: step: 1836/530, loss: 0.04936542361974716
2023-01-23 01:40:46.941210: step: 1840/530, loss: 0.18636426329612732
2023-01-23 01:40:48.053693: step: 1844/530, loss: 0.0564267635345459
2023-01-23 01:40:49.190959: step: 1848/530, loss: 0.0022520541679114103
2023-01-23 01:40:50.314460: step: 1852/530, loss: 0.08404403179883957
2023-01-23 01:40:51.441321: step: 1856/530, loss: 0.02207489125430584
2023-01-23 01:40:52.569086: step: 1860/530, loss: 0.004207802005112171
2023-01-23 01:40:53.699574: step: 1864/530, loss: 0.025124549865722656
2023-01-23 01:40:54.848020: step: 1868/530, loss: 0.03257932513952255
2023-01-23 01:40:55.983304: step: 1872/530, loss: 0.016363907605409622
2023-01-23 01:40:57.095706: step: 1876/530, loss: 0.11972226202487946
2023-01-23 01:40:58.214192: step: 1880/530, loss: 0.024494744837284088
2023-01-23 01:40:59.385196: step: 1884/530, loss: 0.0037693025078624487
2023-01-23 01:41:00.521750: step: 1888/530, loss: 0.08576412498950958
2023-01-23 01:41:01.685931: step: 1892/530, loss: 0.03946724161505699
2023-01-23 01:41:02.849335: step: 1896/530, loss: 0.06874599307775497
2023-01-23 01:41:03.996084: step: 1900/530, loss: 0.044737860560417175
2023-01-23 01:41:05.155261: step: 1904/530, loss: 0.04775981977581978
2023-01-23 01:41:06.285612: step: 1908/530, loss: 0.01249094121158123
2023-01-23 01:41:07.383593: step: 1912/530, loss: 0.039031028747558594
2023-01-23 01:41:08.544981: step: 1916/530, loss: 0.05117683485150337
2023-01-23 01:41:09.667712: step: 1920/530, loss: 0.15757597982883453
2023-01-23 01:41:10.799951: step: 1924/530, loss: 0.13480520248413086
2023-01-23 01:41:11.886878: step: 1928/530, loss: 0.24551606178283691
2023-01-23 01:41:12.996961: step: 1932/530, loss: 0.02641897276043892
2023-01-23 01:41:14.121684: step: 1936/530, loss: 0.007512473966926336
2023-01-23 01:41:15.249249: step: 1940/530, loss: 0.03429088741540909
2023-01-23 01:41:16.393076: step: 1944/530, loss: 0.013879586011171341
2023-01-23 01:41:17.553384: step: 1948/530, loss: 0.0027643204666674137
2023-01-23 01:41:18.691417: step: 1952/530, loss: 0.019124697893857956
2023-01-23 01:41:19.814741: step: 1956/530, loss: 0.006795382592827082
2023-01-23 01:41:20.947063: step: 1960/530, loss: 0.0571383498609066
2023-01-23 01:41:22.054121: step: 1964/530, loss: 0.0031063079368323088
2023-01-23 01:41:23.182186: step: 1968/530, loss: 0.0088227279484272
2023-01-23 01:41:24.327273: step: 1972/530, loss: 0.06085358187556267
2023-01-23 01:41:25.465010: step: 1976/530, loss: 0.037062231451272964
2023-01-23 01:41:26.622183: step: 1980/530, loss: 0.11239328235387802
2023-01-23 01:41:27.709696: step: 1984/530, loss: 0.0081145279109478
2023-01-23 01:41:28.829855: step: 1988/530, loss: 0.06414061039686203
2023-01-23 01:41:29.967238: step: 1992/530, loss: 0.04222848266363144
2023-01-23 01:41:31.118771: step: 1996/530, loss: 0.13775186240673065
2023-01-23 01:41:32.245247: step: 2000/530, loss: 0.015492104925215244
2023-01-23 01:41:33.382721: step: 2004/530, loss: 0.03464484214782715
2023-01-23 01:41:34.520622: step: 2008/530, loss: 0.017658328637480736
2023-01-23 01:41:35.622328: step: 2012/530, loss: 0.01415109634399414
2023-01-23 01:41:36.762796: step: 2016/530, loss: 0.005431285593658686
2023-01-23 01:41:37.911018: step: 2020/530, loss: 0.052102088928222656
2023-01-23 01:41:39.007160: step: 2024/530, loss: 0.02921323850750923
2023-01-23 01:41:40.130828: step: 2028/530, loss: 0.06791029125452042
2023-01-23 01:41:41.250447: step: 2032/530, loss: 0.10938436537981033
2023-01-23 01:41:42.371083: step: 2036/530, loss: 0.0010814667912200093
2023-01-23 01:41:43.478780: step: 2040/530, loss: 0.008490944281220436
2023-01-23 01:41:44.609708: step: 2044/530, loss: 0.0015291214222088456
2023-01-23 01:41:45.741167: step: 2048/530, loss: 0.09002876281738281
2023-01-23 01:41:46.851586: step: 2052/530, loss: 0.02641620673239231
2023-01-23 01:41:47.984644: step: 2056/530, loss: 0.021425439044833183
2023-01-23 01:41:49.099504: step: 2060/530, loss: 0.028833676129579544
2023-01-23 01:41:50.219706: step: 2064/530, loss: 0.11477460712194443
2023-01-23 01:41:51.375810: step: 2068/530, loss: 0.014074612408876419
2023-01-23 01:41:52.474223: step: 2072/530, loss: 0.4296489953994751
2023-01-23 01:41:53.620159: step: 2076/530, loss: 0.026035403832793236
2023-01-23 01:41:54.746167: step: 2080/530, loss: 0.09399977326393127
2023-01-23 01:41:55.889044: step: 2084/530, loss: 0.22609558701515198
2023-01-23 01:41:57.029485: step: 2088/530, loss: 0.02794475667178631
2023-01-23 01:41:58.169505: step: 2092/530, loss: 0.24151897430419922
2023-01-23 01:41:59.273573: step: 2096/530, loss: 0.021518278867006302
2023-01-23 01:42:00.405545: step: 2100/530, loss: 0.016987085342407227
2023-01-23 01:42:01.528540: step: 2104/530, loss: 0.15023207664489746
2023-01-23 01:42:02.685772: step: 2108/530, loss: 0.04144134372472763
2023-01-23 01:42:03.793379: step: 2112/530, loss: 0.11343646794557571
2023-01-23 01:42:04.935157: step: 2116/530, loss: 0.11522826552391052
2023-01-23 01:42:06.053120: step: 2120/530, loss: 0.00948495976626873
==================================================
Loss: 0.080
--------------------
Dev: {'event': {'p': 0.6288770053475936, 'r': 0.7829560585885486, 'f1': 0.697508896797153}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Test: {'event': {'p': 0.64058795637743, 'r': 0.772, 'f1': 0.7001813941435606}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Chinese: {'event': {'p': 0.5974025974025974, 'r': 0.8518518518518519, 'f1': 0.7022900763358778}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Korean: {'event': {'p': 0.6851851851851852, 'r': 0.5873015873015873, 'f1': 0.6324786324786325}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Russian: {'event': {'p': 0.425, 'r': 0.4722222222222222, 'f1': 0.4473684210526316}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
New best korean model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Chinese: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Chinese: {'event': {'p': 0.6190476190476191, 'r': 0.9629629629629629, 'f1': 0.7536231884057971}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6288770053475936, 'r': 0.7829560585885486, 'f1': 0.697508896797153}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Korean: {'event': {'p': 0.64058795637743, 'r': 0.772, 'f1': 0.7001813941435606}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Korean: {'event': {'p': 0.6851851851851852, 'r': 0.5873015873015873, 'f1': 0.6324786324786325}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5319148936170213, 'r': 0.6944444444444444, 'f1': 0.6024096385542169}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
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 01:42:52.112017: step: 4/530, loss: 0.07398071140050888
2023-01-23 01:42:53.223290: step: 8/530, loss: 0.040528297424316406
2023-01-23 01:42:54.371100: step: 12/530, loss: 0.033846285194158554
2023-01-23 01:42:55.490281: step: 16/530, loss: 0.061208344995975494
2023-01-23 01:42:56.616291: step: 20/530, loss: 0.014437771402299404
2023-01-23 01:42:57.726450: step: 24/530, loss: 0.019230078905820847
2023-01-23 01:42:58.879514: step: 28/530, loss: 0.040814876556396484
2023-01-23 01:42:59.988361: step: 32/530, loss: 0.015940189361572266
2023-01-23 01:43:01.135804: step: 36/530, loss: 0.012237166985869408
2023-01-23 01:43:02.309371: step: 40/530, loss: 0.06769218295812607
2023-01-23 01:43:03.456600: step: 44/530, loss: 0.021685171872377396
2023-01-23 01:43:04.574125: step: 48/530, loss: 0.039278794080019
2023-01-23 01:43:05.706035: step: 52/530, loss: 0.09032197296619415
2023-01-23 01:43:06.825881: step: 56/530, loss: 0.002974605653434992
2023-01-23 01:43:07.931448: step: 60/530, loss: 0.03060626983642578
2023-01-23 01:43:09.103814: step: 64/530, loss: 0.36522141098976135
2023-01-23 01:43:10.234751: step: 68/530, loss: 0.004154587164521217
2023-01-23 01:43:11.385201: step: 72/530, loss: 0.016639327630400658
2023-01-23 01:43:12.524468: step: 76/530, loss: 0.803027868270874
2023-01-23 01:43:13.628621: step: 80/530, loss: 0.021478844806551933
2023-01-23 01:43:14.754316: step: 84/530, loss: 0.019259978085756302
2023-01-23 01:43:15.876050: step: 88/530, loss: 0.21379566192626953
2023-01-23 01:43:17.008713: step: 92/530, loss: 0.13825759291648865
2023-01-23 01:43:18.153901: step: 96/530, loss: 0.0801246166229248
2023-01-23 01:43:19.247350: step: 100/530, loss: 0.05334510654211044
2023-01-23 01:43:20.386900: step: 104/530, loss: 0.04725246503949165
2023-01-23 01:43:21.505614: step: 108/530, loss: 0.09036903828382492
2023-01-23 01:43:22.637995: step: 112/530, loss: 0.03862859308719635
2023-01-23 01:43:23.781030: step: 116/530, loss: 0.008417701348662376
2023-01-23 01:43:24.906996: step: 120/530, loss: 0.001842498779296875
2023-01-23 01:43:26.050912: step: 124/530, loss: 0.02998790517449379
2023-01-23 01:43:27.207465: step: 128/530, loss: 0.008072090335190296
2023-01-23 01:43:28.325248: step: 132/530, loss: 0.00067563058109954
2023-01-23 01:43:29.463000: step: 136/530, loss: 0.013930797576904297
2023-01-23 01:43:30.612601: step: 140/530, loss: 0.03284607082605362
2023-01-23 01:43:31.795575: step: 144/530, loss: 0.01740550994873047
2023-01-23 01:43:32.939795: step: 148/530, loss: 0.01164555549621582
2023-01-23 01:43:34.065614: step: 152/530, loss: 0.021640967577695847
2023-01-23 01:43:35.196480: step: 156/530, loss: 0.030883314087986946
2023-01-23 01:43:36.329047: step: 160/530, loss: 0.040308572351932526
2023-01-23 01:43:37.467653: step: 164/530, loss: 0.15443038940429688
2023-01-23 01:43:38.563409: step: 168/530, loss: 0.0005220413440838456
2023-01-23 01:43:39.696880: step: 172/530, loss: 0.02633199840784073
2023-01-23 01:43:40.853065: step: 176/530, loss: 0.03239555284380913
2023-01-23 01:43:41.999190: step: 180/530, loss: 0.005229187197983265
2023-01-23 01:43:43.116298: step: 184/530, loss: 0.02136669121682644
2023-01-23 01:43:44.261031: step: 188/530, loss: 0.18294048309326172
2023-01-23 01:43:45.392532: step: 192/530, loss: 0.00397415179759264
2023-01-23 01:43:46.543272: step: 196/530, loss: 0.0024996281135827303
2023-01-23 01:43:47.680701: step: 200/530, loss: 0.05724659189581871
2023-01-23 01:43:48.804115: step: 204/530, loss: 0.0010045052040368319
2023-01-23 01:43:49.930029: step: 208/530, loss: 0.008377457037568092
2023-01-23 01:43:51.086488: step: 212/530, loss: 0.0017427444690838456
2023-01-23 01:43:52.176443: step: 216/530, loss: 0.006104993633925915
2023-01-23 01:43:53.290889: step: 220/530, loss: 0.07204703986644745
2023-01-23 01:43:54.452883: step: 224/530, loss: 0.013346672058105469
2023-01-23 01:43:55.589212: step: 228/530, loss: 0.0033665657974779606
2023-01-23 01:43:56.740337: step: 232/530, loss: 0.0005195617559365928
2023-01-23 01:43:57.856016: step: 236/530, loss: 0.0021766661666333675
2023-01-23 01:43:59.002265: step: 240/530, loss: 0.02127990871667862
2023-01-23 01:44:00.133472: step: 244/530, loss: 0.04345512390136719
2023-01-23 01:44:01.285404: step: 248/530, loss: 0.02390117570757866
2023-01-23 01:44:02.438703: step: 252/530, loss: 0.014167689718306065
2023-01-23 01:44:03.586914: step: 256/530, loss: 0.08022921532392502
2023-01-23 01:44:04.707502: step: 260/530, loss: 0.08356304466724396
2023-01-23 01:44:05.856021: step: 264/530, loss: 0.079462431371212
2023-01-23 01:44:06.975913: step: 268/530, loss: 0.01774435117840767
2023-01-23 01:44:08.088362: step: 272/530, loss: 0.012601470574736595
2023-01-23 01:44:09.187915: step: 276/530, loss: 0.01583128049969673
2023-01-23 01:44:10.306452: step: 280/530, loss: 0.15616551041603088
2023-01-23 01:44:11.451630: step: 284/530, loss: 0.0051246643997728825
2023-01-23 01:44:12.594693: step: 288/530, loss: 0.04609479755163193
2023-01-23 01:44:13.707770: step: 292/530, loss: 0.001565313432365656
2023-01-23 01:44:14.831009: step: 296/530, loss: 0.0015541077591478825
2023-01-23 01:44:15.960177: step: 300/530, loss: 0.04877987131476402
2023-01-23 01:44:17.102377: step: 304/530, loss: 0.05408892780542374
2023-01-23 01:44:18.219896: step: 308/530, loss: 0.016455842182040215
2023-01-23 01:44:19.315675: step: 312/530, loss: 0.022357558831572533
2023-01-23 01:44:20.429401: step: 316/530, loss: 0.040270138531923294
2023-01-23 01:44:21.552463: step: 320/530, loss: 0.00941934622824192
2023-01-23 01:44:22.705564: step: 324/530, loss: 0.058518312871456146
2023-01-23 01:44:23.824973: step: 328/530, loss: 0.009145354852080345
2023-01-23 01:44:24.953966: step: 332/530, loss: 0.07680606842041016
2023-01-23 01:44:26.065065: step: 336/530, loss: 0.030954742804169655
2023-01-23 01:44:27.180286: step: 340/530, loss: 0.011797047220170498
2023-01-23 01:44:28.309288: step: 344/530, loss: 0.009526061825454235
2023-01-23 01:44:29.449482: step: 348/530, loss: 0.02530832216143608
2023-01-23 01:44:30.592171: step: 352/530, loss: 0.04044971615076065
2023-01-23 01:44:31.712257: step: 356/530, loss: 0.009169482626020908
2023-01-23 01:44:32.851539: step: 360/530, loss: 0.0006190777057781816
2023-01-23 01:44:33.934463: step: 364/530, loss: 0.018922805786132812
2023-01-23 01:44:35.074892: step: 368/530, loss: 0.01688690297305584
2023-01-23 01:44:36.212912: step: 372/530, loss: 0.09695987403392792
2023-01-23 01:44:37.333172: step: 376/530, loss: 0.028640173375606537
2023-01-23 01:44:38.503395: step: 380/530, loss: 0.03937482833862305
2023-01-23 01:44:39.655545: step: 384/530, loss: 0.008267381228506565
2023-01-23 01:44:40.761975: step: 388/530, loss: 0.05264930799603462
2023-01-23 01:44:41.899548: step: 392/530, loss: 0.04300546646118164
2023-01-23 01:44:43.003247: step: 396/530, loss: 0.036551475524902344
2023-01-23 01:44:44.150723: step: 400/530, loss: 0.0185044277459383
2023-01-23 01:44:45.267795: step: 404/530, loss: 0.025232840329408646
2023-01-23 01:44:46.400260: step: 408/530, loss: 0.0014047622680664062
2023-01-23 01:44:47.522785: step: 412/530, loss: 0.003603649325668812
2023-01-23 01:44:48.663836: step: 416/530, loss: 0.005042076110839844
2023-01-23 01:44:49.812952: step: 420/530, loss: 0.1185854896903038
2023-01-23 01:44:50.922353: step: 424/530, loss: 0.016942406073212624
2023-01-23 01:44:52.027882: step: 428/530, loss: 0.0016430855030193925
2023-01-23 01:44:53.159509: step: 432/530, loss: 0.08309340476989746
2023-01-23 01:44:54.289523: step: 436/530, loss: 0.010507297702133656
2023-01-23 01:44:55.411165: step: 440/530, loss: 0.012030982412397861
2023-01-23 01:44:56.519615: step: 444/530, loss: 0.04357652738690376
2023-01-23 01:44:57.640227: step: 448/530, loss: 0.05668983608484268
2023-01-23 01:44:58.738771: step: 452/530, loss: 0.006683635991066694
2023-01-23 01:44:59.853112: step: 456/530, loss: 0.012692738324403763
2023-01-23 01:45:00.995403: step: 460/530, loss: 0.0013941765064373612
2023-01-23 01:45:02.154875: step: 464/530, loss: 0.023555375635623932
2023-01-23 01:45:03.271074: step: 468/530, loss: 0.027986811473965645
2023-01-23 01:45:04.387472: step: 472/530, loss: 0.03971405327320099
2023-01-23 01:45:05.487005: step: 476/530, loss: 0.007008934393525124
2023-01-23 01:45:06.615990: step: 480/530, loss: 0.008699417114257812
2023-01-23 01:45:07.755419: step: 484/530, loss: 0.01346063707023859
2023-01-23 01:45:08.870405: step: 488/530, loss: 0.02027721516788006
2023-01-23 01:45:10.012905: step: 492/530, loss: 0.016364289447665215
2023-01-23 01:45:11.122742: step: 496/530, loss: 0.02846050262451172
2023-01-23 01:45:12.261544: step: 500/530, loss: 0.05443897098302841
2023-01-23 01:45:13.379880: step: 504/530, loss: 0.04571991041302681
2023-01-23 01:45:14.493563: step: 508/530, loss: 2.8133392333984375e-05
2023-01-23 01:45:15.626711: step: 512/530, loss: 0.012814999558031559
2023-01-23 01:45:16.751012: step: 516/530, loss: 0.03642425686120987
2023-01-23 01:45:17.849520: step: 520/530, loss: 0.028331659734249115
2023-01-23 01:45:18.946860: step: 524/530, loss: 0.037322428077459335
2023-01-23 01:45:20.093965: step: 528/530, loss: 0.0013184548588469625
2023-01-23 01:45:21.238846: step: 532/530, loss: 0.04839382320642471
2023-01-23 01:45:22.374249: step: 536/530, loss: 0.007972908206284046
2023-01-23 01:45:23.507869: step: 540/530, loss: 0.025253869593143463
2023-01-23 01:45:24.665431: step: 544/530, loss: 0.048673249781131744
2023-01-23 01:45:25.801534: step: 548/530, loss: 0.47579923272132874
2023-01-23 01:45:26.911341: step: 552/530, loss: 0.04266681522130966
2023-01-23 01:45:28.030570: step: 556/530, loss: 0.008650589734315872
2023-01-23 01:45:29.167596: step: 560/530, loss: 0.05090532451868057
2023-01-23 01:45:30.310411: step: 564/530, loss: 0.014536334201693535
2023-01-23 01:45:31.447736: step: 568/530, loss: 0.013978386297821999
2023-01-23 01:45:32.627380: step: 572/530, loss: 0.009700680151581764
2023-01-23 01:45:33.769242: step: 576/530, loss: 0.014577674679458141
2023-01-23 01:45:34.881525: step: 580/530, loss: 0.10754165053367615
2023-01-23 01:45:36.014840: step: 584/530, loss: 1.4149501323699951
2023-01-23 01:45:37.133983: step: 588/530, loss: 0.015349960885941982
2023-01-23 01:45:38.260103: step: 592/530, loss: 0.05725135654211044
2023-01-23 01:45:39.410558: step: 596/530, loss: 0.01492157019674778
2023-01-23 01:45:40.572179: step: 600/530, loss: 0.005946350283920765
2023-01-23 01:45:41.698390: step: 604/530, loss: 0.05546889454126358
2023-01-23 01:45:42.839845: step: 608/530, loss: 0.018617058172822
2023-01-23 01:45:43.977632: step: 612/530, loss: 0.03833752125501633
2023-01-23 01:45:45.111464: step: 616/530, loss: 0.02911682240664959
2023-01-23 01:45:46.227020: step: 620/530, loss: 0.013194657862186432
2023-01-23 01:45:47.380767: step: 624/530, loss: 0.005923461634665728
2023-01-23 01:45:48.527077: step: 628/530, loss: 0.010469531640410423
2023-01-23 01:45:49.642898: step: 632/530, loss: 0.14634600281715393
2023-01-23 01:45:50.767611: step: 636/530, loss: 0.03739814832806587
2023-01-23 01:45:51.876443: step: 640/530, loss: 0.011187553405761719
2023-01-23 01:45:52.994567: step: 644/530, loss: 0.023834586143493652
2023-01-23 01:45:54.127487: step: 648/530, loss: 0.013212013989686966
2023-01-23 01:45:55.267346: step: 652/530, loss: 0.06017895042896271
2023-01-23 01:45:56.418890: step: 656/530, loss: 0.0145111083984375
2023-01-23 01:45:57.531700: step: 660/530, loss: 0.03867216408252716
2023-01-23 01:45:58.664229: step: 664/530, loss: 0.039589788764715195
2023-01-23 01:45:59.816513: step: 668/530, loss: 0.010405921377241611
2023-01-23 01:46:00.958714: step: 672/530, loss: 0.0029806136153638363
2023-01-23 01:46:02.107833: step: 676/530, loss: 0.5452859997749329
2023-01-23 01:46:03.233291: step: 680/530, loss: 0.015895556658506393
2023-01-23 01:46:04.372800: step: 684/530, loss: 0.0563511848449707
2023-01-23 01:46:05.494288: step: 688/530, loss: 0.04863701015710831
2023-01-23 01:46:06.596817: step: 692/530, loss: 0.03756413608789444
2023-01-23 01:46:07.753637: step: 696/530, loss: 0.061608411371707916
2023-01-23 01:46:08.872950: step: 700/530, loss: 0.012370491400361061
2023-01-23 01:46:10.027050: step: 704/530, loss: 0.04571247100830078
2023-01-23 01:46:11.145801: step: 708/530, loss: 0.05659017711877823
2023-01-23 01:46:12.288485: step: 712/530, loss: 0.0012090683449059725
2023-01-23 01:46:13.410288: step: 716/530, loss: 0.017827987670898438
2023-01-23 01:46:14.557610: step: 720/530, loss: 0.0004285812610760331
2023-01-23 01:46:15.681109: step: 724/530, loss: 0.0041939737275242805
2023-01-23 01:46:16.771465: step: 728/530, loss: 0.10186271369457245
2023-01-23 01:46:17.884630: step: 732/530, loss: 0.03255319595336914
2023-01-23 01:46:19.003019: step: 736/530, loss: 0.0075965882278978825
2023-01-23 01:46:20.099448: step: 740/530, loss: 0.03246726840734482
2023-01-23 01:46:21.201270: step: 744/530, loss: 0.05694274976849556
2023-01-23 01:46:22.333859: step: 748/530, loss: 0.07809115201234818
2023-01-23 01:46:23.467755: step: 752/530, loss: 0.03993682935833931
2023-01-23 01:46:24.578523: step: 756/530, loss: 0.020905494689941406
2023-01-23 01:46:25.706728: step: 760/530, loss: 0.011625099927186966
2023-01-23 01:46:26.859601: step: 764/530, loss: 0.8200300335884094
2023-01-23 01:46:27.983872: step: 768/530, loss: 0.020424747839570045
2023-01-23 01:46:29.111916: step: 772/530, loss: 0.03499555587768555
2023-01-23 01:46:30.218774: step: 776/530, loss: 0.05534668266773224
2023-01-23 01:46:31.338648: step: 780/530, loss: 0.04006495699286461
2023-01-23 01:46:32.481681: step: 784/530, loss: 0.20489098131656647
2023-01-23 01:46:33.613672: step: 788/530, loss: 0.02467327192425728
2023-01-23 01:46:34.738692: step: 792/530, loss: 0.00025119780912064016
2023-01-23 01:46:35.859009: step: 796/530, loss: 0.04124889522790909
2023-01-23 01:46:37.003448: step: 800/530, loss: 0.036313820630311966
2023-01-23 01:46:38.109327: step: 804/530, loss: 0.10097198933362961
2023-01-23 01:46:39.228375: step: 808/530, loss: 0.011997032910585403
2023-01-23 01:46:40.329193: step: 812/530, loss: 0.007013249211013317
2023-01-23 01:46:41.456838: step: 816/530, loss: 0.03416423872113228
2023-01-23 01:46:42.569651: step: 820/530, loss: 0.18572503328323364
2023-01-23 01:46:43.735449: step: 824/530, loss: 0.018530750647187233
2023-01-23 01:46:44.869095: step: 828/530, loss: 0.0008031845209188759
2023-01-23 01:46:46.017800: step: 832/530, loss: 0.111823171377182
2023-01-23 01:46:47.177641: step: 836/530, loss: 0.00376548757776618
2023-01-23 01:46:48.316034: step: 840/530, loss: 0.09680958092212677
2023-01-23 01:46:49.467168: step: 844/530, loss: 0.00603141775354743
2023-01-23 01:46:50.580751: step: 848/530, loss: 0.045821402221918106
2023-01-23 01:46:51.704911: step: 852/530, loss: 0.031633950769901276
2023-01-23 01:46:52.831843: step: 856/530, loss: 0.03334445878863335
2023-01-23 01:46:53.935890: step: 860/530, loss: 0.07749243080615997
2023-01-23 01:46:55.054211: step: 864/530, loss: 0.049832917749881744
2023-01-23 01:46:56.239950: step: 868/530, loss: 0.01040792465209961
2023-01-23 01:46:57.363865: step: 872/530, loss: 0.08721017837524414
2023-01-23 01:46:58.507352: step: 876/530, loss: 0.24433784186840057
2023-01-23 01:46:59.628814: step: 880/530, loss: 0.03598470985889435
2023-01-23 01:47:00.747617: step: 884/530, loss: 0.004406738560646772
2023-01-23 01:47:01.892321: step: 888/530, loss: 0.326913446187973
2023-01-23 01:47:03.021064: step: 892/530, loss: 0.04628896713256836
2023-01-23 01:47:04.108915: step: 896/530, loss: 0.025586891919374466
2023-01-23 01:47:05.223580: step: 900/530, loss: 0.039945222437381744
2023-01-23 01:47:06.341025: step: 904/530, loss: 0.009619045071303844
2023-01-23 01:47:07.455112: step: 908/530, loss: 0.02143258973956108
2023-01-23 01:47:08.583701: step: 912/530, loss: 0.0413791686296463
2023-01-23 01:47:09.713233: step: 916/530, loss: 0.05025697126984596
2023-01-23 01:47:10.823136: step: 920/530, loss: 0.3042936325073242
2023-01-23 01:47:11.927145: step: 924/530, loss: 0.02534313127398491
2023-01-23 01:47:13.064685: step: 928/530, loss: 0.02383415773510933
2023-01-23 01:47:14.205491: step: 932/530, loss: 0.19055995345115662
2023-01-23 01:47:15.316130: step: 936/530, loss: 0.003114700550213456
2023-01-23 01:47:16.438543: step: 940/530, loss: 0.015610313974320889
2023-01-23 01:47:17.586880: step: 944/530, loss: 0.01200723648071289
2023-01-23 01:47:18.687044: step: 948/530, loss: 0.0345064178109169
2023-01-23 01:47:19.784453: step: 952/530, loss: 0.06942739337682724
2023-01-23 01:47:20.909679: step: 956/530, loss: 0.08161535114049911
2023-01-23 01:47:22.028186: step: 960/530, loss: 0.0808025375008583
2023-01-23 01:47:23.158439: step: 964/530, loss: 0.03148593753576279
2023-01-23 01:47:24.266221: step: 968/530, loss: 0.05908598750829697
2023-01-23 01:47:25.374631: step: 972/530, loss: 0.23652076721191406
2023-01-23 01:47:26.509568: step: 976/530, loss: 0.008577823638916016
2023-01-23 01:47:27.642766: step: 980/530, loss: 0.012327003292739391
2023-01-23 01:47:28.775905: step: 984/530, loss: 0.2261420339345932
2023-01-23 01:47:29.914063: step: 988/530, loss: 0.060776807367801666
2023-01-23 01:47:31.068759: step: 992/530, loss: 0.018669700250029564
2023-01-23 01:47:32.193233: step: 996/530, loss: 0.047416117042303085
2023-01-23 01:47:33.305329: step: 1000/530, loss: 0.04935278743505478
2023-01-23 01:47:34.449492: step: 1004/530, loss: 0.024928638711571693
2023-01-23 01:47:35.579710: step: 1008/530, loss: 0.021472929045557976
2023-01-23 01:47:36.678324: step: 1012/530, loss: 0.029722262173891068
2023-01-23 01:47:37.821474: step: 1016/530, loss: 0.09951954334974289
2023-01-23 01:47:38.948238: step: 1020/530, loss: 0.0039619444869458675
2023-01-23 01:47:40.086965: step: 1024/530, loss: 0.0562870018184185
2023-01-23 01:47:41.178218: step: 1028/530, loss: 0.0490182526409626
2023-01-23 01:47:42.323545: step: 1032/530, loss: 0.06122525781393051
2023-01-23 01:47:43.425693: step: 1036/530, loss: 0.046708058565855026
2023-01-23 01:47:44.613314: step: 1040/530, loss: 0.00039358140202239156
2023-01-23 01:47:45.727376: step: 1044/530, loss: 0.08382701873779297
2023-01-23 01:47:46.840290: step: 1048/530, loss: 0.08624887466430664
2023-01-23 01:47:47.958578: step: 1052/530, loss: 0.03083954006433487
2023-01-23 01:47:49.091268: step: 1056/530, loss: 0.0290464386343956
2023-01-23 01:47:50.193282: step: 1060/530, loss: 0.11408348381519318
2023-01-23 01:47:51.317716: step: 1064/530, loss: 0.03804807737469673
2023-01-23 01:47:52.434845: step: 1068/530, loss: 0.008701324462890625
2023-01-23 01:47:53.562164: step: 1072/530, loss: 0.0008764266967773438
2023-01-23 01:47:54.686664: step: 1076/530, loss: 0.031462620943784714
2023-01-23 01:47:55.786106: step: 1080/530, loss: 0.01626615598797798
2023-01-23 01:47:56.905832: step: 1084/530, loss: 0.050166890025138855
2023-01-23 01:47:58.024415: step: 1088/530, loss: 0.019926857203245163
2023-01-23 01:47:59.154785: step: 1092/530, loss: 0.025343704968690872
2023-01-23 01:48:00.272579: step: 1096/530, loss: 0.06629572063684464
2023-01-23 01:48:01.391427: step: 1100/530, loss: 0.015285802073776722
2023-01-23 01:48:02.516221: step: 1104/530, loss: 0.03376542031764984
2023-01-23 01:48:03.641188: step: 1108/530, loss: 0.06569776684045792
2023-01-23 01:48:04.756735: step: 1112/530, loss: 0.037779998034238815
2023-01-23 01:48:05.897972: step: 1116/530, loss: 0.09744323045015335
2023-01-23 01:48:07.033323: step: 1120/530, loss: 0.05023784935474396
2023-01-23 01:48:08.170945: step: 1124/530, loss: 0.04346742480993271
2023-01-23 01:48:09.261842: step: 1128/530, loss: 0.03752937540411949
2023-01-23 01:48:10.402742: step: 1132/530, loss: 0.0013034821022301912
2023-01-23 01:48:11.542296: step: 1136/530, loss: 0.03620576858520508
2023-01-23 01:48:12.656708: step: 1140/530, loss: 0.016366004943847656
2023-01-23 01:48:13.790285: step: 1144/530, loss: 0.025661468505859375
2023-01-23 01:48:14.924564: step: 1148/530, loss: 0.023536063730716705
2023-01-23 01:48:16.048804: step: 1152/530, loss: 0.08747889846563339
2023-01-23 01:48:17.178783: step: 1156/530, loss: 0.05126542970538139
2023-01-23 01:48:18.280570: step: 1160/530, loss: 0.0679684653878212
2023-01-23 01:48:19.395348: step: 1164/530, loss: 0.04883904755115509
2023-01-23 01:48:20.515144: step: 1168/530, loss: 0.2679372727870941
2023-01-23 01:48:21.653852: step: 1172/530, loss: 0.015944385901093483
2023-01-23 01:48:22.804489: step: 1176/530, loss: 0.1687939167022705
2023-01-23 01:48:23.938434: step: 1180/530, loss: 0.013532734476029873
2023-01-23 01:48:25.054620: step: 1184/530, loss: 0.0886436477303505
2023-01-23 01:48:26.207155: step: 1188/530, loss: 0.03256569057703018
2023-01-23 01:48:27.312991: step: 1192/530, loss: 0.013889789581298828
2023-01-23 01:48:28.435942: step: 1196/530, loss: 0.04050111770629883
2023-01-23 01:48:29.573944: step: 1200/530, loss: 0.03629150241613388
2023-01-23 01:48:30.745165: step: 1204/530, loss: 0.07319466769695282
2023-01-23 01:48:31.879708: step: 1208/530, loss: 0.026548005640506744
2023-01-23 01:48:32.983131: step: 1212/530, loss: 0.013202667236328125
2023-01-23 01:48:34.107248: step: 1216/530, loss: 0.01926402933895588
2023-01-23 01:48:35.216108: step: 1220/530, loss: 0.182640939950943
2023-01-23 01:48:36.337852: step: 1224/530, loss: 0.09590368717908859
2023-01-23 01:48:37.456796: step: 1228/530, loss: 0.005127239506691694
2023-01-23 01:48:38.568490: step: 1232/530, loss: 0.021857118234038353
2023-01-23 01:48:39.694011: step: 1236/530, loss: 0.02572507970035076
2023-01-23 01:48:40.840402: step: 1240/530, loss: 0.0413665771484375
2023-01-23 01:48:41.982520: step: 1244/530, loss: 0.0046179769560694695
2023-01-23 01:48:43.089161: step: 1248/530, loss: 0.013308191671967506
2023-01-23 01:48:44.212334: step: 1252/530, loss: 0.008606291376054287
2023-01-23 01:48:45.319672: step: 1256/530, loss: 0.010782265104353428
2023-01-23 01:48:46.464298: step: 1260/530, loss: 0.19547052681446075
2023-01-23 01:48:47.581324: step: 1264/530, loss: 0.054781630635261536
2023-01-23 01:48:48.719459: step: 1268/530, loss: 0.00021877288236282766
2023-01-23 01:48:49.839424: step: 1272/530, loss: 0.029821300879120827
2023-01-23 01:48:50.977295: step: 1276/530, loss: 0.01794891431927681
2023-01-23 01:48:52.120545: step: 1280/530, loss: 0.06071462854743004
2023-01-23 01:48:53.253213: step: 1284/530, loss: 0.0012153149582445621
2023-01-23 01:48:54.392750: step: 1288/530, loss: 0.05071248859167099
2023-01-23 01:48:55.511034: step: 1292/530, loss: 0.009397363290190697
2023-01-23 01:48:56.635982: step: 1296/530, loss: 0.032709695398807526
2023-01-23 01:48:57.750319: step: 1300/530, loss: 0.1351376473903656
2023-01-23 01:48:58.864064: step: 1304/530, loss: 0.009944058023393154
2023-01-23 01:48:59.959747: step: 1308/530, loss: 0.045655060559511185
2023-01-23 01:49:01.082918: step: 1312/530, loss: 0.0862884521484375
2023-01-23 01:49:02.195929: step: 1316/530, loss: 0.011104297824203968
2023-01-23 01:49:03.331651: step: 1320/530, loss: 0.0068988800048828125
2023-01-23 01:49:04.438381: step: 1324/530, loss: 0.011665822006762028
2023-01-23 01:49:05.529035: step: 1328/530, loss: 0.02241211012005806
2023-01-23 01:49:06.650831: step: 1332/530, loss: 0.046392299234867096
2023-01-23 01:49:07.792748: step: 1336/530, loss: 0.0018444061279296875
2023-01-23 01:49:08.964335: step: 1340/530, loss: 0.05024013668298721
2023-01-23 01:49:10.085377: step: 1344/530, loss: 0.0178254134953022
2023-01-23 01:49:11.196931: step: 1348/530, loss: 0.04663848876953125
2023-01-23 01:49:12.316366: step: 1352/530, loss: 0.06724052131175995
2023-01-23 01:49:13.478022: step: 1356/530, loss: 0.009629917331039906
2023-01-23 01:49:14.584134: step: 1360/530, loss: 0.02982483059167862
2023-01-23 01:49:15.731458: step: 1364/530, loss: 0.0008590698707848787
2023-01-23 01:49:16.851394: step: 1368/530, loss: 0.05316190794110298
2023-01-23 01:49:17.945880: step: 1372/530, loss: 0.001986694522202015
2023-01-23 01:49:19.091369: step: 1376/530, loss: 0.050048112869262695
2023-01-23 01:49:20.187843: step: 1380/530, loss: 0.02764434926211834
2023-01-23 01:49:21.292509: step: 1384/530, loss: 0.030058478936553
2023-01-23 01:49:22.426995: step: 1388/530, loss: 0.03251190111041069
2023-01-23 01:49:23.545715: step: 1392/530, loss: 0.08532381057739258
2023-01-23 01:49:24.668466: step: 1396/530, loss: 0.04369411617517471
2023-01-23 01:49:25.800725: step: 1400/530, loss: 0.0405157133936882
2023-01-23 01:49:26.921953: step: 1404/530, loss: 0.014038181863725185
2023-01-23 01:49:28.042459: step: 1408/530, loss: 0.011718273162841797
2023-01-23 01:49:29.202443: step: 1412/530, loss: 0.028931427747011185
2023-01-23 01:49:30.304038: step: 1416/530, loss: 0.13845320045948029
2023-01-23 01:49:31.429320: step: 1420/530, loss: 0.09256420284509659
2023-01-23 01:49:32.573107: step: 1424/530, loss: 0.00949859619140625
2023-01-23 01:49:33.751054: step: 1428/530, loss: 0.014885520562529564
2023-01-23 01:49:34.866617: step: 1432/530, loss: 0.01170492172241211
2023-01-23 01:49:35.985145: step: 1436/530, loss: 0.03163490444421768
2023-01-23 01:49:37.114329: step: 1440/530, loss: 0.008007621392607689
2023-01-23 01:49:38.227364: step: 1444/530, loss: 0.011084175668656826
2023-01-23 01:49:39.363573: step: 1448/530, loss: 0.006390380673110485
2023-01-23 01:49:40.463605: step: 1452/530, loss: 0.023880815133452415
2023-01-23 01:49:41.572293: step: 1456/530, loss: 0.020429516211152077
2023-01-23 01:49:42.676444: step: 1460/530, loss: 0.03908605873584747
2023-01-23 01:49:43.819469: step: 1464/530, loss: 0.007166767027229071
2023-01-23 01:49:44.972745: step: 1468/530, loss: 0.08937874436378479
2023-01-23 01:49:46.106438: step: 1472/530, loss: 0.03241314738988876
2023-01-23 01:49:47.190792: step: 1476/530, loss: 0.012744748964905739
2023-01-23 01:49:48.323501: step: 1480/530, loss: 0.008614778518676758
2023-01-23 01:49:49.426494: step: 1484/530, loss: 0.02712726593017578
2023-01-23 01:49:50.537221: step: 1488/530, loss: 0.02927122265100479
2023-01-23 01:49:51.657079: step: 1492/530, loss: 0.022269820794463158
2023-01-23 01:49:52.792619: step: 1496/530, loss: 0.022495746612548828
2023-01-23 01:49:53.912543: step: 1500/530, loss: 0.03468479961156845
2023-01-23 01:49:55.027896: step: 1504/530, loss: 0.0064643267542123795
2023-01-23 01:49:56.189710: step: 1508/530, loss: 0.027135848999023438
2023-01-23 01:49:57.313061: step: 1512/530, loss: 0.17398318648338318
2023-01-23 01:49:58.432490: step: 1516/530, loss: 0.052553750574588776
2023-01-23 01:49:59.562265: step: 1520/530, loss: 0.03342113643884659
2023-01-23 01:50:00.729393: step: 1524/530, loss: 0.02911529690027237
2023-01-23 01:50:01.882333: step: 1528/530, loss: 0.055855441838502884
2023-01-23 01:50:03.041501: step: 1532/530, loss: 0.04987840726971626
2023-01-23 01:50:04.159013: step: 1536/530, loss: 0.023444557562470436
2023-01-23 01:50:05.279786: step: 1540/530, loss: 0.008450699038803577
2023-01-23 01:50:06.435208: step: 1544/530, loss: 0.004190301988273859
2023-01-23 01:50:07.557528: step: 1548/530, loss: 0.01269979402422905
2023-01-23 01:50:08.719026: step: 1552/530, loss: 0.6657583117485046
2023-01-23 01:50:09.848812: step: 1556/530, loss: 0.044672489166259766
2023-01-23 01:50:10.974106: step: 1560/530, loss: 0.026215698570013046
2023-01-23 01:50:12.070387: step: 1564/530, loss: 0.008369358256459236
2023-01-23 01:50:13.191827: step: 1568/530, loss: 0.06663589179515839
2023-01-23 01:50:14.338723: step: 1572/530, loss: 0.06325502693653107
2023-01-23 01:50:15.453892: step: 1576/530, loss: 0.006842422299087048
2023-01-23 01:50:16.611822: step: 1580/530, loss: 0.14408570528030396
2023-01-23 01:50:17.733755: step: 1584/530, loss: 0.05181474611163139
2023-01-23 01:50:18.883327: step: 1588/530, loss: 0.013959884643554688
2023-01-23 01:50:20.029799: step: 1592/530, loss: 0.05548761039972305
2023-01-23 01:50:21.168703: step: 1596/530, loss: 0.03722257539629936
2023-01-23 01:50:22.306743: step: 1600/530, loss: 0.08740988373756409
2023-01-23 01:50:23.410875: step: 1604/530, loss: 0.06963644176721573
2023-01-23 01:50:24.530488: step: 1608/530, loss: 0.017441559582948685
2023-01-23 01:50:25.652902: step: 1612/530, loss: 0.018889809027314186
2023-01-23 01:50:26.764308: step: 1616/530, loss: 0.04833946377038956
2023-01-23 01:50:27.878999: step: 1620/530, loss: 0.04017071798443794
2023-01-23 01:50:28.997214: step: 1624/530, loss: 0.044857535511255264
2023-01-23 01:50:30.091939: step: 1628/530, loss: 0.0030335187911987305
2023-01-23 01:50:31.210145: step: 1632/530, loss: 0.05566072463989258
2023-01-23 01:50:32.346123: step: 1636/530, loss: 0.047643475234508514
2023-01-23 01:50:33.522864: step: 1640/530, loss: 0.017865944653749466
2023-01-23 01:50:34.624854: step: 1644/530, loss: 0.01834592968225479
2023-01-23 01:50:35.744441: step: 1648/530, loss: 0.03781948238611221
2023-01-23 01:50:36.901026: step: 1652/530, loss: 0.030655860900878906
2023-01-23 01:50:38.016600: step: 1656/530, loss: 0.033209990710020065
2023-01-23 01:50:39.131051: step: 1660/530, loss: 0.04573860019445419
2023-01-23 01:50:40.246271: step: 1664/530, loss: 0.020556068047881126
2023-01-23 01:50:41.366378: step: 1668/530, loss: 0.006572437472641468
2023-01-23 01:50:42.535078: step: 1672/530, loss: 0.058839987963438034
2023-01-23 01:50:43.678170: step: 1676/530, loss: 0.010986709967255592
2023-01-23 01:50:44.782977: step: 1680/530, loss: 0.03487148508429527
2023-01-23 01:50:45.886967: step: 1684/530, loss: 0.009535599499940872
2023-01-23 01:50:47.008403: step: 1688/530, loss: 0.44318628311157227
2023-01-23 01:50:48.147608: step: 1692/530, loss: 0.030763745307922363
2023-01-23 01:50:49.281251: step: 1696/530, loss: 0.0001489639253122732
2023-01-23 01:50:50.402574: step: 1700/530, loss: 0.0012716293567791581
2023-01-23 01:50:51.534482: step: 1704/530, loss: 0.0171247236430645
2023-01-23 01:50:52.643819: step: 1708/530, loss: 0.02732543833553791
2023-01-23 01:50:53.780213: step: 1712/530, loss: 0.013888073153793812
2023-01-23 01:50:54.923440: step: 1716/530, loss: 0.030884599313139915
2023-01-23 01:50:56.050208: step: 1720/530, loss: 0.007103061769157648
2023-01-23 01:50:57.176684: step: 1724/530, loss: 0.004729175940155983
2023-01-23 01:50:58.298843: step: 1728/530, loss: 0.05706644058227539
2023-01-23 01:50:59.426076: step: 1732/530, loss: 0.005995369050651789
2023-01-23 01:51:00.550245: step: 1736/530, loss: 0.0003991127014160156
2023-01-23 01:51:01.664582: step: 1740/530, loss: 0.6925798058509827
2023-01-23 01:51:02.814855: step: 1744/530, loss: 0.04055919498205185
2023-01-23 01:51:03.928634: step: 1748/530, loss: 0.002102470491081476
2023-01-23 01:51:05.079353: step: 1752/530, loss: 0.07019243389368057
2023-01-23 01:51:06.223250: step: 1756/530, loss: 0.05658683925867081
2023-01-23 01:51:07.341363: step: 1760/530, loss: 0.002086341381072998
2023-01-23 01:51:08.450241: step: 1764/530, loss: 0.001577663468196988
2023-01-23 01:51:09.602125: step: 1768/530, loss: 0.006244373507797718
2023-01-23 01:51:10.745036: step: 1772/530, loss: 0.3612518310546875
2023-01-23 01:51:11.853970: step: 1776/530, loss: 0.015101909637451172
2023-01-23 01:51:12.965687: step: 1780/530, loss: 0.0847724974155426
2023-01-23 01:51:14.069564: step: 1784/530, loss: 0.00976638775318861
2023-01-23 01:51:15.229324: step: 1788/530, loss: 0.02677140198647976
2023-01-23 01:51:16.364305: step: 1792/530, loss: 0.12057328224182129
2023-01-23 01:51:17.469641: step: 1796/530, loss: 0.039566993713378906
2023-01-23 01:51:18.592786: step: 1800/530, loss: 0.031155064702033997
2023-01-23 01:51:19.742455: step: 1804/530, loss: 0.0510038360953331
2023-01-23 01:51:20.847568: step: 1808/530, loss: 0.2271948754787445
2023-01-23 01:51:21.999156: step: 1812/530, loss: 0.03770599514245987
2023-01-23 01:51:23.146541: step: 1816/530, loss: 0.02655792236328125
2023-01-23 01:51:24.269343: step: 1820/530, loss: 0.06353969871997833
2023-01-23 01:51:25.380941: step: 1824/530, loss: 0.011070728302001953
2023-01-23 01:51:26.517658: step: 1828/530, loss: 0.02124013751745224
2023-01-23 01:51:27.654754: step: 1832/530, loss: 0.04510974884033203
2023-01-23 01:51:28.754139: step: 1836/530, loss: 0.0037247182335704565
2023-01-23 01:51:29.873434: step: 1840/530, loss: 0.0009141922346316278
2023-01-23 01:51:31.050733: step: 1844/530, loss: 0.07598743587732315
2023-01-23 01:51:32.174606: step: 1848/530, loss: 0.002524757292121649
2023-01-23 01:51:33.339946: step: 1852/530, loss: 0.002463913056999445
2023-01-23 01:51:34.450644: step: 1856/530, loss: 0.01686582714319229
2023-01-23 01:51:35.584662: step: 1860/530, loss: 0.04805488884449005
2023-01-23 01:51:36.705365: step: 1864/530, loss: 0.10145625472068787
2023-01-23 01:51:37.837064: step: 1868/530, loss: 0.014920043759047985
2023-01-23 01:51:38.975367: step: 1872/530, loss: 0.04007253795862198
2023-01-23 01:51:40.104423: step: 1876/530, loss: 0.01601381227374077
2023-01-23 01:51:41.265200: step: 1880/530, loss: 0.07569461315870285
2023-01-23 01:51:42.398135: step: 1884/530, loss: 0.08276758342981339
2023-01-23 01:51:43.518995: step: 1888/530, loss: 0.02415626309812069
2023-01-23 01:51:44.640967: step: 1892/530, loss: 0.0721045434474945
2023-01-23 01:51:45.753230: step: 1896/530, loss: 0.005602741148322821
2023-01-23 01:51:46.897981: step: 1900/530, loss: 0.028749562799930573
2023-01-23 01:51:48.083704: step: 1904/530, loss: 0.07246243953704834
2023-01-23 01:51:49.203302: step: 1908/530, loss: 0.0035462379455566406
2023-01-23 01:51:50.312509: step: 1912/530, loss: 0.027600575238466263
2023-01-23 01:51:51.449394: step: 1916/530, loss: 0.0345795638859272
2023-01-23 01:51:52.611691: step: 1920/530, loss: 0.027924824506044388
2023-01-23 01:51:53.719252: step: 1924/530, loss: 0.10221491008996964
2023-01-23 01:51:54.856275: step: 1928/530, loss: 0.033768463879823685
2023-01-23 01:51:55.996158: step: 1932/530, loss: 0.10360822081565857
2023-01-23 01:51:57.111960: step: 1936/530, loss: 0.008487892337143421
2023-01-23 01:51:58.247034: step: 1940/530, loss: 0.0664735808968544
2023-01-23 01:51:59.392094: step: 1944/530, loss: 0.01702880859375
2023-01-23 01:52:00.558202: step: 1948/530, loss: 0.041228488087654114
2023-01-23 01:52:01.679356: step: 1952/530, loss: 0.04789924621582031
2023-01-23 01:52:02.798840: step: 1956/530, loss: 0.24480323493480682
2023-01-23 01:52:03.937900: step: 1960/530, loss: 0.06211147457361221
2023-01-23 01:52:05.066473: step: 1964/530, loss: 0.08158645778894424
2023-01-23 01:52:06.198483: step: 1968/530, loss: 0.050138380378484726
2023-01-23 01:52:07.305591: step: 1972/530, loss: 0.0493866428732872
2023-01-23 01:52:08.440553: step: 1976/530, loss: 0.07204370945692062
2023-01-23 01:52:09.583581: step: 1980/530, loss: 0.00893263891339302
2023-01-23 01:52:10.710879: step: 1984/530, loss: 0.018795490264892578
2023-01-23 01:52:11.819468: step: 1988/530, loss: 0.005730056669563055
2023-01-23 01:52:12.929791: step: 1992/530, loss: 0.023281527683138847
2023-01-23 01:52:14.110623: step: 1996/530, loss: 0.0038669584318995476
2023-01-23 01:52:15.244980: step: 2000/530, loss: 0.005566787905991077
2023-01-23 01:52:16.373703: step: 2004/530, loss: 0.16923484206199646
2023-01-23 01:52:17.494066: step: 2008/530, loss: 0.002850151155143976
2023-01-23 01:52:18.627489: step: 2012/530, loss: 0.021324731409549713
2023-01-23 01:52:19.758494: step: 2016/530, loss: 0.05795307457447052
2023-01-23 01:52:20.885482: step: 2020/530, loss: 0.007312488742172718
2023-01-23 01:52:21.981766: step: 2024/530, loss: 0.10779037326574326
2023-01-23 01:52:23.092500: step: 2028/530, loss: 0.24489173293113708
2023-01-23 01:52:24.203224: step: 2032/530, loss: 0.07219743728637695
2023-01-23 01:52:25.318469: step: 2036/530, loss: 0.05699653923511505
2023-01-23 01:52:26.430733: step: 2040/530, loss: 0.009831905364990234
2023-01-23 01:52:27.560474: step: 2044/530, loss: 0.026160717010498047
2023-01-23 01:52:28.684964: step: 2048/530, loss: 0.08962202072143555
2023-01-23 01:52:29.807298: step: 2052/530, loss: 0.025419235229492188
2023-01-23 01:52:30.962367: step: 2056/530, loss: 0.07543888688087463
2023-01-23 01:52:32.105002: step: 2060/530, loss: 0.02982664294540882
2023-01-23 01:52:33.233833: step: 2064/530, loss: 0.007875251583755016
2023-01-23 01:52:34.348690: step: 2068/530, loss: 0.013072680681943893
2023-01-23 01:52:35.489873: step: 2072/530, loss: 0.014038849622011185
2023-01-23 01:52:36.612958: step: 2076/530, loss: 0.04870729520916939
2023-01-23 01:52:37.729717: step: 2080/530, loss: 0.007353019900619984
2023-01-23 01:52:38.858526: step: 2084/530, loss: 0.01072912197560072
2023-01-23 01:52:39.978457: step: 2088/530, loss: 0.024243880063295364
2023-01-23 01:52:41.092194: step: 2092/530, loss: 0.006252300925552845
2023-01-23 01:52:42.271244: step: 2096/530, loss: 0.04982433468103409
2023-01-23 01:52:43.412565: step: 2100/530, loss: 0.17879848182201385
2023-01-23 01:52:44.544554: step: 2104/530, loss: 0.5306503176689148
2023-01-23 01:52:45.686339: step: 2108/530, loss: 0.015310097485780716
2023-01-23 01:52:46.835313: step: 2112/530, loss: 0.26381298899650574
2023-01-23 01:52:47.963534: step: 2116/530, loss: 0.0025281906127929688
2023-01-23 01:52:49.099754: step: 2120/530, loss: 0.044076062738895416
==================================================
Loss: 0.054
--------------------
Dev: {'event': {'p': 0.5844155844155844, 'r': 0.7789613848202397, 'f1': 0.6678082191780821}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Test: {'event': {'p': 0.6120122753178431, 'r': 0.7977142857142857, 'f1': 0.6926321012155793}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Chinese: {'event': {'p': 0.532608695652174, 'r': 0.9074074074074074, 'f1': 0.6712328767123288}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Korean: {'event': {'p': 0.6029411764705882, 'r': 0.6507936507936508, 'f1': 0.6259541984732825}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
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': 13}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Chinese: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Chinese: {'event': {'p': 0.6190476190476191, 'r': 0.9629629629629629, 'f1': 0.7536231884057971}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6288770053475936, 'r': 0.7829560585885486, 'f1': 0.697508896797153}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Korean: {'event': {'p': 0.64058795637743, 'r': 0.772, 'f1': 0.7001813941435606}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Korean: {'event': {'p': 0.6851851851851852, 'r': 0.5873015873015873, 'f1': 0.6324786324786325}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5319148936170213, 'r': 0.6944444444444444, 'f1': 0.6024096385542169}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
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 01:53:29.922459: step: 4/530, loss: 0.011614632792770863
2023-01-23 01:53:31.053333: step: 8/530, loss: 0.00875482615083456
2023-01-23 01:53:32.161401: step: 12/530, loss: 0.006048774812370539
2023-01-23 01:53:33.278931: step: 16/530, loss: 0.038019370287656784
2023-01-23 01:53:34.380280: step: 20/530, loss: 0.055533263832330704
2023-01-23 01:53:35.505902: step: 24/530, loss: 0.09281311184167862
2023-01-23 01:53:36.648606: step: 28/530, loss: 0.05190415307879448
2023-01-23 01:53:37.774162: step: 32/530, loss: 0.037296175956726074
2023-01-23 01:53:38.917716: step: 36/530, loss: 0.022765349596738815
2023-01-23 01:53:40.042692: step: 40/530, loss: 0.018834495916962624
2023-01-23 01:53:41.162648: step: 44/530, loss: 0.01993551291525364
2023-01-23 01:53:42.317052: step: 48/530, loss: 0.071375273168087
2023-01-23 01:53:43.441230: step: 52/530, loss: 0.06283202022314072
2023-01-23 01:53:44.586053: step: 56/530, loss: 0.00954127311706543
2023-01-23 01:53:45.728044: step: 60/530, loss: 0.01134424190968275
2023-01-23 01:53:46.856651: step: 64/530, loss: 0.04735145717859268
2023-01-23 01:53:47.976911: step: 68/530, loss: 0.01192550640553236
2023-01-23 01:53:49.074763: step: 72/530, loss: 0.00162420270498842
2023-01-23 01:53:50.207030: step: 76/530, loss: 0.013175392523407936
2023-01-23 01:53:51.342060: step: 80/530, loss: 0.03166847303509712
2023-01-23 01:53:52.447739: step: 84/530, loss: 0.018859293311834335
2023-01-23 01:53:53.586975: step: 88/530, loss: 0.007655191235244274
2023-01-23 01:53:54.697617: step: 92/530, loss: 0.005402469541877508
2023-01-23 01:53:55.811751: step: 96/530, loss: 0.007023811340332031
2023-01-23 01:53:56.901781: step: 100/530, loss: 0.008267688564956188
2023-01-23 01:53:58.027221: step: 104/530, loss: 0.00035915375337935984
2023-01-23 01:53:59.159088: step: 108/530, loss: 0.010041522793471813
2023-01-23 01:54:00.265519: step: 112/530, loss: 0.021944807842373848
2023-01-23 01:54:01.394717: step: 116/530, loss: 0.00869598425924778
2023-01-23 01:54:02.519218: step: 120/530, loss: 0.02496328391134739
2023-01-23 01:54:03.672291: step: 124/530, loss: 0.01858053170144558
2023-01-23 01:54:04.801491: step: 128/530, loss: 0.002537250518798828
2023-01-23 01:54:05.926752: step: 132/530, loss: 0.09897881001234055
2023-01-23 01:54:07.066703: step: 136/530, loss: 0.02609109878540039
2023-01-23 01:54:08.174655: step: 140/530, loss: 0.010743808932602406
2023-01-23 01:54:09.326055: step: 144/530, loss: 0.02468266524374485
2023-01-23 01:54:10.479189: step: 148/530, loss: 0.008451557718217373
2023-01-23 01:54:11.607577: step: 152/530, loss: 0.05584258958697319
2023-01-23 01:54:12.716255: step: 156/530, loss: 0.025601863861083984
2023-01-23 01:54:13.849618: step: 160/530, loss: 0.014312935061752796
2023-01-23 01:54:14.986040: step: 164/530, loss: 0.024593163281679153
2023-01-23 01:54:16.090567: step: 168/530, loss: 0.0048694610595703125
2023-01-23 01:54:17.241072: step: 172/530, loss: 0.04972973093390465
2023-01-23 01:54:18.373908: step: 176/530, loss: 0.033026073127985
2023-01-23 01:54:19.499734: step: 180/530, loss: 0.004881524946540594
2023-01-23 01:54:20.659238: step: 184/530, loss: 0.010072755627334118
2023-01-23 01:54:21.799963: step: 188/530, loss: 0.0007537842029705644
2023-01-23 01:54:22.915617: step: 192/530, loss: 0.061823271214962006
2023-01-23 01:54:24.044360: step: 196/530, loss: 0.09506092220544815
2023-01-23 01:54:25.160088: step: 200/530, loss: 0.051161766052246094
2023-01-23 01:54:26.316891: step: 204/530, loss: 0.06315699219703674
2023-01-23 01:54:27.435537: step: 208/530, loss: 0.04589395597577095
2023-01-23 01:54:28.574604: step: 212/530, loss: 0.021100236102938652
2023-01-23 01:54:29.682464: step: 216/530, loss: 0.0356840118765831
2023-01-23 01:54:30.818467: step: 220/530, loss: 0.07996167987585068
2023-01-23 01:54:31.944007: step: 224/530, loss: 0.0011939048999920487
2023-01-23 01:54:33.103838: step: 228/530, loss: 0.013439369387924671
2023-01-23 01:54:34.235747: step: 232/530, loss: 0.003192424774169922
2023-01-23 01:54:35.332677: step: 236/530, loss: 0.01443710457533598
2023-01-23 01:54:36.459021: step: 240/530, loss: 0.0623815543949604
2023-01-23 01:54:37.598622: step: 244/530, loss: 0.06008262559771538
2023-01-23 01:54:38.725416: step: 248/530, loss: 0.13958033919334412
2023-01-23 01:54:39.858365: step: 252/530, loss: 0.0049245357513427734
2023-01-23 01:54:41.009624: step: 256/530, loss: 0.04537773132324219
2023-01-23 01:54:42.145896: step: 260/530, loss: 0.03262901306152344
2023-01-23 01:54:43.268323: step: 264/530, loss: 0.002602195832878351
2023-01-23 01:54:44.387575: step: 268/530, loss: 0.03478863090276718
2023-01-23 01:54:45.541095: step: 272/530, loss: 0.02126617543399334
2023-01-23 01:54:46.679186: step: 276/530, loss: 0.03520050272345543
2023-01-23 01:54:47.794109: step: 280/530, loss: 0.018367433920502663
2023-01-23 01:54:48.920257: step: 284/530, loss: 0.0038623332511633635
2023-01-23 01:54:50.060782: step: 288/530, loss: 0.07485237717628479
2023-01-23 01:54:51.188444: step: 292/530, loss: 0.0318751335144043
2023-01-23 01:54:52.291714: step: 296/530, loss: 0.5978411436080933
2023-01-23 01:54:53.410204: step: 300/530, loss: 0.0038347244262695312
2023-01-23 01:54:54.533018: step: 304/530, loss: 0.0168367400765419
2023-01-23 01:54:55.667519: step: 308/530, loss: 0.07303667068481445
2023-01-23 01:54:56.811024: step: 312/530, loss: 0.0010248185135424137
2023-01-23 01:54:57.934058: step: 316/530, loss: 0.07247648388147354
2023-01-23 01:54:59.054979: step: 320/530, loss: 0.013176393695175648
2023-01-23 01:55:00.193813: step: 324/530, loss: 0.0006782054551877081
2023-01-23 01:55:01.334211: step: 328/530, loss: 0.0049765584990382195
2023-01-23 01:55:02.439674: step: 332/530, loss: 0.6479880213737488
2023-01-23 01:55:03.564476: step: 336/530, loss: 0.054956816136837006
2023-01-23 01:55:04.673322: step: 340/530, loss: 0.05968761444091797
2023-01-23 01:55:05.794571: step: 344/530, loss: 0.009917259216308594
2023-01-23 01:55:06.925978: step: 348/530, loss: 0.0050331116653978825
2023-01-23 01:55:08.044813: step: 352/530, loss: 0.016166210174560547
2023-01-23 01:55:09.135850: step: 356/530, loss: 0.042746689170598984
2023-01-23 01:55:10.250181: step: 360/530, loss: 0.08296074718236923
2023-01-23 01:55:11.394421: step: 364/530, loss: 0.015878774225711823
2023-01-23 01:55:12.519103: step: 368/530, loss: 0.0005882263649255037
2023-01-23 01:55:13.670387: step: 372/530, loss: 0.05169658735394478
2023-01-23 01:55:14.792143: step: 376/530, loss: 0.04137105867266655
2023-01-23 01:55:15.946245: step: 380/530, loss: 0.0017870903247967362
2023-01-23 01:55:17.065532: step: 384/530, loss: 0.0015769958263263106
2023-01-23 01:55:18.187842: step: 388/530, loss: 0.025294732302427292
2023-01-23 01:55:19.316534: step: 392/530, loss: 0.010542010888457298
2023-01-23 01:55:20.439845: step: 396/530, loss: 0.00035343170748092234
2023-01-23 01:55:21.632666: step: 400/530, loss: 0.0047206878662109375
2023-01-23 01:55:22.758340: step: 404/530, loss: 0.03917226940393448
2023-01-23 01:55:23.874509: step: 408/530, loss: 0.034130096435546875
2023-01-23 01:55:24.969590: step: 412/530, loss: 0.023939132690429688
2023-01-23 01:55:26.093253: step: 416/530, loss: 0.02044057846069336
2023-01-23 01:55:27.235227: step: 420/530, loss: 0.08950252830982208
2023-01-23 01:55:28.368412: step: 424/530, loss: 0.04264846071600914
2023-01-23 01:55:29.480500: step: 428/530, loss: 0.01305251196026802
2023-01-23 01:55:30.635889: step: 432/530, loss: 0.07245617359876633
2023-01-23 01:55:31.770000: step: 436/530, loss: 0.12039823830127716
2023-01-23 01:55:32.899200: step: 440/530, loss: 0.04762401431798935
2023-01-23 01:55:34.038039: step: 444/530, loss: 0.016257477924227715
2023-01-23 01:55:35.188853: step: 448/530, loss: 0.0035455701872706413
2023-01-23 01:55:36.324723: step: 452/530, loss: 0.05297694355249405
2023-01-23 01:55:37.460795: step: 456/530, loss: 0.033902548253536224
2023-01-23 01:55:38.596220: step: 460/530, loss: 0.045664310455322266
2023-01-23 01:55:39.725180: step: 464/530, loss: 0.05560912936925888
2023-01-23 01:55:40.851679: step: 468/530, loss: 0.19419363141059875
2023-01-23 01:55:41.967236: step: 472/530, loss: 0.0026996613014489412
2023-01-23 01:55:43.119739: step: 476/530, loss: 0.014448070898652077
2023-01-23 01:55:44.252993: step: 480/530, loss: 0.15438775718212128
2023-01-23 01:55:45.400698: step: 484/530, loss: 0.018667984753847122
2023-01-23 01:55:46.512857: step: 488/530, loss: 0.10785046219825745
2023-01-23 01:55:47.626278: step: 492/530, loss: 0.041814230382442474
2023-01-23 01:55:48.726196: step: 496/530, loss: 0.048674874007701874
2023-01-23 01:55:49.856426: step: 500/530, loss: 0.09097880870103836
2023-01-23 01:55:50.962855: step: 504/530, loss: 0.009897613897919655
2023-01-23 01:55:52.107831: step: 508/530, loss: 0.05281992256641388
2023-01-23 01:55:53.226264: step: 512/530, loss: 0.01778879202902317
2023-01-23 01:55:54.341365: step: 516/530, loss: 0.03255109861493111
2023-01-23 01:55:55.478778: step: 520/530, loss: 0.04271812364459038
2023-01-23 01:55:56.604693: step: 524/530, loss: 0.0186964999884367
2023-01-23 01:55:57.709348: step: 528/530, loss: 0.084368035197258
2023-01-23 01:55:58.869782: step: 532/530, loss: 0.055545903742313385
2023-01-23 01:55:59.971288: step: 536/530, loss: 0.0026681902818381786
2023-01-23 01:56:01.077462: step: 540/530, loss: 0.013454437255859375
2023-01-23 01:56:02.223233: step: 544/530, loss: 0.02357807196676731
2023-01-23 01:56:03.346942: step: 548/530, loss: 0.004240131471306086
2023-01-23 01:56:04.469344: step: 552/530, loss: 0.05067300796508789
2023-01-23 01:56:05.576949: step: 556/530, loss: 0.024183034896850586
2023-01-23 01:56:06.731783: step: 560/530, loss: 0.06223888322710991
2023-01-23 01:56:07.854340: step: 564/530, loss: 0.016031645238399506
2023-01-23 01:56:08.976135: step: 568/530, loss: 0.0013477326137945056
2023-01-23 01:56:10.128624: step: 572/530, loss: 0.011874294839799404
2023-01-23 01:56:11.212214: step: 576/530, loss: 0.0015110969543457031
2023-01-23 01:56:12.385676: step: 580/530, loss: 0.029699325561523438
2023-01-23 01:56:13.507538: step: 584/530, loss: 0.013843799009919167
2023-01-23 01:56:14.604955: step: 588/530, loss: 0.07956790924072266
2023-01-23 01:56:15.757774: step: 592/530, loss: 0.03493232652544975
2023-01-23 01:56:16.856660: step: 596/530, loss: 0.0057496074587106705
2023-01-23 01:56:17.996694: step: 600/530, loss: 0.02654147334396839
2023-01-23 01:56:19.110207: step: 604/530, loss: 0.006798935122787952
2023-01-23 01:56:20.249742: step: 608/530, loss: 0.0016205310821533203
2023-01-23 01:56:21.383955: step: 612/530, loss: 0.03766594082117081
2023-01-23 01:56:22.519399: step: 616/530, loss: 0.0216046329587698
2023-01-23 01:56:23.630108: step: 620/530, loss: 0.021416999399662018
2023-01-23 01:56:24.773171: step: 624/530, loss: 0.025049591436982155
2023-01-23 01:56:25.893019: step: 628/530, loss: 0.004002762027084827
2023-01-23 01:56:27.019950: step: 632/530, loss: 0.04841761663556099
2023-01-23 01:56:28.138067: step: 636/530, loss: 0.0026119709946215153
2023-01-23 01:56:29.255581: step: 640/530, loss: 0.01607217825949192
2023-01-23 01:56:30.349196: step: 644/530, loss: 0.014604663476347923
2023-01-23 01:56:31.483280: step: 648/530, loss: 0.009646224789321423
2023-01-23 01:56:32.598948: step: 652/530, loss: 0.03547925874590874
2023-01-23 01:56:33.718110: step: 656/530, loss: 0.006899738218635321
2023-01-23 01:56:34.867311: step: 660/530, loss: 0.005611706059426069
2023-01-23 01:56:35.987405: step: 664/530, loss: 0.00176239013671875
2023-01-23 01:56:37.115230: step: 668/530, loss: 0.013766860589385033
2023-01-23 01:56:38.220324: step: 672/530, loss: 0.010090637020766735
2023-01-23 01:56:39.368758: step: 676/530, loss: 0.026205826550722122
2023-01-23 01:56:40.488660: step: 680/530, loss: 0.058071136474609375
2023-01-23 01:56:41.588255: step: 684/530, loss: 0.008561707101762295
2023-01-23 01:56:42.727639: step: 688/530, loss: 0.6043720841407776
2023-01-23 01:56:43.881563: step: 692/530, loss: 0.011764168739318848
2023-01-23 01:56:44.992921: step: 696/530, loss: 0.05540619045495987
2023-01-23 01:56:46.129176: step: 700/530, loss: 0.0029535293579101562
2023-01-23 01:56:47.252533: step: 704/530, loss: 0.010497570969164371
2023-01-23 01:56:48.375767: step: 708/530, loss: 0.0013535500038415194
2023-01-23 01:56:49.485712: step: 712/530, loss: 0.06170158460736275
2023-01-23 01:56:50.644806: step: 716/530, loss: 0.20160122215747833
2023-01-23 01:56:51.758747: step: 720/530, loss: 0.00259819021448493
2023-01-23 01:56:52.896191: step: 724/530, loss: 0.03059425577521324
2023-01-23 01:56:54.025205: step: 728/530, loss: 0.03595118597149849
2023-01-23 01:56:55.140096: step: 732/530, loss: 0.017497826367616653
2023-01-23 01:56:56.275386: step: 736/530, loss: 0.0982154905796051
2023-01-23 01:56:57.415569: step: 740/530, loss: 0.05615973472595215
2023-01-23 01:56:58.552408: step: 744/530, loss: 0.015278339385986328
2023-01-23 01:56:59.670595: step: 748/530, loss: 0.019547367468476295
2023-01-23 01:57:00.803326: step: 752/530, loss: 0.030991362407803535
2023-01-23 01:57:01.952432: step: 756/530, loss: 0.03493404760956764
2023-01-23 01:57:03.100285: step: 760/530, loss: 0.02912154234945774
2023-01-23 01:57:04.241779: step: 764/530, loss: 0.017034530639648438
2023-01-23 01:57:05.378467: step: 768/530, loss: 0.0055144308134913445
2023-01-23 01:57:06.495827: step: 772/530, loss: 0.007080123294144869
2023-01-23 01:57:07.642939: step: 776/530, loss: 0.02785949781537056
2023-01-23 01:57:08.742739: step: 780/530, loss: 0.07312522083520889
2023-01-23 01:57:09.854341: step: 784/530, loss: 0.009125327691435814
2023-01-23 01:57:10.967656: step: 788/530, loss: 0.0877407044172287
2023-01-23 01:57:12.089702: step: 792/530, loss: 0.008423805236816406
2023-01-23 01:57:13.212968: step: 796/530, loss: 0.0689065009355545
2023-01-23 01:57:14.365704: step: 800/530, loss: 0.027076052501797676
2023-01-23 01:57:15.497983: step: 804/530, loss: 0.00040054324199445546
2023-01-23 01:57:16.631357: step: 808/530, loss: 0.04793129116296768
2023-01-23 01:57:17.738732: step: 812/530, loss: 0.13440386950969696
2023-01-23 01:57:18.841883: step: 816/530, loss: 0.04555549472570419
2023-01-23 01:57:19.992924: step: 820/530, loss: 0.053875066339969635
2023-01-23 01:57:21.082120: step: 824/530, loss: 0.04407463222742081
2023-01-23 01:57:22.215881: step: 828/530, loss: 0.004495048429816961
2023-01-23 01:57:23.336143: step: 832/530, loss: 0.022128771990537643
2023-01-23 01:57:24.463470: step: 836/530, loss: 0.12945061922073364
2023-01-23 01:57:25.599449: step: 840/530, loss: 0.023941706866025925
2023-01-23 01:57:26.748818: step: 844/530, loss: 0.01931781880557537
2023-01-23 01:57:27.863994: step: 848/530, loss: 0.24548988044261932
2023-01-23 01:57:28.951348: step: 852/530, loss: 0.040032196789979935
2023-01-23 01:57:30.090247: step: 856/530, loss: 0.022159194573760033
2023-01-23 01:57:31.222410: step: 860/530, loss: 0.02491931989789009
2023-01-23 01:57:32.326808: step: 864/530, loss: 0.007970571517944336
2023-01-23 01:57:33.435763: step: 868/530, loss: 0.005455113016068935
2023-01-23 01:57:34.596071: step: 872/530, loss: 0.021799776703119278
2023-01-23 01:57:35.770312: step: 876/530, loss: 0.00021867752366233617
2023-01-23 01:57:36.888714: step: 880/530, loss: 0.020279215648770332
2023-01-23 01:57:37.998676: step: 884/530, loss: 0.052863121032714844
2023-01-23 01:57:39.129068: step: 888/530, loss: 0.04783926159143448
2023-01-23 01:57:40.241297: step: 892/530, loss: 0.007754087448120117
2023-01-23 01:57:41.408653: step: 896/530, loss: 0.002638149308040738
2023-01-23 01:57:42.563766: step: 900/530, loss: 0.01988067664206028
2023-01-23 01:57:43.706178: step: 904/530, loss: 0.034543611109256744
2023-01-23 01:57:44.811133: step: 908/530, loss: 0.0473298579454422
2023-01-23 01:57:45.912282: step: 912/530, loss: 0.0488801971077919
2023-01-23 01:57:47.043093: step: 916/530, loss: 0.025903893634676933
2023-01-23 01:57:48.154438: step: 920/530, loss: 0.13345539569854736
2023-01-23 01:57:49.306838: step: 924/530, loss: 0.031414031982421875
2023-01-23 01:57:50.443504: step: 928/530, loss: 0.020247556269168854
2023-01-23 01:57:51.570744: step: 932/530, loss: 0.03822936862707138
2023-01-23 01:57:52.687623: step: 936/530, loss: 0.0014460564125329256
2023-01-23 01:57:53.803130: step: 940/530, loss: 0.009243393316864967
2023-01-23 01:57:54.951822: step: 944/530, loss: 0.030127812176942825
2023-01-23 01:57:56.069312: step: 948/530, loss: 0.3189052641391754
2023-01-23 01:57:57.204527: step: 952/530, loss: 0.01964416541159153
2023-01-23 01:57:58.337456: step: 956/530, loss: 0.0015039443969726562
2023-01-23 01:57:59.440604: step: 960/530, loss: 0.05226850509643555
2023-01-23 01:58:00.548454: step: 964/530, loss: 9.179115295410156e-05
2023-01-23 01:58:01.686625: step: 968/530, loss: 0.020391609519720078
2023-01-23 01:58:02.828212: step: 972/530, loss: 0.04525108262896538
2023-01-23 01:58:03.918347: step: 976/530, loss: 0.026174068450927734
2023-01-23 01:58:05.047119: step: 980/530, loss: 0.0138397216796875
2023-01-23 01:58:06.166475: step: 984/530, loss: 0.00580520648509264
2023-01-23 01:58:07.298710: step: 988/530, loss: 0.03634243085980415
2023-01-23 01:58:08.443382: step: 992/530, loss: 0.0058565144427120686
2023-01-23 01:58:09.580110: step: 996/530, loss: 0.03171367943286896
2023-01-23 01:58:10.672388: step: 1000/530, loss: 0.01773528940975666
2023-01-23 01:58:11.822420: step: 1004/530, loss: 0.026846598833799362
2023-01-23 01:58:12.951058: step: 1008/530, loss: 0.0807517021894455
2023-01-23 01:58:14.064380: step: 1012/530, loss: 0.0032012939918786287
2023-01-23 01:58:15.192421: step: 1016/530, loss: 0.005792141426354647
2023-01-23 01:58:16.321493: step: 1020/530, loss: 0.0022260667756199837
2023-01-23 01:58:17.436946: step: 1024/530, loss: 0.03456611931324005
2023-01-23 01:58:18.570616: step: 1028/530, loss: 0.03213310241699219
2023-01-23 01:58:19.684515: step: 1032/530, loss: 0.046746253967285156
2023-01-23 01:58:20.812969: step: 1036/530, loss: 0.01656341552734375
2023-01-23 01:58:21.920227: step: 1040/530, loss: 0.020496560260653496
2023-01-23 01:58:23.055053: step: 1044/530, loss: 0.015752125531435013
2023-01-23 01:58:24.171351: step: 1048/530, loss: 0.03952827304601669
2023-01-23 01:58:25.311896: step: 1052/530, loss: 0.03926678001880646
2023-01-23 01:58:26.429822: step: 1056/530, loss: 0.03547210618853569
2023-01-23 01:58:27.553046: step: 1060/530, loss: 0.007499885745346546
2023-01-23 01:58:28.689854: step: 1064/530, loss: 0.08795013278722763
2023-01-23 01:58:29.781558: step: 1068/530, loss: 0.01462945993989706
2023-01-23 01:58:30.896436: step: 1072/530, loss: 0.0024263381492346525
2023-01-23 01:58:31.991983: step: 1076/530, loss: 0.030530165880918503
2023-01-23 01:58:33.115835: step: 1080/530, loss: 0.025494862347841263
2023-01-23 01:58:34.243185: step: 1084/530, loss: 0.03757515177130699
2023-01-23 01:58:35.380989: step: 1088/530, loss: 0.003063297364860773
2023-01-23 01:58:36.480655: step: 1092/530, loss: 0.03311929479241371
2023-01-23 01:58:37.587898: step: 1096/530, loss: 0.02033987082540989
2023-01-23 01:58:38.732921: step: 1100/530, loss: 0.07032446563243866
2023-01-23 01:58:39.855304: step: 1104/530, loss: 0.07821130752563477
2023-01-23 01:58:40.972390: step: 1108/530, loss: 0.007036781404167414
2023-01-23 01:58:42.103717: step: 1112/530, loss: 0.04807768017053604
2023-01-23 01:58:43.252867: step: 1116/530, loss: 0.06623172760009766
2023-01-23 01:58:44.378758: step: 1120/530, loss: 0.011804867535829544
2023-01-23 01:58:45.508336: step: 1124/530, loss: 0.02893754467368126
2023-01-23 01:58:46.654765: step: 1128/530, loss: 0.012345314025878906
2023-01-23 01:58:47.803013: step: 1132/530, loss: 0.004823207855224609
2023-01-23 01:58:48.937191: step: 1136/530, loss: 0.042534828186035156
2023-01-23 01:58:50.078148: step: 1140/530, loss: 0.016106510534882545
2023-01-23 01:58:51.205013: step: 1144/530, loss: 0.006917620077729225
2023-01-23 01:58:52.327990: step: 1148/530, loss: 0.027724934741854668
2023-01-23 01:58:53.431718: step: 1152/530, loss: 0.0031442642211914062
2023-01-23 01:58:54.554727: step: 1156/530, loss: 0.04799060896039009
2023-01-23 01:58:55.679917: step: 1160/530, loss: 0.01398468017578125
2023-01-23 01:58:56.784630: step: 1164/530, loss: 0.00039610863314010203
2023-01-23 01:58:57.925911: step: 1168/530, loss: 0.0068511962890625
2023-01-23 01:58:59.075043: step: 1172/530, loss: 0.04163169860839844
2023-01-23 01:59:00.188041: step: 1176/530, loss: 0.05417843163013458
2023-01-23 01:59:01.316161: step: 1180/530, loss: 0.0002711772976908833
2023-01-23 01:59:02.419797: step: 1184/530, loss: 0.007947730831801891
2023-01-23 01:59:03.543911: step: 1188/530, loss: 0.07177191227674484
2023-01-23 01:59:04.693675: step: 1192/530, loss: 0.011019134894013405
2023-01-23 01:59:05.849125: step: 1196/530, loss: 0.0009962081676349044
2023-01-23 01:59:06.972703: step: 1200/530, loss: 0.04658927768468857
2023-01-23 01:59:08.111982: step: 1204/530, loss: 0.029930591583251953
2023-01-23 01:59:09.230727: step: 1208/530, loss: 0.09436826407909393
2023-01-23 01:59:10.376143: step: 1212/530, loss: 0.05301017314195633
2023-01-23 01:59:11.485844: step: 1216/530, loss: 0.012265825644135475
2023-01-23 01:59:12.601095: step: 1220/530, loss: 0.011836815625429153
2023-01-23 01:59:13.718990: step: 1224/530, loss: 0.011752987280488014
2023-01-23 01:59:14.852229: step: 1228/530, loss: 0.08987322449684143
2023-01-23 01:59:15.965539: step: 1232/530, loss: 0.06338530033826828
2023-01-23 01:59:17.143377: step: 1236/530, loss: 0.11370324343442917
2023-01-23 01:59:18.258317: step: 1240/530, loss: 0.004010105039924383
2023-01-23 01:59:19.372545: step: 1244/530, loss: 0.023255730047822
2023-01-23 01:59:20.520794: step: 1248/530, loss: 0.03536796569824219
2023-01-23 01:59:21.639721: step: 1252/530, loss: 0.011076068505644798
2023-01-23 01:59:22.765771: step: 1256/530, loss: 0.026825379580259323
2023-01-23 01:59:23.909197: step: 1260/530, loss: 0.05673384666442871
2023-01-23 01:59:25.075798: step: 1264/530, loss: 0.061617661267519
2023-01-23 01:59:26.208692: step: 1268/530, loss: 0.029776956886053085
2023-01-23 01:59:27.344469: step: 1272/530, loss: 0.0402863509953022
2023-01-23 01:59:28.439963: step: 1276/530, loss: 0.09151887893676758
2023-01-23 01:59:29.535894: step: 1280/530, loss: 0.08565321564674377
2023-01-23 01:59:30.675730: step: 1284/530, loss: 0.19208411872386932
2023-01-23 01:59:31.809219: step: 1288/530, loss: 0.06013622134923935
2023-01-23 01:59:32.944972: step: 1292/530, loss: 0.002103495644405484
2023-01-23 01:59:34.058535: step: 1296/530, loss: 0.05688466876745224
2023-01-23 01:59:35.177440: step: 1300/530, loss: 0.020755957812070847
2023-01-23 01:59:36.323391: step: 1304/530, loss: 0.6078685522079468
2023-01-23 01:59:37.477967: step: 1308/530, loss: 0.04209098964929581
2023-01-23 01:59:38.609479: step: 1312/530, loss: 0.0006928443908691406
2023-01-23 01:59:39.716612: step: 1316/530, loss: 0.0005797386402264237
2023-01-23 01:59:40.844261: step: 1320/530, loss: 0.06263237446546555
2023-01-23 01:59:41.951863: step: 1324/530, loss: 0.0015227318508550525
2023-01-23 01:59:43.067668: step: 1328/530, loss: 0.011327744461596012
2023-01-23 01:59:44.208323: step: 1332/530, loss: 0.026087570935487747
2023-01-23 01:59:45.354530: step: 1336/530, loss: 0.03292350843548775
2023-01-23 01:59:46.480142: step: 1340/530, loss: 0.01969299279153347
2023-01-23 01:59:47.627767: step: 1344/530, loss: 0.0038364408537745476
2023-01-23 01:59:48.772063: step: 1348/530, loss: 0.04836463928222656
2023-01-23 01:59:49.893733: step: 1352/530, loss: 0.012911511585116386
2023-01-23 01:59:51.033813: step: 1356/530, loss: 0.013796997256577015
2023-01-23 01:59:52.131206: step: 1360/530, loss: 0.10867755115032196
2023-01-23 01:59:53.330395: step: 1364/530, loss: 0.04073600843548775
2023-01-23 01:59:54.456911: step: 1368/530, loss: 0.22793197631835938
2023-01-23 01:59:55.579719: step: 1372/530, loss: 0.018036365509033203
2023-01-23 01:59:56.693949: step: 1376/530, loss: 0.10865173488855362
2023-01-23 01:59:57.827794: step: 1380/530, loss: 0.010687733069062233
2023-01-23 01:59:58.951904: step: 1384/530, loss: 0.04401545599102974
2023-01-23 02:00:00.080193: step: 1388/530, loss: 0.028109312057495117
2023-01-23 02:00:01.215380: step: 1392/530, loss: 0.008869337849318981
2023-01-23 02:00:02.377539: step: 1396/530, loss: 0.8209370374679565
2023-01-23 02:00:03.508325: step: 1400/530, loss: 0.19197502732276917
2023-01-23 02:00:04.632950: step: 1404/530, loss: 0.15016447007656097
2023-01-23 02:00:05.767401: step: 1408/530, loss: 0.03181910514831543
2023-01-23 02:00:06.869999: step: 1412/530, loss: 0.004067468922585249
2023-01-23 02:00:08.003402: step: 1416/530, loss: 0.024436473846435547
2023-01-23 02:00:09.164882: step: 1420/530, loss: 0.020074177533388138
2023-01-23 02:00:10.301670: step: 1424/530, loss: 0.0016744612948969007
2023-01-23 02:00:11.444172: step: 1428/530, loss: 0.01753692701458931
2023-01-23 02:00:12.558712: step: 1432/530, loss: 0.040731146931648254
2023-01-23 02:00:13.663470: step: 1436/530, loss: 0.14642544090747833
2023-01-23 02:00:14.810660: step: 1440/530, loss: 0.012515068054199219
2023-01-23 02:00:15.917502: step: 1444/530, loss: 0.0251206886023283
2023-01-23 02:00:17.054564: step: 1448/530, loss: 0.0033741951920092106
2023-01-23 02:00:18.197054: step: 1452/530, loss: 0.16393500566482544
2023-01-23 02:00:19.308948: step: 1456/530, loss: 0.005092191975563765
2023-01-23 02:00:20.417705: step: 1460/530, loss: 0.028334427624940872
2023-01-23 02:00:21.551540: step: 1464/530, loss: 0.02130146138370037
2023-01-23 02:00:22.649631: step: 1468/530, loss: 0.0023598670959472656
2023-01-23 02:00:23.810992: step: 1472/530, loss: 0.026300620287656784
2023-01-23 02:00:24.941265: step: 1476/530, loss: 0.02457866631448269
2023-01-23 02:00:26.048324: step: 1480/530, loss: 0.049874190241098404
2023-01-23 02:00:27.197718: step: 1484/530, loss: 0.00018138886662200093
2023-01-23 02:00:28.312056: step: 1488/530, loss: 0.01586780697107315
2023-01-23 02:00:29.462990: step: 1492/530, loss: 0.007094383239746094
2023-01-23 02:00:30.583734: step: 1496/530, loss: 0.013970375061035156
2023-01-23 02:00:31.707862: step: 1500/530, loss: 0.006769562140107155
2023-01-23 02:00:32.878450: step: 1504/530, loss: 0.03720364719629288
2023-01-23 02:00:34.023359: step: 1508/530, loss: 0.004189491271972656
2023-01-23 02:00:35.138454: step: 1512/530, loss: 0.00684509240090847
2023-01-23 02:00:36.252717: step: 1516/530, loss: 0.004998529329895973
2023-01-23 02:00:37.355864: step: 1520/530, loss: 0.011357736773788929
2023-01-23 02:00:38.486643: step: 1524/530, loss: 0.009348297491669655
2023-01-23 02:00:39.604186: step: 1528/530, loss: 0.0015817641979083419
2023-01-23 02:00:40.730430: step: 1532/530, loss: 0.043148234486579895
2023-01-23 02:00:41.873458: step: 1536/530, loss: 0.022484874352812767
2023-01-23 02:00:42.991711: step: 1540/530, loss: 0.08454723656177521
2023-01-23 02:00:44.136388: step: 1544/530, loss: 0.043316081166267395
2023-01-23 02:00:45.249566: step: 1548/530, loss: 0.01892075501382351
2023-01-23 02:00:46.378820: step: 1552/530, loss: 0.09686336666345596
2023-01-23 02:00:47.496385: step: 1556/530, loss: 0.048360638320446014
2023-01-23 02:00:48.622109: step: 1560/530, loss: 0.04056549072265625
2023-01-23 02:00:49.734421: step: 1564/530, loss: 0.008250045590102673
2023-01-23 02:00:50.849409: step: 1568/530, loss: 0.04723015055060387
2023-01-23 02:00:51.946844: step: 1572/530, loss: 0.011099529452621937
2023-01-23 02:00:53.094737: step: 1576/530, loss: 0.016785716637969017
2023-01-23 02:00:54.221305: step: 1580/530, loss: 0.014361954294145107
2023-01-23 02:00:55.362644: step: 1584/530, loss: 0.09405174851417542
2023-01-23 02:00:56.473899: step: 1588/530, loss: 0.06905422359704971
2023-01-23 02:00:57.613166: step: 1592/530, loss: 0.06335728615522385
2023-01-23 02:00:58.723700: step: 1596/530, loss: 0.037729643285274506
2023-01-23 02:00:59.847911: step: 1600/530, loss: 0.05177593231201172
2023-01-23 02:01:00.961169: step: 1604/530, loss: 0.23136445879936218
2023-01-23 02:01:02.102222: step: 1608/530, loss: 0.004282331559807062
2023-01-23 02:01:03.218947: step: 1612/530, loss: 0.026232624426484108
2023-01-23 02:01:04.311576: step: 1616/530, loss: 0.1315983384847641
2023-01-23 02:01:05.461998: step: 1620/530, loss: 0.0872398391366005
2023-01-23 02:01:06.591233: step: 1624/530, loss: 0.021900463849306107
2023-01-23 02:01:07.756609: step: 1628/530, loss: 0.07352671772241592
2023-01-23 02:01:08.883830: step: 1632/530, loss: 0.0126075753942132
2023-01-23 02:01:09.997495: step: 1636/530, loss: 0.006818008609116077
2023-01-23 02:01:11.134895: step: 1640/530, loss: 0.006765037775039673
2023-01-23 02:01:12.230836: step: 1644/530, loss: 0.08382062613964081
2023-01-23 02:01:13.379142: step: 1648/530, loss: 0.00010414123971713707
2023-01-23 02:01:14.505132: step: 1652/530, loss: 0.008768081665039062
2023-01-23 02:01:15.631318: step: 1656/530, loss: 0.005158806219696999
2023-01-23 02:01:16.748735: step: 1660/530, loss: 0.014765358529984951
2023-01-23 02:01:17.858246: step: 1664/530, loss: 0.15240421891212463
2023-01-23 02:01:18.993791: step: 1668/530, loss: 0.03971615061163902
2023-01-23 02:01:20.126075: step: 1672/530, loss: 0.02486591413617134
2023-01-23 02:01:21.264751: step: 1676/530, loss: 0.0031307220924645662
2023-01-23 02:01:22.376750: step: 1680/530, loss: 0.0004601478576660156
2023-01-23 02:01:23.520259: step: 1684/530, loss: 0.08950719982385635
2023-01-23 02:01:24.625982: step: 1688/530, loss: 0.018713902682065964
2023-01-23 02:01:25.741590: step: 1692/530, loss: 0.00400543212890625
2023-01-23 02:01:26.866071: step: 1696/530, loss: 0.009966564364731312
2023-01-23 02:01:27.974847: step: 1700/530, loss: 0.07936535030603409
2023-01-23 02:01:29.077332: step: 1704/530, loss: 0.004069423768669367
2023-01-23 02:01:30.204300: step: 1708/530, loss: 0.03754892200231552
2023-01-23 02:01:31.341623: step: 1712/530, loss: 0.0348600409924984
2023-01-23 02:01:32.462441: step: 1716/530, loss: 0.2651368975639343
2023-01-23 02:01:33.622245: step: 1720/530, loss: 0.025855161249637604
2023-01-23 02:01:34.740341: step: 1724/530, loss: 0.001140594482421875
2023-01-23 02:01:35.887814: step: 1728/530, loss: 0.06389045715332031
2023-01-23 02:01:37.024359: step: 1732/530, loss: 0.1389492005109787
2023-01-23 02:01:38.165279: step: 1736/530, loss: 0.015485953539609909
2023-01-23 02:01:39.308491: step: 1740/530, loss: 0.005508899688720703
2023-01-23 02:01:40.434393: step: 1744/530, loss: 0.009121894836425781
2023-01-23 02:01:41.569245: step: 1748/530, loss: 0.009945916943252087
2023-01-23 02:01:42.683703: step: 1752/530, loss: 0.006153964903205633
2023-01-23 02:01:43.808031: step: 1756/530, loss: 0.09885292500257492
2023-01-23 02:01:44.914762: step: 1760/530, loss: 0.04025983810424805
2023-01-23 02:01:46.052068: step: 1764/530, loss: 0.07625599205493927
2023-01-23 02:01:47.190740: step: 1768/530, loss: 0.019740868359804153
2023-01-23 02:01:48.337240: step: 1772/530, loss: 0.021004868671298027
2023-01-23 02:01:49.461725: step: 1776/530, loss: 0.014562273398041725
2023-01-23 02:01:50.628945: step: 1780/530, loss: 0.04524674266576767
2023-01-23 02:01:51.762350: step: 1784/530, loss: 0.05356607586145401
2023-01-23 02:01:52.911553: step: 1788/530, loss: 0.0212983600795269
2023-01-23 02:01:54.031352: step: 1792/530, loss: 0.00856771506369114
2023-01-23 02:01:55.170005: step: 1796/530, loss: 0.04802503436803818
2023-01-23 02:01:56.295915: step: 1800/530, loss: 0.0057763103395700455
2023-01-23 02:01:57.418221: step: 1804/530, loss: 0.009444618597626686
2023-01-23 02:01:58.539792: step: 1808/530, loss: 0.04359636455774307
2023-01-23 02:01:59.673017: step: 1812/530, loss: 0.06904659420251846
2023-01-23 02:02:00.808980: step: 1816/530, loss: 0.007182121276855469
2023-01-23 02:02:01.923999: step: 1820/530, loss: 0.042980484664440155
2023-01-23 02:02:03.054295: step: 1824/530, loss: 0.16691899299621582
2023-01-23 02:02:04.202323: step: 1828/530, loss: 0.1238914504647255
2023-01-23 02:02:05.320735: step: 1832/530, loss: 0.08206959068775177
2023-01-23 02:02:06.446252: step: 1836/530, loss: 0.13522785902023315
2023-01-23 02:02:07.551339: step: 1840/530, loss: 0.048134710639715195
2023-01-23 02:02:08.695841: step: 1844/530, loss: 0.05525932461023331
2023-01-23 02:02:09.815002: step: 1848/530, loss: 0.012070799246430397
2023-01-23 02:02:10.924683: step: 1852/530, loss: 0.0012735367054119706
2023-01-23 02:02:12.037067: step: 1856/530, loss: 0.01072161179035902
2023-01-23 02:02:13.212463: step: 1860/530, loss: 0.002234077313914895
2023-01-23 02:02:14.351459: step: 1864/530, loss: 0.020227743312716484
2023-01-23 02:02:15.451757: step: 1868/530, loss: 0.015953445807099342
2023-01-23 02:02:16.585249: step: 1872/530, loss: 0.06407356262207031
2023-01-23 02:02:17.725893: step: 1876/530, loss: 0.004475403111428022
2023-01-23 02:02:18.857666: step: 1880/530, loss: 0.0023292540572583675
2023-01-23 02:02:19.992118: step: 1884/530, loss: 0.029547691345214844
2023-01-23 02:02:21.127777: step: 1888/530, loss: 0.024480152875185013
2023-01-23 02:02:22.229378: step: 1892/530, loss: 0.06298257410526276
2023-01-23 02:02:23.364739: step: 1896/530, loss: 0.024497129023075104
2023-01-23 02:02:24.506277: step: 1900/530, loss: 0.03539686277508736
2023-01-23 02:02:25.606381: step: 1904/530, loss: 0.0018640517955645919
2023-01-23 02:02:26.726580: step: 1908/530, loss: 0.03484821319580078
2023-01-23 02:02:27.862470: step: 1912/530, loss: 0.0005494117503985763
2023-01-23 02:02:29.023052: step: 1916/530, loss: 0.03587331995368004
2023-01-23 02:02:30.148351: step: 1920/530, loss: 0.03732709959149361
2023-01-23 02:02:31.284444: step: 1924/530, loss: 0.06584224849939346
2023-01-23 02:02:32.429444: step: 1928/530, loss: 0.01770963706076145
2023-01-23 02:02:33.551741: step: 1932/530, loss: 0.02332754246890545
2023-01-23 02:02:34.683619: step: 1936/530, loss: 0.025484418496489525
2023-01-23 02:02:35.817806: step: 1940/530, loss: 0.049616243690252304
2023-01-23 02:02:36.917693: step: 1944/530, loss: 0.0028761865105479956
2023-01-23 02:02:38.049505: step: 1948/530, loss: 0.006197929382324219
2023-01-23 02:02:39.171769: step: 1952/530, loss: 0.03634147718548775
2023-01-23 02:02:40.315379: step: 1956/530, loss: 0.016082191839814186
2023-01-23 02:02:41.427373: step: 1960/530, loss: 0.07926121354103088
2023-01-23 02:02:42.546624: step: 1964/530, loss: 0.04786348342895508
2023-01-23 02:02:43.648285: step: 1968/530, loss: 0.32118111848831177
2023-01-23 02:02:44.776008: step: 1972/530, loss: 0.06851263344287872
2023-01-23 02:02:45.910458: step: 1976/530, loss: 0.002298068953678012
2023-01-23 02:02:47.037150: step: 1980/530, loss: 0.0031773566734045744
2023-01-23 02:02:48.172757: step: 1984/530, loss: 0.03522634506225586
2023-01-23 02:02:49.294798: step: 1988/530, loss: 0.012848949991166592
2023-01-23 02:02:50.472241: step: 1992/530, loss: 0.01975088194012642
2023-01-23 02:02:51.616785: step: 1996/530, loss: 0.007328987121582031
2023-01-23 02:02:52.734119: step: 2000/530, loss: 0.002330494113266468
2023-01-23 02:02:53.885994: step: 2004/530, loss: 0.005862521938979626
2023-01-23 02:02:55.043437: step: 2008/530, loss: 0.06223049387335777
2023-01-23 02:02:56.184354: step: 2012/530, loss: 0.037198830395936966
2023-01-23 02:02:57.344166: step: 2016/530, loss: 0.0237592700868845
2023-01-23 02:02:58.461863: step: 2020/530, loss: 0.026169586926698685
2023-01-23 02:02:59.605657: step: 2024/530, loss: 0.004082823172211647
2023-01-23 02:03:00.712750: step: 2028/530, loss: 0.004319810774177313
2023-01-23 02:03:01.844292: step: 2032/530, loss: 0.11130237579345703
2023-01-23 02:03:02.985427: step: 2036/530, loss: 0.025355147197842598
2023-01-23 02:03:04.121234: step: 2040/530, loss: 0.006113815121352673
2023-01-23 02:03:05.242942: step: 2044/530, loss: 0.01732168346643448
2023-01-23 02:03:06.377815: step: 2048/530, loss: 0.03524360805749893
2023-01-23 02:03:07.493306: step: 2052/530, loss: 0.012261915020644665
2023-01-23 02:03:08.637906: step: 2056/530, loss: 0.0031192780006676912
2023-01-23 02:03:09.741841: step: 2060/530, loss: 0.018718766048550606
2023-01-23 02:03:10.862164: step: 2064/530, loss: 0.011591911315917969
2023-01-23 02:03:11.977688: step: 2068/530, loss: 0.2759284973144531
2023-01-23 02:03:13.117055: step: 2072/530, loss: 0.029091263189911842
2023-01-23 02:03:14.220248: step: 2076/530, loss: 0.008381462655961514
2023-01-23 02:03:15.364383: step: 2080/530, loss: 0.32871073484420776
2023-01-23 02:03:16.496026: step: 2084/530, loss: 0.03321533277630806
2023-01-23 02:03:17.627833: step: 2088/530, loss: 0.016414355486631393
2023-01-23 02:03:18.745083: step: 2092/530, loss: 0.03246940299868584
2023-01-23 02:03:19.859399: step: 2096/530, loss: 0.38019055128097534
2023-01-23 02:03:20.962850: step: 2100/530, loss: 0.0020826340187340975
2023-01-23 02:03:22.038061: step: 2104/530, loss: 0.19869403541088104
2023-01-23 02:03:23.165630: step: 2108/530, loss: 0.04479274898767471
2023-01-23 02:03:24.340194: step: 2112/530, loss: 0.009046363644301891
2023-01-23 02:03:25.470571: step: 2116/530, loss: 0.07706699520349503
2023-01-23 02:03:26.621864: step: 2120/530, loss: 0.0016527175903320312
==================================================
Loss: 0.044
--------------------
Dev: {'event': {'p': 0.601025641025641, 'r': 0.7802929427430093, 'f1': 0.679026651216686}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 14}
Test: {'event': {'p': 0.6302177858439202, 'r': 0.7937142857142857, 'f1': 0.7025796661608498}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 14}
Chinese: {'event': {'p': 0.5833333333333334, 'r': 0.9074074074074074, 'f1': 0.7101449275362318}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 14}
Korean: {'event': {'p': 0.59375, 'r': 0.6031746031746031, 'f1': 0.5984251968503936}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 14}
Russian: {'event': {'p': 0.45454545454545453, 'r': 0.5555555555555556, 'f1': 0.5}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 14}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Chinese: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Chinese: {'event': {'p': 0.6190476190476191, 'r': 0.9629629629629629, 'f1': 0.7536231884057971}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6288770053475936, 'r': 0.7829560585885486, 'f1': 0.697508896797153}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Korean: {'event': {'p': 0.64058795637743, 'r': 0.772, 'f1': 0.7001813941435606}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Korean: {'event': {'p': 0.6851851851851852, 'r': 0.5873015873015873, 'f1': 0.6324786324786325}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5319148936170213, 'r': 0.6944444444444444, 'f1': 0.6024096385542169}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
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 02:04:07.505062: step: 4/530, loss: 0.0022495747543871403
2023-01-23 02:04:08.684884: step: 8/530, loss: 0.027453137561678886
2023-01-23 02:04:09.797856: step: 12/530, loss: 0.015173769555985928
2023-01-23 02:04:10.903421: step: 16/530, loss: 1.9836426872643642e-05
2023-01-23 02:04:12.018684: step: 20/530, loss: 0.04127292335033417
2023-01-23 02:04:13.170962: step: 24/530, loss: 0.0335293784737587
2023-01-23 02:04:14.299111: step: 28/530, loss: 0.0039837840013206005
2023-01-23 02:04:15.413223: step: 32/530, loss: 0.019377900287508965
2023-01-23 02:04:16.529859: step: 36/530, loss: 0.030337335541844368
2023-01-23 02:04:17.652209: step: 40/530, loss: 0.03910894691944122
2023-01-23 02:04:18.769835: step: 44/530, loss: 0.07952761650085449
2023-01-23 02:04:19.883287: step: 48/530, loss: 0.01567859575152397
2023-01-23 02:04:21.017641: step: 52/530, loss: 0.054190926253795624
2023-01-23 02:04:22.167868: step: 56/530, loss: 0.07511263340711594
2023-01-23 02:04:23.267663: step: 60/530, loss: 0.024922847747802734
2023-01-23 02:04:24.368968: step: 64/530, loss: 0.004439163021743298
2023-01-23 02:04:25.474854: step: 68/530, loss: 0.011149120517075062
2023-01-23 02:04:26.591663: step: 72/530, loss: 0.0002089500630972907
2023-01-23 02:04:27.699126: step: 76/530, loss: 0.004873752593994141
2023-01-23 02:04:28.865329: step: 80/530, loss: 0.00047369004460051656
2023-01-23 02:04:29.974914: step: 84/530, loss: 0.027544498443603516
2023-01-23 02:04:31.109109: step: 88/530, loss: 0.11396074295043945
2023-01-23 02:04:32.232233: step: 92/530, loss: 0.03277111053466797
2023-01-23 02:04:33.354359: step: 96/530, loss: 0.0812450423836708
2023-01-23 02:04:34.482830: step: 100/530, loss: 0.009062194265425205
2023-01-23 02:04:35.617399: step: 104/530, loss: 0.02160368114709854
2023-01-23 02:04:36.746145: step: 108/530, loss: 0.021747970953583717
2023-01-23 02:04:37.857186: step: 112/530, loss: 0.05263872444629669
2023-01-23 02:04:39.001038: step: 116/530, loss: 0.021317483857274055
2023-01-23 02:04:40.121009: step: 120/530, loss: 0.028965378180146217
2023-01-23 02:04:41.276012: step: 124/530, loss: 0.05956468731164932
2023-01-23 02:04:42.381486: step: 128/530, loss: 0.018841171637177467
2023-01-23 02:04:43.500410: step: 132/530, loss: 0.0026429176796227694
2023-01-23 02:04:44.623811: step: 136/530, loss: 0.012954902835190296
2023-01-23 02:04:45.755477: step: 140/530, loss: 0.043633464723825455
2023-01-23 02:04:46.901435: step: 144/530, loss: 0.5690780878067017
2023-01-23 02:04:48.025617: step: 148/530, loss: 0.04194507747888565
2023-01-23 02:04:49.141173: step: 152/530, loss: 0.0075348857790231705
2023-01-23 02:04:50.242142: step: 156/530, loss: 0.006257819943130016
2023-01-23 02:04:51.362042: step: 160/530, loss: 0.0001625060976948589
2023-01-23 02:04:52.491540: step: 164/530, loss: 0.02559070475399494
2023-01-23 02:04:53.630321: step: 168/530, loss: 0.023813629522919655
2023-01-23 02:04:54.759874: step: 172/530, loss: 0.0028514862060546875
2023-01-23 02:04:55.888642: step: 176/530, loss: 0.025811387225985527
2023-01-23 02:04:56.997557: step: 180/530, loss: 0.0026000975631177425
2023-01-23 02:04:58.114714: step: 184/530, loss: 0.00015859604172874242
2023-01-23 02:04:59.220678: step: 188/530, loss: 0.047522738575935364
2023-01-23 02:05:00.325811: step: 192/530, loss: 0.0197772029787302
2023-01-23 02:05:01.432555: step: 196/530, loss: 0.007173729594796896
2023-01-23 02:05:02.574612: step: 200/530, loss: 0.008785438723862171
2023-01-23 02:05:03.738016: step: 204/530, loss: 0.05324520915746689
2023-01-23 02:05:04.867895: step: 208/530, loss: 0.08029670268297195
2023-01-23 02:05:05.989565: step: 212/530, loss: 0.014413261786103249
2023-01-23 02:05:07.118967: step: 216/530, loss: 0.0404631607234478
2023-01-23 02:05:08.236335: step: 220/530, loss: 0.022835921496152878
2023-01-23 02:05:09.343195: step: 224/530, loss: 0.01685018464922905
2023-01-23 02:05:10.515745: step: 228/530, loss: 0.019518554210662842
2023-01-23 02:05:11.635928: step: 232/530, loss: 0.0031232833862304688
2023-01-23 02:05:12.778114: step: 236/530, loss: 0.027121352031826973
2023-01-23 02:05:13.871818: step: 240/530, loss: 0.009561348706483841
2023-01-23 02:05:14.975025: step: 244/530, loss: 0.0013095855247229338
2023-01-23 02:05:16.107177: step: 248/530, loss: 0.11128824949264526
2023-01-23 02:05:17.250628: step: 252/530, loss: 0.00362319964915514
2023-01-23 02:05:18.390890: step: 256/530, loss: 0.0161406509578228
2023-01-23 02:05:19.487365: step: 260/530, loss: 0.02786397933959961
2023-01-23 02:05:20.615871: step: 264/530, loss: 0.01587553136050701
2023-01-23 02:05:21.716493: step: 268/530, loss: 0.0009485245100222528
2023-01-23 02:05:22.845041: step: 272/530, loss: 0.012115478515625
2023-01-23 02:05:23.969401: step: 276/530, loss: 0.006558800116181374
2023-01-23 02:05:25.096464: step: 280/530, loss: 0.008723640814423561
2023-01-23 02:05:26.243607: step: 284/530, loss: 0.016211414709687233
2023-01-23 02:05:27.342017: step: 288/530, loss: 0.003396606305614114
2023-01-23 02:05:28.474380: step: 292/530, loss: 0.03265266492962837
2023-01-23 02:05:29.582535: step: 296/530, loss: 0.0011013984913006425
2023-01-23 02:05:30.698820: step: 300/530, loss: 0.0047817230224609375
2023-01-23 02:05:31.835466: step: 304/530, loss: 0.0015641212230548263
2023-01-23 02:05:33.001571: step: 308/530, loss: 0.025176238268613815
2023-01-23 02:05:34.119584: step: 312/530, loss: 0.009770012460649014
2023-01-23 02:05:35.221910: step: 316/530, loss: 0.006199407856911421
2023-01-23 02:05:36.358771: step: 320/530, loss: 0.024837994948029518
2023-01-23 02:05:37.479411: step: 324/530, loss: 0.0173492431640625
2023-01-23 02:05:38.616677: step: 328/530, loss: 0.019259072840213776
2023-01-23 02:05:39.724690: step: 332/530, loss: 0.004490661434829235
2023-01-23 02:05:40.847869: step: 336/530, loss: 0.03045501746237278
2023-01-23 02:05:41.985475: step: 340/530, loss: 0.010313368402421474
2023-01-23 02:05:43.109178: step: 344/530, loss: 0.12140186131000519
2023-01-23 02:05:44.246971: step: 348/530, loss: 0.0033143043983727694
2023-01-23 02:05:45.378034: step: 352/530, loss: 0.011401081457734108
2023-01-23 02:05:46.500722: step: 356/530, loss: 0.009322643280029297
2023-01-23 02:05:47.646359: step: 360/530, loss: 0.020762061700224876
2023-01-23 02:05:48.784667: step: 364/530, loss: 0.0015563011402264237
2023-01-23 02:05:49.895564: step: 368/530, loss: 0.002956581301987171
2023-01-23 02:05:51.015080: step: 372/530, loss: 0.05156007036566734
2023-01-23 02:05:52.179257: step: 376/530, loss: 0.1172674149274826
2023-01-23 02:05:53.312293: step: 380/530, loss: 0.25614890456199646
2023-01-23 02:05:54.465078: step: 384/530, loss: 0.5383098721504211
2023-01-23 02:05:55.609041: step: 388/530, loss: 0.04896602779626846
2023-01-23 02:05:56.759523: step: 392/530, loss: 0.025785064324736595
2023-01-23 02:05:57.896291: step: 396/530, loss: 0.002616977784782648
2023-01-23 02:05:59.062289: step: 400/530, loss: 0.0023356438614428043
2023-01-23 02:06:00.207517: step: 404/530, loss: 0.036078643053770065
2023-01-23 02:06:01.358829: step: 408/530, loss: 0.016096973791718483
2023-01-23 02:06:02.486318: step: 412/530, loss: 0.11197032779455185
2023-01-23 02:06:03.612227: step: 416/530, loss: 0.001728916191495955
2023-01-23 02:06:04.703407: step: 420/530, loss: 0.7216484546661377
2023-01-23 02:06:05.834905: step: 424/530, loss: 0.11852455139160156
2023-01-23 02:06:06.986210: step: 428/530, loss: 0.0615270659327507
2023-01-23 02:06:08.105155: step: 432/530, loss: 0.01127920113503933
2023-01-23 02:06:09.246367: step: 436/530, loss: 0.04503965377807617
2023-01-23 02:06:10.391160: step: 440/530, loss: 0.02493734285235405
2023-01-23 02:06:11.520589: step: 444/530, loss: 0.022767448797822
2023-01-23 02:06:12.684221: step: 448/530, loss: 0.0014804840320721269
2023-01-23 02:06:13.805960: step: 452/530, loss: 0.002362004015594721
2023-01-23 02:06:14.932903: step: 456/530, loss: 0.011768865399062634
2023-01-23 02:06:16.038418: step: 460/530, loss: 0.0006501197931356728
2023-01-23 02:06:17.150359: step: 464/530, loss: 0.0033471081405878067
2023-01-23 02:06:18.258554: step: 468/530, loss: 0.019545840099453926
2023-01-23 02:06:19.371322: step: 472/530, loss: 0.017697429284453392
2023-01-23 02:06:20.498346: step: 476/530, loss: 0.003911018371582031
2023-01-23 02:06:21.611536: step: 480/530, loss: 0.0004428863467182964
2023-01-23 02:06:22.741829: step: 484/530, loss: 0.03216571733355522
2023-01-23 02:06:23.896221: step: 488/530, loss: 0.002635478973388672
2023-01-23 02:06:25.015978: step: 492/530, loss: 0.0017868519062176347
2023-01-23 02:06:26.167823: step: 496/530, loss: 0.011644745245575905
2023-01-23 02:06:27.287186: step: 500/530, loss: 0.02579822577536106
2023-01-23 02:06:28.436525: step: 504/530, loss: 0.04940824583172798
2023-01-23 02:06:29.569262: step: 508/530, loss: 0.012224579229950905
2023-01-23 02:06:30.671902: step: 512/530, loss: 0.01204976998269558
2023-01-23 02:06:31.803994: step: 516/530, loss: 0.0043631079606711864
2023-01-23 02:06:32.940441: step: 520/530, loss: 0.028780747205018997
2023-01-23 02:06:34.065676: step: 524/530, loss: 0.03128452226519585
2023-01-23 02:06:35.204429: step: 528/530, loss: 0.04554860666394234
2023-01-23 02:06:36.326210: step: 532/530, loss: 0.014803219586610794
2023-01-23 02:06:37.453783: step: 536/530, loss: 0.02670145034790039
2023-01-23 02:06:38.567308: step: 540/530, loss: 0.020496414974331856
2023-01-23 02:06:39.680399: step: 544/530, loss: 0.0012233257293701172
2023-01-23 02:06:40.827619: step: 548/530, loss: 0.008387756533920765
2023-01-23 02:06:41.936986: step: 552/530, loss: 0.0001066207914846018
2023-01-23 02:06:43.064465: step: 556/530, loss: 0.02556305006146431
2023-01-23 02:06:44.173531: step: 560/530, loss: 0.038468170911073685
2023-01-23 02:06:45.295928: step: 564/530, loss: 0.11213312298059464
2023-01-23 02:06:46.425451: step: 568/530, loss: 0.04802103340625763
2023-01-23 02:06:47.524295: step: 572/530, loss: 0.0009373187785968184
2023-01-23 02:06:48.631757: step: 576/530, loss: 0.004887962713837624
2023-01-23 02:06:49.768375: step: 580/530, loss: 0.030956365168094635
2023-01-23 02:06:50.919552: step: 584/530, loss: 0.0010581969982013106
2023-01-23 02:06:52.041239: step: 588/530, loss: 0.028652288019657135
2023-01-23 02:06:53.157866: step: 592/530, loss: 0.023152925074100494
2023-01-23 02:06:54.321776: step: 596/530, loss: 0.006566429045051336
2023-01-23 02:06:55.437139: step: 600/530, loss: 0.01933755911886692
2023-01-23 02:06:56.576233: step: 604/530, loss: 0.02361154742538929
2023-01-23 02:06:57.717913: step: 608/530, loss: 0.04239635542035103
2023-01-23 02:06:58.857134: step: 612/530, loss: 0.08468551933765411
2023-01-23 02:06:59.988195: step: 616/530, loss: 0.009547806344926357
2023-01-23 02:07:01.127119: step: 620/530, loss: 0.00022602081298828125
2023-01-23 02:07:02.257354: step: 624/530, loss: 0.05247362703084946
2023-01-23 02:07:03.377988: step: 628/530, loss: 0.04792613908648491
2023-01-23 02:07:04.506116: step: 632/530, loss: 0.00105371477548033
2023-01-23 02:07:05.645539: step: 636/530, loss: 0.0013751983642578125
2023-01-23 02:07:06.768832: step: 640/530, loss: 0.002451324602589011
2023-01-23 02:07:07.896300: step: 644/530, loss: 0.006276130676269531
2023-01-23 02:07:09.014866: step: 648/530, loss: 0.08488478511571884
2023-01-23 02:07:10.158510: step: 652/530, loss: 0.10239487141370773
2023-01-23 02:07:11.300340: step: 656/530, loss: 0.19045695662498474
2023-01-23 02:07:12.434420: step: 660/530, loss: 0.015345001593232155
2023-01-23 02:07:13.561889: step: 664/530, loss: 0.02175135724246502
2023-01-23 02:07:14.656232: step: 668/530, loss: 0.0006373882642947137
2023-01-23 02:07:15.781921: step: 672/530, loss: 0.08657453209161758
2023-01-23 02:07:16.894927: step: 676/530, loss: 0.004469871986657381
2023-01-23 02:07:18.031658: step: 680/530, loss: 0.003891468048095703
2023-01-23 02:07:19.153692: step: 684/530, loss: 0.004010486416518688
2023-01-23 02:07:20.292950: step: 688/530, loss: 0.04857354238629341
2023-01-23 02:07:21.399259: step: 692/530, loss: 0.07218170166015625
2023-01-23 02:07:22.537914: step: 696/530, loss: 0.022953415289521217
2023-01-23 02:07:23.698616: step: 700/530, loss: 0.014371681027114391
2023-01-23 02:07:24.854035: step: 704/530, loss: 0.020641900599002838
2023-01-23 02:07:25.982868: step: 708/530, loss: 0.04459667205810547
2023-01-23 02:07:27.065800: step: 712/530, loss: 0.00032927992288023233
2023-01-23 02:07:28.196626: step: 716/530, loss: 0.0008575440151616931
2023-01-23 02:07:29.318813: step: 720/530, loss: 0.0030700683128088713
2023-01-23 02:07:30.454161: step: 724/530, loss: 0.4481928050518036
2023-01-23 02:07:31.608345: step: 728/530, loss: 0.039377786219120026
2023-01-23 02:07:32.740473: step: 732/530, loss: 0.01096496544778347
2023-01-23 02:07:33.880714: step: 736/530, loss: 0.00903244037181139
2023-01-23 02:07:35.013409: step: 740/530, loss: 0.25938883423805237
2023-01-23 02:07:36.109499: step: 744/530, loss: 0.00915222242474556
2023-01-23 02:07:37.224718: step: 748/530, loss: 0.015636634081602097
2023-01-23 02:07:38.393023: step: 752/530, loss: 0.0004044532834086567
2023-01-23 02:07:39.514082: step: 756/530, loss: 0.011844445019960403
2023-01-23 02:07:40.649622: step: 760/530, loss: 0.01631746254861355
2023-01-23 02:07:41.822778: step: 764/530, loss: 0.04962310940027237
2023-01-23 02:07:42.949457: step: 768/530, loss: 0.011441421695053577
2023-01-23 02:07:44.103427: step: 772/530, loss: 0.01764697954058647
2023-01-23 02:07:45.226129: step: 776/530, loss: 0.08282966911792755
2023-01-23 02:07:46.347358: step: 780/530, loss: 0.5871692299842834
2023-01-23 02:07:47.470354: step: 784/530, loss: 0.04664936289191246
2023-01-23 02:07:48.598762: step: 788/530, loss: 0.009368419647216797
2023-01-23 02:07:49.725112: step: 792/530, loss: 0.031528569757938385
2023-01-23 02:07:50.866895: step: 796/530, loss: 0.027863502502441406
2023-01-23 02:07:51.994896: step: 800/530, loss: 0.019846439361572266
2023-01-23 02:07:53.107054: step: 804/530, loss: 0.08358190953731537
2023-01-23 02:07:54.209048: step: 808/530, loss: 0.039481259882450104
2023-01-23 02:07:55.344291: step: 812/530, loss: 0.11425495147705078
2023-01-23 02:07:56.452497: step: 816/530, loss: 0.06822285801172256
2023-01-23 02:07:57.562187: step: 820/530, loss: 0.0009700298542156816
2023-01-23 02:07:58.691549: step: 824/530, loss: 0.016520213335752487
2023-01-23 02:07:59.800499: step: 828/530, loss: 0.00345611572265625
2023-01-23 02:08:00.923621: step: 832/530, loss: 0.03575306385755539
2023-01-23 02:08:02.088237: step: 836/530, loss: 0.06122875213623047
2023-01-23 02:08:03.228148: step: 840/530, loss: 0.004982376471161842
2023-01-23 02:08:04.352591: step: 844/530, loss: 0.01490790769457817
2023-01-23 02:08:05.478340: step: 848/530, loss: 0.027049541473388672
2023-01-23 02:08:06.578745: step: 852/530, loss: 0.03465709835290909
2023-01-23 02:08:07.711859: step: 856/530, loss: 0.00519218435510993
2023-01-23 02:08:08.821654: step: 860/530, loss: 0.0035415650345385075
2023-01-23 02:08:09.948093: step: 864/530, loss: 0.03077240101993084
2023-01-23 02:08:11.070374: step: 868/530, loss: 0.021011972799897194
2023-01-23 02:08:12.168521: step: 872/530, loss: 0.0033246041275560856
2023-01-23 02:08:13.294744: step: 876/530, loss: 0.03613033518195152
2023-01-23 02:08:14.411297: step: 880/530, loss: 0.04351158067584038
2023-01-23 02:08:15.544517: step: 884/530, loss: 0.0026803971268236637
2023-01-23 02:08:16.658188: step: 888/530, loss: 0.02001781575381756
2023-01-23 02:08:17.806451: step: 892/530, loss: 0.003724479814991355
2023-01-23 02:08:18.918159: step: 896/530, loss: 0.024578142911195755
2023-01-23 02:08:20.073869: step: 900/530, loss: 0.06598224490880966
2023-01-23 02:08:21.183642: step: 904/530, loss: 0.053090669214725494
2023-01-23 02:08:22.332336: step: 908/530, loss: 0.01750488393008709
2023-01-23 02:08:23.443465: step: 912/530, loss: 0.039853956550359726
2023-01-23 02:08:24.568801: step: 916/530, loss: 0.007404947187751532
2023-01-23 02:08:25.725411: step: 920/530, loss: 0.0014955521328374743
2023-01-23 02:08:26.846332: step: 924/530, loss: 0.04957304149866104
2023-01-23 02:08:27.970352: step: 928/530, loss: 0.002016258193179965
2023-01-23 02:08:29.084976: step: 932/530, loss: 0.04202842712402344
2023-01-23 02:08:30.219024: step: 936/530, loss: 0.004660606384277344
2023-01-23 02:08:31.368497: step: 940/530, loss: 0.029612064361572266
2023-01-23 02:08:32.488865: step: 944/530, loss: 0.011448907665908337
2023-01-23 02:08:33.625897: step: 948/530, loss: 0.019666194915771484
2023-01-23 02:08:34.792261: step: 952/530, loss: 0.028432132676243782
2023-01-23 02:08:35.918983: step: 956/530, loss: 0.0387774258852005
2023-01-23 02:08:37.027159: step: 960/530, loss: 0.00818166695535183
2023-01-23 02:08:38.155806: step: 964/530, loss: 0.00033168791560456157
2023-01-23 02:08:39.285073: step: 968/530, loss: 0.0005858421209268272
2023-01-23 02:08:40.423078: step: 972/530, loss: 0.0048181889578700066
2023-01-23 02:08:41.556288: step: 976/530, loss: 0.006972027011215687
2023-01-23 02:08:42.647895: step: 980/530, loss: 0.014428138732910156
2023-01-23 02:08:43.762499: step: 984/530, loss: 0.0013927459949627519
2023-01-23 02:08:44.862753: step: 988/530, loss: 0.04205961525440216
2023-01-23 02:08:45.992988: step: 992/530, loss: 0.0018564225174486637
2023-01-23 02:08:47.114619: step: 996/530, loss: 0.11214561015367508
2023-01-23 02:08:48.236427: step: 1000/530, loss: 0.044797517359256744
2023-01-23 02:08:49.411578: step: 1004/530, loss: 0.006389426998794079
2023-01-23 02:08:50.514543: step: 1008/530, loss: 0.07247067242860794
2023-01-23 02:08:51.622502: step: 1012/530, loss: 0.011844920925796032
2023-01-23 02:08:52.737332: step: 1016/530, loss: 0.07476310431957245
2023-01-23 02:08:53.869624: step: 1020/530, loss: 0.07355518639087677
2023-01-23 02:08:54.988902: step: 1024/530, loss: 0.00018343926058150828
2023-01-23 02:08:56.108965: step: 1028/530, loss: 0.0309524554759264
2023-01-23 02:08:57.249081: step: 1032/530, loss: 0.0075664520263671875
2023-01-23 02:08:58.379457: step: 1036/530, loss: 0.012372780591249466
2023-01-23 02:08:59.521807: step: 1040/530, loss: 0.04217557981610298
2023-01-23 02:09:00.656665: step: 1044/530, loss: 0.00113334646448493
2023-01-23 02:09:01.792365: step: 1048/530, loss: 0.01747121848165989
2023-01-23 02:09:02.965021: step: 1052/530, loss: 0.033419419080019
2023-01-23 02:09:04.081465: step: 1056/530, loss: 0.012417793273925781
2023-01-23 02:09:05.224261: step: 1060/530, loss: 0.02894134633243084
2023-01-23 02:09:06.335624: step: 1064/530, loss: 0.02543802373111248
2023-01-23 02:09:07.440738: step: 1068/530, loss: 0.03713976591825485
2023-01-23 02:09:08.581831: step: 1072/530, loss: 0.03670807182788849
2023-01-23 02:09:09.688486: step: 1076/530, loss: 0.004036712925881147
2023-01-23 02:09:10.803843: step: 1080/530, loss: 0.011581946164369583
2023-01-23 02:09:11.953631: step: 1084/530, loss: 0.005394076928496361
2023-01-23 02:09:13.060455: step: 1088/530, loss: 0.018703460693359375
2023-01-23 02:09:14.187116: step: 1092/530, loss: 0.04775209724903107
2023-01-23 02:09:15.300527: step: 1096/530, loss: 0.014824104495346546
2023-01-23 02:09:16.449948: step: 1100/530, loss: 0.7751873135566711
2023-01-23 02:09:17.584684: step: 1104/530, loss: 0.055441856384277344
2023-01-23 02:09:18.705358: step: 1108/530, loss: 0.0009801865089684725
2023-01-23 02:09:19.805347: step: 1112/530, loss: 9.479522850597277e-05
2023-01-23 02:09:20.920536: step: 1116/530, loss: 0.00298900599591434
2023-01-23 02:09:22.043505: step: 1120/530, loss: 0.0027958869468420744
2023-01-23 02:09:23.191065: step: 1124/530, loss: 0.04132647439837456
2023-01-23 02:09:24.317226: step: 1128/530, loss: 0.0006742477416992188
2023-01-23 02:09:25.436462: step: 1132/530, loss: 0.015451241284608841
2023-01-23 02:09:26.562529: step: 1136/530, loss: 0.00542373675853014
2023-01-23 02:09:27.689715: step: 1140/530, loss: 0.026175014674663544
2023-01-23 02:09:28.812478: step: 1144/530, loss: 0.004846715833991766
2023-01-23 02:09:29.949591: step: 1148/530, loss: 0.1631934642791748
2023-01-23 02:09:31.074958: step: 1152/530, loss: 0.009257292374968529
2023-01-23 02:09:32.205201: step: 1156/530, loss: 0.019746972247958183
2023-01-23 02:09:33.340544: step: 1160/530, loss: 0.09086446464061737
2023-01-23 02:09:34.469951: step: 1164/530, loss: 0.015233039855957031
2023-01-23 02:09:35.580608: step: 1168/530, loss: 0.004391479305922985
2023-01-23 02:09:36.700563: step: 1172/530, loss: 0.16498994827270508
2023-01-23 02:09:37.896621: step: 1176/530, loss: 0.000125885009765625
2023-01-23 02:09:39.035431: step: 1180/530, loss: 0.025980282574892044
2023-01-23 02:09:40.166217: step: 1184/530, loss: 0.008759498596191406
2023-01-23 02:09:41.314376: step: 1188/530, loss: 0.0016201974358409643
2023-01-23 02:09:42.453845: step: 1192/530, loss: 0.018706941977143288
2023-01-23 02:09:43.581757: step: 1196/530, loss: 0.012826346792280674
2023-01-23 02:09:44.714122: step: 1200/530, loss: 0.0036918639671057463
2023-01-23 02:09:45.866355: step: 1204/530, loss: 0.0005822181701660156
2023-01-23 02:09:46.988470: step: 1208/530, loss: 0.01943178102374077
2023-01-23 02:09:48.102686: step: 1212/530, loss: 0.003605079837143421
2023-01-23 02:09:49.256313: step: 1216/530, loss: 0.142752543091774
2023-01-23 02:09:50.399859: step: 1220/530, loss: 0.12354221194982529
2023-01-23 02:09:51.523270: step: 1224/530, loss: 0.03123927116394043
2023-01-23 02:09:52.641670: step: 1228/530, loss: 0.07926268875598907
2023-01-23 02:09:53.751156: step: 1232/530, loss: 0.004521084018051624
2023-01-23 02:09:54.886975: step: 1236/530, loss: 0.005951500032097101
2023-01-23 02:09:55.998686: step: 1240/530, loss: 0.0013096809852868319
2023-01-23 02:09:57.120927: step: 1244/530, loss: 0.08325204998254776
2023-01-23 02:09:58.240223: step: 1248/530, loss: 0.008430671878159046
2023-01-23 02:09:59.393176: step: 1252/530, loss: 0.0002208709775004536
2023-01-23 02:10:00.488275: step: 1256/530, loss: 0.003626400139182806
2023-01-23 02:10:01.665258: step: 1260/530, loss: 0.03239841386675835
2023-01-23 02:10:02.814612: step: 1264/530, loss: 0.2533597946166992
2023-01-23 02:10:03.914083: step: 1268/530, loss: 0.0015319825615733862
2023-01-23 02:10:05.020953: step: 1272/530, loss: 0.023151494562625885
2023-01-23 02:10:06.153979: step: 1276/530, loss: 0.020995520055294037
2023-01-23 02:10:07.269421: step: 1280/530, loss: 0.06405086815357208
2023-01-23 02:10:08.419346: step: 1284/530, loss: 0.011304665356874466
2023-01-23 02:10:09.553790: step: 1288/530, loss: 0.010596848092973232
2023-01-23 02:10:10.707500: step: 1292/530, loss: 0.02088928036391735
2023-01-23 02:10:11.834267: step: 1296/530, loss: 0.0031269073951989412
2023-01-23 02:10:12.939366: step: 1300/530, loss: 0.05312724411487579
2023-01-23 02:10:14.062694: step: 1304/530, loss: 0.009411764331161976
2023-01-23 02:10:15.201336: step: 1308/530, loss: 0.08324223011732101
2023-01-23 02:10:16.322046: step: 1312/530, loss: 0.009753083810210228
2023-01-23 02:10:17.451236: step: 1316/530, loss: 0.01343164499849081
2023-01-23 02:10:18.586825: step: 1320/530, loss: 0.040036965161561966
2023-01-23 02:10:19.708806: step: 1324/530, loss: 0.038382720202207565
2023-01-23 02:10:20.828478: step: 1328/530, loss: 0.019205475226044655
2023-01-23 02:10:21.982742: step: 1332/530, loss: 0.06474494934082031
2023-01-23 02:10:23.115808: step: 1336/530, loss: 0.0567447654902935
2023-01-23 02:10:24.250981: step: 1340/530, loss: 0.022373007610440254
2023-01-23 02:10:25.362925: step: 1344/530, loss: 0.09464531391859055
2023-01-23 02:10:26.479467: step: 1348/530, loss: 0.24595364928245544
2023-01-23 02:10:27.598111: step: 1352/530, loss: 0.06726942956447601
2023-01-23 02:10:28.714618: step: 1356/530, loss: 0.000587892543990165
2023-01-23 02:10:29.834858: step: 1360/530, loss: 0.03328799456357956
2023-01-23 02:10:30.969028: step: 1364/530, loss: 0.006768417079001665
2023-01-23 02:10:32.101801: step: 1368/530, loss: 0.0036138533614575863
2023-01-23 02:10:33.214366: step: 1372/530, loss: 0.019726086407899857
2023-01-23 02:10:34.329866: step: 1376/530, loss: 0.020239925011992455
2023-01-23 02:10:35.470702: step: 1380/530, loss: 0.061925604939460754
2023-01-23 02:10:36.616852: step: 1384/530, loss: 0.007011318579316139
2023-01-23 02:10:37.751375: step: 1388/530, loss: 0.012970829382538795
2023-01-23 02:10:38.892371: step: 1392/530, loss: 0.05281582102179527
2023-01-23 02:10:40.041819: step: 1396/530, loss: 0.00199127197265625
2023-01-23 02:10:41.151294: step: 1400/530, loss: 0.083338163793087
2023-01-23 02:10:42.271417: step: 1404/530, loss: 0.001103305839933455
2023-01-23 02:10:43.397006: step: 1408/530, loss: 0.03239836543798447
2023-01-23 02:10:44.551648: step: 1412/530, loss: 0.013076973147690296
2023-01-23 02:10:45.688767: step: 1416/530, loss: 0.053762149065732956
2023-01-23 02:10:46.821705: step: 1420/530, loss: 0.01584300957620144
2023-01-23 02:10:47.969277: step: 1424/530, loss: 0.057558417320251465
2023-01-23 02:10:49.082629: step: 1428/530, loss: 0.07993412017822266
2023-01-23 02:10:50.212221: step: 1432/530, loss: 0.06793813407421112
2023-01-23 02:10:51.338820: step: 1436/530, loss: 0.013351822271943092
2023-01-23 02:10:52.455084: step: 1440/530, loss: 0.012730789370834827
2023-01-23 02:10:53.578841: step: 1444/530, loss: 0.018189240247011185
2023-01-23 02:10:54.675692: step: 1448/530, loss: 0.013106727972626686
2023-01-23 02:10:55.800211: step: 1452/530, loss: 0.03323383256793022
2023-01-23 02:10:56.926590: step: 1456/530, loss: 0.044008851051330566
2023-01-23 02:10:58.055542: step: 1460/530, loss: 0.027964306995272636
2023-01-23 02:10:59.201006: step: 1464/530, loss: 0.20341968536376953
2023-01-23 02:11:00.330420: step: 1468/530, loss: 0.014215660281479359
2023-01-23 02:11:01.461420: step: 1472/530, loss: 0.06564760208129883
2023-01-23 02:11:02.614107: step: 1476/530, loss: 0.03257398679852486
2023-01-23 02:11:03.725035: step: 1480/530, loss: 0.034955885261297226
2023-01-23 02:11:04.857531: step: 1484/530, loss: 0.014664220623672009
2023-01-23 02:11:05.962641: step: 1488/530, loss: 0.0292223934084177
2023-01-23 02:11:07.096598: step: 1492/530, loss: 0.019066713750362396
2023-01-23 02:11:08.197406: step: 1496/530, loss: 0.0007094383472576737
2023-01-23 02:11:09.333397: step: 1500/530, loss: 1.05991966847796e-05
2023-01-23 02:11:10.479823: step: 1504/530, loss: 0.04739703983068466
2023-01-23 02:11:11.575909: step: 1508/530, loss: 0.025888871401548386
2023-01-23 02:11:12.700878: step: 1512/530, loss: 0.012617398053407669
2023-01-23 02:11:13.824268: step: 1516/530, loss: 0.28444352746009827
2023-01-23 02:11:14.944503: step: 1520/530, loss: 0.009024095721542835
2023-01-23 02:11:16.073131: step: 1524/530, loss: 0.04159350320696831
2023-01-23 02:11:17.179770: step: 1528/530, loss: 0.04926910623908043
2023-01-23 02:11:18.300749: step: 1532/530, loss: 0.04357462003827095
2023-01-23 02:11:19.417135: step: 1536/530, loss: 0.01802654191851616
2023-01-23 02:11:20.549623: step: 1540/530, loss: 0.09883490204811096
2023-01-23 02:11:21.703451: step: 1544/530, loss: 0.021542739123106003
2023-01-23 02:11:22.815547: step: 1548/530, loss: 0.05192837491631508
2023-01-23 02:11:23.942671: step: 1552/530, loss: 0.04709911346435547
2023-01-23 02:11:25.074661: step: 1556/530, loss: 0.003937769215553999
2023-01-23 02:11:26.171678: step: 1560/530, loss: 0.012407207861542702
2023-01-23 02:11:27.293157: step: 1564/530, loss: 0.08206062018871307
2023-01-23 02:11:28.448263: step: 1568/530, loss: 0.07946185767650604
2023-01-23 02:11:29.561203: step: 1572/530, loss: 0.033326055854558945
2023-01-23 02:11:30.669558: step: 1576/530, loss: 0.004254436586052179
2023-01-23 02:11:31.771532: step: 1580/530, loss: 0.023253725841641426
2023-01-23 02:11:32.907815: step: 1584/530, loss: 0.0005327224498614669
2023-01-23 02:11:34.026311: step: 1588/530, loss: 0.033684540539979935
2023-01-23 02:11:35.138429: step: 1592/530, loss: 0.004670047666877508
2023-01-23 02:11:36.249809: step: 1596/530, loss: 0.010883951559662819
2023-01-23 02:11:37.396464: step: 1600/530, loss: 0.001874303910881281
2023-01-23 02:11:38.539318: step: 1604/530, loss: 0.5510677099227905
2023-01-23 02:11:39.667079: step: 1608/530, loss: 0.08102130889892578
2023-01-23 02:11:40.778634: step: 1612/530, loss: 0.020445728674530983
2023-01-23 02:11:41.913370: step: 1616/530, loss: 0.00021982192993164062
2023-01-23 02:11:43.063804: step: 1620/530, loss: 0.042637065052986145
2023-01-23 02:11:44.190632: step: 1624/530, loss: 0.03626289218664169
2023-01-23 02:11:45.295264: step: 1628/530, loss: 6.201267387950793e-05
2023-01-23 02:11:46.390399: step: 1632/530, loss: 0.1518077850341797
2023-01-23 02:11:47.526931: step: 1636/530, loss: 0.000354766845703125
2023-01-23 02:11:48.645057: step: 1640/530, loss: 0.011517238803207874
2023-01-23 02:11:49.789609: step: 1644/530, loss: 0.08944845199584961
2023-01-23 02:11:50.912651: step: 1648/530, loss: 0.04848074913024902
2023-01-23 02:11:52.016469: step: 1652/530, loss: 0.023461056873202324
2023-01-23 02:11:53.141924: step: 1656/530, loss: 0.01971564255654812
2023-01-23 02:11:54.260142: step: 1660/530, loss: 0.003798866178840399
2023-01-23 02:11:55.378586: step: 1664/530, loss: 0.0005322456709109247
2023-01-23 02:11:56.496009: step: 1668/530, loss: 0.00226764683611691
2023-01-23 02:11:57.583816: step: 1672/530, loss: 0.07877865433692932
2023-01-23 02:11:58.706408: step: 1676/530, loss: 0.017559051513671875
2023-01-23 02:11:59.832558: step: 1680/530, loss: 0.0555761344730854
2023-01-23 02:12:00.943509: step: 1684/530, loss: 0.03500433266162872
2023-01-23 02:12:02.103102: step: 1688/530, loss: 0.03232298046350479
2023-01-23 02:12:03.215094: step: 1692/530, loss: 0.0359375961124897
2023-01-23 02:12:04.328191: step: 1696/530, loss: 0.037431810051202774
2023-01-23 02:12:05.473391: step: 1700/530, loss: 0.030335808172822
2023-01-23 02:12:06.621285: step: 1704/530, loss: 0.07949409633874893
2023-01-23 02:12:07.737453: step: 1708/530, loss: 0.006646347232162952
2023-01-23 02:12:08.866749: step: 1712/530, loss: 0.0024454116355627775
2023-01-23 02:12:10.001598: step: 1716/530, loss: 0.04267530515789986
2023-01-23 02:12:11.112144: step: 1720/530, loss: 0.005366945173591375
2023-01-23 02:12:12.246985: step: 1724/530, loss: 0.0634043738245964
2023-01-23 02:12:13.407728: step: 1728/530, loss: 0.05149383470416069
2023-01-23 02:12:14.570337: step: 1732/530, loss: 0.03491363674402237
2023-01-23 02:12:15.696791: step: 1736/530, loss: 0.036701466888189316
2023-01-23 02:12:16.812210: step: 1740/530, loss: 0.015925992280244827
2023-01-23 02:12:17.947734: step: 1744/530, loss: 0.0012866973411291838
2023-01-23 02:12:19.086614: step: 1748/530, loss: 0.026250457391142845
2023-01-23 02:12:20.247928: step: 1752/530, loss: 0.08851146697998047
2023-01-23 02:12:21.369993: step: 1756/530, loss: 0.01152658462524414
2023-01-23 02:12:22.507715: step: 1760/530, loss: 0.005018806550651789
2023-01-23 02:12:23.668502: step: 1764/530, loss: 0.6873079538345337
2023-01-23 02:12:24.801251: step: 1768/530, loss: 0.12106628715991974
2023-01-23 02:12:25.967196: step: 1772/530, loss: 0.0023463249672204256
2023-01-23 02:12:27.069477: step: 1776/530, loss: 0.4988580644130707
2023-01-23 02:12:28.165913: step: 1780/530, loss: 0.057986073195934296
2023-01-23 02:12:29.284317: step: 1784/530, loss: 0.0013458728790283203
2023-01-23 02:12:30.398128: step: 1788/530, loss: 0.046936798840761185
2023-01-23 02:12:31.535292: step: 1792/530, loss: 0.01726841926574707
2023-01-23 02:12:32.680279: step: 1796/530, loss: 0.010210990905761719
2023-01-23 02:12:33.787698: step: 1800/530, loss: 0.0487792007625103
2023-01-23 02:12:34.916924: step: 1804/530, loss: 0.009932136163115501
2023-01-23 02:12:36.067128: step: 1808/530, loss: 0.024523163214325905
2023-01-23 02:12:37.183724: step: 1812/530, loss: 0.04125223308801651
2023-01-23 02:12:38.311016: step: 1816/530, loss: 0.04036378860473633
2023-01-23 02:12:39.458195: step: 1820/530, loss: 0.3591706156730652
2023-01-23 02:12:40.577465: step: 1824/530, loss: 0.04822826385498047
2023-01-23 02:12:41.698000: step: 1828/530, loss: 0.05476117134094238
2023-01-23 02:12:42.840314: step: 1832/530, loss: 0.034261513501405716
2023-01-23 02:12:43.968360: step: 1836/530, loss: 0.013497447595000267
2023-01-23 02:12:45.105377: step: 1840/530, loss: 0.034429170191287994
2023-01-23 02:12:46.243063: step: 1844/530, loss: 0.002293872879818082
2023-01-23 02:12:47.355765: step: 1848/530, loss: 0.0019749640487134457
2023-01-23 02:12:48.484162: step: 1852/530, loss: 0.04181012883782387
2023-01-23 02:12:49.589554: step: 1856/530, loss: 0.00024565457715652883
2023-01-23 02:12:50.744290: step: 1860/530, loss: 0.020519353449344635
2023-01-23 02:12:51.856676: step: 1864/530, loss: 0.028027629479765892
2023-01-23 02:12:53.000391: step: 1868/530, loss: 0.24358253180980682
2023-01-23 02:12:54.107523: step: 1872/530, loss: 0.074903704226017
2023-01-23 02:12:55.221352: step: 1876/530, loss: 0.0020058155059814453
2023-01-23 02:12:56.315554: step: 1880/530, loss: 0.042814258486032486
2023-01-23 02:12:57.470437: step: 1884/530, loss: 0.007417869754135609
2023-01-23 02:12:58.620850: step: 1888/530, loss: 0.015611648559570312
2023-01-23 02:12:59.716882: step: 1892/530, loss: 0.034890320152044296
2023-01-23 02:13:00.838912: step: 1896/530, loss: 0.00016932487778831273
2023-01-23 02:13:01.961223: step: 1900/530, loss: 0.03131704404950142
2023-01-23 02:13:03.118406: step: 1904/530, loss: 0.003062772797420621
2023-01-23 02:13:04.217901: step: 1908/530, loss: 0.0022687495220452547
2023-01-23 02:13:05.339852: step: 1912/530, loss: 0.026704657822847366
2023-01-23 02:13:06.458327: step: 1916/530, loss: 0.011846351437270641
2023-01-23 02:13:07.588994: step: 1920/530, loss: 0.016640376299619675
2023-01-23 02:13:08.696299: step: 1924/530, loss: 0.0004940032958984375
2023-01-23 02:13:09.804536: step: 1928/530, loss: 0.03679848089814186
2023-01-23 02:13:10.930663: step: 1932/530, loss: 0.010357856750488281
2023-01-23 02:13:12.054718: step: 1936/530, loss: 0.030941247940063477
2023-01-23 02:13:13.213840: step: 1940/530, loss: 0.0673748031258583
2023-01-23 02:13:14.347604: step: 1944/530, loss: 0.004721737001091242
2023-01-23 02:13:15.469879: step: 1948/530, loss: 0.00037875177804380655
2023-01-23 02:13:16.594730: step: 1952/530, loss: 0.05491599813103676
2023-01-23 02:13:17.786262: step: 1956/530, loss: 0.31745922565460205
2023-01-23 02:13:18.903803: step: 1960/530, loss: 0.06049938127398491
2023-01-23 02:13:20.063771: step: 1964/530, loss: 0.009197951294481754
2023-01-23 02:13:21.195492: step: 1968/530, loss: 0.007301711943000555
2023-01-23 02:13:22.326863: step: 1972/530, loss: 0.0244950782507658
2023-01-23 02:13:23.474623: step: 1976/530, loss: 0.05256430059671402
2023-01-23 02:13:24.585174: step: 1980/530, loss: 0.007440376561135054
2023-01-23 02:13:25.727337: step: 1984/530, loss: 0.05788583680987358
2023-01-23 02:13:26.836218: step: 1988/530, loss: 0.04040832445025444
2023-01-23 02:13:27.955067: step: 1992/530, loss: 0.013705158606171608
2023-01-23 02:13:29.050593: step: 1996/530, loss: 0.0027181627228856087
2023-01-23 02:13:30.182137: step: 2000/530, loss: 0.05286836624145508
2023-01-23 02:13:31.307452: step: 2004/530, loss: 0.08677192032337189
2023-01-23 02:13:32.433602: step: 2008/530, loss: 0.019402693957090378
2023-01-23 02:13:33.591443: step: 2012/530, loss: 0.009622668847441673
2023-01-23 02:13:34.699611: step: 2016/530, loss: 0.01846771314740181
2023-01-23 02:13:35.843328: step: 2020/530, loss: 0.018915940076112747
2023-01-23 02:13:36.926107: step: 2024/530, loss: 0.004593086428940296
2023-01-23 02:13:38.058144: step: 2028/530, loss: 0.034824881702661514
2023-01-23 02:13:39.182979: step: 2032/530, loss: 0.07127256691455841
2023-01-23 02:13:40.308927: step: 2036/530, loss: 0.00504226703196764
2023-01-23 02:13:41.423429: step: 2040/530, loss: 0.017795467749238014
2023-01-23 02:13:42.582799: step: 2044/530, loss: 0.05929870903491974
2023-01-23 02:13:43.705366: step: 2048/530, loss: 0.029300592839717865
2023-01-23 02:13:44.833027: step: 2052/530, loss: 0.048245858401060104
2023-01-23 02:13:45.947587: step: 2056/530, loss: 0.024977970868349075
2023-01-23 02:13:47.046321: step: 2060/530, loss: 0.014585781842470169
2023-01-23 02:13:48.191295: step: 2064/530, loss: 0.003798580262809992
2023-01-23 02:13:49.285162: step: 2068/530, loss: 0.08062377572059631
2023-01-23 02:13:50.410996: step: 2072/530, loss: 0.11755017936229706
2023-01-23 02:13:51.566142: step: 2076/530, loss: 0.03792534023523331
2023-01-23 02:13:52.731635: step: 2080/530, loss: 0.008829927071928978
2023-01-23 02:13:53.865719: step: 2084/530, loss: 0.04152316972613335
2023-01-23 02:13:55.036590: step: 2088/530, loss: 0.004197502043098211
2023-01-23 02:13:56.177313: step: 2092/530, loss: 0.01802806928753853
2023-01-23 02:13:57.308080: step: 2096/530, loss: 0.02399163320660591
2023-01-23 02:13:58.415687: step: 2100/530, loss: 0.00042316914186812937
2023-01-23 02:13:59.532107: step: 2104/530, loss: 0.0051198964938521385
2023-01-23 02:14:00.650658: step: 2108/530, loss: 0.008419417776167393
2023-01-23 02:14:01.773832: step: 2112/530, loss: 0.008710384368896484
2023-01-23 02:14:02.883073: step: 2116/530, loss: 0.002822971437126398
2023-01-23 02:14:03.993311: step: 2120/530, loss: 0.0706886276602745
==================================================
Loss: 0.042
--------------------
Dev: {'event': {'p': 0.5909090909090909, 'r': 0.7789613848202397, 'f1': 0.6720275703618609}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Test: {'event': {'p': 0.6181980374665478, 'r': 0.792, 'f1': 0.6943887775551102}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Chinese: {'event': {'p': 0.5617977528089888, 'r': 0.9259259259259259, 'f1': 0.6993006993006993}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Korean: {'event': {'p': 0.5901639344262295, 'r': 0.5714285714285714, 'f1': 0.5806451612903226}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Russian: {'event': {'p': 0.4090909090909091, 'r': 0.5, 'f1': 0.45}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Chinese: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Chinese: {'event': {'p': 0.6190476190476191, 'r': 0.9629629629629629, 'f1': 0.7536231884057971}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6288770053475936, 'r': 0.7829560585885486, 'f1': 0.697508896797153}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Korean: {'event': {'p': 0.64058795637743, 'r': 0.772, 'f1': 0.7001813941435606}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Korean: {'event': {'p': 0.6851851851851852, 'r': 0.5873015873015873, 'f1': 0.6324786324786325}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5319148936170213, 'r': 0.6944444444444444, 'f1': 0.6024096385542169}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
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 02:14:44.750760: step: 4/530, loss: 0.06301908940076828
2023-01-23 02:14:45.852621: step: 8/530, loss: 0.02876119688153267
2023-01-23 02:14:46.955861: step: 12/530, loss: 0.015044212341308594
2023-01-23 02:14:48.063512: step: 16/530, loss: 0.002354526426643133
2023-01-23 02:14:49.196131: step: 20/530, loss: 0.03818511962890625
2023-01-23 02:14:50.328294: step: 24/530, loss: 0.0059782033786177635
2023-01-23 02:14:51.443371: step: 28/530, loss: 0.06077738106250763
2023-01-23 02:14:52.569542: step: 32/530, loss: 0.005969667807221413
2023-01-23 02:14:53.694088: step: 36/530, loss: 0.002396011259406805
2023-01-23 02:14:54.807676: step: 40/530, loss: 0.000508483499288559
2023-01-23 02:14:55.951071: step: 44/530, loss: 0.02786741405725479
2023-01-23 02:14:57.058777: step: 48/530, loss: 0.008535710163414478
2023-01-23 02:14:58.183050: step: 52/530, loss: 0.04281940311193466
2023-01-23 02:14:59.288768: step: 56/530, loss: 0.015337658114731312
2023-01-23 02:15:00.446928: step: 60/530, loss: 0.004324722103774548
2023-01-23 02:15:01.605069: step: 64/530, loss: 0.0053123473189771175
2023-01-23 02:15:02.740347: step: 68/530, loss: 0.006029605865478516
2023-01-23 02:15:03.875596: step: 72/530, loss: 0.02556157112121582
2023-01-23 02:15:05.017174: step: 76/530, loss: 0.008643055334687233
2023-01-23 02:15:06.146171: step: 80/530, loss: 0.00536537216976285
2023-01-23 02:15:07.280853: step: 84/530, loss: 0.00017042159743141383
2023-01-23 02:15:08.429189: step: 88/530, loss: 0.004296398255974054
2023-01-23 02:15:09.553041: step: 92/530, loss: 0.015748023986816406
2023-01-23 02:15:10.701791: step: 96/530, loss: 0.017750263214111328
2023-01-23 02:15:11.819445: step: 100/530, loss: 0.010699748992919922
2023-01-23 02:15:12.960511: step: 104/530, loss: 0.7596079111099243
2023-01-23 02:15:14.074907: step: 108/530, loss: 0.007402515504509211
2023-01-23 02:15:15.194431: step: 112/530, loss: 0.04561633989214897
2023-01-23 02:15:16.316606: step: 116/530, loss: 0.03657369315624237
2023-01-23 02:15:17.433413: step: 120/530, loss: 0.015366936102509499
2023-01-23 02:15:18.558889: step: 124/530, loss: 0.0004837036249227822
2023-01-23 02:15:19.686106: step: 128/530, loss: 0.0021389008034020662
2023-01-23 02:15:20.826058: step: 132/530, loss: 0.0013599395751953125
2023-01-23 02:15:21.966534: step: 136/530, loss: 0.006531191058456898
2023-01-23 02:15:23.067200: step: 140/530, loss: 0.039427757263183594
2023-01-23 02:15:24.194154: step: 144/530, loss: 0.010342788882553577
2023-01-23 02:15:25.333277: step: 148/530, loss: 0.001985931536182761
2023-01-23 02:15:26.434523: step: 152/530, loss: 0.07353687286376953
2023-01-23 02:15:27.573621: step: 156/530, loss: 0.00117664341814816
2023-01-23 02:15:28.705391: step: 160/530, loss: 0.0002525329473428428
2023-01-23 02:15:29.823531: step: 164/530, loss: 0.09442013502120972
2023-01-23 02:15:30.925012: step: 168/530, loss: 0.27707234025001526
2023-01-23 02:15:32.041997: step: 172/530, loss: 0.0026547431480139494
2023-01-23 02:15:33.147306: step: 176/530, loss: 0.0006613731384277344
2023-01-23 02:15:34.260005: step: 180/530, loss: 0.010602761059999466
2023-01-23 02:15:35.384892: step: 184/530, loss: 0.00397338904440403
2023-01-23 02:15:36.505664: step: 188/530, loss: 0.007596493232995272
2023-01-23 02:15:37.609318: step: 192/530, loss: 0.004687977023422718
2023-01-23 02:15:38.751456: step: 196/530, loss: 0.04013033211231232
2023-01-23 02:15:39.877027: step: 200/530, loss: 0.04576144367456436
2023-01-23 02:15:40.975575: step: 204/530, loss: 0.0008302688365802169
2023-01-23 02:15:42.118587: step: 208/530, loss: 0.0037252428010106087
2023-01-23 02:15:43.233907: step: 212/530, loss: 0.01154251117259264
2023-01-23 02:15:44.348772: step: 216/530, loss: 0.05089616775512695
2023-01-23 02:15:45.490095: step: 220/530, loss: 0.001321649644523859
2023-01-23 02:15:46.617976: step: 224/530, loss: 0.038405418395996094
2023-01-23 02:15:47.728494: step: 228/530, loss: 0.0046478272415697575
2023-01-23 02:15:48.843877: step: 232/530, loss: 0.9784982800483704
2023-01-23 02:15:49.957105: step: 236/530, loss: 0.01976604573428631
2023-01-23 02:15:51.087316: step: 240/530, loss: 0.0001201629638671875
2023-01-23 02:15:52.220578: step: 244/530, loss: 0.021088028326630592
2023-01-23 02:15:53.347296: step: 248/530, loss: 0.02731933817267418
2023-01-23 02:15:54.488751: step: 252/530, loss: 0.0005513190990313888
2023-01-23 02:15:55.610196: step: 256/530, loss: 0.10139027237892151
2023-01-23 02:15:56.740804: step: 260/530, loss: 0.00933084450662136
2023-01-23 02:15:57.876476: step: 264/530, loss: 0.02404460869729519
2023-01-23 02:15:59.026792: step: 268/530, loss: 0.0029658316634595394
2023-01-23 02:16:00.142933: step: 272/530, loss: 0.05531797558069229
2023-01-23 02:16:01.261108: step: 276/530, loss: 0.01288375910371542
2023-01-23 02:16:02.406322: step: 280/530, loss: 0.0010653972858563066
2023-01-23 02:16:03.510544: step: 284/530, loss: 0.0038002014625817537
2023-01-23 02:16:04.645933: step: 288/530, loss: 0.025200653821229935
2023-01-23 02:16:05.799034: step: 292/530, loss: 0.01848907582461834
2023-01-23 02:16:06.909807: step: 296/530, loss: 0.0005010605091229081
2023-01-23 02:16:08.042407: step: 300/530, loss: 0.0005220413440838456
2023-01-23 02:16:09.176762: step: 304/530, loss: 0.026517678052186966
2023-01-23 02:16:10.320730: step: 308/530, loss: 0.08356904983520508
2023-01-23 02:16:11.452626: step: 312/530, loss: 0.009510469622910023
2023-01-23 02:16:12.577652: step: 316/530, loss: 0.0733041763305664
2023-01-23 02:16:13.716460: step: 320/530, loss: 0.0075698853470385075
2023-01-23 02:16:14.854420: step: 324/530, loss: 0.0228818878531456
2023-01-23 02:16:15.971243: step: 328/530, loss: 0.13211460411548615
2023-01-23 02:16:17.077284: step: 332/530, loss: 0.021465588361024857
2023-01-23 02:16:18.232515: step: 336/530, loss: 0.01985016092658043
2023-01-23 02:16:19.364589: step: 340/530, loss: 0.06771975010633469
2023-01-23 02:16:20.523598: step: 344/530, loss: 0.008022308349609375
2023-01-23 02:16:21.663173: step: 348/530, loss: 0.03173542022705078
2023-01-23 02:16:22.789661: step: 352/530, loss: 0.025593949481844902
2023-01-23 02:16:23.926470: step: 356/530, loss: 0.011091423220932484
2023-01-23 02:16:25.058771: step: 360/530, loss: 0.012034225277602673
2023-01-23 02:16:26.175265: step: 364/530, loss: 0.02886953391134739
2023-01-23 02:16:27.301511: step: 368/530, loss: 0.04371687024831772
2023-01-23 02:16:28.399685: step: 372/530, loss: 0.00019750595674850047
2023-01-23 02:16:29.496536: step: 376/530, loss: 0.009295654483139515
2023-01-23 02:16:30.625581: step: 380/530, loss: 0.08063545823097229
2023-01-23 02:16:31.734805: step: 384/530, loss: 0.03663082420825958
2023-01-23 02:16:32.866059: step: 388/530, loss: 0.0015880585415288806
2023-01-23 02:16:34.004827: step: 392/530, loss: 0.02606317773461342
2023-01-23 02:16:35.138312: step: 396/530, loss: 0.001323699951171875
2023-01-23 02:16:36.249593: step: 400/530, loss: 0.07313556224107742
2023-01-23 02:16:37.365186: step: 404/530, loss: 0.026813890784978867
2023-01-23 02:16:38.482596: step: 408/530, loss: 0.0016522407531738281
2023-01-23 02:16:39.645631: step: 412/530, loss: 0.05738115310668945
2023-01-23 02:16:40.764917: step: 416/530, loss: 9.117126319324598e-05
2023-01-23 02:16:41.881831: step: 420/530, loss: 0.010639572516083717
2023-01-23 02:16:42.996152: step: 424/530, loss: 0.03826894611120224
2023-01-23 02:16:44.117577: step: 428/530, loss: 0.009136009961366653
2023-01-23 02:16:45.212867: step: 432/530, loss: 0.009017085656523705
2023-01-23 02:16:46.354218: step: 436/530, loss: 0.07303555309772491
2023-01-23 02:16:47.478919: step: 440/530, loss: 0.0015249490970745683
2023-01-23 02:16:48.594493: step: 444/530, loss: 0.0029181481804698706
2023-01-23 02:16:49.719461: step: 448/530, loss: 0.0001624107244424522
2023-01-23 02:16:50.844195: step: 452/530, loss: 0.006937885191291571
2023-01-23 02:16:51.944947: step: 456/530, loss: 0.0015713691245764494
2023-01-23 02:16:53.037880: step: 460/530, loss: 0.005838585086166859
2023-01-23 02:16:54.169002: step: 464/530, loss: 0.035994816571474075
2023-01-23 02:16:55.282813: step: 468/530, loss: 0.04271211847662926
2023-01-23 02:16:56.416274: step: 472/530, loss: 2.956390380859375e-05
2023-01-23 02:16:57.653236: step: 476/530, loss: 0.013714408501982689
2023-01-23 02:16:58.785731: step: 480/530, loss: 0.00209980015642941
2023-01-23 02:16:59.930101: step: 484/530, loss: 0.05198374018073082
2023-01-23 02:17:01.099842: step: 488/530, loss: 0.03801736608147621
2023-01-23 02:17:02.205337: step: 492/530, loss: 0.00574836740270257
2023-01-23 02:17:03.309520: step: 496/530, loss: 0.0014463425613939762
2023-01-23 02:17:04.423624: step: 500/530, loss: 0.002930927090346813
2023-01-23 02:17:05.591219: step: 504/530, loss: 0.00855398178100586
2023-01-23 02:17:06.692774: step: 508/530, loss: 0.05135517194867134
2023-01-23 02:17:07.808845: step: 512/530, loss: 0.002239322755485773
2023-01-23 02:17:08.942385: step: 516/530, loss: 0.008370209485292435
2023-01-23 02:17:10.083504: step: 520/530, loss: 0.07912015914916992
2023-01-23 02:17:11.217685: step: 524/530, loss: 0.051090337336063385
2023-01-23 02:17:12.342141: step: 528/530, loss: 0.013118267059326172
2023-01-23 02:17:13.466731: step: 532/530, loss: 0.022995568811893463
2023-01-23 02:17:14.579010: step: 536/530, loss: 0.0009084702469408512
2023-01-23 02:17:15.690633: step: 540/530, loss: 0.02875232696533203
2023-01-23 02:17:16.826758: step: 544/530, loss: 0.002215576358139515
2023-01-23 02:17:17.932739: step: 548/530, loss: 0.044439125806093216
2023-01-23 02:17:19.058852: step: 552/530, loss: 0.027898024767637253
2023-01-23 02:17:20.190170: step: 556/530, loss: 0.0005229950184002519
2023-01-23 02:17:21.328119: step: 560/530, loss: 0.024617576971650124
2023-01-23 02:17:22.458873: step: 564/530, loss: 0.013333892449736595
2023-01-23 02:17:23.561778: step: 568/530, loss: 0.026875782757997513
2023-01-23 02:17:24.688495: step: 572/530, loss: 0.011289024725556374
2023-01-23 02:17:25.813056: step: 576/530, loss: 0.03284483402967453
2023-01-23 02:17:26.925331: step: 580/530, loss: 0.0021974563132971525
2023-01-23 02:17:28.034139: step: 584/530, loss: 0.06609725952148438
2023-01-23 02:17:29.163258: step: 588/530, loss: 0.01821298711001873
2023-01-23 02:17:30.296012: step: 592/530, loss: 1.0563435554504395
2023-01-23 02:17:31.442831: step: 596/530, loss: 0.012204552069306374
2023-01-23 02:17:32.603088: step: 600/530, loss: 0.025958824902772903
2023-01-23 02:17:33.735792: step: 604/530, loss: 0.02353687211871147
2023-01-23 02:17:34.853816: step: 608/530, loss: 0.004166364669799805
2023-01-23 02:17:35.987252: step: 612/530, loss: 0.01948533020913601
2023-01-23 02:17:37.108523: step: 616/530, loss: 0.01134634017944336
2023-01-23 02:17:38.229938: step: 620/530, loss: 0.009821987710893154
2023-01-23 02:17:39.362926: step: 624/530, loss: 0.07768841087818146
2023-01-23 02:17:40.444828: step: 628/530, loss: 0.018469810485839844
2023-01-23 02:17:41.577493: step: 632/530, loss: 0.00554690370336175
2023-01-23 02:17:42.739694: step: 636/530, loss: 0.006787681952118874
2023-01-23 02:17:43.875615: step: 640/530, loss: 0.004995155148208141
2023-01-23 02:17:45.026644: step: 644/530, loss: -9.5367431640625e-07
2023-01-23 02:17:46.124687: step: 648/530, loss: 0.02008981630206108
2023-01-23 02:17:47.281388: step: 652/530, loss: 0.0032486915588378906
2023-01-23 02:17:48.408522: step: 656/530, loss: 0.019436310976743698
2023-01-23 02:17:49.507169: step: 660/530, loss: 0.0022603035904467106
2023-01-23 02:17:50.658134: step: 664/530, loss: 0.0014338493347167969
2023-01-23 02:17:51.795642: step: 668/530, loss: 0.022200871258974075
2023-01-23 02:17:52.907093: step: 672/530, loss: 0.003977012820541859
2023-01-23 02:17:54.026983: step: 676/530, loss: 0.0037576674949377775
2023-01-23 02:17:55.145767: step: 680/530, loss: 0.0034274100326001644
2023-01-23 02:17:56.258446: step: 684/530, loss: 0.001448345254175365
2023-01-23 02:17:57.377259: step: 688/530, loss: 0.657168984413147
2023-01-23 02:17:58.515589: step: 692/530, loss: 0.06804457306861877
2023-01-23 02:17:59.623150: step: 696/530, loss: 0.02938881143927574
2023-01-23 02:18:00.735850: step: 700/530, loss: 0.00861902255564928
2023-01-23 02:18:01.870412: step: 704/530, loss: 0.039499662816524506
2023-01-23 02:18:03.001454: step: 708/530, loss: 0.0007273674127645791
2023-01-23 02:18:04.152800: step: 712/530, loss: 0.0016185521380975842
2023-01-23 02:18:05.257122: step: 716/530, loss: 0.00935277994722128
2023-01-23 02:18:06.375758: step: 720/530, loss: 0.15545310080051422
2023-01-23 02:18:07.478069: step: 724/530, loss: 2.7418136596679688e-05
2023-01-23 02:18:08.581558: step: 728/530, loss: 0.2362150251865387
2023-01-23 02:18:09.709746: step: 732/530, loss: 0.07468290627002716
2023-01-23 02:18:10.850612: step: 736/530, loss: 0.005737781524658203
2023-01-23 02:18:11.966905: step: 740/530, loss: 0.051972582936286926
2023-01-23 02:18:13.104729: step: 744/530, loss: 0.0015926361083984375
2023-01-23 02:18:14.228834: step: 748/530, loss: 0.03697628900408745
2023-01-23 02:18:15.387864: step: 752/530, loss: 0.0014581680297851562
2023-01-23 02:18:16.498878: step: 756/530, loss: 0.014050101861357689
2023-01-23 02:18:17.648058: step: 760/530, loss: 0.0018521309830248356
2023-01-23 02:18:18.813222: step: 764/530, loss: 0.5094509720802307
2023-01-23 02:18:19.950542: step: 768/530, loss: 0.021326638758182526
2023-01-23 02:18:21.088705: step: 772/530, loss: 0.0595640167593956
2023-01-23 02:18:22.208504: step: 776/530, loss: 0.008613968268036842
2023-01-23 02:18:23.312691: step: 780/530, loss: 0.008191651664674282
2023-01-23 02:18:24.416037: step: 784/530, loss: 0.012143135070800781
2023-01-23 02:18:25.520316: step: 788/530, loss: 0.0003234863397665322
2023-01-23 02:18:26.647471: step: 792/530, loss: 0.016315460205078125
2023-01-23 02:18:27.777422: step: 796/530, loss: 0.004610276315361261
2023-01-23 02:18:28.915322: step: 800/530, loss: 0.6781415939331055
2023-01-23 02:18:30.033175: step: 804/530, loss: 0.01867532730102539
2023-01-23 02:18:31.186820: step: 808/530, loss: 0.00023565591254737228
2023-01-23 02:18:32.336179: step: 812/530, loss: 0.03674297407269478
2023-01-23 02:18:33.429741: step: 816/530, loss: 0.026883315294981003
2023-01-23 02:18:34.532143: step: 820/530, loss: 0.04646725580096245
2023-01-23 02:18:35.662097: step: 824/530, loss: 0.25731638073921204
2023-01-23 02:18:36.773467: step: 828/530, loss: 0.00021610260591842234
2023-01-23 02:18:37.936982: step: 832/530, loss: 0.025727082043886185
2023-01-23 02:18:39.105506: step: 836/530, loss: 0.0569889098405838
2023-01-23 02:18:40.236292: step: 840/530, loss: 0.00020866392878815532
2023-01-23 02:18:41.370798: step: 844/530, loss: 0.002565765520557761
2023-01-23 02:18:42.482943: step: 848/530, loss: 0.01056518591940403
2023-01-23 02:18:43.610031: step: 852/530, loss: 0.03997664526104927
2023-01-23 02:18:44.725837: step: 856/530, loss: 0.007743263617157936
2023-01-23 02:18:45.839369: step: 860/530, loss: 4.4488908315543085e-05
2023-01-23 02:18:46.936922: step: 864/530, loss: 0.0046096802689135075
2023-01-23 02:18:48.061137: step: 868/530, loss: 0.014674091711640358
2023-01-23 02:18:49.211806: step: 872/530, loss: 0.018805695697665215
2023-01-23 02:18:50.323248: step: 876/530, loss: 0.0006470441585406661
2023-01-23 02:18:51.432087: step: 880/530, loss: 0.013023472391068935
2023-01-23 02:18:52.573249: step: 884/530, loss: 0.005887794308364391
2023-01-23 02:18:53.726099: step: 888/530, loss: 0.030852604657411575
2023-01-23 02:18:54.848387: step: 892/530, loss: 0.008310317993164062
2023-01-23 02:18:55.948472: step: 896/530, loss: 0.007686138153076172
2023-01-23 02:18:57.093139: step: 900/530, loss: 0.032025717198848724
2023-01-23 02:18:58.230073: step: 904/530, loss: 0.13664494454860687
2023-01-23 02:18:59.368795: step: 908/530, loss: 0.13686561584472656
2023-01-23 02:19:00.508123: step: 912/530, loss: 0.045676231384277344
2023-01-23 02:19:01.629077: step: 916/530, loss: 0.02201395109295845
2023-01-23 02:19:02.778544: step: 920/530, loss: 0.004035472869873047
2023-01-23 02:19:03.928545: step: 924/530, loss: 0.0007376670837402344
2023-01-23 02:19:05.069100: step: 928/530, loss: 0.018345260992646217
2023-01-23 02:19:06.183162: step: 932/530, loss: 0.00278892507776618
2023-01-23 02:19:07.318263: step: 936/530, loss: 0.05030975118279457
2023-01-23 02:19:08.432077: step: 940/530, loss: 0.004177522845566273
2023-01-23 02:19:09.572039: step: 944/530, loss: 0.02850179746747017
2023-01-23 02:19:10.679629: step: 948/530, loss: 0.007239770609885454
2023-01-23 02:19:11.799148: step: 952/530, loss: 0.011342811398208141
2023-01-23 02:19:12.959851: step: 956/530, loss: 0.016461849212646484
2023-01-23 02:19:14.081608: step: 960/530, loss: 0.018616534769535065
2023-01-23 02:19:15.234404: step: 964/530, loss: 0.0012501716846600175
2023-01-23 02:19:16.332948: step: 968/530, loss: 0.01305084303021431
2023-01-23 02:19:17.450951: step: 972/530, loss: 0.005561256781220436
2023-01-23 02:19:18.564892: step: 976/530, loss: 0.13052532076835632
2023-01-23 02:19:19.692260: step: 980/530, loss: 0.00989465694874525
2023-01-23 02:19:20.810943: step: 984/530, loss: 0.014339066110551357
2023-01-23 02:19:21.923181: step: 988/530, loss: 6.732940528308973e-05
2023-01-23 02:19:23.052414: step: 992/530, loss: 0.006600475404411554
2023-01-23 02:19:24.199949: step: 996/530, loss: 0.021700739860534668
2023-01-23 02:19:25.316519: step: 1000/530, loss: 0.026310348883271217
2023-01-23 02:19:26.448869: step: 1004/530, loss: 0.020311737433075905
2023-01-23 02:19:27.569802: step: 1008/530, loss: 0.08196954429149628
2023-01-23 02:19:28.666504: step: 1012/530, loss: 0.0003003597375936806
2023-01-23 02:19:29.766489: step: 1016/530, loss: 0.0028558254707604647
2023-01-23 02:19:30.883682: step: 1020/530, loss: 0.0011283399071544409
2023-01-23 02:19:31.989326: step: 1024/530, loss: 0.024431325495243073
2023-01-23 02:19:33.103761: step: 1028/530, loss: 0.026449013501405716
2023-01-23 02:19:34.228248: step: 1032/530, loss: 0.017591094598174095
2023-01-23 02:19:35.380374: step: 1036/530, loss: 0.0007052421569824219
2023-01-23 02:19:36.513287: step: 1040/530, loss: 0.02456970326602459
2023-01-23 02:19:37.642082: step: 1044/530, loss: 0.03580150380730629
2023-01-23 02:19:38.767594: step: 1048/530, loss: 0.011391258798539639
2023-01-23 02:19:39.900923: step: 1052/530, loss: 0.01680774800479412
2023-01-23 02:19:40.999516: step: 1056/530, loss: 0.02341938018798828
2023-01-23 02:19:42.106109: step: 1060/530, loss: 0.010100937448441982
2023-01-23 02:19:43.242686: step: 1064/530, loss: 0.006063365843147039
2023-01-23 02:19:44.361377: step: 1068/530, loss: 0.010940885171294212
2023-01-23 02:19:45.510802: step: 1072/530, loss: 0.42117881774902344
2023-01-23 02:19:46.634624: step: 1076/530, loss: 0.0270646084100008
2023-01-23 02:19:47.756909: step: 1080/530, loss: 0.06631851196289062
2023-01-23 02:19:48.888595: step: 1084/530, loss: 0.0265746358782053
2023-01-23 02:19:50.001646: step: 1088/530, loss: 0.02209014818072319
2023-01-23 02:19:51.154876: step: 1092/530, loss: 0.04482688754796982
2023-01-23 02:19:52.265457: step: 1096/530, loss: 0.03228512033820152
2023-01-23 02:19:53.409162: step: 1100/530, loss: 0.000110626220703125
2023-01-23 02:19:54.495485: step: 1104/530, loss: 0.0808483138680458
2023-01-23 02:19:55.628459: step: 1108/530, loss: 0.10856809467077255
2023-01-23 02:19:56.759789: step: 1112/530, loss: 0.002850818447768688
2023-01-23 02:19:57.884774: step: 1116/530, loss: 0.01867103762924671
2023-01-23 02:19:59.058716: step: 1120/530, loss: 0.003425789065659046
2023-01-23 02:20:00.217206: step: 1124/530, loss: 0.01171493623405695
2023-01-23 02:20:01.312397: step: 1128/530, loss: 0.00037660598172806203
2023-01-23 02:20:02.459946: step: 1132/530, loss: 0.0634550154209137
2023-01-23 02:20:03.591748: step: 1136/530, loss: 0.008655071258544922
2023-01-23 02:20:04.722021: step: 1140/530, loss: 0.0020933151245117188
2023-01-23 02:20:05.850983: step: 1144/530, loss: 0.02985682524740696
2023-01-23 02:20:06.985606: step: 1148/530, loss: 0.012695884332060814
2023-01-23 02:20:08.143248: step: 1152/530, loss: 0.024936510249972343
2023-01-23 02:20:09.279202: step: 1156/530, loss: 0.030585383996367455
2023-01-23 02:20:10.433897: step: 1160/530, loss: 0.009078312665224075
2023-01-23 02:20:11.557096: step: 1164/530, loss: 0.008010960184037685
2023-01-23 02:20:12.653816: step: 1168/530, loss: 0.0036783218383789062
2023-01-23 02:20:13.791661: step: 1172/530, loss: 0.02302856370806694
2023-01-23 02:20:14.937268: step: 1176/530, loss: 0.00702743511646986
2023-01-23 02:20:16.054569: step: 1180/530, loss: 0.0002359390346100554
2023-01-23 02:20:17.186626: step: 1184/530, loss: 3.166198803228326e-05
2023-01-23 02:20:18.322214: step: 1188/530, loss: 0.03865652158856392
2023-01-23 02:20:19.421003: step: 1192/530, loss: 0.006236553192138672
2023-01-23 02:20:20.531010: step: 1196/530, loss: 0.005015039350837469
2023-01-23 02:20:21.666253: step: 1200/530, loss: 0.00248374929651618
2023-01-23 02:20:22.795191: step: 1204/530, loss: 0.0006333351484499872
2023-01-23 02:20:23.951257: step: 1208/530, loss: 0.018186094239354134
2023-01-23 02:20:25.061421: step: 1212/530, loss: 0.024813033640384674
2023-01-23 02:20:26.199356: step: 1216/530, loss: 0.007860183715820312
2023-01-23 02:20:27.320050: step: 1220/530, loss: 0.011639213189482689
2023-01-23 02:20:28.485508: step: 1224/530, loss: 0.5874112844467163
2023-01-23 02:20:29.607398: step: 1228/530, loss: 0.00048131943913176656
2023-01-23 02:20:30.745246: step: 1232/530, loss: 0.002529907040297985
2023-01-23 02:20:31.873275: step: 1236/530, loss: 0.0005347415572032332
2023-01-23 02:20:32.961717: step: 1240/530, loss: 0.006069183349609375
2023-01-23 02:20:34.084955: step: 1244/530, loss: 0.0018108368385583162
2023-01-23 02:20:35.213330: step: 1248/530, loss: 0.01851367950439453
2023-01-23 02:20:36.339395: step: 1252/530, loss: 0.10787548869848251
2023-01-23 02:20:37.473668: step: 1256/530, loss: 0.039223670959472656
2023-01-23 02:20:38.592541: step: 1260/530, loss: 0.002181434538215399
2023-01-23 02:20:39.704782: step: 1264/530, loss: 0.0009279251098632812
2023-01-23 02:20:40.832774: step: 1268/530, loss: 0.40292245149612427
2023-01-23 02:20:41.953884: step: 1272/530, loss: 0.026256084442138672
2023-01-23 02:20:43.037979: step: 1276/530, loss: 9.15527380129788e-06
2023-01-23 02:20:44.180386: step: 1280/530, loss: 0.051944732666015625
2023-01-23 02:20:45.309841: step: 1284/530, loss: 0.0008594036335125566
2023-01-23 02:20:46.442646: step: 1288/530, loss: 0.07917194813489914
2023-01-23 02:20:47.563192: step: 1292/530, loss: 0.13904426991939545
2023-01-23 02:20:48.716752: step: 1296/530, loss: 0.09802704304456711
2023-01-23 02:20:49.855644: step: 1300/530, loss: 0.03351593017578125
2023-01-23 02:20:50.943652: step: 1304/530, loss: 0.04357731714844704
2023-01-23 02:20:52.054927: step: 1308/530, loss: 0.00451583880931139
2023-01-23 02:20:53.147585: step: 1312/530, loss: 0.0017642974853515625
2023-01-23 02:20:54.243618: step: 1316/530, loss: 0.09723100811243057
2023-01-23 02:20:55.385028: step: 1320/530, loss: 0.007618522737175226
2023-01-23 02:20:56.508291: step: 1324/530, loss: 0.040081217885017395
2023-01-23 02:20:57.666887: step: 1328/530, loss: 0.029881859198212624
2023-01-23 02:20:58.758523: step: 1332/530, loss: 0.03812370449304581
2023-01-23 02:20:59.899635: step: 1336/530, loss: 0.0563817024230957
2023-01-23 02:21:01.010391: step: 1340/530, loss: 0.04955501854419708
2023-01-23 02:21:02.156527: step: 1344/530, loss: 0.013701161369681358
2023-01-23 02:21:03.304341: step: 1348/530, loss: 0.02276611328125
2023-01-23 02:21:04.448896: step: 1352/530, loss: 0.0004288673517294228
2023-01-23 02:21:05.554092: step: 1356/530, loss: 0.015003586187958717
2023-01-23 02:21:06.660692: step: 1360/530, loss: 0.04562520980834961
2023-01-23 02:21:07.768065: step: 1364/530, loss: 0.018922997638583183
2023-01-23 02:21:08.896500: step: 1368/530, loss: 0.02266693115234375
2023-01-23 02:21:10.021448: step: 1372/530, loss: 0.005838871002197266
2023-01-23 02:21:11.140734: step: 1376/530, loss: 0.0029023527167737484
2023-01-23 02:21:12.283370: step: 1380/530, loss: 0.0149695398285985
2023-01-23 02:21:13.434917: step: 1384/530, loss: 0.004807853605598211
2023-01-23 02:21:14.563318: step: 1388/530, loss: 0.014610386453568935
2023-01-23 02:21:15.664686: step: 1392/530, loss: 0.00854024849832058
2023-01-23 02:21:16.771740: step: 1396/530, loss: 0.0006809234619140625
2023-01-23 02:21:17.885180: step: 1400/530, loss: 0.022415639832615852
2023-01-23 02:21:19.031001: step: 1404/530, loss: 0.029984187334775925
2023-01-23 02:21:20.149462: step: 1408/530, loss: 0.023117495700716972
2023-01-23 02:21:21.265737: step: 1412/530, loss: 0.06122494116425514
2023-01-23 02:21:22.408613: step: 1416/530, loss: 0.004453182220458984
2023-01-23 02:21:23.532509: step: 1420/530, loss: 0.05998754873871803
2023-01-23 02:21:24.682520: step: 1424/530, loss: 0.0006221771473065019
2023-01-23 02:21:25.790212: step: 1428/530, loss: 0.05530204996466637
2023-01-23 02:21:26.919635: step: 1432/530, loss: 0.00868377648293972
2023-01-23 02:21:28.022120: step: 1436/530, loss: 0.00870046578347683
2023-01-23 02:21:29.155003: step: 1440/530, loss: 0.017313959077000618
2023-01-23 02:21:30.272779: step: 1444/530, loss: 0.0027986527420580387
2023-01-23 02:21:31.434668: step: 1448/530, loss: 0.018596267327666283
2023-01-23 02:21:32.582017: step: 1452/530, loss: 0.0007522970554418862
2023-01-23 02:21:33.692232: step: 1456/530, loss: 0.0029664994217455387
2023-01-23 02:21:34.814338: step: 1460/530, loss: 0.008461189456284046
2023-01-23 02:21:35.907047: step: 1464/530, loss: 0.05176115408539772
2023-01-23 02:21:37.005012: step: 1468/530, loss: 0.00011796951002907008
2023-01-23 02:21:38.114751: step: 1472/530, loss: 0.038598060607910156
2023-01-23 02:21:39.218929: step: 1476/530, loss: 0.0007402420160360634
2023-01-23 02:21:40.370943: step: 1480/530, loss: 0.02830381505191326
2023-01-23 02:21:41.491582: step: 1484/530, loss: 0.0010368346702307463
2023-01-23 02:21:42.608920: step: 1488/530, loss: 0.022386837750673294
2023-01-23 02:21:43.762678: step: 1492/530, loss: 0.011796570383012295
2023-01-23 02:21:44.901511: step: 1496/530, loss: 0.0001773834228515625
2023-01-23 02:21:46.010549: step: 1500/530, loss: 0.00111217494122684
2023-01-23 02:21:47.130249: step: 1504/530, loss: 0.04430866241455078
2023-01-23 02:21:48.266705: step: 1508/530, loss: 0.03873375803232193
2023-01-23 02:21:49.401310: step: 1512/530, loss: 0.007622718811035156
2023-01-23 02:21:50.516952: step: 1516/530, loss: 0.02032499387860298
2023-01-23 02:21:51.641387: step: 1520/530, loss: 0.00884780939668417
2023-01-23 02:21:52.752410: step: 1524/530, loss: 0.0009005547035485506
2023-01-23 02:21:53.866869: step: 1528/530, loss: 0.096226267516613
2023-01-23 02:21:55.019389: step: 1532/530, loss: 0.05904083326458931
2023-01-23 02:21:56.183167: step: 1536/530, loss: 0.0036804198753088713
2023-01-23 02:21:57.316824: step: 1540/530, loss: 0.0644993782043457
2023-01-23 02:21:58.416183: step: 1544/530, loss: 0.007517147343605757
2023-01-23 02:21:59.549522: step: 1548/530, loss: 0.003606605576351285
2023-01-23 02:22:00.684903: step: 1552/530, loss: 0.0049468521028757095
2023-01-23 02:22:01.821277: step: 1556/530, loss: 0.013503646478056908
2023-01-23 02:22:02.952356: step: 1560/530, loss: 0.0015736579662188888
2023-01-23 02:22:04.095265: step: 1564/530, loss: 0.002293205354362726
2023-01-23 02:22:05.206190: step: 1568/530, loss: 0.0008790969732217491
2023-01-23 02:22:06.355511: step: 1572/530, loss: 7.43865966796875e-05
2023-01-23 02:22:07.484699: step: 1576/530, loss: 0.033884476870298386
2023-01-23 02:22:08.593399: step: 1580/530, loss: 0.15299153327941895
2023-01-23 02:22:09.714430: step: 1584/530, loss: 0.023784542456269264
2023-01-23 02:22:10.860934: step: 1588/530, loss: 0.01032323855906725
2023-01-23 02:22:11.967147: step: 1592/530, loss: 0.029903031885623932
2023-01-23 02:22:13.102766: step: 1596/530, loss: 0.0003773212374653667
2023-01-23 02:22:14.242050: step: 1600/530, loss: 0.12320718914270401
2023-01-23 02:22:15.364389: step: 1604/530, loss: 0.5541620254516602
2023-01-23 02:22:16.479189: step: 1608/530, loss: 0.0037043574266135693
2023-01-23 02:22:17.611317: step: 1612/530, loss: 0.025124119594693184
2023-01-23 02:22:18.731401: step: 1616/530, loss: 0.02287464216351509
2023-01-23 02:22:19.869955: step: 1620/530, loss: 0.08258037269115448
2023-01-23 02:22:20.982551: step: 1624/530, loss: 0.00163097376935184
2023-01-23 02:22:22.114971: step: 1628/530, loss: 0.00035452842712402344
2023-01-23 02:22:23.264610: step: 1632/530, loss: 0.003934239968657494
2023-01-23 02:22:24.427279: step: 1636/530, loss: 0.02038288302719593
2023-01-23 02:22:25.549785: step: 1640/530, loss: 0.013879776000976562
2023-01-23 02:22:26.659156: step: 1644/530, loss: 0.09607429802417755
2023-01-23 02:22:27.832872: step: 1648/530, loss: 0.06835365295410156
2023-01-23 02:22:28.979909: step: 1652/530, loss: 0.01781644858419895
2023-01-23 02:22:30.141195: step: 1656/530, loss: 0.01643829420208931
2023-01-23 02:22:31.283561: step: 1660/530, loss: 0.006119156256318092
2023-01-23 02:22:32.422552: step: 1664/530, loss: 0.10356283187866211
2023-01-23 02:22:33.548967: step: 1668/530, loss: 0.05298471450805664
2023-01-23 02:22:34.677855: step: 1672/530, loss: 6.427765038097277e-05
2023-01-23 02:22:35.779435: step: 1676/530, loss: 0.01542515680193901
2023-01-23 02:22:36.903369: step: 1680/530, loss: 0.024073602631688118
2023-01-23 02:22:38.012505: step: 1684/530, loss: 0.02604503743350506
2023-01-23 02:22:39.158609: step: 1688/530, loss: 0.03920355066657066
2023-01-23 02:22:40.262282: step: 1692/530, loss: 0.007467078976333141
2023-01-23 02:22:41.367173: step: 1696/530, loss: 0.013394070789217949
2023-01-23 02:22:42.515009: step: 1700/530, loss: 0.012524223886430264
2023-01-23 02:22:43.643300: step: 1704/530, loss: 0.003688239958137274
2023-01-23 02:22:44.770882: step: 1708/530, loss: 0.01958923414349556
2023-01-23 02:22:45.897529: step: 1712/530, loss: 0.013335037976503372
2023-01-23 02:22:47.015401: step: 1716/530, loss: 0.02902812883257866
2023-01-23 02:22:48.154312: step: 1720/530, loss: 0.113642118871212
2023-01-23 02:22:49.277670: step: 1724/530, loss: 0.04945125803351402
2023-01-23 02:22:50.368357: step: 1728/530, loss: 0.011638784781098366
2023-01-23 02:22:51.517527: step: 1732/530, loss: 0.03705959394574165
2023-01-23 02:22:52.652333: step: 1736/530, loss: 0.022434331476688385
2023-01-23 02:22:53.771242: step: 1740/530, loss: 0.022758103907108307
2023-01-23 02:22:54.871287: step: 1744/530, loss: 0.009679795242846012
2023-01-23 02:22:55.974035: step: 1748/530, loss: 0.005592561326920986
2023-01-23 02:22:57.110580: step: 1752/530, loss: 0.0015164853539317846
2023-01-23 02:22:58.245886: step: 1756/530, loss: 0.05279827117919922
2023-01-23 02:22:59.395043: step: 1760/530, loss: 0.0008146286127157509
2023-01-23 02:23:00.594982: step: 1764/530, loss: 5.292892819852568e-05
2023-01-23 02:23:01.730428: step: 1768/530, loss: 0.00389175396412611
2023-01-23 02:23:02.889443: step: 1772/530, loss: 0.004557990934699774
2023-01-23 02:23:04.050417: step: 1776/530, loss: 0.03280467912554741
2023-01-23 02:23:05.199355: step: 1780/530, loss: 0.043671224266290665
2023-01-23 02:23:06.334268: step: 1784/530, loss: 0.00019655228243209422
2023-01-23 02:23:07.469968: step: 1788/530, loss: 0.003915214445441961
2023-01-23 02:23:08.592447: step: 1792/530, loss: 0.003193473909050226
2023-01-23 02:23:09.739793: step: 1796/530, loss: 0.01273260172456503
2023-01-23 02:23:10.862043: step: 1800/530, loss: 5.645752025884576e-05
2023-01-23 02:23:11.971852: step: 1804/530, loss: 0.005122947972267866
2023-01-23 02:23:13.063987: step: 1808/530, loss: 0.030591202899813652
2023-01-23 02:23:14.171186: step: 1812/530, loss: 0.014458179473876953
2023-01-23 02:23:15.293470: step: 1816/530, loss: 0.00010585784912109375
2023-01-23 02:23:16.433411: step: 1820/530, loss: 0.00512008648365736
2023-01-23 02:23:17.571175: step: 1824/530, loss: 0.005435371771454811
2023-01-23 02:23:18.682447: step: 1828/530, loss: 0.003403520444408059
2023-01-23 02:23:19.834730: step: 1832/530, loss: 0.014070987701416016
2023-01-23 02:23:20.960698: step: 1836/530, loss: 0.024495316669344902
2023-01-23 02:23:22.092610: step: 1840/530, loss: 0.019470976665616035
2023-01-23 02:23:23.222451: step: 1844/530, loss: 0.022258473560214043
2023-01-23 02:23:24.344515: step: 1848/530, loss: 0.060204315930604935
2023-01-23 02:23:25.477742: step: 1852/530, loss: 0.020189572125673294
2023-01-23 02:23:26.614004: step: 1856/530, loss: 0.0062272134236991405
2023-01-23 02:23:27.720531: step: 1860/530, loss: 0.006847381591796875
2023-01-23 02:23:28.840764: step: 1864/530, loss: 0.02475299872457981
2023-01-23 02:23:29.981417: step: 1868/530, loss: 0.024157142266631126
2023-01-23 02:23:31.128694: step: 1872/530, loss: 0.0008168220520019531
2023-01-23 02:23:32.265177: step: 1876/530, loss: 0.0006221771473065019
2023-01-23 02:23:33.391060: step: 1880/530, loss: 0.02816629409790039
2023-01-23 02:23:34.501578: step: 1884/530, loss: 0.024259090423583984
2023-01-23 02:23:35.626244: step: 1888/530, loss: 0.0005876540672034025
2023-01-23 02:23:36.752264: step: 1892/530, loss: 0.0029769898392260075
2023-01-23 02:23:37.890833: step: 1896/530, loss: 0.006971264258027077
2023-01-23 02:23:39.024069: step: 1900/530, loss: 0.0040115355513989925
2023-01-23 02:23:40.137755: step: 1904/530, loss: 0.004012393765151501
2023-01-23 02:23:41.242139: step: 1908/530, loss: 0.06063403934240341
2023-01-23 02:23:42.383048: step: 1912/530, loss: 0.004015493206679821
2023-01-23 02:23:43.504121: step: 1916/530, loss: 0.06390835344791412
2023-01-23 02:23:44.658427: step: 1920/530, loss: 0.03961925581097603
2023-01-23 02:23:45.769053: step: 1924/530, loss: 0.00011520386033225805
2023-01-23 02:23:46.891905: step: 1928/530, loss: 0.006448650732636452
2023-01-23 02:23:47.977966: step: 1932/530, loss: 0.010734128765761852
2023-01-23 02:23:49.124104: step: 1936/530, loss: 3.852844383800402e-05
2023-01-23 02:23:50.267888: step: 1940/530, loss: 0.02266845665872097
2023-01-23 02:23:51.406581: step: 1944/530, loss: 0.029458142817020416
2023-01-23 02:23:52.539033: step: 1948/530, loss: 0.046312905848026276
2023-01-23 02:23:53.657885: step: 1952/530, loss: 0.016111183911561966
2023-01-23 02:23:54.752529: step: 1956/530, loss: 0.027915572747588158
2023-01-23 02:23:55.873591: step: 1960/530, loss: 0.03202624246478081
2023-01-23 02:23:57.025045: step: 1964/530, loss: 0.037285804748535156
2023-01-23 02:23:58.159455: step: 1968/530, loss: 0.022404098883271217
2023-01-23 02:23:59.297612: step: 1972/530, loss: 0.024330127984285355
2023-01-23 02:24:00.462944: step: 1976/530, loss: 0.045806884765625
2023-01-23 02:24:01.565796: step: 1980/530, loss: 0.055925749242305756
2023-01-23 02:24:02.678892: step: 1984/530, loss: 0.0024288177955895662
2023-01-23 02:24:03.799564: step: 1988/530, loss: 0.02773284912109375
2023-01-23 02:24:04.921679: step: 1992/530, loss: 0.12617407739162445
2023-01-23 02:24:06.046202: step: 1996/530, loss: 0.0001798153098206967
2023-01-23 02:24:07.177340: step: 2000/530, loss: 0.022842025384306908
2023-01-23 02:24:08.318790: step: 2004/530, loss: 0.0009710312006063759
2023-01-23 02:24:09.435979: step: 2008/530, loss: 0.016420984640717506
2023-01-23 02:24:10.572611: step: 2012/530, loss: 0.011293316259980202
2023-01-23 02:24:11.690252: step: 2016/530, loss: 0.02388370968401432
2023-01-23 02:24:12.805376: step: 2020/530, loss: 0.05840883404016495
2023-01-23 02:24:13.944897: step: 2024/530, loss: 0.017496870830655098
2023-01-23 02:24:15.078363: step: 2028/530, loss: 0.03535033389925957
2023-01-23 02:24:16.210641: step: 2032/530, loss: 0.002891731448471546
2023-01-23 02:24:17.318435: step: 2036/530, loss: 0.04080677032470703
2023-01-23 02:24:18.427214: step: 2040/530, loss: 0.037096213549375534
2023-01-23 02:24:19.549581: step: 2044/530, loss: 0.005787706468254328
2023-01-23 02:24:20.687923: step: 2048/530, loss: 0.0067806243896484375
2023-01-23 02:24:21.844322: step: 2052/530, loss: 0.2756132185459137
2023-01-23 02:24:22.956250: step: 2056/530, loss: 0.06020336225628853
2023-01-23 02:24:24.073278: step: 2060/530, loss: 0.04308032989501953
2023-01-23 02:24:25.231219: step: 2064/530, loss: 0.0013789177173748612
2023-01-23 02:24:26.347815: step: 2068/530, loss: 0.016801167279481888
2023-01-23 02:24:27.488754: step: 2072/530, loss: 0.042267706245183945
2023-01-23 02:24:28.601004: step: 2076/530, loss: 0.0032761571928858757
2023-01-23 02:24:29.745328: step: 2080/530, loss: 0.004434108734130859
2023-01-23 02:24:30.871907: step: 2084/530, loss: 0.0003732681507244706
2023-01-23 02:24:32.028351: step: 2088/530, loss: 0.0034166336990892887
2023-01-23 02:24:33.141572: step: 2092/530, loss: 0.07679310441017151
2023-01-23 02:24:34.297442: step: 2096/530, loss: 0.05839109420776367
2023-01-23 02:24:35.416874: step: 2100/530, loss: 0.002606010530143976
2023-01-23 02:24:36.563482: step: 2104/530, loss: 0.0004708290216512978
2023-01-23 02:24:37.702987: step: 2108/530, loss: 0.012980842962861061
2023-01-23 02:24:38.817044: step: 2112/530, loss: 0.021744156256318092
2023-01-23 02:24:39.964999: step: 2116/530, loss: 0.0007800102466717362
2023-01-23 02:24:41.080622: step: 2120/530, loss: 0.030373573303222656
==================================================
Loss: 0.036
--------------------
Dev: {'event': {'p': 0.57405614714424, 'r': 0.7896138482023968, 'f1': 0.6647982062780268}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
Test: {'event': {'p': 0.5953389830508474, 'r': 0.8028571428571428, 'f1': 0.6836982968369829}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
Chinese: {'event': {'p': 0.5393258426966292, 'r': 0.8888888888888888, 'f1': 0.6713286713286712}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
Korean: {'event': {'p': 0.625, 'r': 0.6349206349206349, 'f1': 0.6299212598425197}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
Russian: {'event': {'p': 0.37254901960784315, 'r': 0.5277777777777778, 'f1': 0.4367816091954023}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Chinese: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Chinese: {'event': {'p': 0.6190476190476191, 'r': 0.9629629629629629, 'f1': 0.7536231884057971}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6288770053475936, 'r': 0.7829560585885486, 'f1': 0.697508896797153}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Korean: {'event': {'p': 0.64058795637743, 'r': 0.772, 'f1': 0.7001813941435606}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Korean: {'event': {'p': 0.6851851851851852, 'r': 0.5873015873015873, 'f1': 0.6324786324786325}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5319148936170213, 'r': 0.6944444444444444, 'f1': 0.6024096385542169}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
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 02:25:22.145676: step: 4/530, loss: 0.015292358584702015
2023-01-23 02:25:23.277064: step: 8/530, loss: 0.00026569367037154734
2023-01-23 02:25:24.413014: step: 12/530, loss: 0.002992343856021762
2023-01-23 02:25:25.556849: step: 16/530, loss: 0.2529309391975403
2023-01-23 02:25:26.680752: step: 20/530, loss: 0.038007546216249466
2023-01-23 02:25:27.805585: step: 24/530, loss: 0.0013069153064861894
2023-01-23 02:25:28.904562: step: 28/530, loss: 0.023984145373106003
2023-01-23 02:25:30.009925: step: 32/530, loss: 0.026635169982910156
2023-01-23 02:25:31.127771: step: 36/530, loss: 0.00894174538552761
2023-01-23 02:25:32.257822: step: 40/530, loss: 0.02837815321981907
2023-01-23 02:25:33.418491: step: 44/530, loss: 0.024371815845370293
2023-01-23 02:25:34.560955: step: 48/530, loss: 0.0006031990051269531
2023-01-23 02:25:35.702952: step: 52/530, loss: 0.004345322027802467
2023-01-23 02:25:36.808889: step: 56/530, loss: 0.0026497840881347656
2023-01-23 02:25:37.926507: step: 60/530, loss: 0.008657646365463734
2023-01-23 02:25:39.017907: step: 64/530, loss: 0.036218974739313126
2023-01-23 02:25:40.140070: step: 68/530, loss: 0.000977325369603932
2023-01-23 02:25:41.255114: step: 72/530, loss: 0.00144443497993052
2023-01-23 02:25:42.418220: step: 76/530, loss: 0.004104423336684704
2023-01-23 02:25:43.554719: step: 80/530, loss: 0.0036943438462913036
2023-01-23 02:25:44.677741: step: 84/530, loss: 0.010357379913330078
2023-01-23 02:25:45.821452: step: 88/530, loss: 0.8404155373573303
2023-01-23 02:25:46.936146: step: 92/530, loss: 0.023323822766542435
2023-01-23 02:25:48.087395: step: 96/530, loss: 0.00033845900907181203
2023-01-23 02:25:49.203706: step: 100/530, loss: 0.019304275512695312
2023-01-23 02:25:50.348689: step: 104/530, loss: 8.61167864059098e-05
2023-01-23 02:25:51.439951: step: 108/530, loss: 0.002255773637443781
2023-01-23 02:25:52.581558: step: 112/530, loss: 0.05083437263965607
2023-01-23 02:25:53.715192: step: 116/530, loss: 0.006120586302131414
2023-01-23 02:25:54.835620: step: 120/530, loss: 0.0011106490856036544
2023-01-23 02:25:55.956699: step: 124/530, loss: 0.582511305809021
2023-01-23 02:25:57.063037: step: 128/530, loss: 0.010121774859726429
2023-01-23 02:25:58.183282: step: 132/530, loss: 0.025431443005800247
2023-01-23 02:25:59.311022: step: 136/530, loss: 0.07729344069957733
2023-01-23 02:26:00.414296: step: 140/530, loss: 0.012636279687285423
2023-01-23 02:26:01.567201: step: 144/530, loss: 0.0013322830200195312
2023-01-23 02:26:02.682786: step: 148/530, loss: 0.01015863474458456
2023-01-23 02:26:03.798906: step: 152/530, loss: 0.001292324042879045
2023-01-23 02:26:04.927296: step: 156/530, loss: 0.00539011973887682
2023-01-23 02:26:06.033093: step: 160/530, loss: 0.0023737431038171053
2023-01-23 02:26:07.195852: step: 164/530, loss: 0.0007633209461346269
2023-01-23 02:26:08.331756: step: 168/530, loss: 0.0025578022468835115
2023-01-23 02:26:09.423858: step: 172/530, loss: 0.001564121339470148
2023-01-23 02:26:10.559720: step: 176/530, loss: 0.27624911069869995
2023-01-23 02:26:11.663805: step: 180/530, loss: 0.010771751403808594
2023-01-23 02:26:12.803175: step: 184/530, loss: 0.005230728071182966
2023-01-23 02:26:13.925054: step: 188/530, loss: 0.004926491063088179
2023-01-23 02:26:15.038589: step: 192/530, loss: 3.519058373058215e-05
2023-01-23 02:26:16.170694: step: 196/530, loss: 0.04157733917236328
2023-01-23 02:26:17.313064: step: 200/530, loss: 0.004698800854384899
2023-01-23 02:26:18.442152: step: 204/530, loss: 0.028289103880524635
2023-01-23 02:26:19.583304: step: 208/530, loss: 0.009384537115693092
2023-01-23 02:26:20.696841: step: 212/530, loss: 0.001333046006038785
2023-01-23 02:26:21.827875: step: 216/530, loss: 0.022342300042510033
2023-01-23 02:26:22.943258: step: 220/530, loss: 0.009606361389160156
2023-01-23 02:26:24.055898: step: 224/530, loss: 0.025665760040283203
2023-01-23 02:26:25.203899: step: 228/530, loss: 0.027713298797607422
2023-01-23 02:26:26.333793: step: 232/530, loss: 0.2112916111946106
2023-01-23 02:26:27.438034: step: 236/530, loss: 0.010000419802963734
2023-01-23 02:26:28.582956: step: 240/530, loss: 0.03228450194001198
2023-01-23 02:26:29.701272: step: 244/530, loss: 4.482269287109375e-05
2023-01-23 02:26:30.825217: step: 248/530, loss: 0.0764358788728714
2023-01-23 02:26:31.974196: step: 252/530, loss: 0.027337217703461647
2023-01-23 02:26:33.132776: step: 256/530, loss: 0.015713881701231003
2023-01-23 02:26:34.255087: step: 260/530, loss: 0.010607052594423294
2023-01-23 02:26:35.373213: step: 264/530, loss: 0.00903863925486803
2023-01-23 02:26:36.464148: step: 268/530, loss: 0.0038719179574400187
2023-01-23 02:26:37.573106: step: 272/530, loss: 0.03119659423828125
2023-01-23 02:26:38.694110: step: 276/530, loss: 0.020299959927797318
2023-01-23 02:26:39.831139: step: 280/530, loss: 0.03040914610028267
2023-01-23 02:26:40.921148: step: 284/530, loss: 0.01949186436831951
2023-01-23 02:26:42.068965: step: 288/530, loss: 0.00021748543076682836
2023-01-23 02:26:43.223770: step: 292/530, loss: 0.02996225468814373
2023-01-23 02:26:44.365126: step: 296/530, loss: 0.04797401651740074
2023-01-23 02:26:45.537531: step: 300/530, loss: 0.012944793328642845
2023-01-23 02:26:46.670842: step: 304/530, loss: 0.0019062042701989412
2023-01-23 02:26:47.819226: step: 308/530, loss: 0.0010084152454510331
2023-01-23 02:26:48.927364: step: 312/530, loss: 0.006839561276137829
2023-01-23 02:26:50.044405: step: 316/530, loss: 0.005239582154899836
2023-01-23 02:26:51.169796: step: 320/530, loss: 0.0025242806877940893
2023-01-23 02:26:52.305893: step: 324/530, loss: 0.5970168709754944
2023-01-23 02:26:53.407814: step: 328/530, loss: 0.015532874502241611
2023-01-23 02:26:54.538907: step: 332/530, loss: 0.023647451773285866
2023-01-23 02:26:55.676921: step: 336/530, loss: 0.006076335906982422
2023-01-23 02:26:56.821172: step: 340/530, loss: 0.07079296559095383
2023-01-23 02:26:57.944045: step: 344/530, loss: 3.89575980079826e-05
2023-01-23 02:26:59.061223: step: 348/530, loss: 0.017483185976743698
2023-01-23 02:27:00.211581: step: 352/530, loss: 0.0016483307117596269
2023-01-23 02:27:01.342820: step: 356/530, loss: 0.006072736345231533
2023-01-23 02:27:02.469256: step: 360/530, loss: 0.004326057620346546
2023-01-23 02:27:03.594610: step: 364/530, loss: 0.011350440792739391
2023-01-23 02:27:04.729153: step: 368/530, loss: 0.014878654852509499
2023-01-23 02:27:05.842778: step: 372/530, loss: 0.001069463905878365
2023-01-23 02:27:06.976722: step: 376/530, loss: 0.04634685441851616
2023-01-23 02:27:08.117821: step: 380/530, loss: 0.05124073103070259
2023-01-23 02:27:09.269895: step: 384/530, loss: 0.030756378546357155
2023-01-23 02:27:10.386866: step: 388/530, loss: 0.0017457485664635897
2023-01-23 02:27:11.524096: step: 392/530, loss: 0.021778490394353867
2023-01-23 02:27:12.673193: step: 396/530, loss: 0.0046524046920239925
2023-01-23 02:27:13.805406: step: 400/530, loss: 0.004118442535400391
2023-01-23 02:27:14.923206: step: 404/530, loss: 0.008835410699248314
2023-01-23 02:27:16.031056: step: 408/530, loss: 0.031606532633304596
2023-01-23 02:27:17.151924: step: 412/530, loss: 0.003976249601691961
2023-01-23 02:27:18.283491: step: 416/530, loss: 0.009182929992675781
2023-01-23 02:27:19.397539: step: 420/530, loss: 0.0003534317365847528
2023-01-23 02:27:20.549948: step: 424/530, loss: 0.013076209463179111
2023-01-23 02:27:21.723278: step: 428/530, loss: 0.010522890836000443
2023-01-23 02:27:22.843434: step: 432/530, loss: 0.010675431229174137
2023-01-23 02:27:23.927779: step: 436/530, loss: 0.036707308143377304
2023-01-23 02:27:25.027085: step: 440/530, loss: 0.009436417371034622
2023-01-23 02:27:26.140570: step: 444/530, loss: 0.021233653649687767
2023-01-23 02:27:27.268078: step: 448/530, loss: 0.00812521018087864
2023-01-23 02:27:28.398597: step: 452/530, loss: 0.0026074410416185856
2023-01-23 02:27:29.554699: step: 456/530, loss: 0.03212928771972656
2023-01-23 02:27:30.672800: step: 460/530, loss: 0.009420204907655716
2023-01-23 02:27:31.781678: step: 464/530, loss: 0.008159256540238857
2023-01-23 02:27:32.910492: step: 468/530, loss: 0.008121872320771217
2023-01-23 02:27:34.022258: step: 472/530, loss: 0.04783668741583824
2023-01-23 02:27:35.159179: step: 476/530, loss: 0.018864108249545097
2023-01-23 02:27:36.294654: step: 480/530, loss: 0.015483103692531586
2023-01-23 02:27:37.434087: step: 484/530, loss: 0.040277671068906784
2023-01-23 02:27:38.548971: step: 488/530, loss: 0.09269017726182938
2023-01-23 02:27:39.669228: step: 492/530, loss: 0.0831671729683876
2023-01-23 02:27:40.790471: step: 496/530, loss: 0.004986572079360485
2023-01-23 02:27:41.909190: step: 500/530, loss: 0.02617473714053631
2023-01-23 02:27:43.023633: step: 504/530, loss: 0.055841825902462006
2023-01-23 02:27:44.152561: step: 508/530, loss: 0.004359626676887274
2023-01-23 02:27:45.295854: step: 512/530, loss: 0.05129947513341904
2023-01-23 02:27:46.440896: step: 516/530, loss: 0.00033016205998137593
2023-01-23 02:27:47.532824: step: 520/530, loss: 0.003555202390998602
2023-01-23 02:27:48.638098: step: 524/530, loss: 0.013533401302993298
2023-01-23 02:27:49.744948: step: 528/530, loss: 0.03858394920825958
2023-01-23 02:27:50.872373: step: 532/530, loss: 0.046680644154548645
2023-01-23 02:27:52.005247: step: 536/530, loss: 0.004794502165168524
2023-01-23 02:27:53.141900: step: 540/530, loss: 0.9126772880554199
2023-01-23 02:27:54.318293: step: 544/530, loss: 0.4460304379463196
2023-01-23 02:27:55.463741: step: 548/530, loss: 0.01091155968606472
2023-01-23 02:27:56.589854: step: 552/530, loss: 0.00333824148401618
2023-01-23 02:27:57.738815: step: 556/530, loss: 0.018437718972563744
2023-01-23 02:27:58.829232: step: 560/530, loss: 0.00156574253924191
2023-01-23 02:27:59.948391: step: 564/530, loss: 0.002931213239207864
2023-01-23 02:28:01.096743: step: 568/530, loss: 0.013604020699858665
2023-01-23 02:28:02.211498: step: 572/530, loss: 0.0710744857788086
2023-01-23 02:28:03.343959: step: 576/530, loss: 0.00013408661470748484
2023-01-23 02:28:04.465465: step: 580/530, loss: 9.021758887683973e-05
2023-01-23 02:28:05.633395: step: 584/530, loss: 0.008456040173768997
2023-01-23 02:28:06.748046: step: 588/530, loss: 0.006662178784608841
2023-01-23 02:28:07.887630: step: 592/530, loss: 0.01610393449664116
2023-01-23 02:28:08.999979: step: 596/530, loss: 0.09527778625488281
2023-01-23 02:28:10.121448: step: 600/530, loss: 0.047502804547548294
2023-01-23 02:28:11.265740: step: 604/530, loss: 0.39616021513938904
2023-01-23 02:28:12.380863: step: 608/530, loss: 6.561278860317543e-05
2023-01-23 02:28:13.550336: step: 612/530, loss: 0.027946854010224342
2023-01-23 02:28:14.667866: step: 616/530, loss: 0.002735137939453125
2023-01-23 02:28:15.809831: step: 620/530, loss: 0.0008907318115234375
2023-01-23 02:28:16.967085: step: 624/530, loss: 0.009626960381865501
2023-01-23 02:28:18.109624: step: 628/530, loss: 0.07941360026597977
2023-01-23 02:28:19.252627: step: 632/530, loss: 0.004505539312958717
2023-01-23 02:28:20.355378: step: 636/530, loss: 0.006349098868668079
2023-01-23 02:28:21.489950: step: 640/530, loss: 0.05294186994433403
2023-01-23 02:28:22.613891: step: 644/530, loss: 0.02378559298813343
2023-01-23 02:28:23.734156: step: 648/530, loss: 0.03638515621423721
2023-01-23 02:28:24.854880: step: 652/530, loss: 0.2197938859462738
2023-01-23 02:28:25.973202: step: 656/530, loss: 0.00023374558077193797
2023-01-23 02:28:27.122760: step: 660/530, loss: 0.018462849780917168
2023-01-23 02:28:28.276653: step: 664/530, loss: 0.020740890875458717
2023-01-23 02:28:29.411996: step: 668/530, loss: 0.007229900453239679
2023-01-23 02:28:30.538192: step: 672/530, loss: 0.0002155303955078125
2023-01-23 02:28:31.649296: step: 676/530, loss: 0.0017820358043536544
2023-01-23 02:28:32.795248: step: 680/530, loss: 0.024843215942382812
2023-01-23 02:28:33.907849: step: 684/530, loss: 0.02043304406106472
2023-01-23 02:28:35.012854: step: 688/530, loss: 0.022045325487852097
2023-01-23 02:28:36.145196: step: 692/530, loss: 0.010693741030991077
2023-01-23 02:28:37.273511: step: 696/530, loss: 0.5845828652381897
2023-01-23 02:28:38.444606: step: 700/530, loss: 0.00490913400426507
2023-01-23 02:28:39.563930: step: 704/530, loss: 0.039392758160829544
2023-01-23 02:28:40.698637: step: 708/530, loss: 0.05005168914794922
2023-01-23 02:28:41.839293: step: 712/530, loss: 0.13192492723464966
2023-01-23 02:28:42.943601: step: 716/530, loss: 0.0031072618439793587
2023-01-23 02:28:44.055935: step: 720/530, loss: 0.032012272626161575
2023-01-23 02:28:45.179209: step: 724/530, loss: 0.03921985626220703
2023-01-23 02:28:46.285975: step: 728/530, loss: 0.008837318047881126
2023-01-23 02:28:47.407752: step: 732/530, loss: 0.003178930375725031
2023-01-23 02:28:48.511980: step: 736/530, loss: 0.0032990456093102694
2023-01-23 02:28:49.639489: step: 740/530, loss: 0.05809302255511284
2023-01-23 02:28:50.781943: step: 744/530, loss: 0.4365171492099762
2023-01-23 02:28:51.902750: step: 748/530, loss: 0.011650276370346546
2023-01-23 02:28:53.004900: step: 752/530, loss: 0.00486335763707757
2023-01-23 02:28:54.086155: step: 756/530, loss: 0.002232837723568082
2023-01-23 02:28:55.184420: step: 760/530, loss: 0.002267384435981512
2023-01-23 02:28:56.310128: step: 764/530, loss: 0.000416040449636057
2023-01-23 02:28:57.464653: step: 768/530, loss: 0.093775175511837
2023-01-23 02:28:58.582262: step: 772/530, loss: 0.0014932631747797132
2023-01-23 02:28:59.697132: step: 776/530, loss: 0.0033706664107739925
2023-01-23 02:29:00.794411: step: 780/530, loss: 0.002823066897690296
2023-01-23 02:29:01.945303: step: 784/530, loss: 0.0004391670227050781
2023-01-23 02:29:03.084203: step: 788/530, loss: 0.00149879464879632
2023-01-23 02:29:04.214841: step: 792/530, loss: 0.027102280408143997
2023-01-23 02:29:05.335743: step: 796/530, loss: 0.00024994611158035696
2023-01-23 02:29:06.443606: step: 800/530, loss: 0.011526107788085938
2023-01-23 02:29:07.552922: step: 804/530, loss: 0.01932373084127903
2023-01-23 02:29:08.653196: step: 808/530, loss: 0.04275193065404892
2023-01-23 02:29:09.789195: step: 812/530, loss: 0.0011491775512695312
2023-01-23 02:29:10.892311: step: 816/530, loss: 0.01269297581166029
2023-01-23 02:29:12.059596: step: 820/530, loss: 0.01688356325030327
2023-01-23 02:29:13.149830: step: 824/530, loss: 0.02442302741110325
2023-01-23 02:29:14.273022: step: 828/530, loss: 1.201629675051663e-05
2023-01-23 02:29:15.423504: step: 832/530, loss: 0.0010560989612713456
2023-01-23 02:29:16.539822: step: 836/530, loss: 0.005330848973244429
2023-01-23 02:29:17.642975: step: 840/530, loss: 0.07421279698610306
2023-01-23 02:29:18.786246: step: 844/530, loss: 0.03576316684484482
2023-01-23 02:29:19.920048: step: 848/530, loss: 0.004836750216782093
2023-01-23 02:29:21.084617: step: 852/530, loss: 0.0076614380814135075
2023-01-23 02:29:22.208082: step: 856/530, loss: 0.14129638671875
2023-01-23 02:29:23.315266: step: 860/530, loss: 0.0008947372552938759
2023-01-23 02:29:24.424838: step: 864/530, loss: 0.008805847726762295
2023-01-23 02:29:25.555327: step: 868/530, loss: 0.004365730099380016
2023-01-23 02:29:26.709755: step: 872/530, loss: 0.005825710482895374
2023-01-23 02:29:27.863427: step: 876/530, loss: 0.0013536453479900956
2023-01-23 02:29:29.005337: step: 880/530, loss: 0.04631233215332031
2023-01-23 02:29:30.144342: step: 884/530, loss: 0.02337360382080078
2023-01-23 02:29:31.255423: step: 888/530, loss: 0.015082931146025658
2023-01-23 02:29:32.389557: step: 892/530, loss: 0.016497422009706497
2023-01-23 02:29:33.516636: step: 896/530, loss: 0.022277260199189186
2023-01-23 02:29:34.654086: step: 900/530, loss: 0.011800384148955345
2023-01-23 02:29:35.789329: step: 904/530, loss: 0.0020702362526208162
2023-01-23 02:29:36.897484: step: 908/530, loss: 0.010740947909653187
2023-01-23 02:29:38.031406: step: 912/530, loss: 0.030042266473174095
2023-01-23 02:29:39.133232: step: 916/530, loss: 0.000881195068359375
2023-01-23 02:29:40.271925: step: 920/530, loss: 0.06256160885095596
2023-01-23 02:29:41.399038: step: 924/530, loss: 0.004214811138808727
2023-01-23 02:29:42.506712: step: 928/530, loss: 0.03674383461475372
2023-01-23 02:29:43.642865: step: 932/530, loss: 0.0001410484401276335
2023-01-23 02:29:44.790573: step: 936/530, loss: 0.005725002381950617
2023-01-23 02:29:45.932968: step: 940/530, loss: 0.02806529961526394
2023-01-23 02:29:47.051698: step: 944/530, loss: 0.005276394076645374
2023-01-23 02:29:48.172866: step: 948/530, loss: 0.03865776211023331
2023-01-23 02:29:49.302450: step: 952/530, loss: 0.018319224938750267
2023-01-23 02:29:50.439424: step: 956/530, loss: 0.15920843183994293
2023-01-23 02:29:51.544129: step: 960/530, loss: 0.0022800446022301912
2023-01-23 02:29:52.694903: step: 964/530, loss: 0.00034961701021529734
2023-01-23 02:29:53.839390: step: 968/530, loss: 0.0007337570423260331
2023-01-23 02:29:54.969970: step: 972/530, loss: 0.0019392013782635331
2023-01-23 02:29:56.108005: step: 976/530, loss: 0.002814674284309149
2023-01-23 02:29:57.233199: step: 980/530, loss: 0.002692151116207242
2023-01-23 02:29:58.362241: step: 984/530, loss: 0.04414090886712074
2023-01-23 02:29:59.477200: step: 988/530, loss: 0.0018574238056316972
2023-01-23 02:30:00.647975: step: 992/530, loss: 0.012186146341264248
2023-01-23 02:30:01.765041: step: 996/530, loss: 0.00014886856661178172
2023-01-23 02:30:02.888280: step: 1000/530, loss: 0.0013407707447186112
2023-01-23 02:30:04.014007: step: 1004/530, loss: 0.009565639309585094
2023-01-23 02:30:05.163989: step: 1008/530, loss: 0.03371448814868927
2023-01-23 02:30:06.296171: step: 1012/530, loss: 0.000559902167879045
2023-01-23 02:30:07.407261: step: 1016/530, loss: 0.0007171511533670127
2023-01-23 02:30:08.495007: step: 1020/530, loss: 0.032666780054569244
2023-01-23 02:30:09.610747: step: 1024/530, loss: 0.0008815765613690019
2023-01-23 02:30:10.747938: step: 1028/530, loss: 0.062098123133182526
2023-01-23 02:30:11.851389: step: 1032/530, loss: 0.006315517704933882
2023-01-23 02:30:12.979194: step: 1036/530, loss: 0.006799602881073952
2023-01-23 02:30:14.096927: step: 1040/530, loss: 0.004569625947624445
2023-01-23 02:30:15.229053: step: 1044/530, loss: 0.013460827060043812
2023-01-23 02:30:16.340381: step: 1048/530, loss: 0.030305862426757812
2023-01-23 02:30:17.480324: step: 1052/530, loss: 0.009350776672363281
2023-01-23 02:30:18.639942: step: 1056/530, loss: 0.008365822024643421
2023-01-23 02:30:19.788573: step: 1060/530, loss: 0.005614662077277899
2023-01-23 02:30:20.916259: step: 1064/530, loss: 0.0524333231151104
2023-01-23 02:30:22.026674: step: 1068/530, loss: 0.0037181854713708162
2023-01-23 02:30:23.162025: step: 1072/530, loss: 0.021323109045624733
2023-01-23 02:30:24.270696: step: 1076/530, loss: 0.015480900183320045
2023-01-23 02:30:25.361747: step: 1080/530, loss: 0.012609672732651234
2023-01-23 02:30:26.575023: step: 1084/530, loss: 0.014031315222382545
2023-01-23 02:30:27.681204: step: 1088/530, loss: 0.00398330669850111
2023-01-23 02:30:28.813898: step: 1092/530, loss: 0.008075237274169922
2023-01-23 02:30:29.911605: step: 1096/530, loss: 0.041944120079278946
2023-01-23 02:30:31.067723: step: 1100/530, loss: 0.0015975951682776213
2023-01-23 02:30:32.205719: step: 1104/530, loss: 0.05503235012292862
2023-01-23 02:30:33.332677: step: 1108/530, loss: 0.004263877868652344
2023-01-23 02:30:34.460997: step: 1112/530, loss: 0.015128898434340954
2023-01-23 02:30:35.597725: step: 1116/530, loss: 0.0086075309664011
2023-01-23 02:30:36.726232: step: 1120/530, loss: 0.01589355617761612
2023-01-23 02:30:37.885746: step: 1124/530, loss: 0.03546085208654404
2023-01-23 02:30:38.997072: step: 1128/530, loss: 0.010693646036088467
2023-01-23 02:30:40.110586: step: 1132/530, loss: 0.004012060351669788
2023-01-23 02:30:41.260920: step: 1136/530, loss: 0.0018407702445983887
2023-01-23 02:30:42.408865: step: 1140/530, loss: 0.0023242949973791838
2023-01-23 02:30:43.530943: step: 1144/530, loss: 0.012179756537079811
2023-01-23 02:30:44.615595: step: 1148/530, loss: 0.0027917863335460424
2023-01-23 02:30:45.744775: step: 1152/530, loss: 0.01964550092816353
2023-01-23 02:30:46.862919: step: 1156/530, loss: 0.049231529235839844
2023-01-23 02:30:48.001658: step: 1160/530, loss: 0.0075706481002271175
2023-01-23 02:30:49.141703: step: 1164/530, loss: 0.1298244446516037
2023-01-23 02:30:50.271703: step: 1168/530, loss: 0.0013109206920489669
2023-01-23 02:30:51.382136: step: 1172/530, loss: 0.016297435387969017
2023-01-23 02:30:52.495597: step: 1176/530, loss: 0.008211469277739525
2023-01-23 02:30:53.627351: step: 1180/530, loss: 0.0010014533763751388
2023-01-23 02:30:54.776147: step: 1184/530, loss: 0.13388614356517792
2023-01-23 02:30:55.898406: step: 1188/530, loss: 0.04209037125110626
2023-01-23 02:30:57.078290: step: 1192/530, loss: 0.03906765207648277
2023-01-23 02:30:58.189169: step: 1196/530, loss: 0.02360248565673828
2023-01-23 02:30:59.334659: step: 1200/530, loss: 0.014113474637269974
2023-01-23 02:31:00.457197: step: 1204/530, loss: 0.0016573906177654862
2023-01-23 02:31:01.604292: step: 1208/530, loss: 0.0651056319475174
2023-01-23 02:31:02.730761: step: 1212/530, loss: 0.013934182934463024
2023-01-23 02:31:03.832031: step: 1216/530, loss: 0.00417594937607646
2023-01-23 02:31:04.960857: step: 1220/530, loss: 0.000713348388671875
2023-01-23 02:31:06.095005: step: 1224/530, loss: 0.018771743401885033
2023-01-23 02:31:07.214664: step: 1228/530, loss: 0.0014384270180016756
2023-01-23 02:31:08.341715: step: 1232/530, loss: 0.015629053115844727
2023-01-23 02:31:09.462701: step: 1236/530, loss: 0.006462669465690851
2023-01-23 02:31:10.561624: step: 1240/530, loss: 0.004350590519607067
2023-01-23 02:31:11.705364: step: 1244/530, loss: 0.048005007207393646
2023-01-23 02:31:12.832812: step: 1248/530, loss: 0.0036044123116880655
2023-01-23 02:31:13.953582: step: 1252/530, loss: 0.00096044538076967
2023-01-23 02:31:15.111515: step: 1256/530, loss: 0.0004400253528729081
2023-01-23 02:31:16.217339: step: 1260/530, loss: 0.021367454901337624
2023-01-23 02:31:17.352810: step: 1264/530, loss: 0.0006041527376510203
2023-01-23 02:31:18.460142: step: 1268/530, loss: 0.03903598710894585
2023-01-23 02:31:19.582654: step: 1272/530, loss: 0.01013789139688015
2023-01-23 02:31:20.705074: step: 1276/530, loss: 0.0046936036087572575
2023-01-23 02:31:21.832188: step: 1280/530, loss: 0.006140995305031538
2023-01-23 02:31:22.965321: step: 1284/530, loss: 0.010223484598100185
2023-01-23 02:31:24.099775: step: 1288/530, loss: 0.07076644897460938
2023-01-23 02:31:25.225076: step: 1292/530, loss: 0.017858220264315605
2023-01-23 02:31:26.351777: step: 1296/530, loss: 0.013049697503447533
2023-01-23 02:31:27.466676: step: 1300/530, loss: 0.012957906350493431
2023-01-23 02:31:28.606974: step: 1304/530, loss: 0.0010457993485033512
2023-01-23 02:31:29.731735: step: 1308/530, loss: -4.38690176451928e-06
2023-01-23 02:31:30.879445: step: 1312/530, loss: 0.013954734429717064
2023-01-23 02:31:31.993241: step: 1316/530, loss: 0.0033947466872632504
2023-01-23 02:31:33.133165: step: 1320/530, loss: 0.06575240939855576
2023-01-23 02:31:34.250591: step: 1324/530, loss: 0.04318585246801376
2023-01-23 02:31:35.364711: step: 1328/530, loss: 0.04382972791790962
2023-01-23 02:31:36.480840: step: 1332/530, loss: 0.0007566451677121222
2023-01-23 02:31:37.634803: step: 1336/530, loss: 0.01949634589254856
2023-01-23 02:31:38.760127: step: 1340/530, loss: 0.010834027081727982
2023-01-23 02:31:39.894254: step: 1344/530, loss: 0.4003015458583832
2023-01-23 02:31:41.049014: step: 1348/530, loss: 0.002799701876938343
2023-01-23 02:31:42.189144: step: 1352/530, loss: 0.005150985904037952
2023-01-23 02:31:43.304158: step: 1356/530, loss: 0.005932617001235485
2023-01-23 02:31:44.426623: step: 1360/530, loss: 0.01842203177511692
2023-01-23 02:31:45.538228: step: 1364/530, loss: 0.0011153221130371094
2023-01-23 02:31:46.657707: step: 1368/530, loss: 0.09692482650279999
2023-01-23 02:31:47.765184: step: 1372/530, loss: 0.011766958050429821
2023-01-23 02:31:48.907580: step: 1376/530, loss: 0.0016706465976312757
2023-01-23 02:31:50.033822: step: 1380/530, loss: 4.839897155761719e-05
2023-01-23 02:31:51.146206: step: 1384/530, loss: 0.011758614331483841
2023-01-23 02:31:52.246427: step: 1388/530, loss: 0.029912948608398438
2023-01-23 02:31:53.383429: step: 1392/530, loss: 0.018086817115545273
2023-01-23 02:31:54.526899: step: 1396/530, loss: 0.0240649227052927
2023-01-23 02:31:55.630826: step: 1400/530, loss: 0.04873094707727432
2023-01-23 02:31:56.765710: step: 1404/530, loss: 0.001138925552368164
2023-01-23 02:31:57.897699: step: 1408/530, loss: 0.02376251295208931
2023-01-23 02:31:59.040171: step: 1412/530, loss: 0.0006364345317706466
2023-01-23 02:32:00.175108: step: 1416/530, loss: 0.06191730499267578
2023-01-23 02:32:01.310136: step: 1420/530, loss: 0.0047851563431322575
2023-01-23 02:32:02.421375: step: 1424/530, loss: 0.04018249362707138
2023-01-23 02:32:03.529684: step: 1428/530, loss: 0.03585944324731827
2023-01-23 02:32:04.665721: step: 1432/530, loss: 0.001352500868961215
2023-01-23 02:32:05.798095: step: 1436/530, loss: 0.7682409286499023
2023-01-23 02:32:06.909758: step: 1440/530, loss: 0.04735374450683594
2023-01-23 02:32:08.023784: step: 1444/530, loss: 0.044617556035518646
2023-01-23 02:32:09.138488: step: 1448/530, loss: 0.1915932148694992
2023-01-23 02:32:10.276385: step: 1452/530, loss: 0.007493495941162109
2023-01-23 02:32:11.402677: step: 1456/530, loss: 0.010313605889678001
2023-01-23 02:32:12.527829: step: 1460/530, loss: 0.003879451658576727
2023-01-23 02:32:13.598803: step: 1464/530, loss: 0.012420511804521084
2023-01-23 02:32:14.730202: step: 1468/530, loss: 0.047693394124507904
2023-01-23 02:32:15.836218: step: 1472/530, loss: 0.01220846176147461
2023-01-23 02:32:16.983593: step: 1476/530, loss: 0.013534116558730602
2023-01-23 02:32:18.120072: step: 1480/530, loss: 0.046292494982481
2023-01-23 02:32:19.254784: step: 1484/530, loss: 5.683898780262098e-05
2023-01-23 02:32:20.402358: step: 1488/530, loss: 0.0736316666007042
2023-01-23 02:32:21.506299: step: 1492/530, loss: 0.18067750334739685
2023-01-23 02:32:22.618940: step: 1496/530, loss: 0.014715098775923252
2023-01-23 02:32:23.747343: step: 1500/530, loss: 0.02805023267865181
2023-01-23 02:32:24.888750: step: 1504/530, loss: 0.0004917144542559981
2023-01-23 02:32:26.012408: step: 1508/530, loss: 0.05224017798900604
2023-01-23 02:32:27.176851: step: 1512/530, loss: 0.008056067861616611
2023-01-23 02:32:28.300731: step: 1516/530, loss: 0.0012901306618005037
2023-01-23 02:32:29.421814: step: 1520/530, loss: 0.017394209280610085
2023-01-23 02:32:30.529821: step: 1524/530, loss: 0.0049024103209376335
2023-01-23 02:32:31.652558: step: 1528/530, loss: 0.05933287367224693
2023-01-23 02:32:32.778833: step: 1532/530, loss: 0.028240490704774857
2023-01-23 02:32:33.901833: step: 1536/530, loss: 0.017984485253691673
2023-01-23 02:32:35.024584: step: 1540/530, loss: 9.322166442871094e-05
2023-01-23 02:32:36.160354: step: 1544/530, loss: 0.004147434141486883
2023-01-23 02:32:37.278199: step: 1548/530, loss: 0.0028263567946851254
2023-01-23 02:32:38.386478: step: 1552/530, loss: 0.002677345182746649
2023-01-23 02:32:39.500226: step: 1556/530, loss: 0.053376391530036926
2023-01-23 02:32:40.641816: step: 1560/530, loss: 0.010211181826889515
2023-01-23 02:32:41.759070: step: 1564/530, loss: 0.05120248720049858
2023-01-23 02:32:42.888229: step: 1568/530, loss: 0.029242707416415215
2023-01-23 02:32:44.030699: step: 1572/530, loss: 0.001630592392757535
2023-01-23 02:32:45.142688: step: 1576/530, loss: 0.013994408771395683
2023-01-23 02:32:46.247388: step: 1580/530, loss: 0.014351654797792435
2023-01-23 02:32:47.373881: step: 1584/530, loss: 0.045104410499334335
2023-01-23 02:32:48.480834: step: 1588/530, loss: 0.00011491775512695312
2023-01-23 02:32:49.645626: step: 1592/530, loss: 0.4080522656440735
2023-01-23 02:32:50.779826: step: 1596/530, loss: 0.008930779062211514
2023-01-23 02:32:51.903515: step: 1600/530, loss: 0.0003186225949320942
2023-01-23 02:32:53.016072: step: 1604/530, loss: 0.0005848884466104209
2023-01-23 02:32:54.128628: step: 1608/530, loss: 0.0009103775373660028
2023-01-23 02:32:55.259915: step: 1612/530, loss: 0.025302886962890625
2023-01-23 02:32:56.383129: step: 1616/530, loss: 0.07699184119701385
2023-01-23 02:32:57.480892: step: 1620/530, loss: 0.004268264397978783
2023-01-23 02:32:58.610513: step: 1624/530, loss: 0.034941770136356354
2023-01-23 02:32:59.735321: step: 1628/530, loss: 0.06112881004810333
2023-01-23 02:33:00.851904: step: 1632/530, loss: 0.050271034240722656
2023-01-23 02:33:02.006126: step: 1636/530, loss: 0.03523597866296768
2023-01-23 02:33:03.123591: step: 1640/530, loss: 0.039323046803474426
2023-01-23 02:33:04.239436: step: 1644/530, loss: 0.0007152557373046875
2023-01-23 02:33:05.387360: step: 1648/530, loss: 0.03070545382797718
2023-01-23 02:33:06.526162: step: 1652/530, loss: 0.0002801895316224545
2023-01-23 02:33:07.632936: step: 1656/530, loss: 0.03340888023376465
2023-01-23 02:33:08.741193: step: 1660/530, loss: 0.03912239149212837
2023-01-23 02:33:09.848913: step: 1664/530, loss: 0.029918670654296875
2023-01-23 02:33:10.976495: step: 1668/530, loss: 0.03626837953925133
2023-01-23 02:33:12.073491: step: 1672/530, loss: 0.00051627162611112
2023-01-23 02:33:13.195140: step: 1676/530, loss: 0.00024852753267623484
2023-01-23 02:33:14.292889: step: 1680/530, loss: 0.10333757847547531
2023-01-23 02:33:15.404419: step: 1684/530, loss: 0.032894037663936615
2023-01-23 02:33:16.513798: step: 1688/530, loss: 0.04468412697315216
2023-01-23 02:33:17.638224: step: 1692/530, loss: 0.06539478898048401
2023-01-23 02:33:18.758494: step: 1696/530, loss: 0.028319358825683594
2023-01-23 02:33:19.884968: step: 1700/530, loss: 0.026014043018221855
2023-01-23 02:33:21.032480: step: 1704/530, loss: 0.02412591129541397
2023-01-23 02:33:22.152811: step: 1708/530, loss: 0.003424358554184437
2023-01-23 02:33:23.288138: step: 1712/530, loss: 0.06916952133178711
2023-01-23 02:33:24.391971: step: 1716/530, loss: 0.018154717981815338
2023-01-23 02:33:25.540376: step: 1720/530, loss: 0.018002605065703392
2023-01-23 02:33:26.640975: step: 1724/530, loss: 0.027803612872958183
2023-01-23 02:33:27.764846: step: 1728/530, loss: 0.029755592346191406
2023-01-23 02:33:28.903569: step: 1732/530, loss: 0.022272396832704544
2023-01-23 02:33:30.029909: step: 1736/530, loss: 0.013708305545151234
2023-01-23 02:33:31.167846: step: 1740/530, loss: 0.010013199411332607
2023-01-23 02:33:32.324717: step: 1744/530, loss: 0.02849132940173149
2023-01-23 02:33:33.449832: step: 1748/530, loss: 0.004912948235869408
2023-01-23 02:33:34.613916: step: 1752/530, loss: 0.02959737740457058
2023-01-23 02:33:35.747539: step: 1756/530, loss: 0.06414385139942169
2023-01-23 02:33:36.907699: step: 1760/530, loss: 0.02694430574774742
2023-01-23 02:33:38.030529: step: 1764/530, loss: 0.007542610168457031
2023-01-23 02:33:39.122469: step: 1768/530, loss: 0.044791363179683685
2023-01-23 02:33:40.259424: step: 1772/530, loss: 0.06140861660242081
2023-01-23 02:33:41.424372: step: 1776/530, loss: 0.007136440370231867
2023-01-23 02:33:42.528760: step: 1780/530, loss: 0.06073713302612305
2023-01-23 02:33:43.685803: step: 1784/530, loss: 0.02201233059167862
2023-01-23 02:33:44.802682: step: 1788/530, loss: 0.14060278236865997
2023-01-23 02:33:45.935427: step: 1792/530, loss: 0.00232276925817132
2023-01-23 02:33:47.087210: step: 1796/530, loss: 0.03365373611450195
2023-01-23 02:33:48.199391: step: 1800/530, loss: 0.006580925080925226
2023-01-23 02:33:49.326799: step: 1804/530, loss: 0.10815596580505371
2023-01-23 02:33:50.443333: step: 1808/530, loss: 0.1154622733592987
2023-01-23 02:33:51.583974: step: 1812/530, loss: 0.005750847049057484
2023-01-23 02:33:52.742070: step: 1816/530, loss: 0.010682869702577591
2023-01-23 02:33:53.827654: step: 1820/530, loss: 0.016840457916259766
2023-01-23 02:33:54.947453: step: 1824/530, loss: 0.0032240867149084806
2023-01-23 02:33:56.090715: step: 1828/530, loss: 0.04145565256476402
2023-01-23 02:33:57.208522: step: 1832/530, loss: 0.011776257306337357
2023-01-23 02:33:58.302405: step: 1836/530, loss: 0.02168302610516548
2023-01-23 02:33:59.414161: step: 1840/530, loss: 0.007101201917976141
2023-01-23 02:34:00.552516: step: 1844/530, loss: 0.011563587933778763
2023-01-23 02:34:01.668275: step: 1848/530, loss: 0.0015417098766192794
2023-01-23 02:34:02.771346: step: 1852/530, loss: 0.023259639739990234
2023-01-23 02:34:03.868927: step: 1856/530, loss: 0.009025287814438343
2023-01-23 02:34:04.985771: step: 1860/530, loss: 0.05360355228185654
2023-01-23 02:34:06.094753: step: 1864/530, loss: 0.07667026668787003
2023-01-23 02:34:07.235559: step: 1868/530, loss: 0.02479849010705948
2023-01-23 02:34:08.376540: step: 1872/530, loss: 0.021096229553222656
2023-01-23 02:34:09.504639: step: 1876/530, loss: 0.025937652215361595
2023-01-23 02:34:10.636013: step: 1880/530, loss: 0.00142841343767941
2023-01-23 02:34:11.774007: step: 1884/530, loss: 0.06055860593914986
2023-01-23 02:34:12.921275: step: 1888/530, loss: 0.02900991216301918
2023-01-23 02:34:14.064866: step: 1892/530, loss: 0.02437887154519558
2023-01-23 02:34:15.154030: step: 1896/530, loss: 0.020090674981474876
2023-01-23 02:34:16.247924: step: 1900/530, loss: 0.0367036834359169
2023-01-23 02:34:17.394799: step: 1904/530, loss: 0.7667005658149719
2023-01-23 02:34:18.523461: step: 1908/530, loss: 0.025771141052246094
2023-01-23 02:34:19.661688: step: 1912/530, loss: 0.0015901147853583097
2023-01-23 02:34:20.779532: step: 1916/530, loss: 0.0046542645432055
2023-01-23 02:34:21.918053: step: 1920/530, loss: 0.008250046521425247
2023-01-23 02:34:23.034393: step: 1924/530, loss: 0.011295031756162643
2023-01-23 02:34:24.165559: step: 1928/530, loss: 0.007999039255082607
2023-01-23 02:34:25.271263: step: 1932/530, loss: 0.0009476662380620837
2023-01-23 02:34:26.398797: step: 1936/530, loss: 0.01576271280646324
2023-01-23 02:34:27.523478: step: 1940/530, loss: 0.016741622239351273
2023-01-23 02:34:28.633175: step: 1944/530, loss: 0.05731058120727539
2023-01-23 02:34:29.770875: step: 1948/530, loss: 0.015318680554628372
2023-01-23 02:34:30.915670: step: 1952/530, loss: 0.005451679695397615
2023-01-23 02:34:32.014626: step: 1956/530, loss: 0.0008780480129644275
2023-01-23 02:34:33.112134: step: 1960/530, loss: 0.024087905883789062
2023-01-23 02:34:34.249126: step: 1964/530, loss: 0.08922433853149414
2023-01-23 02:34:35.369553: step: 1968/530, loss: 0.05738535150885582
2023-01-23 02:34:36.521612: step: 1972/530, loss: 0.0319003127515316
2023-01-23 02:34:37.652701: step: 1976/530, loss: 0.018371202051639557
2023-01-23 02:34:38.770689: step: 1980/530, loss: 0.00092573172878474
2023-01-23 02:34:39.913436: step: 1984/530, loss: 0.01293201558291912
2023-01-23 02:34:41.016332: step: 1988/530, loss: 0.008470535278320312
2023-01-23 02:34:42.145738: step: 1992/530, loss: 0.00740737933665514
2023-01-23 02:34:43.288673: step: 1996/530, loss: 0.0041907308623194695
2023-01-23 02:34:44.407045: step: 2000/530, loss: 0.002651214599609375
2023-01-23 02:34:45.541064: step: 2004/530, loss: 0.0021840096451342106
2023-01-23 02:34:46.674639: step: 2008/530, loss: 0.0011714458232745528
2023-01-23 02:34:47.806269: step: 2012/530, loss: 0.014099788852036
2023-01-23 02:34:48.937495: step: 2016/530, loss: 0.0011686325306072831
2023-01-23 02:34:50.061953: step: 2020/530, loss: 0.020229339599609375
2023-01-23 02:34:51.178620: step: 2024/530, loss: 0.03471355512738228
2023-01-23 02:34:52.324932: step: 2028/530, loss: 0.014459704980254173
2023-01-23 02:34:53.441075: step: 2032/530, loss: 0.007038879673928022
2023-01-23 02:34:54.574409: step: 2036/530, loss: 0.09724826365709305
2023-01-23 02:34:55.704729: step: 2040/530, loss: 0.03464307636022568
2023-01-23 02:34:56.826593: step: 2044/530, loss: 0.005393314640969038
2023-01-23 02:34:57.952808: step: 2048/530, loss: 0.005774307064712048
2023-01-23 02:34:59.070511: step: 2052/530, loss: 0.03452944755554199
2023-01-23 02:35:00.183398: step: 2056/530, loss: 0.0019062042701989412
2023-01-23 02:35:01.278854: step: 2060/530, loss: 0.06154308468103409
2023-01-23 02:35:02.414077: step: 2064/530, loss: 0.00037870407686568797
2023-01-23 02:35:03.550645: step: 2068/530, loss: 0.017535973340272903
2023-01-23 02:35:04.678140: step: 2072/530, loss: 0.0013158798683434725
2023-01-23 02:35:05.814641: step: 2076/530, loss: 0.040188979357481
2023-01-23 02:35:06.938275: step: 2080/530, loss: 0.0002916336234193295
2023-01-23 02:35:08.068207: step: 2084/530, loss: 0.0021088123321533203
2023-01-23 02:35:09.199704: step: 2088/530, loss: 0.02428274229168892
2023-01-23 02:35:10.313682: step: 2092/530, loss: 0.0008046150323934853
2023-01-23 02:35:11.437807: step: 2096/530, loss: 0.02023186907172203
2023-01-23 02:35:12.547932: step: 2100/530, loss: 0.004340457729995251
2023-01-23 02:35:13.675888: step: 2104/530, loss: 0.0037119865883141756
2023-01-23 02:35:14.782481: step: 2108/530, loss: 0.008204841054975986
2023-01-23 02:35:15.927480: step: 2112/530, loss: 0.06804895401000977
2023-01-23 02:35:17.073517: step: 2116/530, loss: 0.013231849297881126
2023-01-23 02:35:18.200893: step: 2120/530, loss: 0.009294414892792702
==================================================
Loss: 0.036
--------------------
Dev: {'event': {'p': 0.6022845275181724, 'r': 0.7723035952063915, 'f1': 0.676779463243874}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
Test: {'event': {'p': 0.6318681318681318, 'r': 0.7885714285714286, 'f1': 0.7015760040671072}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
Chinese: {'event': {'p': 0.5697674418604651, 'r': 0.9074074074074074, 'f1': 0.7}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
Korean: {'event': {'p': 0.7, 'r': 0.5555555555555556, 'f1': 0.6194690265486726}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
Russian: {'event': {'p': 0.45, 'r': 0.5, 'f1': 0.4736842105263158}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Chinese: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Chinese: {'event': {'p': 0.6190476190476191, 'r': 0.9629629629629629, 'f1': 0.7536231884057971}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6288770053475936, 'r': 0.7829560585885486, 'f1': 0.697508896797153}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Korean: {'event': {'p': 0.64058795637743, 'r': 0.772, 'f1': 0.7001813941435606}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Korean: {'event': {'p': 0.6851851851851852, 'r': 0.5873015873015873, 'f1': 0.6324786324786325}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5319148936170213, 'r': 0.6944444444444444, 'f1': 0.6024096385542169}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
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 02:35:59.040487: step: 4/530, loss: 0.021376801654696465
2023-01-23 02:36:00.159036: step: 8/530, loss: 0.01391296461224556
2023-01-23 02:36:01.268988: step: 12/530, loss: 0.047209374606609344
2023-01-23 02:36:02.448369: step: 16/530, loss: 0.005578422453254461
2023-01-23 02:36:03.567099: step: 20/530, loss: 0.00213203439489007
2023-01-23 02:36:04.696430: step: 24/530, loss: 0.02775449864566326
2023-01-23 02:36:05.819701: step: 28/530, loss: 0.0018810272449627519
2023-01-23 02:36:06.959803: step: 32/530, loss: 0.01108322199434042
2023-01-23 02:36:08.060669: step: 36/530, loss: 0.00011758804612327367
2023-01-23 02:36:09.213045: step: 40/530, loss: 0.034690190106630325
2023-01-23 02:36:10.308620: step: 44/530, loss: 0.0009428977500647306
2023-01-23 02:36:11.423707: step: 48/530, loss: 0.024576853960752487
2023-01-23 02:36:12.531539: step: 52/530, loss: 0.001983213471248746
2023-01-23 02:36:13.630355: step: 56/530, loss: 0.004894828889518976
2023-01-23 02:36:14.753495: step: 60/530, loss: 0.008528328500688076
2023-01-23 02:36:15.872036: step: 64/530, loss: 0.0009912491077557206
2023-01-23 02:36:17.000926: step: 68/530, loss: 0.011310959234833717
2023-01-23 02:36:18.101217: step: 72/530, loss: 0.0005329131963662803
2023-01-23 02:36:19.259240: step: 76/530, loss: 0.008119810372591019
2023-01-23 02:36:20.400318: step: 80/530, loss: 0.0006246566772460938
2023-01-23 02:36:21.491098: step: 84/530, loss: 0.0008472918998450041
2023-01-23 02:36:22.618231: step: 88/530, loss: 0.08781089633703232
2023-01-23 02:36:23.722501: step: 92/530, loss: 0.0008754730224609375
2023-01-23 02:36:24.886109: step: 96/530, loss: 0.010413646697998047
2023-01-23 02:36:26.009385: step: 100/530, loss: 0.0020195008255541325
2023-01-23 02:36:27.151304: step: 104/530, loss: 0.006958008278161287
2023-01-23 02:36:28.275266: step: 108/530, loss: 0.0031405449844896793
2023-01-23 02:36:29.396369: step: 112/530, loss: 0.023438643664121628
2023-01-23 02:36:30.541160: step: 116/530, loss: 0.000370025634765625
2023-01-23 02:36:31.679252: step: 120/530, loss: 0.044766999781131744
2023-01-23 02:36:32.837339: step: 124/530, loss: 0.01146621722728014
2023-01-23 02:36:33.941714: step: 128/530, loss: 0.005335998721420765
2023-01-23 02:36:35.075708: step: 132/530, loss: 0.0009471892844885588
2023-01-23 02:36:36.231209: step: 136/530, loss: 0.08883900940418243
2023-01-23 02:36:37.346240: step: 140/530, loss: 0.003948879428207874
2023-01-23 02:36:38.469934: step: 144/530, loss: 0.010422038845717907
2023-01-23 02:36:39.577901: step: 148/530, loss: 0.07162895798683167
2023-01-23 02:36:40.686794: step: 152/530, loss: 0.004631662741303444
2023-01-23 02:36:41.805768: step: 156/530, loss: 0.024773500859737396
2023-01-23 02:36:42.919459: step: 160/530, loss: 0.004440593533217907
2023-01-23 02:36:44.043527: step: 164/530, loss: 0.0001966476411325857
2023-01-23 02:36:45.189940: step: 168/530, loss: 0.049112655222415924
2023-01-23 02:36:46.309939: step: 172/530, loss: 0.015824317932128906
2023-01-23 02:36:47.467597: step: 176/530, loss: 0.004867744632065296
2023-01-23 02:36:48.628801: step: 180/530, loss: 0.0012513160472735763
2023-01-23 02:36:49.735217: step: 184/530, loss: 0.007091092877089977
2023-01-23 02:36:50.892366: step: 188/530, loss: 0.000102996826171875
2023-01-23 02:36:52.008579: step: 192/530, loss: 0.001186370849609375
2023-01-23 02:36:53.185502: step: 196/530, loss: 0.0690065398812294
2023-01-23 02:36:54.283332: step: 200/530, loss: 0.030933953821659088
2023-01-23 02:36:55.387053: step: 204/530, loss: 0.0020143508445471525
2023-01-23 02:36:56.516649: step: 208/530, loss: 0.05099372938275337
2023-01-23 02:36:57.631669: step: 212/530, loss: 0.0025164843536913395
2023-01-23 02:36:58.752742: step: 216/530, loss: 0.0004335403791628778
2023-01-23 02:36:59.866703: step: 220/530, loss: 0.35948413610458374
2023-01-23 02:37:00.981077: step: 224/530, loss: 0.03319816663861275
2023-01-23 02:37:02.148710: step: 228/530, loss: 0.04940204694867134
2023-01-23 02:37:03.246388: step: 232/530, loss: 0.0018831252818927169
2023-01-23 02:37:04.387236: step: 236/530, loss: 0.0030321122612804174
2023-01-23 02:37:05.523506: step: 240/530, loss: 0.006460762117058039
2023-01-23 02:37:06.651992: step: 244/530, loss: 0.0007497787592001259
2023-01-23 02:37:07.799478: step: 248/530, loss: 0.01710362546145916
2023-01-23 02:37:08.907212: step: 252/530, loss: 0.003238201141357422
2023-01-23 02:37:10.039388: step: 256/530, loss: 0.005177593324333429
2023-01-23 02:37:11.177155: step: 260/530, loss: 0.04141349717974663
2023-01-23 02:37:12.332549: step: 264/530, loss: 0.05800752714276314
2023-01-23 02:37:13.462420: step: 268/530, loss: 9.288787987316027e-05
2023-01-23 02:37:14.600290: step: 272/530, loss: 0.08847922831773758
2023-01-23 02:37:15.715855: step: 276/530, loss: 0.02693157084286213
2023-01-23 02:37:16.833985: step: 280/530, loss: 0.009939384646713734
2023-01-23 02:37:17.960520: step: 284/530, loss: 0.05439424514770508
2023-01-23 02:37:19.073367: step: 288/530, loss: 0.010117149911820889
2023-01-23 02:37:20.203837: step: 292/530, loss: 0.0004725456237792969
2023-01-23 02:37:21.303925: step: 296/530, loss: 0.0003830909845419228
2023-01-23 02:37:22.419440: step: 300/530, loss: 0.005652999971061945
2023-01-23 02:37:23.579544: step: 304/530, loss: 0.002002811525017023
2023-01-23 02:37:24.688956: step: 308/530, loss: 0.00045959948329254985
2023-01-23 02:37:25.813716: step: 312/530, loss: 0.060602568089962006
2023-01-23 02:37:26.938897: step: 316/530, loss: 0.0009962081676349044
2023-01-23 02:37:28.076681: step: 320/530, loss: 0.0027749778237193823
2023-01-23 02:37:29.186618: step: 324/530, loss: 0.00012998581223655492
2023-01-23 02:37:30.320564: step: 328/530, loss: 0.052935220301151276
2023-01-23 02:37:31.431590: step: 332/530, loss: 0.0015010833740234375
2023-01-23 02:37:32.590679: step: 336/530, loss: 0.009228706359863281
2023-01-23 02:37:33.707035: step: 340/530, loss: 0.0005983352893963456
2023-01-23 02:37:34.830203: step: 344/530, loss: 0.001098251435905695
2023-01-23 02:37:35.969951: step: 348/530, loss: 0.0018707276321947575
2023-01-23 02:37:37.107828: step: 352/530, loss: 0.0268402099609375
2023-01-23 02:37:38.269244: step: 356/530, loss: 0.0006840705755166709
2023-01-23 02:37:39.402478: step: 360/530, loss: 2.088546534650959e-05
2023-01-23 02:37:40.534420: step: 364/530, loss: 0.03954944387078285
2023-01-23 02:37:41.628591: step: 368/530, loss: 0.003739976789802313
2023-01-23 02:37:42.743378: step: 372/530, loss: 0.000991916749626398
2023-01-23 02:37:43.873231: step: 376/530, loss: 0.004334068391472101
2023-01-23 02:37:44.975834: step: 380/530, loss: 0.009727001190185547
2023-01-23 02:37:46.077620: step: 384/530, loss: 0.137060284614563
2023-01-23 02:37:47.198159: step: 388/530, loss: 2.079009937006049e-05
2023-01-23 02:37:48.315896: step: 392/530, loss: 0.0315219908952713
2023-01-23 02:37:49.471767: step: 396/530, loss: 0.31429120898246765
2023-01-23 02:37:50.590980: step: 400/530, loss: 0.050110626965761185
2023-01-23 02:37:51.710898: step: 404/530, loss: 0.00042238234891556203
2023-01-23 02:37:52.834462: step: 408/530, loss: 0.009432220831513405
2023-01-23 02:37:53.947325: step: 412/530, loss: 0.00604205159470439
2023-01-23 02:37:55.060710: step: 416/530, loss: 0.009143829345703125
2023-01-23 02:37:56.173534: step: 420/530, loss: 0.0012064933544024825
2023-01-23 02:37:57.291847: step: 424/530, loss: 0.04776516184210777
2023-01-23 02:37:58.455955: step: 428/530, loss: 0.026981163769960403
2023-01-23 02:37:59.558904: step: 432/530, loss: 0.0006433010566979647
2023-01-23 02:38:00.698079: step: 436/530, loss: 0.002374935196712613
2023-01-23 02:38:01.839290: step: 440/530, loss: 0.010933113284409046
2023-01-23 02:38:03.007902: step: 444/530, loss: 0.008148575201630592
2023-01-23 02:38:04.189177: step: 448/530, loss: 0.017184162512421608
2023-01-23 02:38:05.314456: step: 452/530, loss: 0.0020130157936364412
2023-01-23 02:38:06.473675: step: 456/530, loss: 0.014023089781403542
2023-01-23 02:38:07.620225: step: 460/530, loss: 0.06027087941765785
2023-01-23 02:38:08.716632: step: 464/530, loss: 0.02288827858865261
2023-01-23 02:38:09.894324: step: 468/530, loss: 0.00015625954256393015
2023-01-23 02:38:11.027463: step: 472/530, loss: 0.023492146283388138
2023-01-23 02:38:12.113473: step: 476/530, loss: 0.02190723456442356
2023-01-23 02:38:13.219394: step: 480/530, loss: 0.00013656617375090718
2023-01-23 02:38:14.348165: step: 484/530, loss: 0.09405479580163956
2023-01-23 02:38:15.480634: step: 488/530, loss: 0.00020732879056595266
2023-01-23 02:38:16.563955: step: 492/530, loss: 0.003944778349250555
2023-01-23 02:38:17.683370: step: 496/530, loss: 0.013114357367157936
2023-01-23 02:38:18.785385: step: 500/530, loss: 4.110336158191785e-05
2023-01-23 02:38:19.905854: step: 504/530, loss: 7.60078473831527e-05
2023-01-23 02:38:21.006190: step: 508/530, loss: 0.0002619743172544986
2023-01-23 02:38:22.144935: step: 512/530, loss: 0.0041793822310864925
2023-01-23 02:38:23.288613: step: 516/530, loss: 0.03414182737469673
2023-01-23 02:38:24.419144: step: 520/530, loss: 0.001016807509586215
2023-01-23 02:38:25.528699: step: 524/530, loss: 0.0018742084503173828
2023-01-23 02:38:26.636543: step: 528/530, loss: 0.04295921325683594
2023-01-23 02:38:27.745296: step: 532/530, loss: 0.009517956525087357
2023-01-23 02:38:28.856337: step: 536/530, loss: 0.0009746550931595266
2023-01-23 02:38:29.994658: step: 540/530, loss: 0.04565925896167755
2023-01-23 02:38:31.123044: step: 544/530, loss: 0.12162236869335175
2023-01-23 02:38:32.247629: step: 548/530, loss: 5.187988426769152e-05
2023-01-23 02:38:33.372353: step: 552/530, loss: 0.020954705774784088
2023-01-23 02:38:34.550362: step: 556/530, loss: 0.0005092620849609375
2023-01-23 02:38:35.681534: step: 560/530, loss: 0.012198067270219326
2023-01-23 02:38:36.805424: step: 564/530, loss: 0.009385108947753906
2023-01-23 02:38:37.909865: step: 568/530, loss: 0.030081558972597122
2023-01-23 02:38:39.031795: step: 572/530, loss: 0.12272453308105469
2023-01-23 02:38:40.162547: step: 576/530, loss: 0.04121856763958931
2023-01-23 02:38:41.290417: step: 580/530, loss: 1.3399124327406753e-05
2023-01-23 02:38:42.425581: step: 584/530, loss: 0.06907663494348526
2023-01-23 02:38:43.554854: step: 588/530, loss: 0.0247024055570364
2023-01-23 02:38:44.699352: step: 592/530, loss: 0.0027711871080100536
2023-01-23 02:38:45.857826: step: 596/530, loss: 0.015142488293349743
2023-01-23 02:38:46.988889: step: 600/530, loss: 0.03383655473589897
2023-01-23 02:38:48.098225: step: 604/530, loss: 0.04236316680908203
2023-01-23 02:38:49.215021: step: 608/530, loss: 0.015430832281708717
2023-01-23 02:38:50.345423: step: 612/530, loss: 0.0033058645203709602
2023-01-23 02:38:51.471600: step: 616/530, loss: 0.5328415632247925
2023-01-23 02:38:52.618302: step: 620/530, loss: 0.0005355835310183465
2023-01-23 02:38:53.746633: step: 624/530, loss: 0.03737277910113335
2023-01-23 02:38:54.874491: step: 628/530, loss: 0.017632579430937767
2023-01-23 02:38:56.007760: step: 632/530, loss: 0.005974388215690851
2023-01-23 02:38:57.155648: step: 636/530, loss: 0.048528481274843216
2023-01-23 02:38:58.306412: step: 640/530, loss: 0.02683448977768421
2023-01-23 02:38:59.424997: step: 644/530, loss: 0.00026149750920012593
2023-01-23 02:39:00.529729: step: 648/530, loss: 0.05040605366230011
2023-01-23 02:39:01.679767: step: 652/530, loss: 0.014464568346738815
2023-01-23 02:39:02.810570: step: 656/530, loss: 0.02264528162777424
2023-01-23 02:39:03.900442: step: 660/530, loss: 0.012154579162597656
2023-01-23 02:39:05.040254: step: 664/530, loss: 0.004620837979018688
2023-01-23 02:39:06.176602: step: 668/530, loss: 0.009050989523530006
2023-01-23 02:39:07.289550: step: 672/530, loss: 0.060083627700805664
2023-01-23 02:39:08.421254: step: 676/530, loss: 0.010952567681670189
2023-01-23 02:39:09.549592: step: 680/530, loss: 0.0549686923623085
2023-01-23 02:39:10.662428: step: 684/530, loss: 0.008303356356918812
2023-01-23 02:39:11.790129: step: 688/530, loss: 0.015359687618911266
2023-01-23 02:39:12.911022: step: 692/530, loss: 0.004053687676787376
2023-01-23 02:39:14.015995: step: 696/530, loss: 0.08860655128955841
2023-01-23 02:39:15.148346: step: 700/530, loss: 0.027171609923243523
2023-01-23 02:39:16.299834: step: 704/530, loss: 0.023876572027802467
2023-01-23 02:39:17.419490: step: 708/530, loss: 0.00023996829986572266
2023-01-23 02:39:18.566304: step: 712/530, loss: 0.07328624278306961
2023-01-23 02:39:19.686756: step: 716/530, loss: 0.012323093600571156
2023-01-23 02:39:20.803336: step: 720/530, loss: 1.506805438111769e-05
2023-01-23 02:39:21.953920: step: 724/530, loss: 0.0019681931007653475
2023-01-23 02:39:23.063732: step: 728/530, loss: 0.04083900526165962
2023-01-23 02:39:24.198034: step: 732/530, loss: 0.00083160400390625
2023-01-23 02:39:25.279902: step: 736/530, loss: 0.0021749495062977076
2023-01-23 02:39:26.399695: step: 740/530, loss: 0.6249213814735413
2023-01-23 02:39:27.536904: step: 744/530, loss: 0.01030359324067831
2023-01-23 02:39:28.679742: step: 748/530, loss: 0.032086946070194244
2023-01-23 02:39:29.800663: step: 752/530, loss: 0.04258289560675621
2023-01-23 02:39:30.924561: step: 756/530, loss: 0.0042785643599927425
2023-01-23 02:39:32.045113: step: 760/530, loss: 0.023368073627352715
2023-01-23 02:39:33.174226: step: 764/530, loss: 0.0016337394481524825
2023-01-23 02:39:34.302849: step: 768/530, loss: 0.010141182690858841
2023-01-23 02:39:35.427193: step: 772/530, loss: 0.036923836916685104
2023-01-23 02:39:36.549410: step: 776/530, loss: 0.0028108598198741674
2023-01-23 02:39:37.678578: step: 780/530, loss: 0.008792877197265625
2023-01-23 02:39:38.785941: step: 784/530, loss: 0.008434963412582874
2023-01-23 02:39:39.920863: step: 788/530, loss: 0.000682878540828824
2023-01-23 02:39:41.035226: step: 792/530, loss: 0.023146821185946465
2023-01-23 02:39:42.136455: step: 796/530, loss: 0.0013587952125817537
2023-01-23 02:39:43.245031: step: 800/530, loss: 0.003368377685546875
2023-01-23 02:39:44.341800: step: 804/530, loss: 0.0010303497547283769
2023-01-23 02:39:45.482210: step: 808/530, loss: 0.029104378074407578
2023-01-23 02:39:46.594357: step: 812/530, loss: 0.011813045479357243
2023-01-23 02:39:47.711102: step: 816/530, loss: 0.0013019561301916838
2023-01-23 02:39:48.842286: step: 820/530, loss: 0.14663906395435333
2023-01-23 02:39:49.962508: step: 824/530, loss: 0.0009376525995321572
2023-01-23 02:39:51.100345: step: 828/530, loss: 0.03287782520055771
2023-01-23 02:39:52.220694: step: 832/530, loss: 0.04450864717364311
2023-01-23 02:39:53.351555: step: 836/530, loss: 0.04730501398444176
2023-01-23 02:39:54.483605: step: 840/530, loss: 0.030045129358768463
2023-01-23 02:39:55.610244: step: 844/530, loss: 0.000533247017301619
2023-01-23 02:39:56.731376: step: 848/530, loss: 0.047948360443115234
2023-01-23 02:39:57.865579: step: 852/530, loss: 0.08938980102539062
2023-01-23 02:39:58.992976: step: 856/530, loss: 0.07054892182350159
2023-01-23 02:40:00.140063: step: 860/530, loss: 0.0005337238544598222
2023-01-23 02:40:01.288606: step: 864/530, loss: 0.0001386642543366179
2023-01-23 02:40:02.403053: step: 868/530, loss: 0.0003506660577841103
2023-01-23 02:40:03.535160: step: 872/530, loss: 0.025488808751106262
2023-01-23 02:40:04.672286: step: 876/530, loss: 0.27946898341178894
2023-01-23 02:40:05.764204: step: 880/530, loss: 0.0014894991181790829
2023-01-23 02:40:06.892547: step: 884/530, loss: 0.023252295330166817
2023-01-23 02:40:08.100298: step: 888/530, loss: 0.0004966736305505037
2023-01-23 02:40:09.266480: step: 892/530, loss: 0.09113006293773651
2023-01-23 02:40:10.362085: step: 896/530, loss: 0.0002075195370707661
2023-01-23 02:40:11.470555: step: 900/530, loss: 0.01126957032829523
2023-01-23 02:40:12.607297: step: 904/530, loss: 0.005335331428796053
2023-01-23 02:40:13.705700: step: 908/530, loss: 0.0017627717461436987
2023-01-23 02:40:14.846561: step: 912/530, loss: 0.00624008197337389
2023-01-23 02:40:15.960390: step: 916/530, loss: 0.003267192980274558
2023-01-23 02:40:17.064446: step: 920/530, loss: 0.0027115822304040194
2023-01-23 02:40:18.224789: step: 924/530, loss: 0.022049523890018463
2023-01-23 02:40:19.357470: step: 928/530, loss: 0.03569812700152397
2023-01-23 02:40:20.501004: step: 932/530, loss: 0.019016314297914505
2023-01-23 02:40:21.630038: step: 936/530, loss: 0.004714870825409889
2023-01-23 02:40:22.735352: step: 940/530, loss: 0.0004932403680868447
2023-01-23 02:40:23.871821: step: 944/530, loss: 0.0004512786981649697
2023-01-23 02:40:24.998297: step: 948/530, loss: 0.0046829222701489925
2023-01-23 02:40:26.154453: step: 952/530, loss: 0.004527711775153875
2023-01-23 02:40:27.282577: step: 956/530, loss: 0.009902680292725563
2023-01-23 02:40:28.384141: step: 960/530, loss: 3.952979750465602e-05
2023-01-23 02:40:29.532663: step: 964/530, loss: 0.0009933471446856856
2023-01-23 02:40:30.656546: step: 968/530, loss: 2.460479663568549e-05
2023-01-23 02:40:31.779768: step: 972/530, loss: 0.0016342162853106856
2023-01-23 02:40:32.942378: step: 976/530, loss: 0.005700302310287952
2023-01-23 02:40:34.036631: step: 980/530, loss: 0.0005764007801190019
2023-01-23 02:40:35.180719: step: 984/530, loss: 0.025848103687167168
2023-01-23 02:40:36.313684: step: 988/530, loss: 0.005493068601936102
2023-01-23 02:40:37.406522: step: 992/530, loss: 0.0025004863273352385
2023-01-23 02:40:38.534964: step: 996/530, loss: 0.001981067704036832
2023-01-23 02:40:39.661895: step: 1000/530, loss: 0.07185673713684082
2023-01-23 02:40:40.788935: step: 1004/530, loss: 0.4234001040458679
2023-01-23 02:40:41.887838: step: 1008/530, loss: 0.00034656524076126516
2023-01-23 02:40:42.999166: step: 1012/530, loss: 0.19825291633605957
2023-01-23 02:40:44.135163: step: 1016/530, loss: 0.008284568786621094
2023-01-23 02:40:45.240368: step: 1020/530, loss: 0.020164204761385918
2023-01-23 02:40:46.348104: step: 1024/530, loss: 0.010042286477982998
2023-01-23 02:40:47.467493: step: 1028/530, loss: 0.04541950300335884
2023-01-23 02:40:48.593128: step: 1032/530, loss: 0.03394145891070366
2023-01-23 02:40:49.713348: step: 1036/530, loss: 0.005318164825439453
2023-01-23 02:40:50.843382: step: 1040/530, loss: 0.018819905817508698
2023-01-23 02:40:51.968942: step: 1044/530, loss: 0.02320117875933647
2023-01-23 02:40:53.135458: step: 1048/530, loss: 0.00689043989405036
2023-01-23 02:40:54.266848: step: 1052/530, loss: 0.012432575225830078
2023-01-23 02:40:55.370757: step: 1056/530, loss: 0.0007476091268472373
2023-01-23 02:40:56.478540: step: 1060/530, loss: 0.0055480957962572575
2023-01-23 02:40:57.575189: step: 1064/530, loss: 0.006934452336281538
2023-01-23 02:40:58.706315: step: 1068/530, loss: 0.00020937919907737523
2023-01-23 02:40:59.848175: step: 1072/530, loss: 0.004772853571921587
2023-01-23 02:41:00.995357: step: 1076/530, loss: 0.004951858427375555
2023-01-23 02:41:02.152125: step: 1080/530, loss: 0.1476408988237381
2023-01-23 02:41:03.285717: step: 1084/530, loss: 0.05446682125329971
2023-01-23 02:41:04.425987: step: 1088/530, loss: 0.000392913818359375
2023-01-23 02:41:05.581035: step: 1092/530, loss: 0.06331367790699005
2023-01-23 02:41:06.683441: step: 1096/530, loss: 0.00222015380859375
2023-01-23 02:41:07.854975: step: 1100/530, loss: 0.0012237548362463713
2023-01-23 02:41:08.979858: step: 1104/530, loss: 2.47955322265625e-05
2023-01-23 02:41:10.109701: step: 1108/530, loss: 0.050952911376953125
2023-01-23 02:41:11.225311: step: 1112/530, loss: 0.04225749894976616
2023-01-23 02:41:12.347107: step: 1116/530, loss: 0.00017862320237327367
2023-01-23 02:41:13.477583: step: 1120/530, loss: 0.004182243719696999
2023-01-23 02:41:14.584776: step: 1124/530, loss: 0.00011167526827193797
2023-01-23 02:41:15.758321: step: 1128/530, loss: 0.24516411125659943
2023-01-23 02:41:16.877530: step: 1132/530, loss: 0.0318724662065506
2023-01-23 02:41:17.984947: step: 1136/530, loss: 0.1067424789071083
2023-01-23 02:41:19.150471: step: 1140/530, loss: 0.03593912348151207
2023-01-23 02:41:20.285859: step: 1144/530, loss: 0.0009889602661132812
2023-01-23 02:41:21.417929: step: 1148/530, loss: 0.03031158447265625
2023-01-23 02:41:22.508353: step: 1152/530, loss: 0.0592309944331646
2023-01-23 02:41:23.594960: step: 1156/530, loss: 0.00394515972584486
2023-01-23 02:41:24.712079: step: 1160/530, loss: 0.0005672455299645662
2023-01-23 02:41:25.824025: step: 1164/530, loss: 6.866455805720761e-05
2023-01-23 02:41:26.962935: step: 1168/530, loss: -1.182556115963962e-05
2023-01-23 02:41:28.087901: step: 1172/530, loss: 0.009155083447694778
2023-01-23 02:41:29.235850: step: 1176/530, loss: 0.0763792097568512
2023-01-23 02:41:30.380266: step: 1180/530, loss: 0.008555984124541283
2023-01-23 02:41:31.491525: step: 1184/530, loss: 0.0500640869140625
2023-01-23 02:41:32.595344: step: 1188/530, loss: 0.007271385286003351
2023-01-23 02:41:33.702520: step: 1192/530, loss: 0.02011279948055744
2023-01-23 02:41:34.846094: step: 1196/530, loss: 0.0688135176897049
2023-01-23 02:41:35.952127: step: 1200/530, loss: 0.04294218868017197
2023-01-23 02:41:37.110178: step: 1204/530, loss: 0.0026073455810546875
2023-01-23 02:41:38.245929: step: 1208/530, loss: 0.01093745231628418
2023-01-23 02:41:39.375425: step: 1212/530, loss: 0.0697048157453537
2023-01-23 02:41:40.473021: step: 1216/530, loss: 0.3891034424304962
2023-01-23 02:41:41.603223: step: 1220/530, loss: 0.011217307299375534
2023-01-23 02:41:42.712663: step: 1224/530, loss: 0.017900992184877396
2023-01-23 02:41:43.827726: step: 1228/530, loss: 0.0010059833293780684
2023-01-23 02:41:44.981085: step: 1232/530, loss: 0.012778043746948242
2023-01-23 02:41:46.095719: step: 1236/530, loss: 0.012760019861161709
2023-01-23 02:41:47.214905: step: 1240/530, loss: 0.057823631912469864
2023-01-23 02:41:48.347173: step: 1244/530, loss: 0.048862457275390625
2023-01-23 02:41:49.492586: step: 1248/530, loss: 0.089727021753788
2023-01-23 02:41:50.615485: step: 1252/530, loss: 0.013313102535903454
2023-01-23 02:41:51.757760: step: 1256/530, loss: 0.06653575599193573
2023-01-23 02:41:52.874442: step: 1260/530, loss: 0.022565318271517754
2023-01-23 02:41:53.998048: step: 1264/530, loss: 0.020505428314208984
2023-01-23 02:41:55.119394: step: 1268/530, loss: 0.013241958804428577
2023-01-23 02:41:56.267944: step: 1272/530, loss: 0.009296322241425514
2023-01-23 02:41:57.381540: step: 1276/530, loss: 0.05469541624188423
2023-01-23 02:41:58.510679: step: 1280/530, loss: 0.003972244448959827
2023-01-23 02:41:59.621620: step: 1284/530, loss: 0.00020618439884856343
2023-01-23 02:42:00.742336: step: 1288/530, loss: 0.0023051260504871607
2023-01-23 02:42:01.867466: step: 1292/530, loss: 0.03743896633386612
2023-01-23 02:42:02.992696: step: 1296/530, loss: 0.003361702198162675
2023-01-23 02:42:04.134686: step: 1300/530, loss: 0.0012639999622479081
2023-01-23 02:42:05.284216: step: 1304/530, loss: 0.0017868519062176347
2023-01-23 02:42:06.383843: step: 1308/530, loss: 0.0005592346424236894
2023-01-23 02:42:07.497248: step: 1312/530, loss: 0.05702686309814453
2023-01-23 02:42:08.627331: step: 1316/530, loss: 0.001959848450496793
2023-01-23 02:42:09.769453: step: 1320/530, loss: 0.00011930465552723035
2023-01-23 02:42:10.928059: step: 1324/530, loss: 0.05461826175451279
2023-01-23 02:42:12.047934: step: 1328/530, loss: 0.013545417226850986
2023-01-23 02:42:13.165902: step: 1332/530, loss: 0.11116848140954971
2023-01-23 02:42:14.276533: step: 1336/530, loss: 0.0016939162742346525
2023-01-23 02:42:15.403976: step: 1340/530, loss: 0.021041106432676315
2023-01-23 02:42:16.533032: step: 1344/530, loss: 0.03249244764447212
2023-01-23 02:42:17.701008: step: 1348/530, loss: 0.0161272045224905
2023-01-23 02:42:18.831607: step: 1352/530, loss: 0.03644008934497833
2023-01-23 02:42:19.955954: step: 1356/530, loss: 0.029905986040830612
2023-01-23 02:42:21.074546: step: 1360/530, loss: 0.010708236135542393
2023-01-23 02:42:22.235775: step: 1364/530, loss: 0.04342212527990341
2023-01-23 02:42:23.352156: step: 1368/530, loss: 0.013961220160126686
2023-01-23 02:42:24.460803: step: 1372/530, loss: 0.0029222487937659025
2023-01-23 02:42:25.571013: step: 1376/530, loss: 0.019478321075439453
2023-01-23 02:42:26.685643: step: 1380/530, loss: 0.009981346316635609
2023-01-23 02:42:27.810776: step: 1384/530, loss: 0.06494884192943573
2023-01-23 02:42:28.921279: step: 1388/530, loss: 0.0041595459915697575
2023-01-23 02:42:30.040798: step: 1392/530, loss: 0.00019254683866165578
2023-01-23 02:42:31.158666: step: 1396/530, loss: 0.001980805303901434
2023-01-23 02:42:32.309811: step: 1400/530, loss: 0.0058116912841796875
2023-01-23 02:42:33.444828: step: 1404/530, loss: 0.03374233469367027
2023-01-23 02:42:34.554285: step: 1408/530, loss: 0.007123374845832586
2023-01-23 02:42:35.675998: step: 1412/530, loss: 0.002434301422908902
2023-01-23 02:42:36.812399: step: 1416/530, loss: 0.01960582658648491
2023-01-23 02:42:37.924592: step: 1420/530, loss: 0.03069124184548855
2023-01-23 02:42:39.038180: step: 1424/530, loss: 0.05376854166388512
2023-01-23 02:42:40.164066: step: 1428/530, loss: 3.280639793956652e-05
2023-01-23 02:42:41.288133: step: 1432/530, loss: 0.29156073927879333
2023-01-23 02:42:42.406102: step: 1436/530, loss: 0.0010064125526696444
2023-01-23 02:42:43.502845: step: 1440/530, loss: 0.016932297497987747
2023-01-23 02:42:44.610907: step: 1444/530, loss: 2.2792815798311494e-05
2023-01-23 02:42:45.759096: step: 1448/530, loss: 0.00266609201207757
2023-01-23 02:42:46.907653: step: 1452/530, loss: 0.0023176195099949837
2023-01-23 02:42:48.021322: step: 1456/530, loss: 0.002462196396663785
2023-01-23 02:42:49.110364: step: 1460/530, loss: 0.0015404701698571444
2023-01-23 02:42:50.213147: step: 1464/530, loss: 0.00019922255887649953
2023-01-23 02:42:51.345158: step: 1468/530, loss: 0.0035831450950354338
2023-01-23 02:42:52.500030: step: 1472/530, loss: 0.012120532803237438
2023-01-23 02:42:53.621287: step: 1476/530, loss: 0.0002880096435546875
2023-01-23 02:42:54.743622: step: 1480/530, loss: 0.004423332400619984
2023-01-23 02:42:55.867201: step: 1484/530, loss: 0.004905891139060259
2023-01-23 02:42:56.995401: step: 1488/530, loss: 0.0012183189392089844
2023-01-23 02:42:58.112429: step: 1492/530, loss: 0.05871410667896271
2023-01-23 02:42:59.243484: step: 1496/530, loss: 0.1794639676809311
2023-01-23 02:43:00.356951: step: 1500/530, loss: 0.048838332295417786
2023-01-23 02:43:01.485533: step: 1504/530, loss: 0.00937876757234335
2023-01-23 02:43:02.622565: step: 1508/530, loss: 0.07528610527515411
2023-01-23 02:43:03.759468: step: 1512/530, loss: 0.04521942511200905
2023-01-23 02:43:04.900012: step: 1516/530, loss: 0.009680652990937233
2023-01-23 02:43:06.036579: step: 1520/530, loss: 0.00779800396412611
2023-01-23 02:43:07.153319: step: 1524/530, loss: 0.2331068068742752
2023-01-23 02:43:08.268935: step: 1528/530, loss: 5.064010474598035e-05
2023-01-23 02:43:09.365269: step: 1532/530, loss: 0.05807342752814293
2023-01-23 02:43:10.496152: step: 1536/530, loss: 0.0001390457182424143
2023-01-23 02:43:11.632985: step: 1540/530, loss: 0.0031814100220799446
2023-01-23 02:43:12.759512: step: 1544/530, loss: 0.023312855511903763
2023-01-23 02:43:13.865067: step: 1548/530, loss: 0.016035079956054688
2023-01-23 02:43:15.009441: step: 1552/530, loss: 0.00011692046973621473
2023-01-23 02:43:16.113854: step: 1556/530, loss: 0.0001737594575388357
2023-01-23 02:43:17.241140: step: 1560/530, loss: 0.053319789469242096
2023-01-23 02:43:18.378420: step: 1564/530, loss: 0.025724982842803
2023-01-23 02:43:19.560699: step: 1568/530, loss: 0.00043697358341887593
2023-01-23 02:43:20.687933: step: 1572/530, loss: 0.0449950248003006
2023-01-23 02:43:21.808939: step: 1576/530, loss: 0.00134449009783566
2023-01-23 02:43:22.950872: step: 1580/530, loss: 0.008546257391571999
2023-01-23 02:43:24.065480: step: 1584/530, loss: 0.003720760578289628
2023-01-23 02:43:25.233767: step: 1588/530, loss: 0.026486970484256744
2023-01-23 02:43:26.345611: step: 1592/530, loss: 0.0810934528708458
2023-01-23 02:43:27.476405: step: 1596/530, loss: 0.07892217487096786
2023-01-23 02:43:28.608465: step: 1600/530, loss: 0.0626898780465126
2023-01-23 02:43:29.719061: step: 1604/530, loss: 0.020459746941924095
2023-01-23 02:43:30.852450: step: 1608/530, loss: 0.003245449159294367
2023-01-23 02:43:31.972737: step: 1612/530, loss: 0.015804052352905273
2023-01-23 02:43:33.157335: step: 1616/530, loss: 0.02175426483154297
2023-01-23 02:43:34.284689: step: 1620/530, loss: 0.005942916963249445
2023-01-23 02:43:35.423994: step: 1624/530, loss: 0.03407726436853409
2023-01-23 02:43:36.552331: step: 1628/530, loss: 0.0007228851318359375
2023-01-23 02:43:37.688679: step: 1632/530, loss: 0.05168113857507706
2023-01-23 02:43:38.801780: step: 1636/530, loss: 0.0023353577125817537
2023-01-23 02:43:39.918603: step: 1640/530, loss: 0.05115985870361328
2023-01-23 02:43:41.068832: step: 1644/530, loss: 0.002491426421329379
2023-01-23 02:43:42.171408: step: 1648/530, loss: 0.0030633925925940275
2023-01-23 02:43:43.292327: step: 1652/530, loss: 0.009731292724609375
2023-01-23 02:43:44.435563: step: 1656/530, loss: 0.017003823071718216
2023-01-23 02:43:45.567752: step: 1660/530, loss: 0.06108655780553818
2023-01-23 02:43:46.677151: step: 1664/530, loss: 0.0021059035789221525
2023-01-23 02:43:47.823320: step: 1668/530, loss: 0.004141617100685835
2023-01-23 02:43:48.949121: step: 1672/530, loss: 0.035585831850767136
2023-01-23 02:43:50.080864: step: 1676/530, loss: 0.03586731106042862
2023-01-23 02:43:51.258158: step: 1680/530, loss: 0.0021348954178392887
2023-01-23 02:43:52.420738: step: 1684/530, loss: 0.017817020416259766
2023-01-23 02:43:53.543416: step: 1688/530, loss: 0.02136058919131756
2023-01-23 02:43:54.660388: step: 1692/530, loss: 0.04454679787158966
2023-01-23 02:43:55.746708: step: 1696/530, loss: 0.00857851468026638
2023-01-23 02:43:56.896062: step: 1700/530, loss: 0.053299762308597565
2023-01-23 02:43:58.044459: step: 1704/530, loss: 0.015199661254882812
2023-01-23 02:43:59.168475: step: 1708/530, loss: 0.017504120245575905
2023-01-23 02:44:00.301232: step: 1712/530, loss: 0.0019131660228595138
2023-01-23 02:44:01.406151: step: 1716/530, loss: 0.0006999016040936112
2023-01-23 02:44:02.587683: step: 1720/530, loss: 0.014224052429199219
2023-01-23 02:44:03.731054: step: 1724/530, loss: 0.002784347627311945
2023-01-23 02:44:04.855792: step: 1728/530, loss: 0.019688988104462624
2023-01-23 02:44:05.975525: step: 1732/530, loss: 0.004349899478256702
2023-01-23 02:44:07.109690: step: 1736/530, loss: 0.0033686638344079256
2023-01-23 02:44:08.233792: step: 1740/530, loss: 0.011678695678710938
2023-01-23 02:44:09.340919: step: 1744/530, loss: 0.036286164075136185
2023-01-23 02:44:10.484131: step: 1748/530, loss: 0.00017337800818495452
2023-01-23 02:44:11.606009: step: 1752/530, loss: 0.0018768310546875
2023-01-23 02:44:12.727642: step: 1756/530, loss: 0.04755065590143204
2023-01-23 02:44:13.872054: step: 1760/530, loss: 0.03820991516113281
2023-01-23 02:44:14.982647: step: 1764/530, loss: 0.0008551597711630166
2023-01-23 02:44:16.136647: step: 1768/530, loss: 0.003847789950668812
2023-01-23 02:44:17.253047: step: 1772/530, loss: 0.003237438155338168
2023-01-23 02:44:18.372171: step: 1776/530, loss: 0.00023202896409202367
2023-01-23 02:44:19.532665: step: 1780/530, loss: 0.04678459092974663
2023-01-23 02:44:20.651215: step: 1784/530, loss: 0.0011911392211914062
2023-01-23 02:44:21.821595: step: 1788/530, loss: 0.05273570865392685
2023-01-23 02:44:22.926656: step: 1792/530, loss: 0.011806010268628597
2023-01-23 02:44:24.062072: step: 1796/530, loss: 0.018580103293061256
2023-01-23 02:44:25.185921: step: 1800/530, loss: 0.0010605811839923263
2023-01-23 02:44:26.307537: step: 1804/530, loss: 0.07782287895679474
2023-01-23 02:44:27.441892: step: 1808/530, loss: 0.006934165954589844
2023-01-23 02:44:28.544450: step: 1812/530, loss: 0.06661901623010635
2023-01-23 02:44:29.652128: step: 1816/530, loss: 0.005472755525261164
2023-01-23 02:44:30.777466: step: 1820/530, loss: 0.0033046724274754524
2023-01-23 02:44:31.882775: step: 1824/530, loss: 0.004302788060158491
2023-01-23 02:44:33.020019: step: 1828/530, loss: 0.0441526398062706
2023-01-23 02:44:34.135044: step: 1832/530, loss: 0.019944049417972565
2023-01-23 02:44:35.271016: step: 1836/530, loss: 0.0746222510933876
2023-01-23 02:44:36.384718: step: 1840/530, loss: 0.004243755247443914
2023-01-23 02:44:37.522678: step: 1844/530, loss: 0.0036203383933752775
2023-01-23 02:44:38.647941: step: 1848/530, loss: 0.0005895614740438759
2023-01-23 02:44:39.768735: step: 1852/530, loss: 0.035605430603027344
2023-01-23 02:44:40.884072: step: 1856/530, loss: 0.0003087043878622353
2023-01-23 02:44:42.028338: step: 1860/530, loss: 0.04499950632452965
2023-01-23 02:44:43.166614: step: 1864/530, loss: 0.0010932445293292403
2023-01-23 02:44:44.266255: step: 1868/530, loss: 0.001951885293237865
2023-01-23 02:44:45.394800: step: 1872/530, loss: 0.049657247960567474
2023-01-23 02:44:46.527512: step: 1876/530, loss: 0.024089623242616653
2023-01-23 02:44:47.657566: step: 1880/530, loss: 0.04950447380542755
2023-01-23 02:44:48.788942: step: 1884/530, loss: 0.007705879397690296
2023-01-23 02:44:49.920536: step: 1888/530, loss: 0.03236236423254013
2023-01-23 02:44:51.048094: step: 1892/530, loss: 0.05093926191329956
2023-01-23 02:44:52.150871: step: 1896/530, loss: 0.05753746256232262
2023-01-23 02:44:53.255231: step: 1900/530, loss: 0.0002115249662892893
2023-01-23 02:44:54.362038: step: 1904/530, loss: 0.0075972555205225945
2023-01-23 02:44:55.510157: step: 1908/530, loss: 0.05229062959551811
2023-01-23 02:44:56.630245: step: 1912/530, loss: 0.0026124001014977694
2023-01-23 02:44:57.722425: step: 1916/530, loss: 0.00786886177957058
2023-01-23 02:44:58.823761: step: 1920/530, loss: 0.02142028883099556
2023-01-23 02:44:59.934304: step: 1924/530, loss: 0.0021814347710460424
2023-01-23 02:45:01.037678: step: 1928/530, loss: 0.00223884591832757
2023-01-23 02:45:02.175225: step: 1932/530, loss: 0.02219877392053604
2023-01-23 02:45:03.314532: step: 1936/530, loss: 0.0005825996631756425
2023-01-23 02:45:04.461324: step: 1940/530, loss: 0.002773761749267578
2023-01-23 02:45:05.580128: step: 1944/530, loss: 0.0045144082978367805
2023-01-23 02:45:06.707983: step: 1948/530, loss: 0.02409515529870987
2023-01-23 02:45:07.812640: step: 1952/530, loss: 0.0006704331026412547
2023-01-23 02:45:08.918574: step: 1956/530, loss: 0.004224204923957586
2023-01-23 02:45:10.020706: step: 1960/530, loss: 0.0015434264205396175
2023-01-23 02:45:11.141216: step: 1964/530, loss: 0.040897272527217865
2023-01-23 02:45:12.238452: step: 1968/530, loss: 0.10474738478660583
2023-01-23 02:45:13.382739: step: 1972/530, loss: 0.01076211966574192
2023-01-23 02:45:14.511029: step: 1976/530, loss: 0.0190963763743639
2023-01-23 02:45:15.642016: step: 1980/530, loss: 0.06103458255529404
2023-01-23 02:45:16.763452: step: 1984/530, loss: 0.02944965288043022
2023-01-23 02:45:17.870845: step: 1988/530, loss: 0.0020330429542809725
2023-01-23 02:45:18.985752: step: 1992/530, loss: 0.0001300811709370464
2023-01-23 02:45:20.132577: step: 1996/530, loss: 0.1824359893798828
2023-01-23 02:45:21.251563: step: 2000/530, loss: 0.016443466767668724
2023-01-23 02:45:22.385816: step: 2004/530, loss: 0.03230753168463707
2023-01-23 02:45:23.516947: step: 2008/530, loss: 0.00783538818359375
2023-01-23 02:45:24.622224: step: 2012/530, loss: 0.024396903812885284
2023-01-23 02:45:25.735661: step: 2016/530, loss: 0.0010374069679528475
2023-01-23 02:45:26.869583: step: 2020/530, loss: 0.007400131318718195
2023-01-23 02:45:28.022131: step: 2024/530, loss: 0.01990509033203125
2023-01-23 02:45:29.151103: step: 2028/530, loss: 0.0026630403008311987
2023-01-23 02:45:30.266435: step: 2032/530, loss: 0.0393676795065403
2023-01-23 02:45:31.378386: step: 2036/530, loss: 0.021541118621826172
2023-01-23 02:45:32.496102: step: 2040/530, loss: 0.01589679718017578
2023-01-23 02:45:33.625552: step: 2044/530, loss: 0.009590482339262962
2023-01-23 02:45:34.766895: step: 2048/530, loss: 0.034490346908569336
2023-01-23 02:45:35.910537: step: 2052/530, loss: 0.015813540667295456
2023-01-23 02:45:37.022698: step: 2056/530, loss: 0.001965808914974332
2023-01-23 02:45:38.139265: step: 2060/530, loss: 2.250671423098538e-05
2023-01-23 02:45:39.261173: step: 2064/530, loss: 0.044591713696718216
2023-01-23 02:45:40.399775: step: 2068/530, loss: 0.008554312400519848
2023-01-23 02:45:41.522607: step: 2072/530, loss: 0.00414619455114007
2023-01-23 02:45:42.670875: step: 2076/530, loss: 0.005199432838708162
2023-01-23 02:45:43.827148: step: 2080/530, loss: 0.0007673263316974044
2023-01-23 02:45:44.971505: step: 2084/530, loss: 0.013872337527573109
2023-01-23 02:45:46.128286: step: 2088/530, loss: 0.020048143342137337
2023-01-23 02:45:47.241254: step: 2092/530, loss: 0.009788990020751953
2023-01-23 02:45:48.356573: step: 2096/530, loss: 0.0009181022178381681
2023-01-23 02:45:49.521794: step: 2100/530, loss: 0.007423591800034046
2023-01-23 02:45:50.656777: step: 2104/530, loss: 0.007729626260697842
2023-01-23 02:45:51.804343: step: 2108/530, loss: 0.008791351690888405
2023-01-23 02:45:52.925998: step: 2112/530, loss: 0.022530268877744675
2023-01-23 02:45:54.065125: step: 2116/530, loss: 0.002525806427001953
2023-01-23 02:45:55.268042: step: 2120/530, loss: 0.016582202166318893
==================================================
Loss: 0.027
--------------------
Dev: {'event': {'p': 0.5865580448065173, 'r': 0.7669773635153129, 'f1': 0.6647432198499712}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
Test: {'event': {'p': 0.6027874564459931, 'r': 0.7908571428571428, 'f1': 0.6841324765200197}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
Chinese: {'event': {'p': 0.5764705882352941, 'r': 0.9074074074074074, 'f1': 0.7050359712230215}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
Korean: {'event': {'p': 0.603448275862069, 'r': 0.5555555555555556, 'f1': 0.5785123966942148}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
Russian: {'event': {'p': 0.4186046511627907, 'r': 0.5, 'f1': 0.45569620253164556}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Chinese: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Chinese: {'event': {'p': 0.6190476190476191, 'r': 0.9629629629629629, 'f1': 0.7536231884057971}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6288770053475936, 'r': 0.7829560585885486, 'f1': 0.697508896797153}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Korean: {'event': {'p': 0.64058795637743, 'r': 0.772, 'f1': 0.7001813941435606}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Korean: {'event': {'p': 0.6851851851851852, 'r': 0.5873015873015873, 'f1': 0.6324786324786325}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5319148936170213, 'r': 0.6944444444444444, 'f1': 0.6024096385542169}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
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 02:46:36.129789: step: 4/530, loss: 0.0006170272827148438
2023-01-23 02:46:37.269350: step: 8/530, loss: 0.008962727151811123
2023-01-23 02:46:38.426042: step: 12/530, loss: 0.0009142875787802041
2023-01-23 02:46:39.559637: step: 16/530, loss: 0.0021963119506835938
2023-01-23 02:46:40.680555: step: 20/530, loss: 0.004263448994606733
2023-01-23 02:46:41.799722: step: 24/530, loss: 0.024438858032226562
2023-01-23 02:46:42.925359: step: 28/530, loss: 0.07940807938575745
2023-01-23 02:46:44.047342: step: 32/530, loss: 0.00513458251953125
2023-01-23 02:46:45.167557: step: 36/530, loss: 0.004402923863381147
2023-01-23 02:46:46.308878: step: 40/530, loss: 0.003044223878532648
2023-01-23 02:46:47.441321: step: 44/530, loss: 0.016464948654174805
2023-01-23 02:46:48.592073: step: 48/530, loss: 0.008777236565947533
2023-01-23 02:46:49.723607: step: 52/530, loss: 0.001104641007259488
2023-01-23 02:46:50.820310: step: 56/530, loss: 0.008661651983857155
2023-01-23 02:46:51.955311: step: 60/530, loss: 0.022327184677124023
2023-01-23 02:46:53.040475: step: 64/530, loss: 0.0633670836687088
2023-01-23 02:46:54.162487: step: 68/530, loss: 0.004669189453125
2023-01-23 02:46:55.305653: step: 72/530, loss: 0.0003538132004905492
2023-01-23 02:46:56.433260: step: 76/530, loss: 0.03853330388665199
2023-01-23 02:46:57.572328: step: 80/530, loss: 0.007919502444565296
2023-01-23 02:46:58.711667: step: 84/530, loss: 0.027817536145448685
2023-01-23 02:46:59.835780: step: 88/530, loss: 0.012743568047881126
2023-01-23 02:47:00.972679: step: 92/530, loss: 0.03397679328918457
2023-01-23 02:47:02.156857: step: 96/530, loss: 0.0014127731556072831
2023-01-23 02:47:03.273306: step: 100/530, loss: 0.0008743763319216669
2023-01-23 02:47:04.396736: step: 104/530, loss: 0.04171466827392578
2023-01-23 02:47:05.517529: step: 108/530, loss: 0.049958229064941406
2023-01-23 02:47:06.634454: step: 112/530, loss: 0.006876373663544655
2023-01-23 02:47:07.750018: step: 116/530, loss: 0.01923818700015545
2023-01-23 02:47:08.862981: step: 120/530, loss: 0.00732765207067132
2023-01-23 02:47:10.017941: step: 124/530, loss: 0.008611107245087624
2023-01-23 02:47:11.143737: step: 128/530, loss: 0.0006887793424539268
2023-01-23 02:47:12.274861: step: 132/530, loss: 0.00702400179579854
2023-01-23 02:47:13.412133: step: 136/530, loss: 0.025534389540553093
2023-01-23 02:47:14.503259: step: 140/530, loss: 0.041330814361572266
2023-01-23 02:47:15.579333: step: 144/530, loss: 0.001424017595127225
2023-01-23 02:47:16.719801: step: 148/530, loss: 0.007486725226044655
2023-01-23 02:47:17.823169: step: 152/530, loss: 0.03888645023107529
2023-01-23 02:47:18.935543: step: 156/530, loss: 0.0001066207914846018
2023-01-23 02:47:20.056579: step: 160/530, loss: 0.153453066945076
2023-01-23 02:47:21.165881: step: 164/530, loss: 0.016442155465483665
2023-01-23 02:47:22.303289: step: 168/530, loss: 0.03246812894940376
2023-01-23 02:47:23.443127: step: 172/530, loss: 0.017256736755371094
2023-01-23 02:47:24.549004: step: 176/530, loss: 0.0009941101307049394
2023-01-23 02:47:25.683048: step: 180/530, loss: -2.2029877072782256e-05
2023-01-23 02:47:26.801458: step: 184/530, loss: 0.0015310286544263363
2023-01-23 02:47:27.928118: step: 188/530, loss: 0.06053924560546875
2023-01-23 02:47:29.050167: step: 192/530, loss: 0.6747072339057922
2023-01-23 02:47:30.206679: step: 196/530, loss: 0.013753890991210938
2023-01-23 02:47:31.323784: step: 200/530, loss: 0.011660766787827015
2023-01-23 02:47:32.429871: step: 204/530, loss: 0.10018176585435867
2023-01-23 02:47:33.546135: step: 208/530, loss: 5.4168704082258046e-05
2023-01-23 02:47:34.685059: step: 212/530, loss: 0.026498936116695404
2023-01-23 02:47:35.798881: step: 216/530, loss: 0.0007252693176269531
2023-01-23 02:47:36.947648: step: 220/530, loss: 0.060758400708436966
2023-01-23 02:47:38.091685: step: 224/530, loss: 0.027014732360839844
2023-01-23 02:47:39.231569: step: 228/530, loss: 0.00015926362539175898
2023-01-23 02:47:40.378935: step: 232/530, loss: 0.005106544587761164
2023-01-23 02:47:41.502729: step: 236/530, loss: 0.01175379753112793
2023-01-23 02:47:42.647852: step: 240/530, loss: 0.0009660720825195312
2023-01-23 02:47:43.782707: step: 244/530, loss: 0.010135556571185589
2023-01-23 02:47:44.915017: step: 248/530, loss: 0.01663360558450222
2023-01-23 02:47:46.019758: step: 252/530, loss: 0.006316948216408491
2023-01-23 02:47:47.122945: step: 256/530, loss: 0.004391288850456476
2023-01-23 02:47:48.259648: step: 260/530, loss: 0.07250719517469406
2023-01-23 02:47:49.402988: step: 264/530, loss: 0.0003520965692587197
2023-01-23 02:47:50.537524: step: 268/530, loss: 0.0043006897903978825
2023-01-23 02:47:51.656410: step: 272/530, loss: 0.007274055853486061
2023-01-23 02:47:52.777619: step: 276/530, loss: 0.0016317367553710938
2023-01-23 02:47:53.892079: step: 280/530, loss: 0.08037243038415909
2023-01-23 02:47:55.000471: step: 284/530, loss: 0.012360096909105778
2023-01-23 02:47:56.126225: step: 288/530, loss: 0.006418419070541859
2023-01-23 02:47:57.281306: step: 292/530, loss: 0.004541206639260054
2023-01-23 02:47:58.402357: step: 296/530, loss: 0.002791118808090687
2023-01-23 02:47:59.522033: step: 300/530, loss: 5.607604907709174e-05
2023-01-23 02:48:00.645970: step: 304/530, loss: 0.0010190963512286544
2023-01-23 02:48:01.754658: step: 308/530, loss: 0.03766059875488281
2023-01-23 02:48:02.852407: step: 312/530, loss: 0.08749494701623917
2023-01-23 02:48:03.990550: step: 316/530, loss: 0.039907075464725494
2023-01-23 02:48:05.121227: step: 320/530, loss: 0.0023992538917809725
2023-01-23 02:48:06.262120: step: 324/530, loss: 0.005767917726188898
2023-01-23 02:48:07.395839: step: 328/530, loss: 0.018404768779873848
2023-01-23 02:48:08.522719: step: 332/530, loss: 0.016777800396084785
2023-01-23 02:48:09.634948: step: 336/530, loss: 0.00243034353479743
2023-01-23 02:48:10.752864: step: 340/530, loss: 0.0010665893787518144
2023-01-23 02:48:11.893102: step: 344/530, loss: 0.0024063109885901213
2023-01-23 02:48:13.009384: step: 348/530, loss: 0.02555275149643421
2023-01-23 02:48:14.159210: step: 352/530, loss: 0.02347269095480442
2023-01-23 02:48:15.269611: step: 356/530, loss: 0.22958174347877502
2023-01-23 02:48:16.378837: step: 360/530, loss: 0.00014390944852493703
2023-01-23 02:48:17.502606: step: 364/530, loss: 0.0022373199462890625
2023-01-23 02:48:18.608049: step: 368/530, loss: 0.009851074777543545
2023-01-23 02:48:19.753198: step: 372/530, loss: 0.02221093326807022
2023-01-23 02:48:20.885906: step: 376/530, loss: 0.00037384033203125
2023-01-23 02:48:22.014160: step: 380/530, loss: 7.655620720470324e-05
2023-01-23 02:48:23.131906: step: 384/530, loss: 0.0001773834228515625
2023-01-23 02:48:24.222492: step: 388/530, loss: 0.005497884936630726
2023-01-23 02:48:25.328417: step: 392/530, loss: 0.0002777099725790322
2023-01-23 02:48:26.472742: step: 396/530, loss: 0.03215827792882919
2023-01-23 02:48:27.629284: step: 400/530, loss: 0.005587005987763405
2023-01-23 02:48:28.763518: step: 404/530, loss: 0.05372406914830208
2023-01-23 02:48:29.883270: step: 408/530, loss: 0.08013200759887695
2023-01-23 02:48:30.986294: step: 412/530, loss: 0.006840371992439032
2023-01-23 02:48:32.219619: step: 416/530, loss: 0.0003841400321107358
2023-01-23 02:48:33.333139: step: 420/530, loss: 1.9574166799429804e-05
2023-01-23 02:48:34.441513: step: 424/530, loss: 0.0021209716796875
2023-01-23 02:48:35.584334: step: 428/530, loss: 0.00475387554615736
2023-01-23 02:48:36.711080: step: 432/530, loss: 0.00013608933659270406
2023-01-23 02:48:37.832033: step: 436/530, loss: 4.024505687993951e-05
2023-01-23 02:48:38.978211: step: 440/530, loss: 0.002505397889763117
2023-01-23 02:48:40.104660: step: 444/530, loss: 0.010141611099243164
2023-01-23 02:48:41.255255: step: 448/530, loss: 1.926422191900201e-05
2023-01-23 02:48:42.380043: step: 452/530, loss: 0.0442357063293457
2023-01-23 02:48:43.547728: step: 456/530, loss: 0.1211620345711708
2023-01-23 02:48:44.694933: step: 460/530, loss: 0.02894299104809761
2023-01-23 02:48:45.818134: step: 464/530, loss: 0.0004015445592813194
2023-01-23 02:48:46.954815: step: 468/530, loss: 0.007358932867646217
2023-01-23 02:48:48.123765: step: 472/530, loss: 0.00270500173792243
2023-01-23 02:48:49.262631: step: 476/530, loss: 0.0007340431329794228
2023-01-23 02:48:50.398188: step: 480/530, loss: 0.027745626866817474
2023-01-23 02:48:51.577628: step: 484/530, loss: 0.11460423469543457
2023-01-23 02:48:52.699081: step: 488/530, loss: 0.007725572679191828
2023-01-23 02:48:53.850333: step: 492/530, loss: 0.0024312972091138363
2023-01-23 02:48:54.951532: step: 496/530, loss: 0.012563705444335938
2023-01-23 02:48:56.057598: step: 500/530, loss: 0.011520194821059704
2023-01-23 02:48:57.157198: step: 504/530, loss: 0.04189472272992134
2023-01-23 02:48:58.267221: step: 508/530, loss: 0.0007476806640625
2023-01-23 02:48:59.368109: step: 512/530, loss: 0.009466171264648438
2023-01-23 02:49:00.502893: step: 516/530, loss: 0.011503219604492188
2023-01-23 02:49:01.604056: step: 520/530, loss: 0.03649614006280899
2023-01-23 02:49:02.740206: step: 524/530, loss: 0.0006355285877361894
2023-01-23 02:49:03.847057: step: 528/530, loss: 0.02817249298095703
2023-01-23 02:49:04.954681: step: 532/530, loss: 0.013330173678696156
2023-01-23 02:49:06.078883: step: 536/530, loss: 0.015714168548583984
2023-01-23 02:49:07.195243: step: 540/530, loss: 0.007248115725815296
2023-01-23 02:49:08.320057: step: 544/530, loss: 0.00024785997811704874
2023-01-23 02:49:09.444145: step: 548/530, loss: 0.007177925202995539
2023-01-23 02:49:10.595954: step: 552/530, loss: 0.0022053720895200968
2023-01-23 02:49:11.705359: step: 556/530, loss: 1.389614462852478
2023-01-23 02:49:12.846534: step: 560/530, loss: 0.0018544197082519531
2023-01-23 02:49:13.943921: step: 564/530, loss: 0.023641683161258698
2023-01-23 02:49:15.045702: step: 568/530, loss: 0.012304306030273438
2023-01-23 02:49:16.142029: step: 572/530, loss: 0.027260446920990944
2023-01-23 02:49:17.247113: step: 576/530, loss: 0.00352401752024889
2023-01-23 02:49:18.356042: step: 580/530, loss: 0.08416776359081268
2023-01-23 02:49:19.503022: step: 584/530, loss: 0.011368370614945889
2023-01-23 02:49:20.619916: step: 588/530, loss: 0.0010231973137706518
2023-01-23 02:49:21.721195: step: 592/530, loss: 6.418228440452367e-05
2023-01-23 02:49:22.818356: step: 596/530, loss: 0.00793533306568861
2023-01-23 02:49:23.914972: step: 600/530, loss: 0.001327133271843195
2023-01-23 02:49:25.062374: step: 604/530, loss: 0.017234230414032936
2023-01-23 02:49:26.187847: step: 608/530, loss: 0.0009544373024255037
2023-01-23 02:49:27.311804: step: 612/530, loss: 0.017559148371219635
2023-01-23 02:49:28.449872: step: 616/530, loss: 0.027152730152010918
2023-01-23 02:49:29.565028: step: 620/530, loss: 0.01896820217370987
2023-01-23 02:49:30.672500: step: 624/530, loss: 0.03765459358692169
2023-01-23 02:49:31.759494: step: 628/530, loss: 0.00030541419982910156
2023-01-23 02:49:32.880455: step: 632/530, loss: 0.016469767317175865
2023-01-23 02:49:34.016987: step: 636/530, loss: 0.03996772691607475
2023-01-23 02:49:35.172956: step: 640/530, loss: 0.01603841781616211
2023-01-23 02:49:36.308677: step: 644/530, loss: 0.16668447852134705
2023-01-23 02:49:37.432570: step: 648/530, loss: 0.0003618240589275956
2023-01-23 02:49:38.556615: step: 652/530, loss: 0.003962898161262274
2023-01-23 02:49:39.663575: step: 656/530, loss: 0.0008433341863565147
2023-01-23 02:49:40.780659: step: 660/530, loss: 0.004819011315703392
2023-01-23 02:49:41.949802: step: 664/530, loss: 0.20168742537498474
2023-01-23 02:49:43.060127: step: 668/530, loss: 0.0016164779663085938
2023-01-23 02:49:44.204020: step: 672/530, loss: 0.005039215553551912
2023-01-23 02:49:45.355122: step: 676/530, loss: 0.04378318786621094
2023-01-23 02:49:46.485505: step: 680/530, loss: 0.006479168310761452
2023-01-23 02:49:47.607977: step: 684/530, loss: 0.023687170818448067
2023-01-23 02:49:48.748188: step: 688/530, loss: 0.001493263291195035
2023-01-23 02:49:49.891634: step: 692/530, loss: 0.00014171600923873484
2023-01-23 02:49:50.981670: step: 696/530, loss: 0.0008190155494958162
2023-01-23 02:49:52.103297: step: 700/530, loss: 0.00030174257699400187
2023-01-23 02:49:53.212931: step: 704/530, loss: 1.4972685676184483e-05
2023-01-23 02:49:54.345477: step: 708/530, loss: 0.004610443487763405
2023-01-23 02:49:55.461458: step: 712/530, loss: 0.033678632229566574
2023-01-23 02:49:56.600421: step: 716/530, loss: 0.01068346481770277
2023-01-23 02:49:57.704083: step: 720/530, loss: 0.021994877606630325
2023-01-23 02:49:58.798816: step: 724/530, loss: 0.02668910101056099
2023-01-23 02:49:59.897683: step: 728/530, loss: 0.036435317248106
2023-01-23 02:50:01.032216: step: 732/530, loss: 0.0004341125313658267
2023-01-23 02:50:02.156783: step: 736/530, loss: 0.000354766845703125
2023-01-23 02:50:03.318450: step: 740/530, loss: 0.001425075577571988
2023-01-23 02:50:04.450871: step: 744/530, loss: 0.023249246180057526
2023-01-23 02:50:05.559988: step: 748/530, loss: 0.0007686614990234375
2023-01-23 02:50:06.664609: step: 752/530, loss: 0.025387166067957878
2023-01-23 02:50:07.791834: step: 756/530, loss: 0.0004726409970317036
2023-01-23 02:50:08.919099: step: 760/530, loss: 0.038896940648555756
2023-01-23 02:50:10.044867: step: 764/530, loss: 0.00043277739314362407
2023-01-23 02:50:11.175303: step: 768/530, loss: 0.0034386159386485815
2023-01-23 02:50:12.310001: step: 772/530, loss: 0.029145622625947
2023-01-23 02:50:13.425731: step: 776/530, loss: 0.0018712998135015368
2023-01-23 02:50:14.546264: step: 780/530, loss: 0.0021556855645030737
2023-01-23 02:50:15.669272: step: 784/530, loss: 0.015527726151049137
2023-01-23 02:50:16.773213: step: 788/530, loss: 0.0001493453892180696
2023-01-23 02:50:17.899881: step: 792/530, loss: 4.281997826183215e-05
2023-01-23 02:50:19.041654: step: 796/530, loss: 0.01034460123628378
2023-01-23 02:50:20.164197: step: 800/530, loss: 0.006088066380470991
2023-01-23 02:50:21.296715: step: 804/530, loss: 0.02073812484741211
2023-01-23 02:50:22.419543: step: 808/530, loss: 0.0002723693905863911
2023-01-23 02:50:23.535062: step: 812/530, loss: 0.001817989395931363
2023-01-23 02:50:24.665603: step: 816/530, loss: 0.028634263202548027
2023-01-23 02:50:25.810353: step: 820/530, loss: 0.0005810738075524569
2023-01-23 02:50:26.968363: step: 824/530, loss: 0.0037511824630200863
2023-01-23 02:50:28.090747: step: 828/530, loss: 0.00021467207989189774
2023-01-23 02:50:29.203214: step: 832/530, loss: 0.026242733001708984
2023-01-23 02:50:30.328948: step: 836/530, loss: 0.03699150308966637
2023-01-23 02:50:31.445959: step: 840/530, loss: 0.003712272737175226
2023-01-23 02:50:32.602141: step: 844/530, loss: 0.0003410339413676411
2023-01-23 02:50:33.740849: step: 848/530, loss: 0.0019670487381517887
2023-01-23 02:50:34.879382: step: 852/530, loss: 0.008776617236435413
2023-01-23 02:50:36.016899: step: 856/530, loss: 0.00881042517721653
2023-01-23 02:50:37.161970: step: 860/530, loss: 0.0010787963401526213
2023-01-23 02:50:38.298084: step: 864/530, loss: 4.091262962901965e-05
2023-01-23 02:50:39.426496: step: 868/530, loss: 0.0031227110885083675
2023-01-23 02:50:40.553787: step: 872/530, loss: 0.00020532608323264867
2023-01-23 02:50:41.677464: step: 876/530, loss: 0.056491851806640625
2023-01-23 02:50:42.845629: step: 880/530, loss: 0.00961084384471178
2023-01-23 02:50:43.950602: step: 884/530, loss: 0.009857368655502796
2023-01-23 02:50:45.089439: step: 888/530, loss: 0.8669643402099609
2023-01-23 02:50:46.226598: step: 892/530, loss: 0.0165266040712595
2023-01-23 02:50:47.324798: step: 896/530, loss: 0.012455177493393421
2023-01-23 02:50:48.453350: step: 900/530, loss: 0.12309174239635468
2023-01-23 02:50:49.560092: step: 904/530, loss: 0.011877631768584251
2023-01-23 02:50:50.680685: step: 908/530, loss: 0.03761015087366104
2023-01-23 02:50:51.797000: step: 912/530, loss: 0.003395461943000555
2023-01-23 02:50:52.944276: step: 916/530, loss: 0.02661123313009739
2023-01-23 02:50:54.083253: step: 920/530, loss: 8.869171142578125e-05
2023-01-23 02:50:55.233530: step: 924/530, loss: 0.001127052353695035
2023-01-23 02:50:56.338585: step: 928/530, loss: 0.0001392364501953125
2023-01-23 02:50:57.453133: step: 932/530, loss: 0.0048828125
2023-01-23 02:50:58.570890: step: 936/530, loss: 0.01406564749777317
2023-01-23 02:50:59.711139: step: 940/530, loss: 0.04362945631146431
2023-01-23 02:51:00.854443: step: 944/530, loss: 0.009560775943100452
2023-01-23 02:51:01.979005: step: 948/530, loss: 0.005719184875488281
2023-01-23 02:51:03.133195: step: 952/530, loss: 0.03713631629943848
2023-01-23 02:51:04.252900: step: 956/530, loss: 0.005797004792839289
2023-01-23 02:51:05.373524: step: 960/530, loss: 4.291534423828125e-06
2023-01-23 02:51:06.524143: step: 964/530, loss: 3.3998490835074335e-05
2023-01-23 02:51:07.629856: step: 968/530, loss: 0.0008330345153808594
2023-01-23 02:51:08.723099: step: 972/530, loss: 0.00067729945294559
2023-01-23 02:51:09.805792: step: 976/530, loss: 0.02462148666381836
2023-01-23 02:51:10.916158: step: 980/530, loss: 0.02042408101260662
2023-01-23 02:51:12.003218: step: 984/530, loss: 0.0011967660393565893
2023-01-23 02:51:13.116381: step: 988/530, loss: 0.04451408237218857
2023-01-23 02:51:14.229823: step: 992/530, loss: 0.06557798385620117
2023-01-23 02:51:15.374326: step: 996/530, loss: 0.016010476276278496
2023-01-23 02:51:16.496541: step: 1000/530, loss: 0.04093341901898384
2023-01-23 02:51:17.626159: step: 1004/530, loss: 0.002197074703872204
2023-01-23 02:51:18.749325: step: 1008/530, loss: 0.047245025634765625
2023-01-23 02:51:19.873542: step: 1012/530, loss: 0.003819370409473777
2023-01-23 02:51:21.006742: step: 1016/530, loss: 0.00243206019513309
2023-01-23 02:51:22.128923: step: 1020/530, loss: 0.003633451648056507
2023-01-23 02:51:23.262211: step: 1024/530, loss: 0.018474770709872246
2023-01-23 02:51:24.418640: step: 1028/530, loss: 0.00106306083034724
2023-01-23 02:51:25.538337: step: 1032/530, loss: 0.0031681060791015625
2023-01-23 02:51:26.662194: step: 1036/530, loss: 0.08078479766845703
2023-01-23 02:51:27.773538: step: 1040/530, loss: 0.003502368927001953
2023-01-23 02:51:28.887922: step: 1044/530, loss: 0.0022749900817871094
2023-01-23 02:51:29.988995: step: 1048/530, loss: 0.00025472641573287547
2023-01-23 02:51:31.120815: step: 1052/530, loss: 0.028161145746707916
2023-01-23 02:51:32.293697: step: 1056/530, loss: 0.0007368088117800653
2023-01-23 02:51:33.418691: step: 1060/530, loss: 0.0037077905144542456
2023-01-23 02:51:34.549981: step: 1064/530, loss: 0.0017420768272131681
2023-01-23 02:51:35.693420: step: 1068/530, loss: 0.012484360486268997
2023-01-23 02:51:36.802985: step: 1072/530, loss: 0.0026571275666356087
2023-01-23 02:51:37.914498: step: 1076/530, loss: 0.004560661502182484
2023-01-23 02:51:39.013380: step: 1080/530, loss: 3.52859501617786e-06
2023-01-23 02:51:40.128096: step: 1084/530, loss: 0.04439201578497887
2023-01-23 02:51:41.265506: step: 1088/530, loss: 0.0045189871452748775
2023-01-23 02:51:42.385683: step: 1092/530, loss: 0.01673908159136772
2023-01-23 02:51:43.510571: step: 1096/530, loss: 0.0016184329288080335
2023-01-23 02:51:44.658476: step: 1100/530, loss: 0.22475281357765198
2023-01-23 02:51:45.808609: step: 1104/530, loss: 0.01683063618838787
2023-01-23 02:51:46.924616: step: 1108/530, loss: 0.00018711091252043843
2023-01-23 02:51:48.057912: step: 1112/530, loss: 0.06868467479944229
2023-01-23 02:51:49.188582: step: 1116/530, loss: 0.03353557735681534
2023-01-23 02:51:50.314603: step: 1120/530, loss: 0.05110645294189453
2023-01-23 02:51:51.424462: step: 1124/530, loss: 0.00029630662174895406
2023-01-23 02:51:52.527119: step: 1128/530, loss: 0.0009054184192791581
2023-01-23 02:51:53.643593: step: 1132/530, loss: 0.0806095153093338
2023-01-23 02:51:54.776254: step: 1136/530, loss: 0.0036535263061523438
2023-01-23 02:51:55.908747: step: 1140/530, loss: 0.006058323197066784
2023-01-23 02:51:57.075489: step: 1144/530, loss: 0.0035493853501975536
2023-01-23 02:51:58.178301: step: 1148/530, loss: 0.007952786050736904
2023-01-23 02:51:59.298897: step: 1152/530, loss: 0.004499530885368586
2023-01-23 02:52:00.412110: step: 1156/530, loss: 0.0030796052888035774
2023-01-23 02:52:01.530386: step: 1160/530, loss: 0.010721445083618164
2023-01-23 02:52:02.667035: step: 1164/530, loss: 0.035219766199588776
2023-01-23 02:52:03.793413: step: 1168/530, loss: 0.002448654267936945
2023-01-23 02:52:04.924766: step: 1172/530, loss: 0.000868940376676619
2023-01-23 02:52:06.039256: step: 1176/530, loss: 0.020801853388547897
2023-01-23 02:52:07.173196: step: 1180/530, loss: 0.04534759372472763
2023-01-23 02:52:08.270784: step: 1184/530, loss: 0.0008951186900958419
2023-01-23 02:52:09.412197: step: 1188/530, loss: 0.028798270970582962
2023-01-23 02:52:10.542914: step: 1192/530, loss: 0.009111499413847923
2023-01-23 02:52:11.656862: step: 1196/530, loss: 0.005178308580070734
2023-01-23 02:52:12.818115: step: 1200/530, loss: 0.024652909487485886
2023-01-23 02:52:13.930421: step: 1204/530, loss: 0.08762951195240021
2023-01-23 02:52:15.058166: step: 1208/530, loss: 0.0006271362653933465
2023-01-23 02:52:16.191088: step: 1212/530, loss: 0.034493256360292435
2023-01-23 02:52:17.341044: step: 1216/530, loss: 0.003872775938361883
2023-01-23 02:52:18.470998: step: 1220/530, loss: 0.0003028869687113911
2023-01-23 02:52:19.580047: step: 1224/530, loss: 0.0041214944794774055
2023-01-23 02:52:20.723541: step: 1228/530, loss: 0.0006351470947265625
2023-01-23 02:52:21.874843: step: 1232/530, loss: 0.7890416979789734
2023-01-23 02:52:22.981330: step: 1236/530, loss: 0.04070940241217613
2023-01-23 02:52:24.098047: step: 1240/530, loss: 0.0001262664736714214
2023-01-23 02:52:25.230775: step: 1244/530, loss: 0.0009400367853231728
2023-01-23 02:52:26.348501: step: 1248/530, loss: 0.08610954880714417
2023-01-23 02:52:27.505541: step: 1252/530, loss: 0.029549315571784973
2023-01-23 02:52:28.622474: step: 1256/530, loss: 0.00037844182224944234
2023-01-23 02:52:29.727004: step: 1260/530, loss: 0.0019823075272142887
2023-01-23 02:52:30.845404: step: 1264/530, loss: 0.0007590294117107987
2023-01-23 02:52:31.977055: step: 1268/530, loss: 0.07779411971569061
2023-01-23 02:52:33.125783: step: 1272/530, loss: 0.0027923583984375
2023-01-23 02:52:34.257869: step: 1276/530, loss: 0.013343526050448418
2023-01-23 02:52:35.363649: step: 1280/530, loss: 0.003886604215949774
2023-01-23 02:52:36.465214: step: 1284/530, loss: 0.004340553190559149
2023-01-23 02:52:37.582857: step: 1288/530, loss: 0.0005331516149453819
2023-01-23 02:52:38.708124: step: 1292/530, loss: 0.012051486410200596
2023-01-23 02:52:39.810201: step: 1296/530, loss: 0.0012164115905761719
2023-01-23 02:52:40.940527: step: 1300/530, loss: 0.008524704724550247
2023-01-23 02:52:42.082781: step: 1304/530, loss: 0.019993115216493607
2023-01-23 02:52:43.211911: step: 1308/530, loss: 0.00892577227205038
2023-01-23 02:52:44.340767: step: 1312/530, loss: 0.002249431796371937
2023-01-23 02:52:45.486726: step: 1316/530, loss: 0.011854744516313076
2023-01-23 02:52:46.597883: step: 1320/530, loss: 0.017955780029296875
2023-01-23 02:52:47.721439: step: 1324/530, loss: 0.08238229900598526
2023-01-23 02:52:48.810336: step: 1328/530, loss: 0.008172226138412952
2023-01-23 02:52:49.933149: step: 1332/530, loss: 0.032794952392578125
2023-01-23 02:52:51.096675: step: 1336/530, loss: 6.48498553346144e-06
2023-01-23 02:52:52.217865: step: 1340/530, loss: 0.017563628032803535
2023-01-23 02:52:53.361871: step: 1344/530, loss: 0.02641143836081028
2023-01-23 02:52:54.478957: step: 1348/530, loss: 0.020216751843690872
2023-01-23 02:52:55.612989: step: 1352/530, loss: 0.04610462114214897
2023-01-23 02:52:56.714628: step: 1356/530, loss: 0.0009861469734460115
2023-01-23 02:52:57.867975: step: 1360/530, loss: 0.01091918908059597
2023-01-23 02:52:58.997917: step: 1364/530, loss: 0.0001029014601954259
2023-01-23 02:53:00.125420: step: 1368/530, loss: 0.0007008552784100175
2023-01-23 02:53:01.263198: step: 1372/530, loss: 0.002441978547722101
2023-01-23 02:53:02.369281: step: 1376/530, loss: 8.373260061489418e-05
2023-01-23 02:53:03.481334: step: 1380/530, loss: 0.0001419544278178364
2023-01-23 02:53:04.588005: step: 1384/530, loss: 0.002406978514045477
2023-01-23 02:53:05.708047: step: 1388/530, loss: 1.4591217222914565e-05
2023-01-23 02:53:06.823956: step: 1392/530, loss: 0.0022152899764478207
2023-01-23 02:53:07.945994: step: 1396/530, loss: 0.022213174030184746
2023-01-23 02:53:09.063769: step: 1400/530, loss: 0.002324581379070878
2023-01-23 02:53:10.189422: step: 1404/530, loss: 0.018366431817412376
2023-01-23 02:53:11.305813: step: 1408/530, loss: 0.00019807815260719508
2023-01-23 02:53:12.443864: step: 1412/530, loss: 0.004859352018684149
2023-01-23 02:53:13.554082: step: 1416/530, loss: 0.0023203850723803043
2023-01-23 02:53:14.684043: step: 1420/530, loss: -4.76837158203125e-06
2023-01-23 02:53:15.810151: step: 1424/530, loss: 0.00162420270498842
2023-01-23 02:53:16.941634: step: 1428/530, loss: 0.017632007598876953
2023-01-23 02:53:18.062961: step: 1432/530, loss: 0.008682822808623314
2023-01-23 02:53:19.184003: step: 1436/530, loss: 2.1791458493680693e-05
2023-01-23 02:53:20.293673: step: 1440/530, loss: 0.14718493819236755
2023-01-23 02:53:21.416933: step: 1444/530, loss: 0.02180929109454155
2023-01-23 02:53:22.556512: step: 1448/530, loss: 0.009678458794951439
2023-01-23 02:53:23.672959: step: 1452/530, loss: 0.04201388359069824
2023-01-23 02:53:24.796174: step: 1456/530, loss: 0.0025659562088549137
2023-01-23 02:53:25.908403: step: 1460/530, loss: 0.0020736693404614925
2023-01-23 02:53:27.044729: step: 1464/530, loss: 0.015268850140273571
2023-01-23 02:53:28.182449: step: 1468/530, loss: 0.009681129828095436
2023-01-23 02:53:29.284861: step: 1472/530, loss: 0.0005296707386150956
2023-01-23 02:53:30.388129: step: 1476/530, loss: 0.0004803180636372417
2023-01-23 02:53:31.532556: step: 1480/530, loss: 0.007884884253144264
2023-01-23 02:53:32.678566: step: 1484/530, loss: 0.001230526017025113
2023-01-23 02:53:33.793155: step: 1488/530, loss: 0.0009352207416668534
2023-01-23 02:53:34.899183: step: 1492/530, loss: 0.013703537173569202
2023-01-23 02:53:36.025894: step: 1496/530, loss: 0.5990536212921143
2023-01-23 02:53:37.114792: step: 1500/530, loss: 0.023607540875673294
2023-01-23 02:53:38.216761: step: 1504/530, loss: 0.0006140708574093878
2023-01-23 02:53:39.374722: step: 1508/530, loss: 0.0032337189186364412
2023-01-23 02:53:40.516363: step: 1512/530, loss: 0.007204818539321423
2023-01-23 02:53:41.653861: step: 1516/530, loss: 0.013696098700165749
2023-01-23 02:53:42.765580: step: 1520/530, loss: 0.00051794049795717
2023-01-23 02:53:43.881602: step: 1524/530, loss: 0.01304397638887167
2023-01-23 02:53:44.995207: step: 1528/530, loss: 8.58306884765625e-05
2023-01-23 02:53:46.140410: step: 1532/530, loss: 0.03037414513528347
2023-01-23 02:53:47.259695: step: 1536/530, loss: 0.002983951708301902
2023-01-23 02:53:48.377098: step: 1540/530, loss: 0.021279336884617805
2023-01-23 02:53:49.473258: step: 1544/530, loss: 0.0013879776233807206
2023-01-23 02:53:50.633152: step: 1548/530, loss: 0.014726829715073109
2023-01-23 02:53:51.756621: step: 1552/530, loss: 0.00760917691513896
2023-01-23 02:53:52.900849: step: 1556/530, loss: 0.00154285435564816
2023-01-23 02:53:54.031006: step: 1560/530, loss: 5.6076052715070546e-05
2023-01-23 02:53:55.182759: step: 1564/530, loss: 0.007347679231315851
2023-01-23 02:53:56.304301: step: 1568/530, loss: 0.03694343566894531
2023-01-23 02:53:57.418331: step: 1572/530, loss: 0.005849361419677734
2023-01-23 02:53:58.537413: step: 1576/530, loss: 0.04314832761883736
2023-01-23 02:53:59.639521: step: 1580/530, loss: 2.937316821771674e-05
2023-01-23 02:54:00.726693: step: 1584/530, loss: 0.050464775413274765
2023-01-23 02:54:01.855325: step: 1588/530, loss: 0.07201328873634338
2023-01-23 02:54:02.966852: step: 1592/530, loss: 0.007155418861657381
2023-01-23 02:54:04.117055: step: 1596/530, loss: 0.06021900475025177
2023-01-23 02:54:05.233063: step: 1600/530, loss: 0.004035568330436945
2023-01-23 02:54:06.385352: step: 1604/530, loss: 0.016447830945253372
2023-01-23 02:54:07.514555: step: 1608/530, loss: 0.007470798213034868
2023-01-23 02:54:08.644880: step: 1612/530, loss: 1.8882752556237392e-05
2023-01-23 02:54:09.764025: step: 1616/530, loss: 0.029623698443174362
2023-01-23 02:54:10.888369: step: 1620/530, loss: 0.0308837890625
2023-01-23 02:54:12.007327: step: 1624/530, loss: 0.008257865905761719
2023-01-23 02:54:13.137836: step: 1628/530, loss: 0.0010222436394542456
2023-01-23 02:54:14.248397: step: 1632/530, loss: 0.0231843963265419
2023-01-23 02:54:15.377891: step: 1636/530, loss: 6.103515625e-05
2023-01-23 02:54:16.488247: step: 1640/530, loss: 0.008834457956254482
2023-01-23 02:54:17.605198: step: 1644/530, loss: 0.0008246421348303556
2023-01-23 02:54:18.735499: step: 1648/530, loss: 0.34993723034858704
2023-01-23 02:54:19.845060: step: 1652/530, loss: 0.044150736182928085
2023-01-23 02:54:20.977842: step: 1656/530, loss: 0.0015690803993493319
2023-01-23 02:54:22.097122: step: 1660/530, loss: 0.020256424322724342
2023-01-23 02:54:23.220604: step: 1664/530, loss: 0.004318046849220991
2023-01-23 02:54:24.355008: step: 1668/530, loss: 0.00022611618624068797
2023-01-23 02:54:25.499824: step: 1672/530, loss: 0.00209884624928236
2023-01-23 02:54:26.624269: step: 1676/530, loss: 0.04850583150982857
2023-01-23 02:54:27.763955: step: 1680/530, loss: 0.003920459654182196
2023-01-23 02:54:28.925884: step: 1684/530, loss: 0.04824981838464737
2023-01-23 02:54:30.031687: step: 1688/530, loss: 0.0015677452320232987
2023-01-23 02:54:31.161064: step: 1692/530, loss: 0.0069971089251339436
2023-01-23 02:54:32.304780: step: 1696/530, loss: 0.007292557042092085
2023-01-23 02:54:33.414794: step: 1700/530, loss: 0.05669093132019043
2023-01-23 02:54:34.543178: step: 1704/530, loss: 0.015943242236971855
2023-01-23 02:54:35.666200: step: 1708/530, loss: 0.0022111416328698397
2023-01-23 02:54:36.792993: step: 1712/530, loss: 0.00674552982673049
2023-01-23 02:54:37.926265: step: 1716/530, loss: 0.033381808549165726
2023-01-23 02:54:39.063162: step: 1720/530, loss: 0.0008404746768064797
2023-01-23 02:54:40.199305: step: 1724/530, loss: 0.0010616302024573088
2023-01-23 02:54:41.332631: step: 1728/530, loss: 0.002975654788315296
2023-01-23 02:54:42.475485: step: 1732/530, loss: 0.01167144812643528
2023-01-23 02:54:43.606960: step: 1736/530, loss: 0.07330246269702911
2023-01-23 02:54:44.699797: step: 1740/530, loss: 0.003134441329166293
2023-01-23 02:54:45.816372: step: 1744/530, loss: 0.022260475903749466
2023-01-23 02:54:46.937828: step: 1748/530, loss: 0.06419877707958221
2023-01-23 02:54:48.089107: step: 1752/530, loss: 0.016246415674686432
2023-01-23 02:54:49.203534: step: 1756/530, loss: 0.0004451751592569053
2023-01-23 02:54:50.338495: step: 1760/530, loss: 0.0027055740356445312
2023-01-23 02:54:51.485351: step: 1764/530, loss: 0.0034275054931640625
2023-01-23 02:54:52.651642: step: 1768/530, loss: 0.0011279582977294922
2023-01-23 02:54:53.780948: step: 1772/530, loss: 0.04172935709357262
2023-01-23 02:54:54.889444: step: 1776/530, loss: 0.0007325172773562372
2023-01-23 02:54:56.019070: step: 1780/530, loss: 0.004502487368881702
2023-01-23 02:54:57.187172: step: 1784/530, loss: 0.11960944533348083
2023-01-23 02:54:58.321666: step: 1788/530, loss: 0.003921127412468195
2023-01-23 02:54:59.482123: step: 1792/530, loss: 0.032137155532836914
2023-01-23 02:55:00.602462: step: 1796/530, loss: 0.0012937546707689762
2023-01-23 02:55:01.757131: step: 1800/530, loss: 0.6597188115119934
2023-01-23 02:55:02.895422: step: 1804/530, loss: 0.01892080344259739
2023-01-23 02:55:04.012349: step: 1808/530, loss: 0.016044998541474342
2023-01-23 02:55:05.157194: step: 1812/530, loss: 6.198897608555853e-07
2023-01-23 02:55:06.295739: step: 1816/530, loss: 0.001491117523983121
2023-01-23 02:55:07.444493: step: 1820/530, loss: 0.008706283755600452
2023-01-23 02:55:08.572357: step: 1824/530, loss: 0.00033245087251998484
2023-01-23 02:55:09.701914: step: 1828/530, loss: 0.0006847382173873484
2023-01-23 02:55:10.811856: step: 1832/530, loss: 9.469986252952367e-05
2023-01-23 02:55:11.948072: step: 1836/530, loss: 0.053072646260261536
2023-01-23 02:55:13.055723: step: 1840/530, loss: 0.0035694122780114412
2023-01-23 02:55:14.198022: step: 1844/530, loss: 0.02610321156680584
2023-01-23 02:55:15.318922: step: 1848/530, loss: 0.0050811767578125
2023-01-23 02:55:16.420541: step: 1852/530, loss: 0.0004945755354128778
2023-01-23 02:55:17.564842: step: 1856/530, loss: 0.01032409630715847
2023-01-23 02:55:18.679425: step: 1860/530, loss: 0.0009616852039471269
2023-01-23 02:55:19.777480: step: 1864/530, loss: 0.0003273010370321572
2023-01-23 02:55:20.911773: step: 1868/530, loss: 0.18396759033203125
2023-01-23 02:55:22.070904: step: 1872/530, loss: 0.013064097613096237
2023-01-23 02:55:23.207964: step: 1876/530, loss: 3.8909915019758046e-05
2023-01-23 02:55:24.315899: step: 1880/530, loss: 0.026477433741092682
2023-01-23 02:55:25.451238: step: 1884/530, loss: 0.04197445139288902
2023-01-23 02:55:26.591110: step: 1888/530, loss: 0.02575073204934597
2023-01-23 02:55:27.705701: step: 1892/530, loss: 0.028217125684022903
2023-01-23 02:55:28.834728: step: 1896/530, loss: 0.005238628946244717
2023-01-23 02:55:29.983079: step: 1900/530, loss: 9.098053124034777e-05
2023-01-23 02:55:31.120418: step: 1904/530, loss: 0.0003612518485169858
2023-01-23 02:55:32.245327: step: 1908/530, loss: 0.023641493171453476
2023-01-23 02:55:33.362710: step: 1912/530, loss: 0.007226848974823952
2023-01-23 02:55:34.443492: step: 1916/530, loss: 0.000567531562410295
2023-01-23 02:55:35.567205: step: 1920/530, loss: 0.00747947720810771
2023-01-23 02:55:36.686651: step: 1924/530, loss: 0.00084686279296875
2023-01-23 02:55:37.825278: step: 1928/530, loss: 0.00532608013600111
2023-01-23 02:55:38.952782: step: 1932/530, loss: 0.041840553283691406
2023-01-23 02:55:40.086803: step: 1936/530, loss: 0.028040315955877304
2023-01-23 02:55:41.254274: step: 1940/530, loss: 0.005005550570785999
2023-01-23 02:55:42.406838: step: 1944/530, loss: 0.016727352514863014
2023-01-23 02:55:43.533914: step: 1948/530, loss: 0.01028070505708456
2023-01-23 02:55:44.667005: step: 1952/530, loss: 0.010974694043397903
2023-01-23 02:55:45.806620: step: 1956/530, loss: 0.02663450315594673
2023-01-23 02:55:46.922265: step: 1960/530, loss: 0.0020390511490404606
2023-01-23 02:55:48.042778: step: 1964/530, loss: 0.00036144256591796875
2023-01-23 02:55:49.148502: step: 1968/530, loss: 0.019230175763368607
2023-01-23 02:55:50.263001: step: 1972/530, loss: 0.016310883685946465
2023-01-23 02:55:51.459605: step: 1976/530, loss: 0.05003839731216431
2023-01-23 02:55:52.582168: step: 1980/530, loss: 0.005981254857033491
2023-01-23 02:55:53.706482: step: 1984/530, loss: 0.11145592480897903
2023-01-23 02:55:54.823470: step: 1988/530, loss: 0.00351638812571764
2023-01-23 02:55:55.935156: step: 1992/530, loss: 0.020348692312836647
2023-01-23 02:55:57.053849: step: 1996/530, loss: 0.04157190024852753
2023-01-23 02:55:58.199403: step: 2000/530, loss: 0.015211963094770908
2023-01-23 02:55:59.333326: step: 2004/530, loss: 0.02807140350341797
2023-01-23 02:56:00.445841: step: 2008/530, loss: 0.0052252295427024364
2023-01-23 02:56:01.562058: step: 2012/530, loss: 6.217956251930445e-05
2023-01-23 02:56:02.666856: step: 2016/530, loss: 0.00076041225111112
2023-01-23 02:56:03.788201: step: 2020/530, loss: 0.002292847726494074
2023-01-23 02:56:04.926255: step: 2024/530, loss: 0.010550356470048428
2023-01-23 02:56:06.083149: step: 2028/530, loss: 0.0016943932278081775
2023-01-23 02:56:07.211076: step: 2032/530, loss: 0.00045757292537018657
2023-01-23 02:56:08.352688: step: 2036/530, loss: 0.006670570466667414
2023-01-23 02:56:09.482389: step: 2040/530, loss: 0.03963852301239967
2023-01-23 02:56:10.640925: step: 2044/530, loss: 0.04340400546789169
2023-01-23 02:56:11.758982: step: 2048/530, loss: 0.0006910323863849044
2023-01-23 02:56:12.884581: step: 2052/530, loss: 0.007282257545739412
2023-01-23 02:56:14.007177: step: 2056/530, loss: 0.003734398167580366
2023-01-23 02:56:15.120815: step: 2060/530, loss: 0.11991024017333984
2023-01-23 02:56:16.250034: step: 2064/530, loss: 0.01284322701394558
2023-01-23 02:56:17.388950: step: 2068/530, loss: 0.0004965782281942666
2023-01-23 02:56:18.514144: step: 2072/530, loss: 0.0005380630609579384
2023-01-23 02:56:19.673222: step: 2076/530, loss: 0.018630409613251686
2023-01-23 02:56:20.796201: step: 2080/530, loss: 0.00046854018000885844
2023-01-23 02:56:21.915261: step: 2084/530, loss: 0.005291461944580078
2023-01-23 02:56:23.075838: step: 2088/530, loss: 0.04149685055017471
2023-01-23 02:56:24.201928: step: 2092/530, loss: 0.014782142825424671
2023-01-23 02:56:25.329341: step: 2096/530, loss: 0.02965397760272026
2023-01-23 02:56:26.424884: step: 2100/530, loss: 0.026604272425174713
2023-01-23 02:56:27.557976: step: 2104/530, loss: 0.01924319379031658
2023-01-23 02:56:28.677595: step: 2108/530, loss: 0.010452747344970703
2023-01-23 02:56:29.779503: step: 2112/530, loss: 4.167556471657008e-05
2023-01-23 02:56:30.910135: step: 2116/530, loss: 0.059009552001953125
2023-01-23 02:56:32.017753: step: 2120/530, loss: 0.0021916390396654606
==================================================
Loss: 0.028
--------------------
Dev: {'event': {'p': 0.6031578947368421, 'r': 0.762982689747004, 'f1': 0.673721340388007}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
Test: {'event': {'p': 0.6401463191586648, 'r': 0.8, 'f1': 0.7112014224028448}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
Chinese: {'event': {'p': 0.5376344086021505, 'r': 0.9259259259259259, 'f1': 0.6802721088435373}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
Korean: {'event': {'p': 0.6666666666666666, 'r': 0.5714285714285714, 'f1': 0.6153846153846153}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
Russian: {'event': {'p': 0.3673469387755102, 'r': 0.5, 'f1': 0.42352941176470593}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Chinese: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Chinese: {'event': {'p': 0.6190476190476191, 'r': 0.9629629629629629, 'f1': 0.7536231884057971}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6288770053475936, 'r': 0.7829560585885486, 'f1': 0.697508896797153}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Korean: {'event': {'p': 0.64058795637743, 'r': 0.772, 'f1': 0.7001813941435606}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Korean: {'event': {'p': 0.6851851851851852, 'r': 0.5873015873015873, 'f1': 0.6324786324786325}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5319148936170213, 'r': 0.6944444444444444, 'f1': 0.6024096385542169}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
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 02:57:12.935452: step: 4/530, loss: 0.003492116928100586
2023-01-23 02:57:14.050973: step: 8/530, loss: 0.005364203825592995
2023-01-23 02:57:15.182421: step: 12/530, loss: 0.0005717277526855469
2023-01-23 02:57:16.335310: step: 16/530, loss: 0.025046730414032936
2023-01-23 02:57:17.467475: step: 20/530, loss: 4.634857032215223e-05
2023-01-23 02:57:18.637726: step: 24/530, loss: 0.00041937828063964844
2023-01-23 02:57:19.784417: step: 28/530, loss: 0.032282259315252304
2023-01-23 02:57:20.945037: step: 32/530, loss: 0.004409408662468195
2023-01-23 02:57:22.075332: step: 36/530, loss: 0.0066699981689453125
2023-01-23 02:57:23.201287: step: 40/530, loss: 0.0007936478359624743
2023-01-23 02:57:24.330638: step: 44/530, loss: 0.00171661376953125
2023-01-23 02:57:25.452978: step: 48/530, loss: 0.0035938501823693514
2023-01-23 02:57:26.598026: step: 52/530, loss: 0.0026996610686182976
2023-01-23 02:57:27.694747: step: 56/530, loss: 0.002084350446239114
2023-01-23 02:57:28.810843: step: 60/530, loss: 0.02218923531472683
2023-01-23 02:57:29.944144: step: 64/530, loss: 0.04186049476265907
2023-01-23 02:57:31.036047: step: 68/530, loss: 0.0020511627662926912
2023-01-23 02:57:32.156376: step: 72/530, loss: 0.06073322519659996
2023-01-23 02:57:33.292711: step: 76/530, loss: 0.0005309581756591797
2023-01-23 02:57:34.399303: step: 80/530, loss: 0.001096534775570035
2023-01-23 02:57:35.517392: step: 84/530, loss: 4.615784200723283e-05
2023-01-23 02:57:36.607764: step: 88/530, loss: 5.054474513599416e-06
2023-01-23 02:57:37.732069: step: 92/530, loss: 0.04574775695800781
2023-01-23 02:57:38.872526: step: 96/530, loss: 0.003422737354412675
2023-01-23 02:57:40.005822: step: 100/530, loss: 0.006926917936652899
2023-01-23 02:57:41.109577: step: 104/530, loss: 0.0016969681018963456
2023-01-23 02:57:42.243888: step: 108/530, loss: 0.030000973492860794
2023-01-23 02:57:43.378697: step: 112/530, loss: 0.011799240484833717
2023-01-23 02:57:44.504127: step: 116/530, loss: 0.0037521361373364925
2023-01-23 02:57:45.623442: step: 120/530, loss: 8.015632920432836e-05
2023-01-23 02:57:46.772182: step: 124/530, loss: 0.03898058086633682
2023-01-23 02:57:47.881737: step: 128/530, loss: 0.0015865325694903731
2023-01-23 02:57:49.035821: step: 132/530, loss: 0.014496517367661
2023-01-23 02:57:50.145508: step: 136/530, loss: 0.053733255714178085
2023-01-23 02:57:51.297373: step: 140/530, loss: 0.04569273069500923
2023-01-23 02:57:52.448104: step: 144/530, loss: 0.05728635936975479
2023-01-23 02:57:53.596609: step: 148/530, loss: 0.003631496336311102
2023-01-23 02:57:54.712214: step: 152/530, loss: 0.0008540153503417969
2023-01-23 02:57:55.828659: step: 156/530, loss: 0.02424955554306507
2023-01-23 02:57:56.927555: step: 160/530, loss: 0.007134628482162952
2023-01-23 02:57:58.054665: step: 164/530, loss: 0.0006804466247558594
2023-01-23 02:57:59.194469: step: 168/530, loss: 0.0016426086658611894
2023-01-23 02:58:00.311599: step: 172/530, loss: 0.02122783660888672
2023-01-23 02:58:01.408971: step: 176/530, loss: 0.001952362130396068
2023-01-23 02:58:02.501810: step: 180/530, loss: 0.006259918212890625
2023-01-23 02:58:03.647345: step: 184/530, loss: 0.12352123111486435
2023-01-23 02:58:04.751512: step: 188/530, loss: 0.05261344835162163
2023-01-23 02:58:05.883790: step: 192/530, loss: 0.005612564273178577
2023-01-23 02:58:06.980984: step: 196/530, loss: 0.035167768597602844
2023-01-23 02:58:08.101260: step: 200/530, loss: 0.002225208329036832
2023-01-23 02:58:09.202358: step: 204/530, loss: 0.0011348247062414885
2023-01-23 02:58:10.335646: step: 208/530, loss: 0.01935615763068199
2023-01-23 02:58:11.535752: step: 212/530, loss: 0.00784378033131361
2023-01-23 02:58:12.673616: step: 216/530, loss: 0.008266258984804153
2023-01-23 02:58:13.797291: step: 220/530, loss: 0.0007605552673339844
2023-01-23 02:58:14.921023: step: 224/530, loss: 0.000609970127698034
2023-01-23 02:58:16.041611: step: 228/530, loss: 0.058336831629276276
2023-01-23 02:58:17.149897: step: 232/530, loss: 0.00051794049795717
2023-01-23 02:58:18.246911: step: 236/530, loss: 0.0016651153564453125
2023-01-23 02:58:19.393002: step: 240/530, loss: 0.008790969848632812
2023-01-23 02:58:20.574885: step: 244/530, loss: 0.015874672681093216
2023-01-23 02:58:21.694776: step: 248/530, loss: 0.003860569093376398
2023-01-23 02:58:22.816887: step: 252/530, loss: 0.012919188477098942
2023-01-23 02:58:23.946227: step: 256/530, loss: 0.04431714862585068
2023-01-23 02:58:25.088682: step: 260/530, loss: 0.0068387980572879314
2023-01-23 02:58:26.240006: step: 264/530, loss: 0.04978370666503906
2023-01-23 02:58:27.365270: step: 268/530, loss: 9.512902033748105e-05
2023-01-23 02:58:28.509764: step: 272/530, loss: 0.0001293182431254536
2023-01-23 02:58:29.616012: step: 276/530, loss: 0.000587892543990165
2023-01-23 02:58:30.738405: step: 280/530, loss: 0.02096080780029297
2023-01-23 02:58:31.869918: step: 284/530, loss: 0.0003495216369628906
2023-01-23 02:58:33.001320: step: 288/530, loss: 0.006916618440300226
2023-01-23 02:58:34.107519: step: 292/530, loss: 0.011733626946806908
2023-01-23 02:58:35.218938: step: 296/530, loss: 0.0004991531604900956
2023-01-23 02:58:36.339197: step: 300/530, loss: 0.012934684753417969
2023-01-23 02:58:37.438136: step: 304/530, loss: 0.13992318511009216
2023-01-23 02:58:38.549852: step: 308/530, loss: 0.0005417824140749872
2023-01-23 02:58:39.682922: step: 312/530, loss: 0.01599092409014702
2023-01-23 02:58:40.859850: step: 316/530, loss: 0.0018291473388671875
2023-01-23 02:58:41.981658: step: 320/530, loss: 0.008711909875273705
2023-01-23 02:58:43.107970: step: 324/530, loss: 0.010356903076171875
2023-01-23 02:58:44.250671: step: 328/530, loss: 0.0003834724484477192
2023-01-23 02:58:45.378087: step: 332/530, loss: 0.04784455522894859
2023-01-23 02:58:46.505016: step: 336/530, loss: 0.008853721432387829
2023-01-23 02:58:47.620437: step: 340/530, loss: 0.0016565322875976562
2023-01-23 02:58:48.743132: step: 344/530, loss: 0.0012794494396075606
2023-01-23 02:58:49.870563: step: 348/530, loss: 0.025172902271151543
2023-01-23 02:58:51.008623: step: 352/530, loss: 0.00020275116548873484
2023-01-23 02:58:52.157388: step: 356/530, loss: 0.0015499114524573088
2023-01-23 02:58:53.282117: step: 360/530, loss: 0.020780278369784355
2023-01-23 02:58:54.399274: step: 364/530, loss: 4.6348573960131034e-05
2023-01-23 02:58:55.551291: step: 368/530, loss: 0.017505645751953125
2023-01-23 02:58:56.680275: step: 372/530, loss: 0.011124420911073685
2023-01-23 02:58:57.831120: step: 376/530, loss: 0.0008269369718618691
2023-01-23 02:58:58.971917: step: 380/530, loss: 0.0013065338134765625
2023-01-23 02:59:00.112697: step: 384/530, loss: 0.03151235729455948
2023-01-23 02:59:01.231272: step: 388/530, loss: 9.961127943824977e-05
2023-01-23 02:59:02.350989: step: 392/530, loss: 0.014006709679961205
2023-01-23 02:59:03.462628: step: 396/530, loss: 0.0017796993488445878
2023-01-23 02:59:04.631602: step: 400/530, loss: 0.002540111541748047
2023-01-23 02:59:05.734018: step: 404/530, loss: 0.009089660830795765
2023-01-23 02:59:06.873945: step: 408/530, loss: 0.0313870944082737
2023-01-23 02:59:07.995626: step: 412/530, loss: 0.006443977355957031
2023-01-23 02:59:09.127333: step: 416/530, loss: 0.008953667245805264
2023-01-23 02:59:10.230126: step: 420/530, loss: 0.00019855500431731343
2023-01-23 02:59:11.341966: step: 424/530, loss: 0.04034481197595596
2023-01-23 02:59:12.455528: step: 428/530, loss: 1.602172778802924e-05
2023-01-23 02:59:13.563962: step: 432/530, loss: 5.0067901611328125e-05
2023-01-23 02:59:14.701359: step: 436/530, loss: 0.010254574008286
2023-01-23 02:59:15.796037: step: 440/530, loss: 0.013773727230727673
2023-01-23 02:59:16.900047: step: 444/530, loss: 3.771782212425023e-05
2023-01-23 02:59:18.058406: step: 448/530, loss: 0.0012991904513910413
2023-01-23 02:59:19.167776: step: 452/530, loss: 0.0012516021961346269
2023-01-23 02:59:20.274888: step: 456/530, loss: 0.005177402403205633
2023-01-23 02:59:21.394305: step: 460/530, loss: 0.003760433290153742
2023-01-23 02:59:22.529688: step: 464/530, loss: 0.004835319239646196
2023-01-23 02:59:23.667076: step: 468/530, loss: 0.0021732330787926912
2023-01-23 02:59:24.780465: step: 472/530, loss: 0.0026501654647290707
2023-01-23 02:59:25.867846: step: 476/530, loss: 0.00015466808690689504
2023-01-23 02:59:27.022956: step: 480/530, loss: 0.0006868839845992625
2023-01-23 02:59:28.151056: step: 484/530, loss: 0.020505379885435104
2023-01-23 02:59:29.265245: step: 488/530, loss: 0.001527500106021762
2023-01-23 02:59:30.400965: step: 492/530, loss: 0.0009910583030432463
2023-01-23 02:59:31.489929: step: 496/530, loss: 0.004509925842285156
2023-01-23 02:59:32.593514: step: 500/530, loss: 0.0008550644270144403
2023-01-23 02:59:33.726596: step: 504/530, loss: 0.0003814697265625
2023-01-23 02:59:34.836068: step: 508/530, loss: 0.000613784824963659
2023-01-23 02:59:35.971640: step: 512/530, loss: 0.09463000297546387
2023-01-23 02:59:37.093391: step: 516/530, loss: 4.024505687993951e-05
2023-01-23 02:59:38.217390: step: 520/530, loss: 0.004937934689223766
2023-01-23 02:59:39.358893: step: 524/530, loss: 0.024849414825439453
2023-01-23 02:59:40.490141: step: 528/530, loss: 0.09353499114513397
2023-01-23 02:59:41.596752: step: 532/530, loss: -6.10351571594947e-06
2023-01-23 02:59:42.731221: step: 536/530, loss: 5.7220458984375e-06
2023-01-23 02:59:43.856972: step: 540/530, loss: 0.011748313903808594
2023-01-23 02:59:45.003330: step: 544/530, loss: 0.015749692916870117
2023-01-23 02:59:46.105541: step: 548/530, loss: 0.009624290280044079
2023-01-23 02:59:47.236876: step: 552/530, loss: 0.03919219970703125
2023-01-23 02:59:48.355879: step: 556/530, loss: 0.0007454872247762978
2023-01-23 02:59:49.455065: step: 560/530, loss: 0.00033988954965025187
2023-01-23 02:59:50.594689: step: 564/530, loss: 1.1444092706369702e-05
2023-01-23 02:59:51.719020: step: 568/530, loss: 0.0009068488725461066
2023-01-23 02:59:52.840582: step: 572/530, loss: 0.0001710891810944304
2023-01-23 02:59:53.993795: step: 576/530, loss: 0.01419143658131361
2023-01-23 02:59:55.177919: step: 580/530, loss: 2.822876012942288e-05
2023-01-23 02:59:56.293292: step: 584/530, loss: 0.011102009564638138
2023-01-23 02:59:57.421851: step: 588/530, loss: 0.0011966705787926912
2023-01-23 02:59:58.540097: step: 592/530, loss: 0.00020194053649902344
2023-01-23 02:59:59.672094: step: 596/530, loss: 0.1919269561767578
2023-01-23 03:00:00.809749: step: 600/530, loss: 0.00882654171437025
2023-01-23 03:00:01.929482: step: 604/530, loss: 0.0003261566162109375
2023-01-23 03:00:03.041992: step: 608/530, loss: 0.022101402282714844
2023-01-23 03:00:04.158693: step: 612/530, loss: 0.024153614416718483
2023-01-23 03:00:05.282959: step: 616/530, loss: 0.0008025646093301475
2023-01-23 03:00:06.416808: step: 620/530, loss: 0.027393151074647903
2023-01-23 03:00:07.553622: step: 624/530, loss: 0.0010135173797607422
2023-01-23 03:00:08.698252: step: 628/530, loss: 0.013886069878935814
2023-01-23 03:00:09.846860: step: 632/530, loss: 0.00018999577150680125
2023-01-23 03:00:10.987830: step: 636/530, loss: 0.011508369818329811
2023-01-23 03:00:12.106776: step: 640/530, loss: 0.004253101069480181
2023-01-23 03:00:13.217187: step: 644/530, loss: 0.031964682042598724
2023-01-23 03:00:14.326444: step: 648/530, loss: 0.007214928045868874
2023-01-23 03:00:15.479814: step: 652/530, loss: 0.0011971474159508944
2023-01-23 03:00:16.582905: step: 656/530, loss: 0.010186959058046341
2023-01-23 03:00:17.717663: step: 660/530, loss: 0.0019048691028729081
2023-01-23 03:00:18.844056: step: 664/530, loss: 0.0010955811012536287
2023-01-23 03:00:19.973908: step: 668/530, loss: 0.0305909626185894
2023-01-23 03:00:21.070792: step: 672/530, loss: 0.00156574253924191
2023-01-23 03:00:22.210621: step: 676/530, loss: 0.02763528749346733
2023-01-23 03:00:23.360706: step: 680/530, loss: 0.003212451934814453
2023-01-23 03:00:24.496948: step: 684/530, loss: 0.00037021638127043843
2023-01-23 03:00:25.624747: step: 688/530, loss: 0.00656471261754632
2023-01-23 03:00:26.725875: step: 692/530, loss: 0.047976307570934296
2023-01-23 03:00:27.856563: step: 696/530, loss: 0.0029567719902843237
2023-01-23 03:00:28.973443: step: 700/530, loss: 0.00097827916033566
2023-01-23 03:00:30.102087: step: 704/530, loss: 0.24476879835128784
2023-01-23 03:00:31.266015: step: 708/530, loss: 0.004502773284912109
2023-01-23 03:00:32.393253: step: 712/530, loss: 0.0003572463756427169
2023-01-23 03:00:33.539956: step: 716/530, loss: 0.03177185356616974
2023-01-23 03:00:34.688030: step: 720/530, loss: 0.0020856859628111124
2023-01-23 03:00:35.803697: step: 724/530, loss: 0.0014862060779705644
2023-01-23 03:00:36.898276: step: 728/530, loss: 0.00334415421821177
2023-01-23 03:00:38.005055: step: 732/530, loss: 0.00809183157980442
2023-01-23 03:00:39.096387: step: 736/530, loss: 0.0019266129238530993
2023-01-23 03:00:40.200759: step: 740/530, loss: 0.0009130477556027472
2023-01-23 03:00:41.312100: step: 744/530, loss: 0.015190697275102139
2023-01-23 03:00:42.450269: step: 748/530, loss: 0.026973916217684746
2023-01-23 03:00:43.580408: step: 752/530, loss: 5.14984139954322e-06
2023-01-23 03:00:44.681823: step: 756/530, loss: 0.0015502453316003084
2023-01-23 03:00:45.806199: step: 760/530, loss: 0.00027551653329283
2023-01-23 03:00:46.925606: step: 764/530, loss: 0.008426999673247337
2023-01-23 03:00:48.105696: step: 768/530, loss: 0.05790691822767258
2023-01-23 03:00:49.225165: step: 772/530, loss: 0.003280830569565296
2023-01-23 03:00:50.320833: step: 776/530, loss: 0.005009079352021217
2023-01-23 03:00:51.473724: step: 780/530, loss: 0.009288978762924671
2023-01-23 03:00:52.591924: step: 784/530, loss: 0.18046382069587708
2023-01-23 03:00:53.708251: step: 788/530, loss: 0.01253962516784668
2023-01-23 03:00:54.805306: step: 792/530, loss: 3.757476952159777e-05
2023-01-23 03:00:55.942452: step: 796/530, loss: 0.028840254992246628
2023-01-23 03:00:57.059404: step: 800/530, loss: 0.0027150153182446957
2023-01-23 03:00:58.175666: step: 804/530, loss: 0.011242866516113281
2023-01-23 03:00:59.294966: step: 808/530, loss: 0.030660152435302734
2023-01-23 03:01:00.431993: step: 812/530, loss: 0.0011314869625493884
2023-01-23 03:01:01.562083: step: 816/530, loss: 0.07943210750818253
2023-01-23 03:01:02.692356: step: 820/530, loss: 0.0005268097156658769
2023-01-23 03:01:03.819160: step: 824/530, loss: 0.0015645623207092285
2023-01-23 03:01:04.930577: step: 828/530, loss: 0.00013427734666038305
2023-01-23 03:01:06.031925: step: 832/530, loss: 0.012929343618452549
2023-01-23 03:01:07.146941: step: 836/530, loss: 0.002537250518798828
2023-01-23 03:01:08.243443: step: 840/530, loss: 0.007545280735939741
2023-01-23 03:01:09.352883: step: 844/530, loss: 0.008433151058852673
2023-01-23 03:01:10.470334: step: 848/530, loss: 0.0005313873407430947
2023-01-23 03:01:11.595676: step: 852/530, loss: 0.007874488830566406
2023-01-23 03:01:12.702710: step: 856/530, loss: 0.034624479711055756
2023-01-23 03:01:13.829563: step: 860/530, loss: 0.023485302925109863
2023-01-23 03:01:14.955834: step: 864/530, loss: 0.0033110626973211765
2023-01-23 03:01:16.058150: step: 868/530, loss: 0.009881210513412952
2023-01-23 03:01:17.164797: step: 872/530, loss: 0.001555633614771068
2023-01-23 03:01:18.308320: step: 876/530, loss: 0.04731525853276253
2023-01-23 03:01:19.432539: step: 880/530, loss: 0.002470779698342085
2023-01-23 03:01:20.569934: step: 884/530, loss: 0.023133039474487305
2023-01-23 03:01:21.708055: step: 888/530, loss: 0.022152137011289597
2023-01-23 03:01:22.841916: step: 892/530, loss: 0.005645895376801491
2023-01-23 03:01:23.965842: step: 896/530, loss: 0.0006113052368164062
2023-01-23 03:01:25.089443: step: 900/530, loss: 0.0030487061012536287
2023-01-23 03:01:26.193181: step: 904/530, loss: 0.006674480624496937
2023-01-23 03:01:27.332014: step: 908/530, loss: 0.054091643542051315
2023-01-23 03:01:28.426553: step: 912/530, loss: 0.0004943847889080644
2023-01-23 03:01:29.547776: step: 916/530, loss: 0.004277515225112438
2023-01-23 03:01:30.666275: step: 920/530, loss: 0.015009785071015358
2023-01-23 03:01:31.785175: step: 924/530, loss: 0.013983441516757011
2023-01-23 03:01:32.922504: step: 928/530, loss: 0.0004916191101074219
2023-01-23 03:01:34.051036: step: 932/530, loss: 0.004873562138527632
2023-01-23 03:01:35.162865: step: 936/530, loss: 0.0009518623119220138
2023-01-23 03:01:36.298199: step: 940/530, loss: 0.0010462760692462325
2023-01-23 03:01:37.401671: step: 944/530, loss: 3.33309180859942e-05
2023-01-23 03:01:38.537015: step: 948/530, loss: 0.00010976791236316785
2023-01-23 03:01:39.668149: step: 952/530, loss: 0.0505407340824604
2023-01-23 03:01:40.804193: step: 956/530, loss: 0.00014715194993186742
2023-01-23 03:01:41.924611: step: 960/530, loss: 0.02407236211001873
2023-01-23 03:01:43.036696: step: 964/530, loss: 0.005028247833251953
2023-01-23 03:01:44.168594: step: 968/530, loss: 0.0656309649348259
2023-01-23 03:01:45.331573: step: 972/530, loss: 0.1735997200012207
2023-01-23 03:01:46.508130: step: 976/530, loss: 0.3993709683418274
2023-01-23 03:01:47.620555: step: 980/530, loss: 0.0008949280017986894
2023-01-23 03:01:48.718135: step: 984/530, loss: 0.00274846563115716
2023-01-23 03:01:49.855026: step: 988/530, loss: 0.00064768799347803
2023-01-23 03:01:50.965939: step: 992/530, loss: 0.00041980744572356343
2023-01-23 03:01:52.041169: step: 996/530, loss: 0.0011851787567138672
2023-01-23 03:01:53.157880: step: 1000/530, loss: 0.0005203246837481856
2023-01-23 03:01:54.272497: step: 1004/530, loss: 3.5762791412707884e-06
2023-01-23 03:01:55.390743: step: 1008/530, loss: 0.10134754329919815
2023-01-23 03:01:56.505516: step: 1012/530, loss: 0.030083274468779564
2023-01-23 03:01:57.624293: step: 1016/530, loss: 0.013525581918656826
2023-01-23 03:01:58.773512: step: 1020/530, loss: 0.030022429302334785
2023-01-23 03:01:59.905654: step: 1024/530, loss: 0.0025085448287427425
2023-01-23 03:02:01.031875: step: 1028/530, loss: 0.0027269364800304174
2023-01-23 03:02:02.149768: step: 1032/530, loss: 0.0010020255576819181
2023-01-23 03:02:03.299867: step: 1036/530, loss: 0.0005570889334194362
2023-01-23 03:02:04.412450: step: 1040/530, loss: 0.0043961526826024055
2023-01-23 03:02:05.539749: step: 1044/530, loss: 0.00017080307588912547
2023-01-23 03:02:06.662868: step: 1048/530, loss: 0.009051132947206497
2023-01-23 03:02:07.800184: step: 1052/530, loss: 0.00014219284639693797
2023-01-23 03:02:08.946481: step: 1056/530, loss: 5.545616295421496e-05
2023-01-23 03:02:10.052846: step: 1060/530, loss: 0.018744181841611862
2023-01-23 03:02:11.164663: step: 1064/530, loss: 0.0028033496346324682
2023-01-23 03:02:12.269369: step: 1068/530, loss: 0.00042953493539243937
2023-01-23 03:02:13.419093: step: 1072/530, loss: 0.02830658107995987
2023-01-23 03:02:14.537691: step: 1076/530, loss: 0.0004821777401957661
2023-01-23 03:02:15.690784: step: 1080/530, loss: 0.0017843246459960938
2023-01-23 03:02:16.799751: step: 1084/530, loss: 0.02479691617190838
2023-01-23 03:02:17.940734: step: 1088/530, loss: 0.0014714241260662675
2023-01-23 03:02:19.076313: step: 1092/530, loss: 0.004219436552375555
2023-01-23 03:02:20.204565: step: 1096/530, loss: 0.0013544083340093493
2023-01-23 03:02:21.308560: step: 1100/530, loss: 0.00019931793212890625
2023-01-23 03:02:22.412947: step: 1104/530, loss: 4.520416405284777e-05
2023-01-23 03:02:23.539391: step: 1108/530, loss: 0.019473552703857422
2023-01-23 03:02:24.646443: step: 1112/530, loss: 0.025881005451083183
2023-01-23 03:02:25.772432: step: 1116/530, loss: 0.0013722418807446957
2023-01-23 03:02:26.908408: step: 1120/530, loss: 0.004391098394989967
2023-01-23 03:02:28.027841: step: 1124/530, loss: 0.0010742187732830644
2023-01-23 03:02:29.158293: step: 1128/530, loss: 0.0005341530195437372
2023-01-23 03:02:30.291784: step: 1132/530, loss: 0.0001489639253122732
2023-01-23 03:02:31.427212: step: 1136/530, loss: 0.08273229748010635
2023-01-23 03:02:32.580780: step: 1140/530, loss: 0.11430750042200089
2023-01-23 03:02:33.705870: step: 1144/530, loss: 0.021305561065673828
2023-01-23 03:02:34.803704: step: 1148/530, loss: 0.00949850119650364
2023-01-23 03:02:35.962932: step: 1152/530, loss: 0.04888945072889328
2023-01-23 03:02:37.076705: step: 1156/530, loss: 0.005693912506103516
2023-01-23 03:02:38.201624: step: 1160/530, loss: 0.11261558532714844
2023-01-23 03:02:39.297693: step: 1164/530, loss: 0.027210427448153496
2023-01-23 03:02:40.453620: step: 1168/530, loss: 0.0071239471435546875
2023-01-23 03:02:41.602187: step: 1172/530, loss: 0.0012688637943938375
2023-01-23 03:02:42.705115: step: 1176/530, loss: 0.001516151474788785
2023-01-23 03:02:43.818865: step: 1180/530, loss: 0.00017681121244095266
2023-01-23 03:02:44.933338: step: 1184/530, loss: 0.00855789240449667
2023-01-23 03:02:46.048523: step: 1188/530, loss: 0.0005306244711391628
2023-01-23 03:02:47.176767: step: 1192/530, loss: 5.817413330078125e-05
2023-01-23 03:02:48.291818: step: 1196/530, loss: 3.2138825190486386e-05
2023-01-23 03:02:49.411176: step: 1200/530, loss: 0.019547080621123314
2023-01-23 03:02:50.539019: step: 1204/530, loss: 0.0007558584329672158
2023-01-23 03:02:51.668269: step: 1208/530, loss: 7.762909081066027e-05
2023-01-23 03:02:52.788703: step: 1212/530, loss: 0.0007013321155682206
2023-01-23 03:02:53.926697: step: 1216/530, loss: 0.008767413906753063
2023-01-23 03:02:55.038638: step: 1220/530, loss: 0.0013755798572674394
2023-01-23 03:02:56.165647: step: 1224/530, loss: 0.018554305657744408
2023-01-23 03:02:57.294848: step: 1228/530, loss: 0.004549598786979914
2023-01-23 03:02:58.427878: step: 1232/530, loss: 0.03680025413632393
2023-01-23 03:02:59.565767: step: 1236/530, loss: 2.593994213384576e-05
2023-01-23 03:03:00.702890: step: 1240/530, loss: 0.00108680734410882
2023-01-23 03:03:01.822868: step: 1244/530, loss: 0.1470225304365158
2023-01-23 03:03:02.987046: step: 1248/530, loss: 0.002731609158217907
2023-01-23 03:03:04.136316: step: 1252/530, loss: 0.004733753390610218
2023-01-23 03:03:05.236205: step: 1256/530, loss: 0.02032909356057644
2023-01-23 03:03:06.342471: step: 1260/530, loss: 0.0007720947614870965
2023-01-23 03:03:07.446703: step: 1264/530, loss: 0.0003725051647052169
2023-01-23 03:03:08.590189: step: 1268/530, loss: 0.00889434851706028
2023-01-23 03:03:09.718938: step: 1272/530, loss: 0.009014797396957874
2023-01-23 03:03:10.844267: step: 1276/530, loss: 0.004097938537597656
2023-01-23 03:03:11.962107: step: 1280/530, loss: 0.00443954486399889
2023-01-23 03:03:13.092428: step: 1284/530, loss: 0.014520931988954544
2023-01-23 03:03:14.200096: step: 1288/530, loss: 0.006578922271728516
2023-01-23 03:03:15.331636: step: 1292/530, loss: 0.0069830892607569695
2023-01-23 03:03:16.456306: step: 1296/530, loss: 0.014919447712600231
2023-01-23 03:03:17.558625: step: 1300/530, loss: 0.007106971926987171
2023-01-23 03:03:18.679985: step: 1304/530, loss: 0.01165771484375
2023-01-23 03:03:19.785738: step: 1308/530, loss: 0.00011310577247058973
2023-01-23 03:03:20.927322: step: 1312/530, loss: 0.020130671560764313
2023-01-23 03:03:22.046457: step: 1316/530, loss: 0.006555354222655296
2023-01-23 03:03:23.179029: step: 1320/530, loss: 0.02274184301495552
2023-01-23 03:03:24.300260: step: 1324/530, loss: 0.013712692074477673
2023-01-23 03:03:25.463269: step: 1328/530, loss: 0.0002461433468852192
2023-01-23 03:03:26.588456: step: 1332/530, loss: 0.11550893634557724
2023-01-23 03:03:27.753819: step: 1336/530, loss: 0.005647087469696999
2023-01-23 03:03:28.869375: step: 1340/530, loss: 0.016373634338378906
2023-01-23 03:03:30.017214: step: 1344/530, loss: 0.006379890255630016
2023-01-23 03:03:31.161405: step: 1348/530, loss: 0.0027209282852709293
2023-01-23 03:03:32.341151: step: 1352/530, loss: 0.0001642227143747732
2023-01-23 03:03:33.454338: step: 1356/530, loss: 6.675720942439511e-05
2023-01-23 03:03:34.580896: step: 1360/530, loss: 0.0002590179501567036
2023-01-23 03:03:35.701880: step: 1364/530, loss: -9.5367431640625e-07
2023-01-23 03:03:36.829149: step: 1368/530, loss: 0.0009847640758380294
2023-01-23 03:03:37.942999: step: 1372/530, loss: 0.00058918003924191
2023-01-23 03:03:39.082305: step: 1376/530, loss: 0.008688544854521751
2023-01-23 03:03:40.204029: step: 1380/530, loss: 0.0005656242137774825
2023-01-23 03:03:41.319560: step: 1384/530, loss: 0.03173980861902237
2023-01-23 03:03:42.455772: step: 1388/530, loss: 0.0014307021629065275
2023-01-23 03:03:43.583037: step: 1392/530, loss: 0.008229827508330345
2023-01-23 03:03:44.705842: step: 1396/530, loss: 0.0028060912154614925
2023-01-23 03:03:45.842144: step: 1400/530, loss: 0.0014524459838867188
2023-01-23 03:03:46.974128: step: 1404/530, loss: 8.544921729480848e-05
2023-01-23 03:03:48.069277: step: 1408/530, loss: 0.0009904861217364669
2023-01-23 03:03:49.176736: step: 1412/530, loss: 0.008179950527846813
2023-01-23 03:03:50.277001: step: 1416/530, loss: 0.004760551266372204
2023-01-23 03:03:51.402099: step: 1420/530, loss: 0.0002079010009765625
2023-01-23 03:03:52.504893: step: 1424/530, loss: 0.016332244500517845
2023-01-23 03:03:53.619629: step: 1428/530, loss: 0.0004106521955691278
2023-01-23 03:03:54.748401: step: 1432/530, loss: 0.002635669894516468
2023-01-23 03:03:55.849550: step: 1436/530, loss: 0.06290683895349503
2023-01-23 03:03:56.979586: step: 1440/530, loss: 0.04638051986694336
2023-01-23 03:03:58.122172: step: 1444/530, loss: 0.01473770197480917
2023-01-23 03:03:59.250896: step: 1448/530, loss: 0.005959844682365656
2023-01-23 03:04:00.409212: step: 1452/530, loss: 0.00367488875053823
2023-01-23 03:04:01.533627: step: 1456/530, loss: 0.009038162417709827
2023-01-23 03:04:02.665421: step: 1460/530, loss: 0.0011934281792491674
2023-01-23 03:04:03.794880: step: 1464/530, loss: 0.06364183127880096
2023-01-23 03:04:04.940523: step: 1468/530, loss: 0.0006703451508656144
2023-01-23 03:04:06.072915: step: 1472/530, loss: 0.041925955563783646
2023-01-23 03:04:07.228954: step: 1476/530, loss: 0.004572487436234951
2023-01-23 03:04:08.389027: step: 1480/530, loss: 0.0020816803444176912
2023-01-23 03:04:09.509879: step: 1484/530, loss: 0.049416329711675644
2023-01-23 03:04:10.647149: step: 1488/530, loss: 0.00034084319486282766
2023-01-23 03:04:11.748671: step: 1492/530, loss: 0.00028295518131926656
2023-01-23 03:04:12.864846: step: 1496/530, loss: 0.026113128289580345
2023-01-23 03:04:14.000518: step: 1500/530, loss: 0.0002037048398051411
2023-01-23 03:04:15.125608: step: 1504/530, loss: 0.00041561125544831157
2023-01-23 03:04:16.252427: step: 1508/530, loss: 0.05303821712732315
2023-01-23 03:04:17.395394: step: 1512/530, loss: 0.02392749860882759
2023-01-23 03:04:18.503519: step: 1516/530, loss: 0.0012850761413574219
2023-01-23 03:04:19.635462: step: 1520/530, loss: 0.0007338523864746094
2023-01-23 03:04:20.763278: step: 1524/530, loss: 0.03653021156787872
2023-01-23 03:04:21.891230: step: 1528/530, loss: 6.036758713889867e-05
2023-01-23 03:04:23.018380: step: 1532/530, loss: 0.0009331703186035156
2023-01-23 03:04:24.111387: step: 1536/530, loss: 2.5081633793888614e-05
2023-01-23 03:04:25.258211: step: 1540/530, loss: 0.022811509668827057
2023-01-23 03:04:26.362939: step: 1544/530, loss: 0.0011051178444176912
2023-01-23 03:04:27.502001: step: 1548/530, loss: 0.0017063140403479338
2023-01-23 03:04:28.642542: step: 1552/530, loss: 0.054059792309999466
2023-01-23 03:04:29.801652: step: 1556/530, loss: 0.0027456283569335938
2023-01-23 03:04:30.953156: step: 1560/530, loss: 0.0030750276055186987
2023-01-23 03:04:32.099104: step: 1564/530, loss: 0.005989265628159046
2023-01-23 03:04:33.215060: step: 1568/530, loss: 0.00015435219393111765
2023-01-23 03:04:34.368654: step: 1572/530, loss: 0.015616798773407936
2023-01-23 03:04:35.517644: step: 1576/530, loss: 0.01568317413330078
2023-01-23 03:04:36.615916: step: 1580/530, loss: 0.00026035308837890625
2023-01-23 03:04:37.747659: step: 1584/530, loss: 0.0040832520462572575
2023-01-23 03:04:38.895222: step: 1588/530, loss: 0.004078674595803022
2023-01-23 03:04:40.035867: step: 1592/530, loss: 0.0016664504073560238
2023-01-23 03:04:41.170051: step: 1596/530, loss: 0.0007556438213214278
2023-01-23 03:04:42.330044: step: 1600/530, loss: 0.24110937118530273
2023-01-23 03:04:43.472389: step: 1604/530, loss: 0.003024292178452015
2023-01-23 03:04:44.586610: step: 1608/530, loss: 0.00032835008460097015
2023-01-23 03:04:45.712965: step: 1612/530, loss: 6.27517729299143e-05
2023-01-23 03:04:46.852472: step: 1616/530, loss: 0.044755078852176666
2023-01-23 03:04:47.967130: step: 1620/530, loss: 0.029242467135190964
2023-01-23 03:04:49.086715: step: 1624/530, loss: 0.009463501162827015
2023-01-23 03:04:50.221884: step: 1628/530, loss: 0.0005584716564044356
2023-01-23 03:04:51.342876: step: 1632/530, loss: 0.000999069306999445
2023-01-23 03:04:52.478450: step: 1636/530, loss: 0.016724014654755592
2023-01-23 03:04:53.652911: step: 1640/530, loss: 0.03345947340130806
2023-01-23 03:04:54.805866: step: 1644/530, loss: 0.017365837469697
2023-01-23 03:04:55.947255: step: 1648/530, loss: 0.02520732954144478
2023-01-23 03:04:57.048389: step: 1652/530, loss: 0.016848569735884666
2023-01-23 03:04:58.217172: step: 1656/530, loss: 0.003930568695068359
2023-01-23 03:04:59.346500: step: 1660/530, loss: 0.9112082123756409
2023-01-23 03:05:00.481773: step: 1664/530, loss: 0.02328939363360405
2023-01-23 03:05:01.625926: step: 1668/530, loss: 0.0008285999647341669
2023-01-23 03:05:02.779345: step: 1672/530, loss: 0.07141170650720596
2023-01-23 03:05:03.884497: step: 1676/530, loss: 0.02132892608642578
2023-01-23 03:05:04.973726: step: 1680/530, loss: 0.00040721893310546875
2023-01-23 03:05:06.130230: step: 1684/530, loss: 0.010220217518508434
2023-01-23 03:05:07.275374: step: 1688/530, loss: 0.06932849436998367
2023-01-23 03:05:08.383955: step: 1692/530, loss: 0.06803293526172638
2023-01-23 03:05:09.508706: step: 1696/530, loss: 0.08004798740148544
2023-01-23 03:05:10.615894: step: 1700/530, loss: 0.0005786895635537803
2023-01-23 03:05:11.744528: step: 1704/530, loss: 0.03284940868616104
2023-01-23 03:05:12.857642: step: 1708/530, loss: 0.0008985519525595009
2023-01-23 03:05:13.964359: step: 1712/530, loss: 0.028046132996678352
2023-01-23 03:05:15.119506: step: 1716/530, loss: 0.0070892334915697575
2023-01-23 03:05:16.235562: step: 1720/530, loss: 0.0024843693245202303
2023-01-23 03:05:17.365576: step: 1724/530, loss: 0.0004583120462484658
2023-01-23 03:05:18.516362: step: 1728/530, loss: 0.0011644839541986585
2023-01-23 03:05:19.601046: step: 1732/530, loss: 0.0013417721493169665
2023-01-23 03:05:20.744391: step: 1736/530, loss: 0.019415998831391335
2023-01-23 03:05:21.861036: step: 1740/530, loss: 3.4999848139705136e-05
2023-01-23 03:05:23.011640: step: 1744/530, loss: 0.018818091601133347
2023-01-23 03:05:24.112207: step: 1748/530, loss: 0.16344338655471802
2023-01-23 03:05:25.245020: step: 1752/530, loss: 0.027814865112304688
2023-01-23 03:05:26.362814: step: 1756/530, loss: 9.880065772449598e-05
2023-01-23 03:05:27.482549: step: 1760/530, loss: 0.020299339666962624
2023-01-23 03:05:28.611691: step: 1764/530, loss: 0.0011214256519451737
2023-01-23 03:05:29.698834: step: 1768/530, loss: 0.01122283935546875
2023-01-23 03:05:30.807285: step: 1772/530, loss: 0.014534950256347656
2023-01-23 03:05:31.985856: step: 1776/530, loss: 0.00034122465876862407
2023-01-23 03:05:33.122068: step: 1780/530, loss: 0.00016117095947265625
2023-01-23 03:05:34.247068: step: 1784/530, loss: 0.051281023770570755
2023-01-23 03:05:35.401776: step: 1788/530, loss: 5.664825584972277e-05
2023-01-23 03:05:36.505788: step: 1792/530, loss: 0.033597756177186966
2023-01-23 03:05:37.627586: step: 1796/530, loss: 0.012615203857421875
2023-01-23 03:05:38.746307: step: 1800/530, loss: 0.008051300421357155
2023-01-23 03:05:39.864401: step: 1804/530, loss: 0.00047912599984556437
2023-01-23 03:05:40.984181: step: 1808/530, loss: 0.04170174524188042
2023-01-23 03:05:42.108850: step: 1812/530, loss: 0.00012054443504894152
2023-01-23 03:05:43.262555: step: 1816/530, loss: 0.005619430914521217
2023-01-23 03:05:44.427768: step: 1820/530, loss: 0.07227249443531036
2023-01-23 03:05:45.563677: step: 1824/530, loss: 0.009703541174530983
2023-01-23 03:05:46.714433: step: 1828/530, loss: 0.0016011715633794665
2023-01-23 03:05:47.862025: step: 1832/530, loss: 0.00013809205847792327
2023-01-23 03:05:49.004847: step: 1836/530, loss: 0.0012617112370207906
2023-01-23 03:05:50.121979: step: 1840/530, loss: 0.005458927247673273
2023-01-23 03:05:51.233371: step: 1844/530, loss: 0.0007686614990234375
2023-01-23 03:05:52.361331: step: 1848/530, loss: 0.06442709267139435
2023-01-23 03:05:53.489354: step: 1852/530, loss: 0.0006074905395507812
2023-01-23 03:05:54.624133: step: 1856/530, loss: 0.0691281333565712
2023-01-23 03:05:55.768468: step: 1860/530, loss: 0.013582325540482998
2023-01-23 03:05:56.891949: step: 1864/530, loss: 0.059889983385801315
2023-01-23 03:05:58.017257: step: 1868/530, loss: 0.006908893585205078
2023-01-23 03:05:59.128772: step: 1872/530, loss: 0.013760089874267578
2023-01-23 03:06:00.265806: step: 1876/530, loss: 0.6280676126480103
2023-01-23 03:06:01.377337: step: 1880/530, loss: 0.011935186572372913
2023-01-23 03:06:02.512939: step: 1884/530, loss: 0.01847400702536106
2023-01-23 03:06:03.660369: step: 1888/530, loss: 0.00018305779667571187
2023-01-23 03:06:04.761459: step: 1892/530, loss: 0.028408478945493698
2023-01-23 03:06:05.864782: step: 1896/530, loss: 0.007440042681992054
2023-01-23 03:06:06.986099: step: 1900/530, loss: 0.004222298040986061
2023-01-23 03:06:08.106826: step: 1904/530, loss: 0.00036523339804261923
2023-01-23 03:06:09.242154: step: 1908/530, loss: 0.025418665260076523
2023-01-23 03:06:10.367187: step: 1912/530, loss: 0.021502310410141945
2023-01-23 03:06:11.504570: step: 1916/530, loss: 0.0028753280639648438
2023-01-23 03:06:12.605728: step: 1920/530, loss: 0.0015292167663574219
2023-01-23 03:06:13.712929: step: 1924/530, loss: 0.019933605566620827
2023-01-23 03:06:14.835392: step: 1928/530, loss: 0.01926102675497532
2023-01-23 03:06:15.983246: step: 1932/530, loss: 0.04358353465795517
2023-01-23 03:06:17.069453: step: 1936/530, loss: 0.003917980007827282
2023-01-23 03:06:18.202566: step: 1940/530, loss: 0.002247762866318226
2023-01-23 03:06:19.340018: step: 1944/530, loss: 0.017661094665527344
2023-01-23 03:06:20.455651: step: 1948/530, loss: 0.03859272226691246
2023-01-23 03:06:21.604169: step: 1952/530, loss: 0.0017878531944006681
2023-01-23 03:06:22.723631: step: 1956/530, loss: 0.005416774656623602
2023-01-23 03:06:23.812878: step: 1960/530, loss: 0.00261096959002316
2023-01-23 03:06:24.905018: step: 1964/530, loss: 0.00031609536381438375
2023-01-23 03:06:26.020643: step: 1968/530, loss: 0.011586189270019531
2023-01-23 03:06:27.145211: step: 1972/530, loss: 0.02148418314754963
2023-01-23 03:06:28.274486: step: 1976/530, loss: 0.029879190027713776
2023-01-23 03:06:29.403368: step: 1980/530, loss: 0.024985410273075104
2023-01-23 03:06:30.502810: step: 1984/530, loss: 0.00131988525390625
2023-01-23 03:06:31.657693: step: 1988/530, loss: 0.0020587921608239412
2023-01-23 03:06:32.804940: step: 1992/530, loss: 0.0026371001731604338
2023-01-23 03:06:33.941941: step: 1996/530, loss: 0.01129989605396986
2023-01-23 03:06:35.115273: step: 2000/530, loss: 0.04454651102423668
2023-01-23 03:06:36.246127: step: 2004/530, loss: 0.13999152183532715
2023-01-23 03:06:37.383274: step: 2008/530, loss: 0.0035488130524754524
2023-01-23 03:06:38.516959: step: 2012/530, loss: 0.03099670447409153
2023-01-23 03:06:39.640055: step: 2016/530, loss: 0.005949592683464289
2023-01-23 03:06:40.788818: step: 2020/530, loss: 0.0419921912252903
2023-01-23 03:06:41.923679: step: 2024/530, loss: 0.016417408362030983
2023-01-23 03:06:43.084449: step: 2028/530, loss: 0.0002111435023834929
2023-01-23 03:06:44.225264: step: 2032/530, loss: 0.006318187806755304
2023-01-23 03:06:45.342987: step: 2036/530, loss: 0.0040801046416163445
2023-01-23 03:06:46.496899: step: 2040/530, loss: 0.023645877838134766
2023-01-23 03:06:47.630665: step: 2044/530, loss: 0.0011806488037109375
2023-01-23 03:06:48.749129: step: 2048/530, loss: 1.182556115963962e-05
2023-01-23 03:06:49.878088: step: 2052/530, loss: 0.000301551801385358
2023-01-23 03:06:50.982066: step: 2056/530, loss: 0.02842610329389572
2023-01-23 03:06:52.128784: step: 2060/530, loss: 0.005990887060761452
2023-01-23 03:06:53.281106: step: 2064/530, loss: 0.08526048809289932
2023-01-23 03:06:54.408723: step: 2068/530, loss: 0.030737783759832382
2023-01-23 03:06:55.527290: step: 2072/530, loss: 0.001333856605924666
2023-01-23 03:06:56.655791: step: 2076/530, loss: 0.00181665422860533
2023-01-23 03:06:57.779498: step: 2080/530, loss: 0.0009383201831951737
2023-01-23 03:06:58.908602: step: 2084/530, loss: 0.07532806694507599
2023-01-23 03:07:00.041333: step: 2088/530, loss: 0.05594940483570099
2023-01-23 03:07:01.185655: step: 2092/530, loss: 0.0026920319069176912
2023-01-23 03:07:02.342211: step: 2096/530, loss: 0.0017239570152014494
2023-01-23 03:07:03.475527: step: 2100/530, loss: 0.0021383287385106087
2023-01-23 03:07:04.640843: step: 2104/530, loss: 0.0056875706650316715
2023-01-23 03:07:05.816989: step: 2108/530, loss: 0.02622518688440323
2023-01-23 03:07:06.918735: step: 2112/530, loss: 0.0035455701872706413
2023-01-23 03:07:08.050683: step: 2116/530, loss: 0.0014051437610760331
2023-01-23 03:07:09.174943: step: 2120/530, loss: 0.0004934311145916581
==================================================
Loss: 0.020
--------------------
Dev: {'event': {'p': 0.6012591815320042, 'r': 0.762982689747004, 'f1': 0.6725352112676055}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 20}
Test: {'event': {'p': 0.6435969868173258, 'r': 0.7811428571428571, 'f1': 0.7057305110996387}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 20}
Chinese: {'event': {'p': 0.5116279069767442, 'r': 0.8148148148148148, 'f1': 0.6285714285714286}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 20}
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': 20}
Russian: {'event': {'p': 0.43902439024390244, 'r': 0.5, 'f1': 0.4675324675324676}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 20}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Chinese: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Chinese: {'event': {'p': 0.6190476190476191, 'r': 0.9629629629629629, 'f1': 0.7536231884057971}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6288770053475936, 'r': 0.7829560585885486, 'f1': 0.697508896797153}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Korean: {'event': {'p': 0.64058795637743, 'r': 0.772, 'f1': 0.7001813941435606}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Korean: {'event': {'p': 0.6851851851851852, 'r': 0.5873015873015873, 'f1': 0.6324786324786325}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5319148936170213, 'r': 0.6944444444444444, 'f1': 0.6024096385542169}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
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 03:07:49.681669: step: 4/530, loss: 0.49011632800102234
2023-01-23 03:07:50.801321: step: 8/530, loss: 0.004227065946906805
2023-01-23 03:07:51.927133: step: 12/530, loss: 0.016133999451994896
2023-01-23 03:07:53.061232: step: 16/530, loss: 0.0037785531021654606
2023-01-23 03:07:54.148962: step: 20/530, loss: 0.010957717895507812
2023-01-23 03:07:55.323944: step: 24/530, loss: 0.053522489964962006
2023-01-23 03:07:56.492269: step: 28/530, loss: 0.0015806198352947831
2023-01-23 03:07:57.639830: step: 32/530, loss: 0.038451384752988815
2023-01-23 03:07:58.759949: step: 36/530, loss: 0.00011548996553756297
2023-01-23 03:07:59.893527: step: 40/530, loss: 0.03133726119995117
2023-01-23 03:08:01.014387: step: 44/530, loss: 0.03824024274945259
2023-01-23 03:08:02.167344: step: 48/530, loss: 0.003679466200992465
2023-01-23 03:08:03.283924: step: 52/530, loss: 0.00012350082397460938
2023-01-23 03:08:04.408276: step: 56/530, loss: 0.01638650894165039
2023-01-23 03:08:05.520700: step: 60/530, loss: 0.019202042371034622
2023-01-23 03:08:06.678723: step: 64/530, loss: 0.0016574382316321135
2023-01-23 03:08:07.830836: step: 68/530, loss: 0.00110120780300349
2023-01-23 03:08:08.946438: step: 72/530, loss: 1.391005277633667
2023-01-23 03:08:10.057654: step: 76/530, loss: 0.0001434326113667339
2023-01-23 03:08:11.175366: step: 80/530, loss: 0.08163568377494812
2023-01-23 03:08:12.323120: step: 84/530, loss: 0.005132961552590132
2023-01-23 03:08:13.433480: step: 88/530, loss: 0.007859230041503906
2023-01-23 03:08:14.549313: step: 92/530, loss: 0.0036460875999182463
2023-01-23 03:08:15.661680: step: 96/530, loss: 0.04182014614343643
2023-01-23 03:08:16.790716: step: 100/530, loss: 0.017016984522342682
2023-01-23 03:08:17.911817: step: 104/530, loss: 0.0027931213844567537
2023-01-23 03:08:19.037496: step: 108/530, loss: 2.2172927856445312e-05
2023-01-23 03:08:20.139497: step: 112/530, loss: 0.0014137268299236894
2023-01-23 03:08:21.266119: step: 116/530, loss: 0.0013768672943115234
2023-01-23 03:08:22.368959: step: 120/530, loss: 0.0009717941284179688
2023-01-23 03:08:23.488027: step: 124/530, loss: 0.10848331451416016
2023-01-23 03:08:24.604607: step: 128/530, loss: 1.6451529264450073
2023-01-23 03:08:25.715387: step: 132/530, loss: 0.0010001182090491056
2023-01-23 03:08:26.852920: step: 136/530, loss: 0.019113779067993164
2023-01-23 03:08:27.972456: step: 140/530, loss: 0.16156692802906036
2023-01-23 03:08:29.091275: step: 144/530, loss: 2.5177003408316523e-05
2023-01-23 03:08:30.200628: step: 148/530, loss: 0.0006868839845992625
2023-01-23 03:08:31.321879: step: 152/530, loss: 0.0230528824031353
2023-01-23 03:08:32.423401: step: 156/530, loss: 0.001032161759212613
2023-01-23 03:08:33.550549: step: 160/530, loss: 0.0005208969232626259
2023-01-23 03:08:34.666336: step: 164/530, loss: 0.017513656988739967
2023-01-23 03:08:35.808359: step: 168/530, loss: 0.001582241035066545
2023-01-23 03:08:36.913446: step: 172/530, loss: 0.0005973338847979903
2023-01-23 03:08:38.070021: step: 176/530, loss: 0.0019715309608727694
2023-01-23 03:08:39.164565: step: 180/530, loss: 0.009799622930586338
2023-01-23 03:08:40.298059: step: 184/530, loss: 0.014711951836943626
2023-01-23 03:08:41.419459: step: 188/530, loss: 0.0002263069327455014
2023-01-23 03:08:42.517248: step: 192/530, loss: 0.0021007535979151726
2023-01-23 03:08:43.628935: step: 196/530, loss: 0.000976991606876254
2023-01-23 03:08:44.735335: step: 200/530, loss: 0.010377217084169388
2023-01-23 03:08:45.863490: step: 204/530, loss: 0.01644148863852024
2023-01-23 03:08:46.987793: step: 208/530, loss: 0.038106538355350494
2023-01-23 03:08:48.115498: step: 212/530, loss: 0.002868270967155695
2023-01-23 03:08:49.247774: step: 216/530, loss: 5.197525388211943e-05
2023-01-23 03:08:50.355641: step: 220/530, loss: 0.0011104702716693282
2023-01-23 03:08:51.489011: step: 224/530, loss: 0.013138055801391602
2023-01-23 03:08:52.640264: step: 228/530, loss: 0.016677284613251686
2023-01-23 03:08:53.767851: step: 232/530, loss: 0.0003247261047363281
2023-01-23 03:08:54.897424: step: 236/530, loss: 0.0007629871251992881
2023-01-23 03:08:56.016085: step: 240/530, loss: 0.0004142761172261089
2023-01-23 03:08:57.132750: step: 244/530, loss: 4.3201445805607364e-05
2023-01-23 03:08:58.282251: step: 248/530, loss: 0.02846856229007244
2023-01-23 03:08:59.415194: step: 252/530, loss: 0.012844085693359375
2023-01-23 03:09:00.542330: step: 256/530, loss: 0.020685385912656784
2023-01-23 03:09:01.670659: step: 260/530, loss: 0.01350174006074667
2023-01-23 03:09:02.872874: step: 264/530, loss: 0.00044803618220612407
2023-01-23 03:09:04.000544: step: 268/530, loss: 0.00299167656339705
2023-01-23 03:09:05.105452: step: 272/530, loss: 0.009971809573471546
2023-01-23 03:09:06.214235: step: 276/530, loss: 0.024344826117157936
2023-01-23 03:09:07.345962: step: 280/530, loss: 0.004234123043715954
2023-01-23 03:09:08.451124: step: 284/530, loss: 0.01858968660235405
2023-01-23 03:09:09.568425: step: 288/530, loss: 0.0006374359363690019
2023-01-23 03:09:10.721333: step: 292/530, loss: 0.00792074203491211
2023-01-23 03:09:11.853043: step: 296/530, loss: 0.00044841767521575093
2023-01-23 03:09:12.976433: step: 300/530, loss: 0.6544893383979797
2023-01-23 03:09:14.099941: step: 304/530, loss: 0.036920737475156784
2023-01-23 03:09:15.252068: step: 308/530, loss: 0.034932900220155716
2023-01-23 03:09:16.360062: step: 312/530, loss: 0.0008483887067995965
2023-01-23 03:09:17.501484: step: 316/530, loss: 0.01162796001881361
2023-01-23 03:09:18.671645: step: 320/530, loss: 0.006617164704948664
2023-01-23 03:09:19.806312: step: 324/530, loss: 0.10611972957849503
2023-01-23 03:09:20.962140: step: 328/530, loss: 0.004826927557587624
2023-01-23 03:09:22.129279: step: 332/530, loss: 0.003083944320678711
2023-01-23 03:09:23.264377: step: 336/530, loss: 0.0007933616871014237
2023-01-23 03:09:24.372049: step: 340/530, loss: 0.020416736602783203
2023-01-23 03:09:25.507707: step: 344/530, loss: 0.04075679928064346
2023-01-23 03:09:26.628481: step: 348/530, loss: 0.00032739638118073344
2023-01-23 03:09:27.762190: step: 352/530, loss: 0.12937593460083008
2023-01-23 03:09:28.886260: step: 356/530, loss: 0.03532858192920685
2023-01-23 03:09:30.014055: step: 360/530, loss: 0.011431765742599964
2023-01-23 03:09:31.168333: step: 364/530, loss: 0.012261486612260342
2023-01-23 03:09:32.302503: step: 368/530, loss: 0.00037374498788267374
2023-01-23 03:09:33.418630: step: 372/530, loss: 0.023598194122314453
2023-01-23 03:09:34.570687: step: 376/530, loss: 0.0346694141626358
2023-01-23 03:09:35.693179: step: 380/530, loss: 0.004454994574189186
2023-01-23 03:09:36.847560: step: 384/530, loss: 0.0006451606750488281
2023-01-23 03:09:37.957674: step: 388/530, loss: 8.22067231638357e-05
2023-01-23 03:09:39.044805: step: 392/530, loss: 0.0007439613109454513
2023-01-23 03:09:40.200439: step: 396/530, loss: 0.0017996788956224918
2023-01-23 03:09:41.317292: step: 400/530, loss: 0.006274128332734108
2023-01-23 03:09:42.430303: step: 404/530, loss: 0.003052616026252508
2023-01-23 03:09:43.544908: step: 408/530, loss: 0.0006673812749795616
2023-01-23 03:09:44.724724: step: 412/530, loss: 0.014032173901796341
2023-01-23 03:09:45.824029: step: 416/530, loss: 0.0003649711434263736
2023-01-23 03:09:46.930374: step: 420/530, loss: 0.00013265610323287547
2023-01-23 03:09:48.074616: step: 424/530, loss: 0.07189436256885529
2023-01-23 03:09:49.173476: step: 428/530, loss: 0.0009311676258221269
2023-01-23 03:09:50.297535: step: 432/530, loss: 0.02896256558597088
2023-01-23 03:09:51.434714: step: 436/530, loss: 0.0015769959427416325
2023-01-23 03:09:52.536662: step: 440/530, loss: 0.0001618385431356728
2023-01-23 03:09:53.681193: step: 444/530, loss: 0.004143416881561279
2023-01-23 03:09:54.799087: step: 448/530, loss: 0.0001451790303690359
2023-01-23 03:09:55.921580: step: 452/530, loss: 0.004675006493926048
2023-01-23 03:09:57.061589: step: 456/530, loss: 3.643035961431451e-05
2023-01-23 03:09:58.185790: step: 460/530, loss: 0.0003921985626220703
2023-01-23 03:09:59.305671: step: 464/530, loss: 0.008510875515639782
2023-01-23 03:10:00.451854: step: 468/530, loss: 0.00013465882511809468
2023-01-23 03:10:01.609657: step: 472/530, loss: 0.006438923068344593
2023-01-23 03:10:02.736048: step: 476/530, loss: 0.0075547220185399055
2023-01-23 03:10:03.880189: step: 480/530, loss: 0.0010969162685796618
2023-01-23 03:10:04.978313: step: 484/530, loss: 0.0026235580444335938
2023-01-23 03:10:06.123559: step: 488/530, loss: 0.32693445682525635
2023-01-23 03:10:07.242793: step: 492/530, loss: 0.0026502609252929688
2023-01-23 03:10:08.364525: step: 496/530, loss: 6.46591215627268e-05
2023-01-23 03:10:09.473371: step: 500/530, loss: 0.7742407321929932
2023-01-23 03:10:10.600637: step: 504/530, loss: 0.0012416839599609375
2023-01-23 03:10:11.719673: step: 508/530, loss: 0.00016717911057639867
2023-01-23 03:10:12.847867: step: 512/530, loss: 0.00022783280292060226
2023-01-23 03:10:13.988307: step: 516/530, loss: 0.002860164502635598
2023-01-23 03:10:15.139997: step: 520/530, loss: 0.0006827354663982987
2023-01-23 03:10:16.299474: step: 524/530, loss: 0.07887883484363556
2023-01-23 03:10:17.442417: step: 528/530, loss: 0.00046096445294097066
2023-01-23 03:10:18.527437: step: 532/530, loss: 0.014565085992217064
2023-01-23 03:10:19.658850: step: 536/530, loss: 0.006557941902428865
2023-01-23 03:10:20.769709: step: 540/530, loss: 4.673004150390625e-05
2023-01-23 03:10:21.892171: step: 544/530, loss: 3.185272362316027e-05
2023-01-23 03:10:23.012265: step: 548/530, loss: 0.0029134750366210938
2023-01-23 03:10:24.150332: step: 552/530, loss: 0.058595798909664154
2023-01-23 03:10:25.305210: step: 556/530, loss: 0.0006774902576580644
2023-01-23 03:10:26.414321: step: 560/530, loss: 0.014229201711714268
2023-01-23 03:10:27.545791: step: 564/530, loss: 0.0013820648891851306
2023-01-23 03:10:28.676073: step: 568/530, loss: 0.0044297222048044205
2023-01-23 03:10:29.809472: step: 572/530, loss: 0.022774314507842064
2023-01-23 03:10:30.969050: step: 576/530, loss: 0.029187774285674095
2023-01-23 03:10:32.105085: step: 580/530, loss: 0.0016811371315270662
2023-01-23 03:10:33.202537: step: 584/530, loss: 0.0011992455692961812
2023-01-23 03:10:34.318309: step: 588/530, loss: 0.055848024785518646
2023-01-23 03:10:35.440461: step: 592/530, loss: 0.3081279993057251
2023-01-23 03:10:36.593005: step: 596/530, loss: 0.013493156060576439
2023-01-23 03:10:37.742645: step: 600/530, loss: 0.0009476661798544228
2023-01-23 03:10:38.847955: step: 604/530, loss: 0.0005537033430300653
2023-01-23 03:10:39.960589: step: 608/530, loss: 0.0027714730240404606
2023-01-23 03:10:41.080830: step: 612/530, loss: 0.00194635393563658
2023-01-23 03:10:42.179033: step: 616/530, loss: 0.0005013465997762978
2023-01-23 03:10:43.286932: step: 620/530, loss: 0.01245727576315403
2023-01-23 03:10:44.416884: step: 624/530, loss: 0.050360869616270065
2023-01-23 03:10:45.547745: step: 628/530, loss: 0.001125335693359375
2023-01-23 03:10:46.680342: step: 632/530, loss: 0.014724541455507278
2023-01-23 03:10:47.785028: step: 636/530, loss: 0.0006517410511150956
2023-01-23 03:10:48.897155: step: 640/530, loss: 0.00015707015700172633
2023-01-23 03:10:50.027613: step: 644/530, loss: 0.02399311028420925
2023-01-23 03:10:51.154685: step: 648/530, loss: 0.0007123947143554688
2023-01-23 03:10:52.276777: step: 652/530, loss: 5.0735470722429454e-05
2023-01-23 03:10:53.411246: step: 656/530, loss: 0.7012096643447876
2023-01-23 03:10:54.548711: step: 660/530, loss: 0.6703810691833496
2023-01-23 03:10:55.678218: step: 664/530, loss: 0.008697891607880592
2023-01-23 03:10:56.784934: step: 668/530, loss: 0.00036010745679959655
2023-01-23 03:10:57.902468: step: 672/530, loss: 0.006646919529885054
2023-01-23 03:10:59.019469: step: 676/530, loss: 0.0017990112537518144
2023-01-23 03:11:00.140927: step: 680/530, loss: 0.013575363904237747
2023-01-23 03:11:01.254503: step: 684/530, loss: 0.021174049004912376
2023-01-23 03:11:02.368245: step: 688/530, loss: 0.004755496978759766
2023-01-23 03:11:03.491566: step: 692/530, loss: 0.00276699080131948
2023-01-23 03:11:04.645738: step: 696/530, loss: 0.02060394361615181
2023-01-23 03:11:05.766892: step: 700/530, loss: 0.0006732940673828125
2023-01-23 03:11:06.915009: step: 704/530, loss: 3.757476952159777e-05
2023-01-23 03:11:08.082481: step: 708/530, loss: 0.003176403231918812
2023-01-23 03:11:09.176016: step: 712/530, loss: 0.0019120455253869295
2023-01-23 03:11:10.294481: step: 716/530, loss: 0.0006477356073446572
2023-01-23 03:11:11.436180: step: 720/530, loss: 0.005207061767578125
2023-01-23 03:11:12.541997: step: 724/530, loss: 0.013041352853178978
2023-01-23 03:11:13.647530: step: 728/530, loss: 0.02233780175447464
2023-01-23 03:11:14.781613: step: 732/530, loss: 2.670288040462765e-06
2023-01-23 03:11:15.904361: step: 736/530, loss: 0.0144195556640625
2023-01-23 03:11:17.046866: step: 740/530, loss: 0.008275222964584827
2023-01-23 03:11:18.171617: step: 744/530, loss: 0.02954578399658203
2023-01-23 03:11:19.324065: step: 748/530, loss: -8.296966370835435e-06
2023-01-23 03:11:20.454434: step: 752/530, loss: 0.004961872007697821
2023-01-23 03:11:21.570399: step: 756/530, loss: 0.0013607979053631425
2023-01-23 03:11:22.669721: step: 760/530, loss: 0.0008280753972940147
2023-01-23 03:11:23.788182: step: 764/530, loss: 0.02119007334113121
2023-01-23 03:11:24.908173: step: 768/530, loss: 0.013470363803207874
2023-01-23 03:11:26.036558: step: 772/530, loss: 0.015328217297792435
2023-01-23 03:11:27.156796: step: 776/530, loss: 0.0005252838600426912
2023-01-23 03:11:28.250042: step: 780/530, loss: 2.365112231927924e-05
2023-01-23 03:11:29.376867: step: 784/530, loss: 0.00020437240891624242
2023-01-23 03:11:30.496487: step: 788/530, loss: 0.01071538869291544
2023-01-23 03:11:31.627953: step: 792/530, loss: 0.022870158776640892
2023-01-23 03:11:32.786963: step: 796/530, loss: 0.0002044677676167339
2023-01-23 03:11:33.909986: step: 800/530, loss: 0.00010385512723587453
2023-01-23 03:11:35.030834: step: 804/530, loss: 0.033193208277225494
2023-01-23 03:11:36.164323: step: 808/530, loss: 0.007413006387650967
2023-01-23 03:11:37.274466: step: 812/530, loss: 0.022733021527528763
2023-01-23 03:11:38.398509: step: 816/530, loss: 8.97407517186366e-05
2023-01-23 03:11:39.547221: step: 820/530, loss: 0.0007865906227380037
2023-01-23 03:11:40.649229: step: 824/530, loss: 0.0020891190506517887
2023-01-23 03:11:41.776463: step: 828/530, loss: 0.023992346599698067
2023-01-23 03:11:42.894010: step: 832/530, loss: 0.0011586189502850175
2023-01-23 03:11:44.018015: step: 836/530, loss: 0.05891776457428932
2023-01-23 03:11:45.165010: step: 840/530, loss: 0.021409176290035248
2023-01-23 03:11:46.318554: step: 844/530, loss: 0.0001924514799611643
2023-01-23 03:11:47.447556: step: 848/530, loss: 0.0001560211239848286
2023-01-23 03:11:48.566807: step: 852/530, loss: 0.0015741348033770919
2023-01-23 03:11:49.680858: step: 856/530, loss: 0.0003898620489053428
2023-01-23 03:11:50.787898: step: 860/530, loss: 0.016292572021484375
2023-01-23 03:11:51.934412: step: 864/530, loss: 0.03315143659710884
2023-01-23 03:11:53.011411: step: 868/530, loss: 0.003843116806820035
2023-01-23 03:11:54.142784: step: 872/530, loss: 3.9839746023062617e-05
2023-01-23 03:11:55.269245: step: 876/530, loss: 0.0007068634149618447
2023-01-23 03:11:56.427832: step: 880/530, loss: 0.006881332024931908
2023-01-23 03:11:57.550146: step: 884/530, loss: 0.003958416171371937
2023-01-23 03:11:58.659095: step: 888/530, loss: 0.01683931238949299
2023-01-23 03:11:59.783002: step: 892/530, loss: 0.0015444993041455746
2023-01-23 03:12:00.889112: step: 896/530, loss: 0.0019664764404296875
2023-01-23 03:12:02.028134: step: 900/530, loss: 0.01835479773581028
2023-01-23 03:12:03.140463: step: 904/530, loss: 0.002390289446339011
2023-01-23 03:12:04.239660: step: 908/530, loss: 0.032248880714178085
2023-01-23 03:12:05.365121: step: 912/530, loss: 0.0010766983032226562
2023-01-23 03:12:06.498730: step: 916/530, loss: 0.00036602019099518657
2023-01-23 03:12:07.723751: step: 920/530, loss: 0.003584289690479636
2023-01-23 03:12:08.841315: step: 924/530, loss: 0.0001146316499216482
2023-01-23 03:12:09.965584: step: 928/530, loss: 0.0035695554688572884
2023-01-23 03:12:11.079132: step: 932/530, loss: 0.00010061264038085938
2023-01-23 03:12:12.168993: step: 936/530, loss: 0.0019312859512865543
2023-01-23 03:12:13.256599: step: 940/530, loss: 0.0008093834039755166
2023-01-23 03:12:14.377878: step: 944/530, loss: 0.011751365847885609
2023-01-23 03:12:15.492796: step: 948/530, loss: 0.0005085945012979209
2023-01-23 03:12:16.601659: step: 952/530, loss: 0.002727604005485773
2023-01-23 03:12:17.736441: step: 956/530, loss: 4.682540748035535e-05
2023-01-23 03:12:18.857930: step: 960/530, loss: 0.00035858154296875
2023-01-23 03:12:19.984408: step: 964/530, loss: 0.00015647412510588765
2023-01-23 03:12:21.103251: step: 968/530, loss: 0.01577177084982395
2023-01-23 03:12:22.223082: step: 972/530, loss: 0.00025310515775345266
2023-01-23 03:12:23.326006: step: 976/530, loss: 0.006222057621926069
2023-01-23 03:12:24.444591: step: 980/530, loss: 0.012386512942612171
2023-01-23 03:12:25.569198: step: 984/530, loss: 0.015457344241440296
2023-01-23 03:12:26.702054: step: 988/530, loss: 0.0035745620261877775
2023-01-23 03:12:27.826777: step: 992/530, loss: 0.044710446149110794
2023-01-23 03:12:28.956537: step: 996/530, loss: 4.196166628389619e-06
2023-01-23 03:12:30.094627: step: 1000/530, loss: 0.0006580352783203125
2023-01-23 03:12:31.218387: step: 1004/530, loss: 0.03691520914435387
2023-01-23 03:12:32.351846: step: 1008/530, loss: 0.015237427316606045
2023-01-23 03:12:33.478870: step: 1012/530, loss: 0.0037853240501135588
2023-01-23 03:12:34.582026: step: 1016/530, loss: 0.020543480291962624
2023-01-23 03:12:35.694736: step: 1020/530, loss: 0.0017120360862463713
2023-01-23 03:12:36.835970: step: 1024/530, loss: 0.0008113860967569053
2023-01-23 03:12:37.966031: step: 1028/530, loss: 0.0001789093075785786
2023-01-23 03:12:39.097498: step: 1032/530, loss: 0.03347358852624893
2023-01-23 03:12:40.234020: step: 1036/530, loss: 0.0534856803715229
2023-01-23 03:12:41.369518: step: 1040/530, loss: 0.013461876660585403
2023-01-23 03:12:42.506377: step: 1044/530, loss: 0.003422737354412675
2023-01-23 03:12:43.634344: step: 1048/530, loss: 0.018561745062470436
2023-01-23 03:12:44.739604: step: 1052/530, loss: 0.1254653036594391
2023-01-23 03:12:45.834915: step: 1056/530, loss: 0.0005100250127725303
2023-01-23 03:12:46.964652: step: 1060/530, loss: 0.02449646033346653
2023-01-23 03:12:48.094664: step: 1064/530, loss: 0.025200605392456055
2023-01-23 03:12:49.239602: step: 1068/530, loss: 0.027215957641601562
2023-01-23 03:12:50.368603: step: 1072/530, loss: 0.01806488074362278
2023-01-23 03:12:51.485020: step: 1076/530, loss: 0.1416957825422287
2023-01-23 03:12:52.617592: step: 1080/530, loss: 0.01165008544921875
2023-01-23 03:12:53.741606: step: 1084/530, loss: -1.9073486328125e-06
2023-01-23 03:12:54.855302: step: 1088/530, loss: 0.013349246233701706
2023-01-23 03:12:55.985134: step: 1092/530, loss: 0.00018806458683684468
2023-01-23 03:12:57.114609: step: 1096/530, loss: 0.005420207977294922
2023-01-23 03:12:58.219424: step: 1100/530, loss: 0.009965182282030582
2023-01-23 03:12:59.336131: step: 1104/530, loss: 0.016663599759340286
2023-01-23 03:13:00.464428: step: 1108/530, loss: 0.022583769634366035
2023-01-23 03:13:01.567902: step: 1112/530, loss: 0.03428182750940323
2023-01-23 03:13:02.667897: step: 1116/530, loss: 0.01601552963256836
2023-01-23 03:13:03.810174: step: 1120/530, loss: 0.03004913404583931
2023-01-23 03:13:04.968829: step: 1124/530, loss: 0.019466208294034004
2023-01-23 03:13:06.117916: step: 1128/530, loss: 0.03588066250085831
2023-01-23 03:13:07.230540: step: 1132/530, loss: 0.0003498077276162803
2023-01-23 03:13:08.359199: step: 1136/530, loss: 0.028367996215820312
2023-01-23 03:13:09.480868: step: 1140/530, loss: 0.00011868477304233238
2023-01-23 03:13:10.593713: step: 1144/530, loss: 0.0023441314697265625
2023-01-23 03:13:11.687696: step: 1148/530, loss: 0.0007661819108761847
2023-01-23 03:13:12.820847: step: 1152/530, loss: 0.0500730499625206
2023-01-23 03:13:13.944697: step: 1156/530, loss: 8.058547973632812e-05
2023-01-23 03:13:15.080963: step: 1160/530, loss: 0.00014963149442337453
2023-01-23 03:13:16.186591: step: 1164/530, loss: 0.020379066467285156
2023-01-23 03:13:17.305340: step: 1168/530, loss: 0.0016283035511150956
2023-01-23 03:13:18.443825: step: 1172/530, loss: 0.023729609325528145
2023-01-23 03:13:19.553780: step: 1176/530, loss: 0.007485914509743452
2023-01-23 03:13:20.696260: step: 1180/530, loss: 0.02717299573123455
2023-01-23 03:13:21.834916: step: 1184/530, loss: 0.00108165736310184
2023-01-23 03:13:22.938710: step: 1188/530, loss: 0.0002513885556254536
2023-01-23 03:13:24.059804: step: 1192/530, loss: 0.00034160615177825093
2023-01-23 03:13:25.176352: step: 1196/530, loss: 5.4931642807787284e-05
2023-01-23 03:13:26.286064: step: 1200/530, loss: 0.00019159316434524953
2023-01-23 03:13:27.430290: step: 1204/530, loss: 4.692077709478326e-05
2023-01-23 03:13:28.579286: step: 1208/530, loss: 0.0010395051212981343
2023-01-23 03:13:29.675901: step: 1212/530, loss: 0.0017034531338140368
2023-01-23 03:13:30.800957: step: 1216/530, loss: 0.054489992558956146
2023-01-23 03:13:31.926408: step: 1220/530, loss: 0.007573127746582031
2023-01-23 03:13:33.064924: step: 1224/530, loss: 0.005268859677016735
2023-01-23 03:13:34.183361: step: 1228/530, loss: 0.0612645149230957
2023-01-23 03:13:35.287034: step: 1232/530, loss: 0.00707740755751729
2023-01-23 03:13:36.400636: step: 1236/530, loss: 0.0005743980873376131
2023-01-23 03:13:37.524629: step: 1240/530, loss: 0.0228118896484375
2023-01-23 03:13:38.677507: step: 1244/530, loss: 0.00022711753263138235
2023-01-23 03:13:39.773262: step: 1248/530, loss: 0.00017818213382270187
2023-01-23 03:13:40.909908: step: 1252/530, loss: 0.017669677734375
2023-01-23 03:13:42.035966: step: 1256/530, loss: 0.11473388969898224
2023-01-23 03:13:43.144588: step: 1260/530, loss: 0.004238129127770662
2023-01-23 03:13:44.299199: step: 1264/530, loss: 0.005385208409279585
2023-01-23 03:13:45.413557: step: 1268/530, loss: 0.0036874772049486637
2023-01-23 03:13:46.543123: step: 1272/530, loss: 0.0019821166060864925
2023-01-23 03:13:47.659175: step: 1276/530, loss: 0.004180908203125
2023-01-23 03:13:48.769759: step: 1280/530, loss: 9.670258441474289e-05
2023-01-23 03:13:49.918197: step: 1284/530, loss: 0.07886752486228943
2023-01-23 03:13:51.050870: step: 1288/530, loss: 0.0017394066089764237
2023-01-23 03:13:52.173001: step: 1292/530, loss: 0.0011807441478595138
2023-01-23 03:13:53.286508: step: 1296/530, loss: 0.18033771216869354
2023-01-23 03:13:54.408994: step: 1300/530, loss: 0.008785533718764782
2023-01-23 03:13:55.535113: step: 1304/530, loss: 0.03551235422492027
2023-01-23 03:13:56.640213: step: 1308/530, loss: 0.009478283114731312
2023-01-23 03:13:57.785208: step: 1312/530, loss: 0.03144025802612305
2023-01-23 03:13:58.893629: step: 1316/530, loss: 0.011328602209687233
2023-01-23 03:14:00.024637: step: 1320/530, loss: 0.010186529718339443
2023-01-23 03:14:01.142446: step: 1324/530, loss: 0.00021009445481467992
2023-01-23 03:14:02.233783: step: 1328/530, loss: 0.0022800446022301912
2023-01-23 03:14:03.372366: step: 1332/530, loss: 9.384155418956652e-05
2023-01-23 03:14:04.500524: step: 1336/530, loss: 0.013181495480239391
2023-01-23 03:14:05.634676: step: 1340/530, loss: 0.000575637852307409
2023-01-23 03:14:06.803075: step: 1344/530, loss: 0.0006193161243572831
2023-01-23 03:14:07.919559: step: 1348/530, loss: 0.005352592561393976
2023-01-23 03:14:09.046398: step: 1352/530, loss: 0.001437807222828269
2023-01-23 03:14:10.190949: step: 1356/530, loss: 0.002618980361148715
2023-01-23 03:14:11.330666: step: 1360/530, loss: 0.02991018444299698
2023-01-23 03:14:12.478945: step: 1364/530, loss: 0.0008039474487304688
2023-01-23 03:14:13.597396: step: 1368/530, loss: 0.05861339718103409
2023-01-23 03:14:14.696435: step: 1372/530, loss: 0.0026342393830418587
2023-01-23 03:14:15.846712: step: 1376/530, loss: 0.04842682182788849
2023-01-23 03:14:16.970042: step: 1380/530, loss: 0.009973621927201748
2023-01-23 03:14:18.080458: step: 1384/530, loss: 5.359649730962701e-05
2023-01-23 03:14:19.195968: step: 1388/530, loss: 0.003119564149528742
2023-01-23 03:14:20.340081: step: 1392/530, loss: 0.20365695655345917
2023-01-23 03:14:21.481564: step: 1396/530, loss: 9.560585567669477e-06
2023-01-23 03:14:22.616375: step: 1400/530, loss: 0.0046735769137740135
2023-01-23 03:14:23.748011: step: 1404/530, loss: 0.0557897575199604
2023-01-23 03:14:24.876691: step: 1408/530, loss: 0.00032682419987395406
2023-01-23 03:14:26.017949: step: 1412/530, loss: 0.00325167179107666
2023-01-23 03:14:27.188410: step: 1416/530, loss: 0.0004341125604696572
2023-01-23 03:14:28.298400: step: 1420/530, loss: 0.01347370259463787
2023-01-23 03:14:29.415912: step: 1424/530, loss: 0.0026268004439771175
2023-01-23 03:14:30.564947: step: 1428/530, loss: 0.006257152650505304
2023-01-23 03:14:31.689833: step: 1432/530, loss: 0.02206411398947239
2023-01-23 03:14:32.859068: step: 1436/530, loss: 0.0002388000430073589
2023-01-23 03:14:33.978610: step: 1440/530, loss: 0.012933732010424137
2023-01-23 03:14:35.101651: step: 1444/530, loss: 0.0028773308731615543
2023-01-23 03:14:36.235551: step: 1448/530, loss: 0.0375092513859272
2023-01-23 03:14:37.363746: step: 1452/530, loss: 0.0008903503185138106
2023-01-23 03:14:38.486493: step: 1456/530, loss: 0.00021238328190520406
2023-01-23 03:14:39.592458: step: 1460/530, loss: 1.5333126783370972
2023-01-23 03:14:40.685480: step: 1464/530, loss: 0.02745637856423855
2023-01-23 03:14:41.797797: step: 1468/530, loss: 0.0003685951523948461
2023-01-23 03:14:42.945217: step: 1472/530, loss: 0.022286606952548027
2023-01-23 03:14:44.033886: step: 1476/530, loss: 0.004867267794907093
2023-01-23 03:14:45.151899: step: 1480/530, loss: 0.00026416778564453125
2023-01-23 03:14:46.284046: step: 1484/530, loss: 0.020837783813476562
2023-01-23 03:14:47.397611: step: 1488/530, loss: 0.02726440504193306
2023-01-23 03:14:48.524571: step: 1492/530, loss: 0.0009504318586550653
2023-01-23 03:14:49.650338: step: 1496/530, loss: 0.011907387524843216
2023-01-23 03:14:50.806700: step: 1500/530, loss: 0.012531662359833717
2023-01-23 03:14:51.920205: step: 1504/530, loss: 0.6905828714370728
2023-01-23 03:14:53.049065: step: 1508/530, loss: 0.008626366034150124
2023-01-23 03:14:54.180515: step: 1512/530, loss: 0.0004220009141135961
2023-01-23 03:14:55.321520: step: 1516/530, loss: 0.003879356663674116
2023-01-23 03:14:56.417680: step: 1520/530, loss: 0.0003732681507244706
2023-01-23 03:14:57.537891: step: 1524/530, loss: 0.007319641299545765
2023-01-23 03:14:58.663682: step: 1528/530, loss: 0.0008094788063317537
2023-01-23 03:14:59.777389: step: 1532/530, loss: 0.00196247105486691
2023-01-23 03:15:00.878585: step: 1536/530, loss: 0.00027985573979094625
2023-01-23 03:15:02.005850: step: 1540/530, loss: 0.004294252954423428
2023-01-23 03:15:03.125263: step: 1544/530, loss: 0.00021991730318404734
2023-01-23 03:15:04.250927: step: 1548/530, loss: 0.0010298729175701737
2023-01-23 03:15:05.362217: step: 1552/530, loss: 0.04912203177809715
2023-01-23 03:15:06.493595: step: 1556/530, loss: 0.0023814202286303043
2023-01-23 03:15:07.595898: step: 1560/530, loss: 0.00015296936908271164
2023-01-23 03:15:08.709106: step: 1564/530, loss: -6.4849850787140895e-06
2023-01-23 03:15:09.824845: step: 1568/530, loss: 0.000583267246838659
2023-01-23 03:15:10.926943: step: 1572/530, loss: 0.002432107925415039
2023-01-23 03:15:12.049718: step: 1576/530, loss: 0.10006694495677948
2023-01-23 03:15:13.168942: step: 1580/530, loss: 0.011987018398940563
2023-01-23 03:15:14.313345: step: 1584/530, loss: 0.019217681139707565
2023-01-23 03:15:15.461018: step: 1588/530, loss: 0.008651352487504482
2023-01-23 03:15:16.555560: step: 1592/530, loss: 0.0003994941362179816
2023-01-23 03:15:17.668369: step: 1596/530, loss: 0.001673793769441545
2023-01-23 03:15:18.783330: step: 1600/530, loss: 0.04468126595020294
2023-01-23 03:15:19.915108: step: 1604/530, loss: 0.0004604339774232358
2023-01-23 03:15:21.042786: step: 1608/530, loss: 0.001903533935546875
2023-01-23 03:15:22.161303: step: 1612/530, loss: 0.02284236066043377
2023-01-23 03:15:23.302760: step: 1616/530, loss: 0.0006439209100790322
2023-01-23 03:15:24.432690: step: 1620/530, loss: 0.04527554661035538
2023-01-23 03:15:25.549773: step: 1624/530, loss: 0.0011399269569665194
2023-01-23 03:15:26.691835: step: 1628/530, loss: 8.935928053688258e-05
2023-01-23 03:15:27.816282: step: 1632/530, loss: 0.006617546547204256
2023-01-23 03:15:28.951263: step: 1636/530, loss: 0.0030029297340661287
2023-01-23 03:15:30.058178: step: 1640/530, loss: 0.0001149714007624425
2023-01-23 03:15:31.193503: step: 1644/530, loss: 0.004120826721191406
2023-01-23 03:15:32.338935: step: 1648/530, loss: 0.0007271766662597656
2023-01-23 03:15:33.449741: step: 1652/530, loss: 0.012736893258988857
2023-01-23 03:15:34.569497: step: 1656/530, loss: 0.00072650914080441
2023-01-23 03:15:35.698364: step: 1660/530, loss: 0.004993868060410023
2023-01-23 03:15:36.819756: step: 1664/530, loss: 0.005924033932387829
2023-01-23 03:15:37.937934: step: 1668/530, loss: 0.00020704269991256297
2023-01-23 03:15:39.057715: step: 1672/530, loss: 3.0493736630887724e-05
2023-01-23 03:15:40.178355: step: 1676/530, loss: 0.0005395889165811241
2023-01-23 03:15:41.274543: step: 1680/530, loss: 0.00020399093045853078
2023-01-23 03:15:42.422556: step: 1684/530, loss: 0.2955062985420227
2023-01-23 03:15:43.540373: step: 1688/530, loss: 0.00022764207096770406
2023-01-23 03:15:44.692175: step: 1692/530, loss: 0.0023202896118164062
2023-01-23 03:15:45.817571: step: 1696/530, loss: 0.010395050048828125
2023-01-23 03:15:46.961614: step: 1700/530, loss: 0.010214615613222122
2023-01-23 03:15:48.070494: step: 1704/530, loss: 0.0014660835731774569
2023-01-23 03:15:49.218560: step: 1708/530, loss: 0.0018846512539312243
2023-01-23 03:15:50.335448: step: 1712/530, loss: 0.0035795210860669613
2023-01-23 03:15:51.445553: step: 1716/530, loss: 0.00019140243239235133
2023-01-23 03:15:52.602692: step: 1720/530, loss: 0.011435985565185547
2023-01-23 03:15:53.726538: step: 1724/530, loss: 0.0029358866158872843
2023-01-23 03:15:54.824826: step: 1728/530, loss: 0.0010211945045739412
2023-01-23 03:15:55.958240: step: 1732/530, loss: 0.0024734498001635075
2023-01-23 03:15:57.070848: step: 1736/530, loss: 0.27268171310424805
2023-01-23 03:15:58.178664: step: 1740/530, loss: 0.003663778305053711
2023-01-23 03:15:59.285749: step: 1744/530, loss: 0.019527101889252663
2023-01-23 03:16:00.411751: step: 1748/530, loss: 0.0012912750244140625
2023-01-23 03:16:01.525691: step: 1752/530, loss: 0.0034158704802393913
2023-01-23 03:16:02.685233: step: 1756/530, loss: 0.002094030613079667
2023-01-23 03:16:03.809899: step: 1760/530, loss: 0.004107666201889515
2023-01-23 03:16:04.948900: step: 1764/530, loss: 0.00025806427584029734
2023-01-23 03:16:06.088969: step: 1768/530, loss: 0.0002704620419535786
2023-01-23 03:16:07.194525: step: 1772/530, loss: 0.00013360977754928172
2023-01-23 03:16:08.340036: step: 1776/530, loss: 0.041413117200136185
2023-01-23 03:16:09.467481: step: 1780/530, loss: 0.0010197639930993319
2023-01-23 03:16:10.567239: step: 1784/530, loss: 3.986358569818549e-05
2023-01-23 03:16:11.702068: step: 1788/530, loss: 0.02375469170510769
2023-01-23 03:16:12.843261: step: 1792/530, loss: 0.0007143020629882812
2023-01-23 03:16:13.954846: step: 1796/530, loss: 0.003890466643497348
2023-01-23 03:16:15.089515: step: 1800/530, loss: 0.009053230285644531
2023-01-23 03:16:16.231429: step: 1804/530, loss: 0.025924302637577057
2023-01-23 03:16:17.367176: step: 1808/530, loss: 0.010184478014707565
2023-01-23 03:16:18.484753: step: 1812/530, loss: 0.0751463919878006
2023-01-23 03:16:19.617245: step: 1816/530, loss: 7.009506134636467e-06
2023-01-23 03:16:20.748696: step: 1820/530, loss: 0.00019207000150345266
2023-01-23 03:16:21.875797: step: 1824/530, loss: 0.0007665634038858116
2023-01-23 03:16:23.020802: step: 1828/530, loss: 0.02518768236041069
2023-01-23 03:16:24.148023: step: 1832/530, loss: 0.00022349358187057078
2023-01-23 03:16:25.306491: step: 1836/530, loss: 0.00047779083251953125
2023-01-23 03:16:26.449426: step: 1840/530, loss: 0.00046539306640625
2023-01-23 03:16:27.617687: step: 1844/530, loss: 0.0021774291526526213
2023-01-23 03:16:28.757828: step: 1848/530, loss: 0.0005764007801190019
2023-01-23 03:16:29.873270: step: 1852/530, loss: 0.0015541077591478825
2023-01-23 03:16:30.993718: step: 1856/530, loss: 0.004560804460197687
2023-01-23 03:16:32.130612: step: 1860/530, loss: 0.00012855530076194555
2023-01-23 03:16:33.229370: step: 1864/530, loss: 0.025412941351532936
2023-01-23 03:16:34.419223: step: 1868/530, loss: 0.002062034560367465
2023-01-23 03:16:35.532814: step: 1872/530, loss: 0.017816925421357155
2023-01-23 03:16:36.639396: step: 1876/530, loss: 9.536744073557202e-06
2023-01-23 03:16:37.742347: step: 1880/530, loss: 0.06563711166381836
2023-01-23 03:16:38.850792: step: 1884/530, loss: 0.0010630607139319181
2023-01-23 03:16:39.957644: step: 1888/530, loss: 0.00199127197265625
2023-01-23 03:16:41.076308: step: 1892/530, loss: 0.019057465717196465
2023-01-23 03:16:42.218655: step: 1896/530, loss: 0.05794239044189453
2023-01-23 03:16:43.361900: step: 1900/530, loss: 0.0023369789123535156
2023-01-23 03:16:44.485111: step: 1904/530, loss: 0.0030307769775390625
2023-01-23 03:16:45.596839: step: 1908/530, loss: 0.01993427239358425
2023-01-23 03:16:46.722771: step: 1912/530, loss: 0.004283905029296875
2023-01-23 03:16:47.835545: step: 1916/530, loss: 0.0036249160766601562
2023-01-23 03:16:48.980193: step: 1920/530, loss: 0.00010251998901367188
2023-01-23 03:16:50.094285: step: 1924/530, loss: 0.001602601958438754
2023-01-23 03:16:51.254286: step: 1928/530, loss: 0.16394224762916565
2023-01-23 03:16:52.393295: step: 1932/530, loss: 0.0011976242531090975
2023-01-23 03:16:53.557889: step: 1936/530, loss: 0.007334232330322266
2023-01-23 03:16:54.701415: step: 1940/530, loss: 0.010462380014359951
2023-01-23 03:16:55.827245: step: 1944/530, loss: 9.288787987316027e-05
2023-01-23 03:16:56.971244: step: 1948/530, loss: 0.00923843402415514
2023-01-23 03:16:58.095162: step: 1952/530, loss: 0.0003485679626464844
2023-01-23 03:16:59.238860: step: 1956/530, loss: 0.01651592180132866
2023-01-23 03:17:00.373992: step: 1960/530, loss: 0.0021847723983228207
2023-01-23 03:17:01.490198: step: 1964/530, loss: 0.030588533729314804
2023-01-23 03:17:02.633962: step: 1968/530, loss: 0.029824543744325638
2023-01-23 03:17:03.768135: step: 1972/530, loss: 0.0004157066287007183
2023-01-23 03:17:04.875080: step: 1976/530, loss: 0.00022153856116347015
2023-01-23 03:17:06.022102: step: 1980/530, loss: 0.0042781829833984375
2023-01-23 03:17:07.142872: step: 1984/530, loss: 7.629396350239404e-07
2023-01-23 03:17:08.274121: step: 1988/530, loss: 0.020429613068699837
2023-01-23 03:17:09.364306: step: 1992/530, loss: 0.0002344131498830393
2023-01-23 03:17:10.498720: step: 1996/530, loss: 0.016537286341190338
2023-01-23 03:17:11.644684: step: 2000/530, loss: 0.00042533877422101796
2023-01-23 03:17:12.779126: step: 2004/530, loss: 0.01352539099752903
2023-01-23 03:17:13.899564: step: 2008/530, loss: 0.036016084253787994
2023-01-23 03:17:15.025751: step: 2012/530, loss: 0.00013818740262649953
2023-01-23 03:17:16.120467: step: 2016/530, loss: 0.0027946471236646175
2023-01-23 03:17:17.253258: step: 2020/530, loss: 0.0006717682117596269
2023-01-23 03:17:18.353019: step: 2024/530, loss: 0.001970004988834262
2023-01-23 03:17:19.476154: step: 2028/530, loss: 0.0053878785111010075
2023-01-23 03:17:20.596330: step: 2032/530, loss: 0.06713466346263885
2023-01-23 03:17:21.710979: step: 2036/530, loss: 0.005345344543457031
2023-01-23 03:17:22.888196: step: 2040/530, loss: 0.0012050628429278731
2023-01-23 03:17:24.057892: step: 2044/530, loss: 0.008620262145996094
2023-01-23 03:17:25.177399: step: 2048/530, loss: 0.0034687044098973274
2023-01-23 03:17:26.289780: step: 2052/530, loss: 0.043709564954042435
2023-01-23 03:17:27.412178: step: 2056/530, loss: 0.0012117385631427169
2023-01-23 03:17:28.534041: step: 2060/530, loss: 0.0814388319849968
2023-01-23 03:17:29.665133: step: 2064/530, loss: 0.18567946553230286
2023-01-23 03:17:30.765688: step: 2068/530, loss: 0.00045833588228560984
2023-01-23 03:17:31.878252: step: 2072/530, loss: 0.001036787056364119
2023-01-23 03:17:33.035710: step: 2076/530, loss: 0.09582772850990295
2023-01-23 03:17:34.140839: step: 2080/530, loss: 0.005129051394760609
2023-01-23 03:17:35.270221: step: 2084/530, loss: 0.033835604786872864
2023-01-23 03:17:36.386821: step: 2088/530, loss: 0.005956077482551336
2023-01-23 03:17:37.517130: step: 2092/530, loss: 0.03995513916015625
2023-01-23 03:17:38.672985: step: 2096/530, loss: 0.00458793668076396
2023-01-23 03:17:39.814039: step: 2100/530, loss: 0.003013801760971546
2023-01-23 03:17:40.934319: step: 2104/530, loss: 0.0007322311284951866
2023-01-23 03:17:42.087356: step: 2108/530, loss: 0.0066069127060472965
2023-01-23 03:17:43.204088: step: 2112/530, loss: 0.05391748622059822
2023-01-23 03:17:44.316983: step: 2116/530, loss: 0.00016255378432106227
2023-01-23 03:17:45.474304: step: 2120/530, loss: 0.020818233489990234
==================================================
Loss: 0.032
--------------------
Dev: {'event': {'p': 0.6198257080610022, 'r': 0.7576564580559254, 'f1': 0.6818454164170161}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
Test: {'event': {'p': 0.642925430210325, 'r': 0.7685714285714286, 'f1': 0.7001561686621551}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
Chinese: {'event': {'p': 0.6153846153846154, 'r': 0.8888888888888888, 'f1': 0.7272727272727274}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
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': 21}
Russian: {'event': {'p': 0.5294117647058824, 'r': 0.5, 'f1': 0.5142857142857143}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
New best chinese model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6198257080610022, 'r': 0.7576564580559254, 'f1': 0.6818454164170161}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
Eng Test for Chinese: {'event': {'p': 0.642925430210325, 'r': 0.7685714285714286, 'f1': 0.7001561686621551}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
Sample Chinese: {'event': {'p': 0.6153846153846154, 'r': 0.8888888888888888, 'f1': 0.7272727272727274}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6288770053475936, 'r': 0.7829560585885486, 'f1': 0.697508896797153}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Korean: {'event': {'p': 0.64058795637743, 'r': 0.772, 'f1': 0.7001813941435606}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Korean: {'event': {'p': 0.6851851851851852, 'r': 0.5873015873015873, 'f1': 0.6324786324786325}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5319148936170213, 'r': 0.6944444444444444, 'f1': 0.6024096385542169}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
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 03:18:30.236408: step: 4/530, loss: 0.013829231262207031
2023-01-23 03:18:31.343610: step: 8/530, loss: 0.028236009180545807
2023-01-23 03:18:32.474966: step: 12/530, loss: 0.020946312695741653
2023-01-23 03:18:33.595675: step: 16/530, loss: 0.02783794328570366
2023-01-23 03:18:34.723159: step: 20/530, loss: 0.005129194352775812
2023-01-23 03:18:35.886454: step: 24/530, loss: 0.0005687713855877519
2023-01-23 03:18:36.993293: step: 28/530, loss: 0.003909873776137829
2023-01-23 03:18:38.140372: step: 32/530, loss: 0.0048799519427120686
2023-01-23 03:18:39.256526: step: 36/530, loss: 1.411438006471144e-05
2023-01-23 03:18:40.384306: step: 40/530, loss: 0.07285986095666885
2023-01-23 03:18:41.534431: step: 44/530, loss: 0.0007911681896075606
2023-01-23 03:18:42.655659: step: 48/530, loss: 0.0018589019309729338
2023-01-23 03:18:43.803879: step: 52/530, loss: 0.01565570756793022
2023-01-23 03:18:44.898582: step: 56/530, loss: 0.002141857286915183
2023-01-23 03:18:46.041237: step: 60/530, loss: 0.010235786437988281
2023-01-23 03:18:47.180279: step: 64/530, loss: 0.0009053230169229209
2023-01-23 03:18:48.293863: step: 68/530, loss: 0.0040565491653978825
2023-01-23 03:18:49.426095: step: 72/530, loss: 0.0029331205878406763
2023-01-23 03:18:50.529875: step: 76/530, loss: 0.018975067883729935
2023-01-23 03:18:51.671554: step: 80/530, loss: 0.0004068374983035028
2023-01-23 03:18:52.796167: step: 84/530, loss: 0.0019807815551757812
2023-01-23 03:18:53.980701: step: 88/530, loss: 0.0025695799849927425
2023-01-23 03:18:55.107378: step: 92/530, loss: 0.0008378028869628906
2023-01-23 03:18:56.245368: step: 96/530, loss: 0.0007655143272131681
2023-01-23 03:18:57.390009: step: 100/530, loss: 0.01660318486392498
2023-01-23 03:18:58.506185: step: 104/530, loss: 0.0012273788452148438
2023-01-23 03:18:59.653713: step: 108/530, loss: 0.004020881373435259
2023-01-23 03:19:00.807410: step: 112/530, loss: 0.0005162238958291709
2023-01-23 03:19:01.972860: step: 116/530, loss: 0.0402795784175396
2023-01-23 03:19:03.115963: step: 120/530, loss: 0.005393505096435547
2023-01-23 03:19:04.266579: step: 124/530, loss: 0.08117543160915375
2023-01-23 03:19:05.392021: step: 128/530, loss: 2.880096508306451e-05
2023-01-23 03:19:06.525732: step: 132/530, loss: 0.022545242682099342
2023-01-23 03:19:07.627826: step: 136/530, loss: 0.023128509521484375
2023-01-23 03:19:08.746665: step: 140/530, loss: 0.0005208969232626259
2023-01-23 03:19:09.888557: step: 144/530, loss: 0.0010251045459881425
2023-01-23 03:19:10.974281: step: 148/530, loss: 0.0014766693348065019
2023-01-23 03:19:12.118733: step: 152/530, loss: 0.005837631411850452
2023-01-23 03:19:13.253781: step: 156/530, loss: 0.0004342079337220639
2023-01-23 03:19:14.388862: step: 160/530, loss: 0.02112274244427681
2023-01-23 03:19:15.515233: step: 164/530, loss: 0.047652244567871094
2023-01-23 03:19:16.655469: step: 168/530, loss: 0.00012140275066485628
2023-01-23 03:19:17.775274: step: 172/530, loss: 0.021535111591219902
2023-01-23 03:19:18.916980: step: 176/530, loss: 0.005016804207116365
2023-01-23 03:19:20.052571: step: 180/530, loss: 0.0008551598293706775
2023-01-23 03:19:21.186394: step: 184/530, loss: 0.0007279396522790194
2023-01-23 03:19:22.301691: step: 188/530, loss: 0.00015754700871184468
2023-01-23 03:19:23.452645: step: 192/530, loss: 0.008654212579131126
2023-01-23 03:19:24.542433: step: 196/530, loss: 0.0007607460138387978
2023-01-23 03:19:25.643324: step: 200/530, loss: 0.04100513458251953
2023-01-23 03:19:26.802864: step: 204/530, loss: 0.017502594739198685
2023-01-23 03:19:27.933120: step: 208/530, loss: 0.0004849433898925781
2023-01-23 03:19:29.048973: step: 212/530, loss: 0.002924978733062744
2023-01-23 03:19:30.166208: step: 216/530, loss: 0.009746551513671875
2023-01-23 03:19:31.265198: step: 220/530, loss: 0.01942138746380806
2023-01-23 03:19:32.392976: step: 224/530, loss: 3.132819983875379e-05
2023-01-23 03:19:33.507931: step: 228/530, loss: 0.0020584582816809416
2023-01-23 03:19:34.661472: step: 232/530, loss: 0.00204124441370368
2023-01-23 03:19:35.762778: step: 236/530, loss: 0.0002586364862509072
2023-01-23 03:19:36.896887: step: 240/530, loss: 0.017728805541992188
2023-01-23 03:19:38.057672: step: 244/530, loss: 0.005463409703224897
2023-01-23 03:19:39.174161: step: 248/530, loss: 0.0037986754905432463
2023-01-23 03:19:40.314259: step: 252/530, loss: 0.10300798714160919
2023-01-23 03:19:41.418237: step: 256/530, loss: 0.0009765625
2023-01-23 03:19:42.536863: step: 260/530, loss: 6.408691115211695e-05
2023-01-23 03:19:43.655095: step: 264/530, loss: 7.06672653905116e-05
2023-01-23 03:19:44.769749: step: 268/530, loss: 0.03311615064740181
2023-01-23 03:19:45.901418: step: 272/530, loss: 0.00034561159554868937
2023-01-23 03:19:47.031496: step: 276/530, loss: 0.029632091522216797
2023-01-23 03:19:48.159748: step: 280/530, loss: 0.001568698906339705
2023-01-23 03:19:49.290149: step: 284/530, loss: 0.006611061282455921
2023-01-23 03:19:50.413434: step: 288/530, loss: 0.0006584167131222785
2023-01-23 03:19:51.550259: step: 292/530, loss: 0.6212767958641052
2023-01-23 03:19:52.683883: step: 296/530, loss: 0.0346410758793354
2023-01-23 03:19:53.798890: step: 300/530, loss: 0.004952240269631147
2023-01-23 03:19:54.898295: step: 304/530, loss: 0.0004743576282635331
2023-01-23 03:19:56.006592: step: 308/530, loss: 0.008572769351303577
2023-01-23 03:19:57.130884: step: 312/530, loss: 0.02337370067834854
2023-01-23 03:19:58.250197: step: 316/530, loss: 0.06982908397912979
2023-01-23 03:19:59.389936: step: 320/530, loss: 0.0008627891074866056
2023-01-23 03:20:00.502602: step: 324/530, loss: 5.8794023061636835e-05
2023-01-23 03:20:01.661980: step: 328/530, loss: 0.0026374817825853825
2023-01-23 03:20:02.782255: step: 332/530, loss: 0.03246669843792915
2023-01-23 03:20:03.914984: step: 336/530, loss: 0.0005084991571493447
2023-01-23 03:20:05.038274: step: 340/530, loss: 0.008952951990067959
2023-01-23 03:20:06.152571: step: 344/530, loss: 0.0029693604446947575
2023-01-23 03:20:07.277180: step: 348/530, loss: 0.010965157300233841
2023-01-23 03:20:08.373758: step: 352/530, loss: 0.008252620697021484
2023-01-23 03:20:09.544759: step: 356/530, loss: 0.006879043765366077
2023-01-23 03:20:10.661971: step: 360/530, loss: 0.05324440076947212
2023-01-23 03:20:11.786154: step: 364/530, loss: 0.0006783485296182334
2023-01-23 03:20:12.899031: step: 368/530, loss: 0.012720013037323952
2023-01-23 03:20:14.006793: step: 372/530, loss: 0.08633708953857422
2023-01-23 03:20:15.124530: step: 376/530, loss: 0.004118633456528187
2023-01-23 03:20:16.240604: step: 380/530, loss: 0.00017189979553222656
2023-01-23 03:20:17.343240: step: 384/530, loss: 0.04844703897833824
2023-01-23 03:20:18.472999: step: 388/530, loss: 0.03181181102991104
2023-01-23 03:20:19.594551: step: 392/530, loss: 0.005729008000344038
2023-01-23 03:20:20.711969: step: 396/530, loss: 0.002358722733333707
2023-01-23 03:20:21.842181: step: 400/530, loss: 0.0004006385861430317
2023-01-23 03:20:22.960467: step: 404/530, loss: 0.06288424134254456
2023-01-23 03:20:24.092877: step: 408/530, loss: 0.00739631662145257
2023-01-23 03:20:25.236067: step: 412/530, loss: 0.042477987706661224
2023-01-23 03:20:26.352487: step: 416/530, loss: 0.003582096192985773
2023-01-23 03:20:27.474820: step: 420/530, loss: 0.0007232666248455644
2023-01-23 03:20:28.599812: step: 424/530, loss: 0.02542419545352459
2023-01-23 03:20:29.703436: step: 428/530, loss: 0.02205963060259819
2023-01-23 03:20:30.813714: step: 432/530, loss: 0.0006108283996582031
2023-01-23 03:20:31.949968: step: 436/530, loss: 0.0008171082008630037
2023-01-23 03:20:33.080183: step: 440/530, loss: 0.033006858080625534
2023-01-23 03:20:34.207270: step: 444/530, loss: 0.027925778180360794
2023-01-23 03:20:35.331650: step: 448/530, loss: 0.00240325927734375
2023-01-23 03:20:36.434123: step: 452/530, loss: 0.027349280193448067
2023-01-23 03:20:37.581505: step: 456/530, loss: 0.018412400037050247
2023-01-23 03:20:38.688245: step: 460/530, loss: 0.0034723279532045126
2023-01-23 03:20:39.784688: step: 464/530, loss: 1.8501283193472773e-05
2023-01-23 03:20:40.924536: step: 468/530, loss: 0.005109215155243874
2023-01-23 03:20:42.046990: step: 472/530, loss: 0.00025024416390806437
2023-01-23 03:20:43.164417: step: 476/530, loss: -8.01086389401462e-06
2023-01-23 03:20:44.289591: step: 480/530, loss: 0.0022285461891442537
2023-01-23 03:20:45.397495: step: 484/530, loss: 0.0015735626220703125
2023-01-23 03:20:46.579719: step: 488/530, loss: 0.0009603500366210938
2023-01-23 03:20:47.697302: step: 492/530, loss: 0.00028176308842375875
2023-01-23 03:20:48.808841: step: 496/530, loss: 3.170967102050781e-05
2023-01-23 03:20:49.923798: step: 500/530, loss: 0.019804857671260834
2023-01-23 03:20:51.074963: step: 504/530, loss: 0.00016222000704146922
2023-01-23 03:20:52.239769: step: 508/530, loss: 0.0215882770717144
2023-01-23 03:20:53.348997: step: 512/530, loss: -1.4781953723286279e-06
2023-01-23 03:20:54.497425: step: 516/530, loss: 0.11693544685840607
2023-01-23 03:20:55.619011: step: 520/530, loss: 0.013869999907910824
2023-01-23 03:20:56.732871: step: 524/530, loss: 3.986358569818549e-05
2023-01-23 03:20:57.884691: step: 528/530, loss: 0.0009098052978515625
2023-01-23 03:20:59.010848: step: 532/530, loss: 0.000244140625
2023-01-23 03:21:00.141841: step: 536/530, loss: 0.00024852753267623484
2023-01-23 03:21:01.240913: step: 540/530, loss: 7.705688040005043e-05
2023-01-23 03:21:02.407973: step: 544/530, loss: 0.02243633382022381
2023-01-23 03:21:03.506656: step: 548/530, loss: 0.0014440537197515368
2023-01-23 03:21:04.631120: step: 552/530, loss: 0.045681193470954895
2023-01-23 03:21:05.722211: step: 556/530, loss: 0.0003986358642578125
2023-01-23 03:21:06.858098: step: 560/530, loss: 0.005690813064575195
2023-01-23 03:21:07.992085: step: 564/530, loss: 0.04710979759693146
2023-01-23 03:21:09.113686: step: 568/530, loss: 1.9073486328125e-05
2023-01-23 03:21:10.233713: step: 572/530, loss: 0.03899326175451279
2023-01-23 03:21:11.333641: step: 576/530, loss: 0.002635193057358265
2023-01-23 03:21:12.471358: step: 580/530, loss: 0.005238533020019531
2023-01-23 03:21:13.594842: step: 584/530, loss: 0.0001941680966410786
2023-01-23 03:21:14.698236: step: 588/530, loss: 0.025834370404481888
2023-01-23 03:21:15.853140: step: 592/530, loss: 0.7795947194099426
2023-01-23 03:21:16.976205: step: 596/530, loss: 0.003987977281212807
2023-01-23 03:21:18.095007: step: 600/530, loss: 0.0012932777171954513
2023-01-23 03:21:19.216688: step: 604/530, loss: 0.32770684361457825
2023-01-23 03:21:20.325017: step: 608/530, loss: 0.0010576248168945312
2023-01-23 03:21:21.420551: step: 612/530, loss: 0.0003802776336669922
2023-01-23 03:21:22.530227: step: 616/530, loss: 0.00010375976853538305
2023-01-23 03:21:23.669375: step: 620/530, loss: 0.5229472517967224
2023-01-23 03:21:24.812320: step: 624/530, loss: 0.0347110740840435
2023-01-23 03:21:25.939406: step: 628/530, loss: 1.0824203855008818e-05
2023-01-23 03:21:27.073007: step: 632/530, loss: 0.0020164488814771175
2023-01-23 03:21:28.214141: step: 636/530, loss: 0.028372574597597122
2023-01-23 03:21:29.324931: step: 640/530, loss: 0.05191326141357422
2023-01-23 03:21:30.455132: step: 644/530, loss: 0.00024700164794921875
2023-01-23 03:21:31.601825: step: 648/530, loss: 0.01607513427734375
2023-01-23 03:21:32.723580: step: 652/530, loss: 8.60214204294607e-05
2023-01-23 03:21:33.821876: step: 656/530, loss: 3.147125244140625e-05
2023-01-23 03:21:34.937026: step: 660/530, loss: 0.00037174223689362407
2023-01-23 03:21:36.057061: step: 664/530, loss: 0.0008466720464639366
2023-01-23 03:21:37.191087: step: 668/530, loss: 0.07638807594776154
2023-01-23 03:21:38.349979: step: 672/530, loss: 0.058062173426151276
2023-01-23 03:21:39.466880: step: 676/530, loss: 0.03454608842730522
2023-01-23 03:21:40.584976: step: 680/530, loss: 0.0001295089750783518
2023-01-23 03:21:41.702628: step: 684/530, loss: 0.0029857635963708162
2023-01-23 03:21:42.812287: step: 688/530, loss: 0.0017117499373853207
2023-01-23 03:21:43.927466: step: 692/530, loss: 5.588531348621473e-05
2023-01-23 03:21:45.037317: step: 696/530, loss: 0.01333913765847683
2023-01-23 03:21:46.187213: step: 700/530, loss: 0.04393291473388672
2023-01-23 03:21:47.294955: step: 704/530, loss: 0.0035429000854492188
2023-01-23 03:21:48.441009: step: 708/530, loss: 0.009376906789839268
2023-01-23 03:21:49.572316: step: 712/530, loss: 0.00033254624577239156
2023-01-23 03:21:50.720681: step: 716/530, loss: 0.00018997192091774195
2023-01-23 03:21:51.857516: step: 720/530, loss: 0.0003508329391479492
2023-01-23 03:21:52.933863: step: 724/530, loss: 0.0007179260137490928
2023-01-23 03:21:54.065533: step: 728/530, loss: 6.694794137729332e-05
2023-01-23 03:21:55.220873: step: 732/530, loss: 0.0013194084167480469
2023-01-23 03:21:56.356419: step: 736/530, loss: 0.022631453350186348
2023-01-23 03:21:57.487349: step: 740/530, loss: 0.022176455706357956
2023-01-23 03:21:58.602725: step: 744/530, loss: 0.015521049499511719
2023-01-23 03:21:59.698652: step: 748/530, loss: 0.01170129794627428
2023-01-23 03:22:00.867284: step: 752/530, loss: 0.01095352228730917
2023-01-23 03:22:01.987887: step: 756/530, loss: 0.00048041343688964844
2023-01-23 03:22:03.098396: step: 760/530, loss: 7.252692739712074e-05
2023-01-23 03:22:04.223844: step: 764/530, loss: 0.0001354217529296875
2023-01-23 03:22:05.360257: step: 768/530, loss: 0.0017064096173271537
2023-01-23 03:22:06.497854: step: 772/530, loss: 0.0003833770751953125
2023-01-23 03:22:07.657539: step: 776/530, loss: 0.009389400482177734
2023-01-23 03:22:08.805669: step: 780/530, loss: 0.00044164658174850047
2023-01-23 03:22:09.908316: step: 784/530, loss: 0.055819131433963776
2023-01-23 03:22:11.012383: step: 788/530, loss: 0.03856682777404785
2023-01-23 03:22:12.122042: step: 792/530, loss: 0.06394214183092117
2023-01-23 03:22:13.224955: step: 796/530, loss: 0.0029307366348803043
2023-01-23 03:22:14.375457: step: 800/530, loss: 0.014421653933823109
2023-01-23 03:22:15.469502: step: 804/530, loss: 0.0017161369323730469
2023-01-23 03:22:16.583417: step: 808/530, loss: 0.009801912121474743
2023-01-23 03:22:17.675475: step: 812/530, loss: 0.02094402350485325
2023-01-23 03:22:18.805665: step: 816/530, loss: 0.012366056442260742
2023-01-23 03:22:19.902676: step: 820/530, loss: 0.00035343170748092234
2023-01-23 03:22:21.017578: step: 824/530, loss: 0.0017243385082110763
2023-01-23 03:22:22.154673: step: 828/530, loss: 0.004668044857680798
2023-01-23 03:22:23.290184: step: 832/530, loss: 0.0005001068348065019
2023-01-23 03:22:24.425553: step: 836/530, loss: 0.0018300532829016447
2023-01-23 03:22:25.522320: step: 840/530, loss: 0.01161875855177641
2023-01-23 03:22:26.659235: step: 844/530, loss: 0.0013685226440429688
2023-01-23 03:22:27.769398: step: 848/530, loss: 0.032754138112068176
2023-01-23 03:22:28.874905: step: 852/530, loss: 0.00020654201216530055
2023-01-23 03:22:29.983185: step: 856/530, loss: 0.010254478082060814
2023-01-23 03:22:31.135410: step: 860/530, loss: 0.00641288748010993
2023-01-23 03:22:32.255750: step: 864/530, loss: 0.02948017232120037
2023-01-23 03:22:33.368229: step: 868/530, loss: 0.006304026115685701
2023-01-23 03:22:34.458375: step: 872/530, loss: 0.006889724638313055
2023-01-23 03:22:35.584230: step: 876/530, loss: 0.0020359039772301912
2023-01-23 03:22:36.704914: step: 880/530, loss: -1.9073486328125e-06
2023-01-23 03:22:37.817530: step: 884/530, loss: 1.7642974853515625e-05
2023-01-23 03:22:38.941914: step: 888/530, loss: 0.0032953263726085424
2023-01-23 03:22:40.054114: step: 892/530, loss: 0.003936958033591509
2023-01-23 03:22:41.193535: step: 896/530, loss: 0.00012683868408203125
2023-01-23 03:22:42.316296: step: 900/530, loss: 0.0009784698486328125
2023-01-23 03:22:43.437322: step: 904/530, loss: 0.0030906677711755037
2023-01-23 03:22:44.588903: step: 908/530, loss: 0.0004165649297647178
2023-01-23 03:22:45.702055: step: 912/530, loss: 0.02554006688296795
2023-01-23 03:22:46.818616: step: 916/530, loss: 0.006756401155143976
2023-01-23 03:22:47.939358: step: 920/530, loss: 0.0031872272957116365
2023-01-23 03:22:49.072641: step: 924/530, loss: 0.0004385948122944683
2023-01-23 03:22:50.214891: step: 928/530, loss: 0.001860809396021068
2023-01-23 03:22:51.337530: step: 932/530, loss: 0.0008029937744140625
2023-01-23 03:22:52.496283: step: 936/530, loss: 0.00012717247591353953
2023-01-23 03:22:53.598471: step: 940/530, loss: 0.0023103714920580387
2023-01-23 03:22:54.715274: step: 944/530, loss: 0.0008705139043740928
2023-01-23 03:22:55.816723: step: 948/530, loss: 3.471374657237902e-05
2023-01-23 03:22:56.956617: step: 952/530, loss: 0.0008937835809774697
2023-01-23 03:22:58.113838: step: 956/530, loss: 0.025219345465302467
2023-01-23 03:22:59.231259: step: 960/530, loss: 0.00015397073002532125
2023-01-23 03:23:00.319349: step: 964/530, loss: 0.0004955291515216231
2023-01-23 03:23:01.457128: step: 968/530, loss: 0.022915270179510117
2023-01-23 03:23:02.617845: step: 972/530, loss: 0.02005748823285103
2023-01-23 03:23:03.733574: step: 976/530, loss: 0.28493309020996094
2023-01-23 03:23:04.842557: step: 980/530, loss: 0.017366694286465645
2023-01-23 03:23:05.937987: step: 984/530, loss: 0.0005136012914590538
2023-01-23 03:23:07.047883: step: 988/530, loss: 0.015446471981704235
2023-01-23 03:23:08.149598: step: 992/530, loss: 2.670288040462765e-06
2023-01-23 03:23:09.287717: step: 996/530, loss: 0.000491714512463659
2023-01-23 03:23:10.410276: step: 1000/530, loss: 2.1123885744600557e-05
2023-01-23 03:23:11.525373: step: 1004/530, loss: 0.00040416716365143657
2023-01-23 03:23:12.649010: step: 1008/530, loss: 0.006275463383644819
2023-01-23 03:23:13.749807: step: 1012/530, loss: 0.0001375198335153982
2023-01-23 03:23:14.899480: step: 1016/530, loss: 0.0008087158203125
2023-01-23 03:23:16.013252: step: 1020/530, loss: 0.0002460479736328125
2023-01-23 03:23:17.152693: step: 1024/530, loss: 1.6021729607018642e-05
2023-01-23 03:23:18.281656: step: 1028/530, loss: 0.0008857726934365928
2023-01-23 03:23:19.390025: step: 1032/530, loss: 0.024689579382538795
2023-01-23 03:23:20.504587: step: 1036/530, loss: 0.003535699797794223
2023-01-23 03:23:21.596627: step: 1040/530, loss: 0.0010266781318932772
2023-01-23 03:23:22.692419: step: 1044/530, loss: 0.0018572807312011719
2023-01-23 03:23:23.818297: step: 1048/530, loss: 0.0007299422868527472
2023-01-23 03:23:24.937532: step: 1052/530, loss: 2.5844574338407256e-05
2023-01-23 03:23:26.052930: step: 1056/530, loss: 0.017903901636600494
2023-01-23 03:23:27.200742: step: 1060/530, loss: 0.1707594394683838
2023-01-23 03:23:28.327890: step: 1064/530, loss: 0.03297806158661842
2023-01-23 03:23:29.445271: step: 1068/530, loss: 0.003120803739875555
2023-01-23 03:23:30.581329: step: 1072/530, loss: 0.0012836457462981343
2023-01-23 03:23:31.693630: step: 1076/530, loss: 0.0035257339477539062
2023-01-23 03:23:32.866811: step: 1080/530, loss: 0.0077565195970237255
2023-01-23 03:23:34.004765: step: 1084/530, loss: 0.0010362624889239669
2023-01-23 03:23:35.154376: step: 1088/530, loss: -1.0585784366412554e-05
2023-01-23 03:23:36.302803: step: 1092/530, loss: 0.0004044532834086567
2023-01-23 03:23:37.409607: step: 1096/530, loss: 4.8208235966740176e-05
2023-01-23 03:23:38.521765: step: 1100/530, loss: 0.012791729532182217
2023-01-23 03:23:39.648621: step: 1104/530, loss: 0.011905670166015625
2023-01-23 03:23:40.778687: step: 1108/530, loss: 5.722046125811175e-07
2023-01-23 03:23:41.927418: step: 1112/530, loss: 0.00017747879610396922
2023-01-23 03:23:43.049203: step: 1116/530, loss: 0.0006025314214639366
2023-01-23 03:23:44.186204: step: 1120/530, loss: 0.03519769012928009
2023-01-23 03:23:45.296569: step: 1124/530, loss: 3.299712989246473e-05
2023-01-23 03:23:46.414397: step: 1128/530, loss: 0.00010938644845737144
2023-01-23 03:23:47.537414: step: 1132/530, loss: 0.00042018890962935984
2023-01-23 03:23:48.647235: step: 1136/530, loss: 0.002977085066959262
2023-01-23 03:23:49.787287: step: 1140/530, loss: 0.01409912109375
2023-01-23 03:23:50.902975: step: 1144/530, loss: 0.0005296707386150956
2023-01-23 03:23:52.014851: step: 1148/530, loss: 0.00026416778564453125
2023-01-23 03:23:53.131365: step: 1152/530, loss: 0.022140981629490852
2023-01-23 03:23:54.239078: step: 1156/530, loss: 3.6239625842426904e-06
2023-01-23 03:23:55.364749: step: 1160/530, loss: 0.5915541648864746
2023-01-23 03:23:56.481802: step: 1164/530, loss: 0.0028985023964196444
2023-01-23 03:23:57.617247: step: 1168/530, loss: 0.00021629333787132055
2023-01-23 03:23:58.717929: step: 1172/530, loss: 0.006834125611931086
2023-01-23 03:23:59.843035: step: 1176/530, loss: 0.0014423370594158769
2023-01-23 03:24:01.003682: step: 1180/530, loss: 0.0011466980213299394
2023-01-23 03:24:02.158000: step: 1184/530, loss: 0.00010385513451183215
2023-01-23 03:24:03.256880: step: 1188/530, loss: 0.0007197380182333291
2023-01-23 03:24:04.380388: step: 1192/530, loss: 0.015859462320804596
2023-01-23 03:24:05.484248: step: 1196/530, loss: 0.005663394927978516
2023-01-23 03:24:06.593204: step: 1200/530, loss: 0.0005887985462322831
2023-01-23 03:24:07.718018: step: 1204/530, loss: 0.0009119987953454256
2023-01-23 03:24:08.844158: step: 1208/530, loss: 0.0029766084626317024
2023-01-23 03:24:09.964777: step: 1212/530, loss: 0.0135955810546875
2023-01-23 03:24:11.074438: step: 1216/530, loss: 0.00010051727440441027
2023-01-23 03:24:12.233352: step: 1220/530, loss: 4.291534423828125e-06
2023-01-23 03:24:13.366997: step: 1224/530, loss: 0.01460032444447279
2023-01-23 03:24:14.461100: step: 1228/530, loss: 0.00010528564598644152
2023-01-23 03:24:15.609455: step: 1232/530, loss: 5.292892637953628e-06
2023-01-23 03:24:16.788083: step: 1236/530, loss: 0.0002620696905069053
2023-01-23 03:24:17.904326: step: 1240/530, loss: 0.0004349708906374872
2023-01-23 03:24:19.024178: step: 1244/530, loss: 0.016066361218690872
2023-01-23 03:24:20.120990: step: 1248/530, loss: 0.016463566571474075
2023-01-23 03:24:21.237731: step: 1252/530, loss: 0.06696290522813797
2023-01-23 03:24:22.365565: step: 1256/530, loss: 0.0016881943447515368
2023-01-23 03:24:23.481687: step: 1260/530, loss: 0.003610038897022605
2023-01-23 03:24:24.608363: step: 1264/530, loss: 0.02721252478659153
2023-01-23 03:24:25.752031: step: 1268/530, loss: 0.04581651836633682
2023-01-23 03:24:26.883095: step: 1272/530, loss: 0.0006538390880450606
2023-01-23 03:24:28.028949: step: 1276/530, loss: 0.001772213145159185
2023-01-23 03:24:29.126078: step: 1280/530, loss: 0.0015751958126202226
2023-01-23 03:24:30.254003: step: 1284/530, loss: 4.7349931264761835e-05
2023-01-23 03:24:31.383414: step: 1288/530, loss: 0.0010425568325445056
2023-01-23 03:24:32.500982: step: 1292/530, loss: 0.00046682360698468983
2023-01-23 03:24:33.629062: step: 1296/530, loss: 0.0006074905395507812
2023-01-23 03:24:34.758345: step: 1300/530, loss: 0.0002407073916401714
2023-01-23 03:24:35.841832: step: 1304/530, loss: 0.007075262255966663
2023-01-23 03:24:36.961148: step: 1308/530, loss: 0.0012199401389807463
2023-01-23 03:24:38.090115: step: 1312/530, loss: 0.0028744698502123356
2023-01-23 03:24:39.213080: step: 1316/530, loss: 0.008667755872011185
2023-01-23 03:24:40.335843: step: 1320/530, loss: 0.0019455909496173263
2023-01-23 03:24:41.483416: step: 1324/530, loss: 0.01106247864663601
2023-01-23 03:24:42.602000: step: 1328/530, loss: 0.03754167631268501
2023-01-23 03:24:43.707452: step: 1332/530, loss: 9.522438631393015e-05
2023-01-23 03:24:44.837381: step: 1336/530, loss: 0.04916572570800781
2023-01-23 03:24:45.977162: step: 1340/530, loss: 0.002193546388298273
2023-01-23 03:24:47.104898: step: 1344/530, loss: 0.0001820087491068989
2023-01-23 03:24:48.232148: step: 1348/530, loss: 0.009278440847992897
2023-01-23 03:24:49.341317: step: 1352/530, loss: 0.0004127502324990928
2023-01-23 03:24:50.447086: step: 1356/530, loss: 0.031043052673339844
2023-01-23 03:24:51.564928: step: 1360/530, loss: 0.03140735998749733
2023-01-23 03:24:52.700790: step: 1364/530, loss: 0.004853058140724897
2023-01-23 03:24:53.849745: step: 1368/530, loss: 0.0028602599631994963
2023-01-23 03:24:54.999912: step: 1372/530, loss: 0.007622337434440851
2023-01-23 03:24:56.156584: step: 1376/530, loss: 0.014221095480024815
2023-01-23 03:24:57.260967: step: 1380/530, loss: 0.0026906966231763363
2023-01-23 03:24:58.389188: step: 1384/530, loss: 0.0019065381493419409
2023-01-23 03:24:59.499748: step: 1388/530, loss: 0.00012321471876930445
2023-01-23 03:25:00.609264: step: 1392/530, loss: 0.041698455810546875
2023-01-23 03:25:01.737349: step: 1396/530, loss: 0.13400626182556152
2023-01-23 03:25:02.876293: step: 1400/530, loss: -5.722040441469289e-07
2023-01-23 03:25:03.990103: step: 1404/530, loss: 0.011005783453583717
2023-01-23 03:25:05.123085: step: 1408/530, loss: 0.015074730850756168
2023-01-23 03:25:06.262013: step: 1412/530, loss: 0.006898403167724609
2023-01-23 03:25:07.394519: step: 1416/530, loss: 0.0070705413818359375
2023-01-23 03:25:08.533849: step: 1420/530, loss: 0.0066041951067745686
2023-01-23 03:25:09.693074: step: 1424/530, loss: 0.023800181224942207
2023-01-23 03:25:10.786096: step: 1428/530, loss: 0.03796839714050293
2023-01-23 03:25:11.889427: step: 1432/530, loss: 0.00023212432279251516
2023-01-23 03:25:13.011909: step: 1436/530, loss: 0.0312378890812397
2023-01-23 03:25:14.147562: step: 1440/530, loss: 0.013933945447206497
2023-01-23 03:25:15.266374: step: 1444/530, loss: 0.056984901428222656
2023-01-23 03:25:16.377103: step: 1448/530, loss: 0.00784149207174778
2023-01-23 03:25:17.493527: step: 1452/530, loss: 0.022394562140107155
2023-01-23 03:25:18.619183: step: 1456/530, loss: 0.0023054121993482113
2023-01-23 03:25:19.738307: step: 1460/530, loss: 0.00033206940861418843
2023-01-23 03:25:20.866310: step: 1464/530, loss: 0.0077651976607739925
2023-01-23 03:25:22.014504: step: 1468/530, loss: 0.007676935754716396
2023-01-23 03:25:23.125051: step: 1472/530, loss: 0.010902214795351028
2023-01-23 03:25:24.253770: step: 1476/530, loss: 0.016046905890107155
2023-01-23 03:25:25.374874: step: 1480/530, loss: 0.12760229408740997
2023-01-23 03:25:26.472415: step: 1484/530, loss: 0.018263543024659157
2023-01-23 03:25:27.593495: step: 1488/530, loss: 0.0007132530445232987
2023-01-23 03:25:28.718901: step: 1492/530, loss: 5.4740903578931466e-05
2023-01-23 03:25:29.844225: step: 1496/530, loss: 0.015716170892119408
2023-01-23 03:25:30.953979: step: 1500/530, loss: 0.025861646980047226
2023-01-23 03:25:32.105506: step: 1504/530, loss: 0.0020416260231286287
2023-01-23 03:25:33.237471: step: 1508/530, loss: 6.923675391590223e-05
2023-01-23 03:25:34.352452: step: 1512/530, loss: 0.017908668145537376
2023-01-23 03:25:35.512348: step: 1516/530, loss: 0.0012227059341967106
2023-01-23 03:25:36.623597: step: 1520/530, loss: 0.0023993493523448706
2023-01-23 03:25:37.735374: step: 1524/530, loss: 7.972717867232859e-05
2023-01-23 03:25:38.848460: step: 1528/530, loss: 2.784729076665826e-05
2023-01-23 03:25:39.972700: step: 1532/530, loss: 0.04759882390499115
2023-01-23 03:25:41.114068: step: 1536/530, loss: 0.019581986591219902
2023-01-23 03:25:42.260372: step: 1540/530, loss: 0.00014991761418059468
2023-01-23 03:25:43.383058: step: 1544/530, loss: 0.01125946082174778
2023-01-23 03:25:44.510267: step: 1548/530, loss: 0.016376685351133347
2023-01-23 03:25:45.644007: step: 1552/530, loss: 0.0001350402890238911
2023-01-23 03:25:46.774733: step: 1556/530, loss: 0.0020140649285167456
2023-01-23 03:25:47.917116: step: 1560/530, loss: 0.03773679956793785
2023-01-23 03:25:49.030835: step: 1564/530, loss: 0.00014610290236305445
2023-01-23 03:25:50.140043: step: 1568/530, loss: 0.0022867678198963404
2023-01-23 03:25:51.260612: step: 1572/530, loss: 0.0015377998352050781
2023-01-23 03:25:52.409590: step: 1576/530, loss: 0.004486274905502796
2023-01-23 03:25:53.538799: step: 1580/530, loss: 1.8314515352249146
2023-01-23 03:25:54.695916: step: 1584/530, loss: 0.0819968655705452
2023-01-23 03:25:55.840878: step: 1588/530, loss: 0.0658847764134407
2023-01-23 03:25:56.960992: step: 1592/530, loss: 0.02240161970257759
2023-01-23 03:25:58.089658: step: 1596/530, loss: 2.136230432370212e-05
2023-01-23 03:25:59.256945: step: 1600/530, loss: 0.0629582405090332
2023-01-23 03:26:00.399439: step: 1604/530, loss: 0.026969147846102715
2023-01-23 03:26:01.513814: step: 1608/530, loss: 0.00016589164442848414
2023-01-23 03:26:02.664246: step: 1612/530, loss: 0.012159157544374466
2023-01-23 03:26:03.771893: step: 1616/530, loss: 0.0005271911504678428
2023-01-23 03:26:04.897033: step: 1620/530, loss: 0.0009271621820516884
2023-01-23 03:26:06.013675: step: 1624/530, loss: 0.0004901885986328125
2023-01-23 03:26:07.111316: step: 1628/530, loss: 0.0006651878356933594
2023-01-23 03:26:08.231597: step: 1632/530, loss: 0.00012989045353606343
2023-01-23 03:26:09.367086: step: 1636/530, loss: 0.02283640019595623
2023-01-23 03:26:10.506483: step: 1640/530, loss: 6.933212716830894e-05
2023-01-23 03:26:11.637845: step: 1644/530, loss: 0.0005867004510946572
2023-01-23 03:26:12.717876: step: 1648/530, loss: 0.0002651214599609375
2023-01-23 03:26:13.850120: step: 1652/530, loss: 0.0008106231689453125
2023-01-23 03:26:14.983384: step: 1656/530, loss: 0.0016009330283850431
2023-01-23 03:26:16.129816: step: 1660/530, loss: 0.02342987060546875
2023-01-23 03:26:17.278434: step: 1664/530, loss: 0.002790832659229636
2023-01-23 03:26:18.394847: step: 1668/530, loss: 8.258819434558973e-05
2023-01-23 03:26:19.532268: step: 1672/530, loss: 0.0005496025551110506
2023-01-23 03:26:20.658283: step: 1676/530, loss: 0.00725822476670146
2023-01-23 03:26:21.791376: step: 1680/530, loss: 0.0015655517345294356
2023-01-23 03:26:22.933029: step: 1684/530, loss: 0.0005455970531329513
2023-01-23 03:26:24.078841: step: 1688/530, loss: 0.020603753626346588
2023-01-23 03:26:25.195614: step: 1692/530, loss: 0.015109825879335403
2023-01-23 03:26:26.318904: step: 1696/530, loss: 0.0020175965037196875
2023-01-23 03:26:27.445676: step: 1700/530, loss: 0.005991172976791859
2023-01-23 03:26:28.577181: step: 1704/530, loss: 1.468658410885837e-05
2023-01-23 03:26:29.669799: step: 1708/530, loss: 7.209777686512098e-05
2023-01-23 03:26:30.792875: step: 1712/530, loss: 0.0023065567947924137
2023-01-23 03:26:31.895766: step: 1716/530, loss: 0.0073375701904296875
2023-01-23 03:26:32.986350: step: 1720/530, loss: 0.12027668952941895
2023-01-23 03:26:34.099233: step: 1724/530, loss: 0.04579009860754013
2023-01-23 03:26:35.243798: step: 1728/530, loss: 0.0013393402332440019
2023-01-23 03:26:36.350386: step: 1732/530, loss: 0.026813127100467682
2023-01-23 03:26:37.472589: step: 1736/530, loss: 0.0028240205720067024
2023-01-23 03:26:38.587446: step: 1740/530, loss: 0.0001180648832814768
2023-01-23 03:26:39.725654: step: 1744/530, loss: 0.14016051590442657
2023-01-23 03:26:40.854616: step: 1748/530, loss: 0.07469246536493301
2023-01-23 03:26:41.994234: step: 1752/530, loss: 0.0035542489495128393
2023-01-23 03:26:43.131458: step: 1756/530, loss: 0.00022583008103538305
2023-01-23 03:26:44.245472: step: 1760/530, loss: 0.00032672882662154734
2023-01-23 03:26:45.375519: step: 1764/530, loss: 0.049144744873046875
2023-01-23 03:26:46.517351: step: 1768/530, loss: 7.886887033237144e-05
2023-01-23 03:26:47.643430: step: 1772/530, loss: 0.0015050411457195878
2023-01-23 03:26:48.755655: step: 1776/530, loss: 0.031502917408943176
2023-01-23 03:26:49.879508: step: 1780/530, loss: 0.0012326240539550781
2023-01-23 03:26:50.995929: step: 1784/530, loss: 0.23514500260353088
2023-01-23 03:26:52.121518: step: 1788/530, loss: 2.5087525844573975
2023-01-23 03:26:53.257529: step: 1792/530, loss: 0.00015745163545943797
2023-01-23 03:26:54.380360: step: 1796/530, loss: 5.1116945542162284e-05
2023-01-23 03:26:55.494787: step: 1800/530, loss: 0.0184160228818655
2023-01-23 03:26:56.632768: step: 1804/530, loss: 0.007402992341667414
2023-01-23 03:26:57.747914: step: 1808/530, loss: 5.2356725063873455e-05
2023-01-23 03:26:58.896309: step: 1812/530, loss: 8.7738037109375e-05
2023-01-23 03:27:00.043276: step: 1816/530, loss: 0.008153343573212624
2023-01-23 03:27:01.180350: step: 1820/530, loss: 0.0234832763671875
2023-01-23 03:27:02.327608: step: 1824/530, loss: 0.004779052920639515
2023-01-23 03:27:03.448416: step: 1828/530, loss: 1.033958077430725
2023-01-23 03:27:04.601563: step: 1832/530, loss: 0.0658964142203331
2023-01-23 03:27:05.691298: step: 1836/530, loss: 0.003172588534653187
2023-01-23 03:27:06.833926: step: 1840/530, loss: 0.5437927842140198
2023-01-23 03:27:07.947486: step: 1844/530, loss: 7.25746140233241e-05
2023-01-23 03:27:09.084240: step: 1848/530, loss: 0.009994315914809704
2023-01-23 03:27:10.195403: step: 1852/530, loss: 0.00011787415132857859
2023-01-23 03:27:11.327082: step: 1856/530, loss: 0.00974807795137167
2023-01-23 03:27:12.460752: step: 1860/530, loss: 0.012867546640336514
2023-01-23 03:27:13.583096: step: 1864/530, loss: 0.019749069586396217
2023-01-23 03:27:14.728101: step: 1868/530, loss: 0.002157306531444192
2023-01-23 03:27:15.847304: step: 1872/530, loss: 5.917549060541205e-05
2023-01-23 03:27:16.952666: step: 1876/530, loss: 0.0006668091518804431
2023-01-23 03:27:18.069143: step: 1880/530, loss: 0.02253551594913006
2023-01-23 03:27:19.176175: step: 1884/530, loss: 0.02967710606753826
2023-01-23 03:27:20.304296: step: 1888/530, loss: 0.001216125558130443
2023-01-23 03:27:21.415714: step: 1892/530, loss: 9.727478754939511e-06
2023-01-23 03:27:22.544307: step: 1896/530, loss: 0.00202598562464118
2023-01-23 03:27:23.696425: step: 1900/530, loss: 0.00018644332885742188
2023-01-23 03:27:24.828071: step: 1904/530, loss: 7.486343747586943e-06
2023-01-23 03:27:25.964981: step: 1908/530, loss: 0.00221080775372684
2023-01-23 03:27:27.069294: step: 1912/530, loss: 0.051728151738643646
2023-01-23 03:27:28.234859: step: 1916/530, loss: 0.028162576258182526
2023-01-23 03:27:29.360761: step: 1920/530, loss: 0.0009329795720987022
2023-01-23 03:27:30.478659: step: 1924/530, loss: 0.010509109124541283
2023-01-23 03:27:31.616469: step: 1928/530, loss: 0.0012278556823730469
2023-01-23 03:27:32.750111: step: 1932/530, loss: 0.0048049925826489925
2023-01-23 03:27:33.852756: step: 1936/530, loss: 0.001105022500269115
2023-01-23 03:27:35.013344: step: 1940/530, loss: 0.014538764953613281
2023-01-23 03:27:36.127608: step: 1944/530, loss: 0.0001770019589457661
2023-01-23 03:27:37.261913: step: 1948/530, loss: 0.0003121376212220639
2023-01-23 03:27:38.370506: step: 1952/530, loss: 0.007830333895981312
2023-01-23 03:27:39.501595: step: 1956/530, loss: 0.004420948214828968
2023-01-23 03:27:40.629125: step: 1960/530, loss: 0.026820659637451172
2023-01-23 03:27:41.776780: step: 1964/530, loss: 0.00023136139498092234
2023-01-23 03:27:42.911043: step: 1968/530, loss: 0.01574230194091797
2023-01-23 03:27:44.027177: step: 1972/530, loss: 0.02344541624188423
2023-01-23 03:27:45.144379: step: 1976/530, loss: 0.004365349188446999
2023-01-23 03:27:46.277716: step: 1980/530, loss: 0.020294189453125
2023-01-23 03:27:47.386293: step: 1984/530, loss: 0.0005817413330078125
2023-01-23 03:27:48.578395: step: 1988/530, loss: 0.0023246766068041325
2023-01-23 03:27:49.706017: step: 1992/530, loss: 0.0026029585860669613
2023-01-23 03:27:50.836967: step: 1996/530, loss: 0.1726539582014084
2023-01-23 03:27:51.962011: step: 2000/530, loss: 0.00016880035400390625
2023-01-23 03:27:53.075747: step: 2004/530, loss: 0.0009980201721191406
2023-01-23 03:27:54.204155: step: 2008/530, loss: 0.010536002926528454
2023-01-23 03:27:55.311051: step: 2012/530, loss: 0.0001770019589457661
2023-01-23 03:27:56.450893: step: 2016/530, loss: 0.0006753921625204384
2023-01-23 03:27:57.623338: step: 2020/530, loss: 0.002168846083804965
2023-01-23 03:27:58.747876: step: 2024/530, loss: 0.01672658883035183
2023-01-23 03:27:59.871878: step: 2028/530, loss: 0.00032329559326171875
2023-01-23 03:28:00.988140: step: 2032/530, loss: 0.04158210754394531
2023-01-23 03:28:02.155135: step: 2036/530, loss: 3.5095217754133046e-05
2023-01-23 03:28:03.310926: step: 2040/530, loss: 0.0030174257699400187
2023-01-23 03:28:04.466195: step: 2044/530, loss: 0.00010643005225574598
2023-01-23 03:28:05.606086: step: 2048/530, loss: 0.0012750625610351562
2023-01-23 03:28:06.745273: step: 2052/530, loss: 0.0005777358892373741
2023-01-23 03:28:07.875543: step: 2056/530, loss: 0.000556564365979284
2023-01-23 03:28:08.998960: step: 2060/530, loss: 0.003240251448005438
2023-01-23 03:28:10.182814: step: 2064/530, loss: 0.0016705513698980212
2023-01-23 03:28:11.293850: step: 2068/530, loss: 0.00024433137150481343
2023-01-23 03:28:12.432934: step: 2072/530, loss: 0.004001522436738014
2023-01-23 03:28:13.560866: step: 2076/530, loss: 0.0004519462527241558
2023-01-23 03:28:14.666504: step: 2080/530, loss: 0.0057003977708518505
2023-01-23 03:28:15.762596: step: 2084/530, loss: 9.384155418956652e-05
2023-01-23 03:28:16.910429: step: 2088/530, loss: 0.0015964508056640625
2023-01-23 03:28:18.078186: step: 2092/530, loss: 4.920959327137098e-05
2023-01-23 03:28:19.216917: step: 2096/530, loss: 0.0012268066639080644
2023-01-23 03:28:20.343630: step: 2100/530, loss: 0.0002544403250794858
2023-01-23 03:28:21.481623: step: 2104/530, loss: 0.0010980606311932206
2023-01-23 03:28:22.607514: step: 2108/530, loss: 0.0007318496936932206
2023-01-23 03:28:23.704843: step: 2112/530, loss: 0.0005483627319335938
2023-01-23 03:28:24.857246: step: 2116/530, loss: 0.00023312569828704
2023-01-23 03:28:25.971501: step: 2120/530, loss: 0.044845011085271835
==================================================
Loss: 0.029
--------------------
Dev: {'event': {'p': 0.5926294820717132, 'r': 0.7922769640479361, 'f1': 0.6780626780626782}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Test: {'event': {'p': 0.6258896797153025, 'r': 0.804, 'f1': 0.7038519259629815}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Chinese: {'event': {'p': 0.5393258426966292, 'r': 0.8888888888888888, 'f1': 0.6713286713286712}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Korean: {'event': {'p': 0.5862068965517241, 'r': 0.5396825396825397, 'f1': 0.5619834710743802}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Russian: {'event': {'p': 0.4444444444444444, 'r': 0.5555555555555556, 'f1': 0.49382716049382713}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6198257080610022, 'r': 0.7576564580559254, 'f1': 0.6818454164170161}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
Eng Test for Chinese: {'event': {'p': 0.642925430210325, 'r': 0.7685714285714286, 'f1': 0.7001561686621551}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
Sample Chinese: {'event': {'p': 0.6153846153846154, 'r': 0.8888888888888888, 'f1': 0.7272727272727274}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6288770053475936, 'r': 0.7829560585885486, 'f1': 0.697508896797153}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Korean: {'event': {'p': 0.64058795637743, 'r': 0.772, 'f1': 0.7001813941435606}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Korean: {'event': {'p': 0.6851851851851852, 'r': 0.5873015873015873, 'f1': 0.6324786324786325}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5319148936170213, 'r': 0.6944444444444444, 'f1': 0.6024096385542169}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
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 03:29:07.098520: step: 4/530, loss: 0.0002652168332133442
2023-01-23 03:29:08.200224: step: 8/530, loss: 0.0021867752075195312
2023-01-23 03:29:09.322045: step: 12/530, loss: 5.736351158702746e-05
2023-01-23 03:29:10.424977: step: 16/530, loss: 0.0004987717256881297
2023-01-23 03:29:11.544508: step: 20/530, loss: 0.0022054670844227076
2023-01-23 03:29:12.659910: step: 24/530, loss: 0.00011386871483409777
2023-01-23 03:29:13.790940: step: 28/530, loss: 9.303689148509875e-05
2023-01-23 03:29:14.925042: step: 32/530, loss: 0.00013236999802757055
2023-01-23 03:29:16.087431: step: 36/530, loss: 0.24577312171459198
2023-01-23 03:29:17.204648: step: 40/530, loss: 0.018052147701382637
2023-01-23 03:29:18.342672: step: 44/530, loss: 0.0033402920234948397
2023-01-23 03:29:19.475378: step: 48/530, loss: 0.0001921653893077746
2023-01-23 03:29:20.605195: step: 52/530, loss: 0.0017047881847247481
2023-01-23 03:29:21.749274: step: 56/530, loss: 0.000439357798313722
2023-01-23 03:29:22.864424: step: 60/530, loss: 0.00656738318502903
2023-01-23 03:29:24.041404: step: 64/530, loss: 0.00370616908185184
2023-01-23 03:29:25.160926: step: 68/530, loss: 0.0008543014409951866
2023-01-23 03:29:26.259871: step: 72/530, loss: 0.0005480766412802041
2023-01-23 03:29:27.389618: step: 76/530, loss: 0.0012156486045569181
2023-01-23 03:29:28.490585: step: 80/530, loss: 9.35554489842616e-05
2023-01-23 03:29:29.596830: step: 84/530, loss: 0.00045013427734375
2023-01-23 03:29:30.699949: step: 88/530, loss: 9.002685692394152e-05
2023-01-23 03:29:31.813337: step: 92/530, loss: 0.0024712085723876953
2023-01-23 03:29:32.953968: step: 96/530, loss: 0.023923112079501152
2023-01-23 03:29:34.071643: step: 100/530, loss: 0.00013589859008789062
2023-01-23 03:29:35.172347: step: 104/530, loss: 0.005844783969223499
2023-01-23 03:29:36.320938: step: 108/530, loss: 0.00018224716768600047
2023-01-23 03:29:37.458328: step: 112/530, loss: 0.031000234186649323
2023-01-23 03:29:38.598021: step: 116/530, loss: 0.012397194281220436
2023-01-23 03:29:39.717847: step: 120/530, loss: 0.47705334424972534
2023-01-23 03:29:40.876983: step: 124/530, loss: 0.0020711899269372225
2023-01-23 03:29:42.004976: step: 128/530, loss: 0.014756584540009499
2023-01-23 03:29:43.120598: step: 132/530, loss: 0.0003341674746479839
2023-01-23 03:29:44.237957: step: 136/530, loss: -9.5367431640625e-06
2023-01-23 03:29:45.343714: step: 140/530, loss: 1.4686585018353071e-05
2023-01-23 03:29:46.469625: step: 144/530, loss: 1.5068053471622989e-05
2023-01-23 03:29:47.580014: step: 148/530, loss: 0.0022258758544921875
2023-01-23 03:29:48.703484: step: 152/530, loss: 0.005324650090187788
2023-01-23 03:29:49.826159: step: 156/530, loss: 0.004137897863984108
2023-01-23 03:29:50.942946: step: 160/530, loss: 0.0009320258977822959
2023-01-23 03:29:52.063854: step: 164/530, loss: 0.0018817902309820056
2023-01-23 03:29:53.206718: step: 168/530, loss: 0.015962744131684303
2023-01-23 03:29:54.341323: step: 172/530, loss: 0.13599014282226562
2023-01-23 03:29:55.468384: step: 176/530, loss: 0.004966879263520241
2023-01-23 03:29:56.616889: step: 180/530, loss: 0.05440349876880646
2023-01-23 03:29:57.768652: step: 184/530, loss: 0.010399341583251953
2023-01-23 03:29:58.866880: step: 188/530, loss: 0.00906233862042427
2023-01-23 03:30:00.020930: step: 192/530, loss: 0.0009181976201944053
2023-01-23 03:30:01.130241: step: 196/530, loss: 0.00033588410587981343
2023-01-23 03:30:02.241994: step: 200/530, loss: 0.00072736747097224
2023-01-23 03:30:03.379183: step: 204/530, loss: 0.0016552925808355212
2023-01-23 03:30:04.528377: step: 208/530, loss: 0.0005908965831622481
2023-01-23 03:30:05.663879: step: 212/530, loss: 0.018049050122499466
2023-01-23 03:30:06.815639: step: 216/530, loss: 0.0001046180768753402
2023-01-23 03:30:07.934376: step: 220/530, loss: 0.0018452645745128393
2023-01-23 03:30:09.032226: step: 224/530, loss: 9.822845640883315e-06
2023-01-23 03:30:10.181231: step: 228/530, loss: 0.0008958816761150956
2023-01-23 03:30:11.301503: step: 232/530, loss: 0.0030859948601573706
2023-01-23 03:30:12.414768: step: 236/530, loss: 0.001262664794921875
2023-01-23 03:30:13.555461: step: 240/530, loss: 0.00992963369935751
2023-01-23 03:30:14.647249: step: 244/530, loss: 0.004852390848100185
2023-01-23 03:30:15.784389: step: 248/530, loss: 0.0006431579822674394
2023-01-23 03:30:16.904444: step: 252/530, loss: 0.0007895947201177478
2023-01-23 03:30:18.016088: step: 256/530, loss: 0.00016098022751975805
2023-01-23 03:30:19.140682: step: 260/530, loss: 0.0013866424560546875
2023-01-23 03:30:20.279331: step: 264/530, loss: 0.00020599365234375
2023-01-23 03:30:21.423874: step: 268/530, loss: 0.15336064994335175
2023-01-23 03:30:22.522349: step: 272/530, loss: 0.0008141517173498869
2023-01-23 03:30:23.633146: step: 276/530, loss: 0.005021095275878906
2023-01-23 03:30:24.793205: step: 280/530, loss: 1.4400483451026957e-05
2023-01-23 03:30:25.921958: step: 284/530, loss: 0.013475418090820312
2023-01-23 03:30:27.053955: step: 288/530, loss: 0.002843189286068082
2023-01-23 03:30:28.183935: step: 292/530, loss: 0.0139312744140625
2023-01-23 03:30:29.320592: step: 296/530, loss: 0.0029879570938646793
2023-01-23 03:30:30.448734: step: 300/530, loss: 0.0336429625749588
2023-01-23 03:30:31.583934: step: 304/530, loss: 0.00017967224994208664
2023-01-23 03:30:32.734332: step: 308/530, loss: 0.025636862963438034
2023-01-23 03:30:33.882063: step: 312/530, loss: 0.0016681670676916838
2023-01-23 03:30:35.006818: step: 316/530, loss: 0.007277298253029585
2023-01-23 03:30:36.129382: step: 320/530, loss: 0.007306623738259077
2023-01-23 03:30:37.225241: step: 324/530, loss: 4.291534423828125e-05
2023-01-23 03:30:38.338402: step: 328/530, loss: 1.6468709707260132
2023-01-23 03:30:39.463946: step: 332/530, loss: 0.08663330227136612
2023-01-23 03:30:40.587329: step: 336/530, loss: 0.013335847295820713
2023-01-23 03:30:41.729409: step: 340/530, loss: 2.307891918462701e-05
2023-01-23 03:30:42.927232: step: 344/530, loss: 0.0011133194202557206
2023-01-23 03:30:44.042567: step: 348/530, loss: 0.0002575874386820942
2023-01-23 03:30:45.146244: step: 352/530, loss: 0.00011959076073253527
2023-01-23 03:30:46.267602: step: 356/530, loss: 0.0016545295948162675
2023-01-23 03:30:47.403190: step: 360/530, loss: 0.0014316559536382556
2023-01-23 03:30:48.515887: step: 364/530, loss: 0.0029211044311523438
2023-01-23 03:30:49.644485: step: 368/530, loss: 0.001989364856854081
2023-01-23 03:30:50.766638: step: 372/530, loss: -9.536744016713783e-08
2023-01-23 03:30:51.884793: step: 376/530, loss: 0.0011081695556640625
2023-01-23 03:30:53.001093: step: 380/530, loss: 0.0003450393851380795
2023-01-23 03:30:54.138125: step: 384/530, loss: 0.005698681343346834
2023-01-23 03:30:55.250298: step: 388/530, loss: 0.0011629104847088456
2023-01-23 03:30:56.384607: step: 392/530, loss: 0.00044193267240189016
2023-01-23 03:30:57.477507: step: 396/530, loss: 0.000639629433862865
2023-01-23 03:30:58.634357: step: 400/530, loss: 0.034870147705078125
2023-01-23 03:30:59.752443: step: 404/530, loss: 0.0034341812133789062
2023-01-23 03:31:00.884888: step: 408/530, loss: 1.888275073724799e-05
2023-01-23 03:31:01.997276: step: 412/530, loss: 1.621246337890625e-05
2023-01-23 03:31:03.117664: step: 416/530, loss: 0.01134481467306614
2023-01-23 03:31:04.249457: step: 420/530, loss: 7.629396350239404e-07
2023-01-23 03:31:05.356551: step: 424/530, loss: 2.307891918462701e-05
2023-01-23 03:31:06.469287: step: 428/530, loss: 4.482892990112305
2023-01-23 03:31:07.614740: step: 432/530, loss: 0.01120071392506361
2023-01-23 03:31:08.749209: step: 436/530, loss: 0.006993246264755726
2023-01-23 03:31:09.869857: step: 440/530, loss: 0.3945600390434265
2023-01-23 03:31:11.015762: step: 444/530, loss: 5.4359438763640355e-06
2023-01-23 03:31:12.146416: step: 448/530, loss: 0.0001337051362497732
2023-01-23 03:31:13.295572: step: 452/530, loss: 0.043811991810798645
2023-01-23 03:31:14.391128: step: 456/530, loss: 0.00966491736471653
2023-01-23 03:31:15.510214: step: 460/530, loss: 0.00011901855032192543
2023-01-23 03:31:16.658954: step: 464/530, loss: 0.020872557535767555
2023-01-23 03:31:17.786529: step: 468/530, loss: 0.0007745742914266884
2023-01-23 03:31:18.921689: step: 472/530, loss: 3.814697265625e-05
2023-01-23 03:31:20.027455: step: 476/530, loss: 0.017302418127655983
2023-01-23 03:31:21.159060: step: 480/530, loss: 0.0019216537475585938
2023-01-23 03:31:22.294786: step: 484/530, loss: 0.00607566861435771
2023-01-23 03:31:23.431377: step: 488/530, loss: 0.0013240814441815019
2023-01-23 03:31:24.564926: step: 492/530, loss: 0.04228191450238228
2023-01-23 03:31:25.665962: step: 496/530, loss: 0.0047626495361328125
2023-01-23 03:31:26.824938: step: 500/530, loss: 0.00312042236328125
2023-01-23 03:31:27.947152: step: 504/530, loss: 0.0016063690418377519
2023-01-23 03:31:29.083796: step: 508/530, loss: 0.0020351409912109375
2023-01-23 03:31:30.210895: step: 512/530, loss: 3.395080420887098e-05
2023-01-23 03:31:31.357205: step: 516/530, loss: 0.021654892712831497
2023-01-23 03:31:32.507820: step: 520/530, loss: 4.138946678722277e-05
2023-01-23 03:31:33.638517: step: 524/530, loss: 0.0013813019031658769
2023-01-23 03:31:34.739566: step: 528/530, loss: 0.009017754346132278
2023-01-23 03:31:35.862098: step: 532/530, loss: 0.006644630804657936
2023-01-23 03:31:37.000647: step: 536/530, loss: 2.098083541568485e-06
2023-01-23 03:31:38.141527: step: 540/530, loss: 6.198883056640625e-05
2023-01-23 03:31:39.268334: step: 544/530, loss: 1.2207030522404239e-05
2023-01-23 03:31:40.401070: step: 548/530, loss: 0.01349563617259264
2023-01-23 03:31:41.534873: step: 552/530, loss: 0.005539512727409601
2023-01-23 03:31:42.666497: step: 556/530, loss: 0.00018587111844681203
2023-01-23 03:31:43.795155: step: 560/530, loss: 0.007181453984230757
2023-01-23 03:31:44.916311: step: 564/530, loss: 0.01138381939381361
2023-01-23 03:31:46.040108: step: 568/530, loss: 0.003118896624073386
2023-01-23 03:31:47.180753: step: 572/530, loss: 0.0012011528015136719
2023-01-23 03:31:48.286495: step: 576/530, loss: 0.0004024505615234375
2023-01-23 03:31:49.434846: step: 580/530, loss: 0.00271778111346066
2023-01-23 03:31:50.540221: step: 584/530, loss: 0.0004760742303915322
2023-01-23 03:31:51.650958: step: 588/530, loss: 5.91278057981981e-06
2023-01-23 03:31:52.783538: step: 592/530, loss: 0.04535055160522461
2023-01-23 03:31:53.916656: step: 596/530, loss: 0.000162219992489554
2023-01-23 03:31:55.032291: step: 600/530, loss: 0.0010696887038648129
2023-01-23 03:31:56.163830: step: 604/530, loss: 0.038133811205625534
2023-01-23 03:31:57.273733: step: 608/530, loss: 0.0013736725086346269
2023-01-23 03:31:58.371700: step: 612/530, loss: 0.11062164604663849
2023-01-23 03:31:59.465280: step: 616/530, loss: 0.003072738880291581
2023-01-23 03:32:00.597280: step: 620/530, loss: 0.005662345793098211
2023-01-23 03:32:01.697494: step: 624/530, loss: 5.2165985835017636e-05
2023-01-23 03:32:02.841100: step: 628/530, loss: 0.03488664701581001
2023-01-23 03:32:03.977388: step: 632/530, loss: 0.0001316070556640625
2023-01-23 03:32:05.112974: step: 636/530, loss: 0.031374357640743256
2023-01-23 03:32:06.228415: step: 640/530, loss: 0.026055097579956055
2023-01-23 03:32:07.406903: step: 644/530, loss: 0.051069069653749466
2023-01-23 03:32:08.537038: step: 648/530, loss: 0.00034923554630950093
2023-01-23 03:32:09.644477: step: 652/530, loss: 0.009720420464873314
2023-01-23 03:32:10.753512: step: 656/530, loss: 1.0967255548166577e-05
2023-01-23 03:32:11.865716: step: 660/530, loss: 0.0012415886158123612
2023-01-23 03:32:12.986438: step: 664/530, loss: 0.004417038056999445
2023-01-23 03:32:14.127555: step: 668/530, loss: 0.00018463133892510086
2023-01-23 03:32:15.250013: step: 672/530, loss: 0.0075469971634447575
2023-01-23 03:32:16.368532: step: 676/530, loss: 0.03972005844116211
2023-01-23 03:32:17.486729: step: 680/530, loss: 0.007507515139877796
2023-01-23 03:32:18.577856: step: 684/530, loss: 0.0022188189905136824
2023-01-23 03:32:19.738666: step: 688/530, loss: 0.005376625340431929
2023-01-23 03:32:20.847840: step: 692/530, loss: 0.0035339356400072575
2023-01-23 03:32:21.960351: step: 696/530, loss: 3.5953522456111386e-05
2023-01-23 03:32:23.115543: step: 700/530, loss: 0.0020013810135424137
2023-01-23 03:32:24.241185: step: 704/530, loss: 0.00698013324290514
2023-01-23 03:32:25.383449: step: 708/530, loss: 0.007763099856674671
2023-01-23 03:32:26.486660: step: 712/530, loss: 0.03202075883746147
2023-01-23 03:32:27.599369: step: 716/530, loss: 0.0015447615878656507
2023-01-23 03:32:28.747490: step: 720/530, loss: 0.0006816864479333162
2023-01-23 03:32:29.870344: step: 724/530, loss: 0.0010725021129474044
2023-01-23 03:32:31.009915: step: 728/530, loss: 0.14784927666187286
2023-01-23 03:32:32.156456: step: 732/530, loss: 0.02184581756591797
2023-01-23 03:32:33.298474: step: 736/530, loss: 0.00106048583984375
2023-01-23 03:32:34.432812: step: 740/530, loss: 0.02141733095049858
2023-01-23 03:32:35.552172: step: 744/530, loss: 0.0013959883945062757
2023-01-23 03:32:36.694688: step: 748/530, loss: 0.05695819854736328
2023-01-23 03:32:37.815050: step: 752/530, loss: 0.008107949048280716
2023-01-23 03:32:38.961684: step: 756/530, loss: 0.0022806168999522924
2023-01-23 03:32:40.073947: step: 760/530, loss: 0.00018024444580078125
2023-01-23 03:32:41.230551: step: 764/530, loss: 0.02486133575439453
2023-01-23 03:32:42.353977: step: 768/530, loss: 0.0014122009743005037
2023-01-23 03:32:43.493375: step: 772/530, loss: 0.004006910603493452
2023-01-23 03:32:44.612869: step: 776/530, loss: 0.058977700769901276
2023-01-23 03:32:45.758851: step: 780/530, loss: 0.03047809563577175
2023-01-23 03:32:46.873047: step: 784/530, loss: 0.009504414163529873
2023-01-23 03:32:47.983969: step: 788/530, loss: 0.0023006440605968237
2023-01-23 03:32:49.126954: step: 792/530, loss: 0.019623756408691406
2023-01-23 03:32:50.239495: step: 796/530, loss: 0.005626964382827282
2023-01-23 03:32:51.366030: step: 800/530, loss: 0.0004570961173158139
2023-01-23 03:32:52.481120: step: 804/530, loss: 0.060202695429325104
2023-01-23 03:32:53.610143: step: 808/530, loss: 8.420944504905492e-05
2023-01-23 03:32:54.742973: step: 812/530, loss: 0.0019321441650390625
2023-01-23 03:32:55.861719: step: 816/530, loss: 0.06533565372228622
2023-01-23 03:32:57.001224: step: 820/530, loss: 0.0016355514526367188
2023-01-23 03:32:58.127513: step: 824/530, loss: 0.006747054867446423
2023-01-23 03:32:59.252551: step: 828/530, loss: 2.6988984245690517e-05
2023-01-23 03:33:00.376375: step: 832/530, loss: 0.00012931822857353836
2023-01-23 03:33:01.519686: step: 836/530, loss: 0.03265238180756569
2023-01-23 03:33:02.627838: step: 840/530, loss: 0.0001417636958649382
2023-01-23 03:33:03.758420: step: 844/530, loss: 0.00210914621129632
2023-01-23 03:33:04.894963: step: 848/530, loss: 0.000881195068359375
2023-01-23 03:33:06.023345: step: 852/530, loss: 0.0003283500554971397
2023-01-23 03:33:07.113932: step: 856/530, loss: 2.1457672119140625e-06
2023-01-23 03:33:08.201259: step: 860/530, loss: 0.002171135041862726
2023-01-23 03:33:09.327837: step: 864/530, loss: 0.0003616332833189517
2023-01-23 03:33:10.433076: step: 868/530, loss: 0.002990245819091797
2023-01-23 03:33:11.571975: step: 872/530, loss: 0.0005285263177938759
2023-01-23 03:33:12.752920: step: 876/530, loss: 0.00011482238915050402
2023-01-23 03:33:13.879319: step: 880/530, loss: 0.0002402305690338835
2023-01-23 03:33:14.984299: step: 884/530, loss: 9.31739850784652e-05
2023-01-23 03:33:16.079132: step: 888/530, loss: 0.00068073277361691
2023-01-23 03:33:17.208918: step: 892/530, loss: 0.003147983690723777
2023-01-23 03:33:18.344849: step: 896/530, loss: 0.0014652252430096269
2023-01-23 03:33:19.442461: step: 900/530, loss: 0.0007004737854003906
2023-01-23 03:33:20.560085: step: 904/530, loss: 6.008148375258315e-06
2023-01-23 03:33:21.689051: step: 908/530, loss: 0.06401939690113068
2023-01-23 03:33:22.804138: step: 912/530, loss: 0.0009490966913290322
2023-01-23 03:33:23.946894: step: 916/530, loss: 0.0013725280296057463
2023-01-23 03:33:25.081510: step: 920/530, loss: 0.022217940539121628
2023-01-23 03:33:26.206972: step: 924/530, loss: 0.1582581102848053
2023-01-23 03:33:27.382950: step: 928/530, loss: 0.0007942199590615928
2023-01-23 03:33:28.504585: step: 932/530, loss: 0.000782012939453125
2023-01-23 03:33:29.646510: step: 936/530, loss: 0.00031552318250760436
2023-01-23 03:33:30.748683: step: 940/530, loss: 0.00069427490234375
2023-01-23 03:33:31.864441: step: 944/530, loss: 1.6880036127986386e-05
2023-01-23 03:33:32.999902: step: 948/530, loss: 7.343292236328125e-05
2023-01-23 03:33:34.092066: step: 952/530, loss: 0.003228092333301902
2023-01-23 03:33:35.195297: step: 956/530, loss: 0.00015144346980378032
2023-01-23 03:33:36.365728: step: 960/530, loss: 0.00040464402991347015
2023-01-23 03:33:37.466821: step: 964/530, loss: 0.001304245088249445
2023-01-23 03:33:38.590353: step: 968/530, loss: 0.000301551801385358
2023-01-23 03:33:39.717149: step: 972/530, loss: 0.0001659393310546875
2023-01-23 03:33:40.798625: step: 976/530, loss: 0.027672292664647102
2023-01-23 03:33:41.926240: step: 980/530, loss: 0.0025873181875795126
2023-01-23 03:33:43.026634: step: 984/530, loss: 0.001699733780696988
2023-01-23 03:33:44.126632: step: 988/530, loss: 0.000926971435546875
2023-01-23 03:33:45.277758: step: 992/530, loss: 0.03643856197595596
2023-01-23 03:33:46.415251: step: 996/530, loss: 3.24249276673072e-06
2023-01-23 03:33:47.571731: step: 1000/530, loss: 4.9591064453125e-05
2023-01-23 03:33:48.698807: step: 1004/530, loss: 0.0005671501276083291
2023-01-23 03:33:49.862199: step: 1008/530, loss: 0.001154232071712613
2023-01-23 03:33:50.995386: step: 1012/530, loss: 0.031168939545750618
2023-01-23 03:33:52.105631: step: 1016/530, loss: 0.0010029793484136462
2023-01-23 03:33:53.307971: step: 1020/530, loss: 0.0015436172252520919
2023-01-23 03:33:54.466161: step: 1024/530, loss: 0.021173859015107155
2023-01-23 03:33:55.572564: step: 1028/530, loss: 0.05048447102308273
2023-01-23 03:33:56.718487: step: 1032/530, loss: 0.0004728376807179302
2023-01-23 03:33:57.873428: step: 1036/530, loss: 0.007236289791762829
2023-01-23 03:33:58.994886: step: 1040/530, loss: 0.0008633971447125077
2023-01-23 03:34:00.148435: step: 1044/530, loss: 0.014343309216201305
2023-01-23 03:34:01.260409: step: 1048/530, loss: 0.009192085824906826
2023-01-23 03:34:02.414041: step: 1052/530, loss: 0.004955005366355181
2023-01-23 03:34:03.515126: step: 1056/530, loss: 0.0013765335315838456
2023-01-23 03:34:04.624519: step: 1060/530, loss: 4.844665454584174e-05
2023-01-23 03:34:05.736637: step: 1064/530, loss: 0.00034670828608796
2023-01-23 03:34:06.857851: step: 1068/530, loss: 0.002631568815559149
2023-01-23 03:34:07.978272: step: 1072/530, loss: 6.0844424297101796e-05
2023-01-23 03:34:09.094030: step: 1076/530, loss: 0.0009773254860192537
2023-01-23 03:34:10.196057: step: 1080/530, loss: 0.009446144104003906
2023-01-23 03:34:11.328161: step: 1084/530, loss: 0.005185508634895086
2023-01-23 03:34:12.464398: step: 1088/530, loss: 0.040428876876831055
2023-01-23 03:34:13.601368: step: 1092/530, loss: 0.0006239891517907381
2023-01-23 03:34:14.740312: step: 1096/530, loss: 0.04018726199865341
2023-01-23 03:34:15.831864: step: 1100/530, loss: 2.1266938347253017e-05
2023-01-23 03:34:16.947443: step: 1104/530, loss: 0.0005405425908975303
2023-01-23 03:34:18.056068: step: 1108/530, loss: 0.0004604339774232358
2023-01-23 03:34:19.177345: step: 1112/530, loss: 3.948211815441027e-05
2023-01-23 03:34:20.326650: step: 1116/530, loss: 0.03215665742754936
2023-01-23 03:34:21.478883: step: 1120/530, loss: 0.0030050277709960938
2023-01-23 03:34:22.588719: step: 1124/530, loss: 4.386902219266631e-06
2023-01-23 03:34:23.708109: step: 1128/530, loss: 0.0014562606811523438
2023-01-23 03:34:24.856477: step: 1132/530, loss: 0.000377464311895892
2023-01-23 03:34:25.973940: step: 1136/530, loss: 0.002502012299373746
2023-01-23 03:34:27.076434: step: 1140/530, loss: 0.013344956561923027
2023-01-23 03:34:28.203979: step: 1144/530, loss: 0.0015727997524663806
2023-01-23 03:34:29.330400: step: 1148/530, loss: 0.008260536007583141
2023-01-23 03:34:30.458042: step: 1152/530, loss: 7.932185690151528e-05
2023-01-23 03:34:31.573624: step: 1156/530, loss: 5.7220458984375e-06
2023-01-23 03:34:32.684807: step: 1160/530, loss: 0.04091301187872887
2023-01-23 03:34:33.818070: step: 1164/530, loss: 0.0063818455673754215
2023-01-23 03:34:34.919721: step: 1168/530, loss: 0.004650211427360773
2023-01-23 03:34:36.049881: step: 1172/530, loss: 0.04616737738251686
2023-01-23 03:34:37.189535: step: 1176/530, loss: 0.0004634857177734375
2023-01-23 03:34:38.324197: step: 1180/530, loss: 4.9185753596248105e-05
2023-01-23 03:34:39.466652: step: 1184/530, loss: 0.0002958297554869205
2023-01-23 03:34:40.591854: step: 1188/530, loss: 0.07427101582288742
2023-01-23 03:34:41.699879: step: 1192/530, loss: 2.040863000729587e-05
2023-01-23 03:34:42.806897: step: 1196/530, loss: 0.48779773712158203
2023-01-23 03:34:43.951368: step: 1200/530, loss: 0.00032577518140897155
2023-01-23 03:34:45.080936: step: 1204/530, loss: 0.008599949069321156
2023-01-23 03:34:46.203181: step: 1208/530, loss: 0.0008096694946289062
2023-01-23 03:34:47.297127: step: 1212/530, loss: 0.013564110733568668
2023-01-23 03:34:48.415189: step: 1216/530, loss: 0.024104690179228783
2023-01-23 03:34:49.542248: step: 1220/530, loss: 0.0373104102909565
2023-01-23 03:34:50.673113: step: 1224/530, loss: 0.03739356994628906
2023-01-23 03:34:51.846431: step: 1228/530, loss: 0.0003410339413676411
2023-01-23 03:34:52.957466: step: 1232/530, loss: 0.010662746615707874
2023-01-23 03:34:54.080323: step: 1236/530, loss: 7.295608520507812e-05
2023-01-23 03:34:55.197855: step: 1240/530, loss: 0.00031194687471725047
2023-01-23 03:34:56.322723: step: 1244/530, loss: 0.5715429186820984
2023-01-23 03:34:57.419684: step: 1248/530, loss: 2.880096508306451e-05
2023-01-23 03:34:58.593262: step: 1252/530, loss: 0.01704993285238743
2023-01-23 03:34:59.714619: step: 1256/530, loss: 0.00756683386862278
2023-01-23 03:35:00.845042: step: 1260/530, loss: 0.0014079571701586246
2023-01-23 03:35:01.946033: step: 1264/530, loss: 0.002998924348503351
2023-01-23 03:35:03.088598: step: 1268/530, loss: 0.00014791489229537547
2023-01-23 03:35:04.217879: step: 1272/530, loss: 0.010972213931381702
2023-01-23 03:35:05.366909: step: 1276/530, loss: 0.0832241028547287
2023-01-23 03:35:06.472642: step: 1280/530, loss: 0.2894379496574402
2023-01-23 03:35:07.603396: step: 1284/530, loss: 0.00041284560575149953
2023-01-23 03:35:08.746241: step: 1288/530, loss: 0.0007882117643021047
2023-01-23 03:35:09.899517: step: 1292/530, loss: 0.0018182755447924137
2023-01-23 03:35:11.022036: step: 1296/530, loss: 0.0027608871459960938
2023-01-23 03:35:12.134875: step: 1300/530, loss: 0.0030174495186656713
2023-01-23 03:35:13.307498: step: 1304/530, loss: 0.05016689375042915
2023-01-23 03:35:14.421694: step: 1308/530, loss: 0.009126568213105202
2023-01-23 03:35:15.521247: step: 1312/530, loss: 1.9550323486328125e-05
2023-01-23 03:35:16.632335: step: 1316/530, loss: 0.003460502717643976
2023-01-23 03:35:17.723889: step: 1320/530, loss: 0.03002491220831871
2023-01-23 03:35:18.834018: step: 1324/530, loss: 0.03893012925982475
2023-01-23 03:35:19.966882: step: 1328/530, loss: 0.00024318695068359375
2023-01-23 03:35:21.071027: step: 1332/530, loss: 0.0005234241834841669
2023-01-23 03:35:22.200297: step: 1336/530, loss: 0.02037992514669895
2023-01-23 03:35:23.328666: step: 1340/530, loss: 0.007461833767592907
2023-01-23 03:35:24.466747: step: 1344/530, loss: 0.011014461517333984
2023-01-23 03:35:25.592186: step: 1348/530, loss: 0.0008279800531454384
2023-01-23 03:35:26.733675: step: 1352/530, loss: 0.00010414123244117945
2023-01-23 03:35:27.869969: step: 1356/530, loss: 0.04655780643224716
2023-01-23 03:35:28.991519: step: 1360/530, loss: 0.011810874566435814
2023-01-23 03:35:30.110671: step: 1364/530, loss: 7.066727266646922e-05
2023-01-23 03:35:31.233727: step: 1368/530, loss: 0.00028162001399323344
2023-01-23 03:35:32.337689: step: 1372/530, loss: 0.0029458999633789062
2023-01-23 03:35:33.463019: step: 1376/530, loss: 0.0025959014892578125
2023-01-23 03:35:34.571181: step: 1380/530, loss: 0.003925800323486328
2023-01-23 03:35:35.696143: step: 1384/530, loss: 0.02117319032549858
2023-01-23 03:35:36.857773: step: 1388/530, loss: 0.0001560211239848286
2023-01-23 03:35:38.039081: step: 1392/530, loss: 0.09024753421545029
2023-01-23 03:35:39.157067: step: 1396/530, loss: 0.0029159546829760075
2023-01-23 03:35:40.296830: step: 1400/530, loss: 0.00019493103900458664
2023-01-23 03:35:41.461025: step: 1404/530, loss: 0.03144645690917969
2023-01-23 03:35:42.600119: step: 1408/530, loss: 0.0027206421364098787
2023-01-23 03:35:43.747687: step: 1412/530, loss: 0.00043697358341887593
2023-01-23 03:35:44.897495: step: 1416/530, loss: 8.22067231638357e-05
2023-01-23 03:35:46.017495: step: 1420/530, loss: 0.00011167525372002274
2023-01-23 03:35:47.145018: step: 1424/530, loss: 0.044243812561035156
2023-01-23 03:35:48.246411: step: 1428/530, loss: 0.11790166050195694
2023-01-23 03:35:49.361925: step: 1432/530, loss: 0.0007271289941854775
2023-01-23 03:35:50.468519: step: 1436/530, loss: 7.796287536621094e-05
2023-01-23 03:35:51.575075: step: 1440/530, loss: 0.10536542534828186
2023-01-23 03:35:52.704183: step: 1444/530, loss: 0.03635730594396591
2023-01-23 03:35:53.836387: step: 1448/530, loss: 7.176399230957031e-05
2023-01-23 03:35:54.962906: step: 1452/530, loss: 0.014511299319565296
2023-01-23 03:35:56.075283: step: 1456/530, loss: 0.08388223499059677
2023-01-23 03:35:57.185895: step: 1460/530, loss: 0.00029792787972837687
2023-01-23 03:35:58.303638: step: 1464/530, loss: 5.7220458984375e-05
2023-01-23 03:35:59.435222: step: 1468/530, loss: 0.00041265488835051656
2023-01-23 03:36:00.547039: step: 1472/530, loss: 0.0018864631420001388
2023-01-23 03:36:01.670575: step: 1476/530, loss: 0.2275291383266449
2023-01-23 03:36:02.777631: step: 1480/530, loss: 0.0010129929287359118
2023-01-23 03:36:03.892238: step: 1484/530, loss: 0.0009576797601766884
2023-01-23 03:36:05.032804: step: 1488/530, loss: 0.02427196502685547
2023-01-23 03:36:06.135716: step: 1492/530, loss: 0.0002503395080566406
2023-01-23 03:36:07.256615: step: 1496/530, loss: 0.00032939910306595266
2023-01-23 03:36:08.404580: step: 1500/530, loss: 0.003056049346923828
2023-01-23 03:36:09.514676: step: 1504/530, loss: 0.0008501053089275956
2023-01-23 03:36:10.622415: step: 1508/530, loss: 0.007679510395973921
2023-01-23 03:36:11.763105: step: 1512/530, loss: 0.0004998207441531122
2023-01-23 03:36:12.917924: step: 1516/530, loss: 0.00039768218994140625
2023-01-23 03:36:14.024743: step: 1520/530, loss: 0.0057086944580078125
2023-01-23 03:36:15.148009: step: 1524/530, loss: 0.06266222149133682
2023-01-23 03:36:16.284067: step: 1528/530, loss: 0.0007397651788778603
2023-01-23 03:36:17.457741: step: 1532/530, loss: 0.0030588151421397924
2023-01-23 03:36:18.575162: step: 1536/530, loss: -1.9073468138230965e-07
2023-01-23 03:36:19.710847: step: 1540/530, loss: 0.004165077116340399
2023-01-23 03:36:20.845388: step: 1544/530, loss: 0.0005764961242675781
2023-01-23 03:36:21.962126: step: 1548/530, loss: 0.0015143394703045487
2023-01-23 03:36:23.098486: step: 1552/530, loss: 0.01902618445456028
2023-01-23 03:36:24.213915: step: 1556/530, loss: 0.0005631447420455515
2023-01-23 03:36:25.378446: step: 1560/530, loss: 0.005268335808068514
2023-01-23 03:36:26.500470: step: 1564/530, loss: 0.0013212204212322831
2023-01-23 03:36:27.632280: step: 1568/530, loss: 3.933906555175781e-06
2023-01-23 03:36:28.762495: step: 1572/530, loss: 0.0002745628298725933
2023-01-23 03:36:29.891772: step: 1576/530, loss: 0.0004952431190758944
2023-01-23 03:36:31.029162: step: 1580/530, loss: 0.0013483046786859632
2023-01-23 03:36:32.164213: step: 1584/530, loss: 0.0239944476634264
2023-01-23 03:36:33.268618: step: 1588/530, loss: 0.00026378632173873484
2023-01-23 03:36:34.381861: step: 1592/530, loss: 0.018082523718476295
2023-01-23 03:36:35.536164: step: 1596/530, loss: 0.004073714837431908
2023-01-23 03:36:36.620156: step: 1600/530, loss: 0.002628421876579523
2023-01-23 03:36:37.744489: step: 1604/530, loss: 5.34057608092553e-06
2023-01-23 03:36:38.890221: step: 1608/530, loss: 0.0017503738636150956
2023-01-23 03:36:40.015770: step: 1612/530, loss: 0.0005064487922936678
2023-01-23 03:36:41.148488: step: 1616/530, loss: 0.029465580359101295
2023-01-23 03:36:42.312341: step: 1620/530, loss: 0.0024291991721838713
2023-01-23 03:36:43.419147: step: 1624/530, loss: 0.0009017944685183465
2023-01-23 03:36:44.511218: step: 1628/530, loss: 0.06373786926269531
2023-01-23 03:36:45.626461: step: 1632/530, loss: 0.012770270928740501
2023-01-23 03:36:46.742079: step: 1636/530, loss: 0.00166578299831599
2023-01-23 03:36:47.895054: step: 1640/530, loss: 5.054474058852065e-06
2023-01-23 03:36:49.017884: step: 1644/530, loss: 0.000250399112701416
2023-01-23 03:36:50.123834: step: 1648/530, loss: 6.561278860317543e-05
2023-01-23 03:36:51.243760: step: 1652/530, loss: 0.0007844925276003778
2023-01-23 03:36:52.356135: step: 1656/530, loss: 0.02035980299115181
2023-01-23 03:36:53.488326: step: 1660/530, loss: 0.011255073361098766
2023-01-23 03:36:54.602463: step: 1664/530, loss: 0.047866251319646835
2023-01-23 03:36:55.710534: step: 1668/530, loss: 0.0017274855636060238
2023-01-23 03:36:56.809902: step: 1672/530, loss: 0.00018740296945907176
2023-01-23 03:36:57.914967: step: 1676/530, loss: 0.0021615028381347656
2023-01-23 03:36:59.044765: step: 1680/530, loss: 0.03169288486242294
2023-01-23 03:37:00.160688: step: 1684/530, loss: 4.291534423828125e-06
2023-01-23 03:37:01.311714: step: 1688/530, loss: 0.0038038729690015316
2023-01-23 03:37:02.456769: step: 1692/530, loss: 2.288818359375e-05
2023-01-23 03:37:03.572500: step: 1696/530, loss: 5.054473876953125e-05
2023-01-23 03:37:04.660939: step: 1700/530, loss: 0.04905281215906143
2023-01-23 03:37:05.775282: step: 1704/530, loss: 0.009461402893066406
2023-01-23 03:37:06.884675: step: 1708/530, loss: 0.015836715698242188
2023-01-23 03:37:08.024415: step: 1712/530, loss: 5.2928924560546875e-05
2023-01-23 03:37:09.148952: step: 1716/530, loss: 0.00027809140738099813
2023-01-23 03:37:10.254469: step: 1720/530, loss: 0.00023746491933707148
2023-01-23 03:37:11.375651: step: 1724/530, loss: 0.000225067138671875
2023-01-23 03:37:12.487170: step: 1728/530, loss: 0.0018990517128258944
2023-01-23 03:37:13.648799: step: 1732/530, loss: 0.0005748748662881553
2023-01-23 03:37:14.760391: step: 1736/530, loss: 0.013747597113251686
2023-01-23 03:37:15.877559: step: 1740/530, loss: 6.29425048828125e-05
2023-01-23 03:37:17.044171: step: 1744/530, loss: 0.00020828247943427414
2023-01-23 03:37:18.148266: step: 1748/530, loss: 0.00048451422480866313
2023-01-23 03:37:19.283936: step: 1752/530, loss: 0.006011295598000288
2023-01-23 03:37:20.410491: step: 1756/530, loss: 0.04006242752075195
2023-01-23 03:37:21.515158: step: 1760/530, loss: 0.00028905869112350047
2023-01-23 03:37:22.620318: step: 1764/530, loss: 0.0007390976534225047
2023-01-23 03:37:23.738004: step: 1768/530, loss: 0.8443310856819153
2023-01-23 03:37:24.863833: step: 1772/530, loss: 0.0006501197931356728
2023-01-23 03:37:25.996269: step: 1776/530, loss: 0.0036193716805428267
2023-01-23 03:37:27.118045: step: 1780/530, loss: 2.079009937006049e-05
2023-01-23 03:37:28.241547: step: 1784/530, loss: 0.006583786103874445
2023-01-23 03:37:29.331448: step: 1788/530, loss: 0.006136417388916016
2023-01-23 03:37:30.439411: step: 1792/530, loss: 0.00046596527681685984
2023-01-23 03:37:31.573765: step: 1796/530, loss: 0.06995125114917755
2023-01-23 03:37:32.686488: step: 1800/530, loss: 0.0018578529125079513
2023-01-23 03:37:33.802003: step: 1804/530, loss: 0.0067008971236646175
2023-01-23 03:37:34.910752: step: 1808/530, loss: 0.010495185852050781
2023-01-23 03:37:36.031628: step: 1812/530, loss: 1.373290979245212e-05
2023-01-23 03:37:37.179657: step: 1816/530, loss: 0.013246918097138405
2023-01-23 03:37:38.314264: step: 1820/530, loss: 0.00014605523028876632
2023-01-23 03:37:39.441233: step: 1824/530, loss: 0.0008626937633380294
2023-01-23 03:37:40.574929: step: 1828/530, loss: 0.002320671221241355
2023-01-23 03:37:41.696884: step: 1832/530, loss: 0.01488800160586834
2023-01-23 03:37:42.824954: step: 1836/530, loss: 0.0014726639492437243
2023-01-23 03:37:43.930842: step: 1840/530, loss: 0.025364303961396217
2023-01-23 03:37:45.035426: step: 1844/530, loss: 0.03314242511987686
2023-01-23 03:37:46.152443: step: 1848/530, loss: 0.027219535782933235
2023-01-23 03:37:47.271535: step: 1852/530, loss: 0.03045206144452095
2023-01-23 03:37:48.409011: step: 1856/530, loss: 0.012042809277772903
2023-01-23 03:37:49.524401: step: 1860/530, loss: -0.0
2023-01-23 03:37:50.648418: step: 1864/530, loss: 0.009336852468550205
2023-01-23 03:37:51.766327: step: 1868/530, loss: 0.00034294126089662313
2023-01-23 03:37:52.909088: step: 1872/530, loss: 0.0014785766834393144
2023-01-23 03:37:54.036157: step: 1876/530, loss: 0.08442115783691406
2023-01-23 03:37:55.160634: step: 1880/530, loss: 0.003116178559139371
2023-01-23 03:37:56.286504: step: 1884/530, loss: 0.009947204031050205
2023-01-23 03:37:57.375454: step: 1888/530, loss: 8.449554297840223e-05
2023-01-23 03:37:58.490189: step: 1892/530, loss: 0.0009847640758380294
2023-01-23 03:37:59.597966: step: 1896/530, loss: 0.040963172912597656
2023-01-23 03:38:00.703014: step: 1900/530, loss: 0.013965511694550514
2023-01-23 03:38:01.822911: step: 1904/530, loss: 0.05112838372588158
2023-01-23 03:38:02.928571: step: 1908/530, loss: 0.0006885528564453125
2023-01-23 03:38:04.021819: step: 1912/530, loss: 0.0009851455688476562
2023-01-23 03:38:05.163294: step: 1916/530, loss: 0.20425738394260406
2023-01-23 03:38:06.316536: step: 1920/530, loss: 0.0018428802723065019
2023-01-23 03:38:07.441044: step: 1924/530, loss: 0.03312397003173828
2023-01-23 03:38:08.570655: step: 1928/530, loss: 0.03607216104865074
2023-01-23 03:38:09.693165: step: 1932/530, loss: 5.90324416407384e-05
2023-01-23 03:38:10.824279: step: 1936/530, loss: 0.06407833099365234
2023-01-23 03:38:11.971582: step: 1940/530, loss: 0.0021198273170739412
2023-01-23 03:38:13.068808: step: 1944/530, loss: 0.007351208012551069
2023-01-23 03:38:14.175900: step: 1948/530, loss: 0.0006916105630807579
2023-01-23 03:38:15.326332: step: 1952/530, loss: 0.012972068972885609
2023-01-23 03:38:16.445528: step: 1956/530, loss: 0.00340957660228014
2023-01-23 03:38:17.560626: step: 1960/530, loss: 0.0008537292596884072
2023-01-23 03:38:18.682802: step: 1964/530, loss: 0.00670547503978014
2023-01-23 03:38:19.816140: step: 1968/530, loss: 0.0009922027820721269
2023-01-23 03:38:20.964597: step: 1972/530, loss: 0.0006067276117391884
2023-01-23 03:38:22.084828: step: 1976/530, loss: 0.47459742426872253
2023-01-23 03:38:23.230648: step: 1980/530, loss: 0.0037537156604230404
2023-01-23 03:38:24.350432: step: 1984/530, loss: 3.8528440200025216e-05
2023-01-23 03:38:25.481203: step: 1988/530, loss: 0.0028828619979321957
2023-01-23 03:38:26.588030: step: 1992/530, loss: 0.0012567519443109632
2023-01-23 03:38:27.725495: step: 1996/530, loss: 0.00022573472233489156
2023-01-23 03:38:28.860128: step: 2000/530, loss: 0.0003105163632426411
2023-01-23 03:38:29.980635: step: 2004/530, loss: 0.009796142578125
2023-01-23 03:38:31.090351: step: 2008/530, loss: 0.007603490725159645
2023-01-23 03:38:32.239086: step: 2012/530, loss: 0.0157470703125
2023-01-23 03:38:33.385794: step: 2016/530, loss: 0.00042028428288176656
2023-01-23 03:38:34.496685: step: 2020/530, loss: 0.001254606293514371
2023-01-23 03:38:35.600306: step: 2024/530, loss: 0.0030759815126657486
2023-01-23 03:38:36.703517: step: 2028/530, loss: 0.2857952415943146
2023-01-23 03:38:37.854524: step: 2032/530, loss: 0.0008859634981490672
2023-01-23 03:38:38.967793: step: 2036/530, loss: 0.028385544195771217
2023-01-23 03:38:40.097627: step: 2040/530, loss: 8.640289888717234e-05
2023-01-23 03:38:41.218698: step: 2044/530, loss: 0.00027523041353560984
2023-01-23 03:38:42.352731: step: 2048/530, loss: 8.487701052217744e-06
2023-01-23 03:38:43.479258: step: 2052/530, loss: 0.01129379216581583
2023-01-23 03:38:44.593406: step: 2056/530, loss: 0.005154800601303577
2023-01-23 03:38:45.755851: step: 2060/530, loss: 0.0001354217529296875
2023-01-23 03:38:46.900202: step: 2064/530, loss: 0.00201072683557868
2023-01-23 03:38:47.995924: step: 2068/530, loss: 0.006250286009162664
2023-01-23 03:38:49.103656: step: 2072/530, loss: 0.026176119223237038
2023-01-23 03:38:50.252772: step: 2076/530, loss: 0.0033628465607762337
2023-01-23 03:38:51.373547: step: 2080/530, loss: 0.0009593904251232743
2023-01-23 03:38:52.478414: step: 2084/530, loss: 0.002859401749446988
2023-01-23 03:38:53.590748: step: 2088/530, loss: 0.000500583671964705
2023-01-23 03:38:54.712536: step: 2092/530, loss: 0.011326218023896217
2023-01-23 03:38:55.826117: step: 2096/530, loss: 2.555549144744873e-06
2023-01-23 03:38:56.939073: step: 2100/530, loss: 0.011316013522446156
2023-01-23 03:38:58.057962: step: 2104/530, loss: 0.025014590471982956
2023-01-23 03:38:59.211967: step: 2108/530, loss: 0.008699418045580387
2023-01-23 03:39:00.319538: step: 2112/530, loss: 2.4604798454674892e-05
2023-01-23 03:39:01.435030: step: 2116/530, loss: 0.00029201508732512593
2023-01-23 03:39:02.589237: step: 2120/530, loss: 0.025395872071385384
==================================================
Loss: 0.030
--------------------
Dev: {'event': {'p': 0.5988083416087389, 'r': 0.8029294274300932, 'f1': 0.6860068259385667}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Test: {'event': {'p': 0.6291122127084272, 'r': 0.7977142857142857, 'f1': 0.7034517510707987}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Chinese: {'event': {'p': 0.5555555555555556, 'r': 0.9259259259259259, 'f1': 0.6944444444444444}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
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': 23}
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': 23}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6198257080610022, 'r': 0.7576564580559254, 'f1': 0.6818454164170161}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
Eng Test for Chinese: {'event': {'p': 0.642925430210325, 'r': 0.7685714285714286, 'f1': 0.7001561686621551}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
Sample Chinese: {'event': {'p': 0.6153846153846154, 'r': 0.8888888888888888, 'f1': 0.7272727272727274}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6288770053475936, 'r': 0.7829560585885486, 'f1': 0.697508896797153}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Korean: {'event': {'p': 0.64058795637743, 'r': 0.772, 'f1': 0.7001813941435606}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Korean: {'event': {'p': 0.6851851851851852, 'r': 0.5873015873015873, 'f1': 0.6324786324786325}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5319148936170213, 'r': 0.6944444444444444, 'f1': 0.6024096385542169}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
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 03:39:43.303353: step: 4/530, loss: 7.152557373046875e-06
2023-01-23 03:39:44.410758: step: 8/530, loss: 0.00015726088895462453
2023-01-23 03:39:45.551901: step: 12/530, loss: 0.011050033383071423
2023-01-23 03:39:46.671322: step: 16/530, loss: 0.0021656036842614412
2023-01-23 03:39:47.769487: step: 20/530, loss: 0.004557132720947266
2023-01-23 03:39:48.892874: step: 24/530, loss: 5.092620995128527e-05
2023-01-23 03:39:50.030317: step: 28/530, loss: 0.0166899673640728
2023-01-23 03:39:51.160549: step: 32/530, loss: 0.0006323814741335809
2023-01-23 03:39:52.284982: step: 36/530, loss: 0.0001312255917582661
2023-01-23 03:39:53.394598: step: 40/530, loss: 9.55581635935232e-05
2023-01-23 03:39:54.519842: step: 44/530, loss: 0.0031045437790453434
2023-01-23 03:39:55.646217: step: 48/530, loss: 0.0005063057178631425
2023-01-23 03:39:56.763801: step: 52/530, loss: 0.0007642745622433722
2023-01-23 03:39:57.882536: step: 56/530, loss: 0.0006123543134890497
2023-01-23 03:39:58.994310: step: 60/530, loss: 7.467270188499242e-05
2023-01-23 03:40:00.151827: step: 64/530, loss: 0.015358471311628819
2023-01-23 03:40:01.313240: step: 68/530, loss: 0.0010952949523925781
2023-01-23 03:40:02.458482: step: 72/530, loss: 0.0012739181984215975
2023-01-23 03:40:03.586371: step: 76/530, loss: 0.013843679800629616
2023-01-23 03:40:04.731866: step: 80/530, loss: 2.012253025895916e-05
2023-01-23 03:40:05.855001: step: 84/530, loss: 0.00014396906772162765
2023-01-23 03:40:06.947361: step: 88/530, loss: 0.004881524946540594
2023-01-23 03:40:08.063471: step: 92/530, loss: 0.0005595684051513672
2023-01-23 03:40:09.191583: step: 96/530, loss: 0.018429376184940338
2023-01-23 03:40:10.343887: step: 100/530, loss: 4.920959327137098e-05
2023-01-23 03:40:11.497370: step: 104/530, loss: 0.0004795074637513608
2023-01-23 03:40:12.636581: step: 108/530, loss: 7.514953904319555e-05
2023-01-23 03:40:13.731932: step: 112/530, loss: 3.0994415283203125e-06
2023-01-23 03:40:14.875971: step: 116/530, loss: 0.14638501405715942
2023-01-23 03:40:15.984363: step: 120/530, loss: 0.00093841552734375
2023-01-23 03:40:17.086000: step: 124/530, loss: 3.852844383800402e-05
2023-01-23 03:40:18.231191: step: 128/530, loss: 0.019143294543027878
2023-01-23 03:40:19.388147: step: 132/530, loss: 0.0029429434798657894
2023-01-23 03:40:20.489682: step: 136/530, loss: 0.15927410125732422
2023-01-23 03:40:21.603590: step: 140/530, loss: 0.0022758482955396175
2023-01-23 03:40:22.756501: step: 144/530, loss: 0.004237556830048561
2023-01-23 03:40:23.872444: step: 148/530, loss: 0.025659942999482155
2023-01-23 03:40:24.951703: step: 152/530, loss: 0.00012283325486350805
2023-01-23 03:40:26.061352: step: 156/530, loss: 0.03389463573694229
2023-01-23 03:40:27.171713: step: 160/530, loss: 0.051458172500133514
2023-01-23 03:40:28.323842: step: 164/530, loss: 0.03884730115532875
2023-01-23 03:40:29.421020: step: 168/530, loss: 0.022504042834043503
2023-01-23 03:40:30.534861: step: 172/530, loss: 0.002415561815723777
2023-01-23 03:40:31.657110: step: 176/530, loss: 0.0030837059020996094
2023-01-23 03:40:32.786280: step: 180/530, loss: 0.0007230758783407509
2023-01-23 03:40:33.897656: step: 184/530, loss: 0.0006591796991415322
2023-01-23 03:40:35.043223: step: 188/530, loss: 9.269714064430445e-05
2023-01-23 03:40:36.138849: step: 192/530, loss: 0.0004520416259765625
2023-01-23 03:40:37.265766: step: 196/530, loss: 0.07262267917394638
2023-01-23 03:40:38.380230: step: 200/530, loss: 0.025091933086514473
2023-01-23 03:40:39.504591: step: 204/530, loss: 0.0014873980544507504
2023-01-23 03:40:40.618676: step: 208/530, loss: 5.0878523325081915e-05
2023-01-23 03:40:41.733375: step: 212/530, loss: 1.3351441339182202e-06
2023-01-23 03:40:42.841887: step: 216/530, loss: 1.049041748046875e-05
2023-01-23 03:40:43.947483: step: 220/530, loss: 0.007101630792021751
2023-01-23 03:40:45.069552: step: 224/530, loss: 0.0008539200061932206
2023-01-23 03:40:46.162439: step: 228/530, loss: 6.399154517566785e-05
2023-01-23 03:40:47.268043: step: 232/530, loss: 0.01993255689740181
2023-01-23 03:40:48.401270: step: 236/530, loss: 0.03745536878705025
2023-01-23 03:40:49.536093: step: 240/530, loss: 0.0044799805618822575
2023-01-23 03:40:50.662513: step: 244/530, loss: 0.008800889365375042
2023-01-23 03:40:51.792124: step: 248/530, loss: 0.0002609252987895161
2023-01-23 03:40:52.920103: step: 252/530, loss: 2.3651125957258046e-05
2023-01-23 03:40:54.035200: step: 256/530, loss: 0.029016779735684395
2023-01-23 03:40:55.189424: step: 260/530, loss: 0.004665565211325884
2023-01-23 03:40:56.306837: step: 264/530, loss: 0.01407470740377903
2023-01-23 03:40:57.414451: step: 268/530, loss: 0.003800773760303855
2023-01-23 03:40:58.541568: step: 272/530, loss: 0.0005889892345294356
2023-01-23 03:40:59.650167: step: 276/530, loss: 0.0014353275764733553
2023-01-23 03:41:00.799921: step: 280/530, loss: 0.0002361297665629536
2023-01-23 03:41:01.919437: step: 284/530, loss: 0.028256798163056374
2023-01-23 03:41:03.045513: step: 288/530, loss: 0.005011558532714844
2023-01-23 03:41:04.144099: step: 292/530, loss: 0.0005118370172567666
2023-01-23 03:41:05.238316: step: 296/530, loss: 0.01968669891357422
2023-01-23 03:41:06.365748: step: 300/530, loss: 0.0001858234463725239
2023-01-23 03:41:07.482093: step: 304/530, loss: 3.356933666509576e-05
2023-01-23 03:41:08.613697: step: 308/530, loss: 0.0003142356872558594
2023-01-23 03:41:09.733709: step: 312/530, loss: 0.0001924514799611643
2023-01-23 03:41:10.881322: step: 316/530, loss: 0.03401012346148491
2023-01-23 03:41:11.990583: step: 320/530, loss: 0.015611362643539906
2023-01-23 03:41:13.158836: step: 324/530, loss: 0.00045566557673737407
2023-01-23 03:41:14.280301: step: 328/530, loss: 0.008899688720703125
2023-01-23 03:41:15.403202: step: 332/530, loss: 0.027733994647860527
2023-01-23 03:41:16.555988: step: 336/530, loss: 0.0008192062377929688
2023-01-23 03:41:17.664549: step: 340/530, loss: 0.0007672309875488281
2023-01-23 03:41:18.792464: step: 344/530, loss: 0.0020941735710948706
2023-01-23 03:41:19.926690: step: 348/530, loss: 0.00027942657470703125
2023-01-23 03:41:21.039914: step: 352/530, loss: 0.0003796577511820942
2023-01-23 03:41:22.179240: step: 356/530, loss: 3.9672853745287284e-05
2023-01-23 03:41:23.281373: step: 360/530, loss: 0.015471458435058594
2023-01-23 03:41:24.395242: step: 364/530, loss: 0.0010601043468341231
2023-01-23 03:41:25.530204: step: 368/530, loss: 1.0871887752728071e-05
2023-01-23 03:41:26.651177: step: 372/530, loss: 0.00013203620619606227
2023-01-23 03:41:27.767729: step: 376/530, loss: 0.008501529693603516
2023-01-23 03:41:28.898583: step: 380/530, loss: 0.09849023818969727
2023-01-23 03:41:30.019071: step: 384/530, loss: 0.002324771834537387
2023-01-23 03:41:31.155549: step: 388/530, loss: 0.0010253905784338713
2023-01-23 03:41:32.308621: step: 392/530, loss: 0.0011699676979333162
2023-01-23 03:41:33.432045: step: 396/530, loss: 0.04737091436982155
2023-01-23 03:41:34.556051: step: 400/530, loss: 0.04481881484389305
2023-01-23 03:41:35.690902: step: 404/530, loss: 0.0011053085327148438
2023-01-23 03:41:36.829329: step: 408/530, loss: 0.00013742447481490672
2023-01-23 03:41:37.929327: step: 412/530, loss: 0.004331398289650679
2023-01-23 03:41:39.052077: step: 416/530, loss: 0.0032176971435546875
2023-01-23 03:41:40.186485: step: 420/530, loss: 0.06962300091981888
2023-01-23 03:41:41.315890: step: 424/530, loss: 0.007407474331557751
2023-01-23 03:41:42.471439: step: 428/530, loss: 0.01403112430125475
2023-01-23 03:41:43.618100: step: 432/530, loss: 0.00010128022404387593
2023-01-23 03:41:44.740550: step: 436/530, loss: 0.001130390097387135
2023-01-23 03:41:45.847601: step: 440/530, loss: 0.0390382781624794
2023-01-23 03:41:46.948117: step: 444/530, loss: 0.0003303527773823589
2023-01-23 03:41:48.080565: step: 448/530, loss: 0.0044831279665231705
2023-01-23 03:41:49.195541: step: 452/530, loss: 0.04946641996502876
2023-01-23 03:41:50.325657: step: 456/530, loss: 0.0009009361965581775
2023-01-23 03:41:51.469188: step: 460/530, loss: 0.0012356758816167712
2023-01-23 03:41:52.590125: step: 464/530, loss: 1.3351440202313825e-06
2023-01-23 03:41:53.725246: step: 468/530, loss: 3.9991726875305176
2023-01-23 03:41:54.843188: step: 472/530, loss: 0.00012855530076194555
2023-01-23 03:41:55.944316: step: 476/530, loss: 0.0003608703555073589
2023-01-23 03:41:57.073802: step: 480/530, loss: 0.004592323210090399
2023-01-23 03:41:58.168669: step: 484/530, loss: 0.002927398541942239
2023-01-23 03:41:59.347869: step: 488/530, loss: 0.0010039329063147306
2023-01-23 03:42:00.455945: step: 492/530, loss: 0.00904550589621067
2023-01-23 03:42:01.582837: step: 496/530, loss: 0.03919067233800888
2023-01-23 03:42:02.697106: step: 500/530, loss: 9.212493750965223e-05
2023-01-23 03:42:03.832158: step: 504/530, loss: 0.006631660740822554
2023-01-23 03:42:04.969538: step: 508/530, loss: 0.0016904830699786544
2023-01-23 03:42:06.110285: step: 512/530, loss: 0.00022029876708984375
2023-01-23 03:42:07.224557: step: 516/530, loss: 0.00036764147807843983
2023-01-23 03:42:08.373349: step: 520/530, loss: 0.0003713608020916581
2023-01-23 03:42:09.507826: step: 524/530, loss: 0.026316454634070396
2023-01-23 03:42:10.610513: step: 528/530, loss: 0.0030215263832360506
2023-01-23 03:42:11.708095: step: 532/530, loss: 1.0204315913142636e-05
2023-01-23 03:42:12.818397: step: 536/530, loss: 0.000194549560546875
2023-01-23 03:42:13.926958: step: 540/530, loss: 0.00462842034175992
2023-01-23 03:42:15.023736: step: 544/530, loss: 0.08375683426856995
2023-01-23 03:42:16.144052: step: 548/530, loss: 4.0531158447265625e-05
2023-01-23 03:42:17.296168: step: 552/530, loss: 0.03683844953775406
2023-01-23 03:42:18.418392: step: 556/530, loss: 0.0009405136224813759
2023-01-23 03:42:19.524028: step: 560/530, loss: 0.013876914978027344
2023-01-23 03:42:20.664202: step: 564/530, loss: 0.011519242078065872
2023-01-23 03:42:21.811835: step: 568/530, loss: 0.003719902131706476
2023-01-23 03:42:22.936460: step: 572/530, loss: 0.0003807067987509072
2023-01-23 03:42:24.078650: step: 576/530, loss: 0.0076913838274776936
2023-01-23 03:42:25.199958: step: 580/530, loss: 0.008653640747070312
2023-01-23 03:42:26.332093: step: 584/530, loss: 4.405975414556451e-05
2023-01-23 03:42:27.437897: step: 588/530, loss: 0.007244396023452282
2023-01-23 03:42:28.564099: step: 592/530, loss: 0.00017280579777434468
2023-01-23 03:42:29.716142: step: 596/530, loss: 0.010655499063432217
2023-01-23 03:42:30.846478: step: 600/530, loss: 0.0015697956550866365
2023-01-23 03:42:31.966264: step: 604/530, loss: 0.0016318322159349918
2023-01-23 03:42:33.121442: step: 608/530, loss: 0.0008715629810467362
2023-01-23 03:42:34.270639: step: 612/530, loss: 0.06163635104894638
2023-01-23 03:42:35.413171: step: 616/530, loss: 0.01646709442138672
2023-01-23 03:42:36.539382: step: 620/530, loss: 1.71661376953125e-05
2023-01-23 03:42:37.648642: step: 624/530, loss: 7.43865984986769e-06
2023-01-23 03:42:38.772215: step: 628/530, loss: 0.02240753173828125
2023-01-23 03:42:39.893163: step: 632/530, loss: 0.005022811703383923
2023-01-23 03:42:40.998436: step: 636/530, loss: 0.0019479751354083419
2023-01-23 03:42:42.123025: step: 640/530, loss: 0.0008593559614382684
2023-01-23 03:42:43.238660: step: 644/530, loss: 0.026267623528838158
2023-01-23 03:42:44.339756: step: 648/530, loss: 0.0009403228759765625
2023-01-23 03:42:45.440504: step: 652/530, loss: 0.018576670438051224
2023-01-23 03:42:46.571601: step: 656/530, loss: 0.02012653462588787
2023-01-23 03:42:47.704112: step: 660/530, loss: 0.007377624977380037
2023-01-23 03:42:48.814946: step: 664/530, loss: 0.00955963134765625
2023-01-23 03:42:49.947737: step: 668/530, loss: 0.0042743682861328125
2023-01-23 03:42:51.071964: step: 672/530, loss: 0.0004724502796307206
2023-01-23 03:42:52.180850: step: 676/530, loss: 0.0006839752313680947
2023-01-23 03:42:53.302550: step: 680/530, loss: 0.19893132150173187
2023-01-23 03:42:54.442348: step: 684/530, loss: 0.041143324226140976
2023-01-23 03:42:55.590825: step: 688/530, loss: 0.0006212234729900956
2023-01-23 03:42:56.714849: step: 692/530, loss: 0.010551405139267445
2023-01-23 03:42:57.836403: step: 696/530, loss: 3.833770824712701e-05
2023-01-23 03:42:58.955221: step: 700/530, loss: 0.00034747127210721374
2023-01-23 03:43:00.057514: step: 704/530, loss: 0.029045678675174713
2023-01-23 03:43:01.197396: step: 708/530, loss: 3.986358569818549e-05
2023-01-23 03:43:02.310568: step: 712/530, loss: 6.380081322276965e-05
2023-01-23 03:43:03.431199: step: 716/530, loss: 0.021427344530820847
2023-01-23 03:43:04.567666: step: 720/530, loss: 7.82012921263231e-06
2023-01-23 03:43:05.725436: step: 724/530, loss: 0.001431369804777205
2023-01-23 03:43:06.855323: step: 728/530, loss: 0.01021423377096653
2023-01-23 03:43:08.000079: step: 732/530, loss: 0.0003966331423725933
2023-01-23 03:43:09.126479: step: 736/530, loss: 0.0002779007190838456
2023-01-23 03:43:10.262088: step: 740/530, loss: 0.00010709762864280492
2023-01-23 03:43:11.383729: step: 744/530, loss: 0.005646133329719305
2023-01-23 03:43:12.525293: step: 748/530, loss: 0.03898201137781143
2023-01-23 03:43:13.642284: step: 752/530, loss: 0.0031970501877367496
2023-01-23 03:43:14.753527: step: 756/530, loss: 1.33514404296875e-05
2023-01-23 03:43:15.898626: step: 760/530, loss: 0.00042138100252486765
2023-01-23 03:43:17.013388: step: 764/530, loss: 8.0108642578125e-05
2023-01-23 03:43:18.143880: step: 768/530, loss: 1.277923547604587e-05
2023-01-23 03:43:19.271979: step: 772/530, loss: 0.0003429412900004536
2023-01-23 03:43:20.382964: step: 776/530, loss: 0.00037469866219908
2023-01-23 03:43:21.501108: step: 780/530, loss: 0.18206195533275604
2023-01-23 03:43:22.666167: step: 784/530, loss: 0.00570945767685771
2023-01-23 03:43:23.832070: step: 788/530, loss: 0.041329190135002136
2023-01-23 03:43:24.933797: step: 792/530, loss: 0.00223884591832757
2023-01-23 03:43:26.060225: step: 796/530, loss: 0.00364856724627316
2023-01-23 03:43:27.176295: step: 800/530, loss: 0.00012598038301803172
2023-01-23 03:43:28.291562: step: 804/530, loss: 0.00011348725092830136
2023-01-23 03:43:29.431833: step: 808/530, loss: 0.049199704080820084
2023-01-23 03:43:30.552661: step: 812/530, loss: 0.0013780593872070312
2023-01-23 03:43:31.683467: step: 816/530, loss: 0.042411185801029205
2023-01-23 03:43:32.844151: step: 820/530, loss: 0.00016288757615257055
2023-01-23 03:43:33.993489: step: 824/530, loss: 0.0019218922825530171
2023-01-23 03:43:35.092043: step: 828/530, loss: 2.250671423098538e-05
2023-01-23 03:43:36.212197: step: 832/530, loss: 0.012330221943557262
2023-01-23 03:43:37.337893: step: 836/530, loss: -8.296966370835435e-06
2023-01-23 03:43:38.440521: step: 840/530, loss: 0.012867164798080921
2023-01-23 03:43:39.541889: step: 844/530, loss: 0.004399108700454235
2023-01-23 03:43:40.672992: step: 848/530, loss: 0.0006018638960085809
2023-01-23 03:43:41.806656: step: 852/530, loss: 0.0002388954017078504
2023-01-23 03:43:42.938126: step: 856/530, loss: 0.0008094788063317537
2023-01-23 03:43:44.112183: step: 860/530, loss: 0.0022572875022888184
2023-01-23 03:43:45.259720: step: 864/530, loss: 0.00013055800809524953
2023-01-23 03:43:46.398204: step: 868/530, loss: 2.4318698706338182e-05
2023-01-23 03:43:47.530138: step: 872/530, loss: 0.005517005920410156
2023-01-23 03:43:48.616012: step: 876/530, loss: 0.00440063513815403
2023-01-23 03:43:49.740025: step: 880/530, loss: 0.00011453629122115672
2023-01-23 03:43:50.842857: step: 884/530, loss: 0.006240462884306908
2023-01-23 03:43:51.962249: step: 888/530, loss: 0.018604470416903496
2023-01-23 03:43:53.100253: step: 892/530, loss: 0.0014380932552739978
2023-01-23 03:43:54.218616: step: 896/530, loss: 0.11781015247106552
2023-01-23 03:43:55.356205: step: 900/530, loss: 6.83784528519027e-05
2023-01-23 03:43:56.476371: step: 904/530, loss: 0.018236063420772552
2023-01-23 03:43:57.584876: step: 908/530, loss: 0.0380365364253521
2023-01-23 03:43:58.697637: step: 912/530, loss: 0.00021753311739303172
2023-01-23 03:43:59.845687: step: 916/530, loss: 8.39233416627394e-06
2023-01-23 03:44:00.972218: step: 920/530, loss: 0.00018014907254837453
2023-01-23 03:44:02.105302: step: 924/530, loss: 8.630752745375503e-06
2023-01-23 03:44:03.241042: step: 928/530, loss: 0.0005167961353436112
2023-01-23 03:44:04.350711: step: 932/530, loss: 0.02090618759393692
2023-01-23 03:44:05.514788: step: 936/530, loss: 0.0028133392333984375
2023-01-23 03:44:06.660766: step: 940/530, loss: 0.004408359527587891
2023-01-23 03:44:07.774206: step: 944/530, loss: -3.910064606316155e-06
2023-01-23 03:44:08.884248: step: 948/530, loss: 0.0024011610075831413
2023-01-23 03:44:10.044654: step: 952/530, loss: 0.020877553150057793
2023-01-23 03:44:11.184582: step: 956/530, loss: 0.01916971243917942
2023-01-23 03:44:12.334295: step: 960/530, loss: 0.026388168334960938
2023-01-23 03:44:13.453899: step: 964/530, loss: 6.418228440452367e-05
2023-01-23 03:44:14.571534: step: 968/530, loss: 3.681182715808973e-05
2023-01-23 03:44:15.710449: step: 972/530, loss: 0.00012826919555664062
2023-01-23 03:44:16.834860: step: 976/530, loss: 0.0026149749755859375
2023-01-23 03:44:18.016987: step: 980/530, loss: 0.08449984341859818
2023-01-23 03:44:19.130954: step: 984/530, loss: 1.316070574830519e-05
2023-01-23 03:44:20.263499: step: 988/530, loss: 4.7063826059456915e-05
2023-01-23 03:44:21.400304: step: 992/530, loss: 0.008516693487763405
2023-01-23 03:44:22.508391: step: 996/530, loss: 0.1637924313545227
2023-01-23 03:44:23.636959: step: 1000/530, loss: 0.005981111433357
2023-01-23 03:44:24.785332: step: 1004/530, loss: 0.019586944952607155
2023-01-23 03:44:25.922257: step: 1008/530, loss: 0.005295563023537397
2023-01-23 03:44:27.057978: step: 1012/530, loss: 5.53131121705519e-06
2023-01-23 03:44:28.177142: step: 1016/530, loss: 2.9182432626839727e-05
2023-01-23 03:44:29.308566: step: 1020/530, loss: 0.002621269319206476
2023-01-23 03:44:30.439291: step: 1024/530, loss: 0.017374420538544655
2023-01-23 03:44:31.549389: step: 1028/530, loss: 1.754760705807712e-05
2023-01-23 03:44:32.690630: step: 1032/530, loss: 0.015008448623120785
2023-01-23 03:44:33.807723: step: 1036/530, loss: 0.07672309875488281
2023-01-23 03:44:34.946787: step: 1040/530, loss: 5.226135181146674e-05
2023-01-23 03:44:36.073862: step: 1044/530, loss: 0.01604476012289524
2023-01-23 03:44:37.223648: step: 1048/530, loss: 0.000881195068359375
2023-01-23 03:44:38.393267: step: 1052/530, loss: 0.02239532396197319
2023-01-23 03:44:39.496516: step: 1056/530, loss: 1.735687328618951e-05
2023-01-23 03:44:40.628668: step: 1060/530, loss: 0.004456138703972101
2023-01-23 03:44:41.736637: step: 1064/530, loss: 0.017177581787109375
2023-01-23 03:44:42.849168: step: 1068/530, loss: 0.02587909810245037
2023-01-23 03:44:43.961971: step: 1072/530, loss: 0.016202544793486595
2023-01-23 03:44:45.095149: step: 1076/530, loss: 0.0004410744004417211
2023-01-23 03:44:46.231797: step: 1080/530, loss: 0.0005770683055743575
2023-01-23 03:44:47.338611: step: 1084/530, loss: 0.0012900352012366056
2023-01-23 03:44:48.444525: step: 1088/530, loss: 0.03190803900361061
2023-01-23 03:44:49.583244: step: 1092/530, loss: 0.3949032723903656
2023-01-23 03:44:50.720569: step: 1096/530, loss: 8.96453857421875e-05
2023-01-23 03:44:51.851538: step: 1100/530, loss: 0.00016717909602448344
2023-01-23 03:44:53.014079: step: 1104/530, loss: 0.02153797075152397
2023-01-23 03:44:54.121524: step: 1108/530, loss: 0.0014883042313158512
2023-01-23 03:44:55.261242: step: 1112/530, loss: 0.16788645088672638
2023-01-23 03:44:56.399862: step: 1116/530, loss: 0.034400273114442825
2023-01-23 03:44:57.517389: step: 1120/530, loss: 0.016187667846679688
2023-01-23 03:44:58.642892: step: 1124/530, loss: 4.215240551275201e-05
2023-01-23 03:44:59.786322: step: 1128/530, loss: 0.0006538391462527215
2023-01-23 03:45:00.929538: step: 1132/530, loss: 0.035448551177978516
2023-01-23 03:45:02.034134: step: 1136/530, loss: 3.910064606316155e-06
2023-01-23 03:45:03.158061: step: 1140/530, loss: 4.00543194700731e-06
2023-01-23 03:45:04.287284: step: 1144/530, loss: 0.002973461290821433
2023-01-23 03:45:05.412591: step: 1148/530, loss: 0.0033791542518883944
2023-01-23 03:45:06.555330: step: 1152/530, loss: 0.0006357193342410028
2023-01-23 03:45:07.666199: step: 1156/530, loss: 0.00778121966868639
2023-01-23 03:45:08.787534: step: 1160/530, loss: 0.0856841579079628
2023-01-23 03:45:09.934078: step: 1164/530, loss: 4.472732689464465e-05
2023-01-23 03:45:11.061334: step: 1168/530, loss: 0.0012611389392986894
2023-01-23 03:45:12.189431: step: 1172/530, loss: 0.0007200241088867188
2023-01-23 03:45:13.298609: step: 1176/530, loss: 2.7656556994770654e-05
2023-01-23 03:45:14.444766: step: 1180/530, loss: 0.0015327453147619963
2023-01-23 03:45:15.615096: step: 1184/530, loss: 0.0008971214410848916
2023-01-23 03:45:16.750637: step: 1188/530, loss: 0.037331581115722656
2023-01-23 03:45:17.880321: step: 1192/530, loss: 5.9890749980695546e-05
2023-01-23 03:45:19.070513: step: 1196/530, loss: 0.007906246930360794
2023-01-23 03:45:20.190909: step: 1200/530, loss: 0.017188740894198418
2023-01-23 03:45:21.295290: step: 1204/530, loss: 0.02514934539794922
2023-01-23 03:45:22.445389: step: 1208/530, loss: 0.018845845013856888
2023-01-23 03:45:23.564299: step: 1212/530, loss: 0.0024932860396802425
2023-01-23 03:45:24.706441: step: 1216/530, loss: 0.05547017976641655
2023-01-23 03:45:25.852226: step: 1220/530, loss: 0.008429241366684437
2023-01-23 03:45:27.006579: step: 1224/530, loss: 0.003713417099788785
2023-01-23 03:45:28.147199: step: 1228/530, loss: 0.021436691284179688
2023-01-23 03:45:29.261387: step: 1232/530, loss: 0.0007604599231854081
2023-01-23 03:45:30.379705: step: 1236/530, loss: 7.82012939453125e-05
2023-01-23 03:45:31.506508: step: 1240/530, loss: 0.0011594772804528475
2023-01-23 03:45:32.649109: step: 1244/530, loss: 8.401871309615672e-05
2023-01-23 03:45:33.787054: step: 1248/530, loss: 6.771087555534905e-06
2023-01-23 03:45:34.892843: step: 1252/530, loss: 0.0007290840148925781
2023-01-23 03:45:36.029700: step: 1256/530, loss: 0.0013675689697265625
2023-01-23 03:45:37.175020: step: 1260/530, loss: 0.013032913208007812
2023-01-23 03:45:38.280241: step: 1264/530, loss: 1.52587890625e-05
2023-01-23 03:45:39.427464: step: 1268/530, loss: 0.032070159912109375
2023-01-23 03:45:40.553359: step: 1272/530, loss: 6.637573824264109e-05
2023-01-23 03:45:41.656820: step: 1276/530, loss: 0.0009118079906329513
2023-01-23 03:45:42.739739: step: 1280/530, loss: 0.023752881214022636
2023-01-23 03:45:43.868010: step: 1284/530, loss: 0.010328864678740501
2023-01-23 03:45:44.975995: step: 1288/530, loss: 0.0006488800281658769
2023-01-23 03:45:46.081048: step: 1292/530, loss: 0.7392614483833313
2023-01-23 03:45:47.193345: step: 1296/530, loss: 0.013381386175751686
2023-01-23 03:45:48.341759: step: 1300/530, loss: 0.014977074228227139
2023-01-23 03:45:49.461360: step: 1304/530, loss: 0.06726054847240448
2023-01-23 03:45:50.594947: step: 1308/530, loss: 0.001568269683048129
2023-01-23 03:45:51.776803: step: 1312/530, loss: 0.0031616210471838713
2023-01-23 03:45:52.895674: step: 1316/530, loss: 0.0012739181984215975
2023-01-23 03:45:54.012622: step: 1320/530, loss: 0.30644530057907104
2023-01-23 03:45:55.145994: step: 1324/530, loss: 0.011318778619170189
2023-01-23 03:45:56.269068: step: 1328/530, loss: 0.004583549685776234
2023-01-23 03:45:57.402348: step: 1332/530, loss: 0.07709579914808273
2023-01-23 03:45:58.545821: step: 1336/530, loss: 1.049041748046875e-05
2023-01-23 03:45:59.685154: step: 1340/530, loss: 0.0005133628728799522
2023-01-23 03:46:00.842743: step: 1344/530, loss: 0.055951498448848724
2023-01-23 03:46:01.968514: step: 1348/530, loss: 0.002674675080925226
2023-01-23 03:46:03.127250: step: 1352/530, loss: 0.005853176116943359
2023-01-23 03:46:04.252725: step: 1356/530, loss: 8.678436279296875e-05
2023-01-23 03:46:05.372708: step: 1360/530, loss: 0.00017986298189498484
2023-01-23 03:46:06.537226: step: 1364/530, loss: 0.06288294494152069
2023-01-23 03:46:07.664488: step: 1368/530, loss: 0.00013256072998046875
2023-01-23 03:46:08.794092: step: 1372/530, loss: 0.007794380187988281
2023-01-23 03:46:09.905706: step: 1376/530, loss: 9.536744983051904e-06
2023-01-23 03:46:11.021368: step: 1380/530, loss: 0.0009719848749227822
2023-01-23 03:46:12.113362: step: 1384/530, loss: 4.091262962901965e-05
2023-01-23 03:46:13.214320: step: 1388/530, loss: 0.0002930641348939389
2023-01-23 03:46:14.361073: step: 1392/530, loss: 0.00034999847412109375
2023-01-23 03:46:15.490079: step: 1396/530, loss: 0.0010705947643145919
2023-01-23 03:46:16.633897: step: 1400/530, loss: 7.43865984986769e-06
2023-01-23 03:46:17.753512: step: 1404/530, loss: 0.08713741600513458
2023-01-23 03:46:18.856619: step: 1408/530, loss: 0.0010047912364825606
2023-01-23 03:46:19.996205: step: 1412/530, loss: 0.0003778458049055189
2023-01-23 03:46:21.094944: step: 1416/530, loss: 0.00030231475830078125
2023-01-23 03:46:22.230546: step: 1420/530, loss: 0.008088684640824795
2023-01-23 03:46:23.375040: step: 1424/530, loss: 0.0066849710419774055
2023-01-23 03:46:24.509291: step: 1428/530, loss: 0.06372775882482529
2023-01-23 03:46:25.615944: step: 1432/530, loss: 5.683898780262098e-05
2023-01-23 03:46:26.753638: step: 1436/530, loss: 0.01704712025821209
2023-01-23 03:46:27.895666: step: 1440/530, loss: 3.385544005141128e-06
2023-01-23 03:46:29.041458: step: 1444/530, loss: 1.0776519957289565e-05
2023-01-23 03:46:30.179097: step: 1448/530, loss: 0.02682037279009819
2023-01-23 03:46:31.284082: step: 1452/530, loss: 0.013961411081254482
2023-01-23 03:46:32.419569: step: 1456/530, loss: 0.013233805075287819
2023-01-23 03:46:33.513554: step: 1460/530, loss: 0.00814275722950697
2023-01-23 03:46:34.645613: step: 1464/530, loss: 0.03822669759392738
2023-01-23 03:46:35.752306: step: 1468/530, loss: 0.00199127197265625
2023-01-23 03:46:36.879992: step: 1472/530, loss: 0.0005277633899822831
2023-01-23 03:46:38.018717: step: 1476/530, loss: 0.0026166916359215975
2023-01-23 03:46:39.138854: step: 1480/530, loss: 0.003086614655330777
2023-01-23 03:46:40.291001: step: 1484/530, loss: 5.5122378398664296e-05
2023-01-23 03:46:41.398355: step: 1488/530, loss: 0.005574607755988836
2023-01-23 03:46:42.515015: step: 1492/530, loss: 9.913444955600426e-05
2023-01-23 03:46:43.645764: step: 1496/530, loss: 0.00253887171857059
2023-01-23 03:46:44.759887: step: 1500/530, loss: 0.05445671081542969
2023-01-23 03:46:45.861316: step: 1504/530, loss: 0.0018342018593102694
2023-01-23 03:46:46.997003: step: 1508/530, loss: 0.0010273456573486328
2023-01-23 03:46:48.115727: step: 1512/530, loss: 0.0006852149963378906
2023-01-23 03:46:49.221705: step: 1516/530, loss: 0.0005591392982751131
2023-01-23 03:46:50.366757: step: 1520/530, loss: 0.0022735595703125
2023-01-23 03:46:51.535181: step: 1524/530, loss: 0.11696648597717285
2023-01-23 03:46:52.664453: step: 1528/530, loss: 0.0007255554082803428
2023-01-23 03:46:53.772045: step: 1532/530, loss: 6.761551048839465e-05
2023-01-23 03:46:54.875149: step: 1536/530, loss: 0.0010030746925622225
2023-01-23 03:46:55.994282: step: 1540/530, loss: 0.0005038738599978387
2023-01-23 03:46:57.130370: step: 1544/530, loss: 0.008318042382597923
2023-01-23 03:46:58.271937: step: 1548/530, loss: 0.006482839584350586
2023-01-23 03:46:59.436558: step: 1552/530, loss: 0.014519883319735527
2023-01-23 03:47:00.571763: step: 1556/530, loss: 0.006329250056296587
2023-01-23 03:47:01.695538: step: 1560/530, loss: 0.07595839351415634
2023-01-23 03:47:02.841049: step: 1564/530, loss: 0.003700447268784046
2023-01-23 03:47:04.024564: step: 1568/530, loss: 1.735687328618951e-05
2023-01-23 03:47:05.170005: step: 1572/530, loss: 0.003451442811638117
2023-01-23 03:47:06.290768: step: 1576/530, loss: 0.00025281906710006297
2023-01-23 03:47:07.416296: step: 1580/530, loss: 0.00036411284236237407
2023-01-23 03:47:08.528262: step: 1584/530, loss: 0.00417705811560154
2023-01-23 03:47:09.659993: step: 1588/530, loss: 0.0002956390380859375
2023-01-23 03:47:10.767277: step: 1592/530, loss: 0.0021317005157470703
2023-01-23 03:47:11.874209: step: 1596/530, loss: 0.002164697740226984
2023-01-23 03:47:13.016413: step: 1600/530, loss: 0.0001234054652741179
2023-01-23 03:47:14.128866: step: 1604/530, loss: 0.0010136604541912675
2023-01-23 03:47:15.262980: step: 1608/530, loss: 0.008666420355439186
2023-01-23 03:47:16.399615: step: 1612/530, loss: 0.007724285125732422
2023-01-23 03:47:17.493859: step: 1616/530, loss: 0.006575965788215399
2023-01-23 03:47:18.607257: step: 1620/530, loss: 0.009416580200195312
2023-01-23 03:47:19.751998: step: 1624/530, loss: 0.010112762451171875
2023-01-23 03:47:20.887325: step: 1628/530, loss: 0.00578198442235589
2023-01-23 03:47:22.023127: step: 1632/530, loss: 0.0006286621210165322
2023-01-23 03:47:23.147186: step: 1636/530, loss: 0.0003871917724609375
2023-01-23 03:47:24.276818: step: 1640/530, loss: 0.002748107770457864
2023-01-23 03:47:25.397437: step: 1644/530, loss: 0.0026155472733080387
2023-01-23 03:47:26.551989: step: 1648/530, loss: 0.014090919867157936
2023-01-23 03:47:27.680598: step: 1652/530, loss: 0.00803146418184042
2023-01-23 03:47:28.833442: step: 1656/530, loss: 0.013839340768754482
2023-01-23 03:47:29.945034: step: 1660/530, loss: 0.007971763610839844
2023-01-23 03:47:31.067150: step: 1664/530, loss: 2.765655608527595e-06
2023-01-23 03:47:32.177368: step: 1668/530, loss: 0.0007596015930175781
2023-01-23 03:47:33.290636: step: 1672/530, loss: 0.0515836700797081
2023-01-23 03:47:34.427468: step: 1676/530, loss: 0.07104549556970596
2023-01-23 03:47:35.520762: step: 1680/530, loss: 8.363723463844508e-05
2023-01-23 03:47:36.642803: step: 1684/530, loss: 0.00046176911564543843
2023-01-23 03:47:37.781950: step: 1688/530, loss: 0.0006183624500408769
2023-01-23 03:47:38.948066: step: 1692/530, loss: 6.27517729299143e-05
2023-01-23 03:47:40.060893: step: 1696/530, loss: 0.008471870794892311
2023-01-23 03:47:41.182816: step: 1700/530, loss: 0.003345584962517023
2023-01-23 03:47:42.288141: step: 1704/530, loss: 5.543231964111328e-05
2023-01-23 03:47:43.427684: step: 1708/530, loss: 0.020847130566835403
2023-01-23 03:47:44.532442: step: 1712/530, loss: 0.005173683166503906
2023-01-23 03:47:45.630033: step: 1716/530, loss: 3.814697265625e-06
2023-01-23 03:47:46.778093: step: 1720/530, loss: 0.00046443939208984375
2023-01-23 03:47:47.896495: step: 1724/530, loss: 0.00019030571274925023
2023-01-23 03:47:48.999969: step: 1728/530, loss: 0.006464672274887562
2023-01-23 03:47:50.111300: step: 1732/530, loss: 0.023212766274809837
2023-01-23 03:47:51.251579: step: 1736/530, loss: 8.163452002918348e-05
2023-01-23 03:47:52.395064: step: 1740/530, loss: 0.000545501708984375
2023-01-23 03:47:53.526340: step: 1744/530, loss: 0.004963874816894531
2023-01-23 03:47:54.632935: step: 1748/530, loss: 0.030713463202118874
2023-01-23 03:47:55.753242: step: 1752/530, loss: 0.005924797151237726
2023-01-23 03:47:56.865786: step: 1756/530, loss: 0.019602395594120026
2023-01-23 03:47:58.002550: step: 1760/530, loss: 0.0004323005850892514
2023-01-23 03:47:59.139971: step: 1764/530, loss: 0.05884575843811035
2023-01-23 03:48:00.295843: step: 1768/530, loss: 0.0010650635231286287
2023-01-23 03:48:01.412993: step: 1772/530, loss: 0.01959228515625
2023-01-23 03:48:02.582029: step: 1776/530, loss: 0.00044307709322310984
2023-01-23 03:48:03.692556: step: 1780/530, loss: 0.012017727829515934
2023-01-23 03:48:04.840375: step: 1784/530, loss: 0.034757040441036224
2023-01-23 03:48:05.972028: step: 1788/530, loss: 0.06316499412059784
2023-01-23 03:48:07.108041: step: 1792/530, loss: 0.025241469964385033
2023-01-23 03:48:08.200220: step: 1796/530, loss: 5.970001075183973e-05
2023-01-23 03:48:09.345215: step: 1800/530, loss: 0.003490924835205078
2023-01-23 03:48:10.508771: step: 1804/530, loss: 0.02016611211001873
2023-01-23 03:48:11.639856: step: 1808/530, loss: 0.00818862859159708
2023-01-23 03:48:12.741555: step: 1812/530, loss: 0.0024250030983239412
2023-01-23 03:48:13.869617: step: 1816/530, loss: 0.019534826278686523
2023-01-23 03:48:14.981311: step: 1820/530, loss: 0.008831215091049671
2023-01-23 03:48:16.090119: step: 1824/530, loss: 3.4809112548828125e-05
2023-01-23 03:48:17.210940: step: 1828/530, loss: 0.012275982648134232
2023-01-23 03:48:18.332356: step: 1832/530, loss: 0.0011055945651605725
2023-01-23 03:48:19.479674: step: 1836/530, loss: 1.258850079466356e-05
2023-01-23 03:48:20.579541: step: 1840/530, loss: 0.013837814331054688
2023-01-23 03:48:21.689004: step: 1844/530, loss: 0.004779530223459005
2023-01-23 03:48:22.813247: step: 1848/530, loss: -4.386901309771929e-06
2023-01-23 03:48:23.921849: step: 1852/530, loss: 0.0004432678106240928
2023-01-23 03:48:25.039696: step: 1856/530, loss: 0.0038407803513109684
2023-01-23 03:48:26.164069: step: 1860/530, loss: 0.00043444635230116546
2023-01-23 03:48:27.282152: step: 1864/530, loss: 0.0013799667358398438
2023-01-23 03:48:28.430579: step: 1868/530, loss: 0.0006229400751180947
2023-01-23 03:48:29.570079: step: 1872/530, loss: 0.010889053344726562
2023-01-23 03:48:30.685693: step: 1876/530, loss: 0.0004259109846316278
2023-01-23 03:48:31.808752: step: 1880/530, loss: 1.5258790881489404e-05
2023-01-23 03:48:32.935881: step: 1884/530, loss: 0.0014681816101074219
2023-01-23 03:48:34.056667: step: 1888/530, loss: 0.00062732701189816
2023-01-23 03:48:35.177298: step: 1892/530, loss: 0.0005293846479617059
2023-01-23 03:48:36.301119: step: 1896/530, loss: 0.0007566451677121222
2023-01-23 03:48:37.412028: step: 1900/530, loss: 0.0004562377871479839
2023-01-23 03:48:38.553398: step: 1904/530, loss: 0.00024633409339003265
2023-01-23 03:48:39.667130: step: 1908/530, loss: 4.6443939936580136e-05
2023-01-23 03:48:40.824474: step: 1912/530, loss: -3.2424923119833693e-06
2023-01-23 03:48:41.947968: step: 1916/530, loss: 0.03647003322839737
2023-01-23 03:48:43.059880: step: 1920/530, loss: 3.471374657237902e-05
2023-01-23 03:48:44.174062: step: 1924/530, loss: 0.00035514833871275187
2023-01-23 03:48:45.286176: step: 1928/530, loss: 8.583069188716763e-07
2023-01-23 03:48:46.412439: step: 1932/530, loss: 2.527237120375503e-05
2023-01-23 03:48:47.550358: step: 1936/530, loss: 0.001122462679632008
2023-01-23 03:48:48.646833: step: 1940/530, loss: 0.00011582375009311363
2023-01-23 03:48:49.766005: step: 1944/530, loss: 0.0007120132795535028
2023-01-23 03:48:50.892809: step: 1948/530, loss: 0.0009958266746252775
2023-01-23 03:48:52.011194: step: 1952/530, loss: 0.00016202926053665578
2023-01-23 03:48:53.143500: step: 1956/530, loss: 2.47955322265625e-05
2023-01-23 03:48:54.257252: step: 1960/530, loss: 0.00019187926955055445
2023-01-23 03:48:55.375764: step: 1964/530, loss: 0.00022373200044967234
2023-01-23 03:48:56.522515: step: 1968/530, loss: 0.00015335084754042327
2023-01-23 03:48:57.642111: step: 1972/530, loss: 8.921623521018773e-05
2023-01-23 03:48:58.762747: step: 1976/530, loss: 0.022678280249238014
2023-01-23 03:48:59.893367: step: 1980/530, loss: 4.85897071484942e-05
2023-01-23 03:49:01.029241: step: 1984/530, loss: 0.00862274132668972
2023-01-23 03:49:02.150140: step: 1988/530, loss: 0.006485462188720703
2023-01-23 03:49:03.293862: step: 1992/530, loss: 0.00014333725266624242
2023-01-23 03:49:04.434597: step: 1996/530, loss: 8.850097947288305e-05
2023-01-23 03:49:05.519079: step: 2000/530, loss: 3.051757857974735e-06
2023-01-23 03:49:06.646441: step: 2004/530, loss: 0.00011463165719760582
2023-01-23 03:49:07.769565: step: 2008/530, loss: 3.528594970703125e-05
2023-01-23 03:49:08.887690: step: 2012/530, loss: 0.0014966964954510331
2023-01-23 03:49:10.041366: step: 2016/530, loss: 0.0903010368347168
2023-01-23 03:49:11.164192: step: 2020/530, loss: 4.4155120122013614e-05
2023-01-23 03:49:12.275701: step: 2024/530, loss: 1.850128137448337e-05
2023-01-23 03:49:13.419371: step: 2028/530, loss: 0.011052322573959827
2023-01-23 03:49:14.523547: step: 2032/530, loss: 0.026906967163085938
2023-01-23 03:49:15.644384: step: 2036/530, loss: 0.0009341239929199219
2023-01-23 03:49:16.757490: step: 2040/530, loss: 0.0003383636358194053
2023-01-23 03:49:17.876740: step: 2044/530, loss: 0.143123060464859
2023-01-23 03:49:19.018910: step: 2048/530, loss: 0.0005216598510742188
2023-01-23 03:49:20.119192: step: 2052/530, loss: 0.0008076668018475175
2023-01-23 03:49:21.223017: step: 2056/530, loss: 0.000354766845703125
2023-01-23 03:49:22.328328: step: 2060/530, loss: 0.016980456188321114
2023-01-23 03:49:23.468199: step: 2064/530, loss: 0.022052954882383347
2023-01-23 03:49:24.603851: step: 2068/530, loss: 0.00031948089599609375
2023-01-23 03:49:25.742775: step: 2072/530, loss: 9.632110595703125e-05
2023-01-23 03:49:26.866302: step: 2076/530, loss: 0.0010297775734215975
2023-01-23 03:49:27.988008: step: 2080/530, loss: 0.0024024962913244963
2023-01-23 03:49:29.128365: step: 2084/530, loss: 0.0001483917294535786
2023-01-23 03:49:30.274468: step: 2088/530, loss: 0.006118011195212603
2023-01-23 03:49:31.446943: step: 2092/530, loss: 0.07015743106603622
2023-01-23 03:49:32.601096: step: 2096/530, loss: 0.0002815246698446572
2023-01-23 03:49:33.711338: step: 2100/530, loss: 0.00015611648268532008
2023-01-23 03:49:34.860216: step: 2104/530, loss: 0.017203141003847122
2023-01-23 03:49:36.005921: step: 2108/530, loss: 0.02082691341638565
2023-01-23 03:49:37.141534: step: 2112/530, loss: 3.156661841785535e-05
2023-01-23 03:49:38.290708: step: 2116/530, loss: 0.0029564856085926294
2023-01-23 03:49:39.414330: step: 2120/530, loss: 0.034891799092292786
==================================================
Loss: 0.022
--------------------
Dev: {'event': {'p': 0.5951417004048583, 'r': 0.7829560585885486, 'f1': 0.6762507188039103}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 24}
Test: {'event': {'p': 0.6360715924736118, 'r': 0.792, 'f1': 0.7055230338508527}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 24}
Chinese: {'event': {'p': 0.5647058823529412, 'r': 0.8888888888888888, 'f1': 0.6906474820143885}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 24}
Korean: {'event': {'p': 0.5849056603773585, 'r': 0.49206349206349204, 'f1': 0.5344827586206896}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 24}
Russian: {'event': {'p': 0.43478260869565216, 'r': 0.5555555555555556, 'f1': 0.4878048780487805}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 24}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6198257080610022, 'r': 0.7576564580559254, 'f1': 0.6818454164170161}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
Eng Test for Chinese: {'event': {'p': 0.642925430210325, 'r': 0.7685714285714286, 'f1': 0.7001561686621551}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
Sample Chinese: {'event': {'p': 0.6153846153846154, 'r': 0.8888888888888888, 'f1': 0.7272727272727274}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6288770053475936, 'r': 0.7829560585885486, 'f1': 0.697508896797153}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Korean: {'event': {'p': 0.64058795637743, 'r': 0.772, 'f1': 0.7001813941435606}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Korean: {'event': {'p': 0.6851851851851852, 'r': 0.5873015873015873, 'f1': 0.6324786324786325}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5319148936170213, 'r': 0.6944444444444444, 'f1': 0.6024096385542169}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
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 03:50:19.990541: step: 4/530, loss: 5.760193016612902e-05
2023-01-23 03:50:21.146326: step: 8/530, loss: 6.294251306826482e-06
2023-01-23 03:50:22.262213: step: 12/530, loss: 0.015520286746323109
2023-01-23 03:50:23.356489: step: 16/530, loss: 7.629394644936838e-07
2023-01-23 03:50:24.459800: step: 20/530, loss: 0.000690460205078125
2023-01-23 03:50:25.599578: step: 24/530, loss: 0.04330749437212944
2023-01-23 03:50:26.719994: step: 28/530, loss: 0.01213607843965292
2023-01-23 03:50:27.838463: step: 32/530, loss: 0.0005928516620770097
2023-01-23 03:50:28.970257: step: 36/530, loss: 3.356933666509576e-05
2023-01-23 03:50:30.131832: step: 40/530, loss: 0.004153442569077015
2023-01-23 03:50:31.235491: step: 44/530, loss: 0.021117497235536575
2023-01-23 03:50:32.358715: step: 48/530, loss: 0.2995050549507141
2023-01-23 03:50:33.483428: step: 52/530, loss: 8.020401583053172e-05
2023-01-23 03:50:34.588333: step: 56/530, loss: 0.03614845499396324
2023-01-23 03:50:35.712548: step: 60/530, loss: 0.0038333891425281763
2023-01-23 03:50:36.823617: step: 64/530, loss: 0.2555854618549347
2023-01-23 03:50:37.931398: step: 68/530, loss: 1.163482647825731e-05
2023-01-23 03:50:39.056202: step: 72/530, loss: 0.0010929107666015625
2023-01-23 03:50:40.161992: step: 76/530, loss: 0.000598907470703125
2023-01-23 03:50:41.305676: step: 80/530, loss: 0.010788917541503906
2023-01-23 03:50:42.462337: step: 84/530, loss: 0.01687498204410076
2023-01-23 03:50:43.580185: step: 88/530, loss: 0.00013828277587890625
2023-01-23 03:50:44.713012: step: 92/530, loss: 2.441406286379788e-05
2023-01-23 03:50:45.858947: step: 96/530, loss: 0.0004898071056231856
2023-01-23 03:50:46.978435: step: 100/530, loss: 0.00017232894606422633
2023-01-23 03:50:48.140695: step: 104/530, loss: 0.029174232855439186
2023-01-23 03:50:49.259440: step: 108/530, loss: 6.19411512161605e-05
2023-01-23 03:50:50.393211: step: 112/530, loss: 0.0020587921608239412
2023-01-23 03:50:51.532058: step: 116/530, loss: 0.010316919535398483
2023-01-23 03:50:52.658217: step: 120/530, loss: 0.2576211988925934
2023-01-23 03:50:53.769042: step: 124/530, loss: 5.722046125811175e-07
2023-01-23 03:50:54.907588: step: 128/530, loss: 7.553101022494957e-05
2023-01-23 03:50:56.001584: step: 132/530, loss: 2.8610231765924254e-06
2023-01-23 03:50:57.128914: step: 136/530, loss: 0.004568958189338446
2023-01-23 03:50:58.191912: step: 140/530, loss: 2.3746491933707148e-05
2023-01-23 03:50:59.333240: step: 144/530, loss: 0.06956224888563156
2023-01-23 03:51:00.462778: step: 148/530, loss: 0.019528819248080254
2023-01-23 03:51:01.614172: step: 152/530, loss: 0.03265991061925888
2023-01-23 03:51:02.739592: step: 156/530, loss: 0.01950244978070259
2023-01-23 03:51:03.848875: step: 160/530, loss: 0.0055661676451563835
2023-01-23 03:51:04.958044: step: 164/530, loss: 0.01079788152128458
2023-01-23 03:51:06.117789: step: 168/530, loss: 0.050382040441036224
2023-01-23 03:51:07.240566: step: 172/530, loss: 0.08066711574792862
2023-01-23 03:51:08.365120: step: 176/530, loss: 0.0007628441089764237
2023-01-23 03:51:09.496400: step: 180/530, loss: 0.0002130508510163054
2023-01-23 03:51:10.622600: step: 184/530, loss: 0.0036909105256199837
2023-01-23 03:51:11.732640: step: 188/530, loss: 0.0018259049393236637
2023-01-23 03:51:12.838326: step: 192/530, loss: 0.010990524664521217
2023-01-23 03:51:14.002050: step: 196/530, loss: 0.047499850392341614
2023-01-23 03:51:15.124815: step: 200/530, loss: 0.0013965606922283769
2023-01-23 03:51:16.275029: step: 204/530, loss: 0.007748221978545189
2023-01-23 03:51:17.381185: step: 208/530, loss: 0.0006358146201819181
2023-01-23 03:51:18.519629: step: 212/530, loss: 0.0666746124625206
2023-01-23 03:51:19.621765: step: 216/530, loss: 0.0017342568608000875
2023-01-23 03:51:20.727483: step: 220/530, loss: 0.0008307457319460809
2023-01-23 03:51:21.836421: step: 224/530, loss: 0.005261421203613281
2023-01-23 03:51:22.958856: step: 228/530, loss: 8.583068620282575e-07
2023-01-23 03:51:24.090873: step: 232/530, loss: 0.03453836217522621
2023-01-23 03:51:25.246166: step: 236/530, loss: 0.0027935029938817024
2023-01-23 03:51:26.357061: step: 240/530, loss: 0.009085082449018955
2023-01-23 03:51:27.443705: step: 244/530, loss: 0.00012674331082962453
2023-01-23 03:51:28.566171: step: 248/530, loss: 0.0001184463471872732
2023-01-23 03:51:29.698621: step: 252/530, loss: 0.00295944232493639
2023-01-23 03:51:30.819631: step: 256/530, loss: 5.34057608092553e-06
2023-01-23 03:51:31.935841: step: 260/530, loss: 0.05891399830579758
2023-01-23 03:51:33.107709: step: 264/530, loss: 0.012195397168397903
2023-01-23 03:51:34.234230: step: 268/530, loss: 0.009903717786073685
2023-01-23 03:51:35.338638: step: 272/530, loss: 0.005273247137665749
2023-01-23 03:51:36.467404: step: 276/530, loss: 0.0003357887326274067
2023-01-23 03:51:37.588903: step: 280/530, loss: 3.8909915019758046e-05
2023-01-23 03:51:38.710692: step: 284/530, loss: 0.3618527352809906
2023-01-23 03:51:39.833868: step: 288/530, loss: 0.00022010803513694555
2023-01-23 03:51:40.942975: step: 292/530, loss: 0.0013450622791424394
2023-01-23 03:51:42.044626: step: 296/530, loss: 0.00010929107520496473
2023-01-23 03:51:43.190807: step: 300/530, loss: 0.0009700774680823088
2023-01-23 03:51:44.344800: step: 304/530, loss: 0.0038476947229355574
2023-01-23 03:51:45.462344: step: 308/530, loss: 0.0008344650268554688
2023-01-23 03:51:46.598577: step: 312/530, loss: 0.00017433166794944555
2023-01-23 03:51:47.727583: step: 316/530, loss: 0.04964103922247887
2023-01-23 03:51:48.864125: step: 320/530, loss: 2.498626781743951e-05
2023-01-23 03:51:49.975876: step: 324/530, loss: 0.03583373874425888
2023-01-23 03:51:51.134218: step: 328/530, loss: 0.0001028060942189768
2023-01-23 03:51:52.251365: step: 332/530, loss: 0.016407204791903496
2023-01-23 03:51:53.389087: step: 336/530, loss: 0.016111182048916817
2023-01-23 03:51:54.545521: step: 340/530, loss: 8.96453857421875e-05
2023-01-23 03:51:55.671400: step: 344/530, loss: 0.00047512055607512593
2023-01-23 03:51:56.768251: step: 348/530, loss: 0.015705490484833717
2023-01-23 03:51:57.881906: step: 352/530, loss: 0.5802481174468994
2023-01-23 03:51:59.005818: step: 356/530, loss: 0.000232696533203125
2023-01-23 03:52:00.133975: step: 360/530, loss: 7.524490501964465e-05
2023-01-23 03:52:01.244604: step: 364/530, loss: 0.011943817138671875
2023-01-23 03:52:02.370585: step: 368/530, loss: 0.031771469861269
2023-01-23 03:52:03.499299: step: 372/530, loss: 0.0012729167938232422
2023-01-23 03:52:04.613182: step: 376/530, loss: 9.5367431640625e-07
2023-01-23 03:52:05.731034: step: 380/530, loss: 0.000213623046875
2023-01-23 03:52:06.852457: step: 384/530, loss: 0.0007368088117800653
2023-01-23 03:52:07.989258: step: 388/530, loss: 0.06365757435560226
2023-01-23 03:52:09.166540: step: 392/530, loss: 0.010807800106704235
2023-01-23 03:52:10.311934: step: 396/530, loss: 0.013941668905317783
2023-01-23 03:52:11.427905: step: 400/530, loss: 0.0019784928299486637
2023-01-23 03:52:12.576433: step: 404/530, loss: 3.185272362316027e-05
2023-01-23 03:52:13.737773: step: 408/530, loss: 0.00016727446927689016
2023-01-23 03:52:14.883012: step: 412/530, loss: 0.0889003798365593
2023-01-23 03:52:16.039939: step: 416/530, loss: 0.0004798888985533267
2023-01-23 03:52:17.158610: step: 420/530, loss: 0.0003810882626567036
2023-01-23 03:52:18.301499: step: 424/530, loss: 0.020220661535859108
2023-01-23 03:52:19.431680: step: 428/530, loss: 6.29425048828125e-05
2023-01-23 03:52:20.571603: step: 432/530, loss: 7.324218313442543e-05
2023-01-23 03:52:21.665947: step: 436/530, loss: 0.00018224716768600047
2023-01-23 03:52:22.785280: step: 440/530, loss: 0.0031751631759107113
2023-01-23 03:52:23.919629: step: 444/530, loss: 0.0001867294340627268
2023-01-23 03:52:25.029981: step: 448/530, loss: 4.5585635234601796e-05
2023-01-23 03:52:26.222467: step: 452/530, loss: 0.00010566711716819555
2023-01-23 03:52:27.331212: step: 456/530, loss: 0.0001087188720703125
2023-01-23 03:52:28.420086: step: 460/530, loss: 4.816055479750503e-06
2023-01-23 03:52:29.588841: step: 464/530, loss: 0.05063781887292862
2023-01-23 03:52:30.700243: step: 468/530, loss: 0.07520905137062073
2023-01-23 03:52:31.817871: step: 472/530, loss: 0.008673572912812233
2023-01-23 03:52:32.945792: step: 476/530, loss: 0.0006789207109250128
2023-01-23 03:52:34.065726: step: 480/530, loss: -8.106235327431932e-07
2023-01-23 03:52:35.181360: step: 484/530, loss: 0.0011214256519451737
2023-01-23 03:52:36.292119: step: 488/530, loss: 0.004423904698342085
2023-01-23 03:52:37.405066: step: 492/530, loss: 0.0004400253528729081
2023-01-23 03:52:38.519840: step: 496/530, loss: 1.9073486328125e-06
2023-01-23 03:52:39.664253: step: 500/530, loss: 9.288787987316027e-05
2023-01-23 03:52:40.789381: step: 504/530, loss: 0.022943973541259766
2023-01-23 03:52:41.902869: step: 508/530, loss: 0.03136320412158966
2023-01-23 03:52:43.026272: step: 512/530, loss: 0.0051250457763671875
2023-01-23 03:52:44.141463: step: 516/530, loss: -3.933906555175781e-06
2023-01-23 03:52:45.244837: step: 520/530, loss: 0.00021214484877418727
2023-01-23 03:52:46.382144: step: 524/530, loss: 0.0002285003720317036
2023-01-23 03:52:47.514197: step: 528/530, loss: 0.00011521577835083008
2023-01-23 03:52:48.608870: step: 532/530, loss: 0.0012777328956872225
2023-01-23 03:52:49.722995: step: 536/530, loss: 0.041399434208869934
2023-01-23 03:52:50.831193: step: 540/530, loss: 0.00311698904260993
2023-01-23 03:52:51.944866: step: 544/530, loss: 0.004006767179816961
2023-01-23 03:52:53.067961: step: 548/530, loss: 0.007896805182099342
2023-01-23 03:52:54.207795: step: 552/530, loss: 0.0001291275111725554
2023-01-23 03:52:55.330707: step: 556/530, loss: 0.00044536590576171875
2023-01-23 03:52:56.431919: step: 560/530, loss: 4.19616708313697e-06
2023-01-23 03:52:57.572211: step: 564/530, loss: 0.005494022276252508
2023-01-23 03:52:58.693967: step: 568/530, loss: 0.00023460389638785273
2023-01-23 03:52:59.803606: step: 572/530, loss: 0.00024433137150481343
2023-01-23 03:53:00.922219: step: 576/530, loss: 0.00197257986292243
2023-01-23 03:53:02.032749: step: 580/530, loss: 0.00055780413094908
2023-01-23 03:53:03.154428: step: 584/530, loss: 0.026679228991270065
2023-01-23 03:53:04.270604: step: 588/530, loss: 0.012189007364213467
2023-01-23 03:53:05.392304: step: 592/530, loss: 0.0001600265532033518
2023-01-23 03:53:06.552548: step: 596/530, loss: 0.011222731322050095
2023-01-23 03:53:07.669541: step: 600/530, loss: 0.0018152237171307206
2023-01-23 03:53:08.780829: step: 604/530, loss: 0.022639179602265358
2023-01-23 03:53:09.889383: step: 608/530, loss: 0.0015533447731286287
2023-01-23 03:53:11.007035: step: 612/530, loss: 3.910064606316155e-06
2023-01-23 03:53:12.140763: step: 616/530, loss: 0.05896148830652237
2023-01-23 03:53:13.234061: step: 620/530, loss: 0.009541917592287064
2023-01-23 03:53:14.361917: step: 624/530, loss: 0.16832828521728516
2023-01-23 03:53:15.481425: step: 628/530, loss: 0.10283298790454865
2023-01-23 03:53:16.630719: step: 632/530, loss: 0.008816242218017578
2023-01-23 03:53:17.715952: step: 636/530, loss: 0.0021834373474121094
2023-01-23 03:53:18.843885: step: 640/530, loss: 0.0006414413801394403
2023-01-23 03:53:19.965544: step: 644/530, loss: 0.053575899451971054
2023-01-23 03:53:21.096755: step: 648/530, loss: 0.22682718932628632
2023-01-23 03:53:22.194756: step: 652/530, loss: 3.4809113458322827e-06
2023-01-23 03:53:23.350832: step: 656/530, loss: 0.03373575210571289
2023-01-23 03:53:24.482994: step: 660/530, loss: 0.0208892822265625
2023-01-23 03:53:25.594976: step: 664/530, loss: 0.0015548706287518144
2023-01-23 03:53:26.713196: step: 668/530, loss: 5.9700014389818534e-05
2023-01-23 03:53:27.804208: step: 672/530, loss: 0.0038442614022642374
2023-01-23 03:53:28.932670: step: 676/530, loss: 0.01062402781099081
2023-01-23 03:53:30.058725: step: 680/530, loss: 0.008145141415297985
2023-01-23 03:53:31.189735: step: 684/530, loss: 0.008001899346709251
2023-01-23 03:53:32.325109: step: 688/530, loss: 0.0007680892595089972
2023-01-23 03:53:33.472760: step: 692/530, loss: 5.187988426769152e-05
2023-01-23 03:53:34.582213: step: 696/530, loss: 2.2315980459097773e-05
2023-01-23 03:53:35.697112: step: 700/530, loss: 0.016297722235322
2023-01-23 03:53:36.793576: step: 704/530, loss: 0.026692010462284088
2023-01-23 03:53:37.912700: step: 708/530, loss: 0.0065919398330152035
2023-01-23 03:53:39.041080: step: 712/530, loss: 0.00010747909982455894
2023-01-23 03:53:40.161069: step: 716/530, loss: 0.00015742778487037867
2023-01-23 03:53:41.289347: step: 720/530, loss: 0.002621269319206476
2023-01-23 03:53:42.386026: step: 724/530, loss: 0.0002571106015238911
2023-01-23 03:53:43.522309: step: 728/530, loss: 0.0019521713256835938
2023-01-23 03:53:44.631889: step: 732/530, loss: 0.022020291537046432
2023-01-23 03:53:45.742539: step: 736/530, loss: 0.002134132431820035
2023-01-23 03:53:46.896654: step: 740/530, loss: 0.005217170808464289
2023-01-23 03:53:48.010347: step: 744/530, loss: 5.53131103515625e-05
2023-01-23 03:53:49.140925: step: 748/530, loss: 0.002600383711978793
2023-01-23 03:53:50.259693: step: 752/530, loss: 0.00021409989858511835
2023-01-23 03:53:51.377058: step: 756/530, loss: 0.0004191398620605469
2023-01-23 03:53:52.475257: step: 760/530, loss: 8.602142770541832e-05
2023-01-23 03:53:53.627217: step: 764/530, loss: 5.7220458984375e-06
2023-01-23 03:53:54.740453: step: 768/530, loss: 6.67572021484375e-06
2023-01-23 03:53:55.860462: step: 772/530, loss: 0.012211799621582031
2023-01-23 03:53:56.985109: step: 776/530, loss: 0.0023056031204760075
2023-01-23 03:53:58.108458: step: 780/530, loss: 0.0010417938465252519
2023-01-23 03:53:59.259176: step: 784/530, loss: 1.3256072634248994e-05
2023-01-23 03:54:00.386896: step: 788/530, loss: 0.0016183375846594572
2023-01-23 03:54:01.522870: step: 792/530, loss: 0.00021648408437613398
2023-01-23 03:54:02.650360: step: 796/530, loss: 0.009194612503051758
2023-01-23 03:54:03.744064: step: 800/530, loss: 0.0014911651378497481
2023-01-23 03:54:04.842407: step: 804/530, loss: 5.9747697378043085e-05
2023-01-23 03:54:05.969366: step: 808/530, loss: 0.0015074253315106034
2023-01-23 03:54:07.111587: step: 812/530, loss: 0.00204124441370368
2023-01-23 03:54:08.218500: step: 816/530, loss: 0.00041809084359556437
2023-01-23 03:54:09.333177: step: 820/530, loss: 0.0001298904389841482
2023-01-23 03:54:10.474822: step: 824/530, loss: 0.014511299319565296
2023-01-23 03:54:11.586210: step: 828/530, loss: 0.000967431056778878
2023-01-23 03:54:12.697704: step: 832/530, loss: 6.29425048828125e-05
2023-01-23 03:54:13.819278: step: 836/530, loss: 0.003452873323112726
2023-01-23 03:54:14.944367: step: 840/530, loss: 0.0040378570556640625
2023-01-23 03:54:16.074480: step: 844/530, loss: 0.027158165350556374
2023-01-23 03:54:17.166826: step: 848/530, loss: 2.6226043701171875e-05
2023-01-23 03:54:18.312171: step: 852/530, loss: 2.1743775505456142e-05
2023-01-23 03:54:19.433170: step: 856/530, loss: 0.006146240513771772
2023-01-23 03:54:20.566075: step: 860/530, loss: 0.04234914854168892
2023-01-23 03:54:21.685366: step: 864/530, loss: 0.006815814878791571
2023-01-23 03:54:22.798383: step: 868/530, loss: 0.0002437591610942036
2023-01-23 03:54:23.897262: step: 872/530, loss: 3.352165367687121e-05
2023-01-23 03:54:24.987704: step: 876/530, loss: 0.020459938794374466
2023-01-23 03:54:26.104247: step: 880/530, loss: 0.0002548217598814517
2023-01-23 03:54:27.260949: step: 884/530, loss: 4.1007992876984645e-06
2023-01-23 03:54:28.388696: step: 888/530, loss: 5.483627683133818e-05
2023-01-23 03:54:29.535961: step: 892/530, loss: 0.024182798340916634
2023-01-23 03:54:30.641893: step: 896/530, loss: 0.008135223761200905
2023-01-23 03:54:31.751661: step: 900/530, loss: 0.00025577546330168843
2023-01-23 03:54:32.910097: step: 904/530, loss: 0.00011825562251033261
2023-01-23 03:54:34.040276: step: 908/530, loss: 6.752014451194555e-05
2023-01-23 03:54:35.176390: step: 912/530, loss: 0.00034332275390625
2023-01-23 03:54:36.344523: step: 916/530, loss: 0.0003939628368243575
2023-01-23 03:54:37.485330: step: 920/530, loss: 0.006469917483627796
2023-01-23 03:54:38.655432: step: 924/530, loss: 0.011805057525634766
2023-01-23 03:54:39.801361: step: 928/530, loss: 0.0002655983262229711
2023-01-23 03:54:40.963479: step: 932/530, loss: 0.041353560984134674
2023-01-23 03:54:42.099482: step: 936/530, loss: 4.4202803110238165e-05
2023-01-23 03:54:43.240896: step: 940/530, loss: 0.11973419040441513
2023-01-23 03:54:44.382422: step: 944/530, loss: 1.621246337890625e-05
2023-01-23 03:54:45.496557: step: 948/530, loss: 8.37326078908518e-05
2023-01-23 03:54:46.599729: step: 952/530, loss: 2.0408631826285273e-05
2023-01-23 03:54:47.712823: step: 956/530, loss: 0.0545259490609169
2023-01-23 03:54:48.848542: step: 960/530, loss: 0.022856904193758965
2023-01-23 03:54:49.984762: step: 964/530, loss: 0.00012044906907249242
2023-01-23 03:54:51.100431: step: 968/530, loss: -4.816055479750503e-06
2023-01-23 03:54:52.222980: step: 972/530, loss: 0.00599327078089118
2023-01-23 03:54:53.318580: step: 976/530, loss: 0.0001146316499216482
2023-01-23 03:54:54.431788: step: 980/530, loss: 4.596710277837701e-05
2023-01-23 03:54:55.553233: step: 984/530, loss: 0.01909642294049263
2023-01-23 03:54:56.677699: step: 988/530, loss: 2.5081635612878017e-05
2023-01-23 03:54:57.791336: step: 992/530, loss: 0.0011288643581792712
2023-01-23 03:54:58.901951: step: 996/530, loss: 0.0008054733625613153
2023-01-23 03:55:00.040027: step: 1000/530, loss: 0.002540207002311945
2023-01-23 03:55:01.166699: step: 1004/530, loss: 0.14998988807201385
2023-01-23 03:55:02.311055: step: 1008/530, loss: 0.0008680343744345009
2023-01-23 03:55:03.444759: step: 1012/530, loss: 0.02559218555688858
2023-01-23 03:55:04.575675: step: 1016/530, loss: 0.0001165389985544607
2023-01-23 03:55:05.680236: step: 1020/530, loss: 0.015374279581010342
2023-01-23 03:55:06.828981: step: 1024/530, loss: -2.19345088225964e-06
2023-01-23 03:55:07.974031: step: 1028/530, loss: 0.002293491503223777
2023-01-23 03:55:09.080144: step: 1032/530, loss: 4.5776364459015895e-06
2023-01-23 03:55:10.221061: step: 1036/530, loss: 0.007201576139777899
2023-01-23 03:55:11.417271: step: 1040/530, loss: 0.0009744644048623741
2023-01-23 03:55:12.539966: step: 1044/530, loss: 0.00432434119284153
2023-01-23 03:55:13.667144: step: 1048/530, loss: 5.0926206313306466e-05
2023-01-23 03:55:14.784233: step: 1052/530, loss: 2.6082992917508818e-05
2023-01-23 03:55:15.882661: step: 1056/530, loss: 0.0032881738152354956
2023-01-23 03:55:17.013007: step: 1060/530, loss: 0.0010266781318932772
2023-01-23 03:55:18.103405: step: 1064/530, loss: 0.022023582831025124
2023-01-23 03:55:19.218899: step: 1068/530, loss: 2.4032591682043858e-05
2023-01-23 03:55:20.308978: step: 1072/530, loss: 0.0015546799404546618
2023-01-23 03:55:21.431006: step: 1076/530, loss: 0.0010232925415039062
2023-01-23 03:55:22.567021: step: 1080/530, loss: 1.6021729607018642e-05
2023-01-23 03:55:23.698970: step: 1084/530, loss: 0.028565790504217148
2023-01-23 03:55:24.834454: step: 1088/530, loss: 0.0006079673767089844
2023-01-23 03:55:26.005033: step: 1092/530, loss: 0.0009604454389773309
2023-01-23 03:55:27.119203: step: 1096/530, loss: 0.0003078460576944053
2023-01-23 03:55:28.227315: step: 1100/530, loss: 0.0527295358479023
2023-01-23 03:55:29.350666: step: 1104/530, loss: 0.004945564083755016
2023-01-23 03:55:30.460905: step: 1108/530, loss: 9.059906005859375e-05
2023-01-23 03:55:31.613118: step: 1112/530, loss: 1.7833710444392636e-05
2023-01-23 03:55:32.729448: step: 1116/530, loss: 0.0004982948303222656
2023-01-23 03:55:33.857643: step: 1120/530, loss: 1.1253358934482094e-05
2023-01-23 03:55:35.006135: step: 1124/530, loss: 1.163482647825731e-05
2023-01-23 03:55:36.121705: step: 1128/530, loss: 0.012365054339170456
2023-01-23 03:55:37.254252: step: 1132/530, loss: -3.43322744811303e-06
2023-01-23 03:55:38.377685: step: 1136/530, loss: -1.487731969973538e-05
2023-01-23 03:55:39.531954: step: 1140/530, loss: 0.05293254926800728
2023-01-23 03:55:40.653544: step: 1144/530, loss: 0.0002735137823037803
2023-01-23 03:55:41.804982: step: 1148/530, loss: -3.0517580853484105e-06
2023-01-23 03:55:42.932720: step: 1152/530, loss: 9.174347360385582e-05
2023-01-23 03:55:44.058439: step: 1156/530, loss: 0.0002172470121877268
2023-01-23 03:55:45.171205: step: 1160/530, loss: 0.0017421721713617444
2023-01-23 03:55:46.302440: step: 1164/530, loss: 0.06765203922986984
2023-01-23 03:55:47.413726: step: 1168/530, loss: 0.0006789207109250128
2023-01-23 03:55:48.523995: step: 1172/530, loss: 0.016523336991667747
2023-01-23 03:55:49.642608: step: 1176/530, loss: 0.0007490158313885331
2023-01-23 03:55:50.772298: step: 1180/530, loss: 0.004408645909279585
2023-01-23 03:55:51.910203: step: 1184/530, loss: 0.00013017655874136835
2023-01-23 03:55:53.096238: step: 1188/530, loss: 2.117157055181451e-05
2023-01-23 03:55:54.247613: step: 1192/530, loss: 0.0036529540084302425
2023-01-23 03:55:55.374827: step: 1196/530, loss: 0.007598018739372492
2023-01-23 03:55:56.529032: step: 1200/530, loss: 2.689361645025201e-05
2023-01-23 03:55:57.687804: step: 1204/530, loss: 6.160735938465223e-05
2023-01-23 03:55:58.792911: step: 1208/530, loss: 0.0001338958682026714
2023-01-23 03:55:59.912118: step: 1212/530, loss: 0.03086128458380699
2023-01-23 03:56:01.026689: step: 1216/530, loss: 7.286071922862902e-05
2023-01-23 03:56:02.150265: step: 1220/530, loss: 0.013055801391601562
2023-01-23 03:56:03.253887: step: 1224/530, loss: 1.2373924619168974e-05
2023-01-23 03:56:04.354828: step: 1228/530, loss: 0.021085072308778763
2023-01-23 03:56:05.450945: step: 1232/530, loss: 2.117157055181451e-05
2023-01-23 03:56:06.586635: step: 1236/530, loss: 0.17790231108665466
2023-01-23 03:56:07.742350: step: 1240/530, loss: 0.012349128723144531
2023-01-23 03:56:08.870951: step: 1244/530, loss: 0.0005983352893963456
2023-01-23 03:56:09.993188: step: 1248/530, loss: 0.02866668626666069
2023-01-23 03:56:11.125026: step: 1252/530, loss: 0.005595398135483265
2023-01-23 03:56:12.225458: step: 1256/530, loss: 0.0021149637177586555
2023-01-23 03:56:13.357385: step: 1260/530, loss: 0.00010948181443382055
2023-01-23 03:56:14.474065: step: 1264/530, loss: 0.00018043517775367945
2023-01-23 03:56:15.625955: step: 1268/530, loss: 0.021932220086455345
2023-01-23 03:56:16.749635: step: 1272/530, loss: 0.00486183213070035
2023-01-23 03:56:17.825749: step: 1276/530, loss: 1.4829635802016128e-05
2023-01-23 03:56:18.957638: step: 1280/530, loss: 0.000545501708984375
2023-01-23 03:56:20.086919: step: 1284/530, loss: 0.005814719013869762
2023-01-23 03:56:21.231893: step: 1288/530, loss: 3.1471254260395654e-06
2023-01-23 03:56:22.344224: step: 1292/530, loss: 0.0007976532797329128
2023-01-23 03:56:23.494875: step: 1296/530, loss: 0.0004677772521972656
2023-01-23 03:56:24.609038: step: 1300/530, loss: 0.0003046035999432206
2023-01-23 03:56:25.751774: step: 1304/530, loss: 0.0003986358642578125
2023-01-23 03:56:26.856005: step: 1308/530, loss: 3.5285952435515355e-06
2023-01-23 03:56:27.971702: step: 1312/530, loss: 0.00101299281232059
2023-01-23 03:56:29.127117: step: 1316/530, loss: 9.078979201149195e-05
2023-01-23 03:56:30.239129: step: 1320/530, loss: 6.809234764659777e-05
2023-01-23 03:56:31.375045: step: 1324/530, loss: 4.00543194700731e-06
2023-01-23 03:56:32.505378: step: 1328/530, loss: 8.58306884765625e-06
2023-01-23 03:56:33.640721: step: 1332/530, loss: 0.0017309188842773438
2023-01-23 03:56:34.802120: step: 1336/530, loss: 0.027537154033780098
2023-01-23 03:56:35.914869: step: 1340/530, loss: 6.027221752447076e-05
2023-01-23 03:56:37.047920: step: 1344/530, loss: 0.0012868881458416581
2023-01-23 03:56:38.159939: step: 1348/530, loss: 0.017282672226428986
2023-01-23 03:56:39.280788: step: 1352/530, loss: 0.04293708875775337
2023-01-23 03:56:40.394878: step: 1356/530, loss: 0.0023069381713867188
2023-01-23 03:56:41.536631: step: 1360/530, loss: 0.0016736506950110197
2023-01-23 03:56:42.645743: step: 1364/530, loss: 9.870529902400449e-05
2023-01-23 03:56:43.757086: step: 1368/530, loss: 0.054799843579530716
2023-01-23 03:56:44.888701: step: 1372/530, loss: 0.02229003980755806
2023-01-23 03:56:46.036508: step: 1376/530, loss: 0.006322097964584827
2023-01-23 03:56:47.177816: step: 1380/530, loss: 9.460449655307457e-05
2023-01-23 03:56:48.310351: step: 1384/530, loss: 0.0002643585321493447
2023-01-23 03:56:49.447200: step: 1388/530, loss: 0.07097721099853516
2023-01-23 03:56:50.573035: step: 1392/530, loss: 0.0002117156982421875
2023-01-23 03:56:51.697620: step: 1396/530, loss: 4.916191392112523e-05
2023-01-23 03:56:52.817065: step: 1400/530, loss: 6.86645489622606e-06
2023-01-23 03:56:53.917811: step: 1404/530, loss: 0.011098289862275124
2023-01-23 03:56:55.025057: step: 1408/530, loss: 0.00038919446524232626
2023-01-23 03:56:56.168705: step: 1412/530, loss: 0.0002101898135151714
2023-01-23 03:56:57.291355: step: 1416/530, loss: 0.0003986358642578125
2023-01-23 03:56:58.424058: step: 1420/530, loss: 0.00483284005895257
2023-01-23 03:56:59.533691: step: 1424/530, loss: 3.051757857974735e-06
2023-01-23 03:57:00.646524: step: 1428/530, loss: 0.00142335903365165
2023-01-23 03:57:01.767834: step: 1432/530, loss: 0.03229503706097603
2023-01-23 03:57:02.901335: step: 1436/530, loss: 0.002235317137092352
2023-01-23 03:57:04.032086: step: 1440/530, loss: 0.03148498758673668
2023-01-23 03:57:05.164782: step: 1444/530, loss: 0.001020717667415738
2023-01-23 03:57:06.322311: step: 1448/530, loss: 0.0027269364800304174
2023-01-23 03:57:07.439080: step: 1452/530, loss: 0.011743354611098766
2023-01-23 03:57:08.564926: step: 1456/530, loss: 0.0004593372577801347
2023-01-23 03:57:09.713505: step: 1460/530, loss: 0.015277290716767311
2023-01-23 03:57:10.856206: step: 1464/530, loss: 0.00011568069749046117
2023-01-23 03:57:11.963802: step: 1468/530, loss: 0.00014925003051757812
2023-01-23 03:57:13.101299: step: 1472/530, loss: 0.005846405401825905
2023-01-23 03:57:14.219901: step: 1476/530, loss: 0.03164215385913849
2023-01-23 03:57:15.375374: step: 1480/530, loss: 0.00312976841814816
2023-01-23 03:57:16.508077: step: 1484/530, loss: 0.00018634795560501516
2023-01-23 03:57:17.648593: step: 1488/530, loss: 0.00010261535499012098
2023-01-23 03:57:18.776644: step: 1492/530, loss: 0.0975341796875
2023-01-23 03:57:19.910828: step: 1496/530, loss: 0.0004000186745543033
2023-01-23 03:57:21.029638: step: 1500/530, loss: 0.0030048370826989412
2023-01-23 03:57:22.156334: step: 1504/530, loss: 0.0015819550026208162
2023-01-23 03:57:23.255798: step: 1508/530, loss: 7.698535773670301e-05
2023-01-23 03:57:24.381260: step: 1512/530, loss: 3.814697322468419e-07
2023-01-23 03:57:25.490273: step: 1516/530, loss: 0.00020380019850563258
2023-01-23 03:57:26.639315: step: 1520/530, loss: 0.003494405886158347
2023-01-23 03:57:27.813436: step: 1524/530, loss: 0.0022994994651526213
2023-01-23 03:57:28.934360: step: 1528/530, loss: 0.00153865828178823
2023-01-23 03:57:30.079346: step: 1532/530, loss: 0.09261074662208557
2023-01-23 03:57:31.203432: step: 1536/530, loss: 0.003301429795101285
2023-01-23 03:57:32.353820: step: 1540/530, loss: 0.018247032538056374
2023-01-23 03:57:33.493964: step: 1544/530, loss: 0.0010723114246502519
2023-01-23 03:57:34.614394: step: 1548/530, loss: 1.0204315913142636e-05
2023-01-23 03:57:35.728821: step: 1552/530, loss: 4.2724612285383046e-05
2023-01-23 03:57:36.822746: step: 1556/530, loss: 8.804201934253797e-05
2023-01-23 03:57:37.924072: step: 1560/530, loss: 2.5272369384765625e-05
2023-01-23 03:57:39.055200: step: 1564/530, loss: 0.0007892608409747481
2023-01-23 03:57:40.169618: step: 1568/530, loss: 0.012942695990204811
2023-01-23 03:57:41.295757: step: 1572/530, loss: 0.0008290291298180819
2023-01-23 03:57:42.435107: step: 1576/530, loss: 8.811950829112902e-05
2023-01-23 03:57:43.570173: step: 1580/530, loss: 0.00042572023812681437
2023-01-23 03:57:44.676696: step: 1584/530, loss: 0.016614437103271484
2023-01-23 03:57:45.801011: step: 1588/530, loss: 0.011886310763657093
2023-01-23 03:57:46.910296: step: 1592/530, loss: 0.006525135133415461
2023-01-23 03:57:48.029470: step: 1596/530, loss: 7.314682443393394e-05
2023-01-23 03:57:49.155028: step: 1600/530, loss: 0.005259704776108265
2023-01-23 03:57:50.282167: step: 1604/530, loss: 0.021658897399902344
2023-01-23 03:57:51.389392: step: 1608/530, loss: 9.193420555675402e-05
2023-01-23 03:57:52.502338: step: 1612/530, loss: 0.0002578735293354839
2023-01-23 03:57:53.625062: step: 1616/530, loss: 0.03895826265215874
2023-01-23 03:57:54.749553: step: 1620/530, loss: 0.005460548680275679
2023-01-23 03:57:55.879328: step: 1624/530, loss: 0.0030788423027843237
2023-01-23 03:57:57.014799: step: 1628/530, loss: 0.015365028753876686
2023-01-23 03:57:58.189756: step: 1632/530, loss: -9.91821252682712e-06
2023-01-23 03:57:59.306143: step: 1636/530, loss: 0.042546749114990234
2023-01-23 03:58:00.413359: step: 1640/530, loss: 0.05019249767065048
2023-01-23 03:58:01.544538: step: 1644/530, loss: 2.346038854739163e-05
2023-01-23 03:58:02.681843: step: 1648/530, loss: 0.001820468925870955
2023-01-23 03:58:03.805037: step: 1652/530, loss: 5.016326758777723e-05
2023-01-23 03:58:04.948204: step: 1656/530, loss: 0.0016891479026526213
2023-01-23 03:58:06.074490: step: 1660/530, loss: 0.05559587478637695
2023-01-23 03:58:07.181018: step: 1664/530, loss: 0.009005165658891201
2023-01-23 03:58:08.276194: step: 1668/530, loss: 7.467270188499242e-05
2023-01-23 03:58:09.394908: step: 1672/530, loss: 0.0014442444080486894
2023-01-23 03:58:10.507464: step: 1676/530, loss: 0.003948783967643976
2023-01-23 03:58:11.617068: step: 1680/530, loss: 0.00039463042048737407
2023-01-23 03:58:12.741121: step: 1684/530, loss: 0.0032584667205810547
2023-01-23 03:58:13.872738: step: 1688/530, loss: 0.03420582041144371
2023-01-23 03:58:14.987361: step: 1692/530, loss: 0.0036219358444213867
2023-01-23 03:58:16.110108: step: 1696/530, loss: 0.029423905536532402
2023-01-23 03:58:17.211276: step: 1700/530, loss: 0.0003448009374551475
2023-01-23 03:58:18.342655: step: 1704/530, loss: 0.00032482147798873484
2023-01-23 03:58:19.458360: step: 1708/530, loss: 0.0387762077152729
2023-01-23 03:58:20.557109: step: 1712/530, loss: 0.0005709648248739541
2023-01-23 03:58:21.665044: step: 1716/530, loss: 0.0665929839015007
2023-01-23 03:58:22.785041: step: 1720/530, loss: 7.600784010719508e-05
2023-01-23 03:58:23.947659: step: 1724/530, loss: 0.03605065494775772
2023-01-23 03:58:25.083436: step: 1728/530, loss: 0.020040130242705345
2023-01-23 03:58:26.204274: step: 1732/530, loss: 0.002011108212172985
2023-01-23 03:58:27.330829: step: 1736/530, loss: 0.04630448669195175
2023-01-23 03:58:28.452019: step: 1740/530, loss: 0.013636552728712559
2023-01-23 03:58:29.566160: step: 1744/530, loss: 0.0006873130914755166
2023-01-23 03:58:30.694816: step: 1748/530, loss: 6.4849853515625e-05
2023-01-23 03:58:31.831624: step: 1752/530, loss: 0.001142215682193637
2023-01-23 03:58:32.933947: step: 1756/530, loss: 6.008148193359375e-05
2023-01-23 03:58:34.056801: step: 1760/530, loss: 0.019082164391875267
2023-01-23 03:58:35.177884: step: 1764/530, loss: 0.008120918646454811
2023-01-23 03:58:36.309408: step: 1768/530, loss: 0.011363839730620384
2023-01-23 03:58:37.436952: step: 1772/530, loss: 0.00016894341388251632
2023-01-23 03:58:38.575967: step: 1776/530, loss: 0.002326393034309149
2023-01-23 03:58:39.702733: step: 1780/530, loss: 0.03616046905517578
2023-01-23 03:58:40.816589: step: 1784/530, loss: 0.024187661707401276
2023-01-23 03:58:41.949280: step: 1788/530, loss: 0.046508025377988815
2023-01-23 03:58:43.082735: step: 1792/530, loss: 0.00937185250222683
2023-01-23 03:58:44.230190: step: 1796/530, loss: 4.2343137465650216e-05
2023-01-23 03:58:45.359472: step: 1800/530, loss: 0.417245090007782
2023-01-23 03:58:46.551700: step: 1804/530, loss: 3.108978125965223e-05
2023-01-23 03:58:47.698338: step: 1808/530, loss: 0.005215073004364967
2023-01-23 03:58:48.864929: step: 1812/530, loss: 0.001076507498510182
2023-01-23 03:58:49.972180: step: 1816/530, loss: 2.0885468984488398e-05
2023-01-23 03:58:51.108586: step: 1820/530, loss: 0.0029243947938084602
2023-01-23 03:58:52.230747: step: 1824/530, loss: 0.00010900497727561742
2023-01-23 03:58:53.342114: step: 1828/530, loss: 9.34600848268019e-06
2023-01-23 03:58:54.484306: step: 1832/530, loss: 0.003025627229362726
2023-01-23 03:58:55.600811: step: 1836/530, loss: 0.00205402378924191
2023-01-23 03:58:56.708625: step: 1840/530, loss: 0.0019567490089684725
2023-01-23 03:58:57.833505: step: 1844/530, loss: 0.0004435539012774825
2023-01-23 03:58:58.924371: step: 1848/530, loss: 0.0016492843860760331
2023-01-23 03:59:00.028139: step: 1852/530, loss: 0.0012628555996343493
2023-01-23 03:59:01.163720: step: 1856/530, loss: 0.005897903814911842
2023-01-23 03:59:02.335066: step: 1860/530, loss: 8.115769014693797e-05
2023-01-23 03:59:03.438887: step: 1864/530, loss: 7.400512549793348e-05
2023-01-23 03:59:04.555140: step: 1868/530, loss: 1.735687328618951e-05
2023-01-23 03:59:05.677803: step: 1872/530, loss: 9.803772263694555e-05
2023-01-23 03:59:06.867926: step: 1876/530, loss: 0.02789182774722576
2023-01-23 03:59:07.993031: step: 1880/530, loss: 0.008263969793915749
2023-01-23 03:59:09.116319: step: 1884/530, loss: 0.00019130707369185984
2023-01-23 03:59:10.251730: step: 1888/530, loss: 0.022878360003232956
2023-01-23 03:59:11.372237: step: 1892/530, loss: 0.00021805762662552297
2023-01-23 03:59:12.462472: step: 1896/530, loss: 4.57763671875e-05
2023-01-23 03:59:13.607972: step: 1900/530, loss: 0.00216770195402205
2023-01-23 03:59:14.729581: step: 1904/530, loss: 0.00010814666893566027
2023-01-23 03:59:15.859781: step: 1908/530, loss: 9.512901306152344e-05
2023-01-23 03:59:16.957211: step: 1912/530, loss: 0.00358238210901618
2023-01-23 03:59:18.064627: step: 1916/530, loss: 0.0021102905739098787
2023-01-23 03:59:19.185571: step: 1920/530, loss: 0.006354904267936945
2023-01-23 03:59:20.282949: step: 1924/530, loss: 0.00906310137361288
2023-01-23 03:59:21.424673: step: 1928/530, loss: 0.015767479315400124
2023-01-23 03:59:22.526787: step: 1932/530, loss: 0.023536013439297676
2023-01-23 03:59:23.642785: step: 1936/530, loss: 0.002283764071762562
2023-01-23 03:59:24.756740: step: 1940/530, loss: 0.001506805419921875
2023-01-23 03:59:25.885350: step: 1944/530, loss: 0.010860919952392578
2023-01-23 03:59:26.985566: step: 1948/530, loss: 9.422302537132055e-05
2023-01-23 03:59:28.123585: step: 1952/530, loss: 0.34278029203414917
2023-01-23 03:59:29.251512: step: 1956/530, loss: 0.000501442002132535
2023-01-23 03:59:30.370867: step: 1960/530, loss: 0.13314132392406464
2023-01-23 03:59:31.489381: step: 1964/530, loss: 0.0020015717018395662
2023-01-23 03:59:32.622907: step: 1968/530, loss: 7.514953904319555e-05
2023-01-23 03:59:33.738506: step: 1972/530, loss: 0.004270076751708984
2023-01-23 03:59:34.843653: step: 1976/530, loss: 0.00013647080049850047
2023-01-23 03:59:35.984807: step: 1980/530, loss: 0.03386888653039932
2023-01-23 03:59:37.077179: step: 1984/530, loss: 0.00276603689417243
2023-01-23 03:59:38.190813: step: 1988/530, loss: 0.0001352310209767893
2023-01-23 03:59:39.348176: step: 1992/530, loss: 0.004714584443718195
2023-01-23 03:59:40.506573: step: 1996/530, loss: 0.004117775242775679
2023-01-23 03:59:41.640724: step: 2000/530, loss: 0.003760433290153742
2023-01-23 03:59:42.762888: step: 2004/530, loss: 0.0006007194169797003
2023-01-23 03:59:43.912228: step: 2008/530, loss: 0.0024663927033543587
2023-01-23 03:59:45.051432: step: 2012/530, loss: 0.030516481027007103
2023-01-23 03:59:46.149141: step: 2016/530, loss: 0.0018155097495764494
2023-01-23 03:59:47.277570: step: 2020/530, loss: 5.722044988942798e-07
2023-01-23 03:59:48.396904: step: 2024/530, loss: 0.00195140833966434
2023-01-23 03:59:49.518138: step: 2028/530, loss: 0.006188392639160156
2023-01-23 03:59:50.697196: step: 2032/530, loss: 0.0067230225540697575
2023-01-23 03:59:51.827868: step: 2036/530, loss: 0.0002838134823832661
2023-01-23 03:59:52.981490: step: 2040/530, loss: 0.0002682686026673764
2023-01-23 03:59:54.090140: step: 2044/530, loss: 0.5250097513198853
2023-01-23 03:59:55.227151: step: 2048/530, loss: 0.004332160577178001
2023-01-23 03:59:56.332859: step: 2052/530, loss: 0.01495276764035225
2023-01-23 03:59:57.450806: step: 2056/530, loss: 0.0024236678145825863
2023-01-23 03:59:58.597566: step: 2060/530, loss: 0.00018310546875
2023-01-23 03:59:59.699711: step: 2064/530, loss: 0.00013675689115189016
2023-01-23 04:00:00.826934: step: 2068/530, loss: 0.001949405763298273
2023-01-23 04:00:01.945846: step: 2072/530, loss: 0.003637981601059437
2023-01-23 04:00:03.087487: step: 2076/530, loss: 0.000590467476285994
2023-01-23 04:00:04.194549: step: 2080/530, loss: 8.773804438533261e-06
2023-01-23 04:00:05.304965: step: 2084/530, loss: 0.0014101981651037931
2023-01-23 04:00:06.432076: step: 2088/530, loss: 0.007420730777084827
2023-01-23 04:00:07.583674: step: 2092/530, loss: 0.003148841904476285
2023-01-23 04:00:08.727570: step: 2096/530, loss: 0.0001987457217182964
2023-01-23 04:00:09.852450: step: 2100/530, loss: 0.09257392585277557
2023-01-23 04:00:10.977313: step: 2104/530, loss: 0.008580494672060013
2023-01-23 04:00:12.091656: step: 2108/530, loss: 0.0009945392375811934
2023-01-23 04:00:13.188234: step: 2112/530, loss: 0.000978660536929965
2023-01-23 04:00:14.323659: step: 2116/530, loss: 0.002523183822631836
2023-01-23 04:00:15.451864: step: 2120/530, loss: 0.049784183502197266
==================================================
Loss: 0.016
--------------------
Dev: {'event': {'p': 0.571150097465887, 'r': 0.7802929427430093, 'f1': 0.6595385481148002}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 25}
Test: {'event': {'p': 0.6182867288060364, 'r': 0.796, 'f1': 0.6959780164876342}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 25}
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': 25}
Korean: {'event': {'p': 0.5714285714285714, 'r': 0.5714285714285714, 'f1': 0.5714285714285714}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 25}
Russian: {'event': {'p': 0.36363636363636365, 'r': 0.4444444444444444, 'f1': 0.39999999999999997}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 25}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6198257080610022, 'r': 0.7576564580559254, 'f1': 0.6818454164170161}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
Eng Test for Chinese: {'event': {'p': 0.642925430210325, 'r': 0.7685714285714286, 'f1': 0.7001561686621551}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
Sample Chinese: {'event': {'p': 0.6153846153846154, 'r': 0.8888888888888888, 'f1': 0.7272727272727274}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6288770053475936, 'r': 0.7829560585885486, 'f1': 0.697508896797153}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Korean: {'event': {'p': 0.64058795637743, 'r': 0.772, 'f1': 0.7001813941435606}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Korean: {'event': {'p': 0.6851851851851852, 'r': 0.5873015873015873, 'f1': 0.6324786324786325}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5319148936170213, 'r': 0.6944444444444444, 'f1': 0.6024096385542169}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
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 04:00:56.568511: step: 4/530, loss: 0.0005044937133789062
2023-01-23 04:00:57.682693: step: 8/530, loss: 2.9039383662166074e-05
2023-01-23 04:00:58.849495: step: 12/530, loss: 6.237030174816027e-05
2023-01-23 04:00:59.994979: step: 16/530, loss: 0.026513230055570602
2023-01-23 04:01:01.113557: step: 20/530, loss: 0.00014247893705032766
2023-01-23 04:01:02.256506: step: 24/530, loss: 0.0013393402332440019
2023-01-23 04:01:03.378322: step: 28/530, loss: 0.00018377305241301656
2023-01-23 04:01:04.450183: step: 32/530, loss: 3.7765505112474784e-05
2023-01-23 04:01:05.556470: step: 36/530, loss: 0.5083279013633728
2023-01-23 04:01:06.687553: step: 40/530, loss: 0.009083176031708717
2023-01-23 04:01:07.814477: step: 44/530, loss: 0.029361821711063385
2023-01-23 04:01:08.945129: step: 48/530, loss: 0.00019493103900458664
2023-01-23 04:01:10.087999: step: 52/530, loss: 0.02713470533490181
2023-01-23 04:01:11.213189: step: 56/530, loss: 0.0029672144446521997
2023-01-23 04:01:12.301569: step: 60/530, loss: -6.198883056640625e-06
2023-01-23 04:01:13.399449: step: 64/530, loss: 8.39233416627394e-06
2023-01-23 04:01:14.528954: step: 68/530, loss: 2.4318695068359375e-05
2023-01-23 04:01:15.677682: step: 72/530, loss: 0.14770202338695526
2023-01-23 04:01:16.811102: step: 76/530, loss: 0.032408908009529114
2023-01-23 04:01:17.928752: step: 80/530, loss: 4.6348573960131034e-05
2023-01-23 04:01:19.038751: step: 84/530, loss: 0.005390167236328125
2023-01-23 04:01:20.161043: step: 88/530, loss: 0.0011595250107347965
2023-01-23 04:01:21.266028: step: 92/530, loss: 0.0012166977394372225
2023-01-23 04:01:22.386456: step: 96/530, loss: 0.0009605407831259072
2023-01-23 04:01:23.524620: step: 100/530, loss: 0.10288061946630478
2023-01-23 04:01:24.676511: step: 104/530, loss: 0.0013006209628656507
2023-01-23 04:01:25.771160: step: 108/530, loss: 0.0006127358064986765
2023-01-23 04:01:26.867171: step: 112/530, loss: 0.00013828277587890625
2023-01-23 04:01:27.999000: step: 116/530, loss: 0.048932649195194244
2023-01-23 04:01:29.136019: step: 120/530, loss: 1.0013581231760327e-05
2023-01-23 04:01:30.270360: step: 124/530, loss: 3.166198803228326e-05
2023-01-23 04:01:31.375318: step: 128/530, loss: 0.0001892089785542339
2023-01-23 04:01:32.466200: step: 132/530, loss: 0.014916039071977139
2023-01-23 04:01:33.566031: step: 136/530, loss: 0.00012149811664130539
2023-01-23 04:01:34.655163: step: 140/530, loss: 0.0015719414222985506
2023-01-23 04:01:35.766937: step: 144/530, loss: 0.0024644851218909025
2023-01-23 04:01:36.873902: step: 148/530, loss: 0.00017480849055573344
2023-01-23 04:01:37.976372: step: 152/530, loss: 0.0004939079517498612
2023-01-23 04:01:39.103293: step: 156/530, loss: 0.00022573472233489156
2023-01-23 04:01:40.244462: step: 160/530, loss: 0.0006559371831826866
2023-01-23 04:01:41.390355: step: 164/530, loss: 0.12548397481441498
2023-01-23 04:01:42.529783: step: 168/530, loss: 0.0164628978818655
2023-01-23 04:01:43.649505: step: 172/530, loss: 0.03999223932623863
2023-01-23 04:01:44.780230: step: 176/530, loss: 0.002995586721226573
2023-01-23 04:01:45.887061: step: 180/530, loss: 0.00010185241262661293
2023-01-23 04:01:47.036331: step: 184/530, loss: 0.000442314165411517
2023-01-23 04:01:48.150742: step: 188/530, loss: 1.1444091796875e-05
2023-01-23 04:01:49.273958: step: 192/530, loss: 0.00028591154841706157
2023-01-23 04:01:50.393232: step: 196/530, loss: 0.008794641122221947
2023-01-23 04:01:51.508238: step: 200/530, loss: 0.0024064064491540194
2023-01-23 04:01:52.649078: step: 204/530, loss: 0.00047397613525390625
2023-01-23 04:01:53.775119: step: 208/530, loss: 0.00029602053109556437
2023-01-23 04:01:54.926461: step: 212/530, loss: -3.566742088878527e-05
2023-01-23 04:01:56.037421: step: 216/530, loss: 0.6951268911361694
2023-01-23 04:01:57.176423: step: 220/530, loss: 0.011384868994355202
2023-01-23 04:01:58.294259: step: 224/530, loss: 0.0051517486572265625
2023-01-23 04:01:59.416408: step: 228/530, loss: 8.535385131835938e-05
2023-01-23 04:02:00.554368: step: 232/530, loss: 0.004618453793227673
2023-01-23 04:02:01.685280: step: 236/530, loss: 0.00012865065946243703
2023-01-23 04:02:02.829166: step: 240/530, loss: 0.0009818077087402344
2023-01-23 04:02:03.954930: step: 244/530, loss: 5.71250930079259e-05
2023-01-23 04:02:05.048628: step: 248/530, loss: 1.950263867911417e-05
2023-01-23 04:02:06.183683: step: 252/530, loss: 0.0013868332607671618
2023-01-23 04:02:07.308762: step: 256/530, loss: 0.0005932330968789756
2023-01-23 04:02:08.446720: step: 260/530, loss: 0.000171661376953125
2023-01-23 04:02:09.551169: step: 264/530, loss: 2.946853419416584e-05
2023-01-23 04:02:10.700686: step: 268/530, loss: 0.007263374514877796
2023-01-23 04:02:11.816278: step: 272/530, loss: 0.0014606952900066972
2023-01-23 04:02:12.924778: step: 276/530, loss: 7.915497008070815e-06
2023-01-23 04:02:14.060298: step: 280/530, loss: 0.0002563476446084678
2023-01-23 04:02:15.143457: step: 284/530, loss: 6.67572021484375e-06
2023-01-23 04:02:16.231217: step: 288/530, loss: 0.00037326812162064016
2023-01-23 04:02:17.377119: step: 292/530, loss: 0.03829498589038849
2023-01-23 04:02:18.482052: step: 296/530, loss: 0.00015964507474564016
2023-01-23 04:02:19.618429: step: 300/530, loss: 0.0012250900035724044
2023-01-23 04:02:20.736569: step: 304/530, loss: 0.007395935244858265
2023-01-23 04:02:21.856305: step: 308/530, loss: 0.0002865791320800781
2023-01-23 04:02:23.003361: step: 312/530, loss: 0.011874771676957607
2023-01-23 04:02:24.166294: step: 316/530, loss: 6.48498553346144e-06
2023-01-23 04:02:25.312166: step: 320/530, loss: 0.0003611564461607486
2023-01-23 04:02:26.422199: step: 324/530, loss: 0.0012183189392089844
2023-01-23 04:02:27.541048: step: 328/530, loss: 0.0015171528793871403
2023-01-23 04:02:28.690918: step: 332/530, loss: 0.07417802512645721
2023-01-23 04:02:29.816492: step: 336/530, loss: 0.00022182465181685984
2023-01-23 04:02:30.919101: step: 340/530, loss: 0.00020065308490302414
2023-01-23 04:02:32.048810: step: 344/530, loss: 0.002754783723503351
2023-01-23 04:02:33.178621: step: 348/530, loss: 0.0044265748001635075
2023-01-23 04:02:34.303228: step: 352/530, loss: 0.00017309188842773438
2023-01-23 04:02:35.422125: step: 356/530, loss: 0.0009841920109465718
2023-01-23 04:02:36.554394: step: 360/530, loss: 0.0006649017450399697
2023-01-23 04:02:37.671002: step: 364/530, loss: 0.00034732819767668843
2023-01-23 04:02:38.803341: step: 368/530, loss: 1.697540210443549e-05
2023-01-23 04:02:39.905389: step: 372/530, loss: 0.018207168206572533
2023-01-23 04:02:41.055098: step: 376/530, loss: 0.0002567291376180947
2023-01-23 04:02:42.195437: step: 380/530, loss: 0.0034462930634617805
2023-01-23 04:02:43.335485: step: 384/530, loss: 0.00018348694720771164
2023-01-23 04:02:44.444511: step: 388/530, loss: 0.014695358462631702
2023-01-23 04:02:45.570127: step: 392/530, loss: 0.0014261245960369706
2023-01-23 04:02:46.692785: step: 396/530, loss: 0.09914422035217285
2023-01-23 04:02:47.797708: step: 400/530, loss: 0.0003533363342285156
2023-01-23 04:02:48.917835: step: 404/530, loss: 1.52587890625e-05
2023-01-23 04:02:50.036095: step: 408/530, loss: 0.0018154144054278731
2023-01-23 04:02:51.153166: step: 412/530, loss: 0.0004873752477578819
2023-01-23 04:02:52.288729: step: 416/530, loss: 0.029822731390595436
2023-01-23 04:02:53.456406: step: 420/530, loss: -1.33514404296875e-05
2023-01-23 04:02:54.631232: step: 424/530, loss: 0.013979149051010609
2023-01-23 04:02:55.757578: step: 428/530, loss: 0.045027781277894974
2023-01-23 04:02:56.875137: step: 432/530, loss: 0.00014057158841751516
2023-01-23 04:02:58.002402: step: 436/530, loss: 0.251665860414505
2023-01-23 04:02:59.127812: step: 440/530, loss: 0.0012916565174236894
2023-01-23 04:03:00.248854: step: 444/530, loss: 0.001100730849429965
2023-01-23 04:03:01.380711: step: 448/530, loss: 0.0018123626941815019
2023-01-23 04:03:02.505323: step: 452/530, loss: 0.00153350830078125
2023-01-23 04:03:03.657800: step: 456/530, loss: 0.0039081573486328125
2023-01-23 04:03:04.747014: step: 460/530, loss: 0.0027206421364098787
2023-01-23 04:03:05.871474: step: 464/530, loss: 0.02383604273200035
2023-01-23 04:03:06.972692: step: 468/530, loss: 0.019712449982762337
2023-01-23 04:03:08.096473: step: 472/530, loss: 0.029551077634096146
2023-01-23 04:03:09.240531: step: 476/530, loss: 2.3031234377413057e-05
2023-01-23 04:03:10.353945: step: 480/530, loss: 8.37326078908518e-05
2023-01-23 04:03:11.457476: step: 484/530, loss: 0.0003444671747274697
2023-01-23 04:03:12.568107: step: 488/530, loss: 0.00011839867511298507
2023-01-23 04:03:13.707973: step: 492/530, loss: 0.0003761291445698589
2023-01-23 04:03:14.858962: step: 496/530, loss: 0.001889896346256137
2023-01-23 04:03:15.982245: step: 500/530, loss: 0.039850424975156784
2023-01-23 04:03:17.155615: step: 504/530, loss: 0.00897131022065878
2023-01-23 04:03:18.280300: step: 508/530, loss: 0.000546360039152205
2023-01-23 04:03:19.438453: step: 512/530, loss: 0.00020809174748137593
2023-01-23 04:03:20.547707: step: 516/530, loss: 0.0010484695667400956
2023-01-23 04:03:21.657880: step: 520/530, loss: 0.0008975982782430947
2023-01-23 04:03:22.781154: step: 524/530, loss: 0.0001348495570709929
2023-01-23 04:03:23.947971: step: 528/530, loss: 0.003911399748176336
2023-01-23 04:03:25.066803: step: 532/530, loss: 1.4400482541532256e-05
2023-01-23 04:03:26.163917: step: 536/530, loss: 0.00047435759915970266
2023-01-23 04:03:27.317977: step: 540/530, loss: 0.00124616629909724
2023-01-23 04:03:28.420169: step: 544/530, loss: 1.9073486612342094e-07
2023-01-23 04:03:29.531458: step: 548/530, loss: 0.004593181889504194
2023-01-23 04:03:30.676036: step: 552/530, loss: 0.016797829419374466
2023-01-23 04:03:31.791536: step: 556/530, loss: 0.002057743025943637
2023-01-23 04:03:32.939383: step: 560/530, loss: 0.021702002733945847
2023-01-23 04:03:34.067341: step: 564/530, loss: 0.0023875234182924032
2023-01-23 04:03:35.219443: step: 568/530, loss: 0.0002008438023040071
2023-01-23 04:03:36.386175: step: 572/530, loss: 0.00331535330042243
2023-01-23 04:03:37.481135: step: 576/530, loss: 0.00017833709716796875
2023-01-23 04:03:38.611836: step: 580/530, loss: 2.0408631826285273e-05
2023-01-23 04:03:39.724572: step: 584/530, loss: 0.00028476715669967234
2023-01-23 04:03:40.845281: step: 588/530, loss: 0.00017492771439719945
2023-01-23 04:03:41.977285: step: 592/530, loss: 9.403228614246473e-05
2023-01-23 04:03:43.085719: step: 596/530, loss: 0.003907203674316406
2023-01-23 04:03:44.215155: step: 600/530, loss: 0.00012063980102539062
2023-01-23 04:03:45.307500: step: 604/530, loss: 1.5926361811580136e-05
2023-01-23 04:03:46.454976: step: 608/530, loss: 0.00021057129197288305
2023-01-23 04:03:47.627714: step: 612/530, loss: 0.00029411318246275187
2023-01-23 04:03:48.774365: step: 616/530, loss: 0.004790878389030695
2023-01-23 04:03:49.905664: step: 620/530, loss: 0.016141222789883614
2023-01-23 04:03:51.041094: step: 624/530, loss: 0.002587222959846258
2023-01-23 04:03:52.200502: step: 628/530, loss: 1.544952465337701e-05
2023-01-23 04:03:53.333962: step: 632/530, loss: 0.006550264544785023
2023-01-23 04:03:54.480702: step: 636/530, loss: 0.0010014057625085115
2023-01-23 04:03:55.653415: step: 640/530, loss: 0.001595306326635182
2023-01-23 04:03:56.745285: step: 644/530, loss: 0.004620933439582586
2023-01-23 04:03:57.860509: step: 648/530, loss: 0.0006326675647869706
2023-01-23 04:03:58.991026: step: 652/530, loss: 0.0013883591163903475
2023-01-23 04:04:00.093426: step: 656/530, loss: 4.4536591303767636e-05
2023-01-23 04:04:01.235423: step: 660/530, loss: 0.0014127731556072831
2023-01-23 04:04:02.375484: step: 664/530, loss: -3.910064606316155e-06
2023-01-23 04:04:03.495158: step: 668/530, loss: 0.00010194778587901965
2023-01-23 04:04:04.621218: step: 672/530, loss: 0.06518612056970596
2023-01-23 04:04:05.750973: step: 676/530, loss: 6.885529001010582e-05
2023-01-23 04:04:06.869157: step: 680/530, loss: 0.41986677050590515
2023-01-23 04:04:08.018835: step: 684/530, loss: 0.0232512466609478
2023-01-23 04:04:09.135359: step: 688/530, loss: 0.005348491482436657
2023-01-23 04:04:10.261833: step: 692/530, loss: 0.00010385513451183215
2023-01-23 04:04:11.404395: step: 696/530, loss: 0.0030729295685887337
2023-01-23 04:04:12.537583: step: 700/530, loss: 1.5115738278836943e-05
2023-01-23 04:04:13.632278: step: 704/530, loss: 7.114410982467234e-05
2023-01-23 04:04:14.770810: step: 708/530, loss: 0.016547203063964844
2023-01-23 04:04:15.900021: step: 712/530, loss: 0.0819944441318512
2023-01-23 04:04:17.041981: step: 716/530, loss: 0.5335685014724731
2023-01-23 04:04:18.185193: step: 720/530, loss: 1.010894811770413e-05
2023-01-23 04:04:19.303106: step: 724/530, loss: 0.004232502076774836
2023-01-23 04:04:20.409709: step: 728/530, loss: 0.0004566192510537803
2023-01-23 04:04:21.519407: step: 732/530, loss: 0.0017559051048010588
2023-01-23 04:04:22.640801: step: 736/530, loss: 0.00017194748215842992
2023-01-23 04:04:23.752074: step: 740/530, loss: 2.498626781743951e-05
2023-01-23 04:04:24.847676: step: 744/530, loss: 2.28881845032447e-06
2023-01-23 04:04:25.949817: step: 748/530, loss: 0.0025947571266442537
2023-01-23 04:04:27.010982: step: 752/530, loss: 0.00017938614473678172
2023-01-23 04:04:28.115741: step: 756/530, loss: 1.068115216185106e-05
2023-01-23 04:04:29.229128: step: 760/530, loss: 4.615783836925402e-05
2023-01-23 04:04:30.328640: step: 764/530, loss: 1.9264220100012608e-05
2023-01-23 04:04:31.438349: step: 768/530, loss: 5.264282663119957e-05
2023-01-23 04:04:32.596285: step: 772/530, loss: 0.00030498503474518657
2023-01-23 04:04:33.747672: step: 776/530, loss: 0.0012316711945459247
2023-01-23 04:04:34.880345: step: 780/530, loss: 0.020836448296904564
2023-01-23 04:04:36.008710: step: 784/530, loss: 0.020872116088867188
2023-01-23 04:04:37.161774: step: 788/530, loss: 0.01145782507956028
2023-01-23 04:04:38.290539: step: 792/530, loss: 5.614757537841797e-05
2023-01-23 04:04:39.420833: step: 796/530, loss: 0.0015381812117993832
2023-01-23 04:04:40.523286: step: 800/530, loss: 0.005966472905129194
2023-01-23 04:04:41.655929: step: 804/530, loss: 0.04548397287726402
2023-01-23 04:04:42.799701: step: 808/530, loss: 5.645752025884576e-05
2023-01-23 04:04:43.909933: step: 812/530, loss: 0.025250960141420364
2023-01-23 04:04:45.036767: step: 816/530, loss: 0.0008625984191894531
2023-01-23 04:04:46.179425: step: 820/530, loss: 0.01715412177145481
2023-01-23 04:04:47.301292: step: 824/530, loss: 0.0003951072576455772
2023-01-23 04:04:48.434965: step: 828/530, loss: 0.0012468575732782483
2023-01-23 04:04:49.572399: step: 832/530, loss: 0.1317061483860016
2023-01-23 04:04:50.700556: step: 836/530, loss: 0.00038466454134322703
2023-01-23 04:04:51.805490: step: 840/530, loss: 0.0006875991821289062
2023-01-23 04:04:52.935494: step: 844/530, loss: 0.011688805185258389
2023-01-23 04:04:54.114297: step: 848/530, loss: 0.013722610659897327
2023-01-23 04:04:55.243430: step: 852/530, loss: 0.0010877609020099044
2023-01-23 04:04:56.376352: step: 856/530, loss: 0.0003499865415506065
2023-01-23 04:04:57.483344: step: 860/530, loss: 0.0004296302795410156
2023-01-23 04:04:58.594694: step: 864/530, loss: 0.007331180851906538
2023-01-23 04:04:59.760839: step: 868/530, loss: 0.0002984285238198936
2023-01-23 04:05:00.867128: step: 872/530, loss: 0.0015621185302734375
2023-01-23 04:05:01.995309: step: 876/530, loss: 0.03164386749267578
2023-01-23 04:05:03.138193: step: 880/530, loss: 0.0001636505185160786
2023-01-23 04:05:04.313902: step: 884/530, loss: 0.008465575985610485
2023-01-23 04:05:05.457439: step: 888/530, loss: 0.007383919321000576
2023-01-23 04:05:06.544961: step: 892/530, loss: 0.005424213595688343
2023-01-23 04:05:07.660238: step: 896/530, loss: 8.96453857421875e-05
2023-01-23 04:05:08.794595: step: 900/530, loss: 0.000993442488834262
2023-01-23 04:05:09.923400: step: 904/530, loss: 0.015662193298339844
2023-01-23 04:05:11.039124: step: 908/530, loss: 0.005560874938964844
2023-01-23 04:05:12.155265: step: 912/530, loss: 0.010552024468779564
2023-01-23 04:05:13.288931: step: 916/530, loss: 0.00017433166794944555
2023-01-23 04:05:14.423281: step: 920/530, loss: 0.06706476956605911
2023-01-23 04:05:15.524512: step: 924/530, loss: 0.0013353824615478516
2023-01-23 04:05:16.669013: step: 928/530, loss: 1.983642505365424e-05
2023-01-23 04:05:17.806104: step: 932/530, loss: 0.0017625809414312243
2023-01-23 04:05:18.916298: step: 936/530, loss: 0.0002804756222758442
2023-01-23 04:05:20.065702: step: 940/530, loss: 0.00341205601580441
2023-01-23 04:05:21.185177: step: 944/530, loss: 0.002634239150211215
2023-01-23 04:05:22.270763: step: 948/530, loss: 0.014643574133515358
2023-01-23 04:05:23.386054: step: 952/530, loss: 0.0036361694801598787
2023-01-23 04:05:24.512394: step: 956/530, loss: 0.01740856096148491
2023-01-23 04:05:25.623615: step: 960/530, loss: 0.00014095305232331157
2023-01-23 04:05:26.733290: step: 964/530, loss: 0.056245993822813034
2023-01-23 04:05:27.860643: step: 968/530, loss: 0.03258171305060387
2023-01-23 04:05:28.997204: step: 972/530, loss: 0.017430592328310013
2023-01-23 04:05:30.111379: step: 976/530, loss: 0.02619628794491291
2023-01-23 04:05:31.224509: step: 980/530, loss: 0.0001300811709370464
2023-01-23 04:05:32.336075: step: 984/530, loss: 0.10193977504968643
2023-01-23 04:05:33.467353: step: 988/530, loss: 0.00136146554723382
2023-01-23 04:05:34.613575: step: 992/530, loss: 0.004538345150649548
2023-01-23 04:05:35.728984: step: 996/530, loss: 0.0016731263604015112
2023-01-23 04:05:36.838715: step: 1000/530, loss: -1.7166138377433526e-06
2023-01-23 04:05:37.959226: step: 1004/530, loss: 0.013771867379546165
2023-01-23 04:05:39.071031: step: 1008/530, loss: 0.07266059517860413
2023-01-23 04:05:40.218877: step: 1012/530, loss: 0.001842546509578824
2023-01-23 04:05:41.363735: step: 1016/530, loss: 0.0002815246698446572
2023-01-23 04:05:42.483264: step: 1020/530, loss: 4.854202416026965e-05
2023-01-23 04:05:43.643619: step: 1024/530, loss: 0.005524826236069202
2023-01-23 04:05:44.745723: step: 1028/530, loss: 0.05985851213335991
2023-01-23 04:05:45.853689: step: 1032/530, loss: 0.0035312653053551912
2023-01-23 04:05:46.959705: step: 1036/530, loss: 0.0004207015153951943
2023-01-23 04:05:48.071968: step: 1040/530, loss: 0.03308238834142685
2023-01-23 04:05:49.185667: step: 1044/530, loss: 0.13214130699634552
2023-01-23 04:05:50.309644: step: 1048/530, loss: 0.005187607370316982
2023-01-23 04:05:51.468328: step: 1052/530, loss: 0.0027896880637854338
2023-01-23 04:05:52.575566: step: 1056/530, loss: 0.03146076202392578
2023-01-23 04:05:53.709849: step: 1060/530, loss: 7.896423630882055e-05
2023-01-23 04:05:54.849146: step: 1064/530, loss: 0.0002637862926349044
2023-01-23 04:05:55.962538: step: 1068/530, loss: 0.015247821807861328
2023-01-23 04:05:57.092153: step: 1072/530, loss: 0.01875896565616131
2023-01-23 04:05:58.249313: step: 1076/530, loss: 0.011057281866669655
2023-01-23 04:05:59.341016: step: 1080/530, loss: 0.00037031175452284515
2023-01-23 04:06:00.446644: step: 1084/530, loss: 1.2779236385540571e-05
2023-01-23 04:06:01.583194: step: 1088/530, loss: 0.005370521917939186
2023-01-23 04:06:02.702288: step: 1092/530, loss: 0.0018253326416015625
2023-01-23 04:06:03.826867: step: 1096/530, loss: 0.0002666473446879536
2023-01-23 04:06:04.954293: step: 1100/530, loss: 0.00074090959969908
2023-01-23 04:06:06.065492: step: 1104/530, loss: 0.00038595200749114156
2023-01-23 04:06:07.179860: step: 1108/530, loss: 0.0001293182431254536
2023-01-23 04:06:08.317374: step: 1112/530, loss: 0.006157493684440851
2023-01-23 04:06:09.446697: step: 1116/530, loss: 0.01682724989950657
2023-01-23 04:06:10.566446: step: 1120/530, loss: 0.0002501726266928017
2023-01-23 04:06:11.696010: step: 1124/530, loss: 0.013865041546523571
2023-01-23 04:06:12.811757: step: 1128/530, loss: 0.009752177633345127
2023-01-23 04:06:13.911383: step: 1132/530, loss: 0.030916595831513405
2023-01-23 04:06:15.051660: step: 1136/530, loss: 0.0061159138567745686
2023-01-23 04:06:16.184950: step: 1140/530, loss: 0.0012445449829101562
2023-01-23 04:06:17.342465: step: 1144/530, loss: 0.010038471780717373
2023-01-23 04:06:18.483232: step: 1148/530, loss: 0.0036173821426928043
2023-01-23 04:06:19.611663: step: 1152/530, loss: 0.004916477017104626
2023-01-23 04:06:20.763501: step: 1156/530, loss: 0.006425237748771906
2023-01-23 04:06:21.858917: step: 1160/530, loss: 0.011096763424575329
2023-01-23 04:06:22.972150: step: 1164/530, loss: 0.042576029896736145
2023-01-23 04:06:24.085239: step: 1168/530, loss: 1.6689300537109375e-05
2023-01-23 04:06:25.211049: step: 1172/530, loss: 0.0052394866943359375
2023-01-23 04:06:26.339305: step: 1176/530, loss: 0.0002004623383982107
2023-01-23 04:06:27.452904: step: 1180/530, loss: 0.005846595391631126
2023-01-23 04:06:28.592737: step: 1184/530, loss: 0.017639541998505592
2023-01-23 04:06:29.709116: step: 1188/530, loss: 6.86645489622606e-06
2023-01-23 04:06:30.832088: step: 1192/530, loss: 0.0014862060779705644
2023-01-23 04:06:31.980706: step: 1196/530, loss: 8.58306884765625e-06
2023-01-23 04:06:33.121867: step: 1200/530, loss: 0.00046100615873001516
2023-01-23 04:06:34.281739: step: 1204/530, loss: 0.0007658958784304559
2023-01-23 04:06:35.396011: step: 1208/530, loss: 0.00031156541081145406
2023-01-23 04:06:36.545604: step: 1212/530, loss: 1.8119812921213452e-06
2023-01-23 04:06:37.700224: step: 1216/530, loss: 0.10358409583568573
2023-01-23 04:06:38.849284: step: 1220/530, loss: 0.000763368618208915
2023-01-23 04:06:39.993271: step: 1224/530, loss: 0.04680747911334038
2023-01-23 04:06:41.132276: step: 1228/530, loss: 0.014463615603744984
2023-01-23 04:06:42.246388: step: 1232/530, loss: 6.027221752447076e-05
2023-01-23 04:06:43.388641: step: 1236/530, loss: 0.022798538208007812
2023-01-23 04:06:44.490029: step: 1240/530, loss: 0.0004942893865518272
2023-01-23 04:06:45.637786: step: 1244/530, loss: 9.741782560013235e-05
2023-01-23 04:06:46.765041: step: 1248/530, loss: 0.007168960757553577
2023-01-23 04:06:47.879163: step: 1252/530, loss: 0.0031770707573741674
2023-01-23 04:06:48.984921: step: 1256/530, loss: 0.002415275666862726
2023-01-23 04:06:50.096717: step: 1260/530, loss: 0.00013618469529319555
2023-01-23 04:06:51.236744: step: 1264/530, loss: 0.00024662018404342234
2023-01-23 04:06:52.360019: step: 1268/530, loss: 0.0018333435291424394
2023-01-23 04:06:53.482309: step: 1272/530, loss: 0.0004924774402752519
2023-01-23 04:06:54.624940: step: 1276/530, loss: 0.16675598919391632
2023-01-23 04:06:55.744593: step: 1280/530, loss: 0.00046749116154387593
2023-01-23 04:06:56.887519: step: 1284/530, loss: 0.057106971740722656
2023-01-23 04:06:58.021784: step: 1288/530, loss: 0.0016298294067382812
2023-01-23 04:06:59.176468: step: 1292/530, loss: 8.296967280330136e-06
2023-01-23 04:07:00.300812: step: 1296/530, loss: 2.0980836779926904e-05
2023-01-23 04:07:01.425244: step: 1300/530, loss: 0.00020179747662041336
2023-01-23 04:07:02.566279: step: 1304/530, loss: 0.0008107185713015497
2023-01-23 04:07:03.714078: step: 1308/530, loss: 0.024582862854003906
2023-01-23 04:07:04.845259: step: 1312/530, loss: 0.003043937962502241
2023-01-23 04:07:05.981502: step: 1316/530, loss: 0.015055847354233265
2023-01-23 04:07:07.086777: step: 1320/530, loss: 0.003883600467815995
2023-01-23 04:07:08.229613: step: 1324/530, loss: 0.018159104511141777
2023-01-23 04:07:09.319953: step: 1328/530, loss: 1.735687328618951e-05
2023-01-23 04:07:10.411811: step: 1332/530, loss: 0.0008635520935058594
2023-01-23 04:07:11.528957: step: 1336/530, loss: 0.002245235489681363
2023-01-23 04:07:12.656542: step: 1340/530, loss: 0.009093952365219593
2023-01-23 04:07:13.790251: step: 1344/530, loss: 4.649162292480469e-05
2023-01-23 04:07:14.928624: step: 1348/530, loss: 6.599426706088707e-05
2023-01-23 04:07:16.055431: step: 1352/530, loss: 4.482269287109375e-05
2023-01-23 04:07:17.164087: step: 1356/530, loss: 0.015350389294326305
2023-01-23 04:07:18.276207: step: 1360/530, loss: 0.0002157211274607107
2023-01-23 04:07:19.420558: step: 1364/530, loss: 0.02983551099896431
2023-01-23 04:07:20.552010: step: 1368/530, loss: 0.007845520973205566
2023-01-23 04:07:21.669030: step: 1372/530, loss: 3.490447852527723e-05
2023-01-23 04:07:22.806276: step: 1376/530, loss: 0.00030803680419921875
2023-01-23 04:07:23.935427: step: 1380/530, loss: 0.001906585763208568
2023-01-23 04:07:25.056019: step: 1384/530, loss: 0.006847381591796875
2023-01-23 04:07:26.163475: step: 1388/530, loss: 6.027222116244957e-05
2023-01-23 04:07:27.267364: step: 1392/530, loss: 6.580352874152595e-06
2023-01-23 04:07:28.384638: step: 1396/530, loss: 5.626678466796875e-05
2023-01-23 04:07:29.517155: step: 1400/530, loss: 0.0010696888202801347
2023-01-23 04:07:30.654631: step: 1404/530, loss: 0.0048417565412819386
2023-01-23 04:07:31.777050: step: 1408/530, loss: 0.001983833499252796
2023-01-23 04:07:32.948928: step: 1412/530, loss: 0.010224675759673119
2023-01-23 04:07:34.090072: step: 1416/530, loss: 0.0007465362432412803
2023-01-23 04:07:35.209776: step: 1420/530, loss: 0.0054306029342114925
2023-01-23 04:07:36.339376: step: 1424/530, loss: 0.0017053603660315275
2023-01-23 04:07:37.470195: step: 1428/530, loss: 0.036640215665102005
2023-01-23 04:07:38.654947: step: 1432/530, loss: 4.291534423828125e-05
2023-01-23 04:07:39.771216: step: 1436/530, loss: 0.0002693176211323589
2023-01-23 04:07:40.864084: step: 1440/530, loss: 3.175735764671117e-05
2023-01-23 04:07:41.993123: step: 1444/530, loss: 9.956360008800402e-05
2023-01-23 04:07:43.131032: step: 1448/530, loss: 0.00011529923358466476
2023-01-23 04:07:44.280204: step: 1452/530, loss: 0.006119919009506702
2023-01-23 04:07:45.403720: step: 1456/530, loss: 3.986358569818549e-05
2023-01-23 04:07:46.512661: step: 1460/530, loss: 1.6689300537109375e-05
2023-01-23 04:07:47.638068: step: 1464/530, loss: 0.0012575149303302169
2023-01-23 04:07:48.719634: step: 1468/530, loss: 0.00020465851412154734
2023-01-23 04:07:49.876587: step: 1472/530, loss: 0.007644271943718195
2023-01-23 04:07:51.005224: step: 1476/530, loss: 0.0014940261607989669
2023-01-23 04:07:52.112527: step: 1480/530, loss: 0.0002783775271382183
2023-01-23 04:07:53.220212: step: 1484/530, loss: 2.7084352041129023e-05
2023-01-23 04:07:54.348188: step: 1488/530, loss: 5.664825584972277e-05
2023-01-23 04:07:55.476976: step: 1492/530, loss: 0.02048635482788086
2023-01-23 04:07:56.597657: step: 1496/530, loss: 0.0001255035458598286
2023-01-23 04:07:57.768314: step: 1500/530, loss: 0.006630897521972656
2023-01-23 04:07:58.889230: step: 1504/530, loss: 0.0014611243968829513
2023-01-23 04:08:00.033122: step: 1508/530, loss: 4.501342846197076e-05
2023-01-23 04:08:01.174723: step: 1512/530, loss: 0.03195362165570259
2023-01-23 04:08:02.324988: step: 1516/530, loss: 0.004269409459084272
2023-01-23 04:08:03.439561: step: 1520/530, loss: 0.00227699289098382
2023-01-23 04:08:04.558515: step: 1524/530, loss: 0.0019541741348803043
2023-01-23 04:08:05.664557: step: 1528/530, loss: 7.939338684082031e-05
2023-01-23 04:08:06.789176: step: 1532/530, loss: 4.301071385270916e-05
2023-01-23 04:08:07.920849: step: 1536/530, loss: 4.1961669921875e-05
2023-01-23 04:08:09.038000: step: 1540/530, loss: 9.403228614246473e-05
2023-01-23 04:08:10.157247: step: 1544/530, loss: 0.0020787238609045744
2023-01-23 04:08:11.274350: step: 1548/530, loss: 0.0001968383730854839
2023-01-23 04:08:12.390903: step: 1552/530, loss: 1.1157989320054185e-05
2023-01-23 04:08:13.512441: step: 1556/530, loss: 0.009734916500747204
2023-01-23 04:08:14.625373: step: 1560/530, loss: 0.0025604248512536287
2023-01-23 04:08:15.734696: step: 1564/530, loss: 0.22236642241477966
2023-01-23 04:08:16.838889: step: 1568/530, loss: 0.0002880096435546875
2023-01-23 04:08:17.959191: step: 1572/530, loss: 0.008819961920380592
2023-01-23 04:08:19.082073: step: 1576/530, loss: 0.019545985385775566
2023-01-23 04:08:20.191822: step: 1580/530, loss: 0.0009176731109619141
2023-01-23 04:08:21.282770: step: 1584/530, loss: 0.00021247864060569555
2023-01-23 04:08:22.428999: step: 1588/530, loss: 0.03221883997321129
2023-01-23 04:08:23.522718: step: 1592/530, loss: 0.03220844268798828
2023-01-23 04:08:24.651030: step: 1596/530, loss: 0.012983512133359909
2023-01-23 04:08:25.784357: step: 1600/530, loss: 8.640289161121473e-05
2023-01-23 04:08:26.904566: step: 1604/530, loss: 0.0003018379211425781
2023-01-23 04:08:28.029191: step: 1608/530, loss: 0.0004072189040016383
2023-01-23 04:08:29.159543: step: 1612/530, loss: 0.022624395787715912
2023-01-23 04:08:30.292068: step: 1616/530, loss: 0.046590711921453476
2023-01-23 04:08:31.396520: step: 1620/530, loss: 6.771087646484375e-05
2023-01-23 04:08:32.510001: step: 1624/530, loss: 0.0033524036407470703
2023-01-23 04:08:33.626916: step: 1628/530, loss: 0.007813072763383389
2023-01-23 04:08:34.744143: step: 1632/530, loss: 0.0018060685833916068
2023-01-23 04:08:35.891348: step: 1636/530, loss: 0.00040330886258743703
2023-01-23 04:08:36.996512: step: 1640/530, loss: 0.008052635006606579
2023-01-23 04:08:38.093631: step: 1644/530, loss: 1.1682344675064087
2023-01-23 04:08:39.235768: step: 1648/530, loss: 0.011875866912305355
2023-01-23 04:08:40.370883: step: 1652/530, loss: 0.03361182287335396
2023-01-23 04:08:41.475790: step: 1656/530, loss: 0.04020567238330841
2023-01-23 04:08:42.604395: step: 1660/530, loss: 0.0005714416620321572
2023-01-23 04:08:43.724189: step: 1664/530, loss: 0.0517704002559185
2023-01-23 04:08:44.844815: step: 1668/530, loss: 0.0002430439053568989
2023-01-23 04:08:45.952576: step: 1672/530, loss: 6.337166269076988e-05
2023-01-23 04:08:47.080696: step: 1676/530, loss: 0.037123870104551315
2023-01-23 04:08:48.172254: step: 1680/530, loss: 0.0031475068535655737
2023-01-23 04:08:49.315206: step: 1684/530, loss: 0.0074204448610544205
2023-01-23 04:08:50.401869: step: 1688/530, loss: 7.869302862673067e-06
2023-01-23 04:08:51.536354: step: 1692/530, loss: 0.007393646519631147
2023-01-23 04:08:52.648355: step: 1696/530, loss: 0.00017261505126953125
2023-01-23 04:08:53.773845: step: 1700/530, loss: 0.014226150698959827
2023-01-23 04:08:54.897504: step: 1704/530, loss: 9.860992577159777e-05
2023-01-23 04:08:56.005478: step: 1708/530, loss: 7.82012939453125e-05
2023-01-23 04:08:57.125853: step: 1712/530, loss: 0.00041618349496275187
2023-01-23 04:08:58.255738: step: 1716/530, loss: 0.02533740922808647
2023-01-23 04:08:59.372201: step: 1720/530, loss: 0.00488891638815403
2023-01-23 04:09:00.489857: step: 1724/530, loss: 0.016846656799316406
2023-01-23 04:09:01.620984: step: 1728/530, loss: 0.025334740057587624
2023-01-23 04:09:02.728124: step: 1732/530, loss: 0.0005181789165362716
2023-01-23 04:09:03.844660: step: 1736/530, loss: 0.012012195773422718
2023-01-23 04:09:04.957041: step: 1740/530, loss: 0.0005353927263058722
2023-01-23 04:09:06.109684: step: 1744/530, loss: 0.0018595695728436112
2023-01-23 04:09:07.199654: step: 1748/530, loss: 0.00014209745859261602
2023-01-23 04:09:08.327031: step: 1752/530, loss: 0.02372569963335991
2023-01-23 04:09:09.419274: step: 1756/530, loss: 0.019558431580662727
2023-01-23 04:09:10.511951: step: 1760/530, loss: 0.0005163192981854081
2023-01-23 04:09:11.600873: step: 1764/530, loss: 0.003431129502132535
2023-01-23 04:09:12.738067: step: 1768/530, loss: 0.025853728875517845
2023-01-23 04:09:13.862358: step: 1772/530, loss: 0.0009540558094158769
2023-01-23 04:09:14.980654: step: 1776/530, loss: 6.198883056640625e-05
2023-01-23 04:09:16.098094: step: 1780/530, loss: 0.0013238907558843493
2023-01-23 04:09:17.249934: step: 1784/530, loss: 0.0002556800900492817
2023-01-23 04:09:18.355646: step: 1788/530, loss: 0.00785675086081028
2023-01-23 04:09:19.499452: step: 1792/530, loss: 0.003692626953125
2023-01-23 04:09:20.617350: step: 1796/530, loss: 0.0002907276211772114
2023-01-23 04:09:21.688978: step: 1800/530, loss: 0.001292371773160994
2023-01-23 04:09:22.837294: step: 1804/530, loss: 0.06846971809864044
2023-01-23 04:09:23.979880: step: 1808/530, loss: 0.005768203642219305
2023-01-23 04:09:25.131869: step: 1812/530, loss: 0.0014713286655023694
2023-01-23 04:09:26.251024: step: 1816/530, loss: 0.005811834707856178
2023-01-23 04:09:27.392940: step: 1820/530, loss: 0.03165092691779137
2023-01-23 04:09:28.493346: step: 1824/530, loss: 0.0002092361537506804
2023-01-23 04:09:29.624278: step: 1828/530, loss: 0.027503110468387604
2023-01-23 04:09:30.747036: step: 1832/530, loss: 0.00041007998515851796
2023-01-23 04:09:31.881239: step: 1836/530, loss: 0.0001643180730752647
2023-01-23 04:09:32.974053: step: 1840/530, loss: 0.00012750625319313258
2023-01-23 04:09:34.091943: step: 1844/530, loss: 0.02797517739236355
2023-01-23 04:09:35.221168: step: 1848/530, loss: -7.247924258990679e-06
2023-01-23 04:09:36.363192: step: 1852/530, loss: 0.03835906833410263
2023-01-23 04:09:37.479073: step: 1856/530, loss: 0.00023431777663063258
2023-01-23 04:09:38.587666: step: 1860/530, loss: 0.0013417245354503393
2023-01-23 04:09:39.712936: step: 1864/530, loss: 0.00025243760319426656
2023-01-23 04:09:40.899481: step: 1868/530, loss: 0.592681348323822
2023-01-23 04:09:42.008680: step: 1872/530, loss: 4.363059997558594e-05
2023-01-23 04:09:43.125451: step: 1876/530, loss: 0.00028705596923828125
2023-01-23 04:09:44.236810: step: 1880/530, loss: 0.0006261825328692794
2023-01-23 04:09:45.402583: step: 1884/530, loss: 0.0007724761962890625
2023-01-23 04:09:46.531143: step: 1888/530, loss: 0.005222320556640625
2023-01-23 04:09:47.685797: step: 1892/530, loss: 0.0003673553583212197
2023-01-23 04:09:48.836431: step: 1896/530, loss: 0.0006048202631063759
2023-01-23 04:09:49.939479: step: 1900/530, loss: 0.0020086290314793587
2023-01-23 04:09:51.094000: step: 1904/530, loss: 0.0031676292419433594
2023-01-23 04:09:52.221979: step: 1908/530, loss: 0.0010183334816247225
2023-01-23 04:09:53.315886: step: 1912/530, loss: 0.01344757154583931
2023-01-23 04:09:54.443246: step: 1916/530, loss: -1.3828277587890625e-05
2023-01-23 04:09:55.578908: step: 1920/530, loss: 0.0010087013943120837
2023-01-23 04:09:56.720069: step: 1924/530, loss: 0.007440090179443359
2023-01-23 04:09:57.822104: step: 1928/530, loss: 0.004156017675995827
2023-01-23 04:09:58.954278: step: 1932/530, loss: 0.11128578335046768
2023-01-23 04:10:00.083755: step: 1936/530, loss: 0.0009811401832848787
2023-01-23 04:10:01.228353: step: 1940/530, loss: 0.00010204315913142636
2023-01-23 04:10:02.367006: step: 1944/530, loss: 0.006575584877282381
2023-01-23 04:10:03.506932: step: 1948/530, loss: 1.100994348526001
2023-01-23 04:10:04.643888: step: 1952/530, loss: 0.000194549560546875
2023-01-23 04:10:05.764279: step: 1956/530, loss: 0.026674749329686165
2023-01-23 04:10:06.918317: step: 1960/530, loss: 0.0002344131498830393
2023-01-23 04:10:08.066951: step: 1964/530, loss: 0.15680675208568573
2023-01-23 04:10:09.212138: step: 1968/530, loss: 0.00011682510375976562
2023-01-23 04:10:10.331590: step: 1972/530, loss: 0.00018057823763228953
2023-01-23 04:10:11.442587: step: 1976/530, loss: 0.01435403898358345
2023-01-23 04:10:12.568902: step: 1980/530, loss: 0.02198333665728569
2023-01-23 04:10:13.715783: step: 1984/530, loss: 0.00907211285084486
2023-01-23 04:10:14.866710: step: 1988/530, loss: 0.0008563041919842362
2023-01-23 04:10:16.016296: step: 1992/530, loss: 0.022344589233398438
2023-01-23 04:10:17.156588: step: 1996/530, loss: 0.00015454292588401586
2023-01-23 04:10:18.315800: step: 2000/530, loss: 5.378723290050402e-05
2023-01-23 04:10:19.435565: step: 2004/530, loss: 0.0005068778991699219
2023-01-23 04:10:20.549589: step: 2008/530, loss: 0.00240325927734375
2023-01-23 04:10:21.690438: step: 2012/530, loss: 0.35337141156196594
2023-01-23 04:10:22.801652: step: 2016/530, loss: 0.0015651703579351306
2023-01-23 04:10:23.917591: step: 2020/530, loss: 0.00012373924255371094
2023-01-23 04:10:25.010518: step: 2024/530, loss: 7.743835885776207e-05
2023-01-23 04:10:26.147382: step: 2028/530, loss: 0.01382293738424778
2023-01-23 04:10:27.285332: step: 2032/530, loss: 0.0010234832298010588
2023-01-23 04:10:28.436791: step: 2036/530, loss: 0.00421638460829854
2023-01-23 04:10:29.535765: step: 2040/530, loss: 4.968643406755291e-05
2023-01-23 04:10:30.701172: step: 2044/530, loss: 0.016026116907596588
2023-01-23 04:10:31.858815: step: 2048/530, loss: 0.0012573242420330644
2023-01-23 04:10:32.985023: step: 2052/530, loss: 0.0010458945762366056
2023-01-23 04:10:34.124166: step: 2056/530, loss: 8.640289161121473e-05
2023-01-23 04:10:35.216851: step: 2060/530, loss: 0.0007375717395916581
2023-01-23 04:10:36.337019: step: 2064/530, loss: 0.0022235752549022436
2023-01-23 04:10:37.459990: step: 2068/530, loss: 0.009613800793886185
2023-01-23 04:10:38.612898: step: 2072/530, loss: 0.2942659258842468
2023-01-23 04:10:39.737353: step: 2076/530, loss: 0.002518558641895652
2023-01-23 04:10:40.859065: step: 2080/530, loss: 3.0994415283203125e-05
2023-01-23 04:10:41.970504: step: 2084/530, loss: 0.007765007205307484
2023-01-23 04:10:43.072842: step: 2088/530, loss: 0.0009613037109375
2023-01-23 04:10:44.176978: step: 2092/530, loss: -5.626678102998994e-06
2023-01-23 04:10:45.299621: step: 2096/530, loss: 0.015579604543745518
2023-01-23 04:10:46.415785: step: 2100/530, loss: 0.016611386090517044
2023-01-23 04:10:47.559562: step: 2104/530, loss: 0.0009471416706219316
2023-01-23 04:10:48.712100: step: 2108/530, loss: 0.02815227583050728
2023-01-23 04:10:49.840639: step: 2112/530, loss: 0.014848137274384499
2023-01-23 04:10:50.984266: step: 2116/530, loss: 0.0022672652266919613
2023-01-23 04:10:52.101204: step: 2120/530, loss: 6.704330735374242e-05
==================================================
Loss: 0.021
--------------------
Dev: {'event': {'p': 0.6043715846994535, 'r': 0.7363515312916112, 'f1': 0.6638655462184874}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
Test: {'event': {'p': 0.6399622997172478, 'r': 0.776, 'f1': 0.7014462809917356}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
Chinese: {'event': {'p': 0.6533333333333333, 'r': 0.9074074074074074, 'f1': 0.7596899224806202}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
Korean: {'event': {'p': 0.7272727272727273, 'r': 0.5079365079365079, 'f1': 0.5981308411214953}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
Russian: {'event': {'p': 0.43902439024390244, 'r': 0.5, 'f1': 0.4675324675324676}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
New best chinese model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6043715846994535, 'r': 0.7363515312916112, 'f1': 0.6638655462184874}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
Eng Test for Chinese: {'event': {'p': 0.6399622997172478, 'r': 0.776, 'f1': 0.7014462809917356}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
Sample Chinese: {'event': {'p': 0.6533333333333333, 'r': 0.9074074074074074, 'f1': 0.7596899224806202}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6288770053475936, 'r': 0.7829560585885486, 'f1': 0.697508896797153}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Korean: {'event': {'p': 0.64058795637743, 'r': 0.772, 'f1': 0.7001813941435606}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Korean: {'event': {'p': 0.6851851851851852, 'r': 0.5873015873015873, 'f1': 0.6324786324786325}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5319148936170213, 'r': 0.6944444444444444, 'f1': 0.6024096385542169}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
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 04:11:37.494229: step: 4/530, loss: 1.33514404296875e-05
2023-01-23 04:11:38.625300: step: 8/530, loss: 0.0006963729974813759
2023-01-23 04:11:39.799934: step: 12/530, loss: 8.106231689453125e-05
2023-01-23 04:11:40.918026: step: 16/530, loss: 1.468658410885837e-05
2023-01-23 04:11:42.046779: step: 20/530, loss: 0.0013601303799077868
2023-01-23 04:11:43.165445: step: 24/530, loss: 0.0007113456376828253
2023-01-23 04:11:44.315701: step: 28/530, loss: 0.00274486537091434
2023-01-23 04:11:45.455388: step: 32/530, loss: -2.670288040462765e-06
2023-01-23 04:11:46.595909: step: 36/530, loss: 0.00011882781836902723
2023-01-23 04:11:47.768109: step: 40/530, loss: 0.005424118135124445
2023-01-23 04:11:48.842515: step: 44/530, loss: -9.5367431640625e-07
2023-01-23 04:11:49.986852: step: 48/530, loss: 0.00010614395432639867
2023-01-23 04:11:51.099387: step: 52/530, loss: 0.0004831314436160028
2023-01-23 04:11:52.208178: step: 56/530, loss: 0.014301871880888939
2023-01-23 04:11:53.323200: step: 60/530, loss: 0.000858306884765625
2023-01-23 04:11:54.443070: step: 64/530, loss: 0.0006476402631960809
2023-01-23 04:11:55.570023: step: 68/530, loss: 0.003938865382224321
2023-01-23 04:11:56.707128: step: 72/530, loss: 0.00041408539982512593
2023-01-23 04:11:57.829246: step: 76/530, loss: 4.76837158203125e-05
2023-01-23 04:11:58.990404: step: 80/530, loss: 0.0008131027570925653
2023-01-23 04:12:00.131667: step: 84/530, loss: 0.0008766173850744963
2023-01-23 04:12:01.229951: step: 88/530, loss: 0.04265327379107475
2023-01-23 04:12:02.343733: step: 92/530, loss: 0.036463167518377304
2023-01-23 04:12:03.487286: step: 96/530, loss: 0.0019070626003667712
2023-01-23 04:12:04.616498: step: 100/530, loss: 0.0002019882231252268
2023-01-23 04:12:05.727572: step: 104/530, loss: 0.0002971649228129536
2023-01-23 04:12:06.846893: step: 108/530, loss: 0.016480350866913795
2023-01-23 04:12:07.974006: step: 112/530, loss: 0.00013418197340797633
2023-01-23 04:12:09.135978: step: 116/530, loss: 0.011288833804428577
2023-01-23 04:12:10.247026: step: 120/530, loss: 0.00025691985501907766
2023-01-23 04:12:11.377588: step: 124/530, loss: 0.00043830869253724813
2023-01-23 04:12:12.489512: step: 128/530, loss: 0.07729263603687286
2023-01-23 04:12:13.606786: step: 132/530, loss: -5.14984139954322e-06
2023-01-23 04:12:14.756868: step: 136/530, loss: 0.02654714696109295
2023-01-23 04:12:15.861426: step: 140/530, loss: 0.00045671462430618703
2023-01-23 04:12:16.967266: step: 144/530, loss: 1.1825562069134321e-05
2023-01-23 04:12:18.098011: step: 148/530, loss: 3.4809112548828125e-05
2023-01-23 04:12:19.223865: step: 152/530, loss: 7.266998727573082e-05
2023-01-23 04:12:20.343181: step: 156/530, loss: 0.016576863825321198
2023-01-23 04:12:21.483891: step: 160/530, loss: 0.0014238357543945312
2023-01-23 04:12:22.604448: step: 164/530, loss: 7.62939453125e-06
2023-01-23 04:12:23.739580: step: 168/530, loss: 0.0010342597961425781
2023-01-23 04:12:24.868326: step: 172/530, loss: 0.0012835502857342362
2023-01-23 04:12:26.013145: step: 176/530, loss: 0.005591964814811945
2023-01-23 04:12:27.133711: step: 180/530, loss: 0.00033483505831100047
2023-01-23 04:12:28.275947: step: 184/530, loss: 0.0006264210096560419
2023-01-23 04:12:29.398542: step: 188/530, loss: 9.803772263694555e-05
2023-01-23 04:12:30.505890: step: 192/530, loss: 2.28881845032447e-06
2023-01-23 04:12:31.607291: step: 196/530, loss: 0.00018615723820403218
2023-01-23 04:12:32.741265: step: 200/530, loss: 0.2512466311454773
2023-01-23 04:12:33.843493: step: 204/530, loss: 0.00427856482565403
2023-01-23 04:12:34.969295: step: 208/530, loss: 0.00813751295208931
2023-01-23 04:12:36.085679: step: 212/530, loss: 0.0011535644298419356
2023-01-23 04:12:37.239222: step: 216/530, loss: 0.00887308083474636
2023-01-23 04:12:38.355416: step: 220/530, loss: 5.588532076217234e-05
2023-01-23 04:12:39.481869: step: 224/530, loss: 0.0004654884396586567
2023-01-23 04:12:40.632203: step: 228/530, loss: 0.014969062991440296
2023-01-23 04:12:41.758424: step: 232/530, loss: 0.011599540710449219
2023-01-23 04:12:42.869232: step: 236/530, loss: 0.0003757476806640625
2023-01-23 04:12:43.997919: step: 240/530, loss: 0.0004986763233318925
2023-01-23 04:12:45.123932: step: 244/530, loss: 0.001185464789159596
2023-01-23 04:12:46.285055: step: 248/530, loss: 0.0018226623069494963
2023-01-23 04:12:47.401621: step: 252/530, loss: 1.544952465337701e-05
2023-01-23 04:12:48.521348: step: 256/530, loss: 0.0035889626014977694
2023-01-23 04:12:49.632146: step: 260/530, loss: 0.0015499115688726306
2023-01-23 04:12:50.767873: step: 264/530, loss: 0.0005758285406045616
2023-01-23 04:12:51.908845: step: 268/530, loss: 0.05413246527314186
2023-01-23 04:12:53.048268: step: 272/530, loss: 0.029965590685606003
2023-01-23 04:12:54.169933: step: 276/530, loss: 0.00231170654296875
2023-01-23 04:12:55.335632: step: 280/530, loss: 0.0001237869291799143
2023-01-23 04:12:56.468564: step: 284/530, loss: 4.08649466407951e-05
2023-01-23 04:12:57.572722: step: 288/530, loss: 0.00018892288790084422
2023-01-23 04:12:58.692343: step: 292/530, loss: 0.0002837181091308594
2023-01-23 04:12:59.845943: step: 296/530, loss: 0.0016630173195153475
2023-01-23 04:13:00.976605: step: 300/530, loss: 0.00010814666893566027
2023-01-23 04:13:02.103902: step: 304/530, loss: 5.626678830594756e-05
2023-01-23 04:13:03.216645: step: 308/530, loss: 0.01047420408576727
2023-01-23 04:13:04.359301: step: 312/530, loss: 0.023032475262880325
2023-01-23 04:13:05.463055: step: 316/530, loss: 7.329694926738739e-05
2023-01-23 04:13:06.563449: step: 320/530, loss: 3.623962356869015e-06
2023-01-23 04:13:07.694934: step: 324/530, loss: 0.0005151748191565275
2023-01-23 04:13:08.829628: step: 328/530, loss: 1.9073486328125e-05
2023-01-23 04:13:09.951751: step: 332/530, loss: 0.00022001266188453883
2023-01-23 04:13:11.059098: step: 336/530, loss: 6.794929504394531e-05
2023-01-23 04:13:12.184600: step: 340/530, loss: 9.260177466785535e-05
2023-01-23 04:13:13.316827: step: 344/530, loss: -4.100799742445815e-06
2023-01-23 04:13:14.447642: step: 348/530, loss: 0.00023689270892646164
2023-01-23 04:13:15.569627: step: 352/530, loss: 0.2725982367992401
2023-01-23 04:13:16.733728: step: 356/530, loss: 0.009602928534150124
2023-01-23 04:13:17.874854: step: 360/530, loss: 0.00011196136620128527
2023-01-23 04:13:18.984764: step: 364/530, loss: 0.0019847869407385588
2023-01-23 04:13:20.123810: step: 368/530, loss: 0.04716377332806587
2023-01-23 04:13:21.243074: step: 372/530, loss: 7.109642319846898e-05
2023-01-23 04:13:22.395999: step: 376/530, loss: 0.012071800418198109
2023-01-23 04:13:23.507022: step: 380/530, loss: 0.006669044494628906
2023-01-23 04:13:24.603215: step: 384/530, loss: 1.2779236385540571e-05
2023-01-23 04:13:25.735591: step: 388/530, loss: 0.0006935119163244963
2023-01-23 04:13:26.849718: step: 392/530, loss: 0.0005155563703738153
2023-01-23 04:13:27.952275: step: 396/530, loss: 3.919601658708416e-05
2023-01-23 04:13:29.061556: step: 400/530, loss: 0.0006895065307617188
2023-01-23 04:13:30.180131: step: 404/530, loss: 0.0009504318004474044
2023-01-23 04:13:31.299508: step: 408/530, loss: 0.00612220773473382
2023-01-23 04:13:32.453148: step: 412/530, loss: 0.01459961012005806
2023-01-23 04:13:33.548062: step: 416/530, loss: 2.0503998712229077e-06
2023-01-23 04:13:34.693969: step: 420/530, loss: 2.632141149661038e-05
2023-01-23 04:13:35.803617: step: 424/530, loss: 0.04956674948334694
2023-01-23 04:13:36.942347: step: 428/530, loss: 0.0017950058681890368
2023-01-23 04:13:38.052342: step: 432/530, loss: 2.2602082026423886e-05
2023-01-23 04:13:39.180255: step: 436/530, loss: 0.03938550874590874
2023-01-23 04:13:40.279665: step: 440/530, loss: 0.0003044128243345767
2023-01-23 04:13:41.419837: step: 444/530, loss: 0.0059951781295239925
2023-01-23 04:13:42.549362: step: 448/530, loss: 0.08512478321790695
2023-01-23 04:13:43.670918: step: 452/530, loss: 0.0013339996803551912
2023-01-23 04:13:44.784337: step: 456/530, loss: 0.001003265380859375
2023-01-23 04:13:45.915760: step: 460/530, loss: 1.5544890629826114e-05
2023-01-23 04:13:47.064139: step: 464/530, loss: 0.024083424359560013
2023-01-23 04:13:48.228156: step: 468/530, loss: 0.00010147094872081652
2023-01-23 04:13:49.360540: step: 472/530, loss: 7.152557373046875e-05
2023-01-23 04:13:50.498409: step: 476/530, loss: 0.6749169230461121
2023-01-23 04:13:51.591094: step: 480/530, loss: 0.0012912750244140625
2023-01-23 04:13:52.714158: step: 484/530, loss: 5.359650094760582e-05
2023-01-23 04:13:53.858075: step: 488/530, loss: 7.45773286325857e-05
2023-01-23 04:13:54.979761: step: 492/530, loss: 1.8596649169921875e-05
2023-01-23 04:13:56.106371: step: 496/530, loss: 0.00033702849759720266
2023-01-23 04:13:57.249709: step: 500/530, loss: 0.00029392243595793843
2023-01-23 04:13:58.358848: step: 504/530, loss: 0.006906700320541859
2023-01-23 04:13:59.463808: step: 508/530, loss: 0.000682449375744909
2023-01-23 04:14:00.605730: step: 512/530, loss: 0.04250946268439293
2023-01-23 04:14:01.750993: step: 516/530, loss: 0.0003803253057412803
2023-01-23 04:14:02.884185: step: 520/530, loss: 0.007968425750732422
2023-01-23 04:14:03.998074: step: 524/530, loss: 0.010615348815917969
2023-01-23 04:14:05.132844: step: 528/530, loss: 0.0003717422659974545
2023-01-23 04:14:06.257135: step: 532/530, loss: 1.6951562429312617e-05
2023-01-23 04:14:07.358850: step: 536/530, loss: 0.0012248038547113538
2023-01-23 04:14:08.498350: step: 540/530, loss: 6.637573096668348e-05
2023-01-23 04:14:09.622614: step: 544/530, loss: -6.103515261202119e-06
2023-01-23 04:14:10.744085: step: 548/530, loss: 6.48498553346144e-06
2023-01-23 04:14:11.833617: step: 552/530, loss: 0.016333866864442825
2023-01-23 04:14:12.973340: step: 556/530, loss: 0.00010395050048828125
2023-01-23 04:14:14.058509: step: 560/530, loss: 0.00030040740966796875
2023-01-23 04:14:15.180503: step: 564/530, loss: 0.0024424553848803043
2023-01-23 04:14:16.313797: step: 568/530, loss: 0.0011411666637286544
2023-01-23 04:14:17.429382: step: 572/530, loss: 0.000148773193359375
2023-01-23 04:14:18.530605: step: 576/530, loss: 8.850097219692543e-05
2023-01-23 04:14:19.649227: step: 580/530, loss: 0.0018905639881268144
2023-01-23 04:14:20.795821: step: 584/530, loss: 0.0012067795032635331
2023-01-23 04:14:21.927502: step: 588/530, loss: 0.00014162063598632812
2023-01-23 04:14:23.047436: step: 592/530, loss: -2.2888182229507947e-06
2023-01-23 04:14:24.182662: step: 596/530, loss: 0.019003773108124733
2023-01-23 04:14:25.297497: step: 600/530, loss: 0.0006348610040731728
2023-01-23 04:14:26.436787: step: 604/530, loss: 0.005875587463378906
2023-01-23 04:14:27.583213: step: 608/530, loss: 1.9359587895451114e-05
2023-01-23 04:14:28.699037: step: 612/530, loss: 0.033556174486875534
2023-01-23 04:14:29.835955: step: 616/530, loss: 8.115769014693797e-05
2023-01-23 04:14:31.000736: step: 620/530, loss: 0.014732694253325462
2023-01-23 04:14:32.154395: step: 624/530, loss: 0.0006362915155477822
2023-01-23 04:14:33.281587: step: 628/530, loss: 0.0014026642311364412
2023-01-23 04:14:34.429364: step: 632/530, loss: 0.0003367900790181011
2023-01-23 04:14:35.554160: step: 636/530, loss: 0.012792778201401234
2023-01-23 04:14:36.661955: step: 640/530, loss: 0.027961159124970436
2023-01-23 04:14:37.794375: step: 644/530, loss: 0.00618248013779521
2023-01-23 04:14:38.933413: step: 648/530, loss: 0.0002590179501567036
2023-01-23 04:14:40.053573: step: 652/530, loss: 0.0014540673000738025
2023-01-23 04:14:41.175613: step: 656/530, loss: 0.015654182061553
2023-01-23 04:14:42.300262: step: 660/530, loss: 0.0003867149353027344
2023-01-23 04:14:43.446054: step: 664/530, loss: 0.010762310586869717
2023-01-23 04:14:44.578443: step: 668/530, loss: 0.004128932952880859
2023-01-23 04:14:45.677978: step: 672/530, loss: 3.3950807846849784e-05
2023-01-23 04:14:46.809669: step: 676/530, loss: 0.14031583070755005
2023-01-23 04:14:47.936412: step: 680/530, loss: 2.4795534045551904e-05
2023-01-23 04:14:49.064510: step: 684/530, loss: 0.0003482818428892642
2023-01-23 04:14:50.210254: step: 688/530, loss: 0.10685501247644424
2023-01-23 04:14:51.340146: step: 692/530, loss: 1.7166134966828395e-06
2023-01-23 04:14:52.495827: step: 696/530, loss: 0.004745292942970991
2023-01-23 04:14:53.595992: step: 700/530, loss: 0.001017761300317943
2023-01-23 04:14:54.732258: step: 704/530, loss: 0.0004174232599325478
2023-01-23 04:14:55.845577: step: 708/530, loss: 0.0001891136053018272
2023-01-23 04:14:56.987182: step: 712/530, loss: 8.384585817111656e-05
2023-01-23 04:14:58.124447: step: 716/530, loss: 3.991126868641004e-05
2023-01-23 04:14:59.279851: step: 720/530, loss: 0.011674690991640091
2023-01-23 04:15:00.397957: step: 724/530, loss: 2.574920654296875e-05
2023-01-23 04:15:01.537784: step: 728/530, loss: 1.239776611328125e-05
2023-01-23 04:15:02.666478: step: 732/530, loss: 1.7261505490751006e-05
2023-01-23 04:15:03.772559: step: 736/530, loss: 2.136230432370212e-05
2023-01-23 04:15:04.903732: step: 740/530, loss: 0.0011869431473314762
2023-01-23 04:15:06.040355: step: 744/530, loss: 0.0023133279755711555
2023-01-23 04:15:07.172269: step: 748/530, loss: 0.002818203065544367
2023-01-23 04:15:08.314141: step: 752/530, loss: 0.029878806322813034
2023-01-23 04:15:09.425065: step: 756/530, loss: 5.34057608092553e-06
2023-01-23 04:15:10.546117: step: 760/530, loss: 0.0017185211181640625
2023-01-23 04:15:11.698959: step: 764/530, loss: 0.01397857628762722
2023-01-23 04:15:12.830570: step: 768/530, loss: 0.000978755997493863
2023-01-23 04:15:13.966863: step: 772/530, loss: 0.0011327743995934725
2023-01-23 04:15:15.098804: step: 776/530, loss: 0.00021915437537245452
2023-01-23 04:15:16.198205: step: 780/530, loss: 0.02690739743411541
2023-01-23 04:15:17.331236: step: 784/530, loss: 1.735687328618951e-05
2023-01-23 04:15:18.443903: step: 788/530, loss: 0.11035966873168945
2023-01-23 04:15:19.550184: step: 792/530, loss: 0.0005445480346679688
2023-01-23 04:15:20.640687: step: 796/530, loss: 6.12258882028982e-05
2023-01-23 04:15:21.778034: step: 800/530, loss: 3.337860107421875e-06
2023-01-23 04:15:22.894231: step: 804/530, loss: 0.0038760185707360506
2023-01-23 04:15:24.019072: step: 808/530, loss: 2.441406286379788e-05
2023-01-23 04:15:25.146791: step: 812/530, loss: 0.005829715635627508
2023-01-23 04:15:26.239563: step: 816/530, loss: 3.849268250633031e-05
2023-01-23 04:15:27.360175: step: 820/530, loss: -3.700256274896674e-05
2023-01-23 04:15:28.473428: step: 824/530, loss: 8.96453821042087e-06
2023-01-23 04:15:29.605686: step: 828/530, loss: 0.0009845733875408769
2023-01-23 04:15:30.716067: step: 832/530, loss: 0.0056663514114916325
2023-01-23 04:15:31.822220: step: 836/530, loss: 0.010106540285050869
2023-01-23 04:15:32.955357: step: 840/530, loss: 0.006153678987175226
2023-01-23 04:15:34.102615: step: 844/530, loss: 0.014376259408891201
2023-01-23 04:15:35.225432: step: 848/530, loss: 0.01888256147503853
2023-01-23 04:15:36.346435: step: 852/530, loss: 0.0016757964622229338
2023-01-23 04:15:37.476525: step: 856/530, loss: 0.00193109514657408
2023-01-23 04:15:38.611100: step: 860/530, loss: 5.769729341409402e-06
2023-01-23 04:15:39.737454: step: 864/530, loss: 0.04777565225958824
2023-01-23 04:15:40.880238: step: 868/530, loss: 0.0006130218971520662
2023-01-23 04:15:42.028759: step: 872/530, loss: 1.6021729607018642e-05
2023-01-23 04:15:43.139053: step: 876/530, loss: 0.03685932233929634
2023-01-23 04:15:44.253596: step: 880/530, loss: 0.00015897750563453883
2023-01-23 04:15:45.392426: step: 884/530, loss: 0.00010423660569358617
2023-01-23 04:15:46.543763: step: 888/530, loss: 0.003323173616081476
2023-01-23 04:15:47.671104: step: 892/530, loss: 0.0015552521217614412
2023-01-23 04:15:48.809908: step: 896/530, loss: 0.00012321471876930445
2023-01-23 04:15:49.930294: step: 900/530, loss: 0.03059844858944416
2023-01-23 04:15:51.059514: step: 904/530, loss: 0.004699421115219593
2023-01-23 04:15:52.183327: step: 908/530, loss: 7.534027645306196e-06
2023-01-23 04:15:53.280645: step: 912/530, loss: 0.0005949974292889237
2023-01-23 04:15:54.410701: step: 916/530, loss: 0.0002773285086732358
2023-01-23 04:15:55.533554: step: 920/530, loss: 0.005634307861328125
2023-01-23 04:15:56.668121: step: 924/530, loss: 0.0207806583493948
2023-01-23 04:15:57.799260: step: 928/530, loss: 1.4400482541532256e-05
2023-01-23 04:15:58.930584: step: 932/530, loss: 0.0009069442749023438
2023-01-23 04:16:00.039873: step: 936/530, loss: 3.9577484130859375e-05
2023-01-23 04:16:01.145496: step: 940/530, loss: 0.01210632361471653
2023-01-23 04:16:02.302569: step: 944/530, loss: 0.042786501348018646
2023-01-23 04:16:03.420915: step: 948/530, loss: 5.722047262679553e-07
2023-01-23 04:16:04.512753: step: 952/530, loss: 2.307891918462701e-05
2023-01-23 04:16:05.630817: step: 956/530, loss: 0.00025177001953125
2023-01-23 04:16:06.751572: step: 960/530, loss: 0.010819816961884499
2023-01-23 04:16:07.870592: step: 964/530, loss: 5.9127810345671605e-06
2023-01-23 04:16:09.004067: step: 968/530, loss: 0.00013818740262649953
2023-01-23 04:16:10.128560: step: 972/530, loss: 1.049041748046875e-05
2023-01-23 04:16:11.266936: step: 976/530, loss: 0.006081342697143555
2023-01-23 04:16:12.428080: step: 980/530, loss: 0.010370660573244095
2023-01-23 04:16:13.555971: step: 984/530, loss: 0.02096271514892578
2023-01-23 04:16:14.667529: step: 988/530, loss: 9.5367431640625e-06
2023-01-23 04:16:15.756187: step: 992/530, loss: 0.00010018348984885961
2023-01-23 04:16:16.891884: step: 996/530, loss: 9.71794142969884e-05
2023-01-23 04:16:17.998867: step: 1000/530, loss: 0.0004708290216512978
2023-01-23 04:16:19.136252: step: 1004/530, loss: 0.007357740309089422
2023-01-23 04:16:20.260943: step: 1008/530, loss: 5.817413330078125e-05
2023-01-23 04:16:21.395715: step: 1012/530, loss: 0.01956481859087944
2023-01-23 04:16:22.554887: step: 1016/530, loss: 0.00013589859008789062
2023-01-23 04:16:23.708061: step: 1020/530, loss: 0.00480308523401618
2023-01-23 04:16:24.876831: step: 1024/530, loss: 0.04133210331201553
2023-01-23 04:16:26.023145: step: 1028/530, loss: 0.01835022121667862
2023-01-23 04:16:27.187489: step: 1032/530, loss: 3.8909915019758046e-05
2023-01-23 04:16:28.291362: step: 1036/530, loss: 0.002245140029117465
2023-01-23 04:16:29.408288: step: 1040/530, loss: 0.0013062477810308337
2023-01-23 04:16:30.508748: step: 1044/530, loss: 1.4400482541532256e-05
2023-01-23 04:16:31.632256: step: 1048/530, loss: 5.111694918014109e-05
2023-01-23 04:16:32.755639: step: 1052/530, loss: 0.00614166259765625
2023-01-23 04:16:33.861973: step: 1056/530, loss: 0.0011013031471520662
2023-01-23 04:16:35.011839: step: 1060/530, loss: 0.00012755393981933594
2023-01-23 04:16:36.167855: step: 1064/530, loss: 0.0006929397350177169
2023-01-23 04:16:37.285182: step: 1068/530, loss: 0.004691123962402344
2023-01-23 04:16:38.390000: step: 1072/530, loss: 0.004897594451904297
2023-01-23 04:16:39.512523: step: 1076/530, loss: 0.0024919509887695312
2023-01-23 04:16:40.628419: step: 1080/530, loss: 0.009699773974716663
2023-01-23 04:16:41.778751: step: 1084/530, loss: 5.092620995128527e-05
2023-01-23 04:16:42.892565: step: 1088/530, loss: 8.37326078908518e-05
2023-01-23 04:16:44.034590: step: 1092/530, loss: 1.068115216185106e-05
2023-01-23 04:16:45.129843: step: 1096/530, loss: 1.23977656585339e-06
2023-01-23 04:16:46.228451: step: 1100/530, loss: 0.00042514799861237407
2023-01-23 04:16:47.354545: step: 1104/530, loss: 0.010024452582001686
2023-01-23 04:16:48.468057: step: 1108/530, loss: 2.9659269785042852e-05
2023-01-23 04:16:49.604714: step: 1112/530, loss: 0.0006076812860555947
2023-01-23 04:16:50.696629: step: 1116/530, loss: 0.06690111011266708
2023-01-23 04:16:51.809149: step: 1120/530, loss: 0.0011879921657964587
2023-01-23 04:16:52.949008: step: 1124/530, loss: 0.02864980697631836
2023-01-23 04:16:54.102025: step: 1128/530, loss: 0.00016021728515625
2023-01-23 04:16:55.221098: step: 1132/530, loss: 0.0007520675426349044
2023-01-23 04:16:56.341049: step: 1136/530, loss: 0.003181409789249301
2023-01-23 04:16:57.466811: step: 1140/530, loss: 0.00046281813411042094
2023-01-23 04:16:58.571959: step: 1144/530, loss: 0.0010197639930993319
2023-01-23 04:16:59.689322: step: 1148/530, loss: 0.00019078254990745336
2023-01-23 04:17:00.848425: step: 1152/530, loss: 2.3460386728402227e-05
2023-01-23 04:17:01.996632: step: 1156/530, loss: 0.04826164245605469
2023-01-23 04:17:03.103354: step: 1160/530, loss: 0.037078857421875
2023-01-23 04:17:04.236157: step: 1164/530, loss: 2.9563905172835803e-06
2023-01-23 04:17:05.358755: step: 1168/530, loss: 0.0006422043079510331
2023-01-23 04:17:06.467852: step: 1172/530, loss: 4.9591067181609105e-06
2023-01-23 04:17:07.589674: step: 1176/530, loss: 0.028036881238222122
2023-01-23 04:17:08.704227: step: 1180/530, loss: 7.247925168485381e-06
2023-01-23 04:17:09.853443: step: 1184/530, loss: 0.0009855270618572831
2023-01-23 04:17:10.980174: step: 1188/530, loss: 0.002782821888104081
2023-01-23 04:17:12.105959: step: 1192/530, loss: 0.0014248847728595138
2023-01-23 04:17:13.272429: step: 1196/530, loss: 0.00985031109303236
2023-01-23 04:17:14.371026: step: 1200/530, loss: 0.0033142089378088713
2023-01-23 04:17:15.496872: step: 1204/530, loss: 0.0012710571754723787
2023-01-23 04:17:16.611703: step: 1208/530, loss: 0.011067772284150124
2023-01-23 04:17:17.715612: step: 1212/530, loss: 0.008889294229447842
2023-01-23 04:17:18.810761: step: 1216/530, loss: 1.8405913579044864e-05
2023-01-23 04:17:19.933130: step: 1220/530, loss: 0.005579185672104359
2023-01-23 04:17:21.048418: step: 1224/530, loss: 0.0038913728203624487
2023-01-23 04:17:22.180741: step: 1228/530, loss: 0.00017795563326217234
2023-01-23 04:17:23.291589: step: 1232/530, loss: 2.4223329091910273e-05
2023-01-23 04:17:24.410544: step: 1236/530, loss: 5.7220458984375e-06
2023-01-23 04:17:25.523818: step: 1240/530, loss: 0.00043363572331145406
2023-01-23 04:17:26.657631: step: 1244/530, loss: 4.825591895496473e-05
2023-01-23 04:17:27.790088: step: 1248/530, loss: 3.490447852527723e-05
2023-01-23 04:17:28.893539: step: 1252/530, loss: 0.00037479400634765625
2023-01-23 04:17:29.999006: step: 1256/530, loss: 4.76837158203125e-07
2023-01-23 04:17:31.127033: step: 1260/530, loss: 0.0021940229926258326
2023-01-23 04:17:32.240167: step: 1264/530, loss: 0.1068042740225792
2023-01-23 04:17:33.360261: step: 1268/530, loss: 0.00038204193697310984
2023-01-23 04:17:34.486471: step: 1272/530, loss: 0.0003219604550395161
2023-01-23 04:17:35.597973: step: 1276/530, loss: 2.86102294921875e-06
2023-01-23 04:17:36.755391: step: 1280/530, loss: 0.024384213611483574
2023-01-23 04:17:37.888855: step: 1284/530, loss: 0.007886409759521484
2023-01-23 04:17:39.024460: step: 1288/530, loss: 0.01261148415505886
2023-01-23 04:17:40.131355: step: 1292/530, loss: 0.000667572021484375
2023-01-23 04:17:41.244663: step: 1296/530, loss: 0.0003046035999432206
2023-01-23 04:17:42.363535: step: 1300/530, loss: 0.0002510070917196572
2023-01-23 04:17:43.483842: step: 1304/530, loss: 0.00026159288245253265
2023-01-23 04:17:44.589839: step: 1308/530, loss: 0.0001598358212504536
2023-01-23 04:17:45.732347: step: 1312/530, loss: 0.05086078494787216
2023-01-23 04:17:46.894317: step: 1316/530, loss: 7.23838820704259e-05
2023-01-23 04:17:48.023036: step: 1320/530, loss: 0.0012585640652105212
2023-01-23 04:17:49.161195: step: 1324/530, loss: -3.051757857974735e-06
2023-01-23 04:17:50.287790: step: 1328/530, loss: 0.0014354229206219316
2023-01-23 04:17:51.418330: step: 1332/530, loss: 4.9591067181609105e-06
2023-01-23 04:17:52.539186: step: 1336/530, loss: 2.2602080207434483e-05
2023-01-23 04:17:53.672787: step: 1340/530, loss: 0.0006549835088662803
2023-01-23 04:17:54.803830: step: 1344/530, loss: 3.089904930675402e-05
2023-01-23 04:17:55.921500: step: 1348/530, loss: 0.012569237500429153
2023-01-23 04:17:57.029330: step: 1352/530, loss: 0.0004571914905682206
2023-01-23 04:17:58.139118: step: 1356/530, loss: 0.02011566422879696
2023-01-23 04:17:59.276590: step: 1360/530, loss: 0.00017471313185524195
2023-01-23 04:18:00.378237: step: 1364/530, loss: 0.00014772414579056203
2023-01-23 04:18:01.520158: step: 1368/530, loss: 0.0014085769653320312
2023-01-23 04:18:02.673987: step: 1372/530, loss: 0.0016020776238292456
2023-01-23 04:18:03.777102: step: 1376/530, loss: 7.877349707996473e-05
2023-01-23 04:18:04.896176: step: 1380/530, loss: 0.0003402710135560483
2023-01-23 04:18:06.025666: step: 1384/530, loss: 0.000286102294921875
2023-01-23 04:18:07.127996: step: 1388/530, loss: 0.004924488253891468
2023-01-23 04:18:08.296116: step: 1392/530, loss: 8.525847806595266e-05
2023-01-23 04:18:09.437498: step: 1396/530, loss: 2.498626781743951e-05
2023-01-23 04:18:10.572840: step: 1400/530, loss: 5.092620995128527e-05
2023-01-23 04:18:11.709203: step: 1404/530, loss: 3.0517580853484105e-06
2023-01-23 04:18:12.825213: step: 1408/530, loss: 4.96864304295741e-05
2023-01-23 04:18:13.978807: step: 1412/530, loss: 0.0012735367054119706
2023-01-23 04:18:15.089878: step: 1416/530, loss: 0.00017452239990234375
2023-01-23 04:18:16.194751: step: 1420/530, loss: 0.005168724339455366
2023-01-23 04:18:17.326708: step: 1424/530, loss: 0.0005486488225869834
2023-01-23 04:18:18.458723: step: 1428/530, loss: 8.20159948489163e-06
2023-01-23 04:18:19.559467: step: 1432/530, loss: 0.012815475463867188
2023-01-23 04:18:20.673595: step: 1436/530, loss: 0.0018611907726153731
2023-01-23 04:18:21.815694: step: 1440/530, loss: 0.004850959870964289
2023-01-23 04:18:22.929931: step: 1444/530, loss: 0.00027475954266265035
2023-01-23 04:18:24.079727: step: 1448/530, loss: 2.651214526849799e-05
2023-01-23 04:18:25.198546: step: 1452/530, loss: 0.00011496544175315648
2023-01-23 04:18:26.293519: step: 1456/530, loss: 0.0004398346063680947
2023-01-23 04:18:27.436042: step: 1460/530, loss: 0.027242470532655716
2023-01-23 04:18:28.555020: step: 1464/530, loss: 0.0001636505185160786
2023-01-23 04:18:29.660709: step: 1468/530, loss: 0.002613067626953125
2023-01-23 04:18:30.802259: step: 1472/530, loss: 0.01245107688009739
2023-01-23 04:18:31.928919: step: 1476/530, loss: 0.0012137412559241056
2023-01-23 04:18:33.101827: step: 1480/530, loss: 0.0002468109305482358
2023-01-23 04:18:34.223522: step: 1484/530, loss: -4.19616708313697e-06
2023-01-23 04:18:35.386777: step: 1488/530, loss: 0.010160732083022594
2023-01-23 04:18:36.523002: step: 1492/530, loss: 3.185272362316027e-05
2023-01-23 04:18:37.648292: step: 1496/530, loss: 9.317397780250758e-05
2023-01-23 04:18:38.748325: step: 1500/530, loss: 0.022419167682528496
2023-01-23 04:18:39.888745: step: 1504/530, loss: 0.024783708155155182
2023-01-23 04:18:41.005941: step: 1508/530, loss: 0.004865455906838179
2023-01-23 04:18:42.130860: step: 1512/530, loss: 0.017813779413700104
2023-01-23 04:18:43.290196: step: 1516/530, loss: 4.482269287109375e-05
2023-01-23 04:18:44.446575: step: 1520/530, loss: 0.024534082040190697
2023-01-23 04:18:45.576131: step: 1524/530, loss: 0.01102676335722208
2023-01-23 04:18:46.736130: step: 1528/530, loss: 0.001506042550317943
2023-01-23 04:18:47.865780: step: 1532/530, loss: 0.00033979417639784515
2023-01-23 04:18:48.969309: step: 1536/530, loss: 0.011409474536776543
2023-01-23 04:18:50.081472: step: 1540/530, loss: 9.284019324695691e-05
2023-01-23 04:18:51.186881: step: 1544/530, loss: 1.182556115963962e-05
2023-01-23 04:18:52.289180: step: 1548/530, loss: 0.000279331230558455
2023-01-23 04:18:53.387382: step: 1552/530, loss: 0.06510734558105469
2023-01-23 04:18:54.492824: step: 1556/530, loss: 0.000981998397037387
2023-01-23 04:18:55.617407: step: 1560/530, loss: 0.010261536575853825
2023-01-23 04:18:56.721667: step: 1564/530, loss: 0.0194154754281044
2023-01-23 04:18:57.844376: step: 1568/530, loss: 0.009335899725556374
2023-01-23 04:18:58.985954: step: 1572/530, loss: 0.0003146171511616558
2023-01-23 04:19:00.088729: step: 1576/530, loss: 3.8814545405330136e-05
2023-01-23 04:19:01.216302: step: 1580/530, loss: 0.0006937027210369706
2023-01-23 04:19:02.346108: step: 1584/530, loss: 0.0026811601128429174
2023-01-23 04:19:03.461027: step: 1588/530, loss: 0.01054458599537611
2023-01-23 04:19:04.568668: step: 1592/530, loss: 0.0010504722595214844
2023-01-23 04:19:05.710695: step: 1596/530, loss: 0.00042090416536666453
2023-01-23 04:19:06.810086: step: 1600/530, loss: 0.00011339188495185226
2023-01-23 04:19:07.950491: step: 1604/530, loss: 0.059081267565488815
2023-01-23 04:19:09.109415: step: 1608/530, loss: 0.0006906510097905993
2023-01-23 04:19:10.221904: step: 1612/530, loss: 0.032831527292728424
2023-01-23 04:19:11.328158: step: 1616/530, loss: 1.3841722011566162
2023-01-23 04:19:12.454835: step: 1620/530, loss: 0.010154151357710361
2023-01-23 04:19:13.572390: step: 1624/530, loss: -5.245208740234375e-06
2023-01-23 04:19:14.684539: step: 1628/530, loss: 0.17993135750293732
2023-01-23 04:19:15.809475: step: 1632/530, loss: 0.00039539337740279734
2023-01-23 04:19:16.929117: step: 1636/530, loss: 0.34007197618484497
2023-01-23 04:19:18.041896: step: 1640/530, loss: 0.06948566436767578
2023-01-23 04:19:19.175419: step: 1644/530, loss: 0.0007593155023641884
2023-01-23 04:19:20.331437: step: 1648/530, loss: 0.004726982209831476
2023-01-23 04:19:21.449182: step: 1652/530, loss: 0.5473955273628235
2023-01-23 04:19:22.593824: step: 1656/530, loss: 0.675804078578949
2023-01-23 04:19:23.725926: step: 1660/530, loss: 0.0002601623709779233
2023-01-23 04:19:24.873315: step: 1664/530, loss: 0.0020437240600585938
2023-01-23 04:19:26.009761: step: 1668/530, loss: 0.0007890701526775956
2023-01-23 04:19:27.112633: step: 1672/530, loss: 0.012912606820464134
2023-01-23 04:19:28.218730: step: 1676/530, loss: 0.00030765534029342234
2023-01-23 04:19:29.374493: step: 1680/530, loss: 0.02881908416748047
2023-01-23 04:19:30.524381: step: 1684/530, loss: 1.0013580322265625e-05
2023-01-23 04:19:31.643308: step: 1688/530, loss: 0.29777488112449646
2023-01-23 04:19:32.755578: step: 1692/530, loss: 0.005026340484619141
2023-01-23 04:19:33.868889: step: 1696/530, loss: 0.0008386134868487716
2023-01-23 04:19:35.007621: step: 1700/530, loss: 0.010757828131318092
2023-01-23 04:19:36.135546: step: 1704/530, loss: 2.2506712411995977e-05
2023-01-23 04:19:37.286592: step: 1708/530, loss: 0.023312950506806374
2023-01-23 04:19:38.459724: step: 1712/530, loss: 0.0448266975581646
2023-01-23 04:19:39.609461: step: 1716/530, loss: 0.0015081405872479081
2023-01-23 04:19:40.740658: step: 1720/530, loss: 0.005154609680175781
2023-01-23 04:19:41.867104: step: 1724/530, loss: 0.010216903872787952
2023-01-23 04:19:42.984052: step: 1728/530, loss: 0.008222103118896484
2023-01-23 04:19:44.098947: step: 1732/530, loss: 0.0007456779712811112
2023-01-23 04:19:45.220819: step: 1736/530, loss: 0.046380139887332916
2023-01-23 04:19:46.322525: step: 1740/530, loss: 0.004082679748535156
2023-01-23 04:19:47.460000: step: 1744/530, loss: 0.0006488800281658769
2023-01-23 04:19:48.584626: step: 1748/530, loss: 0.05324072763323784
2023-01-23 04:19:49.758112: step: 1752/530, loss: 0.6468315124511719
2023-01-23 04:19:50.870979: step: 1756/530, loss: 0.00018033980450127274
2023-01-23 04:19:51.975555: step: 1760/530, loss: 0.004239463713020086
2023-01-23 04:19:53.141939: step: 1764/530, loss: 0.007846260443329811
2023-01-23 04:19:54.253042: step: 1768/530, loss: 0.010870934464037418
2023-01-23 04:19:55.380069: step: 1772/530, loss: 5.908012462896295e-05
2023-01-23 04:19:56.518508: step: 1776/530, loss: 0.0018302917014807463
2023-01-23 04:19:57.635147: step: 1780/530, loss: 9.021759615279734e-05
2023-01-23 04:19:58.725225: step: 1784/530, loss: 0.0002437591610942036
2023-01-23 04:19:59.829451: step: 1788/530, loss: 0.0014827251434326172
2023-01-23 04:20:00.939618: step: 1792/530, loss: 0.014362144283950329
2023-01-23 04:20:02.049841: step: 1796/530, loss: 0.001475858734920621
2023-01-23 04:20:03.179007: step: 1800/530, loss: 0.023401547223329544
2023-01-23 04:20:04.321096: step: 1804/530, loss: 0.004010010045021772
2023-01-23 04:20:05.449235: step: 1808/530, loss: 0.0038078308571130037
2023-01-23 04:20:06.578360: step: 1812/530, loss: 0.0026221275329589844
2023-01-23 04:20:07.696375: step: 1816/530, loss: 0.00026264190091751516
2023-01-23 04:20:08.821930: step: 1820/530, loss: 0.029579926282167435
2023-01-23 04:20:09.936232: step: 1824/530, loss: 6.103515625e-05
2023-01-23 04:20:11.036198: step: 1828/530, loss: 4.67777244921308e-05
2023-01-23 04:20:12.160876: step: 1832/530, loss: 0.006224250886589289
2023-01-23 04:20:13.285851: step: 1836/530, loss: 5.6838991440599784e-05
2023-01-23 04:20:14.435849: step: 1840/530, loss: 0.006007385440170765
2023-01-23 04:20:15.554201: step: 1844/530, loss: 0.00016269684419967234
2023-01-23 04:20:16.682801: step: 1848/530, loss: 0.0003838539414573461
2023-01-23 04:20:17.815689: step: 1852/530, loss: 0.0032398225739598274
2023-01-23 04:20:18.952737: step: 1856/530, loss: 0.00019121170043945312
2023-01-23 04:20:20.071917: step: 1860/530, loss: 0.002493953565135598
2023-01-23 04:20:21.209590: step: 1864/530, loss: 7.858276512706652e-05
2023-01-23 04:20:22.330510: step: 1868/530, loss: 3.337860107421875e-06
2023-01-23 04:20:23.487366: step: 1872/530, loss: 0.0026824951637536287
2023-01-23 04:20:24.625935: step: 1876/530, loss: 0.00015211105346679688
2023-01-23 04:20:25.731262: step: 1880/530, loss: -5.722046125811175e-07
2023-01-23 04:20:26.884584: step: 1884/530, loss: 0.0007213592762127519
2023-01-23 04:20:28.010275: step: 1888/530, loss: 0.009116172790527344
2023-01-23 04:20:29.119107: step: 1892/530, loss: 0.0009084701887331903
2023-01-23 04:20:30.260163: step: 1896/530, loss: 4.978180368198082e-05
2023-01-23 04:20:31.393765: step: 1900/530, loss: 1.602172778802924e-05
2023-01-23 04:20:32.510832: step: 1904/530, loss: 0.033154867589473724
2023-01-23 04:20:33.641155: step: 1908/530, loss: 0.08177509158849716
2023-01-23 04:20:34.743223: step: 1912/530, loss: 0.002113485476002097
2023-01-23 04:20:35.877518: step: 1916/530, loss: 0.0013184547424316406
2023-01-23 04:20:36.980977: step: 1920/530, loss: 0.00022907258244231343
2023-01-23 04:20:38.101059: step: 1924/530, loss: 0.3636288046836853
2023-01-23 04:20:39.229215: step: 1928/530, loss: 0.02152719534933567
2023-01-23 04:20:40.330543: step: 1932/530, loss: 0.015555381774902344
2023-01-23 04:20:41.458082: step: 1936/530, loss: 0.02086048200726509
2023-01-23 04:20:42.604904: step: 1940/530, loss: 0.013928413391113281
2023-01-23 04:20:43.688831: step: 1944/530, loss: 6.732940528308973e-05
2023-01-23 04:20:44.783151: step: 1948/530, loss: 0.019211674109101295
2023-01-23 04:20:45.916962: step: 1952/530, loss: 1.4972687495173886e-05
2023-01-23 04:20:47.019319: step: 1956/530, loss: 1.0013580322265625e-05
2023-01-23 04:20:48.167324: step: 1960/530, loss: 0.007532310672104359
2023-01-23 04:20:49.255195: step: 1964/530, loss: 2.0599363779183477e-05
2023-01-23 04:20:50.379306: step: 1968/530, loss: 0.04944858327507973
2023-01-23 04:20:51.490515: step: 1972/530, loss: 0.015220833010971546
2023-01-23 04:20:52.629006: step: 1976/530, loss: 0.005277395248413086
2023-01-23 04:20:53.744593: step: 1980/530, loss: 0.06283760815858841
2023-01-23 04:20:54.828950: step: 1984/530, loss: -1.049041748046875e-05
2023-01-23 04:20:55.961327: step: 1988/530, loss: 0.012457847595214844
2023-01-23 04:20:57.092416: step: 1992/530, loss: 7.61032133596018e-05
2023-01-23 04:20:58.225892: step: 1996/530, loss: 0.0156339630484581
2023-01-23 04:20:59.339127: step: 2000/530, loss: 0.0009899139404296875
2023-01-23 04:21:00.452741: step: 2004/530, loss: 0.048882272094488144
2023-01-23 04:21:01.557157: step: 2008/530, loss: 0.0246187224984169
2023-01-23 04:21:02.697645: step: 2012/530, loss: 0.035050392150878906
2023-01-23 04:21:03.820977: step: 2016/530, loss: 9.91821252682712e-06
2023-01-23 04:21:04.937809: step: 2020/530, loss: 0.00967397727072239
2023-01-23 04:21:06.043618: step: 2024/530, loss: 0.00017232894606422633
2023-01-23 04:21:07.171200: step: 2028/530, loss: 1.1157990229548886e-05
2023-01-23 04:21:08.329080: step: 2032/530, loss: 0.00047941209049895406
2023-01-23 04:21:09.463985: step: 2036/530, loss: 0.0005478858947753906
2023-01-23 04:21:10.568127: step: 2040/530, loss: 7.877350435592234e-05
2023-01-23 04:21:11.711703: step: 2044/530, loss: 0.017975807189941406
2023-01-23 04:21:12.834264: step: 2048/530, loss: 0.0010637283558025956
2023-01-23 04:21:13.955202: step: 2052/530, loss: 0.00040922165499068797
2023-01-23 04:21:15.063355: step: 2056/530, loss: 0.017572499811649323
2023-01-23 04:21:16.214251: step: 2060/530, loss: 0.005312442779541016
2023-01-23 04:21:17.339127: step: 2064/530, loss: 0.008203793317079544
2023-01-23 04:21:18.441976: step: 2068/530, loss: 0.017166901379823685
2023-01-23 04:21:19.554153: step: 2072/530, loss: 0.00017185212345793843
2023-01-23 04:21:20.692893: step: 2076/530, loss: 1.0538101378188003e-05
2023-01-23 04:21:21.806729: step: 2080/530, loss: 0.00055608747061342
2023-01-23 04:21:22.931959: step: 2084/530, loss: 7.133484177757055e-05
2023-01-23 04:21:24.083472: step: 2088/530, loss: 0.0014274597633630037
2023-01-23 04:21:25.219426: step: 2092/530, loss: 0.0009328365558758378
2023-01-23 04:21:26.343179: step: 2096/530, loss: -4.76837158203125e-06
2023-01-23 04:21:27.473418: step: 2100/530, loss: 0.0008809089777059853
2023-01-23 04:21:28.584232: step: 2104/530, loss: 0.0002529144403524697
2023-01-23 04:21:29.693986: step: 2108/530, loss: 0.25830966234207153
2023-01-23 04:21:30.790598: step: 2112/530, loss: 0.03186798095703125
2023-01-23 04:21:31.899724: step: 2116/530, loss: 0.00039882661076262593
2023-01-23 04:21:33.015763: step: 2120/530, loss: 1.4448166439251509e-05
==================================================
Loss: 0.019
--------------------
Dev: {'event': {'p': 0.596875, 'r': 0.762982689747004, 'f1': 0.6697837521917008}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
Test: {'event': {'p': 0.6148678907299597, 'r': 0.7845714285714286, 'f1': 0.6894300778307809}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
Chinese: {'event': {'p': 0.6363636363636364, 'r': 0.9074074074074074, 'f1': 0.7480916030534351}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
Korean: {'event': {'p': 0.6111111111111112, 'r': 0.5238095238095238, 'f1': 0.5641025641025642}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
Russian: {'event': {'p': 0.4090909090909091, 'r': 0.5, 'f1': 0.45}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6043715846994535, 'r': 0.7363515312916112, 'f1': 0.6638655462184874}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
Eng Test for Chinese: {'event': {'p': 0.6399622997172478, 'r': 0.776, 'f1': 0.7014462809917356}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
Sample Chinese: {'event': {'p': 0.6533333333333333, 'r': 0.9074074074074074, 'f1': 0.7596899224806202}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6288770053475936, 'r': 0.7829560585885486, 'f1': 0.697508896797153}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Korean: {'event': {'p': 0.64058795637743, 'r': 0.772, 'f1': 0.7001813941435606}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Korean: {'event': {'p': 0.6851851851851852, 'r': 0.5873015873015873, 'f1': 0.6324786324786325}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5319148936170213, 'r': 0.6944444444444444, 'f1': 0.6024096385542169}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
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 04:22:13.978784: step: 4/530, loss: 1.61647803906817e-05
2023-01-23 04:22:15.124780: step: 8/530, loss: 0.002895450685173273
2023-01-23 04:22:16.288064: step: 12/530, loss: 0.0001123428373830393
2023-01-23 04:22:17.428623: step: 16/530, loss: 0.00017395020404364914
2023-01-23 04:22:18.529497: step: 20/530, loss: 0.0003459930594544858
2023-01-23 04:22:19.670459: step: 24/530, loss: 0.0007979392539709806
2023-01-23 04:22:20.786628: step: 28/530, loss: -7.629394644936838e-07
2023-01-23 04:22:21.879887: step: 32/530, loss: 0.00016105175018310547
2023-01-23 04:22:23.002152: step: 36/530, loss: 0.00014028549776412547
2023-01-23 04:22:24.136071: step: 40/530, loss: 0.01956052891910076
2023-01-23 04:22:25.291624: step: 44/530, loss: 0.0058405399322509766
2023-01-23 04:22:26.417546: step: 48/530, loss: 0.00042591095552779734
2023-01-23 04:22:27.548039: step: 52/530, loss: 1.9073486328125e-06
2023-01-23 04:22:28.717112: step: 56/530, loss: 1.9073559087701142e-07
2023-01-23 04:22:29.846605: step: 60/530, loss: 2.593994213384576e-05
2023-01-23 04:22:30.955541: step: 64/530, loss: 0.032859232276678085
2023-01-23 04:22:32.140902: step: 68/530, loss: 6.914139248692663e-06
2023-01-23 04:22:33.266808: step: 72/530, loss: 0.0005523681757040322
2023-01-23 04:22:34.402903: step: 76/530, loss: 0.00010128021676791832
2023-01-23 04:22:35.534412: step: 80/530, loss: 6.542205665027723e-05
2023-01-23 04:22:36.632586: step: 84/530, loss: 3.5762786865234375e-05
2023-01-23 04:22:37.742883: step: 88/530, loss: 0.0008863449329510331
2023-01-23 04:22:38.878633: step: 92/530, loss: 3.280639793956652e-05
2023-01-23 04:22:39.998239: step: 96/530, loss: 0.0014580728020519018
2023-01-23 04:22:41.109384: step: 100/530, loss: 0.010656356811523438
2023-01-23 04:22:42.238301: step: 104/530, loss: 0.002040386199951172
2023-01-23 04:22:43.339988: step: 108/530, loss: 0.0015539169544354081
2023-01-23 04:22:44.475030: step: 112/530, loss: 0.042345620691776276
2023-01-23 04:22:45.610313: step: 116/530, loss: 0.0015274047618731856
2023-01-23 04:22:46.706349: step: 120/530, loss: 3.795623706537299e-05
2023-01-23 04:22:47.839095: step: 124/530, loss: 0.00010585784912109375
2023-01-23 04:22:48.954163: step: 128/530, loss: 6.31332368357107e-05
2023-01-23 04:22:50.082914: step: 132/530, loss: 0.005732917692512274
2023-01-23 04:22:51.198336: step: 136/530, loss: 0.0027496337424963713
2023-01-23 04:22:52.283759: step: 140/530, loss: 6.256103370105848e-05
2023-01-23 04:22:53.380399: step: 144/530, loss: 9.813308861339465e-05
2023-01-23 04:22:54.490051: step: 148/530, loss: 0.014726400375366211
2023-01-23 04:22:55.637295: step: 152/530, loss: 0.005751418881118298
2023-01-23 04:22:56.755709: step: 156/530, loss: 0.0002639770682435483
2023-01-23 04:22:57.865812: step: 160/530, loss: 0.0015379906399175525
2023-01-23 04:22:59.009039: step: 164/530, loss: 0.0005727768293581903
2023-01-23 04:23:00.110817: step: 168/530, loss: 0.04943738132715225
2023-01-23 04:23:01.231000: step: 172/530, loss: 1.2111663636460435e-05
2023-01-23 04:23:02.366220: step: 176/530, loss: 0.003657054854556918
2023-01-23 04:23:03.515034: step: 180/530, loss: 0.000196361550479196
2023-01-23 04:23:04.611924: step: 184/530, loss: -1.144409225162235e-06
2023-01-23 04:23:05.751025: step: 188/530, loss: 0.00022940635972190648
2023-01-23 04:23:06.879576: step: 192/530, loss: 0.0006702422979287803
2023-01-23 04:23:08.033845: step: 196/530, loss: 0.014172744937241077
2023-01-23 04:23:09.159263: step: 200/530, loss: 0.0022460937034338713
2023-01-23 04:23:10.261296: step: 204/530, loss: 0.006929206661880016
2023-01-23 04:23:11.389243: step: 208/530, loss: 0.006089400965720415
2023-01-23 04:23:12.510070: step: 212/530, loss: 8.7738037109375e-05
2023-01-23 04:23:13.646162: step: 216/530, loss: 0.00984726008027792
2023-01-23 04:23:14.764064: step: 220/530, loss: 8.296966370835435e-06
2023-01-23 04:23:15.879960: step: 224/530, loss: 0.015216446481645107
2023-01-23 04:23:16.989940: step: 228/530, loss: 0.0031753063667565584
2023-01-23 04:23:18.172537: step: 232/530, loss: 0.0310440082103014
2023-01-23 04:23:19.326275: step: 236/530, loss: 0.006305122282356024
2023-01-23 04:23:20.439278: step: 240/530, loss: 0.0005549431079998612
2023-01-23 04:23:21.601386: step: 244/530, loss: 0.008169079199433327
2023-01-23 04:23:22.736707: step: 248/530, loss: 0.0036918639671057463
2023-01-23 04:23:23.868780: step: 252/530, loss: 4.386902219266631e-06
2023-01-23 04:23:24.977329: step: 256/530, loss: 0.015699386596679688
2023-01-23 04:23:26.096317: step: 260/530, loss: -1.33514404296875e-05
2023-01-23 04:23:27.190676: step: 264/530, loss: 0.00044374470598995686
2023-01-23 04:23:28.328204: step: 268/530, loss: 0.0037364959716796875
2023-01-23 04:23:29.459014: step: 272/530, loss: 0.0004578590451274067
2023-01-23 04:23:30.594293: step: 276/530, loss: 0.36111927032470703
2023-01-23 04:23:31.726259: step: 280/530, loss: 0.0012763977283611894
2023-01-23 04:23:32.849713: step: 284/530, loss: 0.0036357881035655737
2023-01-23 04:23:33.944511: step: 288/530, loss: 0.00019040108600165695
2023-01-23 04:23:35.083649: step: 292/530, loss: 0.01742076873779297
2023-01-23 04:23:36.230254: step: 296/530, loss: 0.002397155622020364
2023-01-23 04:23:37.339031: step: 300/530, loss: 0.022004319354891777
2023-01-23 04:23:38.463983: step: 304/530, loss: 0.0009565353393554688
2023-01-23 04:23:39.601484: step: 308/530, loss: 0.012733936309814453
2023-01-23 04:23:40.718141: step: 312/530, loss: 0.0023849487770348787
2023-01-23 04:23:41.906986: step: 316/530, loss: 1.773834264895413e-05
2023-01-23 04:23:43.047804: step: 320/530, loss: 0.004548454657196999
2023-01-23 04:23:44.192717: step: 324/530, loss: 3.919601658708416e-05
2023-01-23 04:23:45.322764: step: 328/530, loss: 0.0006677627679891884
2023-01-23 04:23:46.455861: step: 332/530, loss: 1.621246337890625e-05
2023-01-23 04:23:47.570069: step: 336/530, loss: 0.00011048316810047254
2023-01-23 04:23:48.714874: step: 340/530, loss: 0.0001567840517964214
2023-01-23 04:23:49.801574: step: 344/530, loss: 0.0007076263427734375
2023-01-23 04:23:50.937206: step: 348/530, loss: 8.0108642578125e-05
2023-01-23 04:23:52.052133: step: 352/530, loss: 0.6086832284927368
2023-01-23 04:23:53.195057: step: 356/530, loss: 0.02562532387673855
2023-01-23 04:23:54.292558: step: 360/530, loss: 0.00019035338482353836
2023-01-23 04:23:55.393628: step: 364/530, loss: 2.4795533590804553e-06
2023-01-23 04:23:56.550267: step: 368/530, loss: 0.028681470081210136
2023-01-23 04:23:57.688762: step: 372/530, loss: 0.04610119014978409
2023-01-23 04:23:58.831060: step: 376/530, loss: 0.007653284352272749
2023-01-23 04:23:59.950525: step: 380/530, loss: 1.1444092706369702e-05
2023-01-23 04:24:01.062772: step: 384/530, loss: 0.0058803558349609375
2023-01-23 04:24:02.183100: step: 388/530, loss: 0.00010013580322265625
2023-01-23 04:24:03.299934: step: 392/530, loss: 0.00013875961303710938
2023-01-23 04:24:04.447120: step: 396/530, loss: 0.14408770203590393
2023-01-23 04:24:05.578798: step: 400/530, loss: 0.007503700442612171
2023-01-23 04:24:06.672392: step: 404/530, loss: 0.00020685195340774953
2023-01-23 04:24:07.814799: step: 408/530, loss: 0.00017423629469703883
2023-01-23 04:24:08.940093: step: 412/530, loss: 0.0037204741965979338
2023-01-23 04:24:10.065536: step: 416/530, loss: 0.02051677741110325
2023-01-23 04:24:11.203229: step: 420/530, loss: 0.00021266937255859375
2023-01-23 04:24:12.290001: step: 424/530, loss: 0.010767459869384766
2023-01-23 04:24:13.388994: step: 428/530, loss: 0.0011314392322674394
2023-01-23 04:24:14.510306: step: 432/530, loss: 2.9563905172835803e-06
2023-01-23 04:24:15.658258: step: 436/530, loss: 0.023217011243104935
2023-01-23 04:24:16.783484: step: 440/530, loss: 0.007027054205536842
2023-01-23 04:24:17.896237: step: 444/530, loss: 0.005853176582604647
2023-01-23 04:24:19.004030: step: 448/530, loss: 0.0007048607221804559
2023-01-23 04:24:20.119113: step: 452/530, loss: 0.007026386447250843
2023-01-23 04:24:21.243046: step: 456/530, loss: 9.431839134776965e-05
2023-01-23 04:24:22.375386: step: 460/530, loss: 1.4972687495173886e-05
2023-01-23 04:24:23.507309: step: 464/530, loss: 0.0014553070068359375
2023-01-23 04:24:24.628401: step: 468/530, loss: 0.04153694957494736
2023-01-23 04:24:25.728687: step: 472/530, loss: 0.002308464143425226
2023-01-23 04:24:26.854920: step: 476/530, loss: 0.0004938125493936241
2023-01-23 04:24:27.991906: step: 480/530, loss: 0.049247268587350845
2023-01-23 04:24:29.111735: step: 484/530, loss: 0.00914468802511692
2023-01-23 04:24:30.275422: step: 488/530, loss: 0.032621193677186966
2023-01-23 04:24:31.375770: step: 492/530, loss: 0.005867003928869963
2023-01-23 04:24:32.488750: step: 496/530, loss: 0.0025401234161108732
2023-01-23 04:24:33.619779: step: 500/530, loss: 0.0560823455452919
2023-01-23 04:24:34.740943: step: 504/530, loss: 0.0191024299710989
2023-01-23 04:24:35.881217: step: 508/530, loss: 2.593994213384576e-05
2023-01-23 04:24:36.986029: step: 512/530, loss: 0.059711456298828125
2023-01-23 04:24:38.086931: step: 516/530, loss: 0.010155963711440563
2023-01-23 04:24:39.219465: step: 520/530, loss: 0.0002598762512207031
2023-01-23 04:24:40.352945: step: 524/530, loss: 0.004161930177360773
2023-01-23 04:24:41.468747: step: 528/530, loss: 1.3589859008789062e-05
2023-01-23 04:24:42.558586: step: 532/530, loss: 0.00012807846360374242
2023-01-23 04:24:43.667792: step: 536/530, loss: 5.34057608092553e-06
2023-01-23 04:24:44.790458: step: 540/530, loss: 0.022748898714780807
2023-01-23 04:24:45.919593: step: 544/530, loss: 0.0030088424682617188
2023-01-23 04:24:47.022056: step: 548/530, loss: 0.01999511756002903
2023-01-23 04:24:48.123134: step: 552/530, loss: 0.0001902341900859028
2023-01-23 04:24:49.226017: step: 556/530, loss: 0.262780100107193
2023-01-23 04:24:50.341866: step: 560/530, loss: 0.0006860733265057206
2023-01-23 04:24:51.467775: step: 564/530, loss: 0.00732688931748271
2023-01-23 04:24:52.578547: step: 568/530, loss: 6.322861008811742e-05
2023-01-23 04:24:53.692191: step: 572/530, loss: 0.006182384677231312
2023-01-23 04:24:54.829122: step: 576/530, loss: 0.002134656999260187
2023-01-23 04:24:55.967427: step: 580/530, loss: 0.00017662048048805445
2023-01-23 04:24:57.097750: step: 584/530, loss: 9.002686419989914e-05
2023-01-23 04:24:58.227751: step: 588/530, loss: 9.174347360385582e-05
2023-01-23 04:24:59.332070: step: 592/530, loss: 0.014150524511933327
2023-01-23 04:25:00.449578: step: 596/530, loss: 0.002223968505859375
2023-01-23 04:25:01.566739: step: 600/530, loss: 0.04023418575525284
2023-01-23 04:25:02.696517: step: 604/530, loss: 0.004775805864483118
2023-01-23 04:25:03.800283: step: 608/530, loss: 5.53131121705519e-06
2023-01-23 04:25:04.945159: step: 612/530, loss: 0.0010930061107501388
2023-01-23 04:25:06.062153: step: 616/530, loss: 7.181167165981606e-05
2023-01-23 04:25:07.178265: step: 620/530, loss: 0.00042381288949400187
2023-01-23 04:25:08.275824: step: 624/530, loss: -4.291534423828125e-06
2023-01-23 04:25:09.384584: step: 628/530, loss: 0.00019874573627021164
2023-01-23 04:25:10.502530: step: 632/530, loss: 0.00044651032658293843
2023-01-23 04:25:11.626948: step: 636/530, loss: 0.013640307821333408
2023-01-23 04:25:12.748928: step: 640/530, loss: 0.009754180908203125
2023-01-23 04:25:13.869422: step: 644/530, loss: 0.00875711441040039
2023-01-23 04:25:15.003379: step: 648/530, loss: 0.004778098780661821
2023-01-23 04:25:16.161301: step: 652/530, loss: 6.608962576137856e-05
2023-01-23 04:25:17.278709: step: 656/530, loss: 0.0017053604824468493
2023-01-23 04:25:18.385987: step: 660/530, loss: 0.0698385238647461
2023-01-23 04:25:19.499581: step: 664/530, loss: -1.010894811770413e-05
2023-01-23 04:25:20.604922: step: 668/530, loss: 0.008668137714266777
2023-01-23 04:25:21.734500: step: 672/530, loss: 0.0006757735973224044
2023-01-23 04:25:22.856271: step: 676/530, loss: 0.0001385211944580078
2023-01-23 04:25:23.973618: step: 680/530, loss: 0.031541064381599426
2023-01-23 04:25:25.094464: step: 684/530, loss: 0.007217979524284601
2023-01-23 04:25:26.203363: step: 688/530, loss: 0.0016963959205895662
2023-01-23 04:25:27.331106: step: 692/530, loss: 0.00010528564598644152
2023-01-23 04:25:28.451387: step: 696/530, loss: 0.0011213303077965975
2023-01-23 04:25:29.587030: step: 700/530, loss: 0.006923961453139782
2023-01-23 04:25:30.748714: step: 704/530, loss: 0.00010042190842796117
2023-01-23 04:25:31.870447: step: 708/530, loss: 9.498596045887098e-05
2023-01-23 04:25:33.004296: step: 712/530, loss: 0.002708053681999445
2023-01-23 04:25:34.101528: step: 716/530, loss: 0.05470886081457138
2023-01-23 04:25:35.225496: step: 720/530, loss: 0.00021219253540039062
2023-01-23 04:25:36.303875: step: 724/530, loss: 9.431839134776965e-05
2023-01-23 04:25:37.451509: step: 728/530, loss: 0.008250999264419079
2023-01-23 04:25:38.605443: step: 732/530, loss: 0.0015811920166015625
2023-01-23 04:25:39.705048: step: 736/530, loss: 0.00401916541159153
2023-01-23 04:25:40.810021: step: 740/530, loss: 0.02395792119204998
2023-01-23 04:25:41.936284: step: 744/530, loss: 0.0009042739984579384
2023-01-23 04:25:43.076180: step: 748/530, loss: 0.000752353691495955
2023-01-23 04:25:44.187505: step: 752/530, loss: 0.795527994632721
2023-01-23 04:25:45.277066: step: 756/530, loss: 0.016500424593687057
2023-01-23 04:25:46.395107: step: 760/530, loss: 0.0014204978942871094
2023-01-23 04:25:47.523066: step: 764/530, loss: -6.103515261202119e-06
2023-01-23 04:25:48.650823: step: 768/530, loss: 0.006800651550292969
2023-01-23 04:25:49.763491: step: 772/530, loss: 0.032942771911621094
2023-01-23 04:25:50.852679: step: 776/530, loss: 0.0019129753345623612
2023-01-23 04:25:51.976784: step: 780/530, loss: 0.002397727919742465
2023-01-23 04:25:53.121530: step: 784/530, loss: 0.00051116943359375
2023-01-23 04:25:54.237558: step: 788/530, loss: 0.011448669247329235
2023-01-23 04:25:55.362580: step: 792/530, loss: 0.025690842419862747
2023-01-23 04:25:56.487526: step: 796/530, loss: 2.7287005650578067e-05
2023-01-23 04:25:57.607450: step: 800/530, loss: 1.029968279908644e-05
2023-01-23 04:25:58.723979: step: 804/530, loss: 1.182556115963962e-05
2023-01-23 04:25:59.847899: step: 808/530, loss: 0.6968754529953003
2023-01-23 04:26:00.989482: step: 812/530, loss: 0.03249816969037056
2023-01-23 04:26:02.105342: step: 816/530, loss: 0.002442741533741355
2023-01-23 04:26:03.216394: step: 820/530, loss: 0.0011867046123370528
2023-01-23 04:26:04.360433: step: 824/530, loss: 0.007768154144287109
2023-01-23 04:26:05.479491: step: 828/530, loss: 0.02147960662841797
2023-01-23 04:26:06.640022: step: 832/530, loss: 0.0002189636288676411
2023-01-23 04:26:07.763480: step: 836/530, loss: 0.03344393149018288
2023-01-23 04:26:08.895581: step: 840/530, loss: 3.2711028325138614e-05
2023-01-23 04:26:10.020681: step: 844/530, loss: 6.341934204101562e-05
2023-01-23 04:26:11.125000: step: 848/530, loss: 0.00029501915560103953
2023-01-23 04:26:12.224266: step: 852/530, loss: 0.0001030921921483241
2023-01-23 04:26:13.381373: step: 856/530, loss: 1.373290979245212e-05
2023-01-23 04:26:14.497897: step: 860/530, loss: 0.00044536590576171875
2023-01-23 04:26:15.612199: step: 864/530, loss: 0.018575668334960938
2023-01-23 04:26:16.760756: step: 868/530, loss: 0.0007208347669802606
2023-01-23 04:26:17.882340: step: 872/530, loss: 0.04862871393561363
2023-01-23 04:26:19.018179: step: 876/530, loss: 0.00033745766268111765
2023-01-23 04:26:20.125499: step: 880/530, loss: 4.27722952736076e-05
2023-01-23 04:26:21.286843: step: 884/530, loss: 0.0006854057428427041
2023-01-23 04:26:22.413204: step: 888/530, loss: 0.0011775969760492444
2023-01-23 04:26:23.567847: step: 892/530, loss: 0.0008594513055868447
2023-01-23 04:26:24.652818: step: 896/530, loss: 7.963179996295366e-06
2023-01-23 04:26:25.773877: step: 900/530, loss: 0.003631782718002796
2023-01-23 04:26:26.935479: step: 904/530, loss: 0.00031414031400345266
2023-01-23 04:26:28.057050: step: 908/530, loss: -1.9073486612342094e-07
2023-01-23 04:26:29.202197: step: 912/530, loss: 0.002008628798648715
2023-01-23 04:26:30.329143: step: 916/530, loss: 0.0008638381841592491
2023-01-23 04:26:31.457230: step: 920/530, loss: 0.0001652240753173828
2023-01-23 04:26:32.571667: step: 924/530, loss: 0.00010886192467296496
2023-01-23 04:26:33.688263: step: 928/530, loss: 0.00020947455777786672
2023-01-23 04:26:34.811839: step: 932/530, loss: 0.0015834808582440019
2023-01-23 04:26:35.942627: step: 936/530, loss: 0.007834816351532936
2023-01-23 04:26:37.071489: step: 940/530, loss: 0.0047487737610936165
2023-01-23 04:26:38.175997: step: 944/530, loss: 0.0001928329438669607
2023-01-23 04:26:39.312133: step: 948/530, loss: 0.00012836456880904734
2023-01-23 04:26:40.422928: step: 952/530, loss: 0.01651759073138237
2023-01-23 04:26:41.553128: step: 956/530, loss: 0.000850296055432409
2023-01-23 04:26:42.683754: step: 960/530, loss: 1.068115216185106e-05
2023-01-23 04:26:43.805604: step: 964/530, loss: 0.0011074066860601306
2023-01-23 04:26:44.957786: step: 968/530, loss: 0.0030498504638671875
2023-01-23 04:26:46.053409: step: 972/530, loss: 0.0011825562687590718
2023-01-23 04:26:47.124896: step: 976/530, loss: 9.822844731388614e-06
2023-01-23 04:26:48.240337: step: 980/530, loss: 0.0001998901425395161
2023-01-23 04:26:49.333128: step: 984/530, loss: 5.235672142589465e-05
2023-01-23 04:26:50.475164: step: 988/530, loss: 0.11468525230884552
2023-01-23 04:26:51.610769: step: 992/530, loss: 0.006410980597138405
2023-01-23 04:26:52.736005: step: 996/530, loss: 9.89913969533518e-05
2023-01-23 04:26:53.840662: step: 1000/530, loss: 0.0001962661772267893
2023-01-23 04:26:54.936154: step: 1004/530, loss: 1.354217511106981e-05
2023-01-23 04:26:56.069912: step: 1008/530, loss: 0.007386684417724609
2023-01-23 04:26:57.194204: step: 1012/530, loss: -1.5926361811580136e-05
2023-01-23 04:26:58.310385: step: 1016/530, loss: 7.190704491222277e-05
2023-01-23 04:26:59.439156: step: 1020/530, loss: 0.001410675118677318
2023-01-23 04:27:00.570486: step: 1024/530, loss: 1.71661376953125e-05
2023-01-23 04:27:01.660085: step: 1028/530, loss: 7.305145845748484e-05
2023-01-23 04:27:02.761197: step: 1032/530, loss: 3.528594970703125e-05
2023-01-23 04:27:03.846636: step: 1036/530, loss: 0.000873947108630091
2023-01-23 04:27:04.982168: step: 1040/530, loss: 0.004680252633988857
2023-01-23 04:27:06.134358: step: 1044/530, loss: 1.888275073724799e-05
2023-01-23 04:27:07.258248: step: 1048/530, loss: 0.004245043266564608
2023-01-23 04:27:08.379970: step: 1052/530, loss: 0.00020294189744163305
2023-01-23 04:27:09.520916: step: 1056/530, loss: 0.21936731040477753
2023-01-23 04:27:10.636615: step: 1060/530, loss: 0.012591171078383923
2023-01-23 04:27:11.761330: step: 1064/530, loss: 0.004246711730957031
2023-01-23 04:27:12.915381: step: 1068/530, loss: 0.0016354559920728207
2023-01-23 04:27:14.041503: step: 1072/530, loss: 0.017191791906952858
2023-01-23 04:27:15.166087: step: 1076/530, loss: 9.250641596736386e-06
2023-01-23 04:27:16.310119: step: 1080/530, loss: 0.045319173485040665
2023-01-23 04:27:17.417273: step: 1084/530, loss: 1.864433397713583e-05
2023-01-23 04:27:18.544951: step: 1088/530, loss: 0.00010933876183116809
2023-01-23 04:27:19.667062: step: 1092/530, loss: 3.986358569818549e-05
2023-01-23 04:27:20.828920: step: 1096/530, loss: 0.013704204931855202
2023-01-23 04:27:21.952973: step: 1100/530, loss: 0.0003279685915913433
2023-01-23 04:27:23.053170: step: 1104/530, loss: 0.0005154609680175781
2023-01-23 04:27:24.161943: step: 1108/530, loss: 0.0011608124477788806
2023-01-23 04:27:25.300569: step: 1112/530, loss: 0.00014228820509742945
2023-01-23 04:27:26.430780: step: 1116/530, loss: 0.015127467922866344
2023-01-23 04:27:27.545959: step: 1120/530, loss: 0.0012807846069335938
2023-01-23 04:27:28.658261: step: 1124/530, loss: 0.029927827417850494
2023-01-23 04:27:29.775714: step: 1128/530, loss: 0.0002655029238667339
2023-01-23 04:27:30.896915: step: 1132/530, loss: 0.00026569367037154734
2023-01-23 04:27:32.041159: step: 1136/530, loss: 0.05796490237116814
2023-01-23 04:27:33.226428: step: 1140/530, loss: 1.201629675051663e-05
2023-01-23 04:27:34.360689: step: 1144/530, loss: 0.0002628326474223286
2023-01-23 04:27:35.492542: step: 1148/530, loss: 0.005240822210907936
2023-01-23 04:27:36.605038: step: 1152/530, loss: 3.452301098150201e-05
2023-01-23 04:27:37.736604: step: 1156/530, loss: 7.057190487103071e-06
2023-01-23 04:27:38.896711: step: 1160/530, loss: 0.01654491387307644
2023-01-23 04:27:40.031018: step: 1164/530, loss: 6.866455078125e-05
2023-01-23 04:27:41.165335: step: 1168/530, loss: 1.850128137448337e-05
2023-01-23 04:27:42.299966: step: 1172/530, loss: 2.47955322265625e-05
2023-01-23 04:27:43.424786: step: 1176/530, loss: 0.05250587314367294
2023-01-23 04:27:44.590911: step: 1180/530, loss: 0.024602126330137253
2023-01-23 04:27:45.744585: step: 1184/530, loss: 0.0006070137023925781
2023-01-23 04:27:46.868419: step: 1188/530, loss: 0.0005891799810342491
2023-01-23 04:27:47.973950: step: 1192/530, loss: 0.0009168625110760331
2023-01-23 04:27:49.120704: step: 1196/530, loss: 0.003345012664794922
2023-01-23 04:27:50.231784: step: 1200/530, loss: 4.4822695599577855e-06
2023-01-23 04:27:51.358198: step: 1204/530, loss: 0.00022363662719726562
2023-01-23 04:27:52.498593: step: 1208/530, loss: 0.0014486312866210938
2023-01-23 04:27:53.617570: step: 1212/530, loss: 1.9311904907226562e-05
2023-01-23 04:27:54.728528: step: 1216/530, loss: 0.00435905484482646
2023-01-23 04:27:55.852885: step: 1220/530, loss: 5.722046125811175e-07
2023-01-23 04:27:56.965225: step: 1224/530, loss: 0.01454086322337389
2023-01-23 04:27:58.086840: step: 1228/530, loss: 0.00012530684762168676
2023-01-23 04:27:59.203162: step: 1232/530, loss: 7.4386593951203395e-06
2023-01-23 04:28:00.309390: step: 1236/530, loss: 0.00303993234410882
2023-01-23 04:28:01.419447: step: 1240/530, loss: 0.022078227251768112
2023-01-23 04:28:02.580693: step: 1244/530, loss: 7.64846772653982e-05
2023-01-23 04:28:03.700541: step: 1248/530, loss: 0.000225067138671875
2023-01-23 04:28:04.865907: step: 1252/530, loss: 0.014113521203398705
2023-01-23 04:28:06.006887: step: 1256/530, loss: 0.0016180991660803556
2023-01-23 04:28:07.122957: step: 1260/530, loss: 0.000667190586682409
2023-01-23 04:28:08.221270: step: 1264/530, loss: 9.5367431640625e-06
2023-01-23 04:28:09.339306: step: 1268/530, loss: 0.0033041476272046566
2023-01-23 04:28:10.485289: step: 1272/530, loss: 0.0652918815612793
2023-01-23 04:28:11.611589: step: 1276/530, loss: 0.0017426013946533203
2023-01-23 04:28:12.750078: step: 1280/530, loss: 0.00021839141845703125
2023-01-23 04:28:13.893460: step: 1284/530, loss: 0.0005246162763796747
2023-01-23 04:28:15.014041: step: 1288/530, loss: 0.03068218193948269
2023-01-23 04:28:16.125476: step: 1292/530, loss: 0.0006031990051269531
2023-01-23 04:28:17.255073: step: 1296/530, loss: 0.0037992477882653475
2023-01-23 04:28:18.387858: step: 1300/530, loss: 0.007296753115952015
2023-01-23 04:28:19.521545: step: 1304/530, loss: 9.922981553245336e-05
2023-01-23 04:28:20.654470: step: 1308/530, loss: 0.00131397251971066
2023-01-23 04:28:21.777377: step: 1312/530, loss: 0.021523714065551758
2023-01-23 04:28:22.904810: step: 1316/530, loss: 0.006301593966782093
2023-01-23 04:28:24.025304: step: 1320/530, loss: 0.05940885469317436
2023-01-23 04:28:25.147599: step: 1324/530, loss: 8.068084571277723e-05
2023-01-23 04:28:26.237658: step: 1328/530, loss: 0.0001291275111725554
2023-01-23 04:28:27.379440: step: 1332/530, loss: 0.0001401424378855154
2023-01-23 04:28:28.491049: step: 1336/530, loss: 0.0016834258567541838
2023-01-23 04:28:29.606458: step: 1340/530, loss: 0.0017696380382403731
2023-01-23 04:28:30.754710: step: 1344/530, loss: 0.007561111822724342
2023-01-23 04:28:31.885559: step: 1348/530, loss: 3.337860107421875e-05
2023-01-23 04:28:33.065307: step: 1352/530, loss: 0.0014807701809331775
2023-01-23 04:28:34.165922: step: 1356/530, loss: 0.0010259627597406507
2023-01-23 04:28:35.282660: step: 1360/530, loss: 0.004295539576560259
2023-01-23 04:28:36.434233: step: 1364/530, loss: 0.00040435791015625
2023-01-23 04:28:37.594630: step: 1368/530, loss: 7.99179106252268e-05
2023-01-23 04:28:38.712300: step: 1372/530, loss: 3.919601658708416e-05
2023-01-23 04:28:39.845097: step: 1376/530, loss: 0.0005127430194988847
2023-01-23 04:28:40.950021: step: 1380/530, loss: 0.022951554507017136
2023-01-23 04:28:42.071306: step: 1384/530, loss: 0.03648862987756729
2023-01-23 04:28:43.200439: step: 1388/530, loss: 0.00014171600923873484
2023-01-23 04:28:44.331619: step: 1392/530, loss: 0.013144874945282936
2023-01-23 04:28:45.453278: step: 1396/530, loss: 1.430511474609375e-05
2023-01-23 04:28:46.562107: step: 1400/530, loss: 0.013997460715472698
2023-01-23 04:28:47.701412: step: 1404/530, loss: 0.0007356643909588456
2023-01-23 04:28:48.868629: step: 1408/530, loss: 0.00011672973778331652
2023-01-23 04:28:49.988373: step: 1412/530, loss: 0.00097999582067132
2023-01-23 04:28:51.120721: step: 1416/530, loss: 0.040242765098810196
2023-01-23 04:28:52.249106: step: 1420/530, loss: 0.0820918083190918
2023-01-23 04:28:53.416291: step: 1424/530, loss: 3.9386748539982364e-05
2023-01-23 04:28:54.550330: step: 1428/530, loss: 0.0012460709549486637
2023-01-23 04:28:55.684989: step: 1432/530, loss: 0.01254129409790039
2023-01-23 04:28:56.812122: step: 1436/530, loss: 1.487731969973538e-05
2023-01-23 04:28:57.919783: step: 1440/530, loss: 0.0012409210903570056
2023-01-23 04:28:59.027080: step: 1444/530, loss: 1.7023086911649443e-05
2023-01-23 04:29:00.151735: step: 1448/530, loss: 0.007244110107421875
2023-01-23 04:29:01.264261: step: 1452/530, loss: 4.863739013671875e-05
2023-01-23 04:29:02.409461: step: 1456/530, loss: 1.9073486328125e-05
2023-01-23 04:29:03.517154: step: 1460/530, loss: 2.2792815798311494e-05
2023-01-23 04:29:04.632664: step: 1464/530, loss: 0.0006019592401571572
2023-01-23 04:29:05.746909: step: 1468/530, loss: 0.0007682800060138106
2023-01-23 04:29:06.864302: step: 1472/530, loss: 0.0003310680331196636
2023-01-23 04:29:07.972495: step: 1476/530, loss: 7.467270188499242e-05
2023-01-23 04:29:09.105143: step: 1480/530, loss: 0.020303726196289062
2023-01-23 04:29:10.232173: step: 1484/530, loss: 0.027871323749423027
2023-01-23 04:29:11.372684: step: 1488/530, loss: 0.08097591251134872
2023-01-23 04:29:12.462727: step: 1492/530, loss: 8.7738037109375e-05
2023-01-23 04:29:13.585071: step: 1496/530, loss: 0.0005620956653729081
2023-01-23 04:29:14.698408: step: 1500/530, loss: 0.00018367767916060984
2023-01-23 04:29:15.818899: step: 1504/530, loss: 0.0002502441348042339
2023-01-23 04:29:16.940229: step: 1508/530, loss: 0.008749008178710938
2023-01-23 04:29:18.098378: step: 1512/530, loss: 0.00023584366135764867
2023-01-23 04:29:19.228560: step: 1516/530, loss: 0.0005668640369549394
2023-01-23 04:29:20.360667: step: 1520/530, loss: 0.0002513885556254536
2023-01-23 04:29:21.484908: step: 1524/530, loss: -8.39233416627394e-06
2023-01-23 04:29:22.616214: step: 1528/530, loss: 4.634857032215223e-05
2023-01-23 04:29:23.755271: step: 1532/530, loss: 0.0074217794463038445
2023-01-23 04:29:24.905121: step: 1536/530, loss: 0.061150550842285156
2023-01-23 04:29:26.045297: step: 1540/530, loss: 0.009557152166962624
2023-01-23 04:29:27.177117: step: 1544/530, loss: 0.029620077461004257
2023-01-23 04:29:28.327248: step: 1548/530, loss: 9.1552734375e-05
2023-01-23 04:29:29.493083: step: 1552/530, loss: 0.003959464840590954
2023-01-23 04:29:30.651256: step: 1556/530, loss: 1.2779236385540571e-05
2023-01-23 04:29:31.761919: step: 1560/530, loss: 1.850128137448337e-05
2023-01-23 04:29:32.886594: step: 1564/530, loss: 7.686615572310984e-05
2023-01-23 04:29:33.996522: step: 1568/530, loss: 1.144409225162235e-06
2023-01-23 04:29:35.112683: step: 1572/530, loss: 0.000873184239026159
2023-01-23 04:29:36.226697: step: 1576/530, loss: 0.01471166592091322
2023-01-23 04:29:37.369255: step: 1580/530, loss: 4.062652442371473e-05
2023-01-23 04:29:38.473706: step: 1584/530, loss: 1.1062621524615679e-05
2023-01-23 04:29:39.579476: step: 1588/530, loss: 0.11321940273046494
2023-01-23 04:29:40.715443: step: 1592/530, loss: 0.00165729527361691
2023-01-23 04:29:41.826094: step: 1596/530, loss: 0.00014109612675383687
2023-01-23 04:29:42.957799: step: 1600/530, loss: 0.044467777013778687
2023-01-23 04:29:44.052677: step: 1604/530, loss: 0.00013828277587890625
2023-01-23 04:29:45.164534: step: 1608/530, loss: 3.1805036996956915e-05
2023-01-23 04:29:46.311788: step: 1612/530, loss: 5.264282299322076e-05
2023-01-23 04:29:47.443184: step: 1616/530, loss: 0.0006480216979980469
2023-01-23 04:29:48.559245: step: 1620/530, loss: 0.21274375915527344
2023-01-23 04:29:49.660599: step: 1624/530, loss: 0.011458968743681908
2023-01-23 04:29:50.793640: step: 1628/530, loss: 0.3617177903652191
2023-01-23 04:29:51.926913: step: 1632/530, loss: 3.63349899998866e-05
2023-01-23 04:29:53.086886: step: 1636/530, loss: 4.959107172908261e-06
2023-01-23 04:29:54.211782: step: 1640/530, loss: 0.0006572723505087197
2023-01-23 04:29:55.323772: step: 1644/530, loss: 0.018769264221191406
2023-01-23 04:29:56.482058: step: 1648/530, loss: 0.032418251037597656
2023-01-23 04:29:57.578991: step: 1652/530, loss: 0.00014553070650435984
2023-01-23 04:29:58.704180: step: 1656/530, loss: 0.0023059844970703125
2023-01-23 04:29:59.820925: step: 1660/530, loss: 9.450913057662547e-05
2023-01-23 04:30:00.967695: step: 1664/530, loss: 0.037392616271972656
2023-01-23 04:30:02.104778: step: 1668/530, loss: 0.00015087128849700093
2023-01-23 04:30:03.212249: step: 1672/530, loss: 0.0036058425903320312
2023-01-23 04:30:04.343146: step: 1676/530, loss: 0.001372528146021068
2023-01-23 04:30:05.457862: step: 1680/530, loss: 0.001028347061946988
2023-01-23 04:30:06.585362: step: 1684/530, loss: 7.152557373046875e-06
2023-01-23 04:30:07.697651: step: 1688/530, loss: 0.0006948471418581903
2023-01-23 04:30:08.815243: step: 1692/530, loss: 0.0008212566608563066
2023-01-23 04:30:09.951080: step: 1696/530, loss: 3.707162618637085
2023-01-23 04:30:11.070481: step: 1700/530, loss: -1.010894811770413e-05
2023-01-23 04:30:12.205954: step: 1704/530, loss: 0.0007089615100994706
2023-01-23 04:30:13.345248: step: 1708/530, loss: 0.1291082352399826
2023-01-23 04:30:14.467268: step: 1712/530, loss: 0.007496833801269531
2023-01-23 04:30:15.589732: step: 1716/530, loss: 1.182556115963962e-05
2023-01-23 04:30:16.698069: step: 1720/530, loss: 0.005074024200439453
2023-01-23 04:30:17.831434: step: 1724/530, loss: 0.0012141228653490543
2023-01-23 04:30:18.958304: step: 1728/530, loss: 0.0007661819690838456
2023-01-23 04:30:20.102529: step: 1732/530, loss: 0.020349977537989616
2023-01-23 04:30:21.203182: step: 1736/530, loss: 0.0003414154052734375
2023-01-23 04:30:22.329094: step: 1740/530, loss: 0.007851791568100452
2023-01-23 04:30:23.468371: step: 1744/530, loss: 4.215240551275201e-05
2023-01-23 04:30:24.625178: step: 1748/530, loss: 0.0511111281812191
2023-01-23 04:30:25.731642: step: 1752/530, loss: 0.006505107972770929
2023-01-23 04:30:26.881265: step: 1756/530, loss: 0.0012559890747070312
2023-01-23 04:30:28.010432: step: 1760/530, loss: 0.0036535263061523438
2023-01-23 04:30:29.133488: step: 1764/530, loss: 0.00010719298734329641
2023-01-23 04:30:30.273651: step: 1768/530, loss: 0.016880227252840996
2023-01-23 04:30:31.383138: step: 1772/530, loss: 0.001476287841796875
2023-01-23 04:30:32.501361: step: 1776/530, loss: 7.352829561568797e-05
2023-01-23 04:30:33.645738: step: 1780/530, loss: 0.00015754700871184468
2023-01-23 04:30:34.762155: step: 1784/530, loss: 4.882812572759576e-05
2023-01-23 04:30:35.867260: step: 1788/530, loss: 0.005413055885583162
2023-01-23 04:30:37.010469: step: 1792/530, loss: 0.0055335042998194695
2023-01-23 04:30:38.128657: step: 1796/530, loss: 0.0014709711540490389
2023-01-23 04:30:39.248879: step: 1800/530, loss: 0.020827293395996094
2023-01-23 04:30:40.388503: step: 1804/530, loss: 0.015207291580736637
2023-01-23 04:30:41.522510: step: 1808/530, loss: 0.0009137630695477128
2023-01-23 04:30:42.646266: step: 1812/530, loss: -1.8596649624669226e-06
2023-01-23 04:30:43.755390: step: 1816/530, loss: 0.0003429412900004536
2023-01-23 04:30:44.893683: step: 1820/530, loss: 6.67572021484375e-06
2023-01-23 04:30:46.017993: step: 1824/530, loss: 7.095337059581652e-05
2023-01-23 04:30:47.145680: step: 1828/530, loss: 4.348754737293348e-05
2023-01-23 04:30:48.253295: step: 1832/530, loss: 6.904602196300402e-05
2023-01-23 04:30:49.365508: step: 1836/530, loss: 1.1444091796875e-05
2023-01-23 04:30:50.468053: step: 1840/530, loss: 2.9850007194909267e-05
2023-01-23 04:30:51.565020: step: 1844/530, loss: 0.008457946591079235
2023-01-23 04:30:52.693372: step: 1848/530, loss: 1.9550323486328125e-05
2023-01-23 04:30:53.803231: step: 1852/530, loss: 1.5735627130197827e-06
2023-01-23 04:30:54.942804: step: 1856/530, loss: 2.0313264030846767e-05
2023-01-23 04:30:56.063958: step: 1860/530, loss: 8.20159948489163e-06
2023-01-23 04:30:57.191574: step: 1864/530, loss: 0.00018796921358443797
2023-01-23 04:30:58.292953: step: 1868/530, loss: 5.722044988942798e-07
2023-01-23 04:30:59.421525: step: 1872/530, loss: 0.0005973816150799394
2023-01-23 04:31:00.538429: step: 1876/530, loss: 4.959107172908261e-06
2023-01-23 04:31:01.651797: step: 1880/530, loss: 0.0010441780323162675
2023-01-23 04:31:02.756331: step: 1884/530, loss: 0.00104017264675349
2023-01-23 04:31:03.873119: step: 1888/530, loss: 0.007729530334472656
2023-01-23 04:31:05.003709: step: 1892/530, loss: 1.1444091796875e-05
2023-01-23 04:31:06.094839: step: 1896/530, loss: 9.536744073557202e-06
2023-01-23 04:31:07.244661: step: 1900/530, loss: 5.1212311518611386e-05
2023-01-23 04:31:08.358695: step: 1904/530, loss: 3.757476952159777e-05
2023-01-23 04:31:09.492291: step: 1908/530, loss: 0.0032654760871082544
2023-01-23 04:31:10.627859: step: 1912/530, loss: 0.00033016205998137593
2023-01-23 04:31:11.744932: step: 1916/530, loss: 0.015048027969896793
2023-01-23 04:31:12.852824: step: 1920/530, loss: 0.041097067296504974
2023-01-23 04:31:13.947358: step: 1924/530, loss: 0.012709617614746094
2023-01-23 04:31:15.070688: step: 1928/530, loss: 0.07657375186681747
2023-01-23 04:31:16.195349: step: 1932/530, loss: 0.0003211974981240928
2023-01-23 04:31:17.342413: step: 1936/530, loss: 0.0002628326474223286
2023-01-23 04:31:18.467686: step: 1940/530, loss: 0.0007530212169513106
2023-01-23 04:31:19.580211: step: 1944/530, loss: 0.0001944542018463835
2023-01-23 04:31:20.703510: step: 1948/530, loss: 4.138946678722277e-05
2023-01-23 04:31:21.851175: step: 1952/530, loss: 1.5258810890372843e-06
2023-01-23 04:31:22.970699: step: 1956/530, loss: 2.4414061044808477e-05
2023-01-23 04:31:24.086305: step: 1960/530, loss: 0.0005186080816201866
2023-01-23 04:31:25.207226: step: 1964/530, loss: 1.8596649169921875e-05
2023-01-23 04:31:26.320865: step: 1968/530, loss: 0.00014038087101653218
2023-01-23 04:31:27.477300: step: 1972/530, loss: 0.017737960442900658
2023-01-23 04:31:28.655335: step: 1976/530, loss: 0.05726933479309082
2023-01-23 04:31:29.810169: step: 1980/530, loss: 0.0063987732864916325
2023-01-23 04:31:30.925080: step: 1984/530, loss: 0.010416317731142044
2023-01-23 04:31:32.088718: step: 1988/530, loss: 1.411438006471144e-05
2023-01-23 04:31:33.195136: step: 1992/530, loss: 4.57763690064894e-06
2023-01-23 04:31:34.351970: step: 1996/530, loss: 0.0006276131025515497
2023-01-23 04:31:35.469627: step: 2000/530, loss: 0.027610303834080696
2023-01-23 04:31:36.583308: step: 2004/530, loss: 0.0029823302756994963
2023-01-23 04:31:37.698548: step: 2008/530, loss: 8.106231689453125e-06
2023-01-23 04:31:38.819976: step: 2012/530, loss: 0.007798385806381702
2023-01-23 04:31:39.939166: step: 2016/530, loss: 0.002561855362728238
2023-01-23 04:31:41.054499: step: 2020/530, loss: 0.009146117605268955
2023-01-23 04:31:42.173120: step: 2024/530, loss: 0.08603902161121368
2023-01-23 04:31:43.314100: step: 2028/530, loss: 0.0023164749145507812
2023-01-23 04:31:44.457466: step: 2032/530, loss: 0.00018539429584052414
2023-01-23 04:31:45.552143: step: 2036/530, loss: 0.0003789901966229081
2023-01-23 04:31:46.683345: step: 2040/530, loss: 0.0009212493896484375
2023-01-23 04:31:47.816561: step: 2044/530, loss: 0.0001682281435932964
2023-01-23 04:31:48.934825: step: 2048/530, loss: 0.0015082359313964844
2023-01-23 04:31:50.052651: step: 2052/530, loss: 0.0013895988231524825
2023-01-23 04:31:51.194607: step: 2056/530, loss: 5.874633643543348e-05
2023-01-23 04:31:52.314179: step: 2060/530, loss: 0.0005882263649255037
2023-01-23 04:31:53.446885: step: 2064/530, loss: 9.422301809536293e-05
2023-01-23 04:31:54.566000: step: 2068/530, loss: 0.034859661012887955
2023-01-23 04:31:55.671363: step: 2072/530, loss: 1.163482647825731e-05
2023-01-23 04:31:56.788335: step: 2076/530, loss: 4.19616708313697e-06
2023-01-23 04:31:57.907049: step: 2080/530, loss: 0.0001239776611328125
2023-01-23 04:31:59.011806: step: 2084/530, loss: 0.00015316010103560984
2023-01-23 04:32:00.121148: step: 2088/530, loss: 0.005597210023552179
2023-01-23 04:32:01.233488: step: 2092/530, loss: 0.029268836602568626
2023-01-23 04:32:02.391323: step: 2096/530, loss: 0.0008559227571822703
2023-01-23 04:32:03.500165: step: 2100/530, loss: 0.4550245404243469
2023-01-23 04:32:04.615343: step: 2104/530, loss: 0.00037784577580168843
2023-01-23 04:32:05.744359: step: 2108/530, loss: 0.0013015747535973787
2023-01-23 04:32:06.939652: step: 2112/530, loss: 6.29425048828125e-05
2023-01-23 04:32:08.060055: step: 2116/530, loss: 0.0007175445789471269
2023-01-23 04:32:09.197488: step: 2120/530, loss: 0.0687929168343544
==================================================
Loss: 0.022
--------------------
Dev: {'event': {'p': 0.6204301075268818, 'r': 0.7683089214380826, 'f1': 0.6864961332540155}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 28}
Test: {'event': {'p': 0.639605818864383, 'r': 0.7788571428571428, 'f1': 0.7023962896160783}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 28}
Chinese: {'event': {'p': 0.6447368421052632, 'r': 0.9074074074074074, 'f1': 0.7538461538461537}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 28}
Korean: {'event': {'p': 0.7083333333333334, 'r': 0.5396825396825397, 'f1': 0.6126126126126126}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 28}
Russian: {'event': {'p': 0.525, 'r': 0.5833333333333334, 'f1': 0.5526315789473685}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 28}
New best chinese model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6204301075268818, 'r': 0.7683089214380826, 'f1': 0.6864961332540155}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 28}
Eng Test for Chinese: {'event': {'p': 0.639605818864383, 'r': 0.7788571428571428, 'f1': 0.7023962896160783}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 28}
Sample Chinese: {'event': {'p': 0.6447368421052632, 'r': 0.9074074074074074, 'f1': 0.7538461538461537}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 28}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6288770053475936, 'r': 0.7829560585885486, 'f1': 0.697508896797153}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Korean: {'event': {'p': 0.64058795637743, 'r': 0.772, 'f1': 0.7001813941435606}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Korean: {'event': {'p': 0.6851851851851852, 'r': 0.5873015873015873, 'f1': 0.6324786324786325}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5319148936170213, 'r': 0.6944444444444444, 'f1': 0.6024096385542169}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
******************************
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 04:32:55.007714: step: 4/530, loss: 0.00079345703125
2023-01-23 04:32:56.161554: step: 8/530, loss: 1.5509127479163e-05
2023-01-23 04:32:57.266685: step: 12/530, loss: 0.019551753997802734
2023-01-23 04:32:58.376193: step: 16/530, loss: 0.021620750427246094
2023-01-23 04:32:59.508339: step: 20/530, loss: 1.1253358024987392e-05
2023-01-23 04:33:00.652611: step: 24/530, loss: 0.04051017761230469
2023-01-23 04:33:01.781051: step: 28/530, loss: 9.975433204090223e-05
2023-01-23 04:33:02.903875: step: 32/530, loss: 0.0012271881569176912
2023-01-23 04:33:04.028044: step: 36/530, loss: 0.0005517005920410156
2023-01-23 04:33:05.135692: step: 40/530, loss: 0.017620563507080078
2023-01-23 04:33:06.254585: step: 44/530, loss: 0.011277580633759499
2023-01-23 04:33:07.382752: step: 48/530, loss: 0.002271413803100586
2023-01-23 04:33:08.544360: step: 52/530, loss: 0.0003104209899902344
2023-01-23 04:33:09.660010: step: 56/530, loss: 0.010919761843979359
2023-01-23 04:33:10.808046: step: 60/530, loss: 0.013683080673217773
2023-01-23 04:33:11.935340: step: 64/530, loss: 0.006194401066750288
2023-01-23 04:33:13.043173: step: 68/530, loss: 1.4400481632037554e-05
2023-01-23 04:33:14.162968: step: 72/530, loss: 0.0048118592239916325
2023-01-23 04:33:15.267684: step: 76/530, loss: 2.174377368646674e-05
2023-01-23 04:33:16.380252: step: 80/530, loss: 9.536744300930877e-07
2023-01-23 04:33:17.510786: step: 84/530, loss: 0.04347953572869301
2023-01-23 04:33:18.619263: step: 88/530, loss: 0.00010375976853538305
2023-01-23 04:33:19.719068: step: 92/530, loss: 0.002568531082943082
2023-01-23 04:33:20.855272: step: 96/530, loss: 5.53131121705519e-06
2023-01-23 04:33:21.998627: step: 100/530, loss: 2.841949390131049e-05
2023-01-23 04:33:23.108609: step: 104/530, loss: 0.010214042849838734
2023-01-23 04:33:24.289094: step: 108/530, loss: 0.0001184463471872732
2023-01-23 04:33:25.435359: step: 112/530, loss: 9.460448927711695e-05
2023-01-23 04:33:26.542032: step: 116/530, loss: 0.44897136092185974
2023-01-23 04:33:27.651514: step: 120/530, loss: 8.96453857421875e-05
2023-01-23 04:33:28.778136: step: 124/530, loss: 0.007636642549186945
2023-01-23 04:33:29.887330: step: 128/530, loss: 7.314682443393394e-05
2023-01-23 04:33:31.002917: step: 132/530, loss: 1.106262243411038e-05
2023-01-23 04:33:32.156381: step: 136/530, loss: 2.460479663568549e-05
2023-01-23 04:33:33.266790: step: 140/530, loss: 2.956390289909905e-06
2023-01-23 04:33:34.374112: step: 144/530, loss: 2.288818359375e-05
2023-01-23 04:33:35.492642: step: 148/530, loss: 0.018181229010224342
2023-01-23 04:33:36.653631: step: 152/530, loss: 0.019393444061279297
2023-01-23 04:33:37.769146: step: 156/530, loss: 3.051757857974735e-06
2023-01-23 04:33:38.887411: step: 160/530, loss: 0.0005416870699264109
2023-01-23 04:33:40.017440: step: 164/530, loss: 0.012201404199004173
2023-01-23 04:33:41.162660: step: 168/530, loss: 0.054689787328243256
2023-01-23 04:33:42.293722: step: 172/530, loss: 0.12627945840358734
2023-01-23 04:33:43.405507: step: 176/530, loss: 0.0007482529035769403
2023-01-23 04:33:44.495224: step: 180/530, loss: 1.544952465337701e-05
2023-01-23 04:33:45.619463: step: 184/530, loss: 1.3828277587890625e-05
2023-01-23 04:33:46.742415: step: 188/530, loss: 8.220673043979332e-05
2023-01-23 04:33:47.857557: step: 192/530, loss: 2.670288040462765e-06
2023-01-23 04:33:48.980592: step: 196/530, loss: 0.005424118135124445
2023-01-23 04:33:50.112903: step: 200/530, loss: 2.6702882678364404e-06
2023-01-23 04:33:51.234177: step: 204/530, loss: 0.025966264307498932
2023-01-23 04:33:52.350439: step: 208/530, loss: 1.8978118532686494e-05
2023-01-23 04:33:53.496009: step: 212/530, loss: 0.00042548179044388235
2023-01-23 04:33:54.666857: step: 216/530, loss: 0.0030125619377940893
2023-01-23 04:33:55.790467: step: 220/530, loss: 0.014338708482682705
2023-01-23 04:33:56.927027: step: 224/530, loss: 0.00021138192096259445
2023-01-23 04:33:58.013788: step: 228/530, loss: 2.6702882678364404e-06
2023-01-23 04:33:59.124183: step: 232/530, loss: -5.5313107623078395e-06
2023-01-23 04:34:00.235082: step: 236/530, loss: 0.00017042159743141383
2023-01-23 04:34:01.368075: step: 240/530, loss: 1.6975405742414296e-05
2023-01-23 04:34:02.502225: step: 244/530, loss: 0.0014446259010583162
2023-01-23 04:34:03.612308: step: 248/530, loss: 8.616447303211316e-05
2023-01-23 04:34:04.701913: step: 252/530, loss: 0.0004924774402752519
2023-01-23 04:34:05.826221: step: 256/530, loss: 1.62124638336536e-06
2023-01-23 04:34:06.933559: step: 260/530, loss: 0.000396728515625
2023-01-23 04:34:08.055918: step: 264/530, loss: 4.978180004400201e-05
2023-01-23 04:34:09.190868: step: 268/530, loss: 0.0004265785391908139
2023-01-23 04:34:10.353418: step: 272/530, loss: -1.3351441339182202e-06
2023-01-23 04:34:11.463316: step: 276/530, loss: 4.38690185546875e-05
2023-01-23 04:34:12.562924: step: 280/530, loss: 0.0010662078857421875
2023-01-23 04:34:13.717061: step: 284/530, loss: 6.809234037064016e-05
2023-01-23 04:34:14.826002: step: 288/530, loss: 0.00013213157944846898
2023-01-23 04:34:15.951396: step: 292/530, loss: 0.00015316010103560984
2023-01-23 04:34:17.083142: step: 296/530, loss: 0.0009434223757125437
2023-01-23 04:34:18.236275: step: 300/530, loss: 0.007957267574965954
2023-01-23 04:34:19.369374: step: 304/530, loss: 0.11589831858873367
2023-01-23 04:34:20.503801: step: 308/530, loss: 0.002113723661750555
2023-01-23 04:34:21.620365: step: 312/530, loss: 0.00020542144193314016
2023-01-23 04:34:22.761544: step: 316/530, loss: 5.874633643543348e-05
2023-01-23 04:34:23.880118: step: 320/530, loss: 0.0035803914070129395
2023-01-23 04:34:25.011825: step: 324/530, loss: 0.0015953064430505037
2023-01-23 04:34:26.120353: step: 328/530, loss: 4.062652442371473e-05
2023-01-23 04:34:27.245379: step: 332/530, loss: 4.3487551010912284e-05
2023-01-23 04:34:28.377531: step: 336/530, loss: 8.39233416627394e-06
2023-01-23 04:34:29.524146: step: 340/530, loss: 0.0023468018043786287
2023-01-23 04:34:30.739664: step: 344/530, loss: 0.001714515732601285
2023-01-23 04:34:31.876821: step: 348/530, loss: 0.00026216506375931203
2023-01-23 04:34:32.995474: step: 352/530, loss: 0.0325162410736084
2023-01-23 04:34:34.089788: step: 356/530, loss: 0.00040836335392668843
2023-01-23 04:34:35.235357: step: 360/530, loss: 0.014062691479921341
2023-01-23 04:34:36.356467: step: 364/530, loss: 0.00017700194439385086
2023-01-23 04:34:37.473377: step: 368/530, loss: 0.0025928497780114412
2023-01-23 04:34:38.590929: step: 372/530, loss: 0.0033207894302904606
2023-01-23 04:34:39.671390: step: 376/530, loss: 2.8038026357535273e-05
2023-01-23 04:34:40.780856: step: 380/530, loss: 6.10351571594947e-06
2023-01-23 04:34:41.900692: step: 384/530, loss: 7.152557373046875e-06
2023-01-23 04:34:43.042155: step: 388/530, loss: 0.038664769381284714
2023-01-23 04:34:44.170650: step: 392/530, loss: 1.487731969973538e-05
2023-01-23 04:34:45.302884: step: 396/530, loss: 0.05026111751794815
2023-01-23 04:34:46.411437: step: 400/530, loss: 0.00047369004460051656
2023-01-23 04:34:47.532875: step: 404/530, loss: 3.3950807846849784e-05
2023-01-23 04:34:48.645772: step: 408/530, loss: 0.004271125886589289
2023-01-23 04:34:49.752424: step: 412/530, loss: 0.06146135553717613
2023-01-23 04:34:50.845567: step: 416/530, loss: 0.00027561187744140625
2023-01-23 04:34:51.970601: step: 420/530, loss: 0.013042259030044079
2023-01-23 04:34:53.071448: step: 424/530, loss: 0.027518462389707565
2023-01-23 04:34:54.166076: step: 428/530, loss: 0.0008126259199343622
2023-01-23 04:34:55.264563: step: 432/530, loss: 7.82012921263231e-06
2023-01-23 04:34:56.407231: step: 436/530, loss: 0.0009278059005737305
2023-01-23 04:34:57.567457: step: 440/530, loss: 0.0014368057018145919
2023-01-23 04:34:58.685306: step: 444/530, loss: 0.034787844866514206
2023-01-23 04:34:59.806034: step: 448/530, loss: 0.00036087038461118937
2023-01-23 04:35:00.924068: step: 452/530, loss: 0.0007333755493164062
2023-01-23 04:35:02.095087: step: 456/530, loss: 0.008822965435683727
2023-01-23 04:35:03.216221: step: 460/530, loss: 0.02304835431277752
2023-01-23 04:35:04.379909: step: 464/530, loss: 0.00293560023419559
2023-01-23 04:35:05.504773: step: 468/530, loss: 5.2738188969669864e-05
2023-01-23 04:35:06.629680: step: 472/530, loss: 0.061448004096746445
2023-01-23 04:35:07.755061: step: 476/530, loss: 0.08494148403406143
2023-01-23 04:35:08.896100: step: 480/530, loss: 0.009108400903642178
2023-01-23 04:35:10.038551: step: 484/530, loss: 0.01986703835427761
2023-01-23 04:35:11.163952: step: 488/530, loss: 0.014183616265654564
2023-01-23 04:35:12.353017: step: 492/530, loss: 0.0032669068314135075
2023-01-23 04:35:13.449830: step: 496/530, loss: 0.22437401115894318
2023-01-23 04:35:14.560544: step: 500/530, loss: 0.015742206946015358
2023-01-23 04:35:15.681783: step: 504/530, loss: 1.2302398317842744e-05
2023-01-23 04:35:16.838904: step: 508/530, loss: 0.00033054352388717234
2023-01-23 04:35:17.947517: step: 512/530, loss: 0.035310935229063034
2023-01-23 04:35:19.059301: step: 516/530, loss: 0.00014743805513717234
2023-01-23 04:35:20.158521: step: 520/530, loss: 1.659393274167087e-05
2023-01-23 04:35:21.252290: step: 524/530, loss: 0.0001928329438669607
2023-01-23 04:35:22.344791: step: 528/530, loss: 1.735687328618951e-05
2023-01-23 04:35:23.481060: step: 532/530, loss: 0.0001472473086323589
2023-01-23 04:35:24.615921: step: 536/530, loss: 0.00209388742223382
2023-01-23 04:35:25.718114: step: 540/530, loss: 0.0001644134463276714
2023-01-23 04:35:26.876588: step: 544/530, loss: 0.00508384732529521
2023-01-23 04:35:27.988268: step: 548/530, loss: 0.002101993653923273
2023-01-23 04:35:29.099169: step: 552/530, loss: 0.03772277757525444
2023-01-23 04:35:30.241567: step: 556/530, loss: 0.00019149780564475805
2023-01-23 04:35:31.371460: step: 560/530, loss: 6.942749314475805e-05
2023-01-23 04:35:32.496393: step: 564/530, loss: 0.09079819172620773
2023-01-23 04:35:33.620659: step: 568/530, loss: 0.0001126289353123866
2023-01-23 04:35:34.707149: step: 572/530, loss: 0.0027053833473473787
2023-01-23 04:35:35.797431: step: 576/530, loss: 0.0010382652981206775
2023-01-23 04:35:36.928813: step: 580/530, loss: 0.00031909943209029734
2023-01-23 04:35:38.059405: step: 584/530, loss: 0.000604820204898715
2023-01-23 04:35:39.183634: step: 588/530, loss: 5.9127810345671605e-06
2023-01-23 04:35:40.314382: step: 592/530, loss: 0.0003447532653808594
2023-01-23 04:35:41.479330: step: 596/530, loss: 0.00018482207087799907
2023-01-23 04:35:42.590855: step: 600/530, loss: 0.009919453412294388
2023-01-23 04:35:43.730037: step: 604/530, loss: 3.44276413670741e-05
2023-01-23 04:35:44.847738: step: 608/530, loss: 0.006410503294318914
2023-01-23 04:35:45.973948: step: 612/530, loss: 0.00015934706607367843
2023-01-23 04:35:47.122115: step: 616/530, loss: 0.01974477805197239
2023-01-23 04:35:48.239228: step: 620/530, loss: 0.011882972903549671
2023-01-23 04:35:49.365092: step: 624/530, loss: 1.5735631677671336e-06
2023-01-23 04:35:50.465175: step: 628/530, loss: 0.0017063141567632556
2023-01-23 04:35:51.570062: step: 632/530, loss: 0.0005319595220498741
2023-01-23 04:35:52.726238: step: 636/530, loss: 0.004999542608857155
2023-01-23 04:35:53.813237: step: 640/530, loss: 0.00010442733764648438
2023-01-23 04:35:54.939654: step: 644/530, loss: 0.04184231907129288
2023-01-23 04:35:56.052263: step: 648/530, loss: 0.00018548966909293085
2023-01-23 04:35:57.201692: step: 652/530, loss: 0.017480850219726562
2023-01-23 04:35:58.371702: step: 656/530, loss: 0.0011454581981524825
2023-01-23 04:35:59.480079: step: 660/530, loss: 1.6021729607018642e-05
2023-01-23 04:36:00.572173: step: 664/530, loss: 2.6130677724722773e-05
2023-01-23 04:36:01.709214: step: 668/530, loss: 0.03771800920367241
2023-01-23 04:36:02.839781: step: 672/530, loss: 9.226799193129409e-06
2023-01-23 04:36:03.950765: step: 676/530, loss: 7.677078974666074e-05
2023-01-23 04:36:05.075319: step: 680/530, loss: 0.04489760473370552
2023-01-23 04:36:06.172697: step: 684/530, loss: 0.015763282775878906
2023-01-23 04:36:07.318869: step: 688/530, loss: 0.0006033897516317666
2023-01-23 04:36:08.473611: step: 692/530, loss: 0.0003755569632630795
2023-01-23 04:36:09.590964: step: 696/530, loss: 0.0007669448968954384
2023-01-23 04:36:10.708353: step: 700/530, loss: 4.291534423828125e-06
2023-01-23 04:36:11.824185: step: 704/530, loss: 0.0007427215459756553
2023-01-23 04:36:12.952662: step: 708/530, loss: 0.00571098318323493
2023-01-23 04:36:14.093794: step: 712/530, loss: 0.011141491122543812
2023-01-23 04:36:15.196975: step: 716/530, loss: 1.430511474609375e-06
2023-01-23 04:36:16.312062: step: 720/530, loss: 0.20702685415744781
2023-01-23 04:36:17.445085: step: 724/530, loss: 0.012928485870361328
2023-01-23 04:36:18.564176: step: 728/530, loss: 0.002323722932487726
2023-01-23 04:36:19.672831: step: 732/530, loss: 0.020373154431581497
2023-01-23 04:36:20.793929: step: 736/530, loss: 0.008115767501294613
2023-01-23 04:36:21.891885: step: 740/530, loss: 0.0003360748232807964
2023-01-23 04:36:22.997846: step: 744/530, loss: 0.12447166442871094
2023-01-23 04:36:24.155014: step: 748/530, loss: 5.2118302846793085e-05
2023-01-23 04:36:25.281841: step: 752/530, loss: 0.0001142501860158518
2023-01-23 04:36:26.403451: step: 756/530, loss: 0.0004748344363179058
2023-01-23 04:36:27.515367: step: 760/530, loss: 0.015793515369296074
2023-01-23 04:36:28.645102: step: 764/530, loss: 0.00022301674471236765
2023-01-23 04:36:29.791130: step: 768/530, loss: 0.1791359931230545
2023-01-23 04:36:30.923052: step: 772/530, loss: 0.0017072678310796618
2023-01-23 04:36:32.038176: step: 776/530, loss: 0.0023328782990574837
2023-01-23 04:36:33.126145: step: 780/530, loss: 0.0023365020751953125
2023-01-23 04:36:34.227141: step: 784/530, loss: 8.361339860130101e-05
2023-01-23 04:36:35.340382: step: 788/530, loss: 0.006721973419189453
2023-01-23 04:36:36.489258: step: 792/530, loss: 3.2949446904240176e-05
2023-01-23 04:36:37.632296: step: 796/530, loss: 0.004120540805160999
2023-01-23 04:36:38.775828: step: 800/530, loss: 3.1805036996956915e-05
2023-01-23 04:36:39.922024: step: 804/530, loss: 0.0010140062076970935
2023-01-23 04:36:41.053893: step: 808/530, loss: 0.0009886741172522306
2023-01-23 04:36:42.164119: step: 812/530, loss: 0.0016706467140465975
2023-01-23 04:36:43.283477: step: 816/530, loss: 0.0001350402890238911
2023-01-23 04:36:44.379562: step: 820/530, loss: 0.0010343551402911544
2023-01-23 04:36:45.524823: step: 824/530, loss: 0.00015325545973610133
2023-01-23 04:36:46.647279: step: 828/530, loss: -8.96453821042087e-06
2023-01-23 04:36:47.776019: step: 832/530, loss: 0.00033946038456633687
2023-01-23 04:36:48.884984: step: 836/530, loss: 0.025153733789920807
2023-01-23 04:36:50.012162: step: 840/530, loss: 1.8882752556237392e-05
2023-01-23 04:36:51.146430: step: 844/530, loss: 0.0014745712978765368
2023-01-23 04:36:52.283298: step: 848/530, loss: 0.00015897752018645406
2023-01-23 04:36:53.396286: step: 852/530, loss: 5.574226088356227e-05
2023-01-23 04:36:54.497135: step: 856/530, loss: 0.00037593842716887593
2023-01-23 04:36:55.652763: step: 860/530, loss: 4.081726001459174e-05
2023-01-23 04:36:56.759514: step: 864/530, loss: 0.0012316703796386719
2023-01-23 04:36:57.906579: step: 868/530, loss: 0.0010339736472815275
2023-01-23 04:36:59.047254: step: 872/530, loss: 0.00020675659470725805
2023-01-23 04:37:00.154166: step: 876/530, loss: 0.004602527711540461
2023-01-23 04:37:01.291872: step: 880/530, loss: 0.00017337800818495452
2023-01-23 04:37:02.429574: step: 884/530, loss: 0.03265686333179474
2023-01-23 04:37:03.557368: step: 888/530, loss: 0.01048431359231472
2023-01-23 04:37:04.659195: step: 892/530, loss: 6.86645489622606e-06
2023-01-23 04:37:05.776653: step: 896/530, loss: 0.006386566441506147
2023-01-23 04:37:06.904714: step: 900/530, loss: 3.833770824712701e-05
2023-01-23 04:37:08.044224: step: 904/530, loss: 8.010864803509321e-06
2023-01-23 04:37:09.156472: step: 908/530, loss: 0.0010983466636389494
2023-01-23 04:37:10.293730: step: 912/530, loss: 1.5163421267061494e-05
2023-01-23 04:37:11.424610: step: 916/530, loss: 0.00011682510375976562
2023-01-23 04:37:12.566680: step: 920/530, loss: 1.583099401614163e-05
2023-01-23 04:37:13.722460: step: 924/530, loss: 2.1076200937386602e-05
2023-01-23 04:37:14.844601: step: 928/530, loss: 0.0025695799849927425
2023-01-23 04:37:16.011414: step: 932/530, loss: -3.623962356869015e-06
2023-01-23 04:37:17.128954: step: 936/530, loss: 0.0005474090576171875
2023-01-23 04:37:18.232421: step: 940/530, loss: 8.292197890114039e-05
2023-01-23 04:37:19.350790: step: 944/530, loss: 0.0005310059059411287
2023-01-23 04:37:20.520731: step: 948/530, loss: -3.814698175119702e-07
2023-01-23 04:37:21.640690: step: 952/530, loss: 0.0001771926908986643
2023-01-23 04:37:22.762991: step: 956/530, loss: 0.01968097686767578
2023-01-23 04:37:23.861681: step: 960/530, loss: 0.0007839202880859375
2023-01-23 04:37:24.994776: step: 964/530, loss: 0.006590843666344881
2023-01-23 04:37:26.082075: step: 968/530, loss: -6.29425039733178e-06
2023-01-23 04:37:27.199350: step: 972/530, loss: 0.7183490991592407
2023-01-23 04:37:28.351047: step: 976/530, loss: -5.722045557376987e-07
2023-01-23 04:37:29.471469: step: 980/530, loss: 2.765655608527595e-06
2023-01-23 04:37:30.605317: step: 984/530, loss: 0.00017633438983466476
2023-01-23 04:37:31.730224: step: 988/530, loss: 6.523132469737902e-05
2023-01-23 04:37:32.839423: step: 992/530, loss: 3.2138825190486386e-05
2023-01-23 04:37:33.965307: step: 996/530, loss: 0.00048065185546875
2023-01-23 04:37:35.082189: step: 1000/530, loss: 2.4795533590804553e-06
2023-01-23 04:37:36.206642: step: 1004/530, loss: 0.011059284210205078
2023-01-23 04:37:37.314500: step: 1008/530, loss: 4.940032886224799e-05
2023-01-23 04:37:38.454166: step: 1012/530, loss: 3.814697265625e-05
2023-01-23 04:37:39.579070: step: 1016/530, loss: 3.509521411615424e-05
2023-01-23 04:37:40.705946: step: 1020/530, loss: 0.0050761220045387745
2023-01-23 04:37:41.885296: step: 1024/530, loss: 0.011490631848573685
2023-01-23 04:37:43.013678: step: 1028/530, loss: 0.00021901131549384445
2023-01-23 04:37:44.121985: step: 1032/530, loss: 0.09355153888463974
2023-01-23 04:37:45.240876: step: 1036/530, loss: 4.9591064453125e-05
2023-01-23 04:37:46.352839: step: 1040/530, loss: 3.414153979974799e-05
2023-01-23 04:37:47.492746: step: 1044/530, loss: 0.009853744879364967
2023-01-23 04:37:48.635295: step: 1048/530, loss: 0.011802864260971546
2023-01-23 04:37:49.753381: step: 1052/530, loss: 0.0032684325706213713
2023-01-23 04:37:50.877014: step: 1056/530, loss: 0.0016590118175372481
2023-01-23 04:37:51.985174: step: 1060/530, loss: 0.04302871227264404
2023-01-23 04:37:53.102979: step: 1064/530, loss: 2.422332727292087e-05
2023-01-23 04:37:54.215638: step: 1068/530, loss: 1.583099401614163e-05
2023-01-23 04:37:55.326087: step: 1072/530, loss: 0.00019731521024368703
2023-01-23 04:37:56.456537: step: 1076/530, loss: 0.00016350747318938375
2023-01-23 04:37:57.562207: step: 1080/530, loss: 1.71661376953125e-05
2023-01-23 04:37:58.659102: step: 1084/530, loss: 0.4312833547592163
2023-01-23 04:37:59.783148: step: 1088/530, loss: 0.0005179405561648309
2023-01-23 04:38:00.927228: step: 1092/530, loss: 0.0004741668817587197
2023-01-23 04:38:02.104832: step: 1096/530, loss: 0.005675507243722677
2023-01-23 04:38:03.215917: step: 1100/530, loss: 0.031122399494051933
2023-01-23 04:38:04.351013: step: 1104/530, loss: 0.0034559250343590975
2023-01-23 04:38:05.472813: step: 1108/530, loss: 0.0001655578671488911
2023-01-23 04:38:06.605729: step: 1112/530, loss: -4.00543194700731e-06
2023-01-23 04:38:07.726644: step: 1116/530, loss: 1.9073486328125e-06
2023-01-23 04:38:08.838087: step: 1120/530, loss: 2.3937225705594756e-05
2023-01-23 04:38:09.972678: step: 1124/530, loss: 0.00945138931274414
2023-01-23 04:38:11.118354: step: 1128/530, loss: 0.08567800372838974
2023-01-23 04:38:12.247565: step: 1132/530, loss: 0.020180892199277878
2023-01-23 04:38:13.384468: step: 1136/530, loss: 0.0748104527592659
2023-01-23 04:38:14.486748: step: 1140/530, loss: 0.0011360167991369963
2023-01-23 04:38:15.588492: step: 1144/530, loss: 0.0010410308605059981
2023-01-23 04:38:16.691671: step: 1148/530, loss: 3.8623809814453125e-05
2023-01-23 04:38:17.832816: step: 1152/530, loss: 0.005289745517075062
2023-01-23 04:38:18.932749: step: 1156/530, loss: 0.00014171600923873484
2023-01-23 04:38:20.074748: step: 1160/530, loss: 0.01902141608297825
2023-01-23 04:38:21.180213: step: 1164/530, loss: 0.0044425963424146175
2023-01-23 04:38:22.322178: step: 1168/530, loss: 0.0018917083507403731
2023-01-23 04:38:23.464410: step: 1172/530, loss: -1.9073486328125e-06
2023-01-23 04:38:24.602485: step: 1176/530, loss: 9.183883958030492e-05
2023-01-23 04:38:25.726035: step: 1180/530, loss: 5.226135181146674e-05
2023-01-23 04:38:26.861072: step: 1184/530, loss: 0.00020675659470725805
2023-01-23 04:38:28.002610: step: 1188/530, loss: 0.003336047986522317
2023-01-23 04:38:29.137410: step: 1192/530, loss: 0.011052894406020641
2023-01-23 04:38:30.261217: step: 1196/530, loss: 7.705688767600805e-05
2023-01-23 04:38:31.402246: step: 1200/530, loss: 0.0025212287437170744
2023-01-23 04:38:32.584501: step: 1204/530, loss: 1.487731969973538e-05
2023-01-23 04:38:33.686203: step: 1208/530, loss: 0.016433142125606537
2023-01-23 04:38:34.786737: step: 1212/530, loss: 3.1471254260395654e-06
2023-01-23 04:38:35.930336: step: 1216/530, loss: 0.030451392754912376
2023-01-23 04:38:37.030600: step: 1220/530, loss: 0.016788482666015625
2023-01-23 04:38:38.174194: step: 1224/530, loss: 0.00016136169142555445
2023-01-23 04:38:39.335545: step: 1228/530, loss: 2.9373170036706142e-05
2023-01-23 04:38:40.463765: step: 1232/530, loss: 0.6264863610267639
2023-01-23 04:38:41.611929: step: 1236/530, loss: 0.0001085281401174143
2023-01-23 04:38:42.729474: step: 1240/530, loss: 0.0015645980602130294
2023-01-23 04:38:43.843964: step: 1244/530, loss: 0.0003445625479798764
2023-01-23 04:38:44.960591: step: 1248/530, loss: 0.0004322052118368447
2023-01-23 04:38:46.090576: step: 1252/530, loss: 0.012646770104765892
2023-01-23 04:38:47.220302: step: 1256/530, loss: 0.17248135805130005
2023-01-23 04:38:48.323977: step: 1260/530, loss: 0.00039463042048737407
2023-01-23 04:38:49.471240: step: 1264/530, loss: 0.008760261349380016
2023-01-23 04:38:50.627087: step: 1268/530, loss: 0.021333791315555573
2023-01-23 04:38:51.780749: step: 1272/530, loss: 0.0022455216385424137
2023-01-23 04:38:52.911313: step: 1276/530, loss: 7.343292963923886e-05
2023-01-23 04:38:54.046006: step: 1280/530, loss: 0.0006988525274209678
2023-01-23 04:38:55.168103: step: 1284/530, loss: 1.506805438111769e-05
2023-01-23 04:38:56.283400: step: 1288/530, loss: 0.12216072529554367
2023-01-23 04:38:57.436614: step: 1292/530, loss: 0.23700428009033203
2023-01-23 04:38:58.566232: step: 1296/530, loss: 2.6702882678364404e-06
2023-01-23 04:38:59.729445: step: 1300/530, loss: 2.354684829711914
2023-01-23 04:39:00.845928: step: 1304/530, loss: 0.00035858154296875
2023-01-23 04:39:02.004962: step: 1308/530, loss: 1.5926361811580136e-05
2023-01-23 04:39:03.114687: step: 1312/530, loss: 3.757476952159777e-05
2023-01-23 04:39:04.258230: step: 1316/530, loss: 1.9073486328125e-05
2023-01-23 04:39:05.385970: step: 1320/530, loss: 0.001146507216617465
2023-01-23 04:39:06.505053: step: 1324/530, loss: 0.08950471878051758
2023-01-23 04:39:07.636065: step: 1328/530, loss: 0.0017413139576092362
2023-01-23 04:39:08.750844: step: 1332/530, loss: 6.0653688706224784e-05
2023-01-23 04:39:09.915164: step: 1336/530, loss: 0.002889251569285989
2023-01-23 04:39:11.056813: step: 1340/530, loss: 3.814697265625e-06
2023-01-23 04:39:12.159077: step: 1344/530, loss: 2.5153160095214844e-05
2023-01-23 04:39:13.303552: step: 1348/530, loss: 0.0005192756652832031
2023-01-23 04:39:14.434014: step: 1352/530, loss: 0.0018189430702477694
2023-01-23 04:39:15.553387: step: 1356/530, loss: 0.04093179851770401
2023-01-23 04:39:16.664781: step: 1360/530, loss: -6.389617738022935e-06
2023-01-23 04:39:17.759387: step: 1364/530, loss: 9.078979201149195e-05
2023-01-23 04:39:18.893221: step: 1368/530, loss: 2.9659271604032256e-05
2023-01-23 04:39:20.017934: step: 1372/530, loss: 0.03148021548986435
2023-01-23 04:39:21.151828: step: 1376/530, loss: 0.04650874435901642
2023-01-23 04:39:22.291653: step: 1380/530, loss: 0.06006135791540146
2023-01-23 04:39:23.456686: step: 1384/530, loss: 0.18733759224414825
2023-01-23 04:39:24.580692: step: 1388/530, loss: 8.201598575396929e-06
2023-01-23 04:39:25.714840: step: 1392/530, loss: 6.055831818230217e-06
2023-01-23 04:39:26.862019: step: 1396/530, loss: 0.03217601776123047
2023-01-23 04:39:28.030363: step: 1400/530, loss: 0.00035724640474654734
2023-01-23 04:39:29.158342: step: 1404/530, loss: 0.0002681732294149697
2023-01-23 04:39:30.303351: step: 1408/530, loss: 6.67572021484375e-05
2023-01-23 04:39:31.442328: step: 1412/530, loss: 0.013782024383544922
2023-01-23 04:39:32.580692: step: 1416/530, loss: 0.0007758140563964844
2023-01-23 04:39:33.684455: step: 1420/530, loss: 0.00846567191183567
2023-01-23 04:39:34.840928: step: 1424/530, loss: 0.004046440124511719
2023-01-23 04:39:36.004541: step: 1428/530, loss: 1.6784666513558477e-05
2023-01-23 04:39:37.123111: step: 1432/530, loss: 3.814697265625e-05
2023-01-23 04:39:38.282790: step: 1436/530, loss: 0.00046529772225767374
2023-01-23 04:39:39.403057: step: 1440/530, loss: 0.00018682479276321828
2023-01-23 04:39:40.556682: step: 1444/530, loss: 0.0010677337413653731
2023-01-23 04:39:41.705834: step: 1448/530, loss: 4.014969090349041e-05
2023-01-23 04:39:42.855297: step: 1452/530, loss: 0.10161977261304855
2023-01-23 04:39:43.973051: step: 1456/530, loss: 0.0007867813110351562
2023-01-23 04:39:45.126384: step: 1460/530, loss: 0.001186370849609375
2023-01-23 04:39:46.256991: step: 1464/530, loss: 1.277923547604587e-05
2023-01-23 04:39:47.391163: step: 1468/530, loss: 0.010891342535614967
2023-01-23 04:39:48.521803: step: 1472/530, loss: 0.00031557082547806203
2023-01-23 04:39:49.644167: step: 1476/530, loss: 0.018378637731075287
2023-01-23 04:39:50.806615: step: 1480/530, loss: 0.00950632058084011
2023-01-23 04:39:51.951303: step: 1484/530, loss: 0.012335587292909622
2023-01-23 04:39:53.086823: step: 1488/530, loss: 6.179809861350805e-05
2023-01-23 04:39:54.206404: step: 1492/530, loss: 0.00035648344783112407
2023-01-23 04:39:55.344794: step: 1496/530, loss: 2.0694733393611386e-05
2023-01-23 04:39:56.484376: step: 1500/530, loss: 6.923675391590223e-05
2023-01-23 04:39:57.637859: step: 1504/530, loss: -5.435943421616685e-06
2023-01-23 04:39:58.763949: step: 1508/530, loss: 3.1757354008732364e-05
2023-01-23 04:39:59.896336: step: 1512/530, loss: 0.024010848253965378
2023-01-23 04:40:01.079453: step: 1516/530, loss: 0.062677763402462
2023-01-23 04:40:02.208165: step: 1520/530, loss: 2.2697449821862392e-05
2023-01-23 04:40:03.334376: step: 1524/530, loss: 0.0012394428486004472
2023-01-23 04:40:04.458360: step: 1528/530, loss: 0.00821762066334486
2023-01-23 04:40:05.617672: step: 1532/530, loss: 0.000427055376349017
2023-01-23 04:40:06.732218: step: 1536/530, loss: 0.05485858768224716
2023-01-23 04:40:07.869017: step: 1540/530, loss: 0.024939347058534622
2023-01-23 04:40:09.001045: step: 1544/530, loss: 0.0018972395919263363
2023-01-23 04:40:10.144116: step: 1548/530, loss: 8.926391456043348e-05
2023-01-23 04:40:11.252788: step: 1552/530, loss: 1.2588501704158261e-05
2023-01-23 04:40:12.402474: step: 1556/530, loss: 7.095337059581652e-05
2023-01-23 04:40:13.515923: step: 1560/530, loss: 3.728866795427166e-05
2023-01-23 04:40:14.637711: step: 1564/530, loss: 9.646416583564132e-05
2023-01-23 04:40:15.746246: step: 1568/530, loss: 5.4836273193359375e-05
2023-01-23 04:40:16.884902: step: 1572/530, loss: 0.001531410263851285
2023-01-23 04:40:18.013499: step: 1576/530, loss: 0.045307449996471405
2023-01-23 04:40:19.170996: step: 1580/530, loss: 0.00022716523380950093
2023-01-23 04:40:20.298722: step: 1584/530, loss: 0.0007770538795739412
2023-01-23 04:40:21.426860: step: 1588/530, loss: 0.002796649932861328
2023-01-23 04:40:22.567134: step: 1592/530, loss: 0.0022030831314623356
2023-01-23 04:40:23.681785: step: 1596/530, loss: 0.0009593963623046875
2023-01-23 04:40:24.812569: step: 1600/530, loss: 0.003910255618393421
2023-01-23 04:40:25.954254: step: 1604/530, loss: 0.01869049109518528
2023-01-23 04:40:27.073323: step: 1608/530, loss: 0.01817293092608452
2023-01-23 04:40:28.213181: step: 1612/530, loss: -1.926422191900201e-05
2023-01-23 04:40:29.341639: step: 1616/530, loss: 4.434585662238533e-06
2023-01-23 04:40:30.486315: step: 1620/530, loss: 0.06271228939294815
2023-01-23 04:40:31.595731: step: 1624/530, loss: 4.587173680192791e-05
2023-01-23 04:40:32.720920: step: 1628/530, loss: 0.0002096176176564768
2023-01-23 04:40:33.877141: step: 1632/530, loss: 0.015357781201601028
2023-01-23 04:40:34.964441: step: 1636/530, loss: 7.104873657226562e-05
2023-01-23 04:40:36.113669: step: 1640/530, loss: 0.0002233505219919607
2023-01-23 04:40:37.273699: step: 1644/530, loss: 2.193450927734375e-05
2023-01-23 04:40:38.395512: step: 1648/530, loss: 0.010013389401137829
2023-01-23 04:40:39.527530: step: 1652/530, loss: 0.005037689581513405
2023-01-23 04:40:40.691937: step: 1656/530, loss: 7.62939453125e-06
2023-01-23 04:40:41.848321: step: 1660/530, loss: 0.00010166168794967234
2023-01-23 04:40:42.997510: step: 1664/530, loss: 0.017991257831454277
2023-01-23 04:40:44.125097: step: 1668/530, loss: 0.00015373229689430445
2023-01-23 04:40:45.277624: step: 1672/530, loss: 0.7769744992256165
2023-01-23 04:40:46.423650: step: 1676/530, loss: 9.15527380129788e-06
2023-01-23 04:40:47.538692: step: 1680/530, loss: 5.8555600844556466e-05
2023-01-23 04:40:48.632881: step: 1684/530, loss: -6.675720669591101e-07
2023-01-23 04:40:49.741620: step: 1688/530, loss: 1.1539459592313506e-05
2023-01-23 04:40:50.891926: step: 1692/530, loss: 0.006903648376464844
2023-01-23 04:40:52.003971: step: 1696/530, loss: 0.0006614684825763106
2023-01-23 04:40:53.141166: step: 1700/530, loss: 0.01711397059261799
2023-01-23 04:40:54.259108: step: 1704/530, loss: 0.00030069350032135844
2023-01-23 04:40:55.383124: step: 1708/530, loss: 0.00013742447481490672
2023-01-23 04:40:56.488197: step: 1712/530, loss: 0.0006753921625204384
2023-01-23 04:40:57.609962: step: 1716/530, loss: 0.0037540437187999487
2023-01-23 04:40:58.755599: step: 1720/530, loss: 0.00014820098294876516
2023-01-23 04:40:59.884201: step: 1724/530, loss: 0.007804203312844038
2023-01-23 04:41:01.006540: step: 1728/530, loss: 0.005549097433686256
2023-01-23 04:41:02.162680: step: 1732/530, loss: 0.04431319236755371
2023-01-23 04:41:03.301772: step: 1736/530, loss: 0.0322418212890625
2023-01-23 04:41:04.452218: step: 1740/530, loss: 0.0321170836687088
2023-01-23 04:41:05.573666: step: 1744/530, loss: 3.4332276754867053e-06
2023-01-23 04:41:06.739581: step: 1748/530, loss: 0.0006090164533816278
2023-01-23 04:41:07.842833: step: 1752/530, loss: 0.007384109776467085
2023-01-23 04:41:08.984476: step: 1756/530, loss: 2.6130677724722773e-05
2023-01-23 04:41:10.131915: step: 1760/530, loss: 0.009052658453583717
2023-01-23 04:41:11.244465: step: 1764/530, loss: 6.303787813521922e-05
2023-01-23 04:41:12.407625: step: 1768/530, loss: 0.00020713805861305445
2023-01-23 04:41:13.531511: step: 1772/530, loss: 4.673004514188506e-05
2023-01-23 04:41:14.680096: step: 1776/530, loss: 0.011557579971849918
2023-01-23 04:41:15.807411: step: 1780/530, loss: 2.1362306142691523e-05
2023-01-23 04:41:16.930754: step: 1784/530, loss: 0.0005896568181924522
2023-01-23 04:41:18.102960: step: 1788/530, loss: 0.007252311799675226
2023-01-23 04:41:19.243896: step: 1792/530, loss: 0.012494659051299095
2023-01-23 04:41:20.383895: step: 1796/530, loss: 0.006176948547363281
2023-01-23 04:41:21.554599: step: 1800/530, loss: 0.0003561973571777344
2023-01-23 04:41:22.686521: step: 1804/530, loss: 0.0012302398681640625
2023-01-23 04:41:23.812261: step: 1808/530, loss: 8.435249765170738e-05
2023-01-23 04:41:24.947403: step: 1812/530, loss: 0.014499283395707607
2023-01-23 04:41:26.041832: step: 1816/530, loss: 0.004173469729721546
2023-01-23 04:41:27.186696: step: 1820/530, loss: 2.093315197271295e-05
2023-01-23 04:41:28.271808: step: 1824/530, loss: 0.0005592346424236894
2023-01-23 04:41:29.362231: step: 1828/530, loss: 0.00696220388635993
2023-01-23 04:41:30.486483: step: 1832/530, loss: 0.0006017685518600047
2023-01-23 04:41:31.637185: step: 1836/530, loss: 9.899138967739418e-05
2023-01-23 04:41:32.771395: step: 1840/530, loss: 6.637573096668348e-05
2023-01-23 04:41:33.895249: step: 1844/530, loss: 1.1444092706369702e-05
2023-01-23 04:41:35.014621: step: 1848/530, loss: 2.28881845032447e-06
2023-01-23 04:41:36.118198: step: 1852/530, loss: 0.0051666260696947575
2023-01-23 04:41:37.221843: step: 1856/530, loss: 0.005717277526855469
2023-01-23 04:41:38.351205: step: 1860/530, loss: 3.080368333030492e-05
2023-01-23 04:41:39.467208: step: 1864/530, loss: 0.00042028428288176656
2023-01-23 04:41:40.576947: step: 1868/530, loss: 1.6880036127986386e-05
2023-01-23 04:41:41.678402: step: 1872/530, loss: 0.08003588020801544
2023-01-23 04:41:42.790383: step: 1876/530, loss: 3.0517580853484105e-06
2023-01-23 04:41:43.919430: step: 1880/530, loss: 0.03461189568042755
2023-01-23 04:41:45.085643: step: 1884/530, loss: 0.0018207550747320056
2023-01-23 04:41:46.223821: step: 1888/530, loss: 0.010653972625732422
2023-01-23 04:41:47.315238: step: 1892/530, loss: 2.384185791015625e-07
2023-01-23 04:41:48.424501: step: 1896/530, loss: -0.0
2023-01-23 04:41:49.575823: step: 1900/530, loss: 0.00644683837890625
2023-01-23 04:41:50.687110: step: 1904/530, loss: 0.00018730164447333664
2023-01-23 04:41:51.796013: step: 1908/530, loss: 2.6035309929284267e-05
2023-01-23 04:41:52.889078: step: 1912/530, loss: -5.948543730482925e-06
2023-01-23 04:41:54.003444: step: 1916/530, loss: 0.0016862869961187243
2023-01-23 04:41:55.192682: step: 1920/530, loss: 1.0294657945632935
2023-01-23 04:41:56.309656: step: 1924/530, loss: 1.8119812921213452e-06
2023-01-23 04:41:57.431085: step: 1928/530, loss: 0.012655830942094326
2023-01-23 04:41:58.553743: step: 1932/530, loss: 0.0010618210071697831
2023-01-23 04:41:59.687517: step: 1936/530, loss: 0.0877775177359581
2023-01-23 04:42:00.801747: step: 1940/530, loss: 0.0005313873407430947
2023-01-23 04:42:01.918342: step: 1944/530, loss: 3.2424925393570447e-06
2023-01-23 04:42:03.065510: step: 1948/530, loss: 7.286071922862902e-05
2023-01-23 04:42:04.176158: step: 1952/530, loss: 0.0007328033680096269
2023-01-23 04:42:05.301854: step: 1956/530, loss: 0.0003553390852175653
2023-01-23 04:42:06.455761: step: 1960/530, loss: 0.0001773834228515625
2023-01-23 04:42:07.587481: step: 1964/530, loss: 0.0019729614723473787
2023-01-23 04:42:08.742593: step: 1968/530, loss: 0.006718444637954235
2023-01-23 04:42:09.860459: step: 1972/530, loss: 0.0022602081298828125
2023-01-23 04:42:10.979008: step: 1976/530, loss: 0.00017051697068382055
2023-01-23 04:42:12.096343: step: 1980/530, loss: 0.0003715515194926411
2023-01-23 04:42:13.232287: step: 1984/530, loss: 0.0006301880348473787
2023-01-23 04:42:14.376328: step: 1988/530, loss: 0.0002187728969147429
2023-01-23 04:42:15.491331: step: 1992/530, loss: 3.886222839355469e-05
2023-01-23 04:42:16.603421: step: 1996/530, loss: 6.666182889603078e-05
2023-01-23 04:42:17.741208: step: 2000/530, loss: 0.0007330895168706775
2023-01-23 04:42:18.851399: step: 2004/530, loss: 0.040247153490781784
2023-01-23 04:42:19.978517: step: 2008/530, loss: 3.852844383800402e-05
2023-01-23 04:42:21.119533: step: 2012/530, loss: 0.004876041319221258
2023-01-23 04:42:22.274876: step: 2016/530, loss: -2.918243444582913e-05
2023-01-23 04:42:23.424622: step: 2020/530, loss: 0.0013820647727698088
2023-01-23 04:42:24.524934: step: 2024/530, loss: 0.0023657798301428556
2023-01-23 04:42:25.643819: step: 2028/530, loss: 0.2879234552383423
2023-01-23 04:42:26.768979: step: 2032/530, loss: 0.012592888437211514
2023-01-23 04:42:27.892114: step: 2036/530, loss: 0.00013198853412177414
2023-01-23 04:42:29.004530: step: 2040/530, loss: 0.007924270816147327
2023-01-23 04:42:30.142730: step: 2044/530, loss: -1.220703143189894e-05
2023-01-23 04:42:31.276919: step: 2048/530, loss: 2.86102294921875e-05
2023-01-23 04:42:32.431345: step: 2052/530, loss: 0.0011165140895172954
2023-01-23 04:42:33.586347: step: 2056/530, loss: 4.673004241340095e-06
2023-01-23 04:42:34.708493: step: 2060/530, loss: 0.01006460189819336
2023-01-23 04:42:35.836108: step: 2064/530, loss: 0.004045606125146151
2023-01-23 04:42:36.949943: step: 2068/530, loss: 6.160735938465223e-05
2023-01-23 04:42:38.055533: step: 2072/530, loss: 0.0007658004760742188
2023-01-23 04:42:39.182782: step: 2076/530, loss: 1.2731552487821318e-05
2023-01-23 04:42:40.291466: step: 2080/530, loss: 0.00309066753834486
2023-01-23 04:42:41.393866: step: 2084/530, loss: 0.009735775180161
2023-01-23 04:42:42.504588: step: 2088/530, loss: 0.006229114718735218
2023-01-23 04:42:43.628259: step: 2092/530, loss: 0.0019541741348803043
2023-01-23 04:42:44.726354: step: 2096/530, loss: 1.831054760259576e-05
2023-01-23 04:42:45.866424: step: 2100/530, loss: 0.0003796577511820942
2023-01-23 04:42:46.994105: step: 2104/530, loss: 0.005587578285485506
2023-01-23 04:42:48.117883: step: 2108/530, loss: 0.00028820039005950093
2023-01-23 04:42:49.228069: step: 2112/530, loss: 9.088516526389867e-05
2023-01-23 04:42:50.366057: step: 2116/530, loss: 0.00019569396681617945
2023-01-23 04:42:51.485836: step: 2120/530, loss: 0.0038644790183752775
==================================================
Loss: 0.023
--------------------
Dev: {'event': {'p': 0.6082251082251082, 'r': 0.748335552596538, 'f1': 0.6710447761194029}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 29}
Test: {'event': {'p': 0.6490004649000465, 'r': 0.7977142857142857, 'f1': 0.7157139195078186}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 29}
Chinese: {'event': {'p': 0.6071428571428571, 'r': 0.9444444444444444, 'f1': 0.7391304347826088}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 29}
Korean: {'event': {'p': 0.5901639344262295, 'r': 0.5714285714285714, 'f1': 0.5806451612903226}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 29}
Russian: {'event': {'p': 0.3953488372093023, 'r': 0.4722222222222222, 'f1': 0.43037974683544306}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 29}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6204301075268818, 'r': 0.7683089214380826, 'f1': 0.6864961332540155}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 28}
Eng Test for Chinese: {'event': {'p': 0.639605818864383, 'r': 0.7788571428571428, 'f1': 0.7023962896160783}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 28}
Sample Chinese: {'event': {'p': 0.6447368421052632, 'r': 0.9074074074074074, 'f1': 0.7538461538461537}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 28}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6288770053475936, 'r': 0.7829560585885486, 'f1': 0.697508896797153}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Korean: {'event': {'p': 0.64058795637743, 'r': 0.772, 'f1': 0.7001813941435606}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Korean: {'event': {'p': 0.6851851851851852, 'r': 0.5873015873015873, 'f1': 0.6324786324786325}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5600384245917387, 'r': 0.7762982689747004, 'f1': 0.6506696428571429}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6342804766269478, 'r': 0.7908571428571428, 'f1': 0.7039674465920651}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5319148936170213, 'r': 0.6944444444444444, 'f1': 0.6024096385542169}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}