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 23:22:51.945345: step: 4/530, loss: 2.5161194801330566
2023-01-22 23:22:53.103021: step: 8/530, loss: 4.797885417938232
2023-01-22 23:22:54.240026: step: 12/530, loss: 11.926904678344727
2023-01-22 23:22:55.433256: step: 16/530, loss: 4.0641045570373535
2023-01-22 23:22:56.580211: step: 20/530, loss: 13.01579475402832
2023-01-22 23:22:57.790404: step: 24/530, loss: 3.866377353668213
2023-01-22 23:22:59.053571: step: 28/530, loss: 22.95454978942871
2023-01-22 23:23:00.236887: step: 32/530, loss: 21.726295471191406
2023-01-22 23:23:01.391415: step: 36/530, loss: 3.471451759338379
2023-01-22 23:23:02.557293: step: 40/530, loss: 15.960955619812012
2023-01-22 23:23:03.706602: step: 44/530, loss: 3.9349400997161865
2023-01-22 23:23:04.940547: step: 48/530, loss: 20.913089752197266
2023-01-22 23:23:06.117791: step: 52/530, loss: 13.196843147277832
2023-01-22 23:23:07.299563: step: 56/530, loss: 4.372941017150879
2023-01-22 23:23:08.485697: step: 60/530, loss: 8.25861930847168
2023-01-22 23:23:09.658644: step: 64/530, loss: 4.974344730377197
2023-01-22 23:23:10.803742: step: 68/530, loss: 5.565827369689941
2023-01-22 23:23:11.978031: step: 72/530, loss: 15.985088348388672
2023-01-22 23:23:13.126961: step: 76/530, loss: 10.396745681762695
2023-01-22 23:23:14.325379: step: 80/530, loss: 10.244354248046875
2023-01-22 23:23:15.515882: step: 84/530, loss: 18.344085693359375
2023-01-22 23:23:16.688022: step: 88/530, loss: 13.439335823059082
2023-01-22 23:23:17.873270: step: 92/530, loss: 14.317118644714355
2023-01-22 23:23:18.991775: step: 96/530, loss: 2.4477803707122803
2023-01-22 23:23:20.181632: step: 100/530, loss: 37.005043029785156
2023-01-22 23:23:21.361855: step: 104/530, loss: 3.7880821228027344
2023-01-22 23:23:22.532226: step: 108/530, loss: 15.911226272583008
2023-01-22 23:23:23.763143: step: 112/530, loss: 4.127887725830078
2023-01-22 23:23:24.960670: step: 116/530, loss: 3.908759593963623
2023-01-22 23:23:26.125549: step: 120/530, loss: 13.880085945129395
2023-01-22 23:23:27.278878: step: 124/530, loss: 12.014925956726074
2023-01-22 23:23:28.450376: step: 128/530, loss: 9.153682708740234
2023-01-22 23:23:29.667407: step: 132/530, loss: 5.017300605773926
2023-01-22 23:23:30.832895: step: 136/530, loss: 3.6399130821228027
2023-01-22 23:23:32.007724: step: 140/530, loss: 15.44703483581543
2023-01-22 23:23:33.163839: step: 144/530, loss: 3.0643105506896973
2023-01-22 23:23:34.359964: step: 148/530, loss: 3.4777750968933105
2023-01-22 23:23:35.522716: step: 152/530, loss: 13.222376823425293
2023-01-22 23:23:36.703499: step: 156/530, loss: 5.787364959716797
2023-01-22 23:23:37.857687: step: 160/530, loss: 14.943460464477539
2023-01-22 23:23:39.032488: step: 164/530, loss: 40.55250549316406
2023-01-22 23:23:40.175994: step: 168/530, loss: 4.62084436416626
2023-01-22 23:23:41.349182: step: 172/530, loss: 8.43724250793457
2023-01-22 23:23:42.514375: step: 176/530, loss: 16.676973342895508
2023-01-22 23:23:43.675613: step: 180/530, loss: 6.348862648010254
2023-01-22 23:23:44.852137: step: 184/530, loss: 5.053753852844238
2023-01-22 23:23:46.007195: step: 188/530, loss: 2.9925246238708496
2023-01-22 23:23:47.191319: step: 192/530, loss: 9.537186622619629
2023-01-22 23:23:48.367670: step: 196/530, loss: 2.9689135551452637
2023-01-22 23:23:49.559763: step: 200/530, loss: 10.174930572509766
2023-01-22 23:23:50.721151: step: 204/530, loss: 9.401609420776367
2023-01-22 23:23:51.883691: step: 208/530, loss: 32.26618957519531
2023-01-22 23:23:53.038888: step: 212/530, loss: 12.614603996276855
2023-01-22 23:23:54.197341: step: 216/530, loss: 15.97144889831543
2023-01-22 23:23:55.381508: step: 220/530, loss: 15.788025856018066
2023-01-22 23:23:56.585541: step: 224/530, loss: 2.724240303039551
2023-01-22 23:23:57.779760: step: 228/530, loss: 14.002435684204102
2023-01-22 23:23:58.925904: step: 232/530, loss: 3.3141677379608154
2023-01-22 23:24:00.081637: step: 236/530, loss: 7.198806285858154
2023-01-22 23:24:01.293545: step: 240/530, loss: 7.068933486938477
2023-01-22 23:24:02.488073: step: 244/530, loss: 14.713768005371094
2023-01-22 23:24:03.649306: step: 248/530, loss: 2.278554916381836
2023-01-22 23:24:04.854663: step: 252/530, loss: 4.386191368103027
2023-01-22 23:24:06.032314: step: 256/530, loss: 2.6234817504882812
2023-01-22 23:24:07.187674: step: 260/530, loss: 2.371807098388672
2023-01-22 23:24:08.357892: step: 264/530, loss: 2.3581998348236084
2023-01-22 23:24:09.532321: step: 268/530, loss: 15.002385139465332
2023-01-22 23:24:10.674549: step: 272/530, loss: 12.71749496459961
2023-01-22 23:24:11.882448: step: 276/530, loss: 4.442104339599609
2023-01-22 23:24:13.035150: step: 280/530, loss: 2.006585121154785
2023-01-22 23:24:14.197326: step: 284/530, loss: 3.3839800357818604
2023-01-22 23:24:15.340904: step: 288/530, loss: 11.266592025756836
2023-01-22 23:24:16.512563: step: 292/530, loss: 3.737403392791748
2023-01-22 23:24:17.720997: step: 296/530, loss: 22.517480850219727
2023-01-22 23:24:18.882084: step: 300/530, loss: 16.706323623657227
2023-01-22 23:24:20.037168: step: 304/530, loss: 2.7792234420776367
2023-01-22 23:24:21.225572: step: 308/530, loss: 12.020271301269531
2023-01-22 23:24:22.472703: step: 312/530, loss: 4.782174110412598
2023-01-22 23:24:23.634117: step: 316/530, loss: 3.55352783203125
2023-01-22 23:24:24.801927: step: 320/530, loss: 27.624523162841797
2023-01-22 23:24:26.027190: step: 324/530, loss: 11.016018867492676
2023-01-22 23:24:27.154614: step: 328/530, loss: 3.1291041374206543
2023-01-22 23:24:28.348242: step: 332/530, loss: 3.4651546478271484
2023-01-22 23:24:29.510915: step: 336/530, loss: 21.539016723632812
2023-01-22 23:24:30.725732: step: 340/530, loss: 3.6725924015045166
2023-01-22 23:24:31.929567: step: 344/530, loss: 3.7882513999938965
2023-01-22 23:24:33.093489: step: 348/530, loss: 3.1051297187805176
2023-01-22 23:24:34.277217: step: 352/530, loss: 4.410858154296875
2023-01-22 23:24:35.440850: step: 356/530, loss: 2.0844953060150146
2023-01-22 23:24:36.618827: step: 360/530, loss: 12.848541259765625
2023-01-22 23:24:37.790151: step: 364/530, loss: 1.903769850730896
2023-01-22 23:24:38.986789: step: 368/530, loss: 4.888723373413086
2023-01-22 23:24:40.153297: step: 372/530, loss: 17.24649429321289
2023-01-22 23:24:41.356605: step: 376/530, loss: 8.166925430297852
2023-01-22 23:24:42.520146: step: 380/530, loss: 20.124874114990234
2023-01-22 23:24:43.665772: step: 384/530, loss: 12.455825805664062
2023-01-22 23:24:44.858744: step: 388/530, loss: 9.368526458740234
2023-01-22 23:24:46.021966: step: 392/530, loss: 2.452817440032959
2023-01-22 23:24:47.191569: step: 396/530, loss: 5.114747047424316
2023-01-22 23:24:48.360623: step: 400/530, loss: 9.535774230957031
2023-01-22 23:24:49.530185: step: 404/530, loss: 2.9233994483947754
2023-01-22 23:24:50.671859: step: 408/530, loss: 19.035572052001953
2023-01-22 23:24:51.852183: step: 412/530, loss: 13.949315071105957
2023-01-22 23:24:52.988875: step: 416/530, loss: 2.444232940673828
2023-01-22 23:24:54.138994: step: 420/530, loss: 2.2327866554260254
2023-01-22 23:24:55.331563: step: 424/530, loss: 2.627701759338379
2023-01-22 23:24:56.481754: step: 428/530, loss: 5.002713203430176
2023-01-22 23:24:57.656984: step: 432/530, loss: 3.3038406372070312
2023-01-22 23:24:58.816128: step: 436/530, loss: 2.5352187156677246
2023-01-22 23:25:00.008232: step: 440/530, loss: 19.64345359802246
2023-01-22 23:25:01.173989: step: 444/530, loss: 9.372864723205566
2023-01-22 23:25:02.382088: step: 448/530, loss: 4.161972522735596
2023-01-22 23:25:03.558433: step: 452/530, loss: 6.6680908203125
2023-01-22 23:25:04.709810: step: 456/530, loss: 2.3650639057159424
2023-01-22 23:25:05.903219: step: 460/530, loss: 13.355592727661133
2023-01-22 23:25:07.066123: step: 464/530, loss: 8.220755577087402
2023-01-22 23:25:08.208506: step: 468/530, loss: 1.9070762395858765
2023-01-22 23:25:09.403321: step: 472/530, loss: 8.14748764038086
2023-01-22 23:25:10.563507: step: 476/530, loss: 10.209144592285156
2023-01-22 23:25:11.692412: step: 480/530, loss: 1.5899099111557007
2023-01-22 23:25:12.887106: step: 484/530, loss: 2.1008899211883545
2023-01-22 23:25:14.075750: step: 488/530, loss: 2.344302177429199
2023-01-22 23:25:15.236948: step: 492/530, loss: 9.750861167907715
2023-01-22 23:25:16.394594: step: 496/530, loss: 1.621309518814087
2023-01-22 23:25:17.545658: step: 500/530, loss: 2.753882646560669
2023-01-22 23:25:18.738983: step: 504/530, loss: 4.010830402374268
2023-01-22 23:25:19.912270: step: 508/530, loss: 1.1693798303604126
2023-01-22 23:25:21.064059: step: 512/530, loss: 3.1112325191497803
2023-01-22 23:25:22.249919: step: 516/530, loss: 1.2566814422607422
2023-01-22 23:25:23.426158: step: 520/530, loss: 5.21751070022583
2023-01-22 23:25:24.578637: step: 524/530, loss: 5.255274772644043
2023-01-22 23:25:25.782468: step: 528/530, loss: 10.421780586242676
2023-01-22 23:25:26.941368: step: 532/530, loss: 2.817828893661499
2023-01-22 23:25:28.101606: step: 536/530, loss: 0.7683872580528259
2023-01-22 23:25:29.291386: step: 540/530, loss: 6.435408592224121
2023-01-22 23:25:30.459426: step: 544/530, loss: 3.2435226440429688
2023-01-22 23:25:31.628456: step: 548/530, loss: 4.753021717071533
2023-01-22 23:25:32.807270: step: 552/530, loss: 3.7606306076049805
2023-01-22 23:25:34.005963: step: 556/530, loss: 0.8844271898269653
2023-01-22 23:25:35.163915: step: 560/530, loss: 0.7438180446624756
2023-01-22 23:25:36.333029: step: 564/530, loss: 0.7047466039657593
2023-01-22 23:25:37.499664: step: 568/530, loss: 3.958590507507324
2023-01-22 23:25:38.680895: step: 572/530, loss: 3.6301538944244385
2023-01-22 23:25:39.817308: step: 576/530, loss: 4.452891826629639
2023-01-22 23:25:41.023497: step: 580/530, loss: 3.3826839923858643
2023-01-22 23:25:42.171632: step: 584/530, loss: 1.2414543628692627
2023-01-22 23:25:43.305610: step: 588/530, loss: 1.8615998029708862
2023-01-22 23:25:44.513351: step: 592/530, loss: 0.9703147411346436
2023-01-22 23:25:45.682703: step: 596/530, loss: 0.9260671138763428
2023-01-22 23:25:46.841874: step: 600/530, loss: 2.785079002380371
2023-01-22 23:25:48.002201: step: 604/530, loss: 1.8783903121948242
2023-01-22 23:25:49.170117: step: 608/530, loss: 1.935996174812317
2023-01-22 23:25:50.320074: step: 612/530, loss: 1.8300502300262451
2023-01-22 23:25:51.505027: step: 616/530, loss: 0.5617196559906006
2023-01-22 23:25:52.705490: step: 620/530, loss: 1.0309745073318481
2023-01-22 23:25:53.859401: step: 624/530, loss: 3.1078665256500244
2023-01-22 23:25:55.015451: step: 628/530, loss: 4.157384872436523
2023-01-22 23:25:56.184015: step: 632/530, loss: 1.0077488422393799
2023-01-22 23:25:57.377125: step: 636/530, loss: 0.7220383882522583
2023-01-22 23:25:58.559356: step: 640/530, loss: 1.2440093755722046
2023-01-22 23:25:59.670885: step: 644/530, loss: 0.3529917597770691
2023-01-22 23:26:00.832689: step: 648/530, loss: 0.768575131893158
2023-01-22 23:26:01.990217: step: 652/530, loss: 0.31803983449935913
2023-01-22 23:26:03.130509: step: 656/530, loss: 6.022542953491211
2023-01-22 23:26:04.286543: step: 660/530, loss: 1.6316437721252441
2023-01-22 23:26:05.462659: step: 664/530, loss: 1.0451242923736572
2023-01-22 23:26:06.646886: step: 668/530, loss: 0.5916638374328613
2023-01-22 23:26:07.820001: step: 672/530, loss: 0.6444135904312134
2023-01-22 23:26:08.983009: step: 676/530, loss: 3.8935070037841797
2023-01-22 23:26:10.143614: step: 680/530, loss: 1.9293432235717773
2023-01-22 23:26:11.266868: step: 684/530, loss: 1.006641149520874
2023-01-22 23:26:12.421747: step: 688/530, loss: 0.714217483997345
2023-01-22 23:26:13.597594: step: 692/530, loss: 4.431859016418457
2023-01-22 23:26:14.766128: step: 696/530, loss: 3.916639566421509
2023-01-22 23:26:15.903784: step: 700/530, loss: 2.7038116455078125
2023-01-22 23:26:17.094185: step: 704/530, loss: 1.762603521347046
2023-01-22 23:26:18.252985: step: 708/530, loss: 0.4076938033103943
2023-01-22 23:26:19.420252: step: 712/530, loss: 0.48345476388931274
2023-01-22 23:26:20.557380: step: 716/530, loss: 1.45754075050354
2023-01-22 23:26:21.759643: step: 720/530, loss: 0.7138513326644897
2023-01-22 23:26:22.910924: step: 724/530, loss: 0.7309765815734863
2023-01-22 23:26:24.064438: step: 728/530, loss: 1.2813173532485962
2023-01-22 23:26:25.214942: step: 732/530, loss: 2.56290602684021
2023-01-22 23:26:26.404356: step: 736/530, loss: 1.2265419960021973
2023-01-22 23:26:27.603171: step: 740/530, loss: 2.386249542236328
2023-01-22 23:26:28.751653: step: 744/530, loss: 6.997499465942383
2023-01-22 23:26:29.921361: step: 748/530, loss: 0.44485947489738464
2023-01-22 23:26:31.136409: step: 752/530, loss: 0.47446194291114807
2023-01-22 23:26:32.341234: step: 756/530, loss: 3.82497501373291
2023-01-22 23:26:33.512674: step: 760/530, loss: 1.0958218574523926
2023-01-22 23:26:34.662403: step: 764/530, loss: 0.7192956209182739
2023-01-22 23:26:35.845738: step: 768/530, loss: 0.7497055530548096
2023-01-22 23:26:37.011309: step: 772/530, loss: 3.1190707683563232
2023-01-22 23:26:38.173870: step: 776/530, loss: 2.8811700344085693
2023-01-22 23:26:39.350284: step: 780/530, loss: 2.8657805919647217
2023-01-22 23:26:40.508018: step: 784/530, loss: 1.971901774406433
2023-01-22 23:26:41.700997: step: 788/530, loss: 1.0352015495300293
2023-01-22 23:26:42.902355: step: 792/530, loss: 0.9032777547836304
2023-01-22 23:26:44.045851: step: 796/530, loss: 0.7656562924385071
2023-01-22 23:26:45.214108: step: 800/530, loss: 3.5292155742645264
2023-01-22 23:26:46.397728: step: 804/530, loss: 2.4679925441741943
2023-01-22 23:26:47.547406: step: 808/530, loss: 0.3880865275859833
2023-01-22 23:26:48.749482: step: 812/530, loss: 1.3852752447128296
2023-01-22 23:26:49.941847: step: 816/530, loss: 1.9122967720031738
2023-01-22 23:26:51.104868: step: 820/530, loss: 1.0261013507843018
2023-01-22 23:26:52.279049: step: 824/530, loss: 0.5673860311508179
2023-01-22 23:26:53.446487: step: 828/530, loss: 9.804205894470215
2023-01-22 23:26:54.620532: step: 832/530, loss: 1.009171485900879
2023-01-22 23:26:55.825316: step: 836/530, loss: 0.5999876260757446
2023-01-22 23:26:56.984052: step: 840/530, loss: 0.5948918461799622
2023-01-22 23:26:58.140034: step: 844/530, loss: 0.47238612174987793
2023-01-22 23:26:59.282289: step: 848/530, loss: 0.38903582096099854
2023-01-22 23:27:00.475031: step: 852/530, loss: 1.9784491062164307
2023-01-22 23:27:01.658652: step: 856/530, loss: 7.061280250549316
2023-01-22 23:27:02.839266: step: 860/530, loss: 1.0529119968414307
2023-01-22 23:27:04.036556: step: 864/530, loss: 0.8442457318305969
2023-01-22 23:27:05.241939: step: 868/530, loss: 3.041553497314453
2023-01-22 23:27:06.398310: step: 872/530, loss: 0.2720159888267517
2023-01-22 23:27:07.537671: step: 876/530, loss: 0.7017601728439331
2023-01-22 23:27:08.748107: step: 880/530, loss: 1.4306416511535645
2023-01-22 23:27:09.985983: step: 884/530, loss: 0.7119876146316528
2023-01-22 23:27:11.153554: step: 888/530, loss: 1.416643500328064
2023-01-22 23:27:12.319931: step: 892/530, loss: 2.188974142074585
2023-01-22 23:27:13.452755: step: 896/530, loss: 0.6373625993728638
2023-01-22 23:27:14.630681: step: 900/530, loss: 2.17868709564209
2023-01-22 23:27:15.785161: step: 904/530, loss: 0.44701725244522095
2023-01-22 23:27:16.969658: step: 908/530, loss: 0.7150293588638306
2023-01-22 23:27:18.185383: step: 912/530, loss: 7.174227714538574
2023-01-22 23:27:19.349499: step: 916/530, loss: 2.646710157394409
2023-01-22 23:27:20.496003: step: 920/530, loss: 0.8314789533615112
2023-01-22 23:27:21.614802: step: 924/530, loss: 1.1968625783920288
2023-01-22 23:27:22.819108: step: 928/530, loss: 1.7923980951309204
2023-01-22 23:27:23.972678: step: 932/530, loss: 0.30722665786743164
2023-01-22 23:27:25.162623: step: 936/530, loss: 2.4092276096343994
2023-01-22 23:27:26.294286: step: 940/530, loss: 1.95243501663208
2023-01-22 23:27:27.468464: step: 944/530, loss: 1.0235170125961304
2023-01-22 23:27:28.658889: step: 948/530, loss: 0.5962594747543335
2023-01-22 23:27:29.798205: step: 952/530, loss: 0.2668376863002777
2023-01-22 23:27:30.974387: step: 956/530, loss: 1.1881362199783325
2023-01-22 23:27:32.161901: step: 960/530, loss: 0.9031090140342712
2023-01-22 23:27:33.305137: step: 964/530, loss: 0.9046097993850708
2023-01-22 23:27:34.452049: step: 968/530, loss: 0.5459737777709961
2023-01-22 23:27:35.608342: step: 972/530, loss: 0.2694365680217743
2023-01-22 23:27:36.812740: step: 976/530, loss: 3.8331170082092285
2023-01-22 23:27:37.974605: step: 980/530, loss: 0.6028522849082947
2023-01-22 23:27:39.128601: step: 984/530, loss: 0.4941166043281555
2023-01-22 23:27:40.280857: step: 988/530, loss: 0.5745193958282471
2023-01-22 23:27:41.465287: step: 992/530, loss: 1.136129379272461
2023-01-22 23:27:42.623159: step: 996/530, loss: 0.6408124566078186
2023-01-22 23:27:43.769529: step: 1000/530, loss: 1.2257132530212402
2023-01-22 23:27:44.992565: step: 1004/530, loss: 0.49207180738449097
2023-01-22 23:27:46.197964: step: 1008/530, loss: 1.4571502208709717
2023-01-22 23:27:47.390204: step: 1012/530, loss: 1.139090895652771
2023-01-22 23:27:48.526486: step: 1016/530, loss: 1.1502777338027954
2023-01-22 23:27:49.726592: step: 1020/530, loss: 0.5020865201950073
2023-01-22 23:27:50.909675: step: 1024/530, loss: 1.5950565338134766
2023-01-22 23:27:52.079093: step: 1028/530, loss: 0.27119016647338867
2023-01-22 23:27:53.277406: step: 1032/530, loss: 0.7815744876861572
2023-01-22 23:27:54.472898: step: 1036/530, loss: 0.3496941924095154
2023-01-22 23:27:55.649410: step: 1040/530, loss: 2.5934882164001465
2023-01-22 23:27:56.782784: step: 1044/530, loss: 0.6182379722595215
2023-01-22 23:27:57.945552: step: 1048/530, loss: 0.5631403923034668
2023-01-22 23:27:59.188993: step: 1052/530, loss: 2.31282114982605
2023-01-22 23:28:00.328671: step: 1056/530, loss: 2.662299871444702
2023-01-22 23:28:01.486112: step: 1060/530, loss: 0.6531960964202881
2023-01-22 23:28:02.676426: step: 1064/530, loss: 2.829932689666748
2023-01-22 23:28:03.828415: step: 1068/530, loss: 5.218477249145508
2023-01-22 23:28:04.978572: step: 1072/530, loss: 4.102937698364258
2023-01-22 23:28:06.142135: step: 1076/530, loss: 0.6146771907806396
2023-01-22 23:28:07.341054: step: 1080/530, loss: 0.3529133200645447
2023-01-22 23:28:08.532878: step: 1084/530, loss: 0.6025075912475586
2023-01-22 23:28:09.688260: step: 1088/530, loss: 1.490753412246704
2023-01-22 23:28:10.854817: step: 1092/530, loss: 0.8239052295684814
2023-01-22 23:28:12.033574: step: 1096/530, loss: 1.2392657995224
2023-01-22 23:28:13.211017: step: 1100/530, loss: 0.23670083284378052
2023-01-22 23:28:14.424427: step: 1104/530, loss: 2.0383994579315186
2023-01-22 23:28:15.564746: step: 1108/530, loss: 0.509362518787384
2023-01-22 23:28:16.771053: step: 1112/530, loss: 1.8773927688598633
2023-01-22 23:28:17.941231: step: 1116/530, loss: 1.4129194021224976
2023-01-22 23:28:19.121853: step: 1120/530, loss: 0.8332359790802002
2023-01-22 23:28:20.350001: step: 1124/530, loss: 0.8844027519226074
2023-01-22 23:28:21.501623: step: 1128/530, loss: 1.3705568313598633
2023-01-22 23:28:22.678140: step: 1132/530, loss: 1.9089680910110474
2023-01-22 23:28:23.828081: step: 1136/530, loss: 1.832566261291504
2023-01-22 23:28:24.995647: step: 1140/530, loss: 0.34784209728240967
2023-01-22 23:28:26.148576: step: 1144/530, loss: 1.0678129196166992
2023-01-22 23:28:27.321579: step: 1148/530, loss: 0.5765253305435181
2023-01-22 23:28:28.503358: step: 1152/530, loss: 0.8868647813796997
2023-01-22 23:28:29.671208: step: 1156/530, loss: 1.7719250917434692
2023-01-22 23:28:30.799058: step: 1160/530, loss: 0.28223738074302673
2023-01-22 23:28:31.973951: step: 1164/530, loss: 1.5586905479431152
2023-01-22 23:28:33.127878: step: 1168/530, loss: 0.941847026348114
2023-01-22 23:28:34.261800: step: 1172/530, loss: 1.9285145998001099
2023-01-22 23:28:35.427156: step: 1176/530, loss: 1.6009633541107178
2023-01-22 23:28:36.618948: step: 1180/530, loss: 0.4060894846916199
2023-01-22 23:28:37.789598: step: 1184/530, loss: 1.1366400718688965
2023-01-22 23:28:38.948604: step: 1188/530, loss: 0.7903562188148499
2023-01-22 23:28:40.115234: step: 1192/530, loss: 0.43699389696121216
2023-01-22 23:28:41.274399: step: 1196/530, loss: 0.4940643906593323
2023-01-22 23:28:42.459525: step: 1200/530, loss: 7.775330066680908
2023-01-22 23:28:43.623922: step: 1204/530, loss: 0.17007428407669067
2023-01-22 23:28:44.805043: step: 1208/530, loss: 0.34428685903549194
2023-01-22 23:28:45.985806: step: 1212/530, loss: 0.7938814163208008
2023-01-22 23:28:47.179970: step: 1216/530, loss: 3.598043203353882
2023-01-22 23:28:48.338163: step: 1220/530, loss: 1.4521902799606323
2023-01-22 23:28:49.513469: step: 1224/530, loss: 1.7422288656234741
2023-01-22 23:28:50.656063: step: 1228/530, loss: 1.2381190061569214
2023-01-22 23:28:51.786869: step: 1232/530, loss: 0.27103549242019653
2023-01-22 23:28:52.937966: step: 1236/530, loss: 0.7396968007087708
2023-01-22 23:28:54.109117: step: 1240/530, loss: 0.3635512590408325
2023-01-22 23:28:55.270317: step: 1244/530, loss: 2.7506442070007324
2023-01-22 23:28:56.441483: step: 1248/530, loss: 0.4463156461715698
2023-01-22 23:28:57.608890: step: 1252/530, loss: 0.30058756470680237
2023-01-22 23:28:58.763284: step: 1256/530, loss: 0.6068265438079834
2023-01-22 23:28:59.912926: step: 1260/530, loss: 8.187128067016602
2023-01-22 23:29:01.076753: step: 1264/530, loss: 1.5500524044036865
2023-01-22 23:29:02.239840: step: 1268/530, loss: 2.888580560684204
2023-01-22 23:29:03.465230: step: 1272/530, loss: 2.5192904472351074
2023-01-22 23:29:04.634654: step: 1276/530, loss: 7.838134288787842
2023-01-22 23:29:05.778944: step: 1280/530, loss: 0.23743054270744324
2023-01-22 23:29:06.955896: step: 1284/530, loss: 1.9662806987762451
2023-01-22 23:29:08.108521: step: 1288/530, loss: 0.8476062417030334
2023-01-22 23:29:09.325333: step: 1292/530, loss: 1.777708649635315
2023-01-22 23:29:10.499034: step: 1296/530, loss: 0.3524801433086395
2023-01-22 23:29:11.692254: step: 1300/530, loss: 3.048319101333618
2023-01-22 23:29:12.903067: step: 1304/530, loss: 2.00106143951416
2023-01-22 23:29:14.054049: step: 1308/530, loss: 0.5819625854492188
2023-01-22 23:29:15.265961: step: 1312/530, loss: 0.5257468223571777
2023-01-22 23:29:16.465331: step: 1316/530, loss: 2.175075054168701
2023-01-22 23:29:17.596986: step: 1320/530, loss: 0.5954471826553345
2023-01-22 23:29:18.783010: step: 1324/530, loss: 1.0144542455673218
2023-01-22 23:29:19.943589: step: 1328/530, loss: 1.098166823387146
2023-01-22 23:29:21.112868: step: 1332/530, loss: 2.2659215927124023
2023-01-22 23:29:22.317289: step: 1336/530, loss: 2.822305202484131
2023-01-22 23:29:23.492829: step: 1340/530, loss: 0.5859823822975159
2023-01-22 23:29:24.698143: step: 1344/530, loss: 1.0970247983932495
2023-01-22 23:29:25.872389: step: 1348/530, loss: 0.2839561998844147
2023-01-22 23:29:27.076758: step: 1352/530, loss: 1.1143438816070557
2023-01-22 23:29:28.227828: step: 1356/530, loss: 0.6988218426704407
2023-01-22 23:29:29.401049: step: 1360/530, loss: 0.3243767321109772
2023-01-22 23:29:30.569095: step: 1364/530, loss: 1.795779824256897
2023-01-22 23:29:31.755801: step: 1368/530, loss: 0.4606708586215973
2023-01-22 23:29:32.903991: step: 1372/530, loss: 1.1833899021148682
2023-01-22 23:29:34.061369: step: 1376/530, loss: 0.26833319664001465
2023-01-22 23:29:35.221369: step: 1380/530, loss: 0.6115039587020874
2023-01-22 23:29:36.362998: step: 1384/530, loss: 0.32991185784339905
2023-01-22 23:29:37.566368: step: 1388/530, loss: 1.9790300130844116
2023-01-22 23:29:38.707600: step: 1392/530, loss: 1.6219842433929443
2023-01-22 23:29:39.883568: step: 1396/530, loss: 0.2364889681339264
2023-01-22 23:29:41.078829: step: 1400/530, loss: 1.5593031644821167
2023-01-22 23:29:42.278346: step: 1404/530, loss: 2.0267093181610107
2023-01-22 23:29:43.469200: step: 1408/530, loss: 0.975976288318634
2023-01-22 23:29:44.641060: step: 1412/530, loss: 0.2554343044757843
2023-01-22 23:29:45.813482: step: 1416/530, loss: 0.49041810631752014
2023-01-22 23:29:46.979836: step: 1420/530, loss: 1.1858885288238525
2023-01-22 23:29:48.151580: step: 1424/530, loss: 0.42878180742263794
2023-01-22 23:29:49.320277: step: 1428/530, loss: 0.5493103861808777
2023-01-22 23:29:50.491102: step: 1432/530, loss: 1.5281364917755127
2023-01-22 23:29:51.650891: step: 1436/530, loss: 1.5015480518341064
2023-01-22 23:29:52.802122: step: 1440/530, loss: 1.9158960580825806
2023-01-22 23:29:53.991999: step: 1444/530, loss: 1.9169243574142456
2023-01-22 23:29:55.153810: step: 1448/530, loss: 0.32771578431129456
2023-01-22 23:29:56.333840: step: 1452/530, loss: 0.5097944736480713
2023-01-22 23:29:57.474916: step: 1456/530, loss: 0.26397567987442017
2023-01-22 23:29:58.638126: step: 1460/530, loss: 0.9739590883255005
2023-01-22 23:29:59.874060: step: 1464/530, loss: 0.39235609769821167
2023-01-22 23:30:01.058866: step: 1468/530, loss: 1.3040274381637573
2023-01-22 23:30:02.213982: step: 1472/530, loss: 1.1072018146514893
2023-01-22 23:30:03.391798: step: 1476/530, loss: 2.0209405422210693
2023-01-22 23:30:04.584045: step: 1480/530, loss: 1.5498924255371094
2023-01-22 23:30:05.803648: step: 1484/530, loss: 0.2637074589729309
2023-01-22 23:30:06.986232: step: 1488/530, loss: 1.4442286491394043
2023-01-22 23:30:08.143286: step: 1492/530, loss: 0.9857972860336304
2023-01-22 23:30:09.304604: step: 1496/530, loss: 0.3248816430568695
2023-01-22 23:30:10.531064: step: 1500/530, loss: 1.0157831907272339
2023-01-22 23:30:11.723832: step: 1504/530, loss: 1.0291160345077515
2023-01-22 23:30:12.898612: step: 1508/530, loss: 0.13757237792015076
2023-01-22 23:30:14.044482: step: 1512/530, loss: 2.0784716606140137
2023-01-22 23:30:15.245910: step: 1516/530, loss: 2.0741190910339355
2023-01-22 23:30:16.454476: step: 1520/530, loss: 0.277141809463501
2023-01-22 23:30:17.632041: step: 1524/530, loss: 1.0505849123001099
2023-01-22 23:30:18.765983: step: 1528/530, loss: 1.8539321422576904
2023-01-22 23:30:19.942381: step: 1532/530, loss: 2.7188661098480225
2023-01-22 23:30:21.095375: step: 1536/530, loss: 0.35789886116981506
2023-01-22 23:30:22.251908: step: 1540/530, loss: 0.45019227266311646
2023-01-22 23:30:23.428023: step: 1544/530, loss: 2.5588836669921875
2023-01-22 23:30:24.588768: step: 1548/530, loss: 2.848616600036621
2023-01-22 23:30:25.750681: step: 1552/530, loss: 1.191169023513794
2023-01-22 23:30:26.922070: step: 1556/530, loss: 0.6516002416610718
2023-01-22 23:30:28.079493: step: 1560/530, loss: 1.4375171661376953
2023-01-22 23:30:29.213379: step: 1564/530, loss: 2.6166090965270996
2023-01-22 23:30:30.362119: step: 1568/530, loss: 0.4241008758544922
2023-01-22 23:30:31.581541: step: 1572/530, loss: 0.7075384855270386
2023-01-22 23:30:32.747755: step: 1576/530, loss: 0.30217456817626953
2023-01-22 23:30:33.877125: step: 1580/530, loss: 1.2296066284179688
2023-01-22 23:30:35.042168: step: 1584/530, loss: 0.1581396609544754
2023-01-22 23:30:36.237202: step: 1588/530, loss: 0.15544824302196503
2023-01-22 23:30:37.411588: step: 1592/530, loss: 0.9800190925598145
2023-01-22 23:30:38.586038: step: 1596/530, loss: 0.6308501362800598
2023-01-22 23:30:39.763800: step: 1600/530, loss: 1.304701566696167
2023-01-22 23:30:40.916565: step: 1604/530, loss: 0.48541295528411865
2023-01-22 23:30:42.075626: step: 1608/530, loss: 1.5686932802200317
2023-01-22 23:30:43.248068: step: 1612/530, loss: 1.1183862686157227
2023-01-22 23:30:44.444696: step: 1616/530, loss: 1.0055925846099854
2023-01-22 23:30:45.632438: step: 1620/530, loss: 1.1093666553497314
2023-01-22 23:30:46.791719: step: 1624/530, loss: 2.5413472652435303
2023-01-22 23:30:47.976130: step: 1628/530, loss: 1.0392913818359375
2023-01-22 23:30:49.110172: step: 1632/530, loss: 0.6367090344429016
2023-01-22 23:30:50.289056: step: 1636/530, loss: 0.9832679629325867
2023-01-22 23:30:51.473323: step: 1640/530, loss: 2.923659563064575
2023-01-22 23:30:52.664722: step: 1644/530, loss: 0.9545735120773315
2023-01-22 23:30:53.820238: step: 1648/530, loss: 2.4707348346710205
2023-01-22 23:30:54.957438: step: 1652/530, loss: 8.249143600463867
2023-01-22 23:30:56.181790: step: 1656/530, loss: 5.710055351257324
2023-01-22 23:30:57.328101: step: 1660/530, loss: 3.128147602081299
2023-01-22 23:30:58.523137: step: 1664/530, loss: 2.0731728076934814
2023-01-22 23:30:59.675351: step: 1668/530, loss: 1.7015742063522339
2023-01-22 23:31:00.898989: step: 1672/530, loss: 3.0843937397003174
2023-01-22 23:31:02.074520: step: 1676/530, loss: 0.5505193471908569
2023-01-22 23:31:03.227290: step: 1680/530, loss: 0.24050307273864746
2023-01-22 23:31:04.407859: step: 1684/530, loss: 2.563603401184082
2023-01-22 23:31:05.569710: step: 1688/530, loss: 0.2692674696445465
2023-01-22 23:31:06.730833: step: 1692/530, loss: 1.6214840412139893
2023-01-22 23:31:07.907550: step: 1696/530, loss: 2.4539895057678223
2023-01-22 23:31:09.043543: step: 1700/530, loss: 0.4843244254589081
2023-01-22 23:31:10.273539: step: 1704/530, loss: 0.9586536288261414
2023-01-22 23:31:11.438949: step: 1708/530, loss: 0.31897610425949097
2023-01-22 23:31:12.668488: step: 1712/530, loss: 0.6313233971595764
2023-01-22 23:31:13.837107: step: 1716/530, loss: 0.2316306233406067
2023-01-22 23:31:14.999098: step: 1720/530, loss: 2.878556251525879
2023-01-22 23:31:16.143793: step: 1724/530, loss: 0.682036280632019
2023-01-22 23:31:17.347821: step: 1728/530, loss: 2.095612049102783
2023-01-22 23:31:18.547185: step: 1732/530, loss: 0.5580075979232788
2023-01-22 23:31:19.709887: step: 1736/530, loss: 0.3293209969997406
2023-01-22 23:31:20.866524: step: 1740/530, loss: 1.3797705173492432
2023-01-22 23:31:22.060700: step: 1744/530, loss: 7.03170919418335
2023-01-22 23:31:23.207513: step: 1748/530, loss: 2.1363449096679688
2023-01-22 23:31:24.396369: step: 1752/530, loss: 1.2319419384002686
2023-01-22 23:31:25.580856: step: 1756/530, loss: 0.23436132073402405
2023-01-22 23:31:26.720916: step: 1760/530, loss: 2.2236969470977783
2023-01-22 23:31:27.892974: step: 1764/530, loss: 0.5651636123657227
2023-01-22 23:31:29.066136: step: 1768/530, loss: 2.6681671142578125
2023-01-22 23:31:30.224388: step: 1772/530, loss: 2.197348117828369
2023-01-22 23:31:31.406029: step: 1776/530, loss: 1.106221079826355
2023-01-22 23:31:32.571310: step: 1780/530, loss: 2.397181987762451
2023-01-22 23:31:33.745795: step: 1784/530, loss: 0.9104430079460144
2023-01-22 23:31:34.908498: step: 1788/530, loss: 0.5737716555595398
2023-01-22 23:31:36.067747: step: 1792/530, loss: 7.948434352874756
2023-01-22 23:31:37.246632: step: 1796/530, loss: 0.8916475176811218
2023-01-22 23:31:38.424591: step: 1800/530, loss: 1.126198649406433
2023-01-22 23:31:39.598396: step: 1804/530, loss: 1.0233383178710938
2023-01-22 23:31:40.839494: step: 1808/530, loss: 1.742366909980774
2023-01-22 23:31:42.007422: step: 1812/530, loss: 2.1947848796844482
2023-01-22 23:31:43.195784: step: 1816/530, loss: 0.20224609971046448
2023-01-22 23:31:44.353396: step: 1820/530, loss: 0.47669029235839844
2023-01-22 23:31:45.518849: step: 1824/530, loss: 1.6268694400787354
2023-01-22 23:31:46.648260: step: 1828/530, loss: 0.35870909690856934
2023-01-22 23:31:47.835519: step: 1832/530, loss: 0.2243306189775467
2023-01-22 23:31:48.988900: step: 1836/530, loss: 1.190079927444458
2023-01-22 23:31:50.179347: step: 1840/530, loss: 0.48348483443260193
2023-01-22 23:31:51.320078: step: 1844/530, loss: 0.6199809312820435
2023-01-22 23:31:52.494234: step: 1848/530, loss: 2.471400260925293
2023-01-22 23:31:53.690217: step: 1852/530, loss: 0.8697818517684937
2023-01-22 23:31:54.881477: step: 1856/530, loss: 0.256306916475296
2023-01-22 23:31:56.065031: step: 1860/530, loss: 2.5766377449035645
2023-01-22 23:31:57.209733: step: 1864/530, loss: 0.1835063397884369
2023-01-22 23:31:58.395410: step: 1868/530, loss: 0.26685434579849243
2023-01-22 23:31:59.581043: step: 1872/530, loss: 0.5715863704681396
2023-01-22 23:32:00.765586: step: 1876/530, loss: 1.0721778869628906
2023-01-22 23:32:01.920986: step: 1880/530, loss: 0.2672633230686188
2023-01-22 23:32:03.146259: step: 1884/530, loss: 0.9958361983299255
2023-01-22 23:32:04.326583: step: 1888/530, loss: 0.6078117489814758
2023-01-22 23:32:05.482523: step: 1892/530, loss: 0.16473440825939178
2023-01-22 23:32:06.703033: step: 1896/530, loss: 0.313943088054657
2023-01-22 23:32:07.879444: step: 1900/530, loss: 1.1060047149658203
2023-01-22 23:32:09.074822: step: 1904/530, loss: 0.32612329721450806
2023-01-22 23:32:10.269292: step: 1908/530, loss: 0.679754376411438
2023-01-22 23:32:11.449865: step: 1912/530, loss: 3.5244832038879395
2023-01-22 23:32:12.662502: step: 1916/530, loss: 0.6347153186798096
2023-01-22 23:32:13.832406: step: 1920/530, loss: 0.38395142555236816
2023-01-22 23:32:14.991650: step: 1924/530, loss: 0.43221569061279297
2023-01-22 23:32:16.175323: step: 1928/530, loss: 1.3999722003936768
2023-01-22 23:32:17.363520: step: 1932/530, loss: 2.0128231048583984
2023-01-22 23:32:18.551591: step: 1936/530, loss: 0.3185945451259613
2023-01-22 23:32:19.711304: step: 1940/530, loss: 0.13733787834644318
2023-01-22 23:32:20.892097: step: 1944/530, loss: 2.5620791912078857
2023-01-22 23:32:22.079827: step: 1948/530, loss: 0.35016995668411255
2023-01-22 23:32:23.216085: step: 1952/530, loss: 0.47112616896629333
2023-01-22 23:32:24.385218: step: 1956/530, loss: 0.24896173179149628
2023-01-22 23:32:25.565281: step: 1960/530, loss: 1.667509913444519
2023-01-22 23:32:26.737903: step: 1964/530, loss: 0.420863538980484
2023-01-22 23:32:27.957664: step: 1968/530, loss: 0.5923202633857727
2023-01-22 23:32:29.121837: step: 1972/530, loss: 0.6023988723754883
2023-01-22 23:32:30.272112: step: 1976/530, loss: 0.16907010972499847
2023-01-22 23:32:31.492816: step: 1980/530, loss: 1.136102557182312
2023-01-22 23:32:32.704351: step: 1984/530, loss: 0.23996008932590485
2023-01-22 23:32:33.883834: step: 1988/530, loss: 1.2824426889419556
2023-01-22 23:32:35.053562: step: 1992/530, loss: 1.0406427383422852
2023-01-22 23:32:36.214125: step: 1996/530, loss: 0.3827822208404541
2023-01-22 23:32:37.390240: step: 2000/530, loss: 0.7970246076583862
2023-01-22 23:32:38.570816: step: 2004/530, loss: 0.4341971278190613
2023-01-22 23:32:39.730995: step: 2008/530, loss: 0.6576734781265259
2023-01-22 23:32:40.910567: step: 2012/530, loss: 0.3152327537536621
2023-01-22 23:32:42.141732: step: 2016/530, loss: 0.2892214059829712
2023-01-22 23:32:43.310881: step: 2020/530, loss: 0.34775933623313904
2023-01-22 23:32:44.470233: step: 2024/530, loss: 0.6816993951797485
2023-01-22 23:32:45.601636: step: 2028/530, loss: 1.1355819702148438
2023-01-22 23:32:46.789008: step: 2032/530, loss: 0.4416075050830841
2023-01-22 23:32:47.932704: step: 2036/530, loss: 2.18332576751709
2023-01-22 23:32:49.140037: step: 2040/530, loss: 0.3988000750541687
2023-01-22 23:32:50.315019: step: 2044/530, loss: 0.9270526766777039
2023-01-22 23:32:51.481501: step: 2048/530, loss: 0.31174221634864807
2023-01-22 23:32:52.645511: step: 2052/530, loss: 1.2042081356048584
2023-01-22 23:32:53.808674: step: 2056/530, loss: 0.4926568865776062
2023-01-22 23:32:54.980288: step: 2060/530, loss: 0.9439895153045654
2023-01-22 23:32:56.210291: step: 2064/530, loss: 0.6370525360107422
2023-01-22 23:32:57.404964: step: 2068/530, loss: 0.38037627935409546
2023-01-22 23:32:58.549636: step: 2072/530, loss: 0.9322097897529602
2023-01-22 23:32:59.717059: step: 2076/530, loss: 0.3103620111942291
2023-01-22 23:33:00.903231: step: 2080/530, loss: 1.1562665700912476
2023-01-22 23:33:02.046971: step: 2084/530, loss: 1.0123546123504639
2023-01-22 23:33:03.231003: step: 2088/530, loss: 0.33552056550979614
2023-01-22 23:33:04.405228: step: 2092/530, loss: 0.4500119090080261
2023-01-22 23:33:05.582111: step: 2096/530, loss: 0.2729125916957855
2023-01-22 23:33:06.750045: step: 2100/530, loss: 0.8104250431060791
2023-01-22 23:33:07.972557: step: 2104/530, loss: 0.520806074142456
2023-01-22 23:33:09.184268: step: 2108/530, loss: 1.4512125253677368
2023-01-22 23:33:10.360978: step: 2112/530, loss: 0.4688398540019989
2023-01-22 23:33:11.604016: step: 2116/530, loss: 0.9123752117156982
2023-01-22 23:33:12.783052: step: 2120/530, loss: 0.18193435668945312
==================================================
Loss: 3.271
--------------------
Dev: {'event': {'p': 0.6494345718901454, 'r': 0.5352862849533955, 'f1': 0.5868613138686131}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Test: {'event': {'p': 0.6062717770034843, 'r': 0.40023001725129387, 'f1': 0.48216141323172845}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Chinese: {'event': {'p': 0.6451612903225806, 'r': 0.37037037037037035, 'f1': 0.4705882352941176}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Korean: {'event': {'p': 0.875, 'r': 0.2222222222222222, 'f1': 0.3544303797468354}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Russian: {'event': {'p': 0.8333333333333334, 'r': 0.1388888888888889, 'f1': 0.2380952380952381}, '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': 0.6494345718901454, 'r': 0.5352862849533955, 'f1': 0.5868613138686131}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Eng Test for Chinese: {'event': {'p': 0.6062717770034843, 'r': 0.40023001725129387, 'f1': 0.48216141323172845}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Sample Chinese: {'event': {'p': 0.6451612903225806, 'r': 0.37037037037037035, 'f1': 0.4705882352941176}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6494345718901454, 'r': 0.5352862849533955, 'f1': 0.5868613138686131}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Eng Test for Korean: {'event': {'p': 0.6062717770034843, 'r': 0.40023001725129387, 'f1': 0.48216141323172845}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Sample Korean: {'event': {'p': 0.875, 'r': 0.2222222222222222, 'f1': 0.3544303797468354}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6494345718901454, 'r': 0.5352862849533955, 'f1': 0.5868613138686131}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Eng Test for Russian: {'event': {'p': 0.6062717770034843, 'r': 0.40023001725129387, 'f1': 0.48216141323172845}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Sample Russian: {'event': {'p': 0.8333333333333334, 'r': 0.1388888888888889, 'f1': 0.2380952380952381}, '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 23:34:20.145245: step: 4/530, loss: 0.855586051940918
2023-01-22 23:34:21.287240: step: 8/530, loss: 0.4452177882194519
2023-01-22 23:34:22.457520: step: 12/530, loss: 0.7808765172958374
2023-01-22 23:34:23.662372: step: 16/530, loss: 2.1084628105163574
2023-01-22 23:34:24.870829: step: 20/530, loss: 1.1509861946105957
2023-01-22 23:34:26.031035: step: 24/530, loss: 4.751423358917236
2023-01-22 23:34:27.188079: step: 28/530, loss: 1.015251874923706
2023-01-22 23:34:28.396545: step: 32/530, loss: 0.6905354261398315
2023-01-22 23:34:29.548420: step: 36/530, loss: 2.4051554203033447
2023-01-22 23:34:30.706018: step: 40/530, loss: 0.6779331564903259
2023-01-22 23:34:31.854400: step: 44/530, loss: 1.6110358238220215
2023-01-22 23:34:33.058929: step: 48/530, loss: 2.5808560848236084
2023-01-22 23:34:34.272698: step: 52/530, loss: 2.0342133045196533
2023-01-22 23:34:35.488483: step: 56/530, loss: 1.0091273784637451
2023-01-22 23:34:36.649038: step: 60/530, loss: 1.0374675989151
2023-01-22 23:34:37.802645: step: 64/530, loss: 1.0511161088943481
2023-01-22 23:34:38.960819: step: 68/530, loss: 0.7938187122344971
2023-01-22 23:34:40.158587: step: 72/530, loss: 1.57943856716156
2023-01-22 23:34:41.342348: step: 76/530, loss: 0.8337065577507019
2023-01-22 23:34:42.527995: step: 80/530, loss: 0.44812488555908203
2023-01-22 23:34:43.738210: step: 84/530, loss: 0.4170568287372589
2023-01-22 23:34:44.919391: step: 88/530, loss: 0.8539484143257141
2023-01-22 23:34:46.128576: step: 92/530, loss: 1.6921844482421875
2023-01-22 23:34:47.308848: step: 96/530, loss: 0.21476612985134125
2023-01-22 23:34:48.443784: step: 100/530, loss: 0.26030951738357544
2023-01-22 23:34:49.591035: step: 104/530, loss: 6.710485935211182
2023-01-22 23:34:50.746966: step: 108/530, loss: 1.340043544769287
2023-01-22 23:34:51.992155: step: 112/530, loss: 0.37760084867477417
2023-01-22 23:34:53.161711: step: 116/530, loss: 0.7547712922096252
2023-01-22 23:34:54.319438: step: 120/530, loss: 0.7568196058273315
2023-01-22 23:34:55.508931: step: 124/530, loss: 1.65353262424469
2023-01-22 23:34:56.676564: step: 128/530, loss: 0.8805731534957886
2023-01-22 23:34:57.850087: step: 132/530, loss: 1.305283546447754
2023-01-22 23:34:59.068709: step: 136/530, loss: 0.19624194502830505
2023-01-22 23:35:00.232852: step: 140/530, loss: 0.16028723120689392
2023-01-22 23:35:01.372874: step: 144/530, loss: 0.11081180721521378
2023-01-22 23:35:02.501588: step: 148/530, loss: 0.38658079504966736
2023-01-22 23:35:03.679958: step: 152/530, loss: 0.5124524831771851
2023-01-22 23:35:04.841953: step: 156/530, loss: 0.9850184917449951
2023-01-22 23:35:06.033800: step: 160/530, loss: 0.38996392488479614
2023-01-22 23:35:07.198489: step: 164/530, loss: 0.9529595375061035
2023-01-22 23:35:08.378280: step: 168/530, loss: 0.2647349238395691
2023-01-22 23:35:09.557543: step: 172/530, loss: 0.2961168885231018
2023-01-22 23:35:10.745973: step: 176/530, loss: 0.829142689704895
2023-01-22 23:35:11.933384: step: 180/530, loss: 0.2034660279750824
2023-01-22 23:35:13.105895: step: 184/530, loss: 0.09820985794067383
2023-01-22 23:35:14.248888: step: 188/530, loss: 0.1975582093000412
2023-01-22 23:35:15.451353: step: 192/530, loss: 0.10032311081886292
2023-01-22 23:35:16.642656: step: 196/530, loss: 0.5717596411705017
2023-01-22 23:35:17.826414: step: 200/530, loss: 0.26164865493774414
2023-01-22 23:35:18.956649: step: 204/530, loss: 0.240918830037117
2023-01-22 23:35:20.222988: step: 208/530, loss: 0.733033299446106
2023-01-22 23:35:21.407639: step: 212/530, loss: 1.5578622817993164
2023-01-22 23:35:22.562206: step: 216/530, loss: 1.1439812183380127
2023-01-22 23:35:23.762293: step: 220/530, loss: 0.10916472226381302
2023-01-22 23:35:24.889760: step: 224/530, loss: 0.219997376203537
2023-01-22 23:35:26.005839: step: 228/530, loss: 0.2788964807987213
2023-01-22 23:35:27.211487: step: 232/530, loss: 0.38707637786865234
2023-01-22 23:35:28.409541: step: 236/530, loss: 0.4448709487915039
2023-01-22 23:35:29.586677: step: 240/530, loss: 0.8720974922180176
2023-01-22 23:35:30.760336: step: 244/530, loss: 1.384368658065796
2023-01-22 23:35:31.934313: step: 248/530, loss: 0.29836687445640564
2023-01-22 23:35:33.083014: step: 252/530, loss: 0.6134076118469238
2023-01-22 23:35:34.266565: step: 256/530, loss: 0.2177387773990631
2023-01-22 23:35:35.423756: step: 260/530, loss: 1.3922553062438965
2023-01-22 23:35:36.635401: step: 264/530, loss: 0.6501887440681458
2023-01-22 23:35:37.829105: step: 268/530, loss: 0.2935255169868469
2023-01-22 23:35:38.983419: step: 272/530, loss: 0.15427465736865997
2023-01-22 23:35:40.150115: step: 276/530, loss: 1.3494079113006592
2023-01-22 23:35:41.349643: step: 280/530, loss: 0.3016176223754883
2023-01-22 23:35:42.582905: step: 284/530, loss: 1.1531164646148682
2023-01-22 23:35:43.791872: step: 288/530, loss: 0.6608260869979858
2023-01-22 23:35:44.952084: step: 292/530, loss: 0.29079669713974
2023-01-22 23:35:46.091305: step: 296/530, loss: 0.33798158168792725
2023-01-22 23:35:47.235911: step: 300/530, loss: 0.285319983959198
2023-01-22 23:35:48.437440: step: 304/530, loss: 0.35087910294532776
2023-01-22 23:35:49.591467: step: 308/530, loss: 1.0302305221557617
2023-01-22 23:35:50.734113: step: 312/530, loss: 0.7295089960098267
2023-01-22 23:35:51.930075: step: 316/530, loss: 1.2713327407836914
2023-01-22 23:35:53.108701: step: 320/530, loss: 2.478558301925659
2023-01-22 23:35:54.307389: step: 324/530, loss: 1.1010805368423462
2023-01-22 23:35:55.538807: step: 328/530, loss: 0.25483864545822144
2023-01-22 23:35:56.694940: step: 332/530, loss: 0.7715908288955688
2023-01-22 23:35:57.864387: step: 336/530, loss: 1.1186020374298096
2023-01-22 23:35:59.026137: step: 340/530, loss: 1.389279842376709
2023-01-22 23:36:00.171601: step: 344/530, loss: 0.2544185519218445
2023-01-22 23:36:01.312736: step: 348/530, loss: 1.660683274269104
2023-01-22 23:36:02.473247: step: 352/530, loss: 0.18009424209594727
2023-01-22 23:36:03.603075: step: 356/530, loss: 0.1359354555606842
2023-01-22 23:36:04.756119: step: 360/530, loss: 0.43625032901763916
2023-01-22 23:36:05.908597: step: 364/530, loss: 1.1416860818862915
2023-01-22 23:36:07.077115: step: 368/530, loss: 1.5651010274887085
2023-01-22 23:36:08.264649: step: 372/530, loss: 0.6074217557907104
2023-01-22 23:36:09.439331: step: 376/530, loss: 0.43942880630493164
2023-01-22 23:36:10.641794: step: 380/530, loss: 0.16805659234523773
2023-01-22 23:36:11.869395: step: 384/530, loss: 8.138800621032715
2023-01-22 23:36:13.090642: step: 388/530, loss: 0.12257328629493713
2023-01-22 23:36:14.294611: step: 392/530, loss: 0.5365084409713745
2023-01-22 23:36:15.469497: step: 396/530, loss: 0.43380793929100037
2023-01-22 23:36:16.661990: step: 400/530, loss: 0.4543578624725342
2023-01-22 23:36:17.813748: step: 404/530, loss: 1.8094607591629028
2023-01-22 23:36:19.008311: step: 408/530, loss: 1.2202258110046387
2023-01-22 23:36:20.188698: step: 412/530, loss: 1.421649694442749
2023-01-22 23:36:21.365902: step: 416/530, loss: 0.18434977531433105
2023-01-22 23:36:22.567371: step: 420/530, loss: 9.340108871459961
2023-01-22 23:36:23.753399: step: 424/530, loss: 0.5615571141242981
2023-01-22 23:36:24.939468: step: 428/530, loss: 0.8760896921157837
2023-01-22 23:36:26.146607: step: 432/530, loss: 1.0122190713882446
2023-01-22 23:36:27.364494: step: 436/530, loss: 0.27063122391700745
2023-01-22 23:36:28.512934: step: 440/530, loss: 7.342632293701172
2023-01-22 23:36:29.644059: step: 444/530, loss: 1.4113372564315796
2023-01-22 23:36:30.821340: step: 448/530, loss: 3.759502410888672
2023-01-22 23:36:31.974150: step: 452/530, loss: 0.32438936829566956
2023-01-22 23:36:33.119792: step: 456/530, loss: 0.8607702255249023
2023-01-22 23:36:34.299939: step: 460/530, loss: 0.07533013820648193
2023-01-22 23:36:35.495404: step: 464/530, loss: 0.2518903315067291
2023-01-22 23:36:36.636941: step: 468/530, loss: 2.029696464538574
2023-01-22 23:36:37.829560: step: 472/530, loss: 0.3324987292289734
2023-01-22 23:36:39.035144: step: 476/530, loss: 1.5389682054519653
2023-01-22 23:36:40.227571: step: 480/530, loss: 0.3384334444999695
2023-01-22 23:36:41.375742: step: 484/530, loss: 2.2825450897216797
2023-01-22 23:36:42.618710: step: 488/530, loss: 0.7989309430122375
2023-01-22 23:36:43.809629: step: 492/530, loss: 0.28409624099731445
2023-01-22 23:36:45.017340: step: 496/530, loss: 0.752198338508606
2023-01-22 23:36:46.208093: step: 500/530, loss: 0.8345478773117065
2023-01-22 23:36:47.385321: step: 504/530, loss: 0.1897333264350891
2023-01-22 23:36:48.572208: step: 508/530, loss: 1.1299785375595093
2023-01-22 23:36:49.752985: step: 512/530, loss: 0.23597225546836853
2023-01-22 23:36:50.918063: step: 516/530, loss: 0.39859825372695923
2023-01-22 23:36:52.130277: step: 520/530, loss: 4.35719633102417
2023-01-22 23:36:53.309532: step: 524/530, loss: 1.389021396636963
2023-01-22 23:36:54.483305: step: 528/530, loss: 0.16513347625732422
2023-01-22 23:36:55.679987: step: 532/530, loss: 0.0874779224395752
2023-01-22 23:36:56.884331: step: 536/530, loss: 2.670804500579834
2023-01-22 23:36:58.034668: step: 540/530, loss: 0.7235707640647888
2023-01-22 23:36:59.218421: step: 544/530, loss: 0.1981537938117981
2023-01-22 23:37:00.406393: step: 548/530, loss: 0.34508436918258667
2023-01-22 23:37:01.551212: step: 552/530, loss: 0.1716330647468567
2023-01-22 23:37:02.730539: step: 556/530, loss: 0.2664264738559723
2023-01-22 23:37:03.888643: step: 560/530, loss: 0.21540242433547974
2023-01-22 23:37:05.067746: step: 564/530, loss: 1.2255761623382568
2023-01-22 23:37:06.277156: step: 568/530, loss: 0.31872478127479553
2023-01-22 23:37:07.472428: step: 572/530, loss: 1.0184437036514282
2023-01-22 23:37:08.701971: step: 576/530, loss: 0.9865986108779907
2023-01-22 23:37:09.882334: step: 580/530, loss: 0.25358596444129944
2023-01-22 23:37:11.076619: step: 584/530, loss: 0.20358476042747498
2023-01-22 23:37:12.256930: step: 588/530, loss: 1.6305444240570068
2023-01-22 23:37:13.418555: step: 592/530, loss: 0.26738205552101135
2023-01-22 23:37:14.601250: step: 596/530, loss: 0.652937114238739
2023-01-22 23:37:15.744562: step: 600/530, loss: 1.003240704536438
2023-01-22 23:37:16.947479: step: 604/530, loss: 1.7002644538879395
2023-01-22 23:37:18.158189: step: 608/530, loss: 2.705268144607544
2023-01-22 23:37:19.316094: step: 612/530, loss: 1.6582444906234741
2023-01-22 23:37:20.479580: step: 616/530, loss: 0.2572961747646332
2023-01-22 23:37:21.630521: step: 620/530, loss: 0.3205597698688507
2023-01-22 23:37:22.811024: step: 624/530, loss: 0.25733035802841187
2023-01-22 23:37:23.988920: step: 628/530, loss: 0.40362483263015747
2023-01-22 23:37:25.137319: step: 632/530, loss: 1.9283860921859741
2023-01-22 23:37:26.290505: step: 636/530, loss: 0.7558004260063171
2023-01-22 23:37:27.388681: step: 640/530, loss: 0.8630129098892212
2023-01-22 23:37:28.534132: step: 644/530, loss: 0.2125963568687439
2023-01-22 23:37:29.686701: step: 648/530, loss: 0.714661180973053
2023-01-22 23:37:30.853111: step: 652/530, loss: 0.20170755684375763
2023-01-22 23:37:32.014881: step: 656/530, loss: 2.27115535736084
2023-01-22 23:37:33.159705: step: 660/530, loss: 0.3236314058303833
2023-01-22 23:37:34.284689: step: 664/530, loss: 0.785652220249176
2023-01-22 23:37:35.466561: step: 668/530, loss: 1.093957781791687
2023-01-22 23:37:36.675895: step: 672/530, loss: 0.21857725083827972
2023-01-22 23:37:37.867076: step: 676/530, loss: 0.37661075592041016
2023-01-22 23:37:39.055973: step: 680/530, loss: 0.49998435378074646
2023-01-22 23:37:40.231205: step: 684/530, loss: 0.583878219127655
2023-01-22 23:37:41.390010: step: 688/530, loss: 0.873389720916748
2023-01-22 23:37:42.592209: step: 692/530, loss: 3.0190699100494385
2023-01-22 23:37:43.724713: step: 696/530, loss: 0.38237205147743225
2023-01-22 23:37:44.915136: step: 700/530, loss: 0.20649003982543945
2023-01-22 23:37:46.092059: step: 704/530, loss: 0.6627522706985474
2023-01-22 23:37:47.218016: step: 708/530, loss: 0.3603910505771637
2023-01-22 23:37:48.367890: step: 712/530, loss: 0.549861490726471
2023-01-22 23:37:49.548079: step: 716/530, loss: 1.6641340255737305
2023-01-22 23:37:50.746499: step: 720/530, loss: 0.5336326360702515
2023-01-22 23:37:51.903914: step: 724/530, loss: 6.969512939453125
2023-01-22 23:37:53.079921: step: 728/530, loss: 0.5900471210479736
2023-01-22 23:37:54.251947: step: 732/530, loss: 0.8938699960708618
2023-01-22 23:37:55.439792: step: 736/530, loss: 0.38054150342941284
2023-01-22 23:37:56.582744: step: 740/530, loss: 0.13817104697227478
2023-01-22 23:37:57.766174: step: 744/530, loss: 0.4687361717224121
2023-01-22 23:37:58.918120: step: 748/530, loss: 0.23717433214187622
2023-01-22 23:38:00.064446: step: 752/530, loss: 0.23689956963062286
2023-01-22 23:38:01.216648: step: 756/530, loss: 0.11090616881847382
2023-01-22 23:38:02.411003: step: 760/530, loss: 0.2205759435892105
2023-01-22 23:38:03.554693: step: 764/530, loss: 0.7549692988395691
2023-01-22 23:38:04.679857: step: 768/530, loss: 0.5236148834228516
2023-01-22 23:38:05.856499: step: 772/530, loss: 0.34295111894607544
2023-01-22 23:38:07.027562: step: 776/530, loss: 1.338382601737976
2023-01-22 23:38:08.182793: step: 780/530, loss: 2.277797222137451
2023-01-22 23:38:09.319943: step: 784/530, loss: 0.9836255311965942
2023-01-22 23:38:10.518281: step: 788/530, loss: 0.24366359412670135
2023-01-22 23:38:11.716552: step: 792/530, loss: 1.9622857570648193
2023-01-22 23:38:12.868145: step: 796/530, loss: 0.49967890977859497
2023-01-22 23:38:13.989742: step: 800/530, loss: 0.24676236510276794
2023-01-22 23:38:15.157393: step: 804/530, loss: 0.2415885031223297
2023-01-22 23:38:16.339915: step: 808/530, loss: 0.49461764097213745
2023-01-22 23:38:17.504299: step: 812/530, loss: 0.7522754669189453
2023-01-22 23:38:18.700194: step: 816/530, loss: 0.16216811537742615
2023-01-22 23:38:19.867005: step: 820/530, loss: 0.23912134766578674
2023-01-22 23:38:21.057663: step: 824/530, loss: 0.538262665271759
2023-01-22 23:38:22.241970: step: 828/530, loss: 1.7306843996047974
2023-01-22 23:38:23.420108: step: 832/530, loss: 0.40253207087516785
2023-01-22 23:38:24.638903: step: 836/530, loss: 0.14648601412773132
2023-01-22 23:38:25.802473: step: 840/530, loss: 0.7606114149093628
2023-01-22 23:38:26.979797: step: 844/530, loss: 0.32902881503105164
2023-01-22 23:38:28.158427: step: 848/530, loss: 1.9820952415466309
2023-01-22 23:38:29.352719: step: 852/530, loss: 0.2864893972873688
2023-01-22 23:38:30.528978: step: 856/530, loss: 1.0638301372528076
2023-01-22 23:38:31.681107: step: 860/530, loss: 1.1397560834884644
2023-01-22 23:38:32.845605: step: 864/530, loss: 0.31781044602394104
2023-01-22 23:38:34.070859: step: 868/530, loss: 0.34152308106422424
2023-01-22 23:38:35.238778: step: 872/530, loss: 0.27122706174850464
2023-01-22 23:38:36.364526: step: 876/530, loss: 0.8363618850708008
2023-01-22 23:38:37.489841: step: 880/530, loss: 0.22394169867038727
2023-01-22 23:38:38.692567: step: 884/530, loss: 0.8044120073318481
2023-01-22 23:38:39.878989: step: 888/530, loss: 0.13389262557029724
2023-01-22 23:38:41.013553: step: 892/530, loss: 0.4735240042209625
2023-01-22 23:38:42.154700: step: 896/530, loss: 0.5812658071517944
2023-01-22 23:38:43.310030: step: 900/530, loss: 0.1132417693734169
2023-01-22 23:38:44.490751: step: 904/530, loss: 0.4325030744075775
2023-01-22 23:38:45.763401: step: 908/530, loss: 0.3314061164855957
2023-01-22 23:38:46.934718: step: 912/530, loss: 0.301017165184021
2023-01-22 23:38:48.122619: step: 916/530, loss: 0.32120147347450256
2023-01-22 23:38:49.281592: step: 920/530, loss: 0.483271062374115
2023-01-22 23:38:50.450707: step: 924/530, loss: 0.4006916284561157
2023-01-22 23:38:51.557576: step: 928/530, loss: 0.29290294647216797
2023-01-22 23:38:52.730515: step: 932/530, loss: 0.8069778680801392
2023-01-22 23:38:53.859018: step: 936/530, loss: 0.2538430988788605
2023-01-22 23:38:55.054765: step: 940/530, loss: 0.5062859058380127
2023-01-22 23:38:56.217988: step: 944/530, loss: 0.16179409623146057
2023-01-22 23:38:57.393603: step: 948/530, loss: 0.5537605881690979
2023-01-22 23:38:58.559074: step: 952/530, loss: 2.170041084289551
2023-01-22 23:38:59.732368: step: 956/530, loss: 0.14002355933189392
2023-01-22 23:39:00.912624: step: 960/530, loss: 0.19696339964866638
2023-01-22 23:39:02.109706: step: 964/530, loss: 0.23387423157691956
2023-01-22 23:39:03.281013: step: 968/530, loss: 0.3124666213989258
2023-01-22 23:39:04.434123: step: 972/530, loss: 0.35653600096702576
2023-01-22 23:39:05.618776: step: 976/530, loss: 0.2768324017524719
2023-01-22 23:39:06.760498: step: 980/530, loss: 0.429777592420578
2023-01-22 23:39:07.902678: step: 984/530, loss: 0.36741504073143005
2023-01-22 23:39:09.063757: step: 988/530, loss: 1.3030859231948853
2023-01-22 23:39:10.220057: step: 992/530, loss: 0.9199998378753662
2023-01-22 23:39:11.404643: step: 996/530, loss: 1.656630277633667
2023-01-22 23:39:12.579887: step: 1000/530, loss: 1.1406357288360596
2023-01-22 23:39:13.752724: step: 1004/530, loss: 0.7632325291633606
2023-01-22 23:39:14.906562: step: 1008/530, loss: 2.2819864749908447
2023-01-22 23:39:16.072293: step: 1012/530, loss: 0.3723047375679016
2023-01-22 23:39:17.211657: step: 1016/530, loss: 0.6346299052238464
2023-01-22 23:39:18.351104: step: 1020/530, loss: 1.2969610691070557
2023-01-22 23:39:19.518841: step: 1024/530, loss: 2.084010601043701
2023-01-22 23:39:20.657894: step: 1028/530, loss: 0.2546687126159668
2023-01-22 23:39:21.844681: step: 1032/530, loss: 0.31039056181907654
2023-01-22 23:39:23.029974: step: 1036/530, loss: 0.5513472557067871
2023-01-22 23:39:24.181166: step: 1040/530, loss: 0.17282705008983612
2023-01-22 23:39:25.330258: step: 1044/530, loss: 1.9321483373641968
2023-01-22 23:39:26.502439: step: 1048/530, loss: 1.239111065864563
2023-01-22 23:39:27.688621: step: 1052/530, loss: 0.09634113311767578
2023-01-22 23:39:28.896386: step: 1056/530, loss: 0.09708116203546524
2023-01-22 23:39:30.075115: step: 1060/530, loss: 1.2651984691619873
2023-01-22 23:39:31.283524: step: 1064/530, loss: 0.9781036376953125
2023-01-22 23:39:32.470342: step: 1068/530, loss: 0.4972190260887146
2023-01-22 23:39:33.601069: step: 1072/530, loss: 1.2587275505065918
2023-01-22 23:39:34.826643: step: 1076/530, loss: 0.30931395292282104
2023-01-22 23:39:36.018480: step: 1080/530, loss: 1.9697833061218262
2023-01-22 23:39:37.149607: step: 1084/530, loss: 0.5634654760360718
2023-01-22 23:39:38.309142: step: 1088/530, loss: 0.5499882698059082
2023-01-22 23:39:39.456160: step: 1092/530, loss: 0.11186311393976212
2023-01-22 23:39:40.604365: step: 1096/530, loss: 0.4333803057670593
2023-01-22 23:39:41.812687: step: 1100/530, loss: 2.1811606884002686
2023-01-22 23:39:43.007531: step: 1104/530, loss: 1.069535732269287
2023-01-22 23:39:44.160208: step: 1108/530, loss: 0.294659286737442
2023-01-22 23:39:45.305101: step: 1112/530, loss: 0.0853419303894043
2023-01-22 23:39:46.502149: step: 1116/530, loss: 0.22624774277210236
2023-01-22 23:39:47.637658: step: 1120/530, loss: 3.4426982402801514
2023-01-22 23:39:48.782318: step: 1124/530, loss: 0.15368223190307617
2023-01-22 23:39:49.970780: step: 1128/530, loss: 1.1220883131027222
2023-01-22 23:39:51.140867: step: 1132/530, loss: 1.181382179260254
2023-01-22 23:39:52.287668: step: 1136/530, loss: 1.783968448638916
2023-01-22 23:39:53.469652: step: 1140/530, loss: 1.5801727771759033
2023-01-22 23:39:54.644913: step: 1144/530, loss: 0.30916959047317505
2023-01-22 23:39:55.795346: step: 1148/530, loss: 0.11473093926906586
2023-01-22 23:39:56.932370: step: 1152/530, loss: 0.06336665153503418
2023-01-22 23:39:58.110013: step: 1156/530, loss: 2.589488983154297
2023-01-22 23:39:59.271348: step: 1160/530, loss: 0.6953050494194031
2023-01-22 23:40:00.453484: step: 1164/530, loss: 0.9822004437446594
2023-01-22 23:40:01.612881: step: 1168/530, loss: 0.18992625176906586
2023-01-22 23:40:02.740063: step: 1172/530, loss: 0.21517829596996307
2023-01-22 23:40:03.912796: step: 1176/530, loss: 0.45739316940307617
2023-01-22 23:40:05.080817: step: 1180/530, loss: 0.2898138165473938
2023-01-22 23:40:06.240856: step: 1184/530, loss: 0.4239616394042969
2023-01-22 23:40:07.393578: step: 1188/530, loss: 0.9341291785240173
2023-01-22 23:40:08.618338: step: 1192/530, loss: 0.2211524248123169
2023-01-22 23:40:09.810884: step: 1196/530, loss: 0.15282964706420898
2023-01-22 23:40:10.963019: step: 1200/530, loss: 0.44604846835136414
2023-01-22 23:40:12.149991: step: 1204/530, loss: 0.8141376376152039
2023-01-22 23:40:13.329449: step: 1208/530, loss: 0.344840407371521
2023-01-22 23:40:14.507637: step: 1212/530, loss: 0.4054010510444641
2023-01-22 23:40:15.671268: step: 1216/530, loss: 0.2823209762573242
2023-01-22 23:40:16.850589: step: 1220/530, loss: 1.0747520923614502
2023-01-22 23:40:18.012822: step: 1224/530, loss: 0.5190297961235046
2023-01-22 23:40:19.205213: step: 1228/530, loss: 0.2597466707229614
2023-01-22 23:40:20.390865: step: 1232/530, loss: 0.298832505941391
2023-01-22 23:40:21.576678: step: 1236/530, loss: 0.17823466658592224
2023-01-22 23:40:22.732914: step: 1240/530, loss: 0.20935240387916565
2023-01-22 23:40:23.921635: step: 1244/530, loss: 7.065886497497559
2023-01-22 23:40:25.123078: step: 1248/530, loss: 1.1593705415725708
2023-01-22 23:40:26.284379: step: 1252/530, loss: 0.20686674118041992
2023-01-22 23:40:27.455490: step: 1256/530, loss: 0.687012255191803
2023-01-22 23:40:28.656530: step: 1260/530, loss: 0.2044035941362381
2023-01-22 23:40:29.821839: step: 1264/530, loss: 0.5511137247085571
2023-01-22 23:40:31.016351: step: 1268/530, loss: 0.26776981353759766
2023-01-22 23:40:32.163285: step: 1272/530, loss: 0.5039999485015869
2023-01-22 23:40:33.301897: step: 1276/530, loss: 0.8315163850784302
2023-01-22 23:40:34.501756: step: 1280/530, loss: 0.16047143936157227
2023-01-22 23:40:35.689946: step: 1284/530, loss: 0.5449684858322144
2023-01-22 23:40:36.830032: step: 1288/530, loss: 1.1899182796478271
2023-01-22 23:40:38.000538: step: 1292/530, loss: 0.49589109420776367
2023-01-22 23:40:39.144133: step: 1296/530, loss: 0.12924447655677795
2023-01-22 23:40:40.297754: step: 1300/530, loss: 0.4900023937225342
2023-01-22 23:40:41.524908: step: 1304/530, loss: 1.0236679315567017
2023-01-22 23:40:42.661291: step: 1308/530, loss: 0.2753603458404541
2023-01-22 23:40:43.840225: step: 1312/530, loss: 0.7138504981994629
2023-01-22 23:40:44.992754: step: 1316/530, loss: 0.6343221664428711
2023-01-22 23:40:46.174987: step: 1320/530, loss: 0.5754326581954956
2023-01-22 23:40:47.354877: step: 1324/530, loss: 0.8345422148704529
2023-01-22 23:40:48.509831: step: 1328/530, loss: 0.973320722579956
2023-01-22 23:40:49.701346: step: 1332/530, loss: 0.2973896861076355
2023-01-22 23:40:50.883024: step: 1336/530, loss: 0.38233500719070435
2023-01-22 23:40:52.035283: step: 1340/530, loss: 0.2734871506690979
2023-01-22 23:40:53.191891: step: 1344/530, loss: 0.1499413549900055
2023-01-22 23:40:54.368027: step: 1348/530, loss: 0.377157986164093
2023-01-22 23:40:55.527076: step: 1352/530, loss: 0.280233770608902
2023-01-22 23:40:56.720660: step: 1356/530, loss: 6.821019172668457
2023-01-22 23:40:57.904063: step: 1360/530, loss: 0.6271806955337524
2023-01-22 23:40:59.113972: step: 1364/530, loss: 0.166996568441391
2023-01-22 23:41:00.280212: step: 1368/530, loss: 0.473133385181427
2023-01-22 23:41:01.425783: step: 1372/530, loss: 0.12262926995754242
2023-01-22 23:41:02.569238: step: 1376/530, loss: 0.8330333232879639
2023-01-22 23:41:03.737832: step: 1380/530, loss: 0.374843031167984
2023-01-22 23:41:04.860966: step: 1384/530, loss: 0.3352983891963959
2023-01-22 23:41:06.031233: step: 1388/530, loss: 0.2312088906764984
2023-01-22 23:41:07.195761: step: 1392/530, loss: 0.3540719151496887
2023-01-22 23:41:08.370196: step: 1396/530, loss: 0.43876639008522034
2023-01-22 23:41:09.537123: step: 1400/530, loss: 1.0939544439315796
2023-01-22 23:41:10.694885: step: 1404/530, loss: 0.12450514733791351
2023-01-22 23:41:11.873140: step: 1408/530, loss: 0.3507053256034851
2023-01-22 23:41:13.032424: step: 1412/530, loss: 0.2615653872489929
2023-01-22 23:41:14.179864: step: 1416/530, loss: 2.3222451210021973
2023-01-22 23:41:15.352542: step: 1420/530, loss: 0.18468505144119263
2023-01-22 23:41:16.590134: step: 1424/530, loss: 0.6247105598449707
2023-01-22 23:41:17.766305: step: 1428/530, loss: 0.4519351124763489
2023-01-22 23:41:18.929667: step: 1432/530, loss: 0.23634500801563263
2023-01-22 23:41:20.097158: step: 1436/530, loss: 2.7619738578796387
2023-01-22 23:41:21.254111: step: 1440/530, loss: 0.5247284173965454
2023-01-22 23:41:22.469672: step: 1444/530, loss: 0.39628496766090393
2023-01-22 23:41:23.680442: step: 1448/530, loss: 0.6105875968933105
2023-01-22 23:41:24.869583: step: 1452/530, loss: 0.9355411529541016
2023-01-22 23:41:26.089944: step: 1456/530, loss: 0.25957679748535156
2023-01-22 23:41:27.320560: step: 1460/530, loss: 0.5639216899871826
2023-01-22 23:41:28.490575: step: 1464/530, loss: 0.0953516960144043
2023-01-22 23:41:29.635294: step: 1468/530, loss: 0.2844092845916748
2023-01-22 23:41:30.777930: step: 1472/530, loss: 0.3961981236934662
2023-01-22 23:41:31.924934: step: 1476/530, loss: 0.12931624054908752
2023-01-22 23:41:33.082037: step: 1480/530, loss: 0.5368785858154297
2023-01-22 23:41:34.262531: step: 1484/530, loss: 0.8295370936393738
2023-01-22 23:41:35.479193: step: 1488/530, loss: 1.185603380203247
2023-01-22 23:41:36.599357: step: 1492/530, loss: 1.35547935962677
2023-01-22 23:41:37.776449: step: 1496/530, loss: 0.1370486319065094
2023-01-22 23:41:38.963178: step: 1500/530, loss: 0.40617600083351135
2023-01-22 23:41:40.142535: step: 1504/530, loss: 0.7772510051727295
2023-01-22 23:41:41.296256: step: 1508/530, loss: 0.3097091317176819
2023-01-22 23:41:42.453063: step: 1512/530, loss: 0.2986011803150177
2023-01-22 23:41:43.609145: step: 1516/530, loss: 0.15018320083618164
2023-01-22 23:41:44.768725: step: 1520/530, loss: 0.1444697380065918
2023-01-22 23:41:45.964916: step: 1524/530, loss: 0.41943708062171936
2023-01-22 23:41:47.138075: step: 1528/530, loss: 0.46325141191482544
2023-01-22 23:41:48.320053: step: 1532/530, loss: 0.3834190368652344
2023-01-22 23:41:49.466350: step: 1536/530, loss: 0.8704002499580383
2023-01-22 23:41:50.660842: step: 1540/530, loss: 0.9263209104537964
2023-01-22 23:41:51.797870: step: 1544/530, loss: 0.494515985250473
2023-01-22 23:41:52.973510: step: 1548/530, loss: 0.24896907806396484
2023-01-22 23:41:54.140215: step: 1552/530, loss: 0.21839872002601624
2023-01-22 23:41:55.335669: step: 1556/530, loss: 0.9395580291748047
2023-01-22 23:41:56.512934: step: 1560/530, loss: 0.40813496708869934
2023-01-22 23:41:57.666662: step: 1564/530, loss: 1.5635590553283691
2023-01-22 23:41:58.835150: step: 1568/530, loss: 0.6656662225723267
2023-01-22 23:42:00.018727: step: 1572/530, loss: 0.7001534104347229
2023-01-22 23:42:01.233569: step: 1576/530, loss: 0.21131138503551483
2023-01-22 23:42:02.407888: step: 1580/530, loss: 0.24342036247253418
2023-01-22 23:42:03.545429: step: 1584/530, loss: 0.07250013202428818
2023-01-22 23:42:04.742501: step: 1588/530, loss: 0.07300672680139542
2023-01-22 23:42:05.903590: step: 1592/530, loss: 0.26943764090538025
2023-01-22 23:42:07.114292: step: 1596/530, loss: 0.18290863931179047
2023-01-22 23:42:08.292187: step: 1600/530, loss: 1.0893621444702148
2023-01-22 23:42:09.485103: step: 1604/530, loss: 0.5250610709190369
2023-01-22 23:42:10.661243: step: 1608/530, loss: 1.76713228225708
2023-01-22 23:42:11.868331: step: 1612/530, loss: 0.7990105152130127
2023-01-22 23:42:13.055490: step: 1616/530, loss: 0.7147620916366577
2023-01-22 23:42:14.207811: step: 1620/530, loss: 2.0545449256896973
2023-01-22 23:42:15.373379: step: 1624/530, loss: 0.8507463932037354
2023-01-22 23:42:16.543198: step: 1628/530, loss: 0.5542624592781067
2023-01-22 23:42:17.685942: step: 1632/530, loss: 0.21331143379211426
2023-01-22 23:42:18.883652: step: 1636/530, loss: 0.4693852663040161
2023-01-22 23:42:20.048931: step: 1640/530, loss: 0.725791335105896
2023-01-22 23:42:21.216696: step: 1644/530, loss: 0.8215768337249756
2023-01-22 23:42:22.440823: step: 1648/530, loss: 0.1420736312866211
2023-01-22 23:42:23.595603: step: 1652/530, loss: 0.47430315613746643
2023-01-22 23:42:24.770378: step: 1656/530, loss: 1.1916295289993286
2023-01-22 23:42:25.902974: step: 1660/530, loss: 0.1517263948917389
2023-01-22 23:42:27.089705: step: 1664/530, loss: 0.3690502941608429
2023-01-22 23:42:28.257496: step: 1668/530, loss: 0.9268876314163208
2023-01-22 23:42:29.466997: step: 1672/530, loss: 0.1950494349002838
2023-01-22 23:42:30.625907: step: 1676/530, loss: 0.6339604258537292
2023-01-22 23:42:31.817143: step: 1680/530, loss: 0.17796821892261505
2023-01-22 23:42:32.977132: step: 1684/530, loss: 0.7268667221069336
2023-01-22 23:42:34.123576: step: 1688/530, loss: 0.1779256910085678
2023-01-22 23:42:35.259956: step: 1692/530, loss: 0.4604984521865845
2023-01-22 23:42:36.455903: step: 1696/530, loss: 0.1403302103281021
2023-01-22 23:42:37.647803: step: 1700/530, loss: 0.21687574684619904
2023-01-22 23:42:38.808764: step: 1704/530, loss: 0.08463907986879349
2023-01-22 23:42:39.991246: step: 1708/530, loss: 0.9153846502304077
2023-01-22 23:42:41.143076: step: 1712/530, loss: 0.20304018259048462
2023-01-22 23:42:42.341320: step: 1716/530, loss: 1.0006614923477173
2023-01-22 23:42:43.511259: step: 1720/530, loss: 0.12624338269233704
2023-01-22 23:42:44.684853: step: 1724/530, loss: 2.6002614498138428
2023-01-22 23:42:45.832421: step: 1728/530, loss: 1.468653917312622
2023-01-22 23:42:46.983169: step: 1732/530, loss: 0.3458734154701233
2023-01-22 23:42:48.189888: step: 1736/530, loss: 0.21797503530979156
2023-01-22 23:42:49.357133: step: 1740/530, loss: 0.20446515083312988
2023-01-22 23:42:50.507335: step: 1744/530, loss: 0.39187535643577576
2023-01-22 23:42:51.639690: step: 1748/530, loss: 0.17925934493541718
2023-01-22 23:42:52.876343: step: 1752/530, loss: 0.24883690476417542
2023-01-22 23:42:54.027675: step: 1756/530, loss: 0.3587840795516968
2023-01-22 23:42:55.224554: step: 1760/530, loss: 0.6691027879714966
2023-01-22 23:42:56.421687: step: 1764/530, loss: 0.15065374970436096
2023-01-22 23:42:57.585468: step: 1768/530, loss: 0.7198614478111267
2023-01-22 23:42:58.752502: step: 1772/530, loss: 0.31544363498687744
2023-01-22 23:42:59.917250: step: 1776/530, loss: 0.27717840671539307
2023-01-22 23:43:01.066691: step: 1780/530, loss: 0.8657217621803284
2023-01-22 23:43:02.241984: step: 1784/530, loss: 1.1702529191970825
2023-01-22 23:43:03.406468: step: 1788/530, loss: 0.133747860789299
2023-01-22 23:43:04.545084: step: 1792/530, loss: 0.4568883776664734
2023-01-22 23:43:05.684950: step: 1796/530, loss: 0.2110402137041092
2023-01-22 23:43:06.838102: step: 1800/530, loss: 0.7984424829483032
2023-01-22 23:43:08.022650: step: 1804/530, loss: 0.2076704055070877
2023-01-22 23:43:09.201044: step: 1808/530, loss: 0.8960598707199097
2023-01-22 23:43:10.317639: step: 1812/530, loss: 0.16908450424671173
2023-01-22 23:43:11.459777: step: 1816/530, loss: 0.049699023365974426
2023-01-22 23:43:12.663476: step: 1820/530, loss: 0.6090865135192871
2023-01-22 23:43:13.842353: step: 1824/530, loss: 0.20098371803760529
2023-01-22 23:43:14.970765: step: 1828/530, loss: 1.9670262336730957
2023-01-22 23:43:16.178876: step: 1832/530, loss: 1.6250746250152588
2023-01-22 23:43:17.342871: step: 1836/530, loss: 0.9139490127563477
2023-01-22 23:43:18.530361: step: 1840/530, loss: 1.5253500938415527
2023-01-22 23:43:19.729327: step: 1844/530, loss: 0.3234158754348755
2023-01-22 23:43:20.904086: step: 1848/530, loss: 0.13614457845687866
2023-01-22 23:43:22.094915: step: 1852/530, loss: 0.2934228777885437
2023-01-22 23:43:23.251636: step: 1856/530, loss: 0.8380802869796753
2023-01-22 23:43:24.436554: step: 1860/530, loss: 0.10628519207239151
2023-01-22 23:43:25.651399: step: 1864/530, loss: 0.2586959898471832
2023-01-22 23:43:26.822477: step: 1868/530, loss: 0.17773085832595825
2023-01-22 23:43:27.978796: step: 1872/530, loss: 0.10024365782737732
2023-01-22 23:43:29.113715: step: 1876/530, loss: 0.33093804121017456
2023-01-22 23:43:30.289218: step: 1880/530, loss: 1.1056833267211914
2023-01-22 23:43:31.467444: step: 1884/530, loss: 0.4413629472255707
2023-01-22 23:43:32.679719: step: 1888/530, loss: 0.525170624256134
2023-01-22 23:43:33.863949: step: 1892/530, loss: 2.2015750408172607
2023-01-22 23:43:35.054708: step: 1896/530, loss: 2.576280117034912
2023-01-22 23:43:36.210643: step: 1900/530, loss: 0.25769686698913574
2023-01-22 23:43:37.389666: step: 1904/530, loss: 0.20434212684631348
2023-01-22 23:43:38.545850: step: 1908/530, loss: 0.5773991942405701
2023-01-22 23:43:39.730639: step: 1912/530, loss: 0.2698260545730591
2023-01-22 23:43:40.880497: step: 1916/530, loss: 0.5288078188896179
2023-01-22 23:43:42.071058: step: 1920/530, loss: 1.4844985008239746
2023-01-22 23:43:43.267878: step: 1924/530, loss: 0.38161301612854004
2023-01-22 23:43:44.457280: step: 1928/530, loss: 0.10798406600952148
2023-01-22 23:43:45.654729: step: 1932/530, loss: 0.17363953590393066
2023-01-22 23:43:46.827799: step: 1936/530, loss: 0.371072381734848
2023-01-22 23:43:48.010590: step: 1940/530, loss: 0.15702897310256958
2023-01-22 23:43:49.165894: step: 1944/530, loss: 0.9871727228164673
2023-01-22 23:43:50.333759: step: 1948/530, loss: 2.017547845840454
2023-01-22 23:43:51.529974: step: 1952/530, loss: 0.6324816346168518
2023-01-22 23:43:52.719428: step: 1956/530, loss: 0.07774534821510315
2023-01-22 23:43:53.857635: step: 1960/530, loss: 0.11034531891345978
2023-01-22 23:43:55.028858: step: 1964/530, loss: 0.30748987197875977
2023-01-22 23:43:56.206375: step: 1968/530, loss: 0.07756614685058594
2023-01-22 23:43:57.384500: step: 1972/530, loss: 0.4122345447540283
2023-01-22 23:43:58.538932: step: 1976/530, loss: 0.1715168058872223
2023-01-22 23:43:59.687035: step: 1980/530, loss: 0.24310904741287231
2023-01-22 23:44:00.827478: step: 1984/530, loss: 0.45279818773269653
2023-01-22 23:44:02.046021: step: 1988/530, loss: 0.1560359001159668
2023-01-22 23:44:03.327500: step: 1992/530, loss: 0.11951227486133575
2023-01-22 23:44:04.484386: step: 1996/530, loss: 0.4826560914516449
2023-01-22 23:44:05.675214: step: 2000/530, loss: 0.265766441822052
2023-01-22 23:44:06.845088: step: 2004/530, loss: 0.7708759307861328
2023-01-22 23:44:08.018211: step: 2008/530, loss: 1.269675850868225
2023-01-22 23:44:09.169178: step: 2012/530, loss: 0.14589612185955048
2023-01-22 23:44:10.329709: step: 2016/530, loss: 0.6239898800849915
2023-01-22 23:44:11.509519: step: 2020/530, loss: 1.1293630599975586
2023-01-22 23:44:12.710851: step: 2024/530, loss: 2.510375738143921
2023-01-22 23:44:13.879906: step: 2028/530, loss: 0.4940025210380554
2023-01-22 23:44:15.064751: step: 2032/530, loss: 0.14799128472805023
2023-01-22 23:44:16.242048: step: 2036/530, loss: 0.11787634342908859
2023-01-22 23:44:17.381206: step: 2040/530, loss: 0.06837411224842072
2023-01-22 23:44:18.571512: step: 2044/530, loss: 6.53923225402832
2023-01-22 23:44:19.766597: step: 2048/530, loss: 1.3320908546447754
2023-01-22 23:44:20.949596: step: 2052/530, loss: 0.6101067662239075
2023-01-22 23:44:22.161520: step: 2056/530, loss: 0.5345121622085571
2023-01-22 23:44:23.336298: step: 2060/530, loss: 0.4946252703666687
2023-01-22 23:44:24.538043: step: 2064/530, loss: 1.1673516035079956
2023-01-22 23:44:25.687148: step: 2068/530, loss: 0.061652086675167084
2023-01-22 23:44:26.841916: step: 2072/530, loss: 0.2297719419002533
2023-01-22 23:44:28.038335: step: 2076/530, loss: 0.3679349422454834
2023-01-22 23:44:29.189118: step: 2080/530, loss: 0.08142280578613281
2023-01-22 23:44:30.366040: step: 2084/530, loss: 0.3446428179740906
2023-01-22 23:44:31.583964: step: 2088/530, loss: 0.05562758818268776
2023-01-22 23:44:32.784471: step: 2092/530, loss: 0.5826784372329712
2023-01-22 23:44:33.990906: step: 2096/530, loss: 0.14145630598068237
2023-01-22 23:44:35.208202: step: 2100/530, loss: 0.12854719161987305
2023-01-22 23:44:36.434487: step: 2104/530, loss: 1.0348286628723145
2023-01-22 23:44:37.623619: step: 2108/530, loss: 0.41253501176834106
2023-01-22 23:44:38.811986: step: 2112/530, loss: 0.3843706250190735
2023-01-22 23:44:39.979210: step: 2116/530, loss: 6.564247131347656
2023-01-22 23:44:41.167045: step: 2120/530, loss: 0.13367091119289398
==================================================
Loss: 0.796
--------------------
Dev: {'event': {'p': 0.5782463928967814, 'r': 0.6937416777629827, 'f1': 0.6307506053268765}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Test: {'event': {'p': 0.5849148418491484, 'r': 0.6912018401380103, 'f1': 0.6336320506062204}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Chinese: {'event': {'p': 0.5263157894736842, 'r': 0.7407407407407407, 'f1': 0.6153846153846153}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Korean: {'event': {'p': 0.5555555555555556, 'r': 0.3968253968253968, 'f1': 0.46296296296296297}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Russian: {'event': {'p': 0.6538461538461539, 'r': 0.4722222222222222, 'f1': 0.5483870967741936}, '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': 0.5782463928967814, 'r': 0.6937416777629827, 'f1': 0.6307506053268765}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Eng Test for Chinese: {'event': {'p': 0.5849148418491484, 'r': 0.6912018401380103, 'f1': 0.6336320506062204}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Sample Chinese: {'event': {'p': 0.5263157894736842, 'r': 0.7407407407407407, 'f1': 0.6153846153846153}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5782463928967814, 'r': 0.6937416777629827, 'f1': 0.6307506053268765}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Eng Test for Korean: {'event': {'p': 0.5849148418491484, 'r': 0.6912018401380103, 'f1': 0.6336320506062204}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Sample Korean: {'event': {'p': 0.5555555555555556, 'r': 0.3968253968253968, 'f1': 0.46296296296296297}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5782463928967814, 'r': 0.6937416777629827, 'f1': 0.6307506053268765}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Eng Test for Russian: {'event': {'p': 0.5849148418491484, 'r': 0.6912018401380103, 'f1': 0.6336320506062204}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Sample Russian: {'event': {'p': 0.6538461538461539, 'r': 0.4722222222222222, 'f1': 0.5483870967741936}, '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 23:45:51.195168: step: 4/530, loss: 0.8131009936332703
2023-01-22 23:45:52.344650: step: 8/530, loss: 0.2753911018371582
2023-01-22 23:45:53.534084: step: 12/530, loss: 0.1350574493408203
2023-01-22 23:45:54.731928: step: 16/530, loss: 0.7728590965270996
2023-01-22 23:45:55.905092: step: 20/530, loss: 0.14564308524131775
2023-01-22 23:45:57.051904: step: 24/530, loss: 0.5636929273605347
2023-01-22 23:45:58.223357: step: 28/530, loss: 0.7194770574569702
2023-01-22 23:45:59.377314: step: 32/530, loss: 0.6098282337188721
2023-01-22 23:46:00.554311: step: 36/530, loss: 0.5917724967002869
2023-01-22 23:46:01.748123: step: 40/530, loss: 0.18003712594509125
2023-01-22 23:46:02.938766: step: 44/530, loss: 1.6628830432891846
2023-01-22 23:46:04.103098: step: 48/530, loss: 0.17299708724021912
2023-01-22 23:46:05.237791: step: 52/530, loss: 0.06985471397638321
2023-01-22 23:46:06.379651: step: 56/530, loss: 0.5200003385543823
2023-01-22 23:46:07.544263: step: 60/530, loss: 0.2953694760799408
2023-01-22 23:46:08.809404: step: 64/530, loss: 1.024534821510315
2023-01-22 23:46:09.966666: step: 68/530, loss: 0.17959380149841309
2023-01-22 23:46:11.160150: step: 72/530, loss: 0.27204903960227966
2023-01-22 23:46:12.347226: step: 76/530, loss: 0.5689713954925537
2023-01-22 23:46:13.509004: step: 80/530, loss: 0.2503332197666168
2023-01-22 23:46:14.684842: step: 84/530, loss: 1.1759052276611328
2023-01-22 23:46:15.830820: step: 88/530, loss: 0.2369137704372406
2023-01-22 23:46:17.014065: step: 92/530, loss: 0.20265722274780273
2023-01-22 23:46:18.186318: step: 96/530, loss: 1.1507142782211304
2023-01-22 23:46:19.341528: step: 100/530, loss: 0.5338325500488281
2023-01-22 23:46:20.539573: step: 104/530, loss: 0.41796875
2023-01-22 23:46:21.767334: step: 108/530, loss: 0.2484571635723114
2023-01-22 23:46:22.961450: step: 112/530, loss: 6.588026523590088
2023-01-22 23:46:24.104834: step: 116/530, loss: 0.3105196952819824
2023-01-22 23:46:25.278394: step: 120/530, loss: 1.5536683797836304
2023-01-22 23:46:26.455423: step: 124/530, loss: 0.7035400867462158
2023-01-22 23:46:27.632580: step: 128/530, loss: 0.8814365267753601
2023-01-22 23:46:28.810547: step: 132/530, loss: 0.01931467093527317
2023-01-22 23:46:29.978943: step: 136/530, loss: 0.1277008056640625
2023-01-22 23:46:31.151350: step: 140/530, loss: 0.9832637310028076
2023-01-22 23:46:32.349643: step: 144/530, loss: 0.1299816220998764
2023-01-22 23:46:33.509145: step: 148/530, loss: 0.4132902920246124
2023-01-22 23:46:34.683310: step: 152/530, loss: 0.916653037071228
2023-01-22 23:46:35.838767: step: 156/530, loss: 0.1310131996870041
2023-01-22 23:46:37.006372: step: 160/530, loss: 0.29777127504348755
2023-01-22 23:46:38.256151: step: 164/530, loss: 1.2421156167984009
2023-01-22 23:46:39.401105: step: 168/530, loss: 0.7385039329528809
2023-01-22 23:46:40.566941: step: 172/530, loss: 0.22313295304775238
2023-01-22 23:46:41.753674: step: 176/530, loss: 0.9820431470870972
2023-01-22 23:46:42.955381: step: 180/530, loss: 1.0439101457595825
2023-01-22 23:46:44.114903: step: 184/530, loss: 0.21177302300930023
2023-01-22 23:46:45.272641: step: 188/530, loss: 0.3938840627670288
2023-01-22 23:46:46.468734: step: 192/530, loss: 0.3223575949668884
2023-01-22 23:46:47.633157: step: 196/530, loss: 0.2527282238006592
2023-01-22 23:46:48.783126: step: 200/530, loss: 2.1202712059020996
2023-01-22 23:46:49.952271: step: 204/530, loss: 0.23718786239624023
2023-01-22 23:46:51.113011: step: 208/530, loss: 0.32902735471725464
2023-01-22 23:46:52.282685: step: 212/530, loss: 0.2543381452560425
2023-01-22 23:46:53.426517: step: 216/530, loss: 0.8075509667396545
2023-01-22 23:46:54.608420: step: 220/530, loss: 0.32854345440864563
2023-01-22 23:46:55.793520: step: 224/530, loss: 0.0640825554728508
2023-01-22 23:46:56.941282: step: 228/530, loss: 0.16528578102588654
2023-01-22 23:46:58.080756: step: 232/530, loss: 0.12071094661951065
2023-01-22 23:46:59.273495: step: 236/530, loss: 0.7248602509498596
2023-01-22 23:47:00.497418: step: 240/530, loss: 0.3958938717842102
2023-01-22 23:47:01.666549: step: 244/530, loss: 0.2956007122993469
2023-01-22 23:47:02.810474: step: 248/530, loss: 0.0948890745639801
2023-01-22 23:47:03.947141: step: 252/530, loss: 0.30303990840911865
2023-01-22 23:47:05.153536: step: 256/530, loss: 0.276243656873703
2023-01-22 23:47:06.321906: step: 260/530, loss: 0.2590638995170593
2023-01-22 23:47:07.505708: step: 264/530, loss: 0.2553989291191101
2023-01-22 23:47:08.707807: step: 268/530, loss: 0.5618802905082703
2023-01-22 23:47:09.877850: step: 272/530, loss: 0.11624794453382492
2023-01-22 23:47:11.056584: step: 276/530, loss: 0.7249786853790283
2023-01-22 23:47:12.252038: step: 280/530, loss: 0.8657317161560059
2023-01-22 23:47:13.400111: step: 284/530, loss: 0.1536935418844223
2023-01-22 23:47:14.554543: step: 288/530, loss: 0.1114933043718338
2023-01-22 23:47:15.764394: step: 292/530, loss: 0.5105417966842651
2023-01-22 23:47:16.965616: step: 296/530, loss: 0.8160227537155151
2023-01-22 23:47:18.115776: step: 300/530, loss: 0.1807362139225006
2023-01-22 23:47:19.296263: step: 304/530, loss: 0.120049387216568
2023-01-22 23:47:20.501363: step: 308/530, loss: 0.4047604501247406
2023-01-22 23:47:21.657455: step: 312/530, loss: 0.3224331736564636
2023-01-22 23:47:22.804667: step: 316/530, loss: 0.16246314346790314
2023-01-22 23:47:23.953272: step: 320/530, loss: 0.3033720850944519
2023-01-22 23:47:25.109771: step: 324/530, loss: 0.3792285919189453
2023-01-22 23:47:26.310038: step: 328/530, loss: 0.15760020911693573
2023-01-22 23:47:27.477620: step: 332/530, loss: 0.2603931427001953
2023-01-22 23:47:28.649145: step: 336/530, loss: 0.7599878907203674
2023-01-22 23:47:29.811397: step: 340/530, loss: 0.07117342948913574
2023-01-22 23:47:30.966711: step: 344/530, loss: 0.13313297927379608
2023-01-22 23:47:32.185307: step: 348/530, loss: 0.7614139914512634
2023-01-22 23:47:33.370381: step: 352/530, loss: 0.4813288748264313
2023-01-22 23:47:34.539224: step: 356/530, loss: 0.07317791134119034
2023-01-22 23:47:35.677708: step: 360/530, loss: 0.8157491087913513
2023-01-22 23:47:36.896121: step: 364/530, loss: 0.14983519911766052
2023-01-22 23:47:38.048662: step: 368/530, loss: 0.12586575746536255
2023-01-22 23:47:39.212789: step: 372/530, loss: 0.3335806727409363
2023-01-22 23:47:40.357872: step: 376/530, loss: 0.1913493275642395
2023-01-22 23:47:41.539213: step: 380/530, loss: 1.2610762119293213
2023-01-22 23:47:42.709782: step: 384/530, loss: 0.23879270255565643
2023-01-22 23:47:43.892138: step: 388/530, loss: 0.32907745242118835
2023-01-22 23:47:45.117334: step: 392/530, loss: 0.4629434645175934
2023-01-22 23:47:46.277936: step: 396/530, loss: 0.11997786164283752
2023-01-22 23:47:47.456708: step: 400/530, loss: 6.266993522644043
2023-01-22 23:47:48.610471: step: 404/530, loss: 0.9506653547286987
2023-01-22 23:47:49.802457: step: 408/530, loss: 0.45406827330589294
2023-01-22 23:47:51.000113: step: 412/530, loss: 0.3469398021697998
2023-01-22 23:47:52.168816: step: 416/530, loss: 0.6269220113754272
2023-01-22 23:47:53.367929: step: 420/530, loss: 0.6761634945869446
2023-01-22 23:47:54.523576: step: 424/530, loss: 0.4549899101257324
2023-01-22 23:47:55.715915: step: 428/530, loss: 0.2658103108406067
2023-01-22 23:47:56.891766: step: 432/530, loss: 0.1528553068637848
2023-01-22 23:47:58.069834: step: 436/530, loss: 0.539262592792511
2023-01-22 23:47:59.258496: step: 440/530, loss: 0.31333863735198975
2023-01-22 23:48:00.442583: step: 444/530, loss: 0.11689119040966034
2023-01-22 23:48:01.648825: step: 448/530, loss: 1.137494683265686
2023-01-22 23:48:02.850493: step: 452/530, loss: 0.1895713359117508
2023-01-22 23:48:03.996117: step: 456/530, loss: 0.14369288086891174
2023-01-22 23:48:05.124772: step: 460/530, loss: 0.8174580931663513
2023-01-22 23:48:06.314119: step: 464/530, loss: 0.12201175838708878
2023-01-22 23:48:07.492037: step: 468/530, loss: 0.6958547830581665
2023-01-22 23:48:08.623790: step: 472/530, loss: 1.3475228548049927
2023-01-22 23:48:09.791194: step: 476/530, loss: 0.2060166746377945
2023-01-22 23:48:10.946335: step: 480/530, loss: 1.407651424407959
2023-01-22 23:48:12.156860: step: 484/530, loss: 0.27689677476882935
2023-01-22 23:48:13.311984: step: 488/530, loss: 0.18881730735301971
2023-01-22 23:48:14.447301: step: 492/530, loss: 0.1488383263349533
2023-01-22 23:48:15.686694: step: 496/530, loss: 0.21495437622070312
2023-01-22 23:48:16.842038: step: 500/530, loss: 0.30411404371261597
2023-01-22 23:48:18.005630: step: 504/530, loss: 0.7492003440856934
2023-01-22 23:48:19.190624: step: 508/530, loss: 0.35484811663627625
2023-01-22 23:48:20.409272: step: 512/530, loss: 0.20064754784107208
2023-01-22 23:48:21.584900: step: 516/530, loss: 0.2230207920074463
2023-01-22 23:48:22.753868: step: 520/530, loss: 0.6519554257392883
2023-01-22 23:48:23.915309: step: 524/530, loss: 0.28657275438308716
2023-01-22 23:48:25.122154: step: 528/530, loss: 0.06410565972328186
2023-01-22 23:48:26.300710: step: 532/530, loss: 0.6508861780166626
2023-01-22 23:48:27.480231: step: 536/530, loss: 0.1381603181362152
2023-01-22 23:48:28.659399: step: 540/530, loss: 0.6873812079429626
2023-01-22 23:48:29.800602: step: 544/530, loss: 0.06801362335681915
2023-01-22 23:48:30.951579: step: 548/530, loss: 0.1821175217628479
2023-01-22 23:48:32.145544: step: 552/530, loss: 0.04282717779278755
2023-01-22 23:48:33.279348: step: 556/530, loss: 0.31935185194015503
2023-01-22 23:48:34.433233: step: 560/530, loss: 0.043768785893917084
2023-01-22 23:48:35.590795: step: 564/530, loss: 0.2452186644077301
2023-01-22 23:48:36.804128: step: 568/530, loss: 0.8599094152450562
2023-01-22 23:48:37.962021: step: 572/530, loss: 1.3989853858947754
2023-01-22 23:48:39.152368: step: 576/530, loss: 0.05030636861920357
2023-01-22 23:48:40.321329: step: 580/530, loss: 0.09564314037561417
2023-01-22 23:48:41.499563: step: 584/530, loss: 0.8789792060852051
2023-01-22 23:48:42.677437: step: 588/530, loss: 0.07741013169288635
2023-01-22 23:48:43.821986: step: 592/530, loss: 0.14804983139038086
2023-01-22 23:48:44.996114: step: 596/530, loss: 0.33742353320121765
2023-01-22 23:48:46.178901: step: 600/530, loss: 0.5756341218948364
2023-01-22 23:48:47.294341: step: 604/530, loss: 0.614681601524353
2023-01-22 23:48:48.478243: step: 608/530, loss: 0.40944191813468933
2023-01-22 23:48:49.644739: step: 612/530, loss: 1.3625683784484863
2023-01-22 23:48:50.841483: step: 616/530, loss: 0.9454197883605957
2023-01-22 23:48:51.985439: step: 620/530, loss: 0.2700842022895813
2023-01-22 23:48:53.172778: step: 624/530, loss: 0.23967324197292328
2023-01-22 23:48:54.346011: step: 628/530, loss: 0.8394330143928528
2023-01-22 23:48:55.506315: step: 632/530, loss: 0.043608665466308594
2023-01-22 23:48:56.659748: step: 636/530, loss: 0.5413864850997925
2023-01-22 23:48:57.812048: step: 640/530, loss: 0.48300600051879883
2023-01-22 23:48:58.967404: step: 644/530, loss: 0.3193744719028473
2023-01-22 23:49:00.099279: step: 648/530, loss: 0.25874224305152893
2023-01-22 23:49:01.250952: step: 652/530, loss: 0.13567595183849335
2023-01-22 23:49:02.419979: step: 656/530, loss: 0.05915489047765732
2023-01-22 23:49:03.533810: step: 660/530, loss: 0.04206056520342827
2023-01-22 23:49:04.725587: step: 664/530, loss: 2.687025308609009
2023-01-22 23:49:05.907814: step: 668/530, loss: 0.09054012596607208
2023-01-22 23:49:07.090226: step: 672/530, loss: 0.14900818467140198
2023-01-22 23:49:08.283556: step: 676/530, loss: 1.380944013595581
2023-01-22 23:49:09.450651: step: 680/530, loss: 1.0504292249679565
2023-01-22 23:49:10.667008: step: 684/530, loss: 0.3370684087276459
2023-01-22 23:49:11.884210: step: 688/530, loss: 0.7799224853515625
2023-01-22 23:49:13.032102: step: 692/530, loss: 1.2012555599212646
2023-01-22 23:49:14.224233: step: 696/530, loss: 0.28496646881103516
2023-01-22 23:49:15.420519: step: 700/530, loss: 0.07615514099597931
2023-01-22 23:49:16.582905: step: 704/530, loss: 0.23797884583473206
2023-01-22 23:49:17.746662: step: 708/530, loss: 0.2721117436885834
2023-01-22 23:49:18.937316: step: 712/530, loss: 0.8619662523269653
2023-01-22 23:49:20.102746: step: 716/530, loss: 0.7956581115722656
2023-01-22 23:49:21.265020: step: 720/530, loss: 2.710904598236084
2023-01-22 23:49:22.433206: step: 724/530, loss: 0.1275218427181244
2023-01-22 23:49:23.607251: step: 728/530, loss: 0.7589025497436523
2023-01-22 23:49:24.783204: step: 732/530, loss: 0.15051718056201935
2023-01-22 23:49:25.930021: step: 736/530, loss: 0.2746492922306061
2023-01-22 23:49:27.130020: step: 740/530, loss: 0.7011812925338745
2023-01-22 23:49:28.323475: step: 744/530, loss: 0.6710712313652039
2023-01-22 23:49:29.453248: step: 748/530, loss: 0.06359276920557022
2023-01-22 23:49:30.621175: step: 752/530, loss: 0.3000645041465759
2023-01-22 23:49:31.793164: step: 756/530, loss: 0.37415334582328796
2023-01-22 23:49:32.988613: step: 760/530, loss: 0.17929087579250336
2023-01-22 23:49:34.174095: step: 764/530, loss: 0.8596959710121155
2023-01-22 23:49:35.323858: step: 768/530, loss: 0.37162408232688904
2023-01-22 23:49:36.477351: step: 772/530, loss: 0.1953103095293045
2023-01-22 23:49:37.670790: step: 776/530, loss: 0.2356177419424057
2023-01-22 23:49:38.841391: step: 780/530, loss: 0.08539637923240662
2023-01-22 23:49:40.078859: step: 784/530, loss: 0.5177396535873413
2023-01-22 23:49:41.244403: step: 788/530, loss: 0.21384677290916443
2023-01-22 23:49:42.418859: step: 792/530, loss: 0.5052059888839722
2023-01-22 23:49:43.555787: step: 796/530, loss: 0.28495168685913086
2023-01-22 23:49:44.681399: step: 800/530, loss: 1.3187782764434814
2023-01-22 23:49:45.816486: step: 804/530, loss: 0.14456062018871307
2023-01-22 23:49:46.972253: step: 808/530, loss: 0.8939498662948608
2023-01-22 23:49:48.125177: step: 812/530, loss: 0.5543131828308105
2023-01-22 23:49:49.321051: step: 816/530, loss: 0.45672476291656494
2023-01-22 23:49:50.505358: step: 820/530, loss: 0.17112235724925995
2023-01-22 23:49:51.767366: step: 824/530, loss: 0.13266411423683167
2023-01-22 23:49:52.904650: step: 828/530, loss: 0.058018967509269714
2023-01-22 23:49:54.098700: step: 832/530, loss: 7.35406494140625
2023-01-22 23:49:55.299800: step: 836/530, loss: 1.0081827640533447
2023-01-22 23:49:56.464371: step: 840/530, loss: 1.3607404232025146
2023-01-22 23:49:57.680217: step: 844/530, loss: 2.0624141693115234
2023-01-22 23:49:58.859527: step: 848/530, loss: 0.40151041746139526
2023-01-22 23:50:00.033267: step: 852/530, loss: 0.14539632201194763
2023-01-22 23:50:01.154518: step: 856/530, loss: 0.12623482942581177
2023-01-22 23:50:02.356786: step: 860/530, loss: 0.37502819299697876
2023-01-22 23:50:03.552245: step: 864/530, loss: 0.3493295907974243
2023-01-22 23:50:04.719299: step: 868/530, loss: 0.17808513343334198
2023-01-22 23:50:05.895467: step: 872/530, loss: 1.501434564590454
2023-01-22 23:50:07.099839: step: 876/530, loss: 0.7126620411872864
2023-01-22 23:50:08.297745: step: 880/530, loss: 0.9364823698997498
2023-01-22 23:50:09.498852: step: 884/530, loss: 0.26331090927124023
2023-01-22 23:50:10.664126: step: 888/530, loss: 0.671194851398468
2023-01-22 23:50:11.875893: step: 892/530, loss: 0.6448396444320679
2023-01-22 23:50:13.090427: step: 896/530, loss: 0.09248952567577362
2023-01-22 23:50:14.238290: step: 900/530, loss: 0.27679795026779175
2023-01-22 23:50:15.410592: step: 904/530, loss: 0.14033597707748413
2023-01-22 23:50:16.569263: step: 908/530, loss: 0.11329788714647293
2023-01-22 23:50:17.749120: step: 912/530, loss: 0.25210103392601013
2023-01-22 23:50:18.919359: step: 916/530, loss: 0.20909824967384338
2023-01-22 23:50:20.057265: step: 920/530, loss: 0.5642339587211609
2023-01-22 23:50:21.219553: step: 924/530, loss: 0.11197614669799805
2023-01-22 23:50:22.384920: step: 928/530, loss: 0.08525638282299042
2023-01-22 23:50:23.517389: step: 932/530, loss: 0.2746533453464508
2023-01-22 23:50:24.640377: step: 936/530, loss: 0.19244170188903809
2023-01-22 23:50:25.820137: step: 940/530, loss: 0.6105697751045227
2023-01-22 23:50:26.984930: step: 944/530, loss: 0.93476802110672
2023-01-22 23:50:28.168771: step: 948/530, loss: 0.1826503872871399
2023-01-22 23:50:29.321545: step: 952/530, loss: 0.29204684495925903
2023-01-22 23:50:30.478780: step: 956/530, loss: 0.4442242681980133
2023-01-22 23:50:31.668582: step: 960/530, loss: 6.2586493492126465
2023-01-22 23:50:32.857360: step: 964/530, loss: 0.9305421113967896
2023-01-22 23:50:34.017580: step: 968/530, loss: 0.5687618255615234
2023-01-22 23:50:35.279657: step: 972/530, loss: 7.020023345947266
2023-01-22 23:50:36.479448: step: 976/530, loss: 0.19057334959506989
2023-01-22 23:50:37.676725: step: 980/530, loss: 0.19445228576660156
2023-01-22 23:50:38.842190: step: 984/530, loss: 0.13064676523208618
2023-01-22 23:50:40.040665: step: 988/530, loss: 0.14483466744422913
2023-01-22 23:50:41.203160: step: 992/530, loss: 0.9262669086456299
2023-01-22 23:50:42.384273: step: 996/530, loss: 1.4446378946304321
2023-01-22 23:50:43.567210: step: 1000/530, loss: 0.43529972434043884
2023-01-22 23:50:44.719841: step: 1004/530, loss: 0.33877742290496826
2023-01-22 23:50:45.909736: step: 1008/530, loss: 0.243761345744133
2023-01-22 23:50:47.106888: step: 1012/530, loss: 1.2754149436950684
2023-01-22 23:50:48.278340: step: 1016/530, loss: 0.37762346863746643
2023-01-22 23:50:49.457426: step: 1020/530, loss: 0.12277646362781525
2023-01-22 23:50:50.688710: step: 1024/530, loss: 1.063736081123352
2023-01-22 23:50:51.859084: step: 1028/530, loss: 0.1324271708726883
2023-01-22 23:50:53.001300: step: 1032/530, loss: 6.387197494506836
2023-01-22 23:50:54.155937: step: 1036/530, loss: 0.06472501903772354
2023-01-22 23:50:55.293629: step: 1040/530, loss: 0.49678337574005127
2023-01-22 23:50:56.495056: step: 1044/530, loss: 0.2159431427717209
2023-01-22 23:50:57.677191: step: 1048/530, loss: 0.16186627745628357
2023-01-22 23:50:58.884358: step: 1052/530, loss: 0.07779045403003693
2023-01-22 23:51:00.036021: step: 1056/530, loss: 0.19702863693237305
2023-01-22 23:51:01.230999: step: 1060/530, loss: 0.9591590166091919
2023-01-22 23:51:02.357329: step: 1064/530, loss: 1.2540150880813599
2023-01-22 23:51:03.545721: step: 1068/530, loss: 0.14994199573993683
2023-01-22 23:51:04.738779: step: 1072/530, loss: 1.0914855003356934
2023-01-22 23:51:05.936951: step: 1076/530, loss: 0.6991499066352844
2023-01-22 23:51:07.129198: step: 1080/530, loss: 0.2397291362285614
2023-01-22 23:51:08.304905: step: 1084/530, loss: 0.09866509586572647
2023-01-22 23:51:09.449036: step: 1088/530, loss: 0.16415591537952423
2023-01-22 23:51:10.708533: step: 1092/530, loss: 0.44816991686820984
2023-01-22 23:51:11.894140: step: 1096/530, loss: 0.10744304955005646
2023-01-22 23:51:13.068551: step: 1100/530, loss: 0.33452340960502625
2023-01-22 23:51:14.232791: step: 1104/530, loss: 0.11847123503684998
2023-01-22 23:51:15.389025: step: 1108/530, loss: 0.5884709358215332
2023-01-22 23:51:16.554196: step: 1112/530, loss: 0.0523066520690918
2023-01-22 23:51:17.707066: step: 1116/530, loss: 0.10171909630298615
2023-01-22 23:51:18.908321: step: 1120/530, loss: 0.32674846053123474
2023-01-22 23:51:20.058370: step: 1124/530, loss: 0.2390117198228836
2023-01-22 23:51:21.253962: step: 1128/530, loss: 0.15587815642356873
2023-01-22 23:51:22.441518: step: 1132/530, loss: 1.5504474639892578
2023-01-22 23:51:23.619770: step: 1136/530, loss: 0.37956732511520386
2023-01-22 23:51:24.798075: step: 1140/530, loss: 0.34873953461647034
2023-01-22 23:51:25.983809: step: 1144/530, loss: 1.1070220470428467
2023-01-22 23:51:27.151014: step: 1148/530, loss: 1.104679822921753
2023-01-22 23:51:28.310902: step: 1152/530, loss: 0.29709187150001526
2023-01-22 23:51:29.513711: step: 1156/530, loss: 0.2701776623725891
2023-01-22 23:51:30.659054: step: 1160/530, loss: 0.10834258049726486
2023-01-22 23:51:31.802904: step: 1164/530, loss: 0.6779764294624329
2023-01-22 23:51:32.975075: step: 1168/530, loss: 0.9808801412582397
2023-01-22 23:51:34.158471: step: 1172/530, loss: 0.8983593583106995
2023-01-22 23:51:35.304266: step: 1176/530, loss: 0.3313419222831726
2023-01-22 23:51:36.490615: step: 1180/530, loss: 0.04407496377825737
2023-01-22 23:51:37.698452: step: 1184/530, loss: 0.14605122804641724
2023-01-22 23:51:38.857882: step: 1188/530, loss: 0.4207576513290405
2023-01-22 23:51:40.076355: step: 1192/530, loss: 0.20644119381904602
2023-01-22 23:51:41.254249: step: 1196/530, loss: 0.2758932113647461
2023-01-22 23:51:42.434778: step: 1200/530, loss: 0.1772373616695404
2023-01-22 23:51:43.565845: step: 1204/530, loss: 0.7057322859764099
2023-01-22 23:51:44.709539: step: 1208/530, loss: 0.07535575330257416
2023-01-22 23:51:45.885643: step: 1212/530, loss: 1.1347315311431885
2023-01-22 23:51:47.021528: step: 1216/530, loss: 1.030280590057373
2023-01-22 23:51:48.171217: step: 1220/530, loss: 0.2256973385810852
2023-01-22 23:51:49.345902: step: 1224/530, loss: 0.06349001079797745
2023-01-22 23:51:50.541653: step: 1228/530, loss: 0.3368093967437744
2023-01-22 23:51:51.697313: step: 1232/530, loss: 0.18343791365623474
2023-01-22 23:51:52.880827: step: 1236/530, loss: 0.7997405529022217
2023-01-22 23:51:54.041262: step: 1240/530, loss: 0.3172716200351715
2023-01-22 23:51:55.249989: step: 1244/530, loss: 0.1435273289680481
2023-01-22 23:51:56.456250: step: 1248/530, loss: 0.11778044700622559
2023-01-22 23:51:57.606116: step: 1252/530, loss: 0.23651990294456482
2023-01-22 23:51:58.776630: step: 1256/530, loss: 0.3496863543987274
2023-01-22 23:51:59.980927: step: 1260/530, loss: 0.06034908443689346
2023-01-22 23:52:01.173196: step: 1264/530, loss: 0.16582655906677246
2023-01-22 23:52:02.333349: step: 1268/530, loss: 0.051279641687870026
2023-01-22 23:52:03.517559: step: 1272/530, loss: 0.2128925919532776
2023-01-22 23:52:04.689854: step: 1276/530, loss: 0.1337498128414154
2023-01-22 23:52:05.872368: step: 1280/530, loss: 1.309667706489563
2023-01-22 23:52:07.029217: step: 1284/530, loss: 0.18239250779151917
2023-01-22 23:52:08.196144: step: 1288/530, loss: 0.9458780884742737
2023-01-22 23:52:09.377095: step: 1292/530, loss: 0.8033409714698792
2023-01-22 23:52:10.544054: step: 1296/530, loss: 1.0918159484863281
2023-01-22 23:52:11.737796: step: 1300/530, loss: 0.0733439028263092
2023-01-22 23:52:12.930301: step: 1304/530, loss: 0.48767149448394775
2023-01-22 23:52:14.114649: step: 1308/530, loss: 1.304060697555542
2023-01-22 23:52:15.286102: step: 1312/530, loss: 0.10146933048963547
2023-01-22 23:52:16.472378: step: 1316/530, loss: 0.07565192878246307
2023-01-22 23:52:17.603067: step: 1320/530, loss: 0.0383114367723465
2023-01-22 23:52:18.801518: step: 1324/530, loss: 0.8748599290847778
2023-01-22 23:52:19.983492: step: 1328/530, loss: 0.04026372358202934
2023-01-22 23:52:21.147125: step: 1332/530, loss: 0.3682217597961426
2023-01-22 23:52:22.303752: step: 1336/530, loss: 0.7549734711647034
2023-01-22 23:52:23.477884: step: 1340/530, loss: 0.7470425963401794
2023-01-22 23:52:24.629394: step: 1344/530, loss: 0.10938072949647903
2023-01-22 23:52:25.760697: step: 1348/530, loss: 0.22176331281661987
2023-01-22 23:52:26.906975: step: 1352/530, loss: 0.4832870364189148
2023-01-22 23:52:28.073512: step: 1356/530, loss: 0.09096997231245041
2023-01-22 23:52:29.249424: step: 1360/530, loss: 0.9750538468360901
2023-01-22 23:52:30.460183: step: 1364/530, loss: 0.21050973236560822
2023-01-22 23:52:31.628734: step: 1368/530, loss: 0.47874486446380615
2023-01-22 23:52:32.744227: step: 1372/530, loss: 0.11202053725719452
2023-01-22 23:52:33.917974: step: 1376/530, loss: 0.22147612273693085
2023-01-22 23:52:35.080776: step: 1380/530, loss: 0.32758206129074097
2023-01-22 23:52:36.257294: step: 1384/530, loss: 0.2593611776828766
2023-01-22 23:52:37.429651: step: 1388/530, loss: 0.499620646238327
2023-01-22 23:52:38.596246: step: 1392/530, loss: 0.41625577211380005
2023-01-22 23:52:39.781031: step: 1396/530, loss: 0.515575647354126
2023-01-22 23:52:40.934622: step: 1400/530, loss: 0.22347040474414825
2023-01-22 23:52:42.131336: step: 1404/530, loss: 0.4543072581291199
2023-01-22 23:52:43.334447: step: 1408/530, loss: 0.06269922852516174
2023-01-22 23:52:44.493149: step: 1412/530, loss: 0.8202094435691833
2023-01-22 23:52:45.661093: step: 1416/530, loss: 0.9506857991218567
2023-01-22 23:52:46.815093: step: 1420/530, loss: 0.1156138926744461
2023-01-22 23:52:47.968925: step: 1424/530, loss: 0.4783044457435608
2023-01-22 23:52:49.110172: step: 1428/530, loss: 0.16861963272094727
2023-01-22 23:52:50.270387: step: 1432/530, loss: 0.7537639141082764
2023-01-22 23:52:51.499835: step: 1436/530, loss: 0.17903974652290344
2023-01-22 23:52:52.686588: step: 1440/530, loss: 0.23431915044784546
2023-01-22 23:52:53.831305: step: 1444/530, loss: 0.13312754034996033
2023-01-22 23:52:54.992613: step: 1448/530, loss: 0.21181516349315643
2023-01-22 23:52:56.166045: step: 1452/530, loss: 0.07324037700891495
2023-01-22 23:52:57.330041: step: 1456/530, loss: 0.1949656456708908
2023-01-22 23:52:58.536540: step: 1460/530, loss: 0.37547311186790466
2023-01-22 23:52:59.696795: step: 1464/530, loss: 0.436201274394989
2023-01-22 23:53:00.854002: step: 1468/530, loss: 1.0353859663009644
2023-01-22 23:53:02.043123: step: 1472/530, loss: 0.25967320799827576
2023-01-22 23:53:03.204404: step: 1476/530, loss: 0.4616713523864746
2023-01-22 23:53:04.399116: step: 1480/530, loss: 0.9396399855613708
2023-01-22 23:53:05.538986: step: 1484/530, loss: 0.3414120674133301
2023-01-22 23:53:06.739229: step: 1488/530, loss: 0.7303752899169922
2023-01-22 23:53:07.899125: step: 1492/530, loss: 0.07259435951709747
2023-01-22 23:53:09.073376: step: 1496/530, loss: 0.6834162473678589
2023-01-22 23:53:10.258134: step: 1500/530, loss: 3.8585567474365234
2023-01-22 23:53:11.476513: step: 1504/530, loss: 0.41714781522750854
2023-01-22 23:53:12.665804: step: 1508/530, loss: 0.0361720435321331
2023-01-22 23:53:13.841842: step: 1512/530, loss: 0.1392539143562317
2023-01-22 23:53:15.044088: step: 1516/530, loss: 0.7899408340454102
2023-01-22 23:53:16.207847: step: 1520/530, loss: 0.2657398283481598
2023-01-22 23:53:17.397349: step: 1524/530, loss: 0.3879263997077942
2023-01-22 23:53:18.559546: step: 1528/530, loss: 0.26767969131469727
2023-01-22 23:53:19.716166: step: 1532/530, loss: 0.16750946640968323
2023-01-22 23:53:20.892773: step: 1536/530, loss: 0.09916935116052628
2023-01-22 23:53:22.048943: step: 1540/530, loss: 6.130626678466797
2023-01-22 23:53:23.250054: step: 1544/530, loss: 0.552817165851593
2023-01-22 23:53:24.426154: step: 1548/530, loss: 1.6418845653533936
2023-01-22 23:53:25.583387: step: 1552/530, loss: 0.7388523817062378
2023-01-22 23:53:26.736908: step: 1556/530, loss: 0.3149663805961609
2023-01-22 23:53:27.913132: step: 1560/530, loss: 0.5894988775253296
2023-01-22 23:53:29.080561: step: 1564/530, loss: 0.2805604934692383
2023-01-22 23:53:30.265358: step: 1568/530, loss: 0.19328290224075317
2023-01-22 23:53:31.401797: step: 1572/530, loss: 0.5188925862312317
2023-01-22 23:53:32.554762: step: 1576/530, loss: 0.6756436228752136
2023-01-22 23:53:33.761834: step: 1580/530, loss: 0.7145251631736755
2023-01-22 23:53:34.969100: step: 1584/530, loss: 0.777800440788269
2023-01-22 23:53:36.140613: step: 1588/530, loss: 0.3991817533969879
2023-01-22 23:53:37.300642: step: 1592/530, loss: 0.17097407579421997
2023-01-22 23:53:38.475818: step: 1596/530, loss: 0.05069741979241371
2023-01-22 23:53:39.669794: step: 1600/530, loss: 0.32514554262161255
2023-01-22 23:53:40.857787: step: 1604/530, loss: 0.8154205679893494
2023-01-22 23:53:42.077573: step: 1608/530, loss: 0.8199716806411743
2023-01-22 23:53:43.246665: step: 1612/530, loss: 0.13968773186206818
2023-01-22 23:53:44.468550: step: 1616/530, loss: 0.9974249601364136
2023-01-22 23:53:45.662698: step: 1620/530, loss: 0.19445961713790894
2023-01-22 23:53:46.801347: step: 1624/530, loss: 0.11992254108190536
2023-01-22 23:53:47.990313: step: 1628/530, loss: 0.17650556564331055
2023-01-22 23:53:49.159211: step: 1632/530, loss: 0.32293254137039185
2023-01-22 23:53:50.327163: step: 1636/530, loss: 0.41194048523902893
2023-01-22 23:53:51.494481: step: 1640/530, loss: 0.22866877913475037
2023-01-22 23:53:52.646591: step: 1644/530, loss: 0.23574122786521912
2023-01-22 23:53:53.815502: step: 1648/530, loss: 7.095818042755127
2023-01-22 23:53:54.989091: step: 1652/530, loss: 0.4307723939418793
2023-01-22 23:53:56.163171: step: 1656/530, loss: 0.2336655557155609
2023-01-22 23:53:57.359026: step: 1660/530, loss: 1.0493323802947998
2023-01-22 23:53:58.493078: step: 1664/530, loss: 0.18368035554885864
2023-01-22 23:53:59.688241: step: 1668/530, loss: 0.6307743191719055
2023-01-22 23:54:00.865700: step: 1672/530, loss: 0.12392202019691467
2023-01-22 23:54:02.073068: step: 1676/530, loss: 0.19623461365699768
2023-01-22 23:54:03.235271: step: 1680/530, loss: 0.1633135825395584
2023-01-22 23:54:04.430889: step: 1684/530, loss: 0.7161133289337158
2023-01-22 23:54:05.622486: step: 1688/530, loss: 0.17464706301689148
2023-01-22 23:54:06.812186: step: 1692/530, loss: 0.5377215147018433
2023-01-22 23:54:07.960660: step: 1696/530, loss: 0.07636852562427521
2023-01-22 23:54:09.132513: step: 1700/530, loss: 0.5019243359565735
2023-01-22 23:54:10.312593: step: 1704/530, loss: 0.48598137497901917
2023-01-22 23:54:11.463558: step: 1708/530, loss: 0.10662110149860382
2023-01-22 23:54:12.694604: step: 1712/530, loss: 0.34850093722343445
2023-01-22 23:54:13.830264: step: 1716/530, loss: 0.15613965690135956
2023-01-22 23:54:15.020967: step: 1720/530, loss: 0.26565903425216675
2023-01-22 23:54:16.223913: step: 1724/530, loss: 1.06226646900177
2023-01-22 23:54:17.407080: step: 1728/530, loss: 0.18133488297462463
2023-01-22 23:54:18.587779: step: 1732/530, loss: 0.1587659865617752
2023-01-22 23:54:19.801795: step: 1736/530, loss: 0.18643851578235626
2023-01-22 23:54:21.016112: step: 1740/530, loss: 0.2335626631975174
2023-01-22 23:54:22.183059: step: 1744/530, loss: 1.085392951965332
2023-01-22 23:54:23.307345: step: 1748/530, loss: 0.17823128402233124
2023-01-22 23:54:24.514309: step: 1752/530, loss: 0.8394138813018799
2023-01-22 23:54:25.694217: step: 1756/530, loss: 0.7023558616638184
2023-01-22 23:54:26.878987: step: 1760/530, loss: 0.21441689133644104
2023-01-22 23:54:28.069250: step: 1764/530, loss: 1.3282926082611084
2023-01-22 23:54:29.280146: step: 1768/530, loss: 1.3719189167022705
2023-01-22 23:54:30.416286: step: 1772/530, loss: 0.1980564147233963
2023-01-22 23:54:31.649010: step: 1776/530, loss: 0.10667157173156738
2023-01-22 23:54:32.849305: step: 1780/530, loss: 0.5589823722839355
2023-01-22 23:54:34.036580: step: 1784/530, loss: 0.19532231986522675
2023-01-22 23:54:35.181827: step: 1788/530, loss: 1.4473024606704712
2023-01-22 23:54:36.342957: step: 1792/530, loss: 6.4610443115234375
2023-01-22 23:54:37.505738: step: 1796/530, loss: 0.1384432315826416
2023-01-22 23:54:38.685728: step: 1800/530, loss: 0.6778097152709961
2023-01-22 23:54:39.862933: step: 1804/530, loss: 0.13512945175170898
2023-01-22 23:54:41.052110: step: 1808/530, loss: 0.25959131121635437
2023-01-22 23:54:42.203300: step: 1812/530, loss: 0.14037713408470154
2023-01-22 23:54:43.393240: step: 1816/530, loss: 0.1534731388092041
2023-01-22 23:54:44.542809: step: 1820/530, loss: 0.7548848986625671
2023-01-22 23:54:45.714660: step: 1824/530, loss: 1.7059985399246216
2023-01-22 23:54:46.918310: step: 1828/530, loss: 0.3666013777256012
2023-01-22 23:54:48.099195: step: 1832/530, loss: 2.224490165710449
2023-01-22 23:54:49.293370: step: 1836/530, loss: 0.06247539445757866
2023-01-22 23:54:50.502490: step: 1840/530, loss: 0.06426487118005753
2023-01-22 23:54:51.665779: step: 1844/530, loss: 0.10009832680225372
2023-01-22 23:54:52.860374: step: 1848/530, loss: 0.29229727387428284
2023-01-22 23:54:54.014874: step: 1852/530, loss: 0.1024850383400917
2023-01-22 23:54:55.167442: step: 1856/530, loss: 0.16965365409851074
2023-01-22 23:54:56.347558: step: 1860/530, loss: 0.3466854989528656
2023-01-22 23:54:57.504011: step: 1864/530, loss: 0.09264745563268661
2023-01-22 23:54:58.725692: step: 1868/530, loss: 0.16719265282154083
2023-01-22 23:54:59.908602: step: 1872/530, loss: 1.2806411981582642
2023-01-22 23:55:01.084527: step: 1876/530, loss: 0.10648641735315323
2023-01-22 23:55:02.255094: step: 1880/530, loss: 0.17291870713233948
2023-01-22 23:55:03.428157: step: 1884/530, loss: 0.20730113983154297
2023-01-22 23:55:04.596441: step: 1888/530, loss: 0.3161739706993103
2023-01-22 23:55:05.750911: step: 1892/530, loss: 0.1714148223400116
2023-01-22 23:55:06.891807: step: 1896/530, loss: 0.16755680739879608
2023-01-22 23:55:08.067791: step: 1900/530, loss: 0.3586142659187317
2023-01-22 23:55:09.213883: step: 1904/530, loss: 0.10557427257299423
2023-01-22 23:55:10.422937: step: 1908/530, loss: 1.698386549949646
2023-01-22 23:55:11.602355: step: 1912/530, loss: 0.43443670868873596
2023-01-22 23:55:12.780272: step: 1916/530, loss: 0.571746826171875
2023-01-22 23:55:13.981324: step: 1920/530, loss: 0.723967969417572
2023-01-22 23:55:15.184846: step: 1924/530, loss: 0.09055925160646439
2023-01-22 23:55:16.375518: step: 1928/530, loss: 0.21665973961353302
2023-01-22 23:55:17.530424: step: 1932/530, loss: 0.12338156998157501
2023-01-22 23:55:18.728498: step: 1936/530, loss: 0.32324540615081787
2023-01-22 23:55:19.949055: step: 1940/530, loss: 1.0081002712249756
2023-01-22 23:55:21.169375: step: 1944/530, loss: 1.304118037223816
2023-01-22 23:55:22.381296: step: 1948/530, loss: 2.1551320552825928
2023-01-22 23:55:23.572417: step: 1952/530, loss: 0.19658727943897247
2023-01-22 23:55:24.760316: step: 1956/530, loss: 1.5743308067321777
2023-01-22 23:55:25.956239: step: 1960/530, loss: 0.22940078377723694
2023-01-22 23:55:27.137427: step: 1964/530, loss: 0.12993459403514862
2023-01-22 23:55:28.347394: step: 1968/530, loss: 0.16153010725975037
2023-01-22 23:55:29.532864: step: 1972/530, loss: 0.7037493586540222
2023-01-22 23:55:30.702888: step: 1976/530, loss: 0.054555606096982956
2023-01-22 23:55:31.876023: step: 1980/530, loss: 0.3966211676597595
2023-01-22 23:55:33.040841: step: 1984/530, loss: 0.33418625593185425
2023-01-22 23:55:34.243050: step: 1988/530, loss: 0.8138771653175354
2023-01-22 23:55:35.424653: step: 1992/530, loss: 0.974611759185791
2023-01-22 23:55:36.586380: step: 1996/530, loss: 0.07023420184850693
2023-01-22 23:55:37.739797: step: 2000/530, loss: 1.3829149007797241
2023-01-22 23:55:38.868182: step: 2004/530, loss: 0.14137983322143555
2023-01-22 23:55:40.041162: step: 2008/530, loss: 0.15284377336502075
2023-01-22 23:55:41.237902: step: 2012/530, loss: 0.07059414684772491
2023-01-22 23:55:42.417635: step: 2016/530, loss: 0.15334263443946838
2023-01-22 23:55:43.574277: step: 2020/530, loss: 0.6841206550598145
2023-01-22 23:55:44.757909: step: 2024/530, loss: 0.3394330143928528
2023-01-22 23:55:45.959578: step: 2028/530, loss: 0.18812847137451172
2023-01-22 23:55:47.120860: step: 2032/530, loss: 0.1167324110865593
2023-01-22 23:55:48.352595: step: 2036/530, loss: 0.23449645936489105
2023-01-22 23:55:49.497965: step: 2040/530, loss: 0.09905443340539932
2023-01-22 23:55:50.671262: step: 2044/530, loss: 6.895667552947998
2023-01-22 23:55:51.874139: step: 2048/530, loss: 0.2752523422241211
2023-01-22 23:55:53.009566: step: 2052/530, loss: 0.20511013269424438
2023-01-22 23:55:54.150577: step: 2056/530, loss: 0.2611364424228668
2023-01-22 23:55:55.330076: step: 2060/530, loss: 0.34802380204200745
2023-01-22 23:55:56.475501: step: 2064/530, loss: 0.22178447246551514
2023-01-22 23:55:57.673580: step: 2068/530, loss: 0.8025556802749634
2023-01-22 23:55:58.875470: step: 2072/530, loss: 0.466240793466568
2023-01-22 23:56:00.066429: step: 2076/530, loss: 0.7449437975883484
2023-01-22 23:56:01.225983: step: 2080/530, loss: 1.3982199430465698
2023-01-22 23:56:02.392539: step: 2084/530, loss: 0.11728854477405548
2023-01-22 23:56:03.538255: step: 2088/530, loss: 0.1916791945695877
2023-01-22 23:56:04.726370: step: 2092/530, loss: 0.383246511220932
2023-01-22 23:56:05.904428: step: 2096/530, loss: 0.43894684314727783
2023-01-22 23:56:07.089127: step: 2100/530, loss: 0.2484123408794403
2023-01-22 23:56:08.241269: step: 2104/530, loss: 1.289673924446106
2023-01-22 23:56:09.412682: step: 2108/530, loss: 0.250160276889801
2023-01-22 23:56:10.603967: step: 2112/530, loss: 0.6158790588378906
2023-01-22 23:56:11.799849: step: 2116/530, loss: 0.3135722875595093
2023-01-22 23:56:12.969120: step: 2120/530, loss: 0.08418045192956924
==================================================
Loss: 0.582
--------------------
Dev: {'event': {'p': 0.6336515513126492, 'r': 0.7070572569906791, 'f1': 0.6683448709880428}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Test: {'event': {'p': 0.6569703622392975, 'r': 0.6883266244968372, 'f1': 0.6722830665543386}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Chinese: {'event': {'p': 0.5483870967741935, 'r': 0.6296296296296297, 'f1': 0.5862068965517241}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Korean: {'event': {'p': 0.5681818181818182, 'r': 0.3968253968253968, 'f1': 0.4672897196261682}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Russian: {'event': {'p': 0.4117647058823529, 'r': 0.3888888888888889, 'f1': 0.39999999999999997}, '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': 0.6336515513126492, 'r': 0.7070572569906791, 'f1': 0.6683448709880428}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Eng Test for Chinese: {'event': {'p': 0.6569703622392975, 'r': 0.6883266244968372, 'f1': 0.6722830665543386}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Sample Chinese: {'event': {'p': 0.5483870967741935, 'r': 0.6296296296296297, 'f1': 0.5862068965517241}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6336515513126492, 'r': 0.7070572569906791, 'f1': 0.6683448709880428}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Eng Test for Korean: {'event': {'p': 0.6569703622392975, 'r': 0.6883266244968372, 'f1': 0.6722830665543386}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Sample Korean: {'event': {'p': 0.5681818181818182, 'r': 0.3968253968253968, 'f1': 0.4672897196261682}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5782463928967814, 'r': 0.6937416777629827, 'f1': 0.6307506053268765}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Eng Test for Russian: {'event': {'p': 0.5849148418491484, 'r': 0.6912018401380103, 'f1': 0.6336320506062204}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Sample Russian: {'event': {'p': 0.6538461538461539, 'r': 0.4722222222222222, 'f1': 0.5483870967741936}, '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 23:57:14.544806: step: 4/530, loss: 0.5191924571990967
2023-01-22 23:57:15.722156: step: 8/530, loss: 1.1706078052520752
2023-01-22 23:57:16.861250: step: 12/530, loss: 0.07949772477149963
2023-01-22 23:57:18.013653: step: 16/530, loss: 0.09682364761829376
2023-01-22 23:57:19.179352: step: 20/530, loss: 0.8770349621772766
2023-01-22 23:57:20.395318: step: 24/530, loss: 0.5905191898345947
2023-01-22 23:57:21.584371: step: 28/530, loss: 0.2906637191772461
2023-01-22 23:57:22.709725: step: 32/530, loss: 0.6441036462783813
2023-01-22 23:57:23.867682: step: 36/530, loss: 0.45494937896728516
2023-01-22 23:57:25.129325: step: 40/530, loss: 0.2761791944503784
2023-01-22 23:57:26.329854: step: 44/530, loss: 0.363181471824646
2023-01-22 23:57:27.465605: step: 48/530, loss: 0.555605411529541
2023-01-22 23:57:28.671119: step: 52/530, loss: 0.6407239437103271
2023-01-22 23:57:29.843588: step: 56/530, loss: 0.7539819478988647
2023-01-22 23:57:31.044844: step: 60/530, loss: 0.6422100067138672
2023-01-22 23:57:32.223731: step: 64/530, loss: 0.5551279187202454
2023-01-22 23:57:33.376736: step: 68/530, loss: 0.7178381085395813
2023-01-22 23:57:34.560195: step: 72/530, loss: 0.04354162514209747
2023-01-22 23:57:35.695289: step: 76/530, loss: 0.20696429908275604
2023-01-22 23:57:36.848711: step: 80/530, loss: 0.2528041899204254
2023-01-22 23:57:38.009349: step: 84/530, loss: 1.1910349130630493
2023-01-22 23:57:39.193762: step: 88/530, loss: 0.386963814496994
2023-01-22 23:57:40.345847: step: 92/530, loss: 0.23293867707252502
2023-01-22 23:57:41.479053: step: 96/530, loss: 0.25381651520729065
2023-01-22 23:57:42.670803: step: 100/530, loss: 0.2759174406528473
2023-01-22 23:57:43.819571: step: 104/530, loss: 0.2803935110569
2023-01-22 23:57:45.023851: step: 108/530, loss: 0.07051368057727814
2023-01-22 23:57:46.209486: step: 112/530, loss: 0.1895613670349121
2023-01-22 23:57:47.358245: step: 116/530, loss: 0.5699976086616516
2023-01-22 23:57:48.497901: step: 120/530, loss: 0.1027122512459755
2023-01-22 23:57:49.660365: step: 124/530, loss: 0.37537500262260437
2023-01-22 23:57:50.841769: step: 128/530, loss: 0.056505490094423294
2023-01-22 23:57:51.994898: step: 132/530, loss: 6.2937188148498535
2023-01-22 23:57:53.163981: step: 136/530, loss: 0.28658831119537354
2023-01-22 23:57:54.322683: step: 140/530, loss: 0.5731838345527649
2023-01-22 23:57:55.480139: step: 144/530, loss: 0.1502998322248459
2023-01-22 23:57:56.620587: step: 148/530, loss: 0.10899467766284943
2023-01-22 23:57:57.821203: step: 152/530, loss: 0.1422867774963379
2023-01-22 23:57:58.980055: step: 156/530, loss: 0.8451544046401978
2023-01-22 23:58:00.151560: step: 160/530, loss: 0.30751779675483704
2023-01-22 23:58:01.334396: step: 164/530, loss: 0.16143354773521423
2023-01-22 23:58:02.547163: step: 168/530, loss: 1.0905141830444336
2023-01-22 23:58:03.700129: step: 172/530, loss: 0.675628125667572
2023-01-22 23:58:04.919312: step: 176/530, loss: 0.21934472024440765
2023-01-22 23:58:06.055920: step: 180/530, loss: 0.6327414512634277
2023-01-22 23:58:07.215584: step: 184/530, loss: 0.3127192258834839
2023-01-22 23:58:08.381296: step: 188/530, loss: 0.02283940277993679
2023-01-22 23:58:09.540137: step: 192/530, loss: 0.11165190488100052
2023-01-22 23:58:10.723992: step: 196/530, loss: 0.14807024598121643
2023-01-22 23:58:11.923191: step: 200/530, loss: 0.4557231068611145
2023-01-22 23:58:13.111606: step: 204/530, loss: 0.26212817430496216
2023-01-22 23:58:14.294696: step: 208/530, loss: 7.076763153076172
2023-01-22 23:58:15.487341: step: 212/530, loss: 0.19836553931236267
2023-01-22 23:58:16.649653: step: 216/530, loss: 0.15052075684070587
2023-01-22 23:58:17.823401: step: 220/530, loss: 0.16224899888038635
2023-01-22 23:58:18.988369: step: 224/530, loss: 0.09037952870130539
2023-01-22 23:58:20.175631: step: 228/530, loss: 0.10467491298913956
2023-01-22 23:58:21.332423: step: 232/530, loss: 0.23347590863704681
2023-01-22 23:58:22.516815: step: 236/530, loss: 0.7598155736923218
2023-01-22 23:58:23.716393: step: 240/530, loss: 0.27143335342407227
2023-01-22 23:58:24.870391: step: 244/530, loss: 0.2126666009426117
2023-01-22 23:58:26.033587: step: 248/530, loss: 0.7509574890136719
2023-01-22 23:58:27.193502: step: 252/530, loss: 0.40980854630470276
2023-01-22 23:58:28.354401: step: 256/530, loss: 0.07153907418251038
2023-01-22 23:58:29.524458: step: 260/530, loss: 0.6321728229522705
2023-01-22 23:58:30.726265: step: 264/530, loss: 0.13787135481834412
2023-01-22 23:58:31.916277: step: 268/530, loss: 0.09872189164161682
2023-01-22 23:58:33.081145: step: 272/530, loss: 0.2302146852016449
2023-01-22 23:58:34.265635: step: 276/530, loss: 0.05352058634161949
2023-01-22 23:58:35.423518: step: 280/530, loss: 0.19960834085941315
2023-01-22 23:58:36.618606: step: 284/530, loss: 0.04820604622364044
2023-01-22 23:58:37.789429: step: 288/530, loss: 0.18540087342262268
2023-01-22 23:58:38.962084: step: 292/530, loss: 0.1493431031703949
2023-01-22 23:58:40.154396: step: 296/530, loss: 0.8330694437026978
2023-01-22 23:58:41.318709: step: 300/530, loss: 0.06468772888183594
2023-01-22 23:58:42.481876: step: 304/530, loss: 0.34788140654563904
2023-01-22 23:58:43.647587: step: 308/530, loss: 0.18793946504592896
2023-01-22 23:58:44.805361: step: 312/530, loss: 1.1298273801803589
2023-01-22 23:58:45.990682: step: 316/530, loss: 1.097474217414856
2023-01-22 23:58:47.131182: step: 320/530, loss: 0.10257778316736221
2023-01-22 23:58:48.306485: step: 324/530, loss: 0.6832658052444458
2023-01-22 23:58:49.473570: step: 328/530, loss: 0.10810303688049316
2023-01-22 23:58:50.636831: step: 332/530, loss: 1.2212339639663696
2023-01-22 23:58:51.762585: step: 336/530, loss: 0.8411941528320312
2023-01-22 23:58:52.916352: step: 340/530, loss: 0.20332685112953186
2023-01-22 23:58:54.069403: step: 344/530, loss: 0.5032680034637451
2023-01-22 23:58:55.304275: step: 348/530, loss: 1.0888937711715698
2023-01-22 23:58:56.518950: step: 352/530, loss: 0.2017425149679184
2023-01-22 23:58:57.669738: step: 356/530, loss: 0.14386549592018127
2023-01-22 23:58:58.855438: step: 360/530, loss: 0.33215874433517456
2023-01-22 23:59:00.020757: step: 364/530, loss: 0.1823878288269043
2023-01-22 23:59:01.221408: step: 368/530, loss: 0.33030763268470764
2023-01-22 23:59:02.429731: step: 372/530, loss: 0.17231746017932892
2023-01-22 23:59:03.645961: step: 376/530, loss: 0.40852493047714233
2023-01-22 23:59:04.825807: step: 380/530, loss: 0.11943116784095764
2023-01-22 23:59:05.999104: step: 384/530, loss: 0.04621467739343643
2023-01-22 23:59:07.175420: step: 388/530, loss: 0.38526660203933716
2023-01-22 23:59:08.301486: step: 392/530, loss: 0.15916013717651367
2023-01-22 23:59:09.488022: step: 396/530, loss: 6.311384677886963
2023-01-22 23:59:10.665238: step: 400/530, loss: 0.224155992269516
2023-01-22 23:59:11.857034: step: 404/530, loss: 0.29802682995796204
2023-01-22 23:59:13.048194: step: 408/530, loss: 0.3599209487438202
2023-01-22 23:59:14.188366: step: 412/530, loss: 0.2007201611995697
2023-01-22 23:59:15.367344: step: 416/530, loss: 0.4488944113254547
2023-01-22 23:59:16.529280: step: 420/530, loss: 1.0110517740249634
2023-01-22 23:59:17.704234: step: 424/530, loss: 0.14849528670310974
2023-01-22 23:59:18.856582: step: 428/530, loss: 0.14279747009277344
2023-01-22 23:59:19.995867: step: 432/530, loss: 0.20845270156860352
2023-01-22 23:59:21.147179: step: 436/530, loss: 0.25758370757102966
2023-01-22 23:59:22.361997: step: 440/530, loss: 0.237433061003685
2023-01-22 23:59:23.506903: step: 444/530, loss: 0.093405582010746
2023-01-22 23:59:24.736132: step: 448/530, loss: 0.054293230175971985
2023-01-22 23:59:25.882888: step: 452/530, loss: 0.09260274469852448
2023-01-22 23:59:27.040931: step: 456/530, loss: 0.0942709892988205
2023-01-22 23:59:28.187819: step: 460/530, loss: 0.3790920376777649
2023-01-22 23:59:29.414230: step: 464/530, loss: 0.13287459313869476
2023-01-22 23:59:30.584652: step: 468/530, loss: 0.5176077485084534
2023-01-22 23:59:31.754312: step: 472/530, loss: 0.09319677948951721
2023-01-22 23:59:32.884596: step: 476/530, loss: 0.0547015443444252
2023-01-22 23:59:34.080707: step: 480/530, loss: 0.3686017096042633
2023-01-22 23:59:35.266765: step: 484/530, loss: 0.11386542022228241
2023-01-22 23:59:36.426517: step: 488/530, loss: 0.6599113941192627
2023-01-22 23:59:37.599329: step: 492/530, loss: 0.22499322891235352
2023-01-22 23:59:38.817075: step: 496/530, loss: 0.3902978301048279
2023-01-22 23:59:39.995397: step: 500/530, loss: 0.24940013885498047
2023-01-22 23:59:41.166937: step: 504/530, loss: 0.2807157635688782
2023-01-22 23:59:42.341601: step: 508/530, loss: 0.22961747646331787
2023-01-22 23:59:43.483273: step: 512/530, loss: 0.05997591093182564
2023-01-22 23:59:44.629342: step: 516/530, loss: 0.1676074117422104
2023-01-22 23:59:45.821482: step: 520/530, loss: 1.066033959388733
2023-01-22 23:59:46.992070: step: 524/530, loss: 0.12823104858398438
2023-01-22 23:59:48.166135: step: 528/530, loss: 0.20828142762184143
2023-01-22 23:59:49.320767: step: 532/530, loss: 0.6198794841766357
2023-01-22 23:59:50.523240: step: 536/530, loss: 0.4361898899078369
2023-01-22 23:59:51.687213: step: 540/530, loss: 0.20145435631275177
2023-01-22 23:59:52.896663: step: 544/530, loss: 0.6686853766441345
2023-01-22 23:59:54.068803: step: 548/530, loss: 0.17464642226696014
2023-01-22 23:59:55.220227: step: 552/530, loss: 0.13746953010559082
2023-01-22 23:59:56.409347: step: 556/530, loss: 0.11354966461658478
2023-01-22 23:59:57.604303: step: 560/530, loss: 0.08568146079778671
2023-01-22 23:59:58.778136: step: 564/530, loss: 0.1313396692276001
2023-01-22 23:59:59.920920: step: 568/530, loss: 0.3456174433231354
2023-01-23 00:00:01.096450: step: 572/530, loss: 0.31579160690307617
2023-01-23 00:00:02.274227: step: 576/530, loss: 0.49187344312667847
2023-01-23 00:00:03.432902: step: 580/530, loss: 0.2015778124332428
2023-01-23 00:00:04.584189: step: 584/530, loss: 0.14697489142417908
2023-01-23 00:00:05.743820: step: 588/530, loss: 2.2941653728485107
2023-01-23 00:00:06.926276: step: 592/530, loss: 0.32093191146850586
2023-01-23 00:00:08.103667: step: 596/530, loss: 0.12202048301696777
2023-01-23 00:00:09.283481: step: 600/530, loss: 0.3250643014907837
2023-01-23 00:00:10.462384: step: 604/530, loss: 0.11785449832677841
2023-01-23 00:00:11.607087: step: 608/530, loss: 0.09085074067115784
2023-01-23 00:00:12.779142: step: 612/530, loss: 0.12013489007949829
2023-01-23 00:00:13.967554: step: 616/530, loss: 0.839863657951355
2023-01-23 00:00:15.145264: step: 620/530, loss: 0.14664916694164276
2023-01-23 00:00:16.274454: step: 624/530, loss: 0.023165225982666016
2023-01-23 00:00:17.455590: step: 628/530, loss: 0.1783846914768219
2023-01-23 00:00:18.642987: step: 632/530, loss: 0.36509278416633606
2023-01-23 00:00:19.804476: step: 636/530, loss: 0.13413682579994202
2023-01-23 00:00:20.966584: step: 640/530, loss: 0.15138070285320282
2023-01-23 00:00:22.121913: step: 644/530, loss: 0.6526864171028137
2023-01-23 00:00:23.317929: step: 648/530, loss: 0.14482823014259338
2023-01-23 00:00:24.496233: step: 652/530, loss: 1.921859860420227
2023-01-23 00:00:25.665528: step: 656/530, loss: 6.161225318908691
2023-01-23 00:00:26.858146: step: 660/530, loss: 0.12913508713245392
2023-01-23 00:00:28.030383: step: 664/530, loss: 0.6400312781333923
2023-01-23 00:00:29.215994: step: 668/530, loss: 0.7473790645599365
2023-01-23 00:00:30.388590: step: 672/530, loss: 0.2976551055908203
2023-01-23 00:00:31.529928: step: 676/530, loss: 0.13958100974559784
2023-01-23 00:00:32.671894: step: 680/530, loss: 0.10299654304981232
2023-01-23 00:00:33.808063: step: 684/530, loss: 1.0223383903503418
2023-01-23 00:00:34.986136: step: 688/530, loss: 0.10239820927381516
2023-01-23 00:00:36.176944: step: 692/530, loss: 0.1845192015171051
2023-01-23 00:00:37.323734: step: 696/530, loss: 0.025221683084964752
2023-01-23 00:00:38.513727: step: 700/530, loss: 1.3266277313232422
2023-01-23 00:00:39.689676: step: 704/530, loss: 0.18309983611106873
2023-01-23 00:00:40.845674: step: 708/530, loss: 0.37653648853302
2023-01-23 00:00:41.980254: step: 712/530, loss: 0.06200771778821945
2023-01-23 00:00:43.150332: step: 716/530, loss: 0.7784267067909241
2023-01-23 00:00:44.330984: step: 720/530, loss: 0.14865227043628693
2023-01-23 00:00:45.527754: step: 724/530, loss: 0.33311232924461365
2023-01-23 00:00:46.712356: step: 728/530, loss: 1.8277270793914795
2023-01-23 00:00:47.877505: step: 732/530, loss: 0.9166950583457947
2023-01-23 00:00:49.009882: step: 736/530, loss: 0.12873688340187073
2023-01-23 00:00:50.152876: step: 740/530, loss: 0.18474312126636505
2023-01-23 00:00:51.308131: step: 744/530, loss: 0.1621491014957428
2023-01-23 00:00:52.476047: step: 748/530, loss: 0.48359689116477966
2023-01-23 00:00:53.638594: step: 752/530, loss: 0.665831446647644
2023-01-23 00:00:54.835547: step: 756/530, loss: 0.1538044512271881
2023-01-23 00:00:56.033122: step: 760/530, loss: 0.09240970760583878
2023-01-23 00:00:57.182310: step: 764/530, loss: 0.21537938714027405
2023-01-23 00:00:58.349892: step: 768/530, loss: 0.0468110591173172
2023-01-23 00:00:59.535143: step: 772/530, loss: 0.8836272954940796
2023-01-23 00:01:00.682995: step: 776/530, loss: 0.74620521068573
2023-01-23 00:01:01.815298: step: 780/530, loss: 0.23835481703281403
2023-01-23 00:01:02.961189: step: 784/530, loss: 0.6982858180999756
2023-01-23 00:01:04.135709: step: 788/530, loss: 0.06144876405596733
2023-01-23 00:01:05.343351: step: 792/530, loss: 0.08733272552490234
2023-01-23 00:01:06.544516: step: 796/530, loss: 0.08771095424890518
2023-01-23 00:01:07.709079: step: 800/530, loss: 0.0940345823764801
2023-01-23 00:01:08.866876: step: 804/530, loss: 0.7421600818634033
2023-01-23 00:01:10.023352: step: 808/530, loss: 0.37771615386009216
2023-01-23 00:01:11.185940: step: 812/530, loss: 0.13880959153175354
2023-01-23 00:01:12.362402: step: 816/530, loss: 0.13163185119628906
2023-01-23 00:01:13.509175: step: 820/530, loss: 0.13775014877319336
2023-01-23 00:01:14.659877: step: 824/530, loss: 0.038422584533691406
2023-01-23 00:01:15.814003: step: 828/530, loss: 0.45583438873291016
2023-01-23 00:01:16.975357: step: 832/530, loss: 0.3177642822265625
2023-01-23 00:01:18.179540: step: 836/530, loss: 0.1935112625360489
2023-01-23 00:01:19.354064: step: 840/530, loss: 0.07412910461425781
2023-01-23 00:01:20.535271: step: 844/530, loss: 0.8029215931892395
2023-01-23 00:01:21.747372: step: 848/530, loss: 0.1322302371263504
2023-01-23 00:01:22.931057: step: 852/530, loss: 0.3052927851676941
2023-01-23 00:01:24.139715: step: 856/530, loss: 0.24283725023269653
2023-01-23 00:01:25.303642: step: 860/530, loss: 0.12081928551197052
2023-01-23 00:01:26.477842: step: 864/530, loss: 0.1414417326450348
2023-01-23 00:01:27.667160: step: 868/530, loss: 0.11298465728759766
2023-01-23 00:01:28.817323: step: 872/530, loss: 0.7825241684913635
2023-01-23 00:01:30.037666: step: 876/530, loss: 0.19887542724609375
2023-01-23 00:01:31.223269: step: 880/530, loss: 0.1622975766658783
2023-01-23 00:01:32.382957: step: 884/530, loss: 1.4077777862548828
2023-01-23 00:01:33.558813: step: 888/530, loss: 0.10478525608778
2023-01-23 00:01:34.717148: step: 892/530, loss: 0.12131252884864807
2023-01-23 00:01:35.913378: step: 896/530, loss: 0.18845997750759125
2023-01-23 00:01:37.105793: step: 900/530, loss: 0.021206902340054512
2023-01-23 00:01:38.277710: step: 904/530, loss: 0.09146595001220703
2023-01-23 00:01:39.470187: step: 908/530, loss: 0.5313259363174438
2023-01-23 00:01:40.656044: step: 912/530, loss: 0.17365026473999023
2023-01-23 00:01:41.842998: step: 916/530, loss: 0.1472891867160797
2023-01-23 00:01:43.009996: step: 920/530, loss: 0.04388804733753204
2023-01-23 00:01:44.156269: step: 924/530, loss: 0.09502525627613068
2023-01-23 00:01:45.327911: step: 928/530, loss: 0.7249863147735596
2023-01-23 00:01:46.505441: step: 932/530, loss: 0.16412439942359924
2023-01-23 00:01:47.681638: step: 936/530, loss: 0.9990280866622925
2023-01-23 00:01:48.857156: step: 940/530, loss: 1.5301529169082642
2023-01-23 00:01:50.008396: step: 944/530, loss: 0.07348103821277618
2023-01-23 00:01:51.150189: step: 948/530, loss: 0.08050890266895294
2023-01-23 00:01:52.299206: step: 952/530, loss: 0.11624650657176971
2023-01-23 00:01:53.475993: step: 956/530, loss: 0.11236119270324707
2023-01-23 00:01:54.655515: step: 960/530, loss: 0.9776906967163086
2023-01-23 00:01:55.803907: step: 964/530, loss: 0.40713661909103394
2023-01-23 00:01:56.973260: step: 968/530, loss: 0.7711392641067505
2023-01-23 00:01:58.136071: step: 972/530, loss: 0.13404206931591034
2023-01-23 00:01:59.293481: step: 976/530, loss: 0.4408808648586273
2023-01-23 00:02:00.439665: step: 980/530, loss: 0.13976383209228516
2023-01-23 00:02:01.589531: step: 984/530, loss: 0.6734783053398132
2023-01-23 00:02:02.770288: step: 988/530, loss: 0.4627707898616791
2023-01-23 00:02:03.947661: step: 992/530, loss: 0.597649097442627
2023-01-23 00:02:05.119865: step: 996/530, loss: 0.11303062736988068
2023-01-23 00:02:06.329138: step: 1000/530, loss: 0.2047712802886963
2023-01-23 00:02:07.479801: step: 1004/530, loss: 0.19961795210838318
2023-01-23 00:02:08.661950: step: 1008/530, loss: 0.06768689304590225
2023-01-23 00:02:09.870007: step: 1012/530, loss: 0.0863809585571289
2023-01-23 00:02:11.033794: step: 1016/530, loss: 0.3175378739833832
2023-01-23 00:02:12.224110: step: 1020/530, loss: 0.13827113807201385
2023-01-23 00:02:13.398364: step: 1024/530, loss: 0.26949015259742737
2023-01-23 00:02:14.606557: step: 1028/530, loss: 0.6692726612091064
2023-01-23 00:02:15.762550: step: 1032/530, loss: 0.3550410866737366
2023-01-23 00:02:16.904971: step: 1036/530, loss: 0.09226550906896591
2023-01-23 00:02:18.095906: step: 1040/530, loss: 0.3014012575149536
2023-01-23 00:02:19.269581: step: 1044/530, loss: 1.3666375875473022
2023-01-23 00:02:20.429952: step: 1048/530, loss: 0.10425176471471786
2023-01-23 00:02:21.596314: step: 1052/530, loss: 1.3791825771331787
2023-01-23 00:02:22.750661: step: 1056/530, loss: 1.2946498394012451
2023-01-23 00:02:23.925039: step: 1060/530, loss: 0.1721879541873932
2023-01-23 00:02:25.063278: step: 1064/530, loss: 0.11235733330249786
2023-01-23 00:02:26.206588: step: 1068/530, loss: 0.435479074716568
2023-01-23 00:02:27.348770: step: 1072/530, loss: 0.15691828727722168
2023-01-23 00:02:28.523585: step: 1076/530, loss: 1.3144248723983765
2023-01-23 00:02:29.669515: step: 1080/530, loss: 0.5212429165840149
2023-01-23 00:02:30.818199: step: 1084/530, loss: 0.14469701051712036
2023-01-23 00:02:31.989595: step: 1088/530, loss: 0.7016888856887817
2023-01-23 00:02:33.174373: step: 1092/530, loss: 0.5364924669265747
2023-01-23 00:02:34.327926: step: 1096/530, loss: 0.7248868346214294
2023-01-23 00:02:35.529422: step: 1100/530, loss: 1.0725609064102173
2023-01-23 00:02:36.715854: step: 1104/530, loss: 0.3142368197441101
2023-01-23 00:02:37.918630: step: 1108/530, loss: 0.07861433178186417
2023-01-23 00:02:39.094847: step: 1112/530, loss: 0.1779017448425293
2023-01-23 00:02:40.309765: step: 1116/530, loss: 0.25320473313331604
2023-01-23 00:02:41.520094: step: 1120/530, loss: 0.7164859771728516
2023-01-23 00:02:42.693999: step: 1124/530, loss: 0.35661038756370544
2023-01-23 00:02:43.852463: step: 1128/530, loss: 0.3326791524887085
2023-01-23 00:02:45.051666: step: 1132/530, loss: 0.9281638860702515
2023-01-23 00:02:46.211352: step: 1136/530, loss: 0.6749950051307678
2023-01-23 00:02:47.393789: step: 1140/530, loss: 0.800000786781311
2023-01-23 00:02:48.623774: step: 1144/530, loss: 0.06312818825244904
2023-01-23 00:02:49.824892: step: 1148/530, loss: 0.15952062606811523
2023-01-23 00:02:50.999566: step: 1152/530, loss: 0.42119836807250977
2023-01-23 00:02:52.170838: step: 1156/530, loss: 0.2126747965812683
2023-01-23 00:02:53.370383: step: 1160/530, loss: 0.15158167481422424
2023-01-23 00:02:54.545479: step: 1164/530, loss: 0.3569963574409485
2023-01-23 00:02:55.735398: step: 1168/530, loss: 0.3941791355609894
2023-01-23 00:02:56.930980: step: 1172/530, loss: 1.6471282243728638
2023-01-23 00:02:58.087088: step: 1176/530, loss: 0.1890300214290619
2023-01-23 00:02:59.315135: step: 1180/530, loss: 4.642889022827148
2023-01-23 00:03:00.502765: step: 1184/530, loss: 0.2530531883239746
2023-01-23 00:03:01.672862: step: 1188/530, loss: 0.09014657139778137
2023-01-23 00:03:02.846039: step: 1192/530, loss: 0.7563281059265137
2023-01-23 00:03:04.020780: step: 1196/530, loss: 7.942691802978516
2023-01-23 00:03:05.167127: step: 1200/530, loss: 0.8773500919342041
2023-01-23 00:03:06.315042: step: 1204/530, loss: 0.6622392535209656
2023-01-23 00:03:07.472893: step: 1208/530, loss: 0.1346883326768875
2023-01-23 00:03:08.666484: step: 1212/530, loss: 0.3898424208164215
2023-01-23 00:03:09.849997: step: 1216/530, loss: 0.5551837086677551
2023-01-23 00:03:11.026709: step: 1220/530, loss: 0.03483228385448456
2023-01-23 00:03:12.215647: step: 1224/530, loss: 0.10519857704639435
2023-01-23 00:03:13.355158: step: 1228/530, loss: 6.247714042663574
2023-01-23 00:03:14.536305: step: 1232/530, loss: 0.07327232509851456
2023-01-23 00:03:15.761190: step: 1236/530, loss: 0.06431026756763458
2023-01-23 00:03:16.964478: step: 1240/530, loss: 0.2630414068698883
2023-01-23 00:03:18.117153: step: 1244/530, loss: 0.7725036144256592
2023-01-23 00:03:19.332487: step: 1248/530, loss: 0.7779296636581421
2023-01-23 00:03:20.534165: step: 1252/530, loss: 0.2596513628959656
2023-01-23 00:03:21.760899: step: 1256/530, loss: 0.17486433684825897
2023-01-23 00:03:22.906002: step: 1260/530, loss: 0.20854301750659943
2023-01-23 00:03:24.071315: step: 1264/530, loss: 0.5837327241897583
2023-01-23 00:03:25.229041: step: 1268/530, loss: 0.09923320263624191
2023-01-23 00:03:26.404105: step: 1272/530, loss: 0.12830042839050293
2023-01-23 00:03:27.599490: step: 1276/530, loss: 0.07933598011732101
2023-01-23 00:03:28.785107: step: 1280/530, loss: 0.10121545195579529
2023-01-23 00:03:29.939641: step: 1284/530, loss: 0.8762174844741821
2023-01-23 00:03:31.106045: step: 1288/530, loss: 0.17349015176296234
2023-01-23 00:03:32.275096: step: 1292/530, loss: 0.23248663544654846
2023-01-23 00:03:33.427758: step: 1296/530, loss: 0.19568046927452087
2023-01-23 00:03:34.625135: step: 1300/530, loss: 0.7276216745376587
2023-01-23 00:03:35.818694: step: 1304/530, loss: 0.32748889923095703
2023-01-23 00:03:37.001120: step: 1308/530, loss: 0.2083718329668045
2023-01-23 00:03:38.216752: step: 1312/530, loss: 0.3393760621547699
2023-01-23 00:03:39.387603: step: 1316/530, loss: 6.476100921630859
2023-01-23 00:03:40.546307: step: 1320/530, loss: 2.1071600914001465
2023-01-23 00:03:41.724619: step: 1324/530, loss: 0.697489321231842
2023-01-23 00:03:42.906949: step: 1328/530, loss: 1.1273558139801025
2023-01-23 00:03:44.118419: step: 1332/530, loss: 0.468283474445343
2023-01-23 00:03:45.312385: step: 1336/530, loss: 0.0896296501159668
2023-01-23 00:03:46.495163: step: 1340/530, loss: 1.3354952335357666
2023-01-23 00:03:47.672969: step: 1344/530, loss: 0.3272493779659271
2023-01-23 00:03:48.849219: step: 1348/530, loss: 0.4466167390346527
2023-01-23 00:03:50.065530: step: 1352/530, loss: 0.10995455086231232
2023-01-23 00:03:51.206289: step: 1356/530, loss: 0.13752499222755432
2023-01-23 00:03:52.384683: step: 1360/530, loss: 0.43463876843452454
2023-01-23 00:03:53.535707: step: 1364/530, loss: 0.20803165435791016
2023-01-23 00:03:54.705832: step: 1368/530, loss: 0.20012864470481873
2023-01-23 00:03:55.873270: step: 1372/530, loss: 0.09706335514783859
2023-01-23 00:03:57.051722: step: 1376/530, loss: 0.5609232783317566
2023-01-23 00:03:58.180913: step: 1380/530, loss: 2.2602148056030273
2023-01-23 00:03:59.334483: step: 1384/530, loss: 0.7181587815284729
2023-01-23 00:04:00.517109: step: 1388/530, loss: 0.036554619669914246
2023-01-23 00:04:01.672866: step: 1392/530, loss: 0.14397478103637695
2023-01-23 00:04:02.868346: step: 1396/530, loss: 0.3144262433052063
2023-01-23 00:04:04.042958: step: 1400/530, loss: 0.12653875350952148
2023-01-23 00:04:05.215024: step: 1404/530, loss: 0.2666395306587219
2023-01-23 00:04:06.374544: step: 1408/530, loss: 0.24201267957687378
2023-01-23 00:04:07.580251: step: 1412/530, loss: 0.07698884606361389
2023-01-23 00:04:08.779859: step: 1416/530, loss: 0.05825548246502876
2023-01-23 00:04:09.964758: step: 1420/530, loss: 0.32834547758102417
2023-01-23 00:04:11.120525: step: 1424/530, loss: 0.27075016498565674
2023-01-23 00:04:12.387175: step: 1428/530, loss: 0.36395910382270813
2023-01-23 00:04:13.561344: step: 1432/530, loss: 0.4368910789489746
2023-01-23 00:04:14.728293: step: 1436/530, loss: 1.0011438131332397
2023-01-23 00:04:15.880502: step: 1440/530, loss: 0.09150008857250214
2023-01-23 00:04:17.059418: step: 1444/530, loss: 0.7740252614021301
2023-01-23 00:04:18.227317: step: 1448/530, loss: 0.08964795619249344
2023-01-23 00:04:19.397476: step: 1452/530, loss: 0.11217927932739258
2023-01-23 00:04:20.562059: step: 1456/530, loss: 0.2322949469089508
2023-01-23 00:04:21.720072: step: 1460/530, loss: 0.043490078300237656
2023-01-23 00:04:22.870062: step: 1464/530, loss: 0.6711433529853821
2023-01-23 00:04:24.019940: step: 1468/530, loss: 0.4433276951313019
2023-01-23 00:04:25.216847: step: 1472/530, loss: 0.222181037068367
2023-01-23 00:04:26.410835: step: 1476/530, loss: 0.723024845123291
2023-01-23 00:04:27.620265: step: 1480/530, loss: 0.11312341690063477
2023-01-23 00:04:28.817875: step: 1484/530, loss: 0.7232824563980103
2023-01-23 00:04:29.993918: step: 1488/530, loss: 0.7157189249992371
2023-01-23 00:04:31.172807: step: 1492/530, loss: 0.4857467710971832
2023-01-23 00:04:32.352865: step: 1496/530, loss: 0.037091925740242004
2023-01-23 00:04:33.531139: step: 1500/530, loss: 0.17124004662036896
2023-01-23 00:04:34.718209: step: 1504/530, loss: 0.3725845217704773
2023-01-23 00:04:35.885324: step: 1508/530, loss: 0.7506771087646484
2023-01-23 00:04:37.033981: step: 1512/530, loss: 1.1414482593536377
2023-01-23 00:04:38.212396: step: 1516/530, loss: 0.4713541567325592
2023-01-23 00:04:39.406365: step: 1520/530, loss: 0.9057143330574036
2023-01-23 00:04:40.608197: step: 1524/530, loss: 0.10838623344898224
2023-01-23 00:04:41.821055: step: 1528/530, loss: 0.15397867560386658
2023-01-23 00:04:43.012757: step: 1532/530, loss: 0.4569709599018097
2023-01-23 00:04:44.160818: step: 1536/530, loss: 0.09263773262500763
2023-01-23 00:04:45.378118: step: 1540/530, loss: 0.39521485567092896
2023-01-23 00:04:46.550126: step: 1544/530, loss: 0.17746220529079437
2023-01-23 00:04:47.714959: step: 1548/530, loss: 0.31682220101356506
2023-01-23 00:04:48.874609: step: 1552/530, loss: 0.21630993485450745
2023-01-23 00:04:50.055198: step: 1556/530, loss: 0.4423714876174927
2023-01-23 00:04:51.195065: step: 1560/530, loss: 0.30737465620040894
2023-01-23 00:04:52.363659: step: 1564/530, loss: 0.11255097389221191
2023-01-23 00:04:53.544714: step: 1568/530, loss: 0.08390870690345764
2023-01-23 00:04:54.729061: step: 1572/530, loss: 0.08495894074440002
2023-01-23 00:04:55.910527: step: 1576/530, loss: 0.08108730614185333
2023-01-23 00:04:57.079753: step: 1580/530, loss: 0.011083221063017845
2023-01-23 00:04:58.234857: step: 1584/530, loss: 0.7003467082977295
2023-01-23 00:04:59.426199: step: 1588/530, loss: 0.07347726821899414
2023-01-23 00:05:00.570643: step: 1592/530, loss: 0.7508512735366821
2023-01-23 00:05:01.748574: step: 1596/530, loss: 0.39373865723609924
2023-01-23 00:05:02.910551: step: 1600/530, loss: 0.2067669928073883
2023-01-23 00:05:04.083882: step: 1604/530, loss: 0.49305328726768494
2023-01-23 00:05:05.261508: step: 1608/530, loss: 0.8078652620315552
2023-01-23 00:05:06.456264: step: 1612/530, loss: 0.10917873680591583
2023-01-23 00:05:07.627276: step: 1616/530, loss: 0.11626091599464417
2023-01-23 00:05:08.745447: step: 1620/530, loss: 0.6472904682159424
2023-01-23 00:05:09.925413: step: 1624/530, loss: 0.18788547813892365
2023-01-23 00:05:11.089600: step: 1628/530, loss: 0.5658272504806519
2023-01-23 00:05:12.262212: step: 1632/530, loss: 1.4634454250335693
2023-01-23 00:05:13.400707: step: 1636/530, loss: 0.3999113440513611
2023-01-23 00:05:14.591992: step: 1640/530, loss: 0.23471951484680176
2023-01-23 00:05:15.812676: step: 1644/530, loss: 2.009218215942383
2023-01-23 00:05:16.968771: step: 1648/530, loss: 0.3491598069667816
2023-01-23 00:05:18.131923: step: 1652/530, loss: 0.8189980983734131
2023-01-23 00:05:19.360225: step: 1656/530, loss: 0.11746149510145187
2023-01-23 00:05:20.533874: step: 1660/530, loss: 0.21372228860855103
2023-01-23 00:05:21.703739: step: 1664/530, loss: 0.2093428075313568
2023-01-23 00:05:22.849831: step: 1668/530, loss: 0.6431800723075867
2023-01-23 00:05:24.036966: step: 1672/530, loss: 0.957047164440155
2023-01-23 00:05:25.189783: step: 1676/530, loss: 0.4716704487800598
2023-01-23 00:05:26.398130: step: 1680/530, loss: 0.13276395201683044
2023-01-23 00:05:27.575259: step: 1684/530, loss: 0.06600695103406906
2023-01-23 00:05:28.765157: step: 1688/530, loss: 0.2204338163137436
2023-01-23 00:05:29.984030: step: 1692/530, loss: 0.44693803787231445
2023-01-23 00:05:31.200195: step: 1696/530, loss: 0.019518518820405006
2023-01-23 00:05:32.376095: step: 1700/530, loss: 0.174461230635643
2023-01-23 00:05:33.576978: step: 1704/530, loss: 0.14608268439769745
2023-01-23 00:05:34.746157: step: 1708/530, loss: 0.8251336812973022
2023-01-23 00:05:35.916105: step: 1712/530, loss: 0.22570917010307312
2023-01-23 00:05:37.114519: step: 1716/530, loss: 0.1938481330871582
2023-01-23 00:05:38.297296: step: 1720/530, loss: 0.08189859241247177
2023-01-23 00:05:39.535347: step: 1724/530, loss: 0.029110431671142578
2023-01-23 00:05:40.684457: step: 1728/530, loss: 0.39237260818481445
2023-01-23 00:05:41.874803: step: 1732/530, loss: 0.4478951394557953
2023-01-23 00:05:43.033563: step: 1736/530, loss: 0.2682609260082245
2023-01-23 00:05:44.168485: step: 1740/530, loss: 0.10963449627161026
2023-01-23 00:05:45.363986: step: 1744/530, loss: 0.11441073566675186
2023-01-23 00:05:46.542225: step: 1748/530, loss: 0.4180283546447754
2023-01-23 00:05:47.726343: step: 1752/530, loss: 0.09568938612937927
2023-01-23 00:05:48.914936: step: 1756/530, loss: 0.0807914212346077
2023-01-23 00:05:50.097889: step: 1760/530, loss: 0.9998427629470825
2023-01-23 00:05:51.278594: step: 1764/530, loss: 1.6703314781188965
2023-01-23 00:05:52.485084: step: 1768/530, loss: 0.6590410470962524
2023-01-23 00:05:53.646028: step: 1772/530, loss: 0.6188690066337585
2023-01-23 00:05:54.801265: step: 1776/530, loss: 0.18719124794006348
2023-01-23 00:05:55.988739: step: 1780/530, loss: 0.6701532602310181
2023-01-23 00:05:57.157165: step: 1784/530, loss: 0.7900204062461853
2023-01-23 00:05:58.372684: step: 1788/530, loss: 0.06714200973510742
2023-01-23 00:05:59.557874: step: 1792/530, loss: 0.41136473417282104
2023-01-23 00:06:00.758397: step: 1796/530, loss: 0.15187856554985046
2023-01-23 00:06:01.878543: step: 1800/530, loss: 0.2718049883842468
2023-01-23 00:06:03.059050: step: 1804/530, loss: 1.4343321323394775
2023-01-23 00:06:04.259363: step: 1808/530, loss: 0.04400014877319336
2023-01-23 00:06:05.415064: step: 1812/530, loss: 0.0534881129860878
2023-01-23 00:06:06.591346: step: 1816/530, loss: 0.6328588724136353
2023-01-23 00:06:07.762776: step: 1820/530, loss: 0.44441384077072144
2023-01-23 00:06:08.964004: step: 1824/530, loss: 0.3629192113876343
2023-01-23 00:06:10.170900: step: 1828/530, loss: 0.08184538036584854
2023-01-23 00:06:11.332356: step: 1832/530, loss: 0.9786496162414551
2023-01-23 00:06:12.512834: step: 1836/530, loss: 0.6580917835235596
2023-01-23 00:06:13.693057: step: 1840/530, loss: 0.2784944176673889
2023-01-23 00:06:14.884923: step: 1844/530, loss: 0.049902915954589844
2023-01-23 00:06:16.047984: step: 1848/530, loss: 0.48249807953834534
2023-01-23 00:06:17.208814: step: 1852/530, loss: 0.12248983979225159
2023-01-23 00:06:18.373412: step: 1856/530, loss: 0.27883464097976685
2023-01-23 00:06:19.533399: step: 1860/530, loss: 0.22698427736759186
2023-01-23 00:06:20.663484: step: 1864/530, loss: 0.07895593345165253
2023-01-23 00:06:21.864848: step: 1868/530, loss: 0.0681583434343338
2023-01-23 00:06:22.991540: step: 1872/530, loss: 0.7056682705879211
2023-01-23 00:06:24.203097: step: 1876/530, loss: 0.18610867857933044
2023-01-23 00:06:25.364682: step: 1880/530, loss: 0.18651799857616425
2023-01-23 00:06:26.552508: step: 1884/530, loss: 0.16434498131275177
2023-01-23 00:06:27.720848: step: 1888/530, loss: 0.15267057716846466
2023-01-23 00:06:28.894582: step: 1892/530, loss: 0.0771174430847168
2023-01-23 00:06:30.080890: step: 1896/530, loss: 0.09339471161365509
2023-01-23 00:06:31.228487: step: 1900/530, loss: 0.16388359665870667
2023-01-23 00:06:32.390767: step: 1904/530, loss: 0.16738960146903992
2023-01-23 00:06:33.554402: step: 1908/530, loss: 0.08777789771556854
2023-01-23 00:06:34.731182: step: 1912/530, loss: 0.4378501772880554
2023-01-23 00:06:35.896216: step: 1916/530, loss: 0.06166696920990944
2023-01-23 00:06:37.065681: step: 1920/530, loss: 0.7372552156448364
2023-01-23 00:06:38.227930: step: 1924/530, loss: 0.11108008027076721
2023-01-23 00:06:39.364868: step: 1928/530, loss: 0.5482058525085449
2023-01-23 00:06:40.530658: step: 1932/530, loss: 1.5744177103042603
2023-01-23 00:06:41.754844: step: 1936/530, loss: 0.1304381787776947
2023-01-23 00:06:42.970218: step: 1940/530, loss: 0.11318016052246094
2023-01-23 00:06:44.189913: step: 1944/530, loss: 1.0561084747314453
2023-01-23 00:06:45.347937: step: 1948/530, loss: 0.07393427193164825
2023-01-23 00:06:46.574120: step: 1952/530, loss: 0.7130127549171448
2023-01-23 00:06:47.714145: step: 1956/530, loss: 0.6980878114700317
2023-01-23 00:06:48.874289: step: 1960/530, loss: 0.1762668639421463
2023-01-23 00:06:50.041521: step: 1964/530, loss: 0.03502092510461807
2023-01-23 00:06:51.187043: step: 1968/530, loss: 0.1391678750514984
2023-01-23 00:06:52.369499: step: 1972/530, loss: 0.1952962428331375
2023-01-23 00:06:53.570565: step: 1976/530, loss: 0.06770763546228409
2023-01-23 00:06:54.781648: step: 1980/530, loss: 0.8508750200271606
2023-01-23 00:06:55.966167: step: 1984/530, loss: 0.12318773567676544
2023-01-23 00:06:57.134771: step: 1988/530, loss: 0.9986238479614258
2023-01-23 00:06:58.289580: step: 1992/530, loss: 0.09084725379943848
2023-01-23 00:06:59.447654: step: 1996/530, loss: 0.10266299545764923
2023-01-23 00:07:00.646553: step: 2000/530, loss: 0.21593937277793884
2023-01-23 00:07:01.813629: step: 2004/530, loss: 0.10083504021167755
2023-01-23 00:07:02.997604: step: 2008/530, loss: 0.1104726791381836
2023-01-23 00:07:04.133251: step: 2012/530, loss: 0.4095633625984192
2023-01-23 00:07:05.308831: step: 2016/530, loss: 1.4537510871887207
2023-01-23 00:07:06.472487: step: 2020/530, loss: 0.1197938472032547
2023-01-23 00:07:07.691040: step: 2024/530, loss: 0.7745867967605591
2023-01-23 00:07:08.856909: step: 2028/530, loss: 6.381715774536133
2023-01-23 00:07:10.008075: step: 2032/530, loss: 0.19721823930740356
2023-01-23 00:07:11.151629: step: 2036/530, loss: 0.05052614212036133
2023-01-23 00:07:12.332885: step: 2040/530, loss: 0.36113440990448
2023-01-23 00:07:13.477720: step: 2044/530, loss: 0.1440139263868332
2023-01-23 00:07:14.669800: step: 2048/530, loss: 0.7743402719497681
2023-01-23 00:07:15.833125: step: 2052/530, loss: 1.2610583305358887
2023-01-23 00:07:17.007316: step: 2056/530, loss: 0.18929719924926758
2023-01-23 00:07:18.186451: step: 2060/530, loss: 0.7542743682861328
2023-01-23 00:07:19.346060: step: 2064/530, loss: 0.397914320230484
2023-01-23 00:07:20.534159: step: 2068/530, loss: 0.6517304182052612
2023-01-23 00:07:21.743528: step: 2072/530, loss: 0.22485850751399994
2023-01-23 00:07:22.943950: step: 2076/530, loss: 0.09159145504236221
2023-01-23 00:07:24.146420: step: 2080/530, loss: 0.1678951382637024
2023-01-23 00:07:25.401001: step: 2084/530, loss: 0.33813199400901794
2023-01-23 00:07:26.594563: step: 2088/530, loss: 0.2143198847770691
2023-01-23 00:07:27.759337: step: 2092/530, loss: 0.03416404873132706
2023-01-23 00:07:28.920892: step: 2096/530, loss: 0.10673792660236359
2023-01-23 00:07:30.100116: step: 2100/530, loss: 0.4254302978515625
2023-01-23 00:07:31.279971: step: 2104/530, loss: 0.5432438850402832
2023-01-23 00:07:32.450715: step: 2108/530, loss: 1.0999172925949097
2023-01-23 00:07:33.622740: step: 2112/530, loss: 1.4006919860839844
2023-01-23 00:07:34.821247: step: 2116/530, loss: 0.03751678392291069
2023-01-23 00:07:35.985513: step: 2120/530, loss: 0.13404826819896698
==================================================
Loss: 0.489
--------------------
Dev: {'event': {'p': 0.5815160955347871, 'r': 0.7456724367509987, 'f1': 0.6534422403733957}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Test: {'event': {'p': 0.604882459312839, 'r': 0.7694077055779184, 'f1': 0.6772968868640851}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Chinese: {'event': {'p': 0.5402298850574713, 'r': 0.8703703703703703, 'f1': 0.6666666666666666}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Korean: {'event': {'p': 0.6666666666666666, 'r': 0.6031746031746031, 'f1': 0.6333333333333333}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Russian: {'event': {'p': 0.5348837209302325, 'r': 0.6388888888888888, 'f1': 0.5822784810126581}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
New best chinese model...
New best korean model...
New best russian model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.5815160955347871, 'r': 0.7456724367509987, 'f1': 0.6534422403733957}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Chinese: {'event': {'p': 0.604882459312839, 'r': 0.7694077055779184, 'f1': 0.6772968868640851}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Chinese: {'event': {'p': 0.5402298850574713, 'r': 0.8703703703703703, 'f1': 0.6666666666666666}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5815160955347871, 'r': 0.7456724367509987, 'f1': 0.6534422403733957}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Korean: {'event': {'p': 0.604882459312839, 'r': 0.7694077055779184, 'f1': 0.6772968868640851}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Korean: {'event': {'p': 0.6666666666666666, 'r': 0.6031746031746031, 'f1': 0.6333333333333333}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5815160955347871, 'r': 0.7456724367509987, 'f1': 0.6534422403733957}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Russian: {'event': {'p': 0.604882459312839, 'r': 0.7694077055779184, 'f1': 0.6772968868640851}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Russian: {'event': {'p': 0.5348837209302325, 'r': 0.6388888888888888, 'f1': 0.5822784810126581}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
******************************
Epoch: 4
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 00:08:46.989004: step: 4/530, loss: 0.11504116654396057
2023-01-23 00:08:48.145265: step: 8/530, loss: 0.06309275329113007
2023-01-23 00:08:49.327314: step: 12/530, loss: 0.09863381087779999
2023-01-23 00:08:50.493865: step: 16/530, loss: 0.5618250966072083
2023-01-23 00:08:51.665730: step: 20/530, loss: 0.1564173698425293
2023-01-23 00:08:52.816950: step: 24/530, loss: 0.6172769665718079
2023-01-23 00:08:53.973816: step: 28/530, loss: 0.2684229016304016
2023-01-23 00:08:55.102235: step: 32/530, loss: 0.044142819941043854
2023-01-23 00:08:56.260547: step: 36/530, loss: 0.14958220720291138
2023-01-23 00:08:57.438752: step: 40/530, loss: 0.4937502145767212
2023-01-23 00:08:58.605629: step: 44/530, loss: 0.09656219184398651
2023-01-23 00:08:59.796316: step: 48/530, loss: 1.2072091102600098
2023-01-23 00:09:00.956280: step: 52/530, loss: 0.3203827738761902
2023-01-23 00:09:02.153566: step: 56/530, loss: 0.05738206207752228
2023-01-23 00:09:03.331551: step: 60/530, loss: 0.6830106973648071
2023-01-23 00:09:04.503102: step: 64/530, loss: 0.07570695877075195
2023-01-23 00:09:05.659719: step: 68/530, loss: 0.8050023913383484
2023-01-23 00:09:06.805915: step: 72/530, loss: 0.2043381780385971
2023-01-23 00:09:07.997650: step: 76/530, loss: 0.15033084154129028
2023-01-23 00:09:09.165461: step: 80/530, loss: 0.17330902814865112
2023-01-23 00:09:10.315657: step: 84/530, loss: 0.11402960121631622
2023-01-23 00:09:11.497209: step: 88/530, loss: 0.21889343857765198
2023-01-23 00:09:12.669470: step: 92/530, loss: 0.10188436508178711
2023-01-23 00:09:13.831146: step: 96/530, loss: 5.968746185302734
2023-01-23 00:09:14.986294: step: 100/530, loss: 0.3515448570251465
2023-01-23 00:09:16.150807: step: 104/530, loss: 0.1457379311323166
2023-01-23 00:09:17.373482: step: 108/530, loss: 0.10499868541955948
2023-01-23 00:09:18.515860: step: 112/530, loss: 0.0640534907579422
2023-01-23 00:09:19.683679: step: 116/530, loss: 0.33132266998291016
2023-01-23 00:09:20.881228: step: 120/530, loss: 0.11684933304786682
2023-01-23 00:09:22.070312: step: 124/530, loss: 0.37670737504959106
2023-01-23 00:09:23.235728: step: 128/530, loss: 0.44663944840431213
2023-01-23 00:09:24.384073: step: 132/530, loss: 0.4856053590774536
2023-01-23 00:09:25.526120: step: 136/530, loss: 0.09383507072925568
2023-01-23 00:09:26.692373: step: 140/530, loss: 0.1646944135427475
2023-01-23 00:09:27.867380: step: 144/530, loss: 0.24426832795143127
2023-01-23 00:09:29.036985: step: 148/530, loss: 0.3743099272251129
2023-01-23 00:09:30.178139: step: 152/530, loss: 0.18976593017578125
2023-01-23 00:09:31.370600: step: 156/530, loss: 0.21158257126808167
2023-01-23 00:09:32.536330: step: 160/530, loss: 0.6596651077270508
2023-01-23 00:09:33.713475: step: 164/530, loss: 0.2552119195461273
2023-01-23 00:09:34.891985: step: 168/530, loss: 0.46443405747413635
2023-01-23 00:09:36.080808: step: 172/530, loss: 0.06911134719848633
2023-01-23 00:09:37.246530: step: 176/530, loss: 0.3262357711791992
2023-01-23 00:09:38.431792: step: 180/530, loss: 0.12964554131031036
2023-01-23 00:09:39.566275: step: 184/530, loss: 1.215349555015564
2023-01-23 00:09:40.720658: step: 188/530, loss: 0.6032072901725769
2023-01-23 00:09:41.874226: step: 192/530, loss: 0.171454519033432
2023-01-23 00:09:43.036300: step: 196/530, loss: 0.22686359286308289
2023-01-23 00:09:44.212121: step: 200/530, loss: 0.09749040752649307
2023-01-23 00:09:45.408612: step: 204/530, loss: 0.8044226765632629
2023-01-23 00:09:46.596217: step: 208/530, loss: 0.09733162075281143
2023-01-23 00:09:47.793947: step: 212/530, loss: 0.1684611290693283
2023-01-23 00:09:48.972294: step: 216/530, loss: 0.6632862687110901
2023-01-23 00:09:50.123645: step: 220/530, loss: 0.6340490579605103
2023-01-23 00:09:51.272325: step: 224/530, loss: 0.058547019958496094
2023-01-23 00:09:52.443431: step: 228/530, loss: 0.6697985529899597
2023-01-23 00:09:53.637861: step: 232/530, loss: 0.21490922570228577
2023-01-23 00:09:54.827326: step: 236/530, loss: 0.24858587980270386
2023-01-23 00:09:55.992710: step: 240/530, loss: 0.018796920776367188
2023-01-23 00:09:57.199612: step: 244/530, loss: 0.15576982498168945
2023-01-23 00:09:58.380903: step: 248/530, loss: 0.04682798311114311
2023-01-23 00:09:59.545452: step: 252/530, loss: 0.25771158933639526
2023-01-23 00:10:00.726535: step: 256/530, loss: 0.10458288341760635
2023-01-23 00:10:01.907618: step: 260/530, loss: 0.09453883022069931
2023-01-23 00:10:03.097629: step: 264/530, loss: 0.41282740235328674
2023-01-23 00:10:04.311655: step: 268/530, loss: 0.40218687057495117
2023-01-23 00:10:05.487238: step: 272/530, loss: 0.3627673089504242
2023-01-23 00:10:06.660031: step: 276/530, loss: 0.03042449988424778
2023-01-23 00:10:07.829885: step: 280/530, loss: 0.15802831947803497
2023-01-23 00:10:08.997970: step: 284/530, loss: 0.45238763093948364
2023-01-23 00:10:10.150887: step: 288/530, loss: 0.20137998461723328
2023-01-23 00:10:11.321839: step: 292/530, loss: 0.09920788556337357
2023-01-23 00:10:12.458666: step: 296/530, loss: 0.10093660652637482
2023-01-23 00:10:13.705038: step: 300/530, loss: 0.06294488906860352
2023-01-23 00:10:14.905099: step: 304/530, loss: 0.1462322175502777
2023-01-23 00:10:16.059098: step: 308/530, loss: 0.09385000169277191
2023-01-23 00:10:17.252117: step: 312/530, loss: 0.1997065544128418
2023-01-23 00:10:18.447236: step: 316/530, loss: 0.26336878538131714
2023-01-23 00:10:19.628355: step: 320/530, loss: 0.13412360846996307
2023-01-23 00:10:20.784843: step: 324/530, loss: 0.27973833680152893
2023-01-23 00:10:21.991203: step: 328/530, loss: 0.734890878200531
2023-01-23 00:10:23.176891: step: 332/530, loss: 0.1044454574584961
2023-01-23 00:10:24.384021: step: 336/530, loss: 0.174531489610672
2023-01-23 00:10:25.535588: step: 340/530, loss: 0.27906572818756104
2023-01-23 00:10:26.705793: step: 344/530, loss: 0.1268673986196518
2023-01-23 00:10:27.854024: step: 348/530, loss: 0.08036752790212631
2023-01-23 00:10:29.015201: step: 352/530, loss: 0.08531427383422852
2023-01-23 00:10:30.154915: step: 356/530, loss: 0.14621086418628693
2023-01-23 00:10:31.302879: step: 360/530, loss: 0.16158372163772583
2023-01-23 00:10:32.499235: step: 364/530, loss: 1.0669214725494385
2023-01-23 00:10:33.674880: step: 368/530, loss: 0.0758119598031044
2023-01-23 00:10:34.846341: step: 372/530, loss: 0.19217178225517273
2023-01-23 00:10:36.040751: step: 376/530, loss: 0.28128406405448914
2023-01-23 00:10:37.269832: step: 380/530, loss: 0.17578107118606567
2023-01-23 00:10:38.419610: step: 384/530, loss: 0.13452312350273132
2023-01-23 00:10:39.620182: step: 388/530, loss: 0.3514425754547119
2023-01-23 00:10:40.789274: step: 392/530, loss: 0.17970696091651917
2023-01-23 00:10:41.950209: step: 396/530, loss: 0.1492437869310379
2023-01-23 00:10:43.159039: step: 400/530, loss: 0.09625058621168137
2023-01-23 00:10:44.301970: step: 404/530, loss: 0.38881435990333557
2023-01-23 00:10:45.465989: step: 408/530, loss: 0.0808505043387413
2023-01-23 00:10:46.681031: step: 412/530, loss: 0.532212495803833
2023-01-23 00:10:47.845694: step: 416/530, loss: 0.22090129554271698
2023-01-23 00:10:49.022601: step: 420/530, loss: 0.31859293580055237
2023-01-23 00:10:50.209505: step: 424/530, loss: 0.656646192073822
2023-01-23 00:10:51.357303: step: 428/530, loss: 0.05401954799890518
2023-01-23 00:10:52.536779: step: 432/530, loss: 0.47288310527801514
2023-01-23 00:10:53.723983: step: 436/530, loss: 0.05650625377893448
2023-01-23 00:10:54.935553: step: 440/530, loss: 0.030762672424316406
2023-01-23 00:10:56.121600: step: 444/530, loss: 0.14616747200489044
2023-01-23 00:10:57.290869: step: 448/530, loss: 0.1826891303062439
2023-01-23 00:10:58.417108: step: 452/530, loss: 0.14718708395957947
2023-01-23 00:10:59.573433: step: 456/530, loss: 0.03799152374267578
2023-01-23 00:11:00.733675: step: 460/530, loss: 0.10636691749095917
2023-01-23 00:11:01.927771: step: 464/530, loss: 0.08111181855201721
2023-01-23 00:11:03.088452: step: 468/530, loss: 0.15735287964344025
2023-01-23 00:11:04.273505: step: 472/530, loss: 0.3596492409706116
2023-01-23 00:11:05.420681: step: 476/530, loss: 0.6144568920135498
2023-01-23 00:11:06.578776: step: 480/530, loss: 0.09223838150501251
2023-01-23 00:11:07.736500: step: 484/530, loss: 0.6614484786987305
2023-01-23 00:11:08.986824: step: 488/530, loss: 0.14772701263427734
2023-01-23 00:11:10.161684: step: 492/530, loss: 0.5365071296691895
2023-01-23 00:11:11.325626: step: 496/530, loss: 0.09287528693675995
2023-01-23 00:11:12.521926: step: 500/530, loss: 0.22825641930103302
2023-01-23 00:11:13.728762: step: 504/530, loss: 0.14748725295066833
2023-01-23 00:11:14.869275: step: 508/530, loss: 0.7564055323600769
2023-01-23 00:11:16.084393: step: 512/530, loss: 0.12780657410621643
2023-01-23 00:11:17.263060: step: 516/530, loss: 0.10014358162879944
2023-01-23 00:11:18.415430: step: 520/530, loss: 0.06992387771606445
2023-01-23 00:11:19.606169: step: 524/530, loss: 2.1496894359588623
2023-01-23 00:11:20.800537: step: 528/530, loss: 0.21606865525245667
2023-01-23 00:11:21.980743: step: 532/530, loss: 0.2792799770832062
2023-01-23 00:11:23.141743: step: 536/530, loss: 0.06187028810381889
2023-01-23 00:11:24.617194: step: 540/530, loss: 0.7613747119903564
2023-01-23 00:11:25.815329: step: 544/530, loss: 0.17714548110961914
2023-01-23 00:11:27.012568: step: 548/530, loss: 0.42918330430984497
2023-01-23 00:11:28.221697: step: 552/530, loss: 0.45491230487823486
2023-01-23 00:11:29.417518: step: 556/530, loss: 0.13996772468090057
2023-01-23 00:11:30.559153: step: 560/530, loss: 0.22470645606517792
2023-01-23 00:11:31.704502: step: 564/530, loss: 2.121541976928711
2023-01-23 00:11:32.843503: step: 568/530, loss: 0.4491124749183655
2023-01-23 00:11:34.031586: step: 572/530, loss: 1.3248398303985596
2023-01-23 00:11:35.188259: step: 576/530, loss: 0.17816373705863953
2023-01-23 00:11:36.329344: step: 580/530, loss: 0.1453545093536377
2023-01-23 00:11:37.517557: step: 584/530, loss: 0.6703928112983704
2023-01-23 00:11:38.694467: step: 588/530, loss: 0.6087626218795776
2023-01-23 00:11:39.846059: step: 592/530, loss: 0.21685227751731873
2023-01-23 00:11:41.063646: step: 596/530, loss: 0.8628969192504883
2023-01-23 00:11:42.259699: step: 600/530, loss: 0.15690821409225464
2023-01-23 00:11:43.432079: step: 604/530, loss: 0.0886748805642128
2023-01-23 00:11:44.612192: step: 608/530, loss: 0.4433382749557495
2023-01-23 00:11:45.788363: step: 612/530, loss: 0.10240907967090607
2023-01-23 00:11:46.976522: step: 616/530, loss: 0.1817978024482727
2023-01-23 00:11:48.117044: step: 620/530, loss: 0.05534829944372177
2023-01-23 00:11:49.382067: step: 624/530, loss: 0.19148457050323486
2023-01-23 00:11:50.537105: step: 628/530, loss: 0.06290941685438156
2023-01-23 00:11:51.753277: step: 632/530, loss: 1.065185546875
2023-01-23 00:11:52.923902: step: 636/530, loss: 0.1368924081325531
2023-01-23 00:11:54.081854: step: 640/530, loss: 0.8383713960647583
2023-01-23 00:11:55.266703: step: 644/530, loss: 0.061547040939331055
2023-01-23 00:11:56.449697: step: 648/530, loss: 0.8709843754768372
2023-01-23 00:11:57.604620: step: 652/530, loss: 0.21643005311489105
2023-01-23 00:11:58.773985: step: 656/530, loss: 0.037795353680849075
2023-01-23 00:11:59.926078: step: 660/530, loss: 0.12889054417610168
2023-01-23 00:12:01.074680: step: 664/530, loss: 0.08923659473657608
2023-01-23 00:12:02.215708: step: 668/530, loss: 0.06104845926165581
2023-01-23 00:12:03.387624: step: 672/530, loss: 0.13848777115345
2023-01-23 00:12:04.570049: step: 676/530, loss: 0.44145089387893677
2023-01-23 00:12:05.718593: step: 680/530, loss: 0.07453594356775284
2023-01-23 00:12:06.891771: step: 684/530, loss: 0.1856156885623932
2023-01-23 00:12:08.054643: step: 688/530, loss: 0.2627621591091156
2023-01-23 00:12:09.256830: step: 692/530, loss: 0.4242572784423828
2023-01-23 00:12:10.426823: step: 696/530, loss: 0.1434219479560852
2023-01-23 00:12:11.559436: step: 700/530, loss: 6.147243022918701
2023-01-23 00:12:12.730670: step: 704/530, loss: 0.08329696953296661
2023-01-23 00:12:13.900263: step: 708/530, loss: 0.08801408112049103
2023-01-23 00:12:15.068478: step: 712/530, loss: 0.6760218739509583
2023-01-23 00:12:16.225695: step: 716/530, loss: 0.07385663688182831
2023-01-23 00:12:17.397309: step: 720/530, loss: 1.380645751953125
2023-01-23 00:12:18.582790: step: 724/530, loss: 0.9720660448074341
2023-01-23 00:12:19.755829: step: 728/530, loss: 1.3602497577667236
2023-01-23 00:12:20.907124: step: 732/530, loss: 0.019658852368593216
2023-01-23 00:12:22.069292: step: 736/530, loss: 0.0592009574174881
2023-01-23 00:12:23.244212: step: 740/530, loss: 0.440293550491333
2023-01-23 00:12:24.377208: step: 744/530, loss: 0.042652323842048645
2023-01-23 00:12:25.547576: step: 748/530, loss: 0.29746943712234497
2023-01-23 00:12:26.744337: step: 752/530, loss: 0.11276054382324219
2023-01-23 00:12:27.897959: step: 756/530, loss: 0.08613958954811096
2023-01-23 00:12:29.062179: step: 760/530, loss: 0.8293267488479614
2023-01-23 00:12:30.251032: step: 764/530, loss: 0.43857520818710327
2023-01-23 00:12:31.409840: step: 768/530, loss: 0.11570611596107483
2023-01-23 00:12:32.594256: step: 772/530, loss: 0.0676707774400711
2023-01-23 00:12:33.768446: step: 776/530, loss: 0.16486911475658417
2023-01-23 00:12:34.984582: step: 780/530, loss: 0.1847650408744812
2023-01-23 00:12:36.146856: step: 784/530, loss: 0.3430578112602234
2023-01-23 00:12:37.298970: step: 788/530, loss: 0.13232699036598206
2023-01-23 00:12:38.486916: step: 792/530, loss: 0.07170705497264862
2023-01-23 00:12:39.683775: step: 796/530, loss: 0.20572510361671448
2023-01-23 00:12:40.843119: step: 800/530, loss: 0.3940994143486023
2023-01-23 00:12:41.969636: step: 804/530, loss: 0.05810442194342613
2023-01-23 00:12:43.121889: step: 808/530, loss: 0.7176900506019592
2023-01-23 00:12:44.304852: step: 812/530, loss: 0.2623118460178375
2023-01-23 00:12:45.488198: step: 816/530, loss: 0.14615269005298615
2023-01-23 00:12:46.704980: step: 820/530, loss: 0.9185382127761841
2023-01-23 00:12:47.861611: step: 824/530, loss: 0.10808901488780975
2023-01-23 00:12:49.012566: step: 828/530, loss: 0.04682669788599014
2023-01-23 00:12:50.170109: step: 832/530, loss: 0.11039677262306213
2023-01-23 00:12:51.353683: step: 836/530, loss: 0.7290699481964111
2023-01-23 00:12:52.530032: step: 840/530, loss: 0.3871700167655945
2023-01-23 00:12:53.697692: step: 844/530, loss: 0.11321544647216797
2023-01-23 00:12:54.862594: step: 848/530, loss: 0.35745924711227417
2023-01-23 00:12:56.038012: step: 852/530, loss: 0.1340000182390213
2023-01-23 00:12:57.201299: step: 856/530, loss: 0.12056718021631241
2023-01-23 00:12:58.379225: step: 860/530, loss: 0.11855802685022354
2023-01-23 00:12:59.509140: step: 864/530, loss: 0.20643272995948792
2023-01-23 00:13:00.690069: step: 868/530, loss: 0.10815267264842987
2023-01-23 00:13:01.865017: step: 872/530, loss: 0.2466880828142166
2023-01-23 00:13:03.058755: step: 876/530, loss: 0.18173113465309143
2023-01-23 00:13:04.226690: step: 880/530, loss: 0.1590673327445984
2023-01-23 00:13:05.384006: step: 884/530, loss: 0.06208677217364311
2023-01-23 00:13:06.549651: step: 888/530, loss: 0.7460730671882629
2023-01-23 00:13:07.713773: step: 892/530, loss: 0.2585233747959137
2023-01-23 00:13:08.911445: step: 896/530, loss: 0.4020500183105469
2023-01-23 00:13:10.087994: step: 900/530, loss: 0.1591947078704834
2023-01-23 00:13:11.271542: step: 904/530, loss: 1.4053617715835571
2023-01-23 00:13:12.494225: step: 908/530, loss: 0.1977907121181488
2023-01-23 00:13:13.679266: step: 912/530, loss: 0.012968683615326881
2023-01-23 00:13:14.882458: step: 916/530, loss: 1.5474811792373657
2023-01-23 00:13:16.008780: step: 920/530, loss: 0.12492141127586365
2023-01-23 00:13:17.211010: step: 924/530, loss: 0.5811511874198914
2023-01-23 00:13:18.382517: step: 928/530, loss: 1.5806465148925781
2023-01-23 00:13:19.598566: step: 932/530, loss: 0.3058616518974304
2023-01-23 00:13:20.766394: step: 936/530, loss: 0.4506802558898926
2023-01-23 00:13:21.931232: step: 940/530, loss: 0.10405564308166504
2023-01-23 00:13:23.087109: step: 944/530, loss: 0.15208196640014648
2023-01-23 00:13:24.256169: step: 948/530, loss: 0.20085574686527252
2023-01-23 00:13:25.415834: step: 952/530, loss: 0.6145564317703247
2023-01-23 00:13:26.618257: step: 956/530, loss: 0.23521976172924042
2023-01-23 00:13:27.756665: step: 960/530, loss: 0.11118493229150772
2023-01-23 00:13:28.957654: step: 964/530, loss: 0.62773197889328
2023-01-23 00:13:30.143131: step: 968/530, loss: 0.6872185468673706
2023-01-23 00:13:31.285804: step: 972/530, loss: 0.5629729628562927
2023-01-23 00:13:32.473997: step: 976/530, loss: 0.11141099780797958
2023-01-23 00:13:33.660020: step: 980/530, loss: 0.3977198600769043
2023-01-23 00:13:34.808740: step: 984/530, loss: 0.1435260772705078
2023-01-23 00:13:35.969663: step: 988/530, loss: 0.3222193717956543
2023-01-23 00:13:37.146645: step: 992/530, loss: 0.21869002282619476
2023-01-23 00:13:38.336694: step: 996/530, loss: 1.8919576406478882
2023-01-23 00:13:39.512908: step: 1000/530, loss: 0.09504786133766174
2023-01-23 00:13:40.682413: step: 1004/530, loss: 0.18802037835121155
2023-01-23 00:13:41.874072: step: 1008/530, loss: 0.09015903621912003
2023-01-23 00:13:43.048517: step: 1012/530, loss: 0.36191725730895996
2023-01-23 00:13:44.247517: step: 1016/530, loss: 0.24782609939575195
2023-01-23 00:13:45.439795: step: 1020/530, loss: 0.6134856343269348
2023-01-23 00:13:46.626039: step: 1024/530, loss: 0.10214006900787354
2023-01-23 00:13:47.787993: step: 1028/530, loss: 0.18128728866577148
2023-01-23 00:13:48.967074: step: 1032/530, loss: 0.2213192880153656
2023-01-23 00:13:50.133854: step: 1036/530, loss: 0.15866489708423615
2023-01-23 00:13:51.328506: step: 1040/530, loss: 0.4899576008319855
2023-01-23 00:13:52.509515: step: 1044/530, loss: 0.29335105419158936
2023-01-23 00:13:53.723908: step: 1048/530, loss: 0.2760809361934662
2023-01-23 00:13:54.862571: step: 1052/530, loss: 0.5233360528945923
2023-01-23 00:13:56.029628: step: 1056/530, loss: 5.769775867462158
2023-01-23 00:13:57.232770: step: 1060/530, loss: 0.1736261397600174
2023-01-23 00:13:58.405147: step: 1064/530, loss: 0.3277997076511383
2023-01-23 00:13:59.639920: step: 1068/530, loss: 0.39767369627952576
2023-01-23 00:14:00.813498: step: 1072/530, loss: 0.5014529228210449
2023-01-23 00:14:02.002464: step: 1076/530, loss: 0.061091043055057526
2023-01-23 00:14:03.187304: step: 1080/530, loss: 0.13750171661376953
2023-01-23 00:14:04.376171: step: 1084/530, loss: 0.3384150564670563
2023-01-23 00:14:05.583728: step: 1088/530, loss: 0.7358753681182861
2023-01-23 00:14:06.738606: step: 1092/530, loss: 0.007086849771440029
2023-01-23 00:14:07.890950: step: 1096/530, loss: 0.02338133007287979
2023-01-23 00:14:09.055558: step: 1100/530, loss: 0.05637001991271973
2023-01-23 00:14:10.223435: step: 1104/530, loss: 0.07068271934986115
2023-01-23 00:14:11.371601: step: 1108/530, loss: 0.04919151961803436
2023-01-23 00:14:12.553524: step: 1112/530, loss: 0.09694957733154297
2023-01-23 00:14:13.733180: step: 1116/530, loss: 0.1630798876285553
2023-01-23 00:14:14.901692: step: 1120/530, loss: 0.26954078674316406
2023-01-23 00:14:16.075290: step: 1124/530, loss: 0.059223368763923645
2023-01-23 00:14:17.203578: step: 1128/530, loss: 0.0944088026881218
2023-01-23 00:14:18.382692: step: 1132/530, loss: 0.24949723482131958
2023-01-23 00:14:19.538622: step: 1136/530, loss: 0.3163944482803345
2023-01-23 00:14:20.680455: step: 1140/530, loss: 0.09070412814617157
2023-01-23 00:14:21.840523: step: 1144/530, loss: 0.10538311302661896
2023-01-23 00:14:22.992960: step: 1148/530, loss: 0.7500730156898499
2023-01-23 00:14:24.139583: step: 1152/530, loss: 0.5823000073432922
2023-01-23 00:14:25.298993: step: 1156/530, loss: 0.7672036290168762
2023-01-23 00:14:26.482852: step: 1160/530, loss: 0.8219207525253296
2023-01-23 00:14:27.621512: step: 1164/530, loss: 0.17678271234035492
2023-01-23 00:14:28.800032: step: 1168/530, loss: 0.14983662962913513
2023-01-23 00:14:29.944654: step: 1172/530, loss: 1.63259756565094
2023-01-23 00:14:31.117266: step: 1176/530, loss: 0.02857823483645916
2023-01-23 00:14:32.293570: step: 1180/530, loss: 0.3964815139770508
2023-01-23 00:14:33.462643: step: 1184/530, loss: 0.22624412178993225
2023-01-23 00:14:34.635769: step: 1188/530, loss: 0.12240705639123917
2023-01-23 00:14:35.772715: step: 1192/530, loss: 0.25912541151046753
2023-01-23 00:14:36.918202: step: 1196/530, loss: 0.1371825635433197
2023-01-23 00:14:38.098635: step: 1200/530, loss: 0.12665843963623047
2023-01-23 00:14:39.319058: step: 1204/530, loss: 0.158858984708786
2023-01-23 00:14:40.477519: step: 1208/530, loss: 0.20194588601589203
2023-01-23 00:14:41.658803: step: 1212/530, loss: 0.04982004314661026
2023-01-23 00:14:42.849353: step: 1216/530, loss: 0.10423240810632706
2023-01-23 00:14:44.070493: step: 1220/530, loss: 0.6155378222465515
2023-01-23 00:14:45.226122: step: 1224/530, loss: 0.19012776017189026
2023-01-23 00:14:46.414119: step: 1228/530, loss: 0.4747328758239746
2023-01-23 00:14:47.607902: step: 1232/530, loss: 0.06692662835121155
2023-01-23 00:14:48.790381: step: 1236/530, loss: 0.12054071575403214
2023-01-23 00:14:49.947263: step: 1240/530, loss: 0.08538446575403214
2023-01-23 00:14:51.101080: step: 1244/530, loss: 0.04577126353979111
2023-01-23 00:14:52.260153: step: 1248/530, loss: 0.6697562336921692
2023-01-23 00:14:53.448183: step: 1252/530, loss: 0.30219078063964844
2023-01-23 00:14:54.622101: step: 1256/530, loss: 2.5943663120269775
2023-01-23 00:14:55.793965: step: 1260/530, loss: 0.663166880607605
2023-01-23 00:14:56.950787: step: 1264/530, loss: 1.2769330739974976
2023-01-23 00:14:58.103118: step: 1268/530, loss: 0.0529206246137619
2023-01-23 00:14:59.267549: step: 1272/530, loss: 0.6857399940490723
2023-01-23 00:15:00.437022: step: 1276/530, loss: 0.4165101945400238
2023-01-23 00:15:01.628764: step: 1280/530, loss: 0.055531978607177734
2023-01-23 00:15:02.768530: step: 1284/530, loss: 0.02820272371172905
2023-01-23 00:15:03.956181: step: 1288/530, loss: 0.11238012462854385
2023-01-23 00:15:05.147085: step: 1292/530, loss: 0.31934604048728943
2023-01-23 00:15:06.312005: step: 1296/530, loss: 0.5369474291801453
2023-01-23 00:15:07.482816: step: 1300/530, loss: 0.5376827120780945
2023-01-23 00:15:08.656721: step: 1304/530, loss: 0.1251607984304428
2023-01-23 00:15:09.784485: step: 1308/530, loss: 0.4383469521999359
2023-01-23 00:15:10.991299: step: 1312/530, loss: 0.210774764418602
2023-01-23 00:15:12.157661: step: 1316/530, loss: 0.1215600073337555
2023-01-23 00:15:13.324055: step: 1320/530, loss: 0.09589624404907227
2023-01-23 00:15:14.505172: step: 1324/530, loss: 0.09111233055591583
2023-01-23 00:15:15.661389: step: 1328/530, loss: 0.5435773730278015
2023-01-23 00:15:16.815383: step: 1332/530, loss: 0.17810040712356567
2023-01-23 00:15:18.014857: step: 1336/530, loss: 0.12381229549646378
2023-01-23 00:15:19.197079: step: 1340/530, loss: 0.23709706962108612
2023-01-23 00:15:20.352248: step: 1344/530, loss: 0.5032418370246887
2023-01-23 00:15:21.523770: step: 1348/530, loss: 0.12311534583568573
2023-01-23 00:15:22.721684: step: 1352/530, loss: 0.06642594933509827
2023-01-23 00:15:23.887754: step: 1356/530, loss: 0.5493218302726746
2023-01-23 00:15:25.057551: step: 1360/530, loss: 0.35551726818084717
2023-01-23 00:15:26.246348: step: 1364/530, loss: 0.9286425113677979
2023-01-23 00:15:27.480538: step: 1368/530, loss: 0.1363869607448578
2023-01-23 00:15:28.649394: step: 1372/530, loss: 0.3926301896572113
2023-01-23 00:15:29.828349: step: 1376/530, loss: 0.07898598909378052
2023-01-23 00:15:30.992073: step: 1380/530, loss: 0.10672781616449356
2023-01-23 00:15:32.165162: step: 1384/530, loss: 0.1182304322719574
2023-01-23 00:15:33.370127: step: 1388/530, loss: 0.1244884580373764
2023-01-23 00:15:34.535462: step: 1392/530, loss: 0.05201368406414986
2023-01-23 00:15:35.689394: step: 1396/530, loss: 0.9493787884712219
2023-01-23 00:15:36.881788: step: 1400/530, loss: 0.24087773263454437
2023-01-23 00:15:38.023216: step: 1404/530, loss: 0.1619156301021576
2023-01-23 00:15:39.186579: step: 1408/530, loss: 0.9481672048568726
2023-01-23 00:15:40.365266: step: 1412/530, loss: 3.5004217624664307
2023-01-23 00:15:41.527289: step: 1416/530, loss: 0.4147112965583801
2023-01-23 00:15:42.730458: step: 1420/530, loss: 0.46288469433784485
2023-01-23 00:15:43.920635: step: 1424/530, loss: 0.23620863258838654
2023-01-23 00:15:45.095234: step: 1428/530, loss: 0.7061934471130371
2023-01-23 00:15:46.249464: step: 1432/530, loss: 0.194000244140625
2023-01-23 00:15:47.408476: step: 1436/530, loss: 0.1050286814570427
2023-01-23 00:15:48.565520: step: 1440/530, loss: 3.008226156234741
2023-01-23 00:15:49.723638: step: 1444/530, loss: 0.10117876529693604
2023-01-23 00:15:50.890083: step: 1448/530, loss: 0.5418194532394409
2023-01-23 00:15:52.052182: step: 1452/530, loss: 0.34288740158081055
2023-01-23 00:15:53.230259: step: 1456/530, loss: 0.12918530404567719
2023-01-23 00:15:54.409749: step: 1460/530, loss: 0.11440548300743103
2023-01-23 00:15:55.633801: step: 1464/530, loss: 0.2064371109008789
2023-01-23 00:15:56.796281: step: 1468/530, loss: 0.14081747829914093
2023-01-23 00:15:57.969136: step: 1472/530, loss: 0.3588187098503113
2023-01-23 00:15:59.201561: step: 1476/530, loss: 0.29937463998794556
2023-01-23 00:16:00.454725: step: 1480/530, loss: 0.7840123772621155
2023-01-23 00:16:01.652816: step: 1484/530, loss: 0.22346076369285583
2023-01-23 00:16:02.849773: step: 1488/530, loss: 0.06924515217542648
2023-01-23 00:16:04.053505: step: 1492/530, loss: 0.12561869621276855
2023-01-23 00:16:05.285516: step: 1496/530, loss: 0.1489323526620865
2023-01-23 00:16:06.455626: step: 1500/530, loss: 0.13118305802345276
2023-01-23 00:16:07.655333: step: 1504/530, loss: 0.23313789069652557
2023-01-23 00:16:08.820444: step: 1508/530, loss: 0.7606579065322876
2023-01-23 00:16:10.003366: step: 1512/530, loss: 0.11915197968482971
2023-01-23 00:16:11.177761: step: 1516/530, loss: 0.20468683540821075
2023-01-23 00:16:12.343790: step: 1520/530, loss: 0.6620468497276306
2023-01-23 00:16:13.487057: step: 1524/530, loss: 0.425516813993454
2023-01-23 00:16:14.680402: step: 1528/530, loss: 0.1416490077972412
2023-01-23 00:16:15.869573: step: 1532/530, loss: 0.08876609802246094
2023-01-23 00:16:17.063306: step: 1536/530, loss: 0.8533191084861755
2023-01-23 00:16:18.216959: step: 1540/530, loss: 0.5719424486160278
2023-01-23 00:16:19.383197: step: 1544/530, loss: 0.09907753765583038
2023-01-23 00:16:20.550523: step: 1548/530, loss: 0.5311188101768494
2023-01-23 00:16:21.770513: step: 1552/530, loss: 0.15549631416797638
2023-01-23 00:16:22.921233: step: 1556/530, loss: 0.11470623314380646
2023-01-23 00:16:24.096503: step: 1560/530, loss: 0.41116294264793396
2023-01-23 00:16:25.251995: step: 1564/530, loss: 0.03378927707672119
2023-01-23 00:16:26.415847: step: 1568/530, loss: 0.16743439435958862
2023-01-23 00:16:27.549150: step: 1572/530, loss: 0.8020839095115662
2023-01-23 00:16:28.754784: step: 1576/530, loss: 1.9527747631072998
2023-01-23 00:16:29.984477: step: 1580/530, loss: 0.7834170460700989
2023-01-23 00:16:31.158950: step: 1584/530, loss: 2.078089475631714
2023-01-23 00:16:32.309495: step: 1588/530, loss: 4.242259979248047
2023-01-23 00:16:33.497634: step: 1592/530, loss: 0.2521018981933594
2023-01-23 00:16:34.740100: step: 1596/530, loss: 0.8832618594169617
2023-01-23 00:16:35.908473: step: 1600/530, loss: 0.10305547714233398
2023-01-23 00:16:37.130831: step: 1604/530, loss: 0.5106960535049438
2023-01-23 00:16:38.298991: step: 1608/530, loss: 0.5067201256752014
2023-01-23 00:16:39.484839: step: 1612/530, loss: 0.11851165443658829
2023-01-23 00:16:40.657670: step: 1616/530, loss: 0.3757248818874359
2023-01-23 00:16:41.871882: step: 1620/530, loss: 0.1681934893131256
2023-01-23 00:16:43.085573: step: 1624/530, loss: 0.18481120467185974
2023-01-23 00:16:44.275543: step: 1628/530, loss: 0.25032997131347656
2023-01-23 00:16:45.476589: step: 1632/530, loss: 0.3608000874519348
2023-01-23 00:16:46.662805: step: 1636/530, loss: 0.07576942443847656
2023-01-23 00:16:47.868947: step: 1640/530, loss: 0.0660221129655838
2023-01-23 00:16:49.026816: step: 1644/530, loss: 0.7730379104614258
2023-01-23 00:16:50.192679: step: 1648/530, loss: 0.09511657059192657
2023-01-23 00:16:51.333969: step: 1652/530, loss: 0.14469321072101593
2023-01-23 00:16:52.524595: step: 1656/530, loss: 0.2972152829170227
2023-01-23 00:16:53.729500: step: 1660/530, loss: 0.26963576674461365
2023-01-23 00:16:54.961608: step: 1664/530, loss: 0.22328528761863708
2023-01-23 00:16:56.098386: step: 1668/530, loss: 0.13425616919994354
2023-01-23 00:16:57.283488: step: 1672/530, loss: 0.6168160438537598
2023-01-23 00:16:58.449141: step: 1676/530, loss: 0.1291390359401703
2023-01-23 00:16:59.659214: step: 1680/530, loss: 0.23894159495830536
2023-01-23 00:17:00.825948: step: 1684/530, loss: 0.2600872218608856
2023-01-23 00:17:01.997523: step: 1688/530, loss: 0.0597049742937088
2023-01-23 00:17:03.202216: step: 1692/530, loss: 0.5511213541030884
2023-01-23 00:17:04.374902: step: 1696/530, loss: 0.20396548509597778
2023-01-23 00:17:05.550963: step: 1700/530, loss: 0.4653128683567047
2023-01-23 00:17:06.720975: step: 1704/530, loss: 0.188886359333992
2023-01-23 00:17:07.871729: step: 1708/530, loss: 0.18251438438892365
2023-01-23 00:17:09.038683: step: 1712/530, loss: 0.7329471707344055
2023-01-23 00:17:10.261242: step: 1716/530, loss: 0.20204153656959534
2023-01-23 00:17:11.454655: step: 1720/530, loss: 0.14072594046592712
2023-01-23 00:17:12.599464: step: 1724/530, loss: 0.037955284118652344
2023-01-23 00:17:13.754774: step: 1728/530, loss: 0.20351390540599823
2023-01-23 00:17:14.908369: step: 1732/530, loss: 0.06529121100902557
2023-01-23 00:17:16.107906: step: 1736/530, loss: 0.21798400580883026
2023-01-23 00:17:17.278470: step: 1740/530, loss: 0.08946972340345383
2023-01-23 00:17:18.461057: step: 1744/530, loss: 0.05043621361255646
2023-01-23 00:17:19.645658: step: 1748/530, loss: 1.1845881938934326
2023-01-23 00:17:20.808182: step: 1752/530, loss: 0.29368191957473755
2023-01-23 00:17:22.058144: step: 1756/530, loss: 0.11359748989343643
2023-01-23 00:17:23.238398: step: 1760/530, loss: 0.052796266973018646
2023-01-23 00:17:24.396603: step: 1764/530, loss: 0.14209671318531036
2023-01-23 00:17:25.583303: step: 1768/530, loss: 0.22507619857788086
2023-01-23 00:17:26.751848: step: 1772/530, loss: 0.07884450256824493
2023-01-23 00:17:27.950724: step: 1776/530, loss: 0.6319993734359741
2023-01-23 00:17:29.145308: step: 1780/530, loss: 0.18795561790466309
2023-01-23 00:17:30.330228: step: 1784/530, loss: 1.055540919303894
2023-01-23 00:17:31.502847: step: 1788/530, loss: 0.12289538979530334
2023-01-23 00:17:32.667108: step: 1792/530, loss: 0.08245712518692017
2023-01-23 00:17:33.833156: step: 1796/530, loss: 0.15867328643798828
2023-01-23 00:17:35.034249: step: 1800/530, loss: 3.0935540199279785
2023-01-23 00:17:36.198643: step: 1804/530, loss: 0.09221392124891281
2023-01-23 00:17:37.365259: step: 1808/530, loss: 0.11634808033704758
2023-01-23 00:17:38.517029: step: 1812/530, loss: 0.24961858987808228
2023-01-23 00:17:39.670391: step: 1816/530, loss: 0.09525594860315323
2023-01-23 00:17:40.844212: step: 1820/530, loss: 0.05817709118127823
2023-01-23 00:17:41.976501: step: 1824/530, loss: 0.1496649831533432
2023-01-23 00:17:43.162865: step: 1828/530, loss: 0.5378350019454956
2023-01-23 00:17:44.360989: step: 1832/530, loss: 0.49689018726348877
2023-01-23 00:17:45.578247: step: 1836/530, loss: 0.3616853654384613
2023-01-23 00:17:46.754246: step: 1840/530, loss: 0.1608024686574936
2023-01-23 00:17:47.919540: step: 1844/530, loss: 2.896019220352173
2023-01-23 00:17:49.090432: step: 1848/530, loss: 0.09119803458452225
2023-01-23 00:17:50.249932: step: 1852/530, loss: 0.8853521347045898
2023-01-23 00:17:51.427875: step: 1856/530, loss: 0.12750062346458435
2023-01-23 00:17:52.578492: step: 1860/530, loss: 0.10769052803516388
2023-01-23 00:17:53.779712: step: 1864/530, loss: 0.28071194887161255
2023-01-23 00:17:54.954736: step: 1868/530, loss: 0.20003385841846466
2023-01-23 00:17:56.159387: step: 1872/530, loss: 0.15764674544334412
2023-01-23 00:17:57.337400: step: 1876/530, loss: 0.0467165932059288
2023-01-23 00:17:58.519809: step: 1880/530, loss: 0.10866604000329971
2023-01-23 00:17:59.679319: step: 1884/530, loss: 0.06531929969787598
2023-01-23 00:18:00.866104: step: 1888/530, loss: 0.4032400846481323
2023-01-23 00:18:02.079648: step: 1892/530, loss: 1.275505781173706
2023-01-23 00:18:03.244902: step: 1896/530, loss: 0.09643135219812393
2023-01-23 00:18:04.409813: step: 1900/530, loss: 0.24523526430130005
2023-01-23 00:18:05.563238: step: 1904/530, loss: 0.6152757406234741
2023-01-23 00:18:06.755133: step: 1908/530, loss: 0.12115345895290375
2023-01-23 00:18:07.948094: step: 1912/530, loss: 0.4646051526069641
2023-01-23 00:18:09.126386: step: 1916/530, loss: 0.26571282744407654
2023-01-23 00:18:10.311440: step: 1920/530, loss: 4.496382236480713
2023-01-23 00:18:11.526582: step: 1924/530, loss: 0.2892496883869171
2023-01-23 00:18:12.720080: step: 1928/530, loss: 0.04979410022497177
2023-01-23 00:18:13.899039: step: 1932/530, loss: 0.15090861916542053
2023-01-23 00:18:15.065083: step: 1936/530, loss: 2.8883774280548096
2023-01-23 00:18:16.235600: step: 1940/530, loss: 0.5007055401802063
2023-01-23 00:18:17.414543: step: 1944/530, loss: 0.1410520076751709
2023-01-23 00:18:18.535245: step: 1948/530, loss: 0.10281658172607422
2023-01-23 00:18:19.719759: step: 1952/530, loss: 0.39216700196266174
2023-01-23 00:18:20.925333: step: 1956/530, loss: 0.07823190093040466
2023-01-23 00:18:22.103877: step: 1960/530, loss: 0.11733589321374893
2023-01-23 00:18:23.262509: step: 1964/530, loss: 0.42570310831069946
2023-01-23 00:18:24.431523: step: 1968/530, loss: 0.46419888734817505
2023-01-23 00:18:25.617233: step: 1972/530, loss: 0.8393044471740723
2023-01-23 00:18:26.779238: step: 1976/530, loss: 0.14136143028736115
2023-01-23 00:18:27.940662: step: 1980/530, loss: 0.06731953471899033
2023-01-23 00:18:29.110991: step: 1984/530, loss: 0.2783690392971039
2023-01-23 00:18:30.288557: step: 1988/530, loss: 0.27179956436157227
2023-01-23 00:18:31.496584: step: 1992/530, loss: 0.3230404853820801
2023-01-23 00:18:32.635756: step: 1996/530, loss: 0.25934526324272156
2023-01-23 00:18:33.789674: step: 2000/530, loss: 0.19412866234779358
2023-01-23 00:18:34.969595: step: 2004/530, loss: 0.15328970551490784
2023-01-23 00:18:36.162787: step: 2008/530, loss: 0.08714685589075089
2023-01-23 00:18:37.354520: step: 2012/530, loss: 0.2520124316215515
2023-01-23 00:18:38.525907: step: 2016/530, loss: 0.09703502804040909
2023-01-23 00:18:39.675182: step: 2020/530, loss: 0.09186959266662598
2023-01-23 00:18:40.889572: step: 2024/530, loss: 0.08249416947364807
2023-01-23 00:18:42.087827: step: 2028/530, loss: 0.13058285415172577
2023-01-23 00:18:43.329982: step: 2032/530, loss: 0.31086570024490356
2023-01-23 00:18:44.455731: step: 2036/530, loss: 0.15235500037670135
2023-01-23 00:18:45.607761: step: 2040/530, loss: 0.04193000867962837
2023-01-23 00:18:46.827873: step: 2044/530, loss: 0.14625893533229828
2023-01-23 00:18:47.982378: step: 2048/530, loss: 0.2028767615556717
2023-01-23 00:18:49.109203: step: 2052/530, loss: 0.09789669513702393
2023-01-23 00:18:50.274243: step: 2056/530, loss: 0.9054768681526184
2023-01-23 00:18:51.417135: step: 2060/530, loss: 0.2827209234237671
2023-01-23 00:18:52.590883: step: 2064/530, loss: 0.10104601085186005
2023-01-23 00:18:53.786734: step: 2068/530, loss: 0.8684676289558411
2023-01-23 00:18:54.956489: step: 2072/530, loss: 0.8356946706771851
2023-01-23 00:18:56.133378: step: 2076/530, loss: 0.6887723803520203
2023-01-23 00:18:57.345519: step: 2080/530, loss: 0.08993025124073029
2023-01-23 00:18:58.526732: step: 2084/530, loss: 0.13519316911697388
2023-01-23 00:18:59.686114: step: 2088/530, loss: 0.17611093819141388
2023-01-23 00:19:00.861315: step: 2092/530, loss: 0.03232526034116745
2023-01-23 00:19:02.045817: step: 2096/530, loss: 0.4869275987148285
2023-01-23 00:19:03.275883: step: 2100/530, loss: 0.20564980804920197
2023-01-23 00:19:04.417909: step: 2104/530, loss: 0.2366410344839096
2023-01-23 00:19:05.619788: step: 2108/530, loss: 0.05308065563440323
2023-01-23 00:19:06.752341: step: 2112/530, loss: 0.18364979326725006
2023-01-23 00:19:07.931205: step: 2116/530, loss: 0.3367350697517395
2023-01-23 00:19:09.102638: step: 2120/530, loss: 0.7386298179626465
==================================================
Loss: 0.393
--------------------
Dev: {'event': {'p': 0.4911816578483245, 'r': 0.7416777629826897, 'f1': 0.5909814323607426}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Test: {'event': {'p': 0.6182416549130231, 'r': 0.7561817136285222, 'f1': 0.6802897051215727}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Chinese: {'event': {'p': 0.4270833333333333, 'r': 0.7592592592592593, 'f1': 0.5466666666666666}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Korean: {'event': {'p': 0.6065573770491803, 'r': 0.5873015873015873, 'f1': 0.5967741935483871}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Russian: {'event': {'p': 0.4339622641509434, 'r': 0.6388888888888888, 'f1': 0.5168539325842696}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.5815160955347871, 'r': 0.7456724367509987, 'f1': 0.6534422403733957}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Chinese: {'event': {'p': 0.604882459312839, 'r': 0.7694077055779184, 'f1': 0.6772968868640851}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Chinese: {'event': {'p': 0.5402298850574713, 'r': 0.8703703703703703, 'f1': 0.6666666666666666}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5815160955347871, 'r': 0.7456724367509987, 'f1': 0.6534422403733957}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Korean: {'event': {'p': 0.604882459312839, 'r': 0.7694077055779184, 'f1': 0.6772968868640851}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Korean: {'event': {'p': 0.6666666666666666, 'r': 0.6031746031746031, 'f1': 0.6333333333333333}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5815160955347871, 'r': 0.7456724367509987, 'f1': 0.6534422403733957}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Russian: {'event': {'p': 0.604882459312839, 'r': 0.7694077055779184, 'f1': 0.6772968868640851}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Russian: {'event': {'p': 0.5348837209302325, 'r': 0.6388888888888888, 'f1': 0.5822784810126581}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
******************************
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 00:19:52.289405: step: 4/530, loss: 0.3395237922668457
2023-01-23 00:19:53.455669: step: 8/530, loss: 0.14292305707931519
2023-01-23 00:19:54.643791: step: 12/530, loss: 0.048886489123106
2023-01-23 00:19:55.811686: step: 16/530, loss: 0.20861344039440155
2023-01-23 00:19:56.989607: step: 20/530, loss: 0.6296416521072388
2023-01-23 00:19:58.173197: step: 24/530, loss: 0.061091139912605286
2023-01-23 00:19:59.346834: step: 28/530, loss: 0.15461082756519318
2023-01-23 00:20:00.515632: step: 32/530, loss: 0.1430390328168869
2023-01-23 00:20:01.707172: step: 36/530, loss: 0.1796915978193283
2023-01-23 00:20:02.851307: step: 40/530, loss: 0.06257183849811554
2023-01-23 00:20:04.070255: step: 44/530, loss: 0.4593068063259125
2023-01-23 00:20:05.261600: step: 48/530, loss: 0.10563822090625763
2023-01-23 00:20:06.421749: step: 52/530, loss: 0.02028479613363743
2023-01-23 00:20:07.568926: step: 56/530, loss: 0.12357921898365021
2023-01-23 00:20:08.773156: step: 60/530, loss: 1.264628529548645
2023-01-23 00:20:09.954817: step: 64/530, loss: 0.3385503888130188
2023-01-23 00:20:11.155039: step: 68/530, loss: 0.08072176575660706
2023-01-23 00:20:12.344937: step: 72/530, loss: 0.20088501274585724
2023-01-23 00:20:13.505864: step: 76/530, loss: 0.04902315139770508
2023-01-23 00:20:14.674012: step: 80/530, loss: 0.033776093274354935
2023-01-23 00:20:15.807859: step: 84/530, loss: 0.10752268135547638
2023-01-23 00:20:16.994333: step: 88/530, loss: 0.5273001790046692
2023-01-23 00:20:18.175201: step: 92/530, loss: 0.22938717901706696
2023-01-23 00:20:19.353762: step: 96/530, loss: 0.3376498222351074
2023-01-23 00:20:20.529880: step: 100/530, loss: 0.3076295852661133
2023-01-23 00:20:21.707783: step: 104/530, loss: 0.07853376865386963
2023-01-23 00:20:22.872705: step: 108/530, loss: 0.17330913245677948
2023-01-23 00:20:24.055068: step: 112/530, loss: 0.8449240326881409
2023-01-23 00:20:25.249797: step: 116/530, loss: 0.12833939492702484
2023-01-23 00:20:26.456203: step: 120/530, loss: 0.7335178852081299
2023-01-23 00:20:27.637674: step: 124/530, loss: 0.1502002775669098
2023-01-23 00:20:28.780845: step: 128/530, loss: 0.3265603184700012
2023-01-23 00:20:29.960486: step: 132/530, loss: 0.09195976704359055
2023-01-23 00:20:31.124551: step: 136/530, loss: 0.11156454682350159
2023-01-23 00:20:32.250881: step: 140/530, loss: 0.8290325999259949
2023-01-23 00:20:33.443323: step: 144/530, loss: 0.11049118638038635
2023-01-23 00:20:34.601280: step: 148/530, loss: 0.17406292259693146
2023-01-23 00:20:35.768952: step: 152/530, loss: 0.08609409630298615
2023-01-23 00:20:36.983079: step: 156/530, loss: 0.3714890480041504
2023-01-23 00:20:38.149158: step: 160/530, loss: 0.355594277381897
2023-01-23 00:20:39.312855: step: 164/530, loss: 0.39681756496429443
2023-01-23 00:20:40.473534: step: 168/530, loss: 0.41215306520462036
2023-01-23 00:20:41.650857: step: 172/530, loss: 0.028958607465028763
2023-01-23 00:20:42.879442: step: 176/530, loss: 0.23906210064888
2023-01-23 00:20:44.019963: step: 180/530, loss: 0.0642690658569336
2023-01-23 00:20:45.225472: step: 184/530, loss: 0.024057675153017044
2023-01-23 00:20:46.403329: step: 188/530, loss: 0.19297924637794495
2023-01-23 00:20:47.573545: step: 192/530, loss: 0.26505905389785767
2023-01-23 00:20:48.716984: step: 196/530, loss: 0.10772333294153214
2023-01-23 00:20:49.916981: step: 200/530, loss: 0.19438190758228302
2023-01-23 00:20:51.095212: step: 204/530, loss: 0.13568845391273499
2023-01-23 00:20:52.249107: step: 208/530, loss: 0.06396003067493439
2023-01-23 00:20:53.444176: step: 212/530, loss: 0.1592452973127365
2023-01-23 00:20:54.597328: step: 216/530, loss: 0.22247348725795746
2023-01-23 00:20:55.753532: step: 220/530, loss: 0.10000196099281311
2023-01-23 00:20:56.932940: step: 224/530, loss: 0.13718347251415253
2023-01-23 00:20:58.126861: step: 228/530, loss: 0.23773781955242157
2023-01-23 00:20:59.293964: step: 232/530, loss: 0.09083373844623566
2023-01-23 00:21:00.446063: step: 236/530, loss: 0.16300687193870544
2023-01-23 00:21:01.645459: step: 240/530, loss: 0.732474148273468
2023-01-23 00:21:02.771568: step: 244/530, loss: 0.33389195799827576
2023-01-23 00:21:03.939245: step: 248/530, loss: 0.07171668857336044
2023-01-23 00:21:05.118292: step: 252/530, loss: 0.09313421696424484
2023-01-23 00:21:06.298271: step: 256/530, loss: 2.2392632961273193
2023-01-23 00:21:07.496365: step: 260/530, loss: 0.23304367065429688
2023-01-23 00:21:08.655788: step: 264/530, loss: 0.049810029566287994
2023-01-23 00:21:09.800630: step: 268/530, loss: 0.2002248764038086
2023-01-23 00:21:10.951498: step: 272/530, loss: 0.034461118280887604
2023-01-23 00:21:12.138343: step: 276/530, loss: 0.37291058897972107
2023-01-23 00:21:13.305465: step: 280/530, loss: 0.16013050079345703
2023-01-23 00:21:14.440387: step: 284/530, loss: 0.322002649307251
2023-01-23 00:21:15.635270: step: 288/530, loss: 0.09548010677099228
2023-01-23 00:21:16.843476: step: 292/530, loss: 0.08332128822803497
2023-01-23 00:21:17.996759: step: 296/530, loss: 0.6049390435218811
2023-01-23 00:21:19.129447: step: 300/530, loss: 0.05335254594683647
2023-01-23 00:21:20.319071: step: 304/530, loss: 0.079053595662117
2023-01-23 00:21:21.476358: step: 308/530, loss: 0.18881192803382874
2023-01-23 00:21:22.641443: step: 312/530, loss: 0.04599170759320259
2023-01-23 00:21:23.828997: step: 316/530, loss: 0.11059131473302841
2023-01-23 00:21:25.020962: step: 320/530, loss: 0.08553659915924072
2023-01-23 00:21:26.202689: step: 324/530, loss: 0.05937357246875763
2023-01-23 00:21:27.391996: step: 328/530, loss: 0.15882810950279236
2023-01-23 00:21:28.588591: step: 332/530, loss: 0.09655638039112091
2023-01-23 00:21:29.742101: step: 336/530, loss: 0.01138682384043932
2023-01-23 00:21:30.906982: step: 340/530, loss: 0.0339818000793457
2023-01-23 00:21:32.085638: step: 344/530, loss: 0.04507635906338692
2023-01-23 00:21:33.266836: step: 348/530, loss: 0.06207151710987091
2023-01-23 00:21:34.428569: step: 352/530, loss: 0.04459104686975479
2023-01-23 00:21:35.656830: step: 356/530, loss: 0.4275591969490051
2023-01-23 00:21:36.869494: step: 360/530, loss: 0.08763594925403595
2023-01-23 00:21:38.023814: step: 364/530, loss: 0.2645406723022461
2023-01-23 00:21:39.238948: step: 368/530, loss: 0.11387267708778381
2023-01-23 00:21:40.429716: step: 372/530, loss: 1.3267130851745605
2023-01-23 00:21:41.616892: step: 376/530, loss: 0.5971904993057251
2023-01-23 00:21:42.765603: step: 380/530, loss: 0.18387582898139954
2023-01-23 00:21:43.977705: step: 384/530, loss: 1.6609737873077393
2023-01-23 00:21:45.156027: step: 388/530, loss: 0.03179154545068741
2023-01-23 00:21:46.361825: step: 392/530, loss: 0.1436682641506195
2023-01-23 00:21:47.542594: step: 396/530, loss: 0.15617981553077698
2023-01-23 00:21:48.715678: step: 400/530, loss: 0.09733657538890839
2023-01-23 00:21:49.905782: step: 404/530, loss: 0.49601441621780396
2023-01-23 00:21:51.037422: step: 408/530, loss: 0.2796943783760071
2023-01-23 00:21:52.213109: step: 412/530, loss: 0.1823309063911438
2023-01-23 00:21:53.423721: step: 416/530, loss: 0.08819971233606339
2023-01-23 00:21:54.610245: step: 420/530, loss: 0.15318146347999573
2023-01-23 00:21:55.765356: step: 424/530, loss: 0.022849464789032936
2023-01-23 00:21:56.934997: step: 428/530, loss: 1.4256436824798584
2023-01-23 00:21:58.101649: step: 432/530, loss: 0.19760262966156006
2023-01-23 00:21:59.277559: step: 436/530, loss: 2.434588670730591
2023-01-23 00:22:00.451582: step: 440/530, loss: 0.1771283745765686
2023-01-23 00:22:01.627127: step: 444/530, loss: 0.06708145141601562
2023-01-23 00:22:02.793768: step: 448/530, loss: 0.9383450746536255
2023-01-23 00:22:04.035960: step: 452/530, loss: 0.04250223934650421
2023-01-23 00:22:05.225509: step: 456/530, loss: 0.07037639617919922
2023-01-23 00:22:06.385551: step: 460/530, loss: 0.1599535048007965
2023-01-23 00:22:07.575047: step: 464/530, loss: 0.05111327022314072
2023-01-23 00:22:08.740652: step: 468/530, loss: 0.6414703130722046
2023-01-23 00:22:09.885128: step: 472/530, loss: 0.10155753791332245
2023-01-23 00:22:11.066660: step: 476/530, loss: 1.2062379121780396
2023-01-23 00:22:12.243168: step: 480/530, loss: 0.1793156862258911
2023-01-23 00:22:13.391605: step: 484/530, loss: 0.08800821006298065
2023-01-23 00:22:14.538744: step: 488/530, loss: 0.12793751060962677
2023-01-23 00:22:15.713362: step: 492/530, loss: 0.17777720093727112
2023-01-23 00:22:16.920939: step: 496/530, loss: 0.8173092007637024
2023-01-23 00:22:18.081255: step: 500/530, loss: 0.38279443979263306
2023-01-23 00:22:19.272886: step: 504/530, loss: 0.9181571006774902
2023-01-23 00:22:20.463603: step: 508/530, loss: 0.348619282245636
2023-01-23 00:22:21.644446: step: 512/530, loss: 0.20670852065086365
2023-01-23 00:22:22.796663: step: 516/530, loss: 0.33444374799728394
2023-01-23 00:22:23.957256: step: 520/530, loss: 0.1402256190776825
2023-01-23 00:22:25.128985: step: 524/530, loss: 0.08646586537361145
2023-01-23 00:22:26.295945: step: 528/530, loss: 0.35968017578125
2023-01-23 00:22:27.495288: step: 532/530, loss: 0.126338392496109
2023-01-23 00:22:28.715174: step: 536/530, loss: 0.3286783993244171
2023-01-23 00:22:29.902404: step: 540/530, loss: 0.04582090675830841
2023-01-23 00:22:31.042773: step: 544/530, loss: 0.12755991518497467
2023-01-23 00:22:32.217371: step: 548/530, loss: 0.3362697660923004
2023-01-23 00:22:33.417605: step: 552/530, loss: 0.08193187415599823
2023-01-23 00:22:34.626684: step: 556/530, loss: 0.3838282823562622
2023-01-23 00:22:35.772303: step: 560/530, loss: 0.2041710913181305
2023-01-23 00:22:36.917988: step: 564/530, loss: 0.3233398497104645
2023-01-23 00:22:38.140758: step: 568/530, loss: 0.6178305149078369
2023-01-23 00:22:39.318270: step: 572/530, loss: 0.07716178894042969
2023-01-23 00:22:40.506260: step: 576/530, loss: 0.41793808341026306
2023-01-23 00:22:41.727096: step: 580/530, loss: 0.3867012858390808
2023-01-23 00:22:42.903158: step: 584/530, loss: 0.06379709392786026
2023-01-23 00:22:44.095653: step: 588/530, loss: 0.1727897673845291
2023-01-23 00:22:45.286168: step: 592/530, loss: 0.10468115657567978
2023-01-23 00:22:46.471558: step: 596/530, loss: 0.0640813335776329
2023-01-23 00:22:47.652660: step: 600/530, loss: 0.4098457396030426
2023-01-23 00:22:48.834305: step: 604/530, loss: 0.08113507926464081
2023-01-23 00:22:49.989513: step: 608/530, loss: 0.6113743185997009
2023-01-23 00:22:51.158544: step: 612/530, loss: 0.30175554752349854
2023-01-23 00:22:52.330654: step: 616/530, loss: 0.0978919044137001
2023-01-23 00:22:53.547507: step: 620/530, loss: 0.06678323447704315
2023-01-23 00:22:54.720193: step: 624/530, loss: 0.5544461607933044
2023-01-23 00:22:55.879172: step: 628/530, loss: 0.24039077758789062
2023-01-23 00:22:57.083296: step: 632/530, loss: 0.013257504440844059
2023-01-23 00:22:58.269382: step: 636/530, loss: 0.27228212356567383
2023-01-23 00:22:59.446744: step: 640/530, loss: 0.1346491426229477
2023-01-23 00:23:00.661243: step: 644/530, loss: 0.46833497285842896
2023-01-23 00:23:01.809447: step: 648/530, loss: 0.07121892273426056
2023-01-23 00:23:02.949278: step: 652/530, loss: 0.1012469157576561
2023-01-23 00:23:04.138822: step: 656/530, loss: 0.690554141998291
2023-01-23 00:23:05.278395: step: 660/530, loss: 0.07158022373914719
2023-01-23 00:23:06.520351: step: 664/530, loss: 0.3830791115760803
2023-01-23 00:23:07.683023: step: 668/530, loss: 0.19862011075019836
2023-01-23 00:23:08.882251: step: 672/530, loss: 0.08588233590126038
2023-01-23 00:23:10.103806: step: 676/530, loss: 0.3338552415370941
2023-01-23 00:23:11.260710: step: 680/530, loss: 0.1229274719953537
2023-01-23 00:23:12.468971: step: 684/530, loss: 0.07652473449707031
2023-01-23 00:23:13.640440: step: 688/530, loss: 0.07457561790943146
2023-01-23 00:23:14.782400: step: 692/530, loss: 0.7510537505149841
2023-01-23 00:23:15.957609: step: 696/530, loss: 0.4571743905544281
2023-01-23 00:23:17.117575: step: 700/530, loss: 0.07020358741283417
2023-01-23 00:23:18.252709: step: 704/530, loss: 0.1106594130396843
2023-01-23 00:23:19.397997: step: 708/530, loss: 0.07189307361841202
2023-01-23 00:23:20.581149: step: 712/530, loss: 0.06367425620555878
2023-01-23 00:23:21.732564: step: 716/530, loss: 0.1598864197731018
2023-01-23 00:23:22.956483: step: 720/530, loss: 0.8086475133895874
2023-01-23 00:23:24.136217: step: 724/530, loss: 0.07574215531349182
2023-01-23 00:23:25.308969: step: 728/530, loss: 0.08137140423059464
2023-01-23 00:23:26.477604: step: 732/530, loss: 0.09217134118080139
2023-01-23 00:23:27.636610: step: 736/530, loss: 0.06056032329797745
2023-01-23 00:23:28.824297: step: 740/530, loss: 0.3768518567085266
2023-01-23 00:23:30.013845: step: 744/530, loss: 0.0956578478217125
2023-01-23 00:23:31.171083: step: 748/530, loss: 0.5609469413757324
2023-01-23 00:23:32.386014: step: 752/530, loss: 0.1131909117102623
2023-01-23 00:23:33.567824: step: 756/530, loss: 0.2542285919189453
2023-01-23 00:23:34.719327: step: 760/530, loss: 0.3582044541835785
2023-01-23 00:23:35.929988: step: 764/530, loss: 0.15882942080497742
2023-01-23 00:23:37.070705: step: 768/530, loss: 0.08517131954431534
2023-01-23 00:23:38.246774: step: 772/530, loss: 0.25613927841186523
2023-01-23 00:23:39.412532: step: 776/530, loss: 0.02603592909872532
2023-01-23 00:23:40.603370: step: 780/530, loss: 0.3542129397392273
2023-01-23 00:23:41.740869: step: 784/530, loss: 0.20385399460792542
2023-01-23 00:23:42.886522: step: 788/530, loss: 0.21186791360378265
2023-01-23 00:23:44.069517: step: 792/530, loss: 0.22977885603904724
2023-01-23 00:23:45.230054: step: 796/530, loss: 0.08125042915344238
2023-01-23 00:23:46.424291: step: 800/530, loss: 0.046143725514411926
2023-01-23 00:23:47.602877: step: 804/530, loss: 0.16149769723415375
2023-01-23 00:23:48.747431: step: 808/530, loss: 0.1089821308851242
2023-01-23 00:23:49.896654: step: 812/530, loss: 0.17021751403808594
2023-01-23 00:23:51.046845: step: 816/530, loss: 0.05350446701049805
2023-01-23 00:23:52.202437: step: 820/530, loss: 0.07904867827892303
2023-01-23 00:23:53.332415: step: 824/530, loss: 0.03456611931324005
2023-01-23 00:23:54.531527: step: 828/530, loss: 0.07885666191577911
2023-01-23 00:23:55.687654: step: 832/530, loss: 0.17894645035266876
2023-01-23 00:23:56.860618: step: 836/530, loss: 0.05385322496294975
2023-01-23 00:23:57.996182: step: 840/530, loss: 0.18747782707214355
2023-01-23 00:23:59.188259: step: 844/530, loss: 0.2732110023498535
2023-01-23 00:24:00.399123: step: 848/530, loss: 0.07937441021203995
2023-01-23 00:24:01.555048: step: 852/530, loss: 0.11732955276966095
2023-01-23 00:24:02.712911: step: 856/530, loss: 0.12375015765428543
2023-01-23 00:24:03.868392: step: 860/530, loss: 0.09790816903114319
2023-01-23 00:24:05.071935: step: 864/530, loss: 1.5532574653625488
2023-01-23 00:24:06.250025: step: 868/530, loss: 0.5177452564239502
2023-01-23 00:24:07.432664: step: 872/530, loss: 0.1959790736436844
2023-01-23 00:24:08.624503: step: 876/530, loss: 0.050359103828668594
2023-01-23 00:24:09.781840: step: 880/530, loss: 0.10697796195745468
2023-01-23 00:24:10.970434: step: 884/530, loss: 0.0900697261095047
2023-01-23 00:24:12.153498: step: 888/530, loss: 0.14047984778881073
2023-01-23 00:24:13.353471: step: 892/530, loss: 0.6372136473655701
2023-01-23 00:24:14.498334: step: 896/530, loss: 0.04483118653297424
2023-01-23 00:24:15.696391: step: 900/530, loss: 0.07319831848144531
2023-01-23 00:24:16.852935: step: 904/530, loss: 1.0199657678604126
2023-01-23 00:24:18.037569: step: 908/530, loss: 0.18231754004955292
2023-01-23 00:24:19.211540: step: 912/530, loss: 0.37246617674827576
2023-01-23 00:24:20.407811: step: 916/530, loss: 0.48592326045036316
2023-01-23 00:24:21.553383: step: 920/530, loss: 0.5735053420066833
2023-01-23 00:24:22.690153: step: 924/530, loss: 0.08694677799940109
2023-01-23 00:24:23.842249: step: 928/530, loss: 0.3604698181152344
2023-01-23 00:24:24.987132: step: 932/530, loss: 0.20838555693626404
2023-01-23 00:24:26.153613: step: 936/530, loss: 0.16676147282123566
2023-01-23 00:24:27.327501: step: 940/530, loss: 0.1354725956916809
2023-01-23 00:24:28.492196: step: 944/530, loss: 0.08504219353199005
2023-01-23 00:24:29.666730: step: 948/530, loss: 0.39967620372772217
2023-01-23 00:24:30.857814: step: 952/530, loss: 0.08267507702112198
2023-01-23 00:24:32.098310: step: 956/530, loss: 0.0610315315425396
2023-01-23 00:24:33.267015: step: 960/530, loss: 0.2283109724521637
2023-01-23 00:24:34.425494: step: 964/530, loss: 0.12507982552051544
2023-01-23 00:24:35.602979: step: 968/530, loss: 0.5888115167617798
2023-01-23 00:24:36.748945: step: 972/530, loss: 0.11314735561609268
2023-01-23 00:24:37.915692: step: 976/530, loss: 0.8343511819839478
2023-01-23 00:24:39.094175: step: 980/530, loss: 0.5755516886711121
2023-01-23 00:24:40.253791: step: 984/530, loss: 0.012020445428788662
2023-01-23 00:24:41.460254: step: 988/530, loss: 0.06647415459156036
2023-01-23 00:24:42.673148: step: 992/530, loss: 0.2904585003852844
2023-01-23 00:24:43.848497: step: 996/530, loss: 0.292728990316391
2023-01-23 00:24:45.022887: step: 1000/530, loss: 0.6669138073921204
2023-01-23 00:24:46.193853: step: 1004/530, loss: 0.18626007437705994
2023-01-23 00:24:47.387955: step: 1008/530, loss: 2.168475389480591
2023-01-23 00:24:48.567324: step: 1012/530, loss: 1.471031904220581
2023-01-23 00:24:49.732262: step: 1016/530, loss: 0.32629913091659546
2023-01-23 00:24:50.898817: step: 1020/530, loss: 0.4751717746257782
2023-01-23 00:24:52.051031: step: 1024/530, loss: 0.2426433563232422
2023-01-23 00:24:53.230066: step: 1028/530, loss: 0.10402746498584747
2023-01-23 00:24:54.400929: step: 1032/530, loss: 0.5038238167762756
2023-01-23 00:24:55.528701: step: 1036/530, loss: 0.01148979738354683
2023-01-23 00:24:56.710759: step: 1040/530, loss: 0.8801649808883667
2023-01-23 00:24:57.837170: step: 1044/530, loss: 0.6397822499275208
2023-01-23 00:24:59.009616: step: 1048/530, loss: 0.2075888216495514
2023-01-23 00:25:00.149307: step: 1052/530, loss: 0.18571627140045166
2023-01-23 00:25:01.299636: step: 1056/530, loss: 0.04957332834601402
2023-01-23 00:25:02.521480: step: 1060/530, loss: 0.8867083787918091
2023-01-23 00:25:03.707130: step: 1064/530, loss: 0.24365095794200897
2023-01-23 00:25:04.874924: step: 1068/530, loss: 0.6125437021255493
2023-01-23 00:25:06.048535: step: 1072/530, loss: 0.43842363357543945
2023-01-23 00:25:07.211057: step: 1076/530, loss: 0.5704627633094788
2023-01-23 00:25:08.367720: step: 1080/530, loss: 0.24505653977394104
2023-01-23 00:25:09.532740: step: 1084/530, loss: 0.07791705429553986
2023-01-23 00:25:10.710702: step: 1088/530, loss: 1.9555320739746094
2023-01-23 00:25:11.877930: step: 1092/530, loss: 0.47729578614234924
2023-01-23 00:25:13.052957: step: 1096/530, loss: 0.13234680891036987
2023-01-23 00:25:14.247157: step: 1100/530, loss: 0.07763376832008362
2023-01-23 00:25:15.423125: step: 1104/530, loss: 0.2553926110267639
2023-01-23 00:25:16.581657: step: 1108/530, loss: 0.05934019386768341
2023-01-23 00:25:17.754815: step: 1112/530, loss: 1.2474793195724487
2023-01-23 00:25:18.894621: step: 1116/530, loss: 0.1332971602678299
2023-01-23 00:25:20.098316: step: 1120/530, loss: 0.4560391902923584
2023-01-23 00:25:21.288730: step: 1124/530, loss: 0.16044750809669495
2023-01-23 00:25:22.520797: step: 1128/530, loss: 0.12127628177404404
2023-01-23 00:25:23.731816: step: 1132/530, loss: 0.5991616249084473
2023-01-23 00:25:24.860611: step: 1136/530, loss: 0.2859123647212982
2023-01-23 00:25:26.001811: step: 1140/530, loss: 0.032474614679813385
2023-01-23 00:25:27.168907: step: 1144/530, loss: 0.03540482372045517
2023-01-23 00:25:28.349873: step: 1148/530, loss: 0.09580278396606445
2023-01-23 00:25:29.545355: step: 1152/530, loss: 0.16927321255207062
2023-01-23 00:25:30.715921: step: 1156/530, loss: 0.20908865332603455
2023-01-23 00:25:31.843630: step: 1160/530, loss: 0.22863316535949707
2023-01-23 00:25:33.031213: step: 1164/530, loss: 0.2704286575317383
2023-01-23 00:25:34.209541: step: 1168/530, loss: 0.18156041204929352
2023-01-23 00:25:35.401667: step: 1172/530, loss: 0.0785895362496376
2023-01-23 00:25:36.581736: step: 1176/530, loss: 0.06458039581775665
2023-01-23 00:25:37.729212: step: 1180/530, loss: 0.06516294181346893
2023-01-23 00:25:38.881874: step: 1184/530, loss: 0.07818622887134552
2023-01-23 00:25:40.043923: step: 1188/530, loss: 0.17929410934448242
2023-01-23 00:25:41.213452: step: 1192/530, loss: 0.9059211611747742
2023-01-23 00:25:42.353702: step: 1196/530, loss: 0.04472675547003746
2023-01-23 00:25:43.532387: step: 1200/530, loss: 0.1156536117196083
2023-01-23 00:25:44.697424: step: 1204/530, loss: 0.5848633646965027
2023-01-23 00:25:45.858701: step: 1208/530, loss: 0.05516824871301651
2023-01-23 00:25:47.025828: step: 1212/530, loss: 0.03132748603820801
2023-01-23 00:25:48.206466: step: 1216/530, loss: 0.051054954528808594
2023-01-23 00:25:49.402328: step: 1220/530, loss: 0.10619644820690155
2023-01-23 00:25:50.587951: step: 1224/530, loss: 0.43752241134643555
2023-01-23 00:25:51.735492: step: 1228/530, loss: 0.0352010503411293
2023-01-23 00:25:52.929066: step: 1232/530, loss: 0.18690891563892365
2023-01-23 00:25:54.122657: step: 1236/530, loss: 0.07504439353942871
2023-01-23 00:25:55.254545: step: 1240/530, loss: 0.16570618748664856
2023-01-23 00:25:56.428293: step: 1244/530, loss: 0.1733359396457672
2023-01-23 00:25:57.659859: step: 1248/530, loss: 0.4787226617336273
2023-01-23 00:25:58.825451: step: 1252/530, loss: 0.13653096556663513
2023-01-23 00:26:00.048717: step: 1256/530, loss: 0.171139195561409
2023-01-23 00:26:01.190177: step: 1260/530, loss: 0.061833858489990234
2023-01-23 00:26:02.361251: step: 1264/530, loss: 0.24273909628391266
2023-01-23 00:26:03.503152: step: 1268/530, loss: 0.04744882881641388
2023-01-23 00:26:04.638162: step: 1272/530, loss: 0.5717808604240417
2023-01-23 00:26:05.810250: step: 1276/530, loss: 0.0474054329097271
2023-01-23 00:26:06.984482: step: 1280/530, loss: 0.020391561090946198
2023-01-23 00:26:08.166179: step: 1284/530, loss: 0.15444627404212952
2023-01-23 00:26:09.349253: step: 1288/530, loss: 0.16565489768981934
2023-01-23 00:26:10.525336: step: 1292/530, loss: 0.18671393394470215
2023-01-23 00:26:11.743352: step: 1296/530, loss: 0.5503236055374146
2023-01-23 00:26:12.915014: step: 1300/530, loss: 0.13108621537685394
2023-01-23 00:26:14.101489: step: 1304/530, loss: 0.17163696885108948
2023-01-23 00:26:15.300805: step: 1308/530, loss: 0.2255449891090393
2023-01-23 00:26:16.502667: step: 1312/530, loss: 0.2358277440071106
2023-01-23 00:26:17.715510: step: 1316/530, loss: 0.4199904501438141
2023-01-23 00:26:18.854928: step: 1320/530, loss: 0.5662668347358704
2023-01-23 00:26:20.057579: step: 1324/530, loss: 0.2246697098016739
2023-01-23 00:26:21.204041: step: 1328/530, loss: 0.6220422387123108
2023-01-23 00:26:22.364371: step: 1332/530, loss: 0.48554858565330505
2023-01-23 00:26:23.521104: step: 1336/530, loss: 0.04615822061896324
2023-01-23 00:26:24.680664: step: 1340/530, loss: 0.10526285320520401
2023-01-23 00:26:25.872916: step: 1344/530, loss: 0.5885298848152161
2023-01-23 00:26:27.061132: step: 1348/530, loss: 0.2826506793498993
2023-01-23 00:26:28.177778: step: 1352/530, loss: 0.13399486243724823
2023-01-23 00:26:29.355475: step: 1356/530, loss: 1.0948952436447144
2023-01-23 00:26:30.552038: step: 1360/530, loss: 0.7194830179214478
2023-01-23 00:26:31.692110: step: 1364/530, loss: 0.04530759155750275
2023-01-23 00:26:32.891677: step: 1368/530, loss: 0.7042287588119507
2023-01-23 00:26:34.054145: step: 1372/530, loss: 0.17493458092212677
2023-01-23 00:26:35.230399: step: 1376/530, loss: 0.07183227688074112
2023-01-23 00:26:36.400477: step: 1380/530, loss: 0.08216257393360138
2023-01-23 00:26:37.569473: step: 1384/530, loss: 0.08559112250804901
2023-01-23 00:26:38.765150: step: 1388/530, loss: 0.03427858650684357
2023-01-23 00:26:39.923990: step: 1392/530, loss: 0.18191371858119965
2023-01-23 00:26:41.123289: step: 1396/530, loss: 0.026778126135468483
2023-01-23 00:26:42.327499: step: 1400/530, loss: 0.2142053246498108
2023-01-23 00:26:43.498790: step: 1404/530, loss: 0.04235114902257919
2023-01-23 00:26:44.685315: step: 1408/530, loss: 0.9389051198959351
2023-01-23 00:26:45.883740: step: 1412/530, loss: 0.19289031624794006
2023-01-23 00:26:47.081303: step: 1416/530, loss: 0.624676525592804
2023-01-23 00:26:48.230331: step: 1420/530, loss: 0.12964196503162384
2023-01-23 00:26:49.438647: step: 1424/530, loss: 0.07281980663537979
2023-01-23 00:26:50.578297: step: 1428/530, loss: 0.6434813737869263
2023-01-23 00:26:51.747310: step: 1432/530, loss: 0.393645703792572
2023-01-23 00:26:52.904555: step: 1436/530, loss: 0.6352441906929016
2023-01-23 00:26:54.095351: step: 1440/530, loss: 0.12835732102394104
2023-01-23 00:26:55.259986: step: 1444/530, loss: 0.2975778579711914
2023-01-23 00:26:56.453511: step: 1448/530, loss: 0.06826931983232498
2023-01-23 00:26:57.673818: step: 1452/530, loss: 0.18356162309646606
2023-01-23 00:26:58.837928: step: 1456/530, loss: 0.091344453394413
2023-01-23 00:27:00.007215: step: 1460/530, loss: 0.2977584898471832
2023-01-23 00:27:01.160589: step: 1464/530, loss: 0.16529908776283264
2023-01-23 00:27:02.428394: step: 1468/530, loss: 0.14218272268772125
2023-01-23 00:27:03.576635: step: 1472/530, loss: 0.3001793920993805
2023-01-23 00:27:04.780596: step: 1476/530, loss: 0.1296243667602539
2023-01-23 00:27:05.951272: step: 1480/530, loss: 0.25451919436454773
2023-01-23 00:27:07.124946: step: 1484/530, loss: 0.16674485802650452
2023-01-23 00:27:08.290536: step: 1488/530, loss: 0.09211044758558273
2023-01-23 00:27:09.450667: step: 1492/530, loss: 0.07760500907897949
2023-01-23 00:27:10.628056: step: 1496/530, loss: 0.36814916133880615
2023-01-23 00:27:11.807674: step: 1500/530, loss: 0.3086715340614319
2023-01-23 00:27:12.973570: step: 1504/530, loss: 0.31361985206604004
2023-01-23 00:27:14.127640: step: 1508/530, loss: 0.39559406042099
2023-01-23 00:27:15.301066: step: 1512/530, loss: 0.04169083014130592
2023-01-23 00:27:16.473062: step: 1516/530, loss: 0.4428962469100952
2023-01-23 00:27:17.616762: step: 1520/530, loss: 0.1047309935092926
2023-01-23 00:27:18.801987: step: 1524/530, loss: 0.049477290362119675
2023-01-23 00:27:20.043560: step: 1528/530, loss: 0.6606917381286621
2023-01-23 00:27:21.235259: step: 1532/530, loss: 0.2922571301460266
2023-01-23 00:27:22.443789: step: 1536/530, loss: 0.16509433090686798
2023-01-23 00:27:23.636810: step: 1540/530, loss: 0.14102521538734436
2023-01-23 00:27:24.815815: step: 1544/530, loss: 0.6083961725234985
2023-01-23 00:27:25.999045: step: 1548/530, loss: 0.07300844043493271
2023-01-23 00:27:27.151838: step: 1552/530, loss: 0.44000494480133057
2023-01-23 00:27:28.374045: step: 1556/530, loss: 0.009563145227730274
2023-01-23 00:27:29.557083: step: 1560/530, loss: 0.4080503582954407
2023-01-23 00:27:30.753565: step: 1564/530, loss: 0.6315172910690308
2023-01-23 00:27:31.967239: step: 1568/530, loss: 0.1180976927280426
2023-01-23 00:27:33.175211: step: 1572/530, loss: 0.10513772815465927
2023-01-23 00:27:34.326713: step: 1576/530, loss: 0.0841943770647049
2023-01-23 00:27:35.485000: step: 1580/530, loss: 0.33826887607574463
2023-01-23 00:27:36.643765: step: 1584/530, loss: 0.05056290701031685
2023-01-23 00:27:37.816219: step: 1588/530, loss: 0.9394656419754028
2023-01-23 00:27:38.974005: step: 1592/530, loss: 0.18289200961589813
2023-01-23 00:27:40.174339: step: 1596/530, loss: 0.12054203450679779
2023-01-23 00:27:41.336403: step: 1600/530, loss: 0.7090510129928589
2023-01-23 00:27:42.508607: step: 1604/530, loss: 0.2092619389295578
2023-01-23 00:27:43.626956: step: 1608/530, loss: 0.3508315682411194
2023-01-23 00:27:44.800654: step: 1612/530, loss: 0.03585987165570259
2023-01-23 00:27:45.980247: step: 1616/530, loss: 0.5515589714050293
2023-01-23 00:27:47.146570: step: 1620/530, loss: 0.15571269392967224
2023-01-23 00:27:48.289136: step: 1624/530, loss: 0.08539529144763947
2023-01-23 00:27:49.462747: step: 1628/530, loss: 0.14687862992286682
2023-01-23 00:27:50.627896: step: 1632/530, loss: 1.0682094097137451
2023-01-23 00:27:51.765575: step: 1636/530, loss: 0.23623287677764893
2023-01-23 00:27:52.920553: step: 1640/530, loss: 0.36274901032447815
2023-01-23 00:27:54.077652: step: 1644/530, loss: 0.21607714891433716
2023-01-23 00:27:55.283966: step: 1648/530, loss: 0.38459983468055725
2023-01-23 00:27:56.442463: step: 1652/530, loss: 2.671396017074585
2023-01-23 00:27:57.628596: step: 1656/530, loss: 0.3264641761779785
2023-01-23 00:27:58.811942: step: 1660/530, loss: 0.1645500659942627
2023-01-23 00:27:59.998648: step: 1664/530, loss: 0.12709493935108185
2023-01-23 00:28:01.162138: step: 1668/530, loss: 0.410942941904068
2023-01-23 00:28:02.320880: step: 1672/530, loss: 0.3050805926322937
2023-01-23 00:28:03.500112: step: 1676/530, loss: 0.1079469695687294
2023-01-23 00:28:04.681558: step: 1680/530, loss: 0.0970836654305458
2023-01-23 00:28:05.889412: step: 1684/530, loss: 0.1347736418247223
2023-01-23 00:28:07.033783: step: 1688/530, loss: 0.6043469309806824
2023-01-23 00:28:08.189882: step: 1692/530, loss: 0.7652765512466431
2023-01-23 00:28:09.350982: step: 1696/530, loss: 0.10198745131492615
2023-01-23 00:28:10.539595: step: 1700/530, loss: 0.4698176383972168
2023-01-23 00:28:11.691071: step: 1704/530, loss: 0.17421293258666992
2023-01-23 00:28:12.907204: step: 1708/530, loss: 0.39454221725463867
2023-01-23 00:28:14.059912: step: 1712/530, loss: 0.19035880267620087
2023-01-23 00:28:15.241999: step: 1716/530, loss: 0.681043803691864
2023-01-23 00:28:16.462759: step: 1720/530, loss: 0.3380935788154602
2023-01-23 00:28:17.616775: step: 1724/530, loss: 0.09006671607494354
2023-01-23 00:28:18.770503: step: 1728/530, loss: 3.8173582553863525
2023-01-23 00:28:19.963879: step: 1732/530, loss: 0.20162925124168396
2023-01-23 00:28:21.169834: step: 1736/530, loss: 0.1108190044760704
2023-01-23 00:28:22.320876: step: 1740/530, loss: 0.09658689796924591
2023-01-23 00:28:23.491444: step: 1744/530, loss: 0.1451614499092102
2023-01-23 00:28:24.694111: step: 1748/530, loss: 0.1478760838508606
2023-01-23 00:28:25.830890: step: 1752/530, loss: 0.5597879886627197
2023-01-23 00:28:27.009942: step: 1756/530, loss: 0.17262262105941772
2023-01-23 00:28:28.151076: step: 1760/530, loss: 0.08454713970422745
2023-01-23 00:28:29.291531: step: 1764/530, loss: 0.28342851996421814
2023-01-23 00:28:30.491920: step: 1768/530, loss: 0.3253527283668518
2023-01-23 00:28:31.670524: step: 1772/530, loss: 0.12964993715286255
2023-01-23 00:28:32.855949: step: 1776/530, loss: 0.17020387947559357
2023-01-23 00:28:33.999341: step: 1780/530, loss: 0.07815121114253998
2023-01-23 00:28:35.155803: step: 1784/530, loss: 0.18504615128040314
2023-01-23 00:28:36.339632: step: 1788/530, loss: 0.04820366948843002
2023-01-23 00:28:37.496254: step: 1792/530, loss: 0.0209047794342041
2023-01-23 00:28:38.678752: step: 1796/530, loss: 0.5757182836532593
2023-01-23 00:28:39.828785: step: 1800/530, loss: 0.17756973206996918
2023-01-23 00:28:41.002865: step: 1804/530, loss: 0.02128014713525772
2023-01-23 00:28:42.205557: step: 1808/530, loss: 0.5995561480522156
2023-01-23 00:28:43.343412: step: 1812/530, loss: 0.07125025242567062
2023-01-23 00:28:44.482362: step: 1816/530, loss: 0.19941289722919464
2023-01-23 00:28:45.642132: step: 1820/530, loss: 0.17385712265968323
2023-01-23 00:28:46.864980: step: 1824/530, loss: 0.16065020859241486
2023-01-23 00:28:48.039283: step: 1828/530, loss: 0.18355488777160645
2023-01-23 00:28:49.218784: step: 1832/530, loss: 0.07288698852062225
2023-01-23 00:28:50.388331: step: 1836/530, loss: 0.11582336574792862
2023-01-23 00:28:51.599044: step: 1840/530, loss: 0.23762167990207672
2023-01-23 00:28:52.787958: step: 1844/530, loss: 0.7768181562423706
2023-01-23 00:28:53.973321: step: 1848/530, loss: 0.09504041820764542
2023-01-23 00:28:55.134520: step: 1852/530, loss: 0.45964327454566956
2023-01-23 00:28:56.386675: step: 1856/530, loss: 0.12890419363975525
2023-01-23 00:28:57.557374: step: 1860/530, loss: 0.08270959556102753
2023-01-23 00:28:58.721579: step: 1864/530, loss: 0.3656943440437317
2023-01-23 00:28:59.872964: step: 1868/530, loss: 0.02837839163839817
2023-01-23 00:29:01.016465: step: 1872/530, loss: 0.06046877056360245
2023-01-23 00:29:02.180137: step: 1876/530, loss: 0.1449769139289856
2023-01-23 00:29:03.364442: step: 1880/530, loss: 0.7949851751327515
2023-01-23 00:29:04.513387: step: 1884/530, loss: 0.060991667211055756
2023-01-23 00:29:05.648772: step: 1888/530, loss: 0.3971121609210968
2023-01-23 00:29:06.812357: step: 1892/530, loss: 0.21435260772705078
2023-01-23 00:29:08.014265: step: 1896/530, loss: 0.08935561031103134
2023-01-23 00:29:09.210065: step: 1900/530, loss: 0.02246398851275444
2023-01-23 00:29:10.394133: step: 1904/530, loss: 0.12360525131225586
2023-01-23 00:29:11.554271: step: 1908/530, loss: 0.475870281457901
2023-01-23 00:29:12.711432: step: 1912/530, loss: 0.19839662313461304
2023-01-23 00:29:13.870474: step: 1916/530, loss: 0.07164087146520615
2023-01-23 00:29:15.045301: step: 1920/530, loss: 0.11918659508228302
2023-01-23 00:29:16.223329: step: 1924/530, loss: 0.11692371219396591
2023-01-23 00:29:17.431521: step: 1928/530, loss: 0.5201605558395386
2023-01-23 00:29:18.620046: step: 1932/530, loss: 0.26014289259910583
2023-01-23 00:29:19.796598: step: 1936/530, loss: 0.10092878341674805
2023-01-23 00:29:20.963267: step: 1940/530, loss: 0.3030557632446289
2023-01-23 00:29:22.154269: step: 1944/530, loss: 0.1404828131198883
2023-01-23 00:29:23.329818: step: 1948/530, loss: 0.11478271335363388
2023-01-23 00:29:24.496476: step: 1952/530, loss: 0.13196983933448792
2023-01-23 00:29:25.683085: step: 1956/530, loss: 0.17698338627815247
2023-01-23 00:29:26.867285: step: 1960/530, loss: 0.15164241194725037
2023-01-23 00:29:28.057759: step: 1964/530, loss: 0.5972582697868347
2023-01-23 00:29:29.231707: step: 1968/530, loss: 0.5600477457046509
2023-01-23 00:29:30.409584: step: 1972/530, loss: 0.021208904683589935
2023-01-23 00:29:31.590710: step: 1976/530, loss: 0.4192635416984558
2023-01-23 00:29:32.792522: step: 1980/530, loss: 0.09897632896900177
2023-01-23 00:29:33.962664: step: 1984/530, loss: 0.6683353781700134
2023-01-23 00:29:35.141229: step: 1988/530, loss: 0.21934795379638672
2023-01-23 00:29:36.308356: step: 1992/530, loss: 0.7338366508483887
2023-01-23 00:29:37.491954: step: 1996/530, loss: 0.0723641887307167
2023-01-23 00:29:38.679035: step: 2000/530, loss: 0.054695844650268555
2023-01-23 00:29:39.850389: step: 2004/530, loss: 0.6086748838424683
2023-01-23 00:29:41.047497: step: 2008/530, loss: 0.07680780440568924
2023-01-23 00:29:42.208595: step: 2012/530, loss: 0.09220962226390839
2023-01-23 00:29:43.346882: step: 2016/530, loss: 0.19119691848754883
2023-01-23 00:29:44.501078: step: 2020/530, loss: 0.34983572363853455
2023-01-23 00:29:45.654584: step: 2024/530, loss: 0.11355714499950409
2023-01-23 00:29:46.855355: step: 2028/530, loss: 0.15759029984474182
2023-01-23 00:29:48.006910: step: 2032/530, loss: 0.08128716796636581
2023-01-23 00:29:49.172908: step: 2036/530, loss: 0.6015458106994629
2023-01-23 00:29:50.311281: step: 2040/530, loss: 0.1496560126543045
2023-01-23 00:29:51.511665: step: 2044/530, loss: 0.21115809679031372
2023-01-23 00:29:52.682449: step: 2048/530, loss: 0.6047495007514954
2023-01-23 00:29:53.831295: step: 2052/530, loss: 0.006008625496178865
2023-01-23 00:29:55.042429: step: 2056/530, loss: 0.06735420227050781
2023-01-23 00:29:56.183753: step: 2060/530, loss: 0.1122509092092514
2023-01-23 00:29:57.362162: step: 2064/530, loss: 0.03537600114941597
2023-01-23 00:29:58.519089: step: 2068/530, loss: 0.1548711359500885
2023-01-23 00:29:59.666767: step: 2072/530, loss: 0.13152997195720673
2023-01-23 00:30:00.826380: step: 2076/530, loss: 0.033211804926395416
2023-01-23 00:30:01.959305: step: 2080/530, loss: 0.5364004969596863
2023-01-23 00:30:03.195153: step: 2084/530, loss: 0.052607253193855286
2023-01-23 00:30:04.405346: step: 2088/530, loss: 0.11160936951637268
2023-01-23 00:30:05.606400: step: 2092/530, loss: 0.10112962871789932
2023-01-23 00:30:06.746202: step: 2096/530, loss: 0.25139886140823364
2023-01-23 00:30:07.936370: step: 2100/530, loss: 0.07464206218719482
2023-01-23 00:30:09.132665: step: 2104/530, loss: 0.2184407263994217
2023-01-23 00:30:10.315579: step: 2108/530, loss: 0.3812035620212555
2023-01-23 00:30:11.460291: step: 2112/530, loss: 0.01790900155901909
2023-01-23 00:30:12.658101: step: 2116/530, loss: 0.20171022415161133
2023-01-23 00:30:13.835469: step: 2120/530, loss: 0.13600090146064758
==================================================
Loss: 0.284
--------------------
Dev: {'event': {'p': 0.5533333333333333, 'r': 0.7736351531291611, 'f1': 0.6451971127151582}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Test: {'event': {'p': 0.618983355825461, 'r': 0.7912593444508338, 'f1': 0.6945986875315496}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
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': 5}
Korean: {'event': {'p': 0.6226415094339622, 'r': 0.5238095238095238, 'f1': 0.5689655172413793}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Russian: {'event': {'p': 0.5227272727272727, 'r': 0.6388888888888888, 'f1': 0.575}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.5815160955347871, 'r': 0.7456724367509987, 'f1': 0.6534422403733957}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Chinese: {'event': {'p': 0.604882459312839, 'r': 0.7694077055779184, 'f1': 0.6772968868640851}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Chinese: {'event': {'p': 0.5402298850574713, 'r': 0.8703703703703703, 'f1': 0.6666666666666666}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5815160955347871, 'r': 0.7456724367509987, 'f1': 0.6534422403733957}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Korean: {'event': {'p': 0.604882459312839, 'r': 0.7694077055779184, 'f1': 0.6772968868640851}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Korean: {'event': {'p': 0.6666666666666666, 'r': 0.6031746031746031, 'f1': 0.6333333333333333}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5815160955347871, 'r': 0.7456724367509987, 'f1': 0.6534422403733957}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Russian: {'event': {'p': 0.604882459312839, 'r': 0.7694077055779184, 'f1': 0.6772968868640851}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Russian: {'event': {'p': 0.5348837209302325, 'r': 0.6388888888888888, 'f1': 0.5822784810126581}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
******************************
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 00:30:56.781464: step: 4/530, loss: 0.15994276106357574
2023-01-23 00:30:57.942597: step: 8/530, loss: 0.045320890843868256
2023-01-23 00:30:59.138890: step: 12/530, loss: 0.23048695921897888
2023-01-23 00:31:00.326802: step: 16/530, loss: 0.5394615530967712
2023-01-23 00:31:01.486192: step: 20/530, loss: 0.12582692503929138
2023-01-23 00:31:02.628014: step: 24/530, loss: 0.0660005584359169
2023-01-23 00:31:03.859675: step: 28/530, loss: 0.025230027735233307
2023-01-23 00:31:04.993680: step: 32/530, loss: 0.07103128731250763
2023-01-23 00:31:06.134256: step: 36/530, loss: 0.008608436211943626
2023-01-23 00:31:07.294259: step: 40/530, loss: 0.14398737251758575
2023-01-23 00:31:08.463803: step: 44/530, loss: 0.2719116508960724
2023-01-23 00:31:09.620793: step: 48/530, loss: 0.06196288764476776
2023-01-23 00:31:10.785253: step: 52/530, loss: 0.038278769701719284
2023-01-23 00:31:11.965059: step: 56/530, loss: 0.43912628293037415
2023-01-23 00:31:13.156959: step: 60/530, loss: 0.09541139751672745
2023-01-23 00:31:14.339343: step: 64/530, loss: 0.31967926025390625
2023-01-23 00:31:15.472526: step: 68/530, loss: 0.09328780323266983
2023-01-23 00:31:16.625542: step: 72/530, loss: 0.12033358216285706
2023-01-23 00:31:17.785496: step: 76/530, loss: 0.1217704489827156
2023-01-23 00:31:19.031579: step: 80/530, loss: 1.1162290573120117
2023-01-23 00:31:20.168709: step: 84/530, loss: 0.20260782539844513
2023-01-23 00:31:21.318150: step: 88/530, loss: 0.2975834310054779
2023-01-23 00:31:22.459062: step: 92/530, loss: 0.0790904089808464
2023-01-23 00:31:23.661341: step: 96/530, loss: 0.41175052523612976
2023-01-23 00:31:24.811685: step: 100/530, loss: 0.07524947822093964
2023-01-23 00:31:25.975931: step: 104/530, loss: 0.10713760554790497
2023-01-23 00:31:27.115735: step: 108/530, loss: 0.24148236215114594
2023-01-23 00:31:28.312867: step: 112/530, loss: 0.12252034991979599
2023-01-23 00:31:29.485360: step: 116/530, loss: 0.13124337792396545
2023-01-23 00:31:30.662282: step: 120/530, loss: 0.42690467834472656
2023-01-23 00:31:31.845233: step: 124/530, loss: 0.14836172759532928
2023-01-23 00:31:33.036677: step: 128/530, loss: 0.26024800539016724
2023-01-23 00:31:34.188082: step: 132/530, loss: 0.09583864361047745
2023-01-23 00:31:35.345421: step: 136/530, loss: 0.12546278536319733
2023-01-23 00:31:36.514266: step: 140/530, loss: 0.18270738422870636
2023-01-23 00:31:37.708310: step: 144/530, loss: 0.05501508712768555
2023-01-23 00:31:38.878630: step: 148/530, loss: 0.2854381501674652
2023-01-23 00:31:40.031356: step: 152/530, loss: 0.1291239857673645
2023-01-23 00:31:41.211332: step: 156/530, loss: 0.06799326092004776
2023-01-23 00:31:42.358783: step: 160/530, loss: 0.10171270370483398
2023-01-23 00:31:43.524343: step: 164/530, loss: 0.12280149757862091
2023-01-23 00:31:44.702692: step: 168/530, loss: 0.5371148586273193
2023-01-23 00:31:45.861250: step: 172/530, loss: 0.08669638633728027
2023-01-23 00:31:47.016402: step: 176/530, loss: 0.15250855684280396
2023-01-23 00:31:48.170321: step: 180/530, loss: 0.15418720245361328
2023-01-23 00:31:49.370930: step: 184/530, loss: 0.330893337726593
2023-01-23 00:31:50.508735: step: 188/530, loss: 0.11315040290355682
2023-01-23 00:31:51.678674: step: 192/530, loss: 0.08025212585926056
2023-01-23 00:31:52.873887: step: 196/530, loss: 0.027968013659119606
2023-01-23 00:31:54.081572: step: 200/530, loss: 0.126437708735466
2023-01-23 00:31:55.235259: step: 204/530, loss: 0.1817864030599594
2023-01-23 00:31:56.419930: step: 208/530, loss: 0.01971263810992241
2023-01-23 00:31:57.597448: step: 212/530, loss: 0.01996746100485325
2023-01-23 00:31:58.799490: step: 216/530, loss: 0.09121789783239365
2023-01-23 00:31:59.981597: step: 220/530, loss: 0.47318220138549805
2023-01-23 00:32:01.133044: step: 224/530, loss: 0.07102303206920624
2023-01-23 00:32:02.324327: step: 228/530, loss: 0.10886078327894211
2023-01-23 00:32:03.528381: step: 232/530, loss: 0.1321459859609604
2023-01-23 00:32:04.743627: step: 236/530, loss: 0.11014099419116974
2023-01-23 00:32:05.931098: step: 240/530, loss: 0.41911324858665466
2023-01-23 00:32:07.104794: step: 244/530, loss: 0.1504814177751541
2023-01-23 00:32:08.277634: step: 248/530, loss: 0.06883887946605682
2023-01-23 00:32:09.422369: step: 252/530, loss: 0.0356929786503315
2023-01-23 00:32:10.621860: step: 256/530, loss: 0.013660860247910023
2023-01-23 00:32:11.815271: step: 260/530, loss: 0.18641920387744904
2023-01-23 00:32:13.007210: step: 264/530, loss: 0.06180419772863388
2023-01-23 00:32:14.163484: step: 268/530, loss: 0.08162336051464081
2023-01-23 00:32:15.288445: step: 272/530, loss: 0.17799797654151917
2023-01-23 00:32:16.421236: step: 276/530, loss: 0.0578128844499588
2023-01-23 00:32:17.583636: step: 280/530, loss: 0.09725475311279297
2023-01-23 00:32:18.756413: step: 284/530, loss: 0.08963232487440109
2023-01-23 00:32:19.905812: step: 288/530, loss: 0.37990498542785645
2023-01-23 00:32:21.059386: step: 292/530, loss: 0.03215036541223526
2023-01-23 00:32:22.234429: step: 296/530, loss: 0.064191535115242
2023-01-23 00:32:23.395407: step: 300/530, loss: 0.08762683719396591
2023-01-23 00:32:24.548514: step: 304/530, loss: 0.05148515850305557
2023-01-23 00:32:25.705437: step: 308/530, loss: 0.17682066559791565
2023-01-23 00:32:26.900985: step: 312/530, loss: 0.17495641112327576
2023-01-23 00:32:28.047261: step: 316/530, loss: 0.022137831896543503
2023-01-23 00:32:29.215079: step: 320/530, loss: 0.07729358971118927
2023-01-23 00:32:30.397275: step: 324/530, loss: 0.06603336334228516
2023-01-23 00:32:31.593867: step: 328/530, loss: 0.11373010277748108
2023-01-23 00:32:32.757807: step: 332/530, loss: 0.049485016614198685
2023-01-23 00:32:33.951036: step: 336/530, loss: 0.4607907235622406
2023-01-23 00:32:35.084602: step: 340/530, loss: 0.12253957241773605
2023-01-23 00:32:36.272371: step: 344/530, loss: 0.0044678207486867905
2023-01-23 00:32:37.436476: step: 348/530, loss: 0.0903073325753212
2023-01-23 00:32:38.596421: step: 352/530, loss: 0.06629905849695206
2023-01-23 00:32:39.770651: step: 356/530, loss: 0.14650268852710724
2023-01-23 00:32:40.929549: step: 360/530, loss: 0.08548612892627716
2023-01-23 00:32:42.096925: step: 364/530, loss: 0.35773396492004395
2023-01-23 00:32:43.238320: step: 368/530, loss: 0.01766963116824627
2023-01-23 00:32:44.419602: step: 372/530, loss: 0.016019249334931374
2023-01-23 00:32:45.614155: step: 376/530, loss: 0.09293222427368164
2023-01-23 00:32:46.752713: step: 380/530, loss: 0.030004145577549934
2023-01-23 00:32:47.927596: step: 384/530, loss: 0.12180319428443909
2023-01-23 00:32:49.110503: step: 388/530, loss: 0.9566667079925537
2023-01-23 00:32:50.283642: step: 392/530, loss: 0.024489833042025566
2023-01-23 00:32:51.513744: step: 396/530, loss: 0.1741258203983307
2023-01-23 00:32:52.665251: step: 400/530, loss: 0.06589307636022568
2023-01-23 00:32:53.821365: step: 404/530, loss: 0.6494244337081909
2023-01-23 00:32:54.977360: step: 408/530, loss: 0.09843003749847412
2023-01-23 00:32:56.133370: step: 412/530, loss: 0.10757436603307724
2023-01-23 00:32:57.293930: step: 416/530, loss: 0.025983812287449837
2023-01-23 00:32:58.461793: step: 420/530, loss: 0.08584971725940704
2023-01-23 00:32:59.619799: step: 424/530, loss: 0.13532963395118713
2023-01-23 00:33:00.737139: step: 428/530, loss: 0.003741312073543668
2023-01-23 00:33:01.977927: step: 432/530, loss: 0.5738229155540466
2023-01-23 00:33:03.171418: step: 436/530, loss: 0.1531471312046051
2023-01-23 00:33:04.404876: step: 440/530, loss: 0.1867099404335022
2023-01-23 00:33:05.562660: step: 444/530, loss: 0.02309880219399929
2023-01-23 00:33:06.746728: step: 448/530, loss: 0.6170173287391663
2023-01-23 00:33:07.885888: step: 452/530, loss: 0.4096931517124176
2023-01-23 00:33:09.024270: step: 456/530, loss: 0.08182539790868759
2023-01-23 00:33:10.190575: step: 460/530, loss: 0.0717935562133789
2023-01-23 00:33:11.335447: step: 464/530, loss: 0.05641374737024307
2023-01-23 00:33:12.511787: step: 468/530, loss: 0.08361849933862686
2023-01-23 00:33:13.685557: step: 472/530, loss: 0.15602579712867737
2023-01-23 00:33:14.840013: step: 476/530, loss: 0.34944647550582886
2023-01-23 00:33:16.018576: step: 480/530, loss: 0.10817337036132812
2023-01-23 00:33:17.197690: step: 484/530, loss: 0.057747554033994675
2023-01-23 00:33:18.377635: step: 488/530, loss: 0.05795030668377876
2023-01-23 00:33:19.498376: step: 492/530, loss: 0.02306889370083809
2023-01-23 00:33:20.714727: step: 496/530, loss: 0.1557292938232422
2023-01-23 00:33:21.869792: step: 500/530, loss: 0.1702808439731598
2023-01-23 00:33:23.001054: step: 504/530, loss: 0.11404943466186523
2023-01-23 00:33:24.176178: step: 508/530, loss: 0.2544203996658325
2023-01-23 00:33:25.392546: step: 512/530, loss: 0.03190431743860245
2023-01-23 00:33:26.571404: step: 516/530, loss: 0.07754459977149963
2023-01-23 00:33:27.743011: step: 520/530, loss: 0.06305336952209473
2023-01-23 00:33:28.884248: step: 524/530, loss: 0.17399534583091736
2023-01-23 00:33:30.087830: step: 528/530, loss: 0.2367015779018402
2023-01-23 00:33:31.245972: step: 532/530, loss: 0.05527792125940323
2023-01-23 00:33:32.443316: step: 536/530, loss: 0.12429256737232208
2023-01-23 00:33:33.623347: step: 540/530, loss: 0.09126138687133789
2023-01-23 00:33:34.798049: step: 544/530, loss: 0.11814985424280167
2023-01-23 00:33:35.930937: step: 548/530, loss: 0.07085929065942764
2023-01-23 00:33:37.120939: step: 552/530, loss: 0.6980571746826172
2023-01-23 00:33:38.320600: step: 556/530, loss: 0.035009339451789856
2023-01-23 00:33:39.502085: step: 560/530, loss: 0.06832804530858994
2023-01-23 00:33:40.690401: step: 564/530, loss: 0.14165955781936646
2023-01-23 00:33:41.903566: step: 568/530, loss: 0.21956318616867065
2023-01-23 00:33:43.083098: step: 572/530, loss: 0.2013145387172699
2023-01-23 00:33:44.238742: step: 576/530, loss: 0.03372984007000923
2023-01-23 00:33:45.374818: step: 580/530, loss: 0.0470459945499897
2023-01-23 00:33:46.523660: step: 584/530, loss: 0.08859510719776154
2023-01-23 00:33:47.705728: step: 588/530, loss: 0.04225621372461319
2023-01-23 00:33:48.929853: step: 592/530, loss: 0.02696380764245987
2023-01-23 00:33:50.101338: step: 596/530, loss: 0.21186891198158264
2023-01-23 00:33:51.265293: step: 600/530, loss: 0.3758409321308136
2023-01-23 00:33:52.426575: step: 604/530, loss: 0.5602823495864868
2023-01-23 00:33:53.589301: step: 608/530, loss: 0.245101660490036
2023-01-23 00:33:54.796176: step: 612/530, loss: 0.09078064560890198
2023-01-23 00:33:55.937905: step: 616/530, loss: 0.022649575024843216
2023-01-23 00:33:57.158632: step: 620/530, loss: 0.1233924850821495
2023-01-23 00:33:58.328271: step: 624/530, loss: 0.15088967978954315
2023-01-23 00:33:59.448258: step: 628/530, loss: 0.08727141469717026
2023-01-23 00:34:00.622956: step: 632/530, loss: 0.10299844294786453
2023-01-23 00:34:01.802334: step: 636/530, loss: 0.1713005155324936
2023-01-23 00:34:03.020265: step: 640/530, loss: 0.10300713032484055
2023-01-23 00:34:04.176991: step: 644/530, loss: 0.7526707053184509
2023-01-23 00:34:05.307443: step: 648/530, loss: 0.019948624074459076
2023-01-23 00:34:06.492672: step: 652/530, loss: 0.2461063414812088
2023-01-23 00:34:07.680525: step: 656/530, loss: 0.15502089262008667
2023-01-23 00:34:08.872815: step: 660/530, loss: 0.41894522309303284
2023-01-23 00:34:10.046405: step: 664/530, loss: 0.4066603481769562
2023-01-23 00:34:11.242165: step: 668/530, loss: 0.15502452850341797
2023-01-23 00:34:12.434823: step: 672/530, loss: 0.4313339293003082
2023-01-23 00:34:13.588676: step: 676/530, loss: 0.48768892884254456
2023-01-23 00:34:14.811011: step: 680/530, loss: 0.11617843806743622
2023-01-23 00:34:15.938133: step: 684/530, loss: 0.13444571197032928
2023-01-23 00:34:17.089296: step: 688/530, loss: 0.37437766790390015
2023-01-23 00:34:18.236916: step: 692/530, loss: 0.07187018543481827
2023-01-23 00:34:19.391782: step: 696/530, loss: 0.11756696552038193
2023-01-23 00:34:20.592620: step: 700/530, loss: 3.940164566040039
2023-01-23 00:34:21.784697: step: 704/530, loss: 0.06498441845178604
2023-01-23 00:34:22.980486: step: 708/530, loss: 0.2053930014371872
2023-01-23 00:34:24.132992: step: 712/530, loss: 0.07378659397363663
2023-01-23 00:34:25.286733: step: 716/530, loss: 0.18421611189842224
2023-01-23 00:34:26.469997: step: 720/530, loss: 0.10775584727525711
2023-01-23 00:34:27.638132: step: 724/530, loss: 0.08516879379749298
2023-01-23 00:34:28.807256: step: 728/530, loss: 0.08640408515930176
2023-01-23 00:34:29.940735: step: 732/530, loss: 0.09573392570018768
2023-01-23 00:34:31.079619: step: 736/530, loss: 0.11057873070240021
2023-01-23 00:34:32.262409: step: 740/530, loss: 0.06999216228723526
2023-01-23 00:34:33.443555: step: 744/530, loss: 0.1182766929268837
2023-01-23 00:34:34.622714: step: 748/530, loss: 0.04304523393511772
2023-01-23 00:34:35.800026: step: 752/530, loss: 0.2601346969604492
2023-01-23 00:34:37.001800: step: 756/530, loss: 0.01540765818208456
2023-01-23 00:34:38.202766: step: 760/530, loss: 0.11564979702234268
2023-01-23 00:34:39.410115: step: 764/530, loss: 0.11279264092445374
2023-01-23 00:34:40.580857: step: 768/530, loss: 0.46986180543899536
2023-01-23 00:34:41.758084: step: 772/530, loss: 0.05500664934515953
2023-01-23 00:34:42.977053: step: 776/530, loss: 0.04750258848071098
2023-01-23 00:34:44.168366: step: 780/530, loss: 0.06596078723669052
2023-01-23 00:34:45.335054: step: 784/530, loss: 0.21787172555923462
2023-01-23 00:34:46.505286: step: 788/530, loss: 0.1595068871974945
2023-01-23 00:34:47.650767: step: 792/530, loss: 0.0601864829659462
2023-01-23 00:34:48.836754: step: 796/530, loss: 0.18331070244312286
2023-01-23 00:34:50.005084: step: 800/530, loss: 0.08046464622020721
2023-01-23 00:34:51.178579: step: 804/530, loss: 0.19010934233665466
2023-01-23 00:34:52.345785: step: 808/530, loss: 1.52919340133667
2023-01-23 00:34:53.528550: step: 812/530, loss: 0.17202357947826385
2023-01-23 00:34:54.711744: step: 816/530, loss: 0.04172716289758682
2023-01-23 00:34:55.892374: step: 820/530, loss: 0.03725111484527588
2023-01-23 00:34:57.050826: step: 824/530, loss: 0.04828687012195587
2023-01-23 00:34:58.272188: step: 828/530, loss: 0.05922241136431694
2023-01-23 00:34:59.526007: step: 832/530, loss: 0.21861086785793304
2023-01-23 00:35:00.694992: step: 836/530, loss: 0.09946451336145401
2023-01-23 00:35:01.837522: step: 840/530, loss: 0.8517389297485352
2023-01-23 00:35:02.968263: step: 844/530, loss: 0.09241466969251633
2023-01-23 00:35:04.135322: step: 848/530, loss: 0.12905187904834747
2023-01-23 00:35:05.259547: step: 852/530, loss: 0.030449392274022102
2023-01-23 00:35:06.369467: step: 856/530, loss: 0.08473119884729385
2023-01-23 00:35:07.584306: step: 860/530, loss: 0.2513468861579895
2023-01-23 00:35:08.779994: step: 864/530, loss: 0.03664522245526314
2023-01-23 00:35:09.967440: step: 868/530, loss: 0.08919048309326172
2023-01-23 00:35:11.178515: step: 872/530, loss: 0.2815885543823242
2023-01-23 00:35:12.396689: step: 876/530, loss: 0.062203314155340195
2023-01-23 00:35:13.570827: step: 880/530, loss: 0.04152614623308182
2023-01-23 00:35:14.736452: step: 884/530, loss: 0.01859750598669052
2023-01-23 00:35:15.916771: step: 888/530, loss: 0.1269826889038086
2023-01-23 00:35:17.091288: step: 892/530, loss: 0.28606393933296204
2023-01-23 00:35:18.233504: step: 896/530, loss: 0.29924410581588745
2023-01-23 00:35:19.367015: step: 900/530, loss: 0.06352901458740234
2023-01-23 00:35:20.502086: step: 904/530, loss: 0.33215630054473877
2023-01-23 00:35:21.676404: step: 908/530, loss: 0.09093455970287323
2023-01-23 00:35:22.883116: step: 912/530, loss: 0.15749092400074005
2023-01-23 00:35:24.062686: step: 916/530, loss: 0.38159170746803284
2023-01-23 00:35:25.217698: step: 920/530, loss: 0.3248440623283386
2023-01-23 00:35:26.355522: step: 924/530, loss: 0.3977890908718109
2023-01-23 00:35:27.504237: step: 928/530, loss: 0.277304083108902
2023-01-23 00:35:28.687383: step: 932/530, loss: 0.17513667047023773
2023-01-23 00:35:29.859147: step: 936/530, loss: 0.12967829406261444
2023-01-23 00:35:31.042686: step: 940/530, loss: 0.1831471472978592
2023-01-23 00:35:32.217149: step: 944/530, loss: 0.30447331070899963
2023-01-23 00:35:33.385355: step: 948/530, loss: 0.07016663998365402
2023-01-23 00:35:34.574320: step: 952/530, loss: 0.22592414915561676
2023-01-23 00:35:35.732874: step: 956/530, loss: 0.3500085771083832
2023-01-23 00:35:36.895030: step: 960/530, loss: 0.16564425826072693
2023-01-23 00:35:38.087872: step: 964/530, loss: 0.08719868957996368
2023-01-23 00:35:39.242736: step: 968/530, loss: 0.04791107028722763
2023-01-23 00:35:40.407871: step: 972/530, loss: 0.104514479637146
2023-01-23 00:35:41.574250: step: 976/530, loss: 0.072528176009655
2023-01-23 00:35:42.775462: step: 980/530, loss: 0.1263895034790039
2023-01-23 00:35:43.932838: step: 984/530, loss: 0.22149062156677246
2023-01-23 00:35:45.083666: step: 988/530, loss: 0.11591244488954544
2023-01-23 00:35:46.225616: step: 992/530, loss: 0.11690769344568253
2023-01-23 00:35:47.403408: step: 996/530, loss: 0.08022499829530716
2023-01-23 00:35:48.601728: step: 1000/530, loss: 0.26442793011665344
2023-01-23 00:35:49.793250: step: 1004/530, loss: 0.5984104871749878
2023-01-23 00:35:50.991978: step: 1008/530, loss: 0.045149803161621094
2023-01-23 00:35:52.170325: step: 1012/530, loss: 0.37886887788772583
2023-01-23 00:35:53.348880: step: 1016/530, loss: 0.014014697633683681
2023-01-23 00:35:54.511075: step: 1020/530, loss: 0.25458794832229614
2023-01-23 00:35:55.677732: step: 1024/530, loss: 0.13895197212696075
2023-01-23 00:35:56.887454: step: 1028/530, loss: 0.0756019577383995
2023-01-23 00:35:58.066438: step: 1032/530, loss: 0.266292005777359
2023-01-23 00:35:59.236200: step: 1036/530, loss: 0.04258022457361221
2023-01-23 00:36:00.409325: step: 1040/530, loss: 0.001929426216520369
2023-01-23 00:36:01.600538: step: 1044/530, loss: 0.08785466849803925
2023-01-23 00:36:02.748101: step: 1048/530, loss: 0.23387575149536133
2023-01-23 00:36:03.945334: step: 1052/530, loss: 0.17601117491722107
2023-01-23 00:36:05.101892: step: 1056/530, loss: 0.3353537619113922
2023-01-23 00:36:06.264462: step: 1060/530, loss: 0.4735613763332367
2023-01-23 00:36:07.425193: step: 1064/530, loss: 0.2276001274585724
2023-01-23 00:36:08.615475: step: 1068/530, loss: 0.6217465400695801
2023-01-23 00:36:09.783073: step: 1072/530, loss: 0.7792909741401672
2023-01-23 00:36:10.922492: step: 1076/530, loss: 0.15578937530517578
2023-01-23 00:36:12.088907: step: 1080/530, loss: 0.22179098427295685
2023-01-23 00:36:13.247628: step: 1084/530, loss: 1.0540108680725098
2023-01-23 00:36:14.384944: step: 1088/530, loss: 0.21569758653640747
2023-01-23 00:36:15.632872: step: 1092/530, loss: 0.04044456407427788
2023-01-23 00:36:16.788361: step: 1096/530, loss: 0.22390252351760864
2023-01-23 00:36:17.957274: step: 1100/530, loss: 0.05426378548145294
2023-01-23 00:36:19.122768: step: 1104/530, loss: 0.11736168712377548
2023-01-23 00:36:20.275748: step: 1108/530, loss: 0.031081369146704674
2023-01-23 00:36:21.460699: step: 1112/530, loss: 0.16550886631011963
2023-01-23 00:36:22.645238: step: 1116/530, loss: 0.06916656345129013
2023-01-23 00:36:23.835247: step: 1120/530, loss: 0.4130594730377197
2023-01-23 00:36:25.006804: step: 1124/530, loss: 0.026887942105531693
2023-01-23 00:36:26.197732: step: 1128/530, loss: 0.024235010147094727
2023-01-23 00:36:27.368454: step: 1132/530, loss: 0.21376925706863403
2023-01-23 00:36:28.489974: step: 1136/530, loss: 0.07202515751123428
2023-01-23 00:36:29.652777: step: 1140/530, loss: 0.15049400925636292
2023-01-23 00:36:30.807764: step: 1144/530, loss: 0.07807321846485138
2023-01-23 00:36:32.036099: step: 1148/530, loss: 0.4974941313266754
2023-01-23 00:36:33.198837: step: 1152/530, loss: 0.08205976337194443
2023-01-23 00:36:34.371962: step: 1156/530, loss: 0.29773080348968506
2023-01-23 00:36:35.557065: step: 1160/530, loss: 0.10683698952198029
2023-01-23 00:36:36.738969: step: 1164/530, loss: 0.1837387979030609
2023-01-23 00:36:37.880144: step: 1168/530, loss: 0.0656818374991417
2023-01-23 00:36:39.057365: step: 1172/530, loss: 0.022454883903265
2023-01-23 00:36:40.219294: step: 1176/530, loss: 0.2713330388069153
2023-01-23 00:36:41.390159: step: 1180/530, loss: 0.23397935926914215
2023-01-23 00:36:42.565596: step: 1184/530, loss: 0.02392716519534588
2023-01-23 00:36:43.731354: step: 1188/530, loss: 0.18648405373096466
2023-01-23 00:36:44.932881: step: 1192/530, loss: 0.32331523299217224
2023-01-23 00:36:46.089921: step: 1196/530, loss: 0.40959683060646057
2023-01-23 00:36:47.279475: step: 1200/530, loss: 0.0525268130004406
2023-01-23 00:36:48.479877: step: 1204/530, loss: 0.10861825942993164
2023-01-23 00:36:49.658554: step: 1208/530, loss: 0.6877531409263611
2023-01-23 00:36:50.823189: step: 1212/530, loss: 0.12965837121009827
2023-01-23 00:36:51.989900: step: 1216/530, loss: 0.07224531471729279
2023-01-23 00:36:53.173081: step: 1220/530, loss: 0.11181239783763885
2023-01-23 00:36:54.369152: step: 1224/530, loss: 0.5127602815628052
2023-01-23 00:36:55.609188: step: 1228/530, loss: 0.07286586612462997
2023-01-23 00:36:56.785985: step: 1232/530, loss: 0.10349297523498535
2023-01-23 00:36:57.906914: step: 1236/530, loss: 0.17519474029541016
2023-01-23 00:36:59.107165: step: 1240/530, loss: 0.31951475143432617
2023-01-23 00:37:00.297025: step: 1244/530, loss: 0.2518370747566223
2023-01-23 00:37:01.456639: step: 1248/530, loss: 0.17135295271873474
2023-01-23 00:37:02.575230: step: 1252/530, loss: 0.10881710052490234
2023-01-23 00:37:03.796728: step: 1256/530, loss: 0.22652125358581543
2023-01-23 00:37:04.984650: step: 1260/530, loss: 0.11236973106861115
2023-01-23 00:37:06.160915: step: 1264/530, loss: 0.06836242973804474
2023-01-23 00:37:07.325355: step: 1268/530, loss: 0.24818316102027893
2023-01-23 00:37:08.507313: step: 1272/530, loss: 0.14482879638671875
2023-01-23 00:37:09.691507: step: 1276/530, loss: 0.41327062249183655
2023-01-23 00:37:10.849146: step: 1280/530, loss: 0.1635892391204834
2023-01-23 00:37:12.049300: step: 1284/530, loss: 0.2615838348865509
2023-01-23 00:37:13.213307: step: 1288/530, loss: 0.254215806722641
2023-01-23 00:37:14.435183: step: 1292/530, loss: 0.09254173934459686
2023-01-23 00:37:15.658999: step: 1296/530, loss: 0.22869205474853516
2023-01-23 00:37:16.817827: step: 1300/530, loss: 0.21679291129112244
2023-01-23 00:37:18.043597: step: 1304/530, loss: 0.2935813069343567
2023-01-23 00:37:19.182170: step: 1308/530, loss: 0.058591797947883606
2023-01-23 00:37:20.391510: step: 1312/530, loss: 0.11359415203332901
2023-01-23 00:37:21.563169: step: 1316/530, loss: 0.12141337990760803
2023-01-23 00:37:22.711736: step: 1320/530, loss: 0.04539071023464203
2023-01-23 00:37:23.873506: step: 1324/530, loss: 0.4009132385253906
2023-01-23 00:37:25.020813: step: 1328/530, loss: 0.20982302725315094
2023-01-23 00:37:26.158255: step: 1332/530, loss: 0.02230815961956978
2023-01-23 00:37:27.371594: step: 1336/530, loss: 0.17309704422950745
2023-01-23 00:37:28.570254: step: 1340/530, loss: 0.27344274520874023
2023-01-23 00:37:29.720748: step: 1344/530, loss: 0.13963204622268677
2023-01-23 00:37:30.922414: step: 1348/530, loss: 0.20550794899463654
2023-01-23 00:37:32.059572: step: 1352/530, loss: 0.06766577064990997
2023-01-23 00:37:33.216268: step: 1356/530, loss: 0.11327500641345978
2023-01-23 00:37:34.403189: step: 1360/530, loss: 0.042272426187992096
2023-01-23 00:37:35.579429: step: 1364/530, loss: 0.18981322646141052
2023-01-23 00:37:36.747116: step: 1368/530, loss: 0.13702067732810974
2023-01-23 00:37:37.925274: step: 1372/530, loss: 0.0883081704378128
2023-01-23 00:37:39.124076: step: 1376/530, loss: 0.06375580281019211
2023-01-23 00:37:40.310795: step: 1380/530, loss: 0.4949127733707428
2023-01-23 00:37:41.464398: step: 1384/530, loss: 0.18713369965553284
2023-01-23 00:37:42.682915: step: 1388/530, loss: 0.5032480955123901
2023-01-23 00:37:43.907343: step: 1392/530, loss: 0.44389107823371887
2023-01-23 00:37:45.058288: step: 1396/530, loss: 0.16145333647727966
2023-01-23 00:37:46.222732: step: 1400/530, loss: 0.11670824885368347
2023-01-23 00:37:47.371397: step: 1404/530, loss: 0.6060651540756226
2023-01-23 00:37:48.539998: step: 1408/530, loss: 0.1625884771347046
2023-01-23 00:37:49.701643: step: 1412/530, loss: 0.21657666563987732
2023-01-23 00:37:50.881102: step: 1416/530, loss: 0.3495885729789734
2023-01-23 00:37:52.091454: step: 1420/530, loss: 0.09297314286231995
2023-01-23 00:37:53.298223: step: 1424/530, loss: 0.3674611747264862
2023-01-23 00:37:54.461406: step: 1428/530, loss: 0.2757939398288727
2023-01-23 00:37:55.633976: step: 1432/530, loss: 0.05768880993127823
2023-01-23 00:37:56.816625: step: 1436/530, loss: 0.03877716138958931
2023-01-23 00:37:57.982793: step: 1440/530, loss: 0.20939913392066956
2023-01-23 00:37:59.157877: step: 1444/530, loss: 0.053881026804447174
2023-01-23 00:38:00.393919: step: 1448/530, loss: 0.15194934606552124
2023-01-23 00:38:01.603996: step: 1452/530, loss: 0.02866850048303604
2023-01-23 00:38:02.810490: step: 1456/530, loss: 0.02809877321124077
2023-01-23 00:38:04.007129: step: 1460/530, loss: 0.38257598876953125
2023-01-23 00:38:05.164784: step: 1464/530, loss: 0.09262686222791672
2023-01-23 00:38:06.374553: step: 1468/530, loss: 0.16281461715698242
2023-01-23 00:38:07.561267: step: 1472/530, loss: 0.5011531710624695
2023-01-23 00:38:08.692189: step: 1476/530, loss: 0.10147133469581604
2023-01-23 00:38:09.834987: step: 1480/530, loss: 0.18984031677246094
2023-01-23 00:38:11.036050: step: 1484/530, loss: 0.13359498977661133
2023-01-23 00:38:12.299008: step: 1488/530, loss: 0.06452690809965134
2023-01-23 00:38:13.485362: step: 1492/530, loss: 0.1623123288154602
2023-01-23 00:38:14.658165: step: 1496/530, loss: 0.21236935257911682
2023-01-23 00:38:15.803652: step: 1500/530, loss: 0.07098865509033203
2023-01-23 00:38:17.016246: step: 1504/530, loss: 0.21271392703056335
2023-01-23 00:38:18.166247: step: 1508/530, loss: 0.167958065867424
2023-01-23 00:38:19.376390: step: 1512/530, loss: 0.19202661514282227
2023-01-23 00:38:20.576232: step: 1516/530, loss: 0.05480156093835831
2023-01-23 00:38:21.720247: step: 1520/530, loss: 0.3604586720466614
2023-01-23 00:38:22.907542: step: 1524/530, loss: 0.11887330561876297
2023-01-23 00:38:24.096080: step: 1528/530, loss: 0.026724625378847122
2023-01-23 00:38:25.270932: step: 1532/530, loss: 0.05379314720630646
2023-01-23 00:38:26.453145: step: 1536/530, loss: 0.6916292309761047
2023-01-23 00:38:27.625344: step: 1540/530, loss: 0.060868166387081146
2023-01-23 00:38:28.814277: step: 1544/530, loss: 0.17217856645584106
2023-01-23 00:38:30.022504: step: 1548/530, loss: 0.06487293541431427
2023-01-23 00:38:31.237562: step: 1552/530, loss: 0.9422714710235596
2023-01-23 00:38:32.389501: step: 1556/530, loss: 0.0428529754281044
2023-01-23 00:38:33.552643: step: 1560/530, loss: 0.3080798089504242
2023-01-23 00:38:34.723918: step: 1564/530, loss: 0.11116448044776917
2023-01-23 00:38:35.887820: step: 1568/530, loss: 0.4356522560119629
2023-01-23 00:38:37.019965: step: 1572/530, loss: 0.12339887768030167
2023-01-23 00:38:38.178508: step: 1576/530, loss: 0.7481446266174316
2023-01-23 00:38:39.396858: step: 1580/530, loss: 0.2189142107963562
2023-01-23 00:38:40.534371: step: 1584/530, loss: 0.04491496458649635
2023-01-23 00:38:41.700064: step: 1588/530, loss: 0.1289730966091156
2023-01-23 00:38:42.929804: step: 1592/530, loss: 0.5015445947647095
2023-01-23 00:38:44.071449: step: 1596/530, loss: 0.1384941041469574
2023-01-23 00:38:45.264620: step: 1600/530, loss: 0.26652345061302185
2023-01-23 00:38:46.452688: step: 1604/530, loss: 0.037052348256111145
2023-01-23 00:38:47.588980: step: 1608/530, loss: 0.06890163570642471
2023-01-23 00:38:48.770156: step: 1612/530, loss: 0.1330997496843338
2023-01-23 00:38:49.966461: step: 1616/530, loss: 0.024618053808808327
2023-01-23 00:38:51.156428: step: 1620/530, loss: 0.10659518837928772
2023-01-23 00:38:52.289006: step: 1624/530, loss: 1.145443320274353
2023-01-23 00:38:53.491020: step: 1628/530, loss: 0.22101622819900513
2023-01-23 00:38:54.648102: step: 1632/530, loss: 0.0627477690577507
2023-01-23 00:38:55.782264: step: 1636/530, loss: 0.42687684297561646
2023-01-23 00:38:56.959365: step: 1640/530, loss: 0.08497443050146103
2023-01-23 00:38:58.137887: step: 1644/530, loss: 0.7222959399223328
2023-01-23 00:38:59.305679: step: 1648/530, loss: 0.25410300493240356
2023-01-23 00:39:00.461836: step: 1652/530, loss: 0.04539642482995987
2023-01-23 00:39:01.626002: step: 1656/530, loss: 0.07592014968395233
2023-01-23 00:39:02.873122: step: 1660/530, loss: 0.09428376704454422
2023-01-23 00:39:04.070746: step: 1664/530, loss: 0.09538131207227707
2023-01-23 00:39:05.239460: step: 1668/530, loss: 0.09697631001472473
2023-01-23 00:39:06.410552: step: 1672/530, loss: 0.5140761733055115
2023-01-23 00:39:07.605642: step: 1676/530, loss: 0.18768806755542755
2023-01-23 00:39:08.791552: step: 1680/530, loss: 0.1679764688014984
2023-01-23 00:39:09.966742: step: 1684/530, loss: 0.17716084420681
2023-01-23 00:39:11.154005: step: 1688/530, loss: 0.30185890197753906
2023-01-23 00:39:12.361472: step: 1692/530, loss: 0.11596088111400604
2023-01-23 00:39:13.502101: step: 1696/530, loss: 0.08103790879249573
2023-01-23 00:39:14.706531: step: 1700/530, loss: 0.2951926290988922
2023-01-23 00:39:15.892430: step: 1704/530, loss: 0.15465545654296875
2023-01-23 00:39:17.084415: step: 1708/530, loss: 0.19264689087867737
2023-01-23 00:39:18.231266: step: 1712/530, loss: 0.1892094612121582
2023-01-23 00:39:19.405608: step: 1716/530, loss: 0.18235455453395844
2023-01-23 00:39:20.589480: step: 1720/530, loss: 0.47205695509910583
2023-01-23 00:39:21.792315: step: 1724/530, loss: 0.4763912260532379
2023-01-23 00:39:22.941746: step: 1728/530, loss: 0.20937252044677734
2023-01-23 00:39:24.126146: step: 1732/530, loss: 0.08466408401727676
2023-01-23 00:39:25.299625: step: 1736/530, loss: 0.079167939722538
2023-01-23 00:39:26.476050: step: 1740/530, loss: 0.1463976800441742
2023-01-23 00:39:27.656538: step: 1744/530, loss: 0.22479954361915588
2023-01-23 00:39:28.853473: step: 1748/530, loss: 0.11581498384475708
2023-01-23 00:39:30.012215: step: 1752/530, loss: 0.07075386494398117
2023-01-23 00:39:31.168151: step: 1756/530, loss: 0.03870382532477379
2023-01-23 00:39:32.325450: step: 1760/530, loss: 0.05649767071008682
2023-01-23 00:39:33.475760: step: 1764/530, loss: 0.20501813292503357
2023-01-23 00:39:34.651905: step: 1768/530, loss: 0.45368680357933044
2023-01-23 00:39:35.875772: step: 1772/530, loss: 0.1366896629333496
2023-01-23 00:39:37.041585: step: 1776/530, loss: 0.06291971355676651
2023-01-23 00:39:38.192723: step: 1780/530, loss: 0.03423266485333443
2023-01-23 00:39:39.396672: step: 1784/530, loss: 0.358668714761734
2023-01-23 00:39:40.564900: step: 1788/530, loss: 0.1780066043138504
2023-01-23 00:39:41.720850: step: 1792/530, loss: 0.04669199138879776
2023-01-23 00:39:42.878047: step: 1796/530, loss: 0.08929596096277237
2023-01-23 00:39:44.108507: step: 1800/530, loss: 0.4923345446586609
2023-01-23 00:39:45.290882: step: 1804/530, loss: 0.18945695459842682
2023-01-23 00:39:46.425389: step: 1808/530, loss: 0.2367473542690277
2023-01-23 00:39:47.606755: step: 1812/530, loss: 0.16152162849903107
2023-01-23 00:39:48.758736: step: 1816/530, loss: 0.04120578616857529
2023-01-23 00:39:49.931802: step: 1820/530, loss: 0.010090827941894531
2023-01-23 00:39:51.147184: step: 1824/530, loss: 0.3527812063694
2023-01-23 00:39:52.311995: step: 1828/530, loss: 0.07495997101068497
2023-01-23 00:39:53.498220: step: 1832/530, loss: 0.09046153724193573
2023-01-23 00:39:54.642649: step: 1836/530, loss: 0.283687949180603
2023-01-23 00:39:55.850153: step: 1840/530, loss: 0.09865465015172958
2023-01-23 00:39:57.010448: step: 1844/530, loss: 0.03781280666589737
2023-01-23 00:39:58.202261: step: 1848/530, loss: 0.08862370997667313
2023-01-23 00:39:59.388846: step: 1852/530, loss: 0.04232124984264374
2023-01-23 00:40:00.554859: step: 1856/530, loss: 0.11981821805238724
2023-01-23 00:40:01.746533: step: 1860/530, loss: 0.07902250438928604
2023-01-23 00:40:02.888291: step: 1864/530, loss: 0.17948079109191895
2023-01-23 00:40:04.051177: step: 1868/530, loss: 0.7560935616493225
2023-01-23 00:40:05.227870: step: 1872/530, loss: 0.17908230423927307
2023-01-23 00:40:06.370802: step: 1876/530, loss: 0.0672379583120346
2023-01-23 00:40:07.518558: step: 1880/530, loss: 0.19324421882629395
2023-01-23 00:40:08.679921: step: 1884/530, loss: 0.1315620392560959
2023-01-23 00:40:09.915894: step: 1888/530, loss: 1.4661343097686768
2023-01-23 00:40:11.064687: step: 1892/530, loss: 0.04889678955078125
2023-01-23 00:40:12.249872: step: 1896/530, loss: 1.085402250289917
2023-01-23 00:40:13.423392: step: 1900/530, loss: 0.19848766922950745
2023-01-23 00:40:14.612007: step: 1904/530, loss: 0.03242054209113121
2023-01-23 00:40:15.790210: step: 1908/530, loss: 0.08120203763246536
2023-01-23 00:40:16.965827: step: 1912/530, loss: 0.16075477004051208
2023-01-23 00:40:18.084951: step: 1916/530, loss: 0.9542765021324158
2023-01-23 00:40:19.256478: step: 1920/530, loss: 0.061582375317811966
2023-01-23 00:40:20.440927: step: 1924/530, loss: 0.13597260415554047
2023-01-23 00:40:21.607126: step: 1928/530, loss: 0.3454255163669586
2023-01-23 00:40:22.782357: step: 1932/530, loss: 0.08326606452465057
2023-01-23 00:40:23.955262: step: 1936/530, loss: 0.11447310447692871
2023-01-23 00:40:25.112901: step: 1940/530, loss: 0.17711572349071503
2023-01-23 00:40:26.271194: step: 1944/530, loss: 0.0465083122253418
2023-01-23 00:40:27.441844: step: 1948/530, loss: 0.06987696141004562
2023-01-23 00:40:28.660380: step: 1952/530, loss: 0.11709193885326385
2023-01-23 00:40:29.834185: step: 1956/530, loss: 0.26295509934425354
2023-01-23 00:40:31.029888: step: 1960/530, loss: 0.022184133529663086
2023-01-23 00:40:32.187657: step: 1964/530, loss: 0.3024407625198364
2023-01-23 00:40:33.376109: step: 1968/530, loss: 0.6750398874282837
2023-01-23 00:40:34.537260: step: 1972/530, loss: 0.18277758359909058
2023-01-23 00:40:35.761861: step: 1976/530, loss: 0.2745946943759918
2023-01-23 00:40:36.925067: step: 1980/530, loss: 0.15864916145801544
2023-01-23 00:40:38.097356: step: 1984/530, loss: 0.3288671374320984
2023-01-23 00:40:39.313676: step: 1988/530, loss: 0.9767069220542908
2023-01-23 00:40:40.494932: step: 1992/530, loss: 1.5673187971115112
2023-01-23 00:40:41.707493: step: 1996/530, loss: 0.0969463363289833
2023-01-23 00:40:42.902033: step: 2000/530, loss: 0.139842227101326
2023-01-23 00:40:44.119393: step: 2004/530, loss: 0.3081510663032532
2023-01-23 00:40:45.272493: step: 2008/530, loss: 0.07534036785364151
2023-01-23 00:40:46.445510: step: 2012/530, loss: 0.18714800477027893
2023-01-23 00:40:47.603826: step: 2016/530, loss: 0.030483627691864967
2023-01-23 00:40:48.759897: step: 2020/530, loss: 0.09415969997644424
2023-01-23 00:40:49.946278: step: 2024/530, loss: 0.0832182914018631
2023-01-23 00:40:51.108016: step: 2028/530, loss: 0.08717307448387146
2023-01-23 00:40:52.293610: step: 2032/530, loss: 0.041825298219919205
2023-01-23 00:40:53.444353: step: 2036/530, loss: 0.19072560966014862
2023-01-23 00:40:54.625465: step: 2040/530, loss: 0.181163027882576
2023-01-23 00:40:55.806283: step: 2044/530, loss: 0.13531243801116943
2023-01-23 00:40:56.990056: step: 2048/530, loss: 0.27516451478004456
2023-01-23 00:40:58.126627: step: 2052/530, loss: 0.19184771180152893
2023-01-23 00:40:59.341870: step: 2056/530, loss: 0.11333389580249786
2023-01-23 00:41:00.492203: step: 2060/530, loss: 0.24420642852783203
2023-01-23 00:41:01.662642: step: 2064/530, loss: 0.18805399537086487
2023-01-23 00:41:02.846126: step: 2068/530, loss: 0.16511748731136322
2023-01-23 00:41:03.990704: step: 2072/530, loss: 0.15647053718566895
2023-01-23 00:41:05.142530: step: 2076/530, loss: 0.09461411833763123
2023-01-23 00:41:06.305472: step: 2080/530, loss: 0.2717522382736206
2023-01-23 00:41:07.465437: step: 2084/530, loss: 0.05843100696802139
2023-01-23 00:41:08.637780: step: 2088/530, loss: 0.07341928780078888
2023-01-23 00:41:09.835738: step: 2092/530, loss: 0.32600533962249756
2023-01-23 00:41:11.012126: step: 2096/530, loss: 0.013328456319868565
2023-01-23 00:41:12.205781: step: 2100/530, loss: 0.025843096897006035
2023-01-23 00:41:13.403340: step: 2104/530, loss: 0.22217494249343872
2023-01-23 00:41:14.550044: step: 2108/530, loss: 0.13391447067260742
2023-01-23 00:41:15.707271: step: 2112/530, loss: 0.1020805835723877
2023-01-23 00:41:16.861088: step: 2116/530, loss: 0.0932595282793045
2023-01-23 00:41:18.016555: step: 2120/530, loss: 0.19845615327358246
==================================================
Loss: 0.201
--------------------
Dev: {'event': {'p': 0.5951882845188284, 'r': 0.7576564580559254, 'f1': 0.6666666666666666}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Test: {'event': {'p': 0.6663405088062623, 'r': 0.7832087406555491, 'f1': 0.7200634417129264}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Chinese: {'event': {'p': 0.5348837209302325, 'r': 0.8518518518518519, 'f1': 0.6571428571428571}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Korean: {'event': {'p': 0.6226415094339622, 'r': 0.5238095238095238, 'f1': 0.5689655172413793}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Russian: {'event': {'p': 0.5, 'r': 0.6666666666666666, 'f1': 0.5714285714285715}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
New best chinese model...
New best russian model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.5951882845188284, 'r': 0.7576564580559254, 'f1': 0.6666666666666666}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Chinese: {'event': {'p': 0.6663405088062623, 'r': 0.7832087406555491, 'f1': 0.7200634417129264}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Chinese: {'event': {'p': 0.5348837209302325, 'r': 0.8518518518518519, 'f1': 0.6571428571428571}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5815160955347871, 'r': 0.7456724367509987, 'f1': 0.6534422403733957}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Eng Test for Korean: {'event': {'p': 0.604882459312839, 'r': 0.7694077055779184, 'f1': 0.6772968868640851}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Sample Korean: {'event': {'p': 0.6666666666666666, 'r': 0.6031746031746031, 'f1': 0.6333333333333333}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5951882845188284, 'r': 0.7576564580559254, 'f1': 0.6666666666666666}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6663405088062623, 'r': 0.7832087406555491, 'f1': 0.7200634417129264}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5, 'r': 0.6666666666666666, 'f1': 0.5714285714285715}, '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 00:42:12.944815: step: 4/530, loss: 0.13870659470558167
2023-01-23 00:42:14.110572: step: 8/530, loss: 0.10851836204528809
2023-01-23 00:42:15.290061: step: 12/530, loss: 0.08128185570240021
2023-01-23 00:42:16.537571: step: 16/530, loss: 0.11258268356323242
2023-01-23 00:42:17.695450: step: 20/530, loss: 0.027537060901522636
2023-01-23 00:42:18.844760: step: 24/530, loss: 0.2404797524213791
2023-01-23 00:42:20.017359: step: 28/530, loss: 0.44863930344581604
2023-01-23 00:42:21.216689: step: 32/530, loss: 0.2597617506980896
2023-01-23 00:42:22.392935: step: 36/530, loss: 0.04968414083123207
2023-01-23 00:42:23.554635: step: 40/530, loss: 0.035601094365119934
2023-01-23 00:42:24.752447: step: 44/530, loss: 0.04424639046192169
2023-01-23 00:42:25.924948: step: 48/530, loss: 0.1674940139055252
2023-01-23 00:42:27.108628: step: 52/530, loss: 0.05557575076818466
2023-01-23 00:42:28.297450: step: 56/530, loss: 0.3687129616737366
2023-01-23 00:42:29.532113: step: 60/530, loss: 0.028432179242372513
2023-01-23 00:42:30.722965: step: 64/530, loss: 0.3487391471862793
2023-01-23 00:42:31.911613: step: 68/530, loss: 0.21637079119682312
2023-01-23 00:42:33.076271: step: 72/530, loss: 0.17811241745948792
2023-01-23 00:42:34.262278: step: 76/530, loss: 0.27146539092063904
2023-01-23 00:42:35.424101: step: 80/530, loss: 0.02970714494585991
2023-01-23 00:42:36.584255: step: 84/530, loss: 0.0748889371752739
2023-01-23 00:42:37.776841: step: 88/530, loss: 0.065901979804039
2023-01-23 00:42:38.933829: step: 92/530, loss: 0.05597992241382599
2023-01-23 00:42:40.057657: step: 96/530, loss: 0.048613451421260834
2023-01-23 00:42:41.240945: step: 100/530, loss: 0.1583629548549652
2023-01-23 00:42:42.388340: step: 104/530, loss: 0.02549438551068306
2023-01-23 00:42:43.552838: step: 108/530, loss: 0.1274530440568924
2023-01-23 00:42:44.760745: step: 112/530, loss: 0.035146284848451614
2023-01-23 00:42:45.964005: step: 116/530, loss: 0.1478159874677658
2023-01-23 00:42:47.146137: step: 120/530, loss: 0.05417003482580185
2023-01-23 00:42:48.304135: step: 124/530, loss: 0.043192580342292786
2023-01-23 00:42:49.502731: step: 128/530, loss: 0.11024819314479828
2023-01-23 00:42:50.669111: step: 132/530, loss: 0.13626575469970703
2023-01-23 00:42:51.850567: step: 136/530, loss: 0.1544477492570877
2023-01-23 00:42:53.016650: step: 140/530, loss: 0.1496930569410324
2023-01-23 00:42:54.152757: step: 144/530, loss: 1.1508122682571411
2023-01-23 00:42:55.303206: step: 148/530, loss: 0.009707403369247913
2023-01-23 00:42:56.489558: step: 152/530, loss: 0.09510812908411026
2023-01-23 00:42:57.669706: step: 156/530, loss: 0.17367486655712128
2023-01-23 00:42:58.830938: step: 160/530, loss: 0.0844632163643837
2023-01-23 00:42:59.993439: step: 164/530, loss: 1.5996429920196533
2023-01-23 00:43:01.181856: step: 168/530, loss: 0.14349107444286346
2023-01-23 00:43:02.323392: step: 172/530, loss: 0.023441409692168236
2023-01-23 00:43:03.507914: step: 176/530, loss: 0.047010280191898346
2023-01-23 00:43:04.700523: step: 180/530, loss: 0.12685108184814453
2023-01-23 00:43:05.860146: step: 184/530, loss: 0.08097989857196808
2023-01-23 00:43:07.107195: step: 188/530, loss: 0.048520758748054504
2023-01-23 00:43:08.257702: step: 192/530, loss: 0.2404986023902893
2023-01-23 00:43:09.437436: step: 196/530, loss: 0.08595848083496094
2023-01-23 00:43:10.633967: step: 200/530, loss: 0.31033191084861755
2023-01-23 00:43:11.845380: step: 204/530, loss: 0.08308496326208115
2023-01-23 00:43:12.997315: step: 208/530, loss: 0.07387419044971466
2023-01-23 00:43:14.168802: step: 212/530, loss: 0.10461874306201935
2023-01-23 00:43:15.302481: step: 216/530, loss: 0.1028100997209549
2023-01-23 00:43:16.485054: step: 220/530, loss: 0.45689117908477783
2023-01-23 00:43:17.621836: step: 224/530, loss: 0.08931207656860352
2023-01-23 00:43:18.799850: step: 228/530, loss: 0.048334527760744095
2023-01-23 00:43:19.967139: step: 232/530, loss: 0.036681175231933594
2023-01-23 00:43:21.202307: step: 236/530, loss: 0.20698876678943634
2023-01-23 00:43:22.389417: step: 240/530, loss: 0.13018901646137238
2023-01-23 00:43:23.538988: step: 244/530, loss: 0.06413483619689941
2023-01-23 00:43:24.711210: step: 248/530, loss: 0.05094633251428604
2023-01-23 00:43:25.902386: step: 252/530, loss: 0.0870383232831955
2023-01-23 00:43:27.081696: step: 256/530, loss: 0.0700145736336708
2023-01-23 00:43:28.260969: step: 260/530, loss: 1.4168819189071655
2023-01-23 00:43:29.435997: step: 264/530, loss: 0.020598269999027252
2023-01-23 00:43:30.610863: step: 268/530, loss: 0.5548242330551147
2023-01-23 00:43:31.779452: step: 272/530, loss: 0.1224660873413086
2023-01-23 00:43:32.929199: step: 276/530, loss: 0.11279530823230743
2023-01-23 00:43:34.132293: step: 280/530, loss: 0.2495754361152649
2023-01-23 00:43:35.287189: step: 284/530, loss: 0.08925295621156693
2023-01-23 00:43:36.423660: step: 288/530, loss: 0.16690409183502197
2023-01-23 00:43:37.640143: step: 292/530, loss: 0.12735548615455627
2023-01-23 00:43:38.811115: step: 296/530, loss: 0.04003152996301651
2023-01-23 00:43:39.987906: step: 300/530, loss: 0.023646164685487747
2023-01-23 00:43:41.157803: step: 304/530, loss: 0.06558997929096222
2023-01-23 00:43:42.350880: step: 308/530, loss: 0.08696547150611877
2023-01-23 00:43:43.534432: step: 312/530, loss: 0.12637010216712952
2023-01-23 00:43:44.717320: step: 316/530, loss: 0.03858175501227379
2023-01-23 00:43:45.877192: step: 320/530, loss: 0.5158554911613464
2023-01-23 00:43:47.062862: step: 324/530, loss: 0.011658954434096813
2023-01-23 00:43:48.234296: step: 328/530, loss: 0.08313693851232529
2023-01-23 00:43:49.458843: step: 332/530, loss: 0.07755003124475479
2023-01-23 00:43:50.681379: step: 336/530, loss: 0.2044386863708496
2023-01-23 00:43:51.822043: step: 340/530, loss: 0.15821929275989532
2023-01-23 00:43:53.059976: step: 344/530, loss: 0.1118369996547699
2023-01-23 00:43:54.257384: step: 348/530, loss: 0.02092599868774414
2023-01-23 00:43:55.397712: step: 352/530, loss: 0.06402969360351562
2023-01-23 00:43:56.618311: step: 356/530, loss: 0.02071847952902317
2023-01-23 00:43:57.812616: step: 360/530, loss: 0.14521408081054688
2023-01-23 00:43:58.989592: step: 364/530, loss: 0.08247213810682297
2023-01-23 00:44:00.181682: step: 368/530, loss: 0.060596562922000885
2023-01-23 00:44:01.326015: step: 372/530, loss: 0.6380486488342285
2023-01-23 00:44:02.489614: step: 376/530, loss: 0.4088096618652344
2023-01-23 00:44:03.637857: step: 380/530, loss: 0.06871576607227325
2023-01-23 00:44:04.793130: step: 384/530, loss: 0.15540266036987305
2023-01-23 00:44:05.961954: step: 388/530, loss: 0.18892605602741241
2023-01-23 00:44:07.171854: step: 392/530, loss: 0.11419849097728729
2023-01-23 00:44:08.311024: step: 396/530, loss: 0.10056620091199875
2023-01-23 00:44:09.407793: step: 400/530, loss: 0.13915902376174927
2023-01-23 00:44:10.583871: step: 404/530, loss: 0.10136671364307404
2023-01-23 00:44:11.823805: step: 408/530, loss: 0.07748584449291229
2023-01-23 00:44:13.023046: step: 412/530, loss: 0.024372100830078125
2023-01-23 00:44:14.194653: step: 416/530, loss: 0.11834478378295898
2023-01-23 00:44:15.383587: step: 420/530, loss: 0.024622727185487747
2023-01-23 00:44:16.549717: step: 424/530, loss: 0.14065399765968323
2023-01-23 00:44:17.712588: step: 428/530, loss: 0.09721308201551437
2023-01-23 00:44:18.875334: step: 432/530, loss: 0.08102860301733017
2023-01-23 00:44:20.069575: step: 436/530, loss: 0.048135899007320404
2023-01-23 00:44:21.186679: step: 440/530, loss: 0.1590632200241089
2023-01-23 00:44:22.364889: step: 444/530, loss: 0.2028520554304123
2023-01-23 00:44:23.572369: step: 448/530, loss: 0.1192622184753418
2023-01-23 00:44:24.788038: step: 452/530, loss: 0.7575895190238953
2023-01-23 00:44:25.950989: step: 456/530, loss: 0.08304329216480255
2023-01-23 00:44:27.106387: step: 460/530, loss: 0.0701976791024208
2023-01-23 00:44:28.280716: step: 464/530, loss: 0.19155970215797424
2023-01-23 00:44:29.451343: step: 468/530, loss: 0.06760769337415695
2023-01-23 00:44:30.613309: step: 472/530, loss: 0.5125473141670227
2023-01-23 00:44:31.745723: step: 476/530, loss: 0.13938313722610474
2023-01-23 00:44:32.915723: step: 480/530, loss: 0.05063953623175621
2023-01-23 00:44:34.121217: step: 484/530, loss: 0.1459488868713379
2023-01-23 00:44:35.283927: step: 488/530, loss: 0.14793729782104492
2023-01-23 00:44:36.475239: step: 492/530, loss: 0.10498276352882385
2023-01-23 00:44:37.616941: step: 496/530, loss: 0.1654163897037506
2023-01-23 00:44:38.789426: step: 500/530, loss: 0.10975951701402664
2023-01-23 00:44:40.015723: step: 504/530, loss: 0.7173225283622742
2023-01-23 00:44:41.171789: step: 508/530, loss: 0.05371842160820961
2023-01-23 00:44:42.382178: step: 512/530, loss: 0.22930708527565002
2023-01-23 00:44:43.536272: step: 516/530, loss: 0.051342010498046875
2023-01-23 00:44:44.730596: step: 520/530, loss: 0.07384524494409561
2023-01-23 00:44:45.866417: step: 524/530, loss: 0.0777139663696289
2023-01-23 00:44:46.980758: step: 528/530, loss: 0.11190232634544373
2023-01-23 00:44:48.197712: step: 532/530, loss: 0.2026950865983963
2023-01-23 00:44:49.342890: step: 536/530, loss: 0.3991660177707672
2023-01-23 00:44:50.546381: step: 540/530, loss: 0.11361722648143768
2023-01-23 00:44:51.693191: step: 544/530, loss: 0.04473155736923218
2023-01-23 00:44:52.875746: step: 548/530, loss: 0.0492459312081337
2023-01-23 00:44:54.047463: step: 552/530, loss: 0.6628842949867249
2023-01-23 00:44:55.176833: step: 556/530, loss: 0.05882025137543678
2023-01-23 00:44:56.349864: step: 560/530, loss: 0.21934282779693604
2023-01-23 00:44:57.519917: step: 564/530, loss: 0.05720691755414009
2023-01-23 00:44:58.663530: step: 568/530, loss: 0.05353212356567383
2023-01-23 00:44:59.852854: step: 572/530, loss: 0.14908629655838013
2023-01-23 00:45:01.013734: step: 576/530, loss: 0.033939410001039505
2023-01-23 00:45:02.185537: step: 580/530, loss: 0.09566888958215714
2023-01-23 00:45:03.364099: step: 584/530, loss: 0.09796305000782013
2023-01-23 00:45:04.512789: step: 588/530, loss: 0.03454389423131943
2023-01-23 00:45:05.675171: step: 592/530, loss: 0.07813195884227753
2023-01-23 00:45:06.842229: step: 596/530, loss: 0.07436561584472656
2023-01-23 00:45:08.013581: step: 600/530, loss: 0.029509449377655983
2023-01-23 00:45:09.197584: step: 604/530, loss: 0.03202085196971893
2023-01-23 00:45:10.397414: step: 608/530, loss: 0.15977001190185547
2023-01-23 00:45:11.537818: step: 612/530, loss: 0.03294672444462776
2023-01-23 00:45:12.714804: step: 616/530, loss: 0.07999812066555023
2023-01-23 00:45:13.869434: step: 620/530, loss: 0.43825700879096985
2023-01-23 00:45:15.022453: step: 624/530, loss: 0.0037241936661303043
2023-01-23 00:45:16.170010: step: 628/530, loss: 0.1160547286272049
2023-01-23 00:45:17.354387: step: 632/530, loss: 0.0742734968662262
2023-01-23 00:45:18.555123: step: 636/530, loss: 0.10195188969373703
2023-01-23 00:45:19.750487: step: 640/530, loss: 0.04310021176934242
2023-01-23 00:45:20.904753: step: 644/530, loss: 0.11594219505786896
2023-01-23 00:45:22.074328: step: 648/530, loss: 0.08516745269298553
2023-01-23 00:45:23.242021: step: 652/530, loss: 0.19553527235984802
2023-01-23 00:45:24.400827: step: 656/530, loss: 0.012005400843918324
2023-01-23 00:45:25.600351: step: 660/530, loss: 0.06505639851093292
2023-01-23 00:45:26.760032: step: 664/530, loss: 0.09030401706695557
2023-01-23 00:45:27.926043: step: 668/530, loss: 0.18781937658786774
2023-01-23 00:45:29.142859: step: 672/530, loss: 0.3081260621547699
2023-01-23 00:45:30.304397: step: 676/530, loss: 0.6232860088348389
2023-01-23 00:45:31.468680: step: 680/530, loss: 0.07573743164539337
2023-01-23 00:45:32.635575: step: 684/530, loss: 0.10615397244691849
2023-01-23 00:45:33.820842: step: 688/530, loss: 0.03545580059289932
2023-01-23 00:45:34.969575: step: 692/530, loss: 0.08056831359863281
2023-01-23 00:45:36.190810: step: 696/530, loss: 0.1761191487312317
2023-01-23 00:45:37.371930: step: 700/530, loss: 0.12173967808485031
2023-01-23 00:45:38.571026: step: 704/530, loss: 0.08709517121315002
2023-01-23 00:45:39.747002: step: 708/530, loss: 0.3394899368286133
2023-01-23 00:45:40.945024: step: 712/530, loss: 0.061670683324337006
2023-01-23 00:45:42.137037: step: 716/530, loss: 0.04032144695520401
2023-01-23 00:45:43.285592: step: 720/530, loss: 0.0463688038289547
2023-01-23 00:45:44.465892: step: 724/530, loss: 0.14275655150413513
2023-01-23 00:45:45.620443: step: 728/530, loss: 0.05639352649450302
2023-01-23 00:45:46.792608: step: 732/530, loss: 0.028322555124759674
2023-01-23 00:45:47.966777: step: 736/530, loss: 0.057747747749090195
2023-01-23 00:45:49.183630: step: 740/530, loss: 0.08018913865089417
2023-01-23 00:45:50.349816: step: 744/530, loss: 0.09463682025671005
2023-01-23 00:45:51.532839: step: 748/530, loss: 0.2068311721086502
2023-01-23 00:45:52.701881: step: 752/530, loss: 0.059811901301145554
2023-01-23 00:45:53.885022: step: 756/530, loss: 0.04284505918622017
2023-01-23 00:45:55.079576: step: 760/530, loss: 0.22188082337379456
2023-01-23 00:45:56.228598: step: 764/530, loss: 0.09251490235328674
2023-01-23 00:45:57.405414: step: 768/530, loss: 0.22749634087085724
2023-01-23 00:45:58.585521: step: 772/530, loss: 0.46761876344680786
2023-01-23 00:45:59.767009: step: 776/530, loss: 0.15681257843971252
2023-01-23 00:46:00.965244: step: 780/530, loss: 0.0394928939640522
2023-01-23 00:46:02.113015: step: 784/530, loss: 0.8242636919021606
2023-01-23 00:46:03.297300: step: 788/530, loss: 0.0690513551235199
2023-01-23 00:46:04.461941: step: 792/530, loss: 0.12767724692821503
2023-01-23 00:46:05.642203: step: 796/530, loss: 0.1885465681552887
2023-01-23 00:46:06.809625: step: 800/530, loss: 0.027648210525512695
2023-01-23 00:46:07.992158: step: 804/530, loss: 0.5100517272949219
2023-01-23 00:46:09.154779: step: 808/530, loss: 0.22364681959152222
2023-01-23 00:46:10.294901: step: 812/530, loss: 0.03222065046429634
2023-01-23 00:46:11.468961: step: 816/530, loss: 1.3350963592529297
2023-01-23 00:46:12.623788: step: 820/530, loss: 0.0690191239118576
2023-01-23 00:46:13.822209: step: 824/530, loss: 0.01998310163617134
2023-01-23 00:46:14.975812: step: 828/530, loss: 0.10699691623449326
2023-01-23 00:46:16.173248: step: 832/530, loss: 0.033284954726696014
2023-01-23 00:46:17.323634: step: 836/530, loss: 0.7190266251564026
2023-01-23 00:46:18.486063: step: 840/530, loss: 0.09366126358509064
2023-01-23 00:46:19.670282: step: 844/530, loss: 0.06663629412651062
2023-01-23 00:46:20.885657: step: 848/530, loss: 0.09553766250610352
2023-01-23 00:46:22.023105: step: 852/530, loss: 0.03830909729003906
2023-01-23 00:46:23.251075: step: 856/530, loss: 0.10642127692699432
2023-01-23 00:46:24.452214: step: 860/530, loss: 0.26812100410461426
2023-01-23 00:46:25.608475: step: 864/530, loss: 0.04738941416144371
2023-01-23 00:46:26.739324: step: 868/530, loss: 0.4965672492980957
2023-01-23 00:46:27.925961: step: 872/530, loss: 0.1625833958387375
2023-01-23 00:46:29.086527: step: 876/530, loss: 0.2255706787109375
2023-01-23 00:46:30.230649: step: 880/530, loss: 0.34958744049072266
2023-01-23 00:46:31.360743: step: 884/530, loss: 0.05814345180988312
2023-01-23 00:46:32.535354: step: 888/530, loss: 0.7029643654823303
2023-01-23 00:46:33.723131: step: 892/530, loss: 0.2767925262451172
2023-01-23 00:46:34.865886: step: 896/530, loss: 0.08101079612970352
2023-01-23 00:46:36.057003: step: 900/530, loss: 0.12409114837646484
2023-01-23 00:46:37.253854: step: 904/530, loss: 0.14632092416286469
2023-01-23 00:46:38.439685: step: 908/530, loss: 0.09457479417324066
2023-01-23 00:46:39.610940: step: 912/530, loss: 0.15415644645690918
2023-01-23 00:46:40.757268: step: 916/530, loss: 0.2620663642883301
2023-01-23 00:46:41.928973: step: 920/530, loss: 0.19425325095653534
2023-01-23 00:46:43.159558: step: 924/530, loss: 0.16412056982517242
2023-01-23 00:46:44.317656: step: 928/530, loss: 0.11373564600944519
2023-01-23 00:46:45.448865: step: 932/530, loss: 0.053139328956604004
2023-01-23 00:46:46.615153: step: 936/530, loss: 0.8598411679267883
2023-01-23 00:46:47.784453: step: 940/530, loss: 0.041358090937137604
2023-01-23 00:46:48.974276: step: 944/530, loss: 0.12312659621238708
2023-01-23 00:46:50.153430: step: 948/530, loss: 0.06576715409755707
2023-01-23 00:46:51.325480: step: 952/530, loss: 0.12359118461608887
2023-01-23 00:46:52.493707: step: 956/530, loss: 0.05999374762177467
2023-01-23 00:46:53.681197: step: 960/530, loss: 0.14909592270851135
2023-01-23 00:46:54.857243: step: 964/530, loss: 0.24081745743751526
2023-01-23 00:46:56.016684: step: 968/530, loss: 0.04611378163099289
2023-01-23 00:46:57.179914: step: 972/530, loss: 0.08156175911426544
2023-01-23 00:46:58.367658: step: 976/530, loss: 0.06103034317493439
2023-01-23 00:46:59.544977: step: 980/530, loss: 0.040491484105587006
2023-01-23 00:47:00.707586: step: 984/530, loss: 0.11292321234941483
2023-01-23 00:47:01.880537: step: 988/530, loss: 0.1835372895002365
2023-01-23 00:47:03.048707: step: 992/530, loss: 0.05430328845977783
2023-01-23 00:47:04.226020: step: 996/530, loss: 0.030447769910097122
2023-01-23 00:47:05.374242: step: 1000/530, loss: 0.14766322076320648
2023-01-23 00:47:06.518387: step: 1004/530, loss: 0.2515069246292114
2023-01-23 00:47:07.734007: step: 1008/530, loss: 0.1741357147693634
2023-01-23 00:47:08.916687: step: 1012/530, loss: 0.1778222918510437
2023-01-23 00:47:10.143530: step: 1016/530, loss: 0.21397018432617188
2023-01-23 00:47:11.340697: step: 1020/530, loss: 0.1313806176185608
2023-01-23 00:47:12.545708: step: 1024/530, loss: 0.11881713569164276
2023-01-23 00:47:13.749825: step: 1028/530, loss: 0.06291327625513077
2023-01-23 00:47:14.951483: step: 1032/530, loss: 0.16330285370349884
2023-01-23 00:47:16.153144: step: 1036/530, loss: 0.14504605531692505
2023-01-23 00:47:17.333054: step: 1040/530, loss: 0.16113443672657013
2023-01-23 00:47:18.520847: step: 1044/530, loss: 0.299398809671402
2023-01-23 00:47:19.688261: step: 1048/530, loss: 0.11269207298755646
2023-01-23 00:47:20.865262: step: 1052/530, loss: 0.07886343449354172
2023-01-23 00:47:21.984977: step: 1056/530, loss: 0.045914940536022186
2023-01-23 00:47:23.151440: step: 1060/530, loss: 0.25135231018066406
2023-01-23 00:47:24.302237: step: 1064/530, loss: 0.09407277405261993
2023-01-23 00:47:25.479448: step: 1068/530, loss: 0.9510295391082764
2023-01-23 00:47:26.657783: step: 1072/530, loss: 0.07523909211158752
2023-01-23 00:47:27.804855: step: 1076/530, loss: 1.2216814756393433
2023-01-23 00:47:29.010529: step: 1080/530, loss: 0.24906902015209198
2023-01-23 00:47:30.162167: step: 1084/530, loss: 0.13651637732982635
2023-01-23 00:47:31.330265: step: 1088/530, loss: 0.1675352156162262
2023-01-23 00:47:32.520937: step: 1092/530, loss: 0.03807785362005234
2023-01-23 00:47:33.693007: step: 1096/530, loss: 0.1280396282672882
2023-01-23 00:47:34.866205: step: 1100/530, loss: 0.19950920343399048
2023-01-23 00:47:36.013822: step: 1104/530, loss: 0.35442599654197693
2023-01-23 00:47:37.198358: step: 1108/530, loss: 0.05653820186853409
2023-01-23 00:47:38.349906: step: 1112/530, loss: 0.6752009391784668
2023-01-23 00:47:39.525347: step: 1116/530, loss: 0.021213434636592865
2023-01-23 00:47:40.708048: step: 1120/530, loss: 0.09452629089355469
2023-01-23 00:47:41.913118: step: 1124/530, loss: 0.04790644347667694
2023-01-23 00:47:43.094184: step: 1128/530, loss: 0.05569944158196449
2023-01-23 00:47:44.281966: step: 1132/530, loss: 0.06117839738726616
2023-01-23 00:47:45.461913: step: 1136/530, loss: 0.17896366119384766
2023-01-23 00:47:46.611553: step: 1140/530, loss: 0.2415408194065094
2023-01-23 00:47:47.802464: step: 1144/530, loss: 0.13051429390907288
2023-01-23 00:47:48.985376: step: 1148/530, loss: 0.24688206613063812
2023-01-23 00:47:50.173817: step: 1152/530, loss: 0.13463154435157776
2023-01-23 00:47:51.363444: step: 1156/530, loss: 0.01905231550335884
2023-01-23 00:47:52.548732: step: 1160/530, loss: 0.28335922956466675
2023-01-23 00:47:53.771720: step: 1164/530, loss: 0.08951287716627121
2023-01-23 00:47:54.939000: step: 1168/530, loss: 0.4913296699523926
2023-01-23 00:47:56.115671: step: 1172/530, loss: 0.0918915718793869
2023-01-23 00:47:57.268211: step: 1176/530, loss: 0.01008062344044447
2023-01-23 00:47:58.421564: step: 1180/530, loss: 0.08041343837976456
2023-01-23 00:47:59.594934: step: 1184/530, loss: 0.11672420799732208
2023-01-23 00:48:00.731207: step: 1188/530, loss: 0.08834800869226456
2023-01-23 00:48:01.880136: step: 1192/530, loss: 0.08642949908971786
2023-01-23 00:48:03.020578: step: 1196/530, loss: 0.06976857781410217
2023-01-23 00:48:04.180459: step: 1200/530, loss: 0.048917584121227264
2023-01-23 00:48:05.392160: step: 1204/530, loss: 0.16319161653518677
2023-01-23 00:48:06.537342: step: 1208/530, loss: 0.14198637008666992
2023-01-23 00:48:07.696791: step: 1212/530, loss: 0.08094444125890732
2023-01-23 00:48:08.876388: step: 1216/530, loss: 0.15412521362304688
2023-01-23 00:48:10.079919: step: 1220/530, loss: 0.050496816635131836
2023-01-23 00:48:11.242879: step: 1224/530, loss: 0.017569376155734062
2023-01-23 00:48:12.403652: step: 1228/530, loss: 0.1967329978942871
2023-01-23 00:48:13.607704: step: 1232/530, loss: 0.029148675501346588
2023-01-23 00:48:14.738310: step: 1236/530, loss: 0.06635943055152893
2023-01-23 00:48:15.944779: step: 1240/530, loss: 0.031171131879091263
2023-01-23 00:48:17.145006: step: 1244/530, loss: 0.3450516164302826
2023-01-23 00:48:18.331166: step: 1248/530, loss: 0.07146825641393661
2023-01-23 00:48:19.486518: step: 1252/530, loss: 0.02122030220925808
2023-01-23 00:48:20.645380: step: 1256/530, loss: 0.04605922847986221
2023-01-23 00:48:21.830246: step: 1260/530, loss: 0.0691690444946289
2023-01-23 00:48:23.037616: step: 1264/530, loss: 0.09634155035018921
2023-01-23 00:48:24.248370: step: 1268/530, loss: 0.3644769787788391
2023-01-23 00:48:25.429570: step: 1272/530, loss: 0.08097486197948456
2023-01-23 00:48:26.592515: step: 1276/530, loss: 0.16014719009399414
2023-01-23 00:48:27.766322: step: 1280/530, loss: 0.6281105279922485
2023-01-23 00:48:28.963022: step: 1284/530, loss: 0.08786201477050781
2023-01-23 00:48:30.117085: step: 1288/530, loss: 0.06126823276281357
2023-01-23 00:48:31.296870: step: 1292/530, loss: 0.07381415367126465
2023-01-23 00:48:32.463683: step: 1296/530, loss: 0.15044927597045898
2023-01-23 00:48:33.658094: step: 1300/530, loss: 0.08012113720178604
2023-01-23 00:48:34.869007: step: 1304/530, loss: 0.08313445746898651
2023-01-23 00:48:36.049495: step: 1308/530, loss: 0.06676559150218964
2023-01-23 00:48:37.248411: step: 1312/530, loss: 0.09964694827795029
2023-01-23 00:48:38.383387: step: 1316/530, loss: 0.6676400303840637
2023-01-23 00:48:39.542980: step: 1320/530, loss: 0.2623558044433594
2023-01-23 00:48:40.730398: step: 1324/530, loss: 0.4281969964504242
2023-01-23 00:48:41.877770: step: 1328/530, loss: 0.05522608757019043
2023-01-23 00:48:43.046559: step: 1332/530, loss: 0.1036454290151596
2023-01-23 00:48:44.204777: step: 1336/530, loss: 0.7949551343917847
2023-01-23 00:48:45.404965: step: 1340/530, loss: 0.12144766747951508
2023-01-23 00:48:46.586098: step: 1344/530, loss: 8.118889808654785
2023-01-23 00:48:47.745858: step: 1348/530, loss: 0.15737371146678925
2023-01-23 00:48:48.926001: step: 1352/530, loss: 0.12530259788036346
2023-01-23 00:48:50.073166: step: 1356/530, loss: 0.37088432908058167
2023-01-23 00:48:51.269412: step: 1360/530, loss: 0.15620647370815277
2023-01-23 00:48:52.431052: step: 1364/530, loss: 0.028477145358920097
2023-01-23 00:48:53.572260: step: 1368/530, loss: 0.1475735455751419
2023-01-23 00:48:54.746982: step: 1372/530, loss: 0.15326552093029022
2023-01-23 00:48:55.965152: step: 1376/530, loss: 0.12698504328727722
2023-01-23 00:48:57.157685: step: 1380/530, loss: 0.0507938414812088
2023-01-23 00:48:58.303224: step: 1384/530, loss: 0.0787678211927414
2023-01-23 00:48:59.453319: step: 1388/530, loss: 1.235237717628479
2023-01-23 00:49:00.667134: step: 1392/530, loss: 0.11850052326917648
2023-01-23 00:49:01.818217: step: 1396/530, loss: 0.0781853199005127
2023-01-23 00:49:02.978954: step: 1400/530, loss: 0.1338120400905609
2023-01-23 00:49:04.159833: step: 1404/530, loss: 0.2014157474040985
2023-01-23 00:49:05.310133: step: 1408/530, loss: 0.37979164719581604
2023-01-23 00:49:06.463993: step: 1412/530, loss: 0.1555541455745697
2023-01-23 00:49:07.627192: step: 1416/530, loss: 0.00940637569874525
2023-01-23 00:49:08.820365: step: 1420/530, loss: 0.11018143594264984
2023-01-23 00:49:09.966464: step: 1424/530, loss: 0.05312395095825195
2023-01-23 00:49:11.155433: step: 1428/530, loss: 0.1751757562160492
2023-01-23 00:49:12.369383: step: 1432/530, loss: 0.23049183189868927
2023-01-23 00:49:13.575511: step: 1436/530, loss: 0.0061484333127737045
2023-01-23 00:49:14.731998: step: 1440/530, loss: 0.03585701063275337
2023-01-23 00:49:15.881844: step: 1444/530, loss: 0.05142708122730255
2023-01-23 00:49:17.050906: step: 1448/530, loss: 0.056695327162742615
2023-01-23 00:49:18.178835: step: 1452/530, loss: 0.05688176304101944
2023-01-23 00:49:19.321781: step: 1456/530, loss: 0.09829340130090714
2023-01-23 00:49:20.518106: step: 1460/530, loss: 0.05451097711920738
2023-01-23 00:49:21.693666: step: 1464/530, loss: 0.15306444466114044
2023-01-23 00:49:22.836958: step: 1468/530, loss: 0.7216490507125854
2023-01-23 00:49:24.063275: step: 1472/530, loss: 0.07557869702577591
2023-01-23 00:49:25.217425: step: 1476/530, loss: 0.053020574152469635
2023-01-23 00:49:26.399269: step: 1480/530, loss: 0.14299039542675018
2023-01-23 00:49:27.586549: step: 1484/530, loss: 0.030964376404881477
2023-01-23 00:49:28.776960: step: 1488/530, loss: 0.004988003056496382
2023-01-23 00:49:29.963321: step: 1492/530, loss: 0.2425040304660797
2023-01-23 00:49:31.171344: step: 1496/530, loss: 0.022293757647275925
2023-01-23 00:49:32.323981: step: 1500/530, loss: 0.11778521537780762
2023-01-23 00:49:33.484933: step: 1504/530, loss: 0.09112139046192169
2023-01-23 00:49:34.672612: step: 1508/530, loss: 0.028851225972175598
2023-01-23 00:49:35.837776: step: 1512/530, loss: 0.08409872651100159
2023-01-23 00:49:37.013177: step: 1516/530, loss: 0.09616873413324356
2023-01-23 00:49:38.180347: step: 1520/530, loss: 0.03184308856725693
2023-01-23 00:49:39.377541: step: 1524/530, loss: 0.15684834122657776
2023-01-23 00:49:40.589490: step: 1528/530, loss: 0.3821706771850586
2023-01-23 00:49:41.832853: step: 1532/530, loss: 0.13774064183235168
2023-01-23 00:49:43.005852: step: 1536/530, loss: 0.07538139820098877
2023-01-23 00:49:44.204696: step: 1540/530, loss: 0.14204131066799164
2023-01-23 00:49:45.347497: step: 1544/530, loss: 0.07960529625415802
2023-01-23 00:49:46.498800: step: 1548/530, loss: 0.08302012085914612
2023-01-23 00:49:47.660711: step: 1552/530, loss: 0.05219545587897301
2023-01-23 00:49:48.832771: step: 1556/530, loss: 0.20789460837841034
2023-01-23 00:49:49.998539: step: 1560/530, loss: 0.12437497079372406
2023-01-23 00:49:51.148033: step: 1564/530, loss: 0.6804086565971375
2023-01-23 00:49:52.322487: step: 1568/530, loss: 0.26605215668678284
2023-01-23 00:49:53.493046: step: 1572/530, loss: 0.1061069443821907
2023-01-23 00:49:54.710415: step: 1576/530, loss: 0.10087203979492188
2023-01-23 00:49:55.899044: step: 1580/530, loss: 0.23875465989112854
2023-01-23 00:49:57.099948: step: 1584/530, loss: 0.7635504603385925
2023-01-23 00:49:58.293698: step: 1588/530, loss: 0.06685705482959747
2023-01-23 00:49:59.452991: step: 1592/530, loss: 0.3336338996887207
2023-01-23 00:50:00.660969: step: 1596/530, loss: 0.33176448941230774
2023-01-23 00:50:01.825398: step: 1600/530, loss: 0.44324979186058044
2023-01-23 00:50:02.993155: step: 1604/530, loss: 0.07779455184936523
2023-01-23 00:50:04.160179: step: 1608/530, loss: 0.13275985419750214
2023-01-23 00:50:05.352154: step: 1612/530, loss: 0.23136940598487854
2023-01-23 00:50:06.503037: step: 1616/530, loss: 0.23307928442955017
2023-01-23 00:50:07.669840: step: 1620/530, loss: 0.01569380797445774
2023-01-23 00:50:08.832972: step: 1624/530, loss: 0.04010000452399254
2023-01-23 00:50:09.973386: step: 1628/530, loss: 0.08722343295812607
2023-01-23 00:50:11.164261: step: 1632/530, loss: 0.03483171761035919
2023-01-23 00:50:12.340882: step: 1636/530, loss: 0.10468673706054688
2023-01-23 00:50:13.527765: step: 1640/530, loss: 0.0700041800737381
2023-01-23 00:50:14.715814: step: 1644/530, loss: 0.09530048817396164
2023-01-23 00:50:15.883042: step: 1648/530, loss: 0.041333772242069244
2023-01-23 00:50:17.071131: step: 1652/530, loss: 0.01904582977294922
2023-01-23 00:50:18.229469: step: 1656/530, loss: 0.049504779279232025
2023-01-23 00:50:19.418944: step: 1660/530, loss: 0.13064345717430115
2023-01-23 00:50:20.571906: step: 1664/530, loss: 0.5991726517677307
2023-01-23 00:50:21.734304: step: 1668/530, loss: 0.10010337829589844
2023-01-23 00:50:22.932028: step: 1672/530, loss: 0.057242583483457565
2023-01-23 00:50:24.120849: step: 1676/530, loss: 0.04651589319109917
2023-01-23 00:50:25.297241: step: 1680/530, loss: 0.16042709350585938
2023-01-23 00:50:26.488238: step: 1684/530, loss: 0.15629100799560547
2023-01-23 00:50:27.670930: step: 1688/530, loss: 0.029331304132938385
2023-01-23 00:50:28.824142: step: 1692/530, loss: 0.05172586441040039
2023-01-23 00:50:30.027130: step: 1696/530, loss: 0.3399297893047333
2023-01-23 00:50:31.190817: step: 1700/530, loss: 0.014093208126723766
2023-01-23 00:50:32.417588: step: 1704/530, loss: 0.16087833046913147
2023-01-23 00:50:33.592772: step: 1708/530, loss: 0.06951618194580078
2023-01-23 00:50:34.737990: step: 1712/530, loss: 0.0356324203312397
2023-01-23 00:50:35.896342: step: 1716/530, loss: 0.43255701661109924
2023-01-23 00:50:37.062648: step: 1720/530, loss: 0.09145680069923401
2023-01-23 00:50:38.248886: step: 1724/530, loss: 0.0860137939453125
2023-01-23 00:50:39.468084: step: 1728/530, loss: 0.04267134517431259
2023-01-23 00:50:40.633419: step: 1732/530, loss: 0.07545671612024307
2023-01-23 00:50:41.779939: step: 1736/530, loss: 0.25702863931655884
2023-01-23 00:50:42.950293: step: 1740/530, loss: 0.3747011423110962
2023-01-23 00:50:44.152605: step: 1744/530, loss: 0.03267383575439453
2023-01-23 00:50:45.370391: step: 1748/530, loss: 0.14868488907814026
2023-01-23 00:50:46.556327: step: 1752/530, loss: 0.08251695334911346
2023-01-23 00:50:47.727728: step: 1756/530, loss: 0.06842704117298126
2023-01-23 00:50:48.948031: step: 1760/530, loss: 0.06780672073364258
2023-01-23 00:50:50.151695: step: 1764/530, loss: 0.022853948175907135
2023-01-23 00:50:51.323332: step: 1768/530, loss: 0.046235088258981705
2023-01-23 00:50:52.443503: step: 1772/530, loss: 0.14488859474658966
2023-01-23 00:50:53.618041: step: 1776/530, loss: 0.04218330234289169
2023-01-23 00:50:54.779689: step: 1780/530, loss: 0.0666736587882042
2023-01-23 00:50:55.960786: step: 1784/530, loss: 0.045351602137088776
2023-01-23 00:50:57.113568: step: 1788/530, loss: 0.024474717676639557
2023-01-23 00:50:58.292169: step: 1792/530, loss: 0.5986720323562622
2023-01-23 00:50:59.431862: step: 1796/530, loss: 0.19614830613136292
2023-01-23 00:51:00.587356: step: 1800/530, loss: 0.14424562454223633
2023-01-23 00:51:01.740839: step: 1804/530, loss: 0.03900689631700516
2023-01-23 00:51:02.927969: step: 1808/530, loss: 0.12048053741455078
2023-01-23 00:51:04.109437: step: 1812/530, loss: 0.17474976181983948
2023-01-23 00:51:05.322421: step: 1816/530, loss: 0.08219261467456818
2023-01-23 00:51:06.517617: step: 1820/530, loss: 0.21182546019554138
2023-01-23 00:51:07.770233: step: 1824/530, loss: 0.15406452119350433
2023-01-23 00:51:08.962401: step: 1828/530, loss: 0.0773673951625824
2023-01-23 00:51:10.154356: step: 1832/530, loss: 0.040265846997499466
2023-01-23 00:51:11.366662: step: 1836/530, loss: 0.5512231588363647
2023-01-23 00:51:12.515427: step: 1840/530, loss: 0.08200240135192871
2023-01-23 00:51:13.660052: step: 1844/530, loss: 0.10322335362434387
2023-01-23 00:51:14.862588: step: 1848/530, loss: 0.1038825511932373
2023-01-23 00:51:16.034477: step: 1852/530, loss: 0.1444016396999359
2023-01-23 00:51:17.202293: step: 1856/530, loss: 0.013876629061996937
2023-01-23 00:51:18.378399: step: 1860/530, loss: 0.27657708525657654
2023-01-23 00:51:19.511150: step: 1864/530, loss: 0.6079106330871582
2023-01-23 00:51:20.626644: step: 1868/530, loss: 0.06888370960950851
2023-01-23 00:51:21.788319: step: 1872/530, loss: 0.04305429756641388
2023-01-23 00:51:22.965627: step: 1876/530, loss: 0.07346191257238388
2023-01-23 00:51:24.155326: step: 1880/530, loss: 0.035425566136837006
2023-01-23 00:51:25.329826: step: 1884/530, loss: 0.08678150177001953
2023-01-23 00:51:26.503149: step: 1888/530, loss: 0.08211731910705566
2023-01-23 00:51:27.660361: step: 1892/530, loss: 0.09818267822265625
2023-01-23 00:51:28.847830: step: 1896/530, loss: 0.12733745574951172
2023-01-23 00:51:30.007448: step: 1900/530, loss: 0.04463662952184677
2023-01-23 00:51:31.219650: step: 1904/530, loss: 0.11427903920412064
2023-01-23 00:51:32.366304: step: 1908/530, loss: 0.14245247840881348
2023-01-23 00:51:33.545674: step: 1912/530, loss: 0.04493694379925728
2023-01-23 00:51:34.708505: step: 1916/530, loss: 0.07463064789772034
2023-01-23 00:51:35.878765: step: 1920/530, loss: 0.15216198563575745
2023-01-23 00:51:37.012277: step: 1924/530, loss: 0.04280037805438042
2023-01-23 00:51:38.205080: step: 1928/530, loss: 0.1652251034975052
2023-01-23 00:51:39.388569: step: 1932/530, loss: 0.03550739213824272
2023-01-23 00:51:40.586868: step: 1936/530, loss: 0.11913518607616425
2023-01-23 00:51:41.795750: step: 1940/530, loss: 0.0704570785164833
2023-01-23 00:51:42.973290: step: 1944/530, loss: 0.20811930298805237
2023-01-23 00:51:44.117901: step: 1948/530, loss: 0.07304179668426514
2023-01-23 00:51:45.316172: step: 1952/530, loss: 0.11367378383874893
2023-01-23 00:51:46.495381: step: 1956/530, loss: 0.1448986977338791
2023-01-23 00:51:47.641578: step: 1960/530, loss: 0.04355278238654137
2023-01-23 00:51:48.827453: step: 1964/530, loss: 0.1907327026128769
2023-01-23 00:51:49.994065: step: 1968/530, loss: 0.05163269490003586
2023-01-23 00:51:51.200991: step: 1972/530, loss: 0.03978443518280983
2023-01-23 00:51:52.329180: step: 1976/530, loss: 0.048858191817998886
2023-01-23 00:51:53.518119: step: 1980/530, loss: 0.11977467685937881
2023-01-23 00:51:54.680503: step: 1984/530, loss: 0.05119209364056587
2023-01-23 00:51:55.852810: step: 1988/530, loss: 0.1476486623287201
2023-01-23 00:51:57.026742: step: 1992/530, loss: 0.19440193474292755
2023-01-23 00:51:58.188238: step: 1996/530, loss: 0.09235715866088867
2023-01-23 00:51:59.346883: step: 2000/530, loss: 0.1252666413784027
2023-01-23 00:52:00.569866: step: 2004/530, loss: 0.10467414557933807
2023-01-23 00:52:01.752302: step: 2008/530, loss: 0.10535478591918945
2023-01-23 00:52:02.968029: step: 2012/530, loss: 0.30162695050239563
2023-01-23 00:52:04.150205: step: 2016/530, loss: 0.07579698413610458
2023-01-23 00:52:05.307843: step: 2020/530, loss: 0.4311635494232178
2023-01-23 00:52:06.448731: step: 2024/530, loss: 0.048597242683172226
2023-01-23 00:52:07.590168: step: 2028/530, loss: 0.16346636414527893
2023-01-23 00:52:08.754446: step: 2032/530, loss: 0.06641187518835068
2023-01-23 00:52:09.924254: step: 2036/530, loss: 0.16264715790748596
2023-01-23 00:52:11.112667: step: 2040/530, loss: 0.062119390815496445
2023-01-23 00:52:12.269446: step: 2044/530, loss: 0.1397738754749298
2023-01-23 00:52:13.508033: step: 2048/530, loss: 0.09591779112815857
2023-01-23 00:52:14.688351: step: 2052/530, loss: 0.11064257472753525
2023-01-23 00:52:15.905866: step: 2056/530, loss: 0.07639209181070328
2023-01-23 00:52:17.055301: step: 2060/530, loss: 0.39465731382369995
2023-01-23 00:52:18.209533: step: 2064/530, loss: 0.38528165221214294
2023-01-23 00:52:19.352482: step: 2068/530, loss: 0.21424904465675354
2023-01-23 00:52:20.501434: step: 2072/530, loss: 0.07137145847082138
2023-01-23 00:52:21.680764: step: 2076/530, loss: 0.025903893634676933
2023-01-23 00:52:22.836148: step: 2080/530, loss: 0.17507098615169525
2023-01-23 00:52:24.029157: step: 2084/530, loss: 0.08531332015991211
2023-01-23 00:52:25.209695: step: 2088/530, loss: 0.04731474071741104
2023-01-23 00:52:26.375637: step: 2092/530, loss: 0.847104549407959
2023-01-23 00:52:27.525105: step: 2096/530, loss: 0.25704002380371094
2023-01-23 00:52:28.720351: step: 2100/530, loss: 0.07107844948768616
2023-01-23 00:52:29.953291: step: 2104/530, loss: 0.09040975570678711
2023-01-23 00:52:31.111416: step: 2108/530, loss: 0.5130107998847961
2023-01-23 00:52:32.321038: step: 2112/530, loss: 1.0085654258728027
2023-01-23 00:52:33.487976: step: 2116/530, loss: 0.04115448147058487
2023-01-23 00:52:34.645155: step: 2120/530, loss: 0.084398552775383
==================================================
Loss: 0.179
--------------------
Dev: {'event': {'p': 0.5875251509054326, 'r': 0.7776298268974701, 'f1': 0.6693409742120344}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Test: {'event': {'p': 0.6419294990723562, 'r': 0.7958596894767107, 'f1': 0.7106546854942234}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Chinese: {'event': {'p': 0.5609756097560976, 'r': 0.8518518518518519, 'f1': 0.6764705882352942}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Korean: {'event': {'p': 0.7727272727272727, 'r': 0.5396825396825397, 'f1': 0.6355140186915886}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
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': 7}
New best chinese model...
New best korean model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.5875251509054326, 'r': 0.7776298268974701, 'f1': 0.6693409742120344}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Eng Test for Chinese: {'event': {'p': 0.6419294990723562, 'r': 0.7958596894767107, 'f1': 0.7106546854942234}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Sample Chinese: {'event': {'p': 0.5609756097560976, 'r': 0.8518518518518519, 'f1': 0.6764705882352942}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5875251509054326, 'r': 0.7776298268974701, 'f1': 0.6693409742120344}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Eng Test for Korean: {'event': {'p': 0.6419294990723562, 'r': 0.7958596894767107, 'f1': 0.7106546854942234}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Sample Korean: {'event': {'p': 0.7727272727272727, 'r': 0.5396825396825397, 'f1': 0.6355140186915886}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5951882845188284, 'r': 0.7576564580559254, 'f1': 0.6666666666666666}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6663405088062623, 'r': 0.7832087406555491, 'f1': 0.7200634417129264}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5, 'r': 0.6666666666666666, 'f1': 0.5714285714285715}, '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 00:53:34.365743: step: 4/530, loss: 0.013045120052993298
2023-01-23 00:53:35.500884: step: 8/530, loss: 0.14052416384220123
2023-01-23 00:53:36.697200: step: 12/530, loss: 0.0852198600769043
2023-01-23 00:53:37.858544: step: 16/530, loss: 0.013116646558046341
2023-01-23 00:53:39.098851: step: 20/530, loss: 0.1346844732761383
2023-01-23 00:53:40.311963: step: 24/530, loss: 0.038956452161073685
2023-01-23 00:53:41.491846: step: 28/530, loss: 0.07555808871984482
2023-01-23 00:53:42.653500: step: 32/530, loss: 0.053922273218631744
2023-01-23 00:53:43.817298: step: 36/530, loss: 0.021027278155088425
2023-01-23 00:53:45.008010: step: 40/530, loss: 0.15186342597007751
2023-01-23 00:53:46.202171: step: 44/530, loss: 0.11963143199682236
2023-01-23 00:53:47.401619: step: 48/530, loss: 0.02114858664572239
2023-01-23 00:53:48.588100: step: 52/530, loss: 0.26652461290359497
2023-01-23 00:53:49.763731: step: 56/530, loss: 0.06590834259986877
2023-01-23 00:53:50.930094: step: 60/530, loss: 0.02814197540283203
2023-01-23 00:53:52.111906: step: 64/530, loss: 0.01302804984152317
2023-01-23 00:53:53.304064: step: 68/530, loss: 0.035091400146484375
2023-01-23 00:53:54.501612: step: 72/530, loss: 0.05958350747823715
2023-01-23 00:53:55.679300: step: 76/530, loss: 0.5154921412467957
2023-01-23 00:53:56.820962: step: 80/530, loss: 0.04587617143988609
2023-01-23 00:53:57.939933: step: 84/530, loss: 0.04583015665411949
2023-01-23 00:53:59.115778: step: 88/530, loss: 0.014336585998535156
2023-01-23 00:54:00.289351: step: 92/530, loss: 0.032526396214962006
2023-01-23 00:54:01.459531: step: 96/530, loss: 0.26413780450820923
2023-01-23 00:54:02.623880: step: 100/530, loss: 0.08424311131238937
2023-01-23 00:54:03.824429: step: 104/530, loss: 0.6141337752342224
2023-01-23 00:54:04.990435: step: 108/530, loss: 0.04038744047284126
2023-01-23 00:54:06.222833: step: 112/530, loss: 0.09230895340442657
2023-01-23 00:54:07.417986: step: 116/530, loss: 0.1172037124633789
2023-01-23 00:54:08.606387: step: 120/530, loss: 0.2667948305606842
2023-01-23 00:54:09.835196: step: 124/530, loss: 0.6686827540397644
2023-01-23 00:54:10.968121: step: 128/530, loss: 0.03657274320721626
2023-01-23 00:54:12.155619: step: 132/530, loss: 0.01795358583331108
2023-01-23 00:54:13.277741: step: 136/530, loss: 0.11793716251850128
2023-01-23 00:54:14.436644: step: 140/530, loss: 0.5495710372924805
2023-01-23 00:54:15.620580: step: 144/530, loss: 0.15649351477622986
2023-01-23 00:54:16.784526: step: 148/530, loss: 0.01924934610724449
2023-01-23 00:54:17.930666: step: 152/530, loss: 0.126353457570076
2023-01-23 00:54:19.117501: step: 156/530, loss: 0.10839171707630157
2023-01-23 00:54:20.294024: step: 160/530, loss: 0.103558748960495
2023-01-23 00:54:21.456919: step: 164/530, loss: 0.03488488122820854
2023-01-23 00:54:22.617557: step: 168/530, loss: 0.07031060010194778
2023-01-23 00:54:23.789166: step: 172/530, loss: 0.11431103199720383
2023-01-23 00:54:24.968068: step: 176/530, loss: 0.14870090782642365
2023-01-23 00:54:26.169816: step: 180/530, loss: 0.07193470001220703
2023-01-23 00:54:27.333702: step: 184/530, loss: 0.05818605422973633
2023-01-23 00:54:28.482905: step: 188/530, loss: 0.06970290839672089
2023-01-23 00:54:29.662947: step: 192/530, loss: 0.0024049757048487663
2023-01-23 00:54:30.822034: step: 196/530, loss: 0.14908239245414734
2023-01-23 00:54:31.980795: step: 200/530, loss: 0.2746809124946594
2023-01-23 00:54:33.196809: step: 204/530, loss: 0.0611940398812294
2023-01-23 00:54:34.354015: step: 208/530, loss: 0.05474557727575302
2023-01-23 00:54:35.518828: step: 212/530, loss: 0.13059405982494354
2023-01-23 00:54:36.640010: step: 216/530, loss: 0.54752117395401
2023-01-23 00:54:37.861161: step: 220/530, loss: 0.11060447245836258
2023-01-23 00:54:39.002800: step: 224/530, loss: 0.0651267021894455
2023-01-23 00:54:40.203423: step: 228/530, loss: 0.03605613857507706
2023-01-23 00:54:41.438828: step: 232/530, loss: 0.016681768000125885
2023-01-23 00:54:42.684718: step: 236/530, loss: 0.057855986058712006
2023-01-23 00:54:43.818148: step: 240/530, loss: 0.03727400302886963
2023-01-23 00:54:44.965364: step: 244/530, loss: 0.02317791059613228
2023-01-23 00:54:46.134638: step: 248/530, loss: 0.08414573967456818
2023-01-23 00:54:47.305998: step: 252/530, loss: 0.1709299087524414
2023-01-23 00:54:48.474389: step: 256/530, loss: 0.1816527396440506
2023-01-23 00:54:49.598770: step: 260/530, loss: 0.40960776805877686
2023-01-23 00:54:50.772277: step: 264/530, loss: 0.10755190998315811
2023-01-23 00:54:51.908598: step: 268/530, loss: 0.09921374171972275
2023-01-23 00:54:53.084849: step: 272/530, loss: 0.04398531839251518
2023-01-23 00:54:54.262390: step: 276/530, loss: 0.037724971771240234
2023-01-23 00:54:55.466859: step: 280/530, loss: 0.21813221275806427
2023-01-23 00:54:56.618381: step: 284/530, loss: 0.008573818020522594
2023-01-23 00:54:57.767900: step: 288/530, loss: 0.057091712951660156
2023-01-23 00:54:58.916468: step: 292/530, loss: 0.017960675060749054
2023-01-23 00:55:00.065555: step: 296/530, loss: 0.39324912428855896
2023-01-23 00:55:01.220046: step: 300/530, loss: 0.08897967636585236
2023-01-23 00:55:02.377275: step: 304/530, loss: 0.04633474349975586
2023-01-23 00:55:03.567138: step: 308/530, loss: 0.09259138256311417
2023-01-23 00:55:04.763490: step: 312/530, loss: 0.08159799873828888
2023-01-23 00:55:05.954856: step: 316/530, loss: 0.11364221572875977
2023-01-23 00:55:07.155791: step: 320/530, loss: 0.05468578264117241
2023-01-23 00:55:08.356286: step: 324/530, loss: 0.11089906096458435
2023-01-23 00:55:09.535297: step: 328/530, loss: 0.10832004994153976
2023-01-23 00:55:10.723725: step: 332/530, loss: 0.16594481468200684
2023-01-23 00:55:11.927446: step: 336/530, loss: 0.03907022625207901
2023-01-23 00:55:13.109143: step: 340/530, loss: 0.23426222801208496
2023-01-23 00:55:14.290477: step: 344/530, loss: 0.21895432472229004
2023-01-23 00:55:15.508313: step: 348/530, loss: 0.07421131432056427
2023-01-23 00:55:16.643125: step: 352/530, loss: 0.07454857975244522
2023-01-23 00:55:17.804582: step: 356/530, loss: 0.11459775269031525
2023-01-23 00:55:19.015784: step: 360/530, loss: 0.11691675335168839
2023-01-23 00:55:20.144565: step: 364/530, loss: 0.028308534994721413
2023-01-23 00:55:21.306967: step: 368/530, loss: 0.07967119663953781
2023-01-23 00:55:22.460946: step: 372/530, loss: 0.7948236465454102
2023-01-23 00:55:23.647727: step: 376/530, loss: 0.10896148532629013
2023-01-23 00:55:24.846662: step: 380/530, loss: 0.07730035483837128
2023-01-23 00:55:25.995646: step: 384/530, loss: 0.11764278262853622
2023-01-23 00:55:27.171929: step: 388/530, loss: 0.4085315465927124
2023-01-23 00:55:28.365367: step: 392/530, loss: 0.06540469825267792
2023-01-23 00:55:29.561336: step: 396/530, loss: 0.05156746134161949
2023-01-23 00:55:30.733877: step: 400/530, loss: 0.3796706199645996
2023-01-23 00:55:31.864408: step: 404/530, loss: 0.04525151476264
2023-01-23 00:55:33.033940: step: 408/530, loss: 0.13885074853897095
2023-01-23 00:55:34.188856: step: 412/530, loss: 0.059441566467285156
2023-01-23 00:55:35.426644: step: 416/530, loss: 0.11389460414648056
2023-01-23 00:55:36.661263: step: 420/530, loss: 0.09221974015235901
2023-01-23 00:55:37.834265: step: 424/530, loss: 0.028554439544677734
2023-01-23 00:55:39.026041: step: 428/530, loss: 0.3380745053291321
2023-01-23 00:55:40.212814: step: 432/530, loss: 0.023958493024110794
2023-01-23 00:55:41.371663: step: 436/530, loss: 0.06500005722045898
2023-01-23 00:55:42.555074: step: 440/530, loss: 0.0658545047044754
2023-01-23 00:55:43.694459: step: 444/530, loss: 0.05891161039471626
2023-01-23 00:55:44.864003: step: 448/530, loss: 0.023718737065792084
2023-01-23 00:55:46.046941: step: 452/530, loss: 0.034954167902469635
2023-01-23 00:55:47.193318: step: 456/530, loss: 0.0340849868953228
2023-01-23 00:55:48.383423: step: 460/530, loss: 0.1800159513950348
2023-01-23 00:55:49.562201: step: 464/530, loss: 0.027072429656982422
2023-01-23 00:55:50.723437: step: 468/530, loss: 0.19576627016067505
2023-01-23 00:55:51.869688: step: 472/530, loss: 0.0490022674202919
2023-01-23 00:55:53.034655: step: 476/530, loss: 0.08780527114868164
2023-01-23 00:55:54.205449: step: 480/530, loss: 0.07503862679004669
2023-01-23 00:55:55.427316: step: 484/530, loss: 0.11762829124927521
2023-01-23 00:55:56.571356: step: 488/530, loss: 0.0416048988699913
2023-01-23 00:55:57.727097: step: 492/530, loss: 0.1955157369375229
2023-01-23 00:55:58.936797: step: 496/530, loss: 0.21065063774585724
2023-01-23 00:56:00.072749: step: 500/530, loss: 0.40678104758262634
2023-01-23 00:56:01.227274: step: 504/530, loss: 0.04530501365661621
2023-01-23 00:56:02.413111: step: 508/530, loss: 0.0852634459733963
2023-01-23 00:56:03.579104: step: 512/530, loss: 0.11491432785987854
2023-01-23 00:56:04.746067: step: 516/530, loss: 0.05294659361243248
2023-01-23 00:56:05.883835: step: 520/530, loss: 0.06817712634801865
2023-01-23 00:56:07.069159: step: 524/530, loss: 0.08993415534496307
2023-01-23 00:56:08.226537: step: 528/530, loss: 0.0556035041809082
2023-01-23 00:56:09.434423: step: 532/530, loss: 0.018457889556884766
2023-01-23 00:56:10.585369: step: 536/530, loss: 0.2707945704460144
2023-01-23 00:56:11.731906: step: 540/530, loss: 0.026917606592178345
2023-01-23 00:56:12.912497: step: 544/530, loss: 0.05884981155395508
2023-01-23 00:56:14.081377: step: 548/530, loss: 0.28797751665115356
2023-01-23 00:56:15.264997: step: 552/530, loss: 0.05277619510889053
2023-01-23 00:56:16.452963: step: 556/530, loss: 0.016150856390595436
2023-01-23 00:56:17.639976: step: 560/530, loss: 0.019348621368408203
2023-01-23 00:56:18.791342: step: 564/530, loss: 0.9106072187423706
2023-01-23 00:56:19.978153: step: 568/530, loss: 0.03239498287439346
2023-01-23 00:56:21.197297: step: 572/530, loss: 0.8493542671203613
2023-01-23 00:56:22.347975: step: 576/530, loss: 0.13186055421829224
2023-01-23 00:56:23.512658: step: 580/530, loss: 0.0899294912815094
2023-01-23 00:56:24.673028: step: 584/530, loss: 0.04232511669397354
2023-01-23 00:56:25.854610: step: 588/530, loss: 0.03737621381878853
2023-01-23 00:56:27.012113: step: 592/530, loss: 0.08451423048973083
2023-01-23 00:56:28.155441: step: 596/530, loss: 0.06950731575489044
2023-01-23 00:56:29.293453: step: 600/530, loss: 0.08066006004810333
2023-01-23 00:56:30.431474: step: 604/530, loss: 0.05632514879107475
2023-01-23 00:56:31.591331: step: 608/530, loss: 0.11548750102519989
2023-01-23 00:56:32.766707: step: 612/530, loss: 0.07566623389720917
2023-01-23 00:56:33.916817: step: 616/530, loss: 0.044866371899843216
2023-01-23 00:56:35.112548: step: 620/530, loss: 0.36357975006103516
2023-01-23 00:56:36.299809: step: 624/530, loss: 0.04405384510755539
2023-01-23 00:56:37.544036: step: 628/530, loss: 0.39372768998146057
2023-01-23 00:56:38.744517: step: 632/530, loss: 0.14358320832252502
2023-01-23 00:56:39.922574: step: 636/530, loss: 0.46996474266052246
2023-01-23 00:56:41.068258: step: 640/530, loss: 0.020949935540556908
2023-01-23 00:56:42.296422: step: 644/530, loss: 0.1604146957397461
2023-01-23 00:56:43.470202: step: 648/530, loss: 0.10612840950489044
2023-01-23 00:56:44.676431: step: 652/530, loss: 0.3621363341808319
2023-01-23 00:56:45.866584: step: 656/530, loss: 0.07020549476146698
2023-01-23 00:56:47.038369: step: 660/530, loss: 0.0519709587097168
2023-01-23 00:56:48.240439: step: 664/530, loss: 0.06753101944923401
2023-01-23 00:56:49.403726: step: 668/530, loss: 0.04194474220275879
2023-01-23 00:56:50.571930: step: 672/530, loss: 0.11760219931602478
2023-01-23 00:56:51.795060: step: 676/530, loss: 0.1327778697013855
2023-01-23 00:56:52.943916: step: 680/530, loss: 0.08648691326379776
2023-01-23 00:56:54.105974: step: 684/530, loss: 0.19290320575237274
2023-01-23 00:56:55.281966: step: 688/530, loss: 0.014221668243408203
2023-01-23 00:56:56.442797: step: 692/530, loss: 0.12658095359802246
2023-01-23 00:56:57.615807: step: 696/530, loss: 0.11362600326538086
2023-01-23 00:56:58.778101: step: 700/530, loss: 0.2863524258136749
2023-01-23 00:56:59.932114: step: 704/530, loss: 0.11817741394042969
2023-01-23 00:57:01.108093: step: 708/530, loss: 0.06823205947875977
2023-01-23 00:57:02.272117: step: 712/530, loss: 0.03991599380970001
2023-01-23 00:57:03.407891: step: 716/530, loss: 0.09215731918811798
2023-01-23 00:57:04.559177: step: 720/530, loss: 0.10536480695009232
2023-01-23 00:57:05.756113: step: 724/530, loss: 1.2240935564041138
2023-01-23 00:57:06.946942: step: 728/530, loss: 0.08709335327148438
2023-01-23 00:57:08.113198: step: 732/530, loss: 0.39023178815841675
2023-01-23 00:57:09.267843: step: 736/530, loss: 0.533431351184845
2023-01-23 00:57:10.440374: step: 740/530, loss: 0.13381260633468628
2023-01-23 00:57:11.626186: step: 744/530, loss: 0.13263873755931854
2023-01-23 00:57:12.796770: step: 748/530, loss: 0.16422347724437714
2023-01-23 00:57:13.987274: step: 752/530, loss: 0.025727272033691406
2023-01-23 00:57:15.143811: step: 756/530, loss: 0.0958210900425911
2023-01-23 00:57:16.282232: step: 760/530, loss: 0.13712501525878906
2023-01-23 00:57:17.463355: step: 764/530, loss: 0.08112931251525879
2023-01-23 00:57:18.639078: step: 768/530, loss: 0.10942325741052628
2023-01-23 00:57:19.826420: step: 772/530, loss: 0.17530114948749542
2023-01-23 00:57:20.994475: step: 776/530, loss: 0.17239519953727722
2023-01-23 00:57:22.159997: step: 780/530, loss: 0.02592456340789795
2023-01-23 00:57:23.328798: step: 784/530, loss: 0.039057470858097076
2023-01-23 00:57:24.509937: step: 788/530, loss: 0.058348558843135834
2023-01-23 00:57:25.675670: step: 792/530, loss: 0.4029165804386139
2023-01-23 00:57:26.872313: step: 796/530, loss: 0.020975828170776367
2023-01-23 00:57:28.027048: step: 800/530, loss: 0.03616919368505478
2023-01-23 00:57:29.214964: step: 804/530, loss: 0.2501760423183441
2023-01-23 00:57:30.354567: step: 808/530, loss: 0.06119508668780327
2023-01-23 00:57:31.560959: step: 812/530, loss: 0.19562816619873047
2023-01-23 00:57:32.698813: step: 816/530, loss: 0.23795709013938904
2023-01-23 00:57:33.844311: step: 820/530, loss: 0.023935556411743164
2023-01-23 00:57:34.998685: step: 824/530, loss: 0.12495122849941254
2023-01-23 00:57:36.138547: step: 828/530, loss: 0.004291725344955921
2023-01-23 00:57:37.298318: step: 832/530, loss: 0.05817871168255806
2023-01-23 00:57:38.471557: step: 836/530, loss: 0.028009986504912376
2023-01-23 00:57:39.669217: step: 840/530, loss: 0.06398141384124756
2023-01-23 00:57:40.860875: step: 844/530, loss: 0.04607763513922691
2023-01-23 00:57:42.044528: step: 848/530, loss: 0.17701320350170135
2023-01-23 00:57:43.206990: step: 852/530, loss: 0.029433155432343483
2023-01-23 00:57:44.376212: step: 856/530, loss: 0.08652222901582718
2023-01-23 00:57:45.530005: step: 860/530, loss: 0.11909443885087967
2023-01-23 00:57:46.666948: step: 864/530, loss: 0.036504171788692474
2023-01-23 00:57:47.851583: step: 868/530, loss: 0.12051931023597717
2023-01-23 00:57:49.024355: step: 872/530, loss: 0.022498322650790215
2023-01-23 00:57:50.219673: step: 876/530, loss: 0.04097125679254532
2023-01-23 00:57:51.405679: step: 880/530, loss: 0.37603139877319336
2023-01-23 00:57:52.580433: step: 884/530, loss: 0.046959877014160156
2023-01-23 00:57:53.734731: step: 888/530, loss: 0.20209531486034393
2023-01-23 00:57:54.932458: step: 892/530, loss: 0.06541232764720917
2023-01-23 00:57:56.091867: step: 896/530, loss: 0.31880244612693787
2023-01-23 00:57:57.244803: step: 900/530, loss: 0.024764299392700195
2023-01-23 00:57:58.398529: step: 904/530, loss: 0.040851689875125885
2023-01-23 00:57:59.578479: step: 908/530, loss: 0.06192808225750923
2023-01-23 00:58:00.764013: step: 912/530, loss: 0.0012679100036621094
2023-01-23 00:58:01.916619: step: 916/530, loss: 0.10110047459602356
2023-01-23 00:58:03.100203: step: 920/530, loss: 0.48553696274757385
2023-01-23 00:58:04.275787: step: 924/530, loss: 0.39482155442237854
2023-01-23 00:58:05.448651: step: 928/530, loss: 0.10315370559692383
2023-01-23 00:58:06.630942: step: 932/530, loss: 0.07056531310081482
2023-01-23 00:58:07.827034: step: 936/530, loss: 0.4381921887397766
2023-01-23 00:58:08.992190: step: 940/530, loss: 0.015747547149658203
2023-01-23 00:58:10.146840: step: 944/530, loss: 0.2618350088596344
2023-01-23 00:58:11.309382: step: 948/530, loss: 0.16479292511940002
2023-01-23 00:58:12.518030: step: 952/530, loss: 0.2234029769897461
2023-01-23 00:58:13.688962: step: 956/530, loss: 0.03433685377240181
2023-01-23 00:58:14.896895: step: 960/530, loss: 0.004579448606818914
2023-01-23 00:58:16.072587: step: 964/530, loss: 0.049104057252407074
2023-01-23 00:58:17.257538: step: 968/530, loss: 0.0518835075199604
2023-01-23 00:58:18.432106: step: 972/530, loss: 0.06821499019861221
2023-01-23 00:58:19.635924: step: 976/530, loss: 0.09833602607250214
2023-01-23 00:58:20.798534: step: 980/530, loss: 0.06892852485179901
2023-01-23 00:58:21.936902: step: 984/530, loss: 0.07818165421485901
2023-01-23 00:58:23.110200: step: 988/530, loss: 0.2109006941318512
2023-01-23 00:58:24.298025: step: 992/530, loss: 0.4272526800632477
2023-01-23 00:58:25.483448: step: 996/530, loss: 0.047452785074710846
2023-01-23 00:58:26.681735: step: 1000/530, loss: 0.15157346427440643
2023-01-23 00:58:27.860583: step: 1004/530, loss: 0.18811312317848206
2023-01-23 00:58:29.045807: step: 1008/530, loss: 0.07474146038293839
2023-01-23 00:58:30.221914: step: 1012/530, loss: 0.06701584160327911
2023-01-23 00:58:31.378540: step: 1016/530, loss: 0.13227252662181854
2023-01-23 00:58:32.585440: step: 1020/530, loss: 0.08481156826019287
2023-01-23 00:58:33.749101: step: 1024/530, loss: 0.07477331161499023
2023-01-23 00:58:34.874516: step: 1028/530, loss: 0.14963455498218536
2023-01-23 00:58:36.089677: step: 1032/530, loss: 0.26902252435684204
2023-01-23 00:58:37.283252: step: 1036/530, loss: 0.06920204311609268
2023-01-23 00:58:38.422213: step: 1040/530, loss: 0.06259097903966904
2023-01-23 00:58:39.578764: step: 1044/530, loss: 0.017882157117128372
2023-01-23 00:58:40.740855: step: 1048/530, loss: 0.16647294163703918
2023-01-23 00:58:41.921934: step: 1052/530, loss: 0.014980221167206764
2023-01-23 00:58:43.098818: step: 1056/530, loss: 0.015264511108398438
2023-01-23 00:58:44.270796: step: 1060/530, loss: 0.05593071132898331
2023-01-23 00:58:45.445902: step: 1064/530, loss: 0.21541514992713928
2023-01-23 00:58:46.626391: step: 1068/530, loss: 0.037931155413389206
2023-01-23 00:58:47.821717: step: 1072/530, loss: 0.44292184710502625
2023-01-23 00:58:48.994122: step: 1076/530, loss: 0.06857776641845703
2023-01-23 00:58:50.194337: step: 1080/530, loss: 0.07078199833631516
2023-01-23 00:58:51.375282: step: 1084/530, loss: 0.08580265194177628
2023-01-23 00:58:52.575283: step: 1088/530, loss: 0.13268999755382538
2023-01-23 00:58:53.809753: step: 1092/530, loss: 0.17966032028198242
2023-01-23 00:58:54.929074: step: 1096/530, loss: 0.05442772060632706
2023-01-23 00:58:56.084160: step: 1100/530, loss: 0.007423782255500555
2023-01-23 00:58:57.250512: step: 1104/530, loss: 0.057573892176151276
2023-01-23 00:58:58.447401: step: 1108/530, loss: 0.5918250679969788
2023-01-23 00:58:59.650500: step: 1112/530, loss: 0.09379902482032776
2023-01-23 00:59:00.825970: step: 1116/530, loss: 0.03173828125
2023-01-23 00:59:01.996538: step: 1120/530, loss: 0.027653945609927177
2023-01-23 00:59:03.155366: step: 1124/530, loss: 0.025098610669374466
2023-01-23 00:59:04.354735: step: 1128/530, loss: 0.15435296297073364
2023-01-23 00:59:05.511151: step: 1132/530, loss: 0.02274918556213379
2023-01-23 00:59:06.694518: step: 1136/530, loss: 0.026772402226924896
2023-01-23 00:59:07.917291: step: 1140/530, loss: 0.03127851337194443
2023-01-23 00:59:09.085982: step: 1144/530, loss: 0.1578589826822281
2023-01-23 00:59:10.254571: step: 1148/530, loss: 0.09690102934837341
2023-01-23 00:59:11.435776: step: 1152/530, loss: 0.09761867672204971
2023-01-23 00:59:12.621382: step: 1156/530, loss: 0.19028446078300476
2023-01-23 00:59:13.817861: step: 1160/530, loss: 0.08661022782325745
2023-01-23 00:59:14.992231: step: 1164/530, loss: 0.14662230014801025
2023-01-23 00:59:16.172007: step: 1168/530, loss: 0.06844548881053925
2023-01-23 00:59:17.342661: step: 1172/530, loss: 0.13025951385498047
2023-01-23 00:59:18.517671: step: 1176/530, loss: 0.09994945675134659
2023-01-23 00:59:19.692277: step: 1180/530, loss: 0.05450735241174698
2023-01-23 00:59:20.912872: step: 1184/530, loss: 0.056549716740846634
2023-01-23 00:59:22.063526: step: 1188/530, loss: 0.5148805379867554
2023-01-23 00:59:23.233258: step: 1192/530, loss: 0.30767592787742615
2023-01-23 00:59:24.407024: step: 1196/530, loss: 0.044800471514463425
2023-01-23 00:59:25.532180: step: 1200/530, loss: 0.04206957668066025
2023-01-23 00:59:26.671358: step: 1204/530, loss: 0.014521313831210136
2023-01-23 00:59:27.820016: step: 1208/530, loss: 0.04784660413861275
2023-01-23 00:59:28.997299: step: 1212/530, loss: 0.13512355089187622
2023-01-23 00:59:30.164739: step: 1216/530, loss: 0.0498172752559185
2023-01-23 00:59:31.290862: step: 1220/530, loss: 0.02315545082092285
2023-01-23 00:59:32.485793: step: 1224/530, loss: 0.24566583335399628
2023-01-23 00:59:33.687206: step: 1228/530, loss: 0.06925515830516815
2023-01-23 00:59:34.830789: step: 1232/530, loss: 0.14455366134643555
2023-01-23 00:59:35.999021: step: 1236/530, loss: 0.04208822175860405
2023-01-23 00:59:37.145146: step: 1240/530, loss: 0.12012634426355362
2023-01-23 00:59:38.314865: step: 1244/530, loss: 0.023621082305908203
2023-01-23 00:59:39.481024: step: 1248/530, loss: 0.03550824895501137
2023-01-23 00:59:40.645553: step: 1252/530, loss: 0.05719804763793945
2023-01-23 00:59:41.845736: step: 1256/530, loss: 0.06784696131944656
2023-01-23 00:59:43.027882: step: 1260/530, loss: 0.09180068969726562
2023-01-23 00:59:44.210223: step: 1264/530, loss: 0.1408812552690506
2023-01-23 00:59:45.394924: step: 1268/530, loss: 0.21204060316085815
2023-01-23 00:59:46.572295: step: 1272/530, loss: 0.14301013946533203
2023-01-23 00:59:47.726007: step: 1276/530, loss: 0.09710659831762314
2023-01-23 00:59:48.873641: step: 1280/530, loss: 0.07046661525964737
2023-01-23 00:59:50.017769: step: 1284/530, loss: 0.15801700949668884
2023-01-23 00:59:51.187863: step: 1288/530, loss: 0.022974874824285507
2023-01-23 00:59:52.374615: step: 1292/530, loss: 0.17636719346046448
2023-01-23 00:59:53.475994: step: 1296/530, loss: 0.033312033861875534
2023-01-23 00:59:54.672134: step: 1300/530, loss: 0.09740486741065979
2023-01-23 00:59:55.842541: step: 1304/530, loss: 0.19906625151634216
2023-01-23 00:59:57.054223: step: 1308/530, loss: 0.07131786644458771
2023-01-23 00:59:58.203016: step: 1312/530, loss: 0.037758734077215195
2023-01-23 00:59:59.351746: step: 1316/530, loss: 0.024937011301517487
2023-01-23 01:00:00.520579: step: 1320/530, loss: 0.14974196255207062
2023-01-23 01:00:01.713965: step: 1324/530, loss: 0.049985792487859726
2023-01-23 01:00:02.902915: step: 1328/530, loss: 0.19455395638942719
2023-01-23 01:00:04.114808: step: 1332/530, loss: 0.4468805193901062
2023-01-23 01:00:05.317720: step: 1336/530, loss: 0.042569350451231
2023-01-23 01:00:06.490353: step: 1340/530, loss: 0.07818488776683807
2023-01-23 01:00:07.669013: step: 1344/530, loss: 0.05048418045043945
2023-01-23 01:00:08.859065: step: 1348/530, loss: 0.024895193055272102
2023-01-23 01:00:10.027411: step: 1352/530, loss: 0.13149681687355042
2023-01-23 01:00:11.215275: step: 1356/530, loss: 0.12719860672950745
2023-01-23 01:00:12.453250: step: 1360/530, loss: 0.010184097103774548
2023-01-23 01:00:13.646389: step: 1364/530, loss: 0.1038001999258995
2023-01-23 01:00:14.803047: step: 1368/530, loss: 0.08869022130966187
2023-01-23 01:00:15.987560: step: 1372/530, loss: 0.20104819536209106
2023-01-23 01:00:17.151580: step: 1376/530, loss: 0.12108460068702698
2023-01-23 01:00:18.374854: step: 1380/530, loss: 0.1257733851671219
2023-01-23 01:00:19.531581: step: 1384/530, loss: 0.10082702338695526
2023-01-23 01:00:20.728641: step: 1388/530, loss: 0.25426143407821655
2023-01-23 01:00:21.916968: step: 1392/530, loss: 0.04248414188623428
2023-01-23 01:00:23.092044: step: 1396/530, loss: 0.09141306579113007
2023-01-23 01:00:24.271631: step: 1400/530, loss: 0.03686637803912163
2023-01-23 01:00:25.533667: step: 1404/530, loss: 0.14809313416481018
2023-01-23 01:00:26.693867: step: 1408/530, loss: 0.38216662406921387
2023-01-23 01:00:27.874344: step: 1412/530, loss: 0.17603188753128052
2023-01-23 01:00:29.029300: step: 1416/530, loss: 0.17136649787425995
2023-01-23 01:00:30.241706: step: 1420/530, loss: 0.10437572002410889
2023-01-23 01:00:31.446067: step: 1424/530, loss: 0.09972548484802246
2023-01-23 01:00:32.615253: step: 1428/530, loss: 0.08594071865081787
2023-01-23 01:00:33.798200: step: 1432/530, loss: 0.06367502361536026
2023-01-23 01:00:34.971619: step: 1436/530, loss: 0.051168348640203476
2023-01-23 01:00:36.140770: step: 1440/530, loss: 0.05116138607263565
2023-01-23 01:00:37.314865: step: 1444/530, loss: 0.38174134492874146
2023-01-23 01:00:38.501136: step: 1448/530, loss: 0.06080923229455948
2023-01-23 01:00:39.679280: step: 1452/530, loss: 0.05187497287988663
2023-01-23 01:00:40.825230: step: 1456/530, loss: 0.2548791766166687
2023-01-23 01:00:41.962104: step: 1460/530, loss: 0.12913627922534943
2023-01-23 01:00:43.144456: step: 1464/530, loss: 0.15458975732326508
2023-01-23 01:00:44.264996: step: 1468/530, loss: 0.03883795812726021
2023-01-23 01:00:45.398402: step: 1472/530, loss: 0.09312081336975098
2023-01-23 01:00:46.575689: step: 1476/530, loss: 0.18543758988380432
2023-01-23 01:00:47.737442: step: 1480/530, loss: 0.11836633831262589
2023-01-23 01:00:48.894821: step: 1484/530, loss: 0.03745298087596893
2023-01-23 01:00:50.063735: step: 1488/530, loss: 0.022816849872469902
2023-01-23 01:00:51.201467: step: 1492/530, loss: 0.11238770186901093
2023-01-23 01:00:52.406136: step: 1496/530, loss: 0.09759664535522461
2023-01-23 01:00:53.566482: step: 1500/530, loss: 0.003906822297722101
2023-01-23 01:00:54.728048: step: 1504/530, loss: 0.04060111194849014
2023-01-23 01:00:55.923252: step: 1508/530, loss: 0.04522418975830078
2023-01-23 01:00:57.125131: step: 1512/530, loss: 0.01917257346212864
2023-01-23 01:00:58.279204: step: 1516/530, loss: 0.10081377625465393
2023-01-23 01:00:59.466165: step: 1520/530, loss: 0.06978444755077362
2023-01-23 01:01:00.670339: step: 1524/530, loss: 0.0520360954105854
2023-01-23 01:01:01.836014: step: 1528/530, loss: 0.025663042441010475
2023-01-23 01:01:02.993659: step: 1532/530, loss: 0.11294908821582794
2023-01-23 01:01:04.162606: step: 1536/530, loss: 0.07499366253614426
2023-01-23 01:01:05.315082: step: 1540/530, loss: 0.13869480788707733
2023-01-23 01:01:06.499276: step: 1544/530, loss: 0.08346385508775711
2023-01-23 01:01:07.652951: step: 1548/530, loss: 0.15427446365356445
2023-01-23 01:01:08.866695: step: 1552/530, loss: 0.17748050391674042
2023-01-23 01:01:10.029161: step: 1556/530, loss: 0.6396341323852539
2023-01-23 01:01:11.186718: step: 1560/530, loss: 0.09145331382751465
2023-01-23 01:01:12.364398: step: 1564/530, loss: 0.05875282362103462
2023-01-23 01:01:13.558973: step: 1568/530, loss: 0.02896604686975479
2023-01-23 01:01:14.742384: step: 1572/530, loss: 0.04940080642700195
2023-01-23 01:01:15.917963: step: 1576/530, loss: 0.08777294307947159
2023-01-23 01:01:17.094692: step: 1580/530, loss: 0.08255481719970703
2023-01-23 01:01:18.279545: step: 1584/530, loss: 0.0699835792183876
2023-01-23 01:01:19.429558: step: 1588/530, loss: 1.2319685220718384
2023-01-23 01:01:20.581632: step: 1592/530, loss: 0.08405351638793945
2023-01-23 01:01:21.787737: step: 1596/530, loss: 0.2647155821323395
2023-01-23 01:01:23.006150: step: 1600/530, loss: 0.07167161256074905
2023-01-23 01:01:24.199149: step: 1604/530, loss: 0.09674038738012314
2023-01-23 01:01:25.330258: step: 1608/530, loss: 0.12136144936084747
2023-01-23 01:01:26.491243: step: 1612/530, loss: 0.0273877140134573
2023-01-23 01:01:27.687013: step: 1616/530, loss: 0.16425058245658875
2023-01-23 01:01:28.861661: step: 1620/530, loss: 0.3084336221218109
2023-01-23 01:01:29.992639: step: 1624/530, loss: 0.08178134262561798
2023-01-23 01:01:31.192283: step: 1628/530, loss: 0.0524139404296875
2023-01-23 01:01:32.368733: step: 1632/530, loss: 0.04134741052985191
2023-01-23 01:01:33.539031: step: 1636/530, loss: 0.09371843189001083
2023-01-23 01:01:34.710385: step: 1640/530, loss: 0.17186136543750763
2023-01-23 01:01:35.870625: step: 1644/530, loss: 0.014878702349960804
2023-01-23 01:01:37.071564: step: 1648/530, loss: 0.06573009490966797
2023-01-23 01:01:38.232206: step: 1652/530, loss: 0.15445438027381897
2023-01-23 01:01:39.410943: step: 1656/530, loss: 0.08109722286462784
2023-01-23 01:01:40.568620: step: 1660/530, loss: 0.15646134316921234
2023-01-23 01:01:41.740447: step: 1664/530, loss: 0.11655063927173615
2023-01-23 01:01:42.949877: step: 1668/530, loss: 0.11370415985584259
2023-01-23 01:01:44.139094: step: 1672/530, loss: 0.06654338538646698
2023-01-23 01:01:45.327535: step: 1676/530, loss: 0.6581330895423889
2023-01-23 01:01:46.465329: step: 1680/530, loss: 0.07632245868444443
2023-01-23 01:01:47.617911: step: 1684/530, loss: 0.037191011011600494
2023-01-23 01:01:48.749311: step: 1688/530, loss: 0.23326975107192993
2023-01-23 01:01:49.934908: step: 1692/530, loss: 0.07800118625164032
2023-01-23 01:01:51.079401: step: 1696/530, loss: 0.07112687826156616
2023-01-23 01:01:52.250014: step: 1700/530, loss: 0.06100158765912056
2023-01-23 01:01:53.419839: step: 1704/530, loss: 0.0885646790266037
2023-01-23 01:01:54.594154: step: 1708/530, loss: 0.0851224958896637
2023-01-23 01:01:55.793688: step: 1712/530, loss: 0.08866768330335617
2023-01-23 01:01:56.958574: step: 1716/530, loss: 0.04599201679229736
2023-01-23 01:01:58.111496: step: 1720/530, loss: 0.2691568434238434
2023-01-23 01:01:59.295067: step: 1724/530, loss: 0.15080443024635315
2023-01-23 01:02:00.521293: step: 1728/530, loss: 0.015879392623901367
2023-01-23 01:02:01.679340: step: 1732/530, loss: 0.0680382177233696
2023-01-23 01:02:02.860664: step: 1736/530, loss: 0.10171106457710266
2023-01-23 01:02:04.056847: step: 1740/530, loss: 0.1690216064453125
2023-01-23 01:02:05.239505: step: 1744/530, loss: 0.11473341286182404
2023-01-23 01:02:06.453288: step: 1748/530, loss: 0.2098928540945053
2023-01-23 01:02:07.585269: step: 1752/530, loss: 0.0438079833984375
2023-01-23 01:02:08.787788: step: 1756/530, loss: 0.09689980000257492
2023-01-23 01:02:09.955771: step: 1760/530, loss: 0.0667186751961708
2023-01-23 01:02:11.100291: step: 1764/530, loss: 0.030570650473237038
2023-01-23 01:02:12.318200: step: 1768/530, loss: 0.05778038501739502
2023-01-23 01:02:13.493183: step: 1772/530, loss: 0.37360525131225586
2023-01-23 01:02:14.678483: step: 1776/530, loss: 0.15706387162208557
2023-01-23 01:02:15.849367: step: 1780/530, loss: 0.11285553127527237
2023-01-23 01:02:17.015599: step: 1784/530, loss: 0.05312204360961914
2023-01-23 01:02:18.163642: step: 1788/530, loss: 0.05213608592748642
2023-01-23 01:02:19.312395: step: 1792/530, loss: 0.09958372265100479
2023-01-23 01:02:20.487129: step: 1796/530, loss: 0.06323198974132538
2023-01-23 01:02:21.676777: step: 1800/530, loss: 0.7849858999252319
2023-01-23 01:02:22.831985: step: 1804/530, loss: 0.14441372454166412
2023-01-23 01:02:23.977825: step: 1808/530, loss: 0.11752147972583771
2023-01-23 01:02:25.145296: step: 1812/530, loss: 1.7219988107681274
2023-01-23 01:02:26.336113: step: 1816/530, loss: 0.019135331735014915
2023-01-23 01:02:27.545455: step: 1820/530, loss: 0.06368637830018997
2023-01-23 01:02:28.755599: step: 1824/530, loss: 0.08287639915943146
2023-01-23 01:02:29.900971: step: 1828/530, loss: 0.12142477184534073
2023-01-23 01:02:31.120962: step: 1832/530, loss: 0.17107053101062775
2023-01-23 01:02:32.280315: step: 1836/530, loss: 0.1173306480050087
2023-01-23 01:02:33.464280: step: 1840/530, loss: 0.009785938076674938
2023-01-23 01:02:34.608946: step: 1844/530, loss: 0.09142885357141495
2023-01-23 01:02:35.780901: step: 1848/530, loss: 0.07177609205245972
2023-01-23 01:02:36.951386: step: 1852/530, loss: 0.128559872508049
2023-01-23 01:02:38.126290: step: 1856/530, loss: 0.05397796630859375
2023-01-23 01:02:39.277327: step: 1860/530, loss: 0.3483026325702667
2023-01-23 01:02:40.455585: step: 1864/530, loss: 0.1017785593867302
2023-01-23 01:02:41.628129: step: 1868/530, loss: 0.06321001052856445
2023-01-23 01:02:42.817498: step: 1872/530, loss: 0.1154613047838211
2023-01-23 01:02:44.018366: step: 1876/530, loss: 0.927815854549408
2023-01-23 01:02:45.178312: step: 1880/530, loss: 0.1866447478532791
2023-01-23 01:02:46.328829: step: 1884/530, loss: 0.05659375339746475
2023-01-23 01:02:47.507549: step: 1888/530, loss: 0.007974433712661266
2023-01-23 01:02:48.701422: step: 1892/530, loss: 0.18185310065746307
2023-01-23 01:02:49.884812: step: 1896/530, loss: 0.06220044940710068
2023-01-23 01:02:51.071644: step: 1900/530, loss: 0.07474067062139511
2023-01-23 01:02:52.240032: step: 1904/530, loss: 0.04894981533288956
2023-01-23 01:02:53.416132: step: 1908/530, loss: 0.07573194801807404
2023-01-23 01:02:54.532574: step: 1912/530, loss: 0.10847350209951401
2023-01-23 01:02:55.710824: step: 1916/530, loss: 0.05642690882086754
2023-01-23 01:02:56.930618: step: 1920/530, loss: 0.06940746307373047
2023-01-23 01:02:58.086373: step: 1924/530, loss: 0.14880256354808807
2023-01-23 01:02:59.210925: step: 1928/530, loss: 0.08731837570667267
2023-01-23 01:03:00.405982: step: 1932/530, loss: 0.2570681571960449
2023-01-23 01:03:01.591183: step: 1936/530, loss: 0.03943147882819176
2023-01-23 01:03:02.755538: step: 1940/530, loss: 0.11312108486890793
2023-01-23 01:03:03.958200: step: 1944/530, loss: 0.0878661647439003
2023-01-23 01:03:05.098099: step: 1948/530, loss: 0.002971744630485773
2023-01-23 01:03:06.258559: step: 1952/530, loss: 0.08201484382152557
2023-01-23 01:03:07.431748: step: 1956/530, loss: 0.2055068016052246
2023-01-23 01:03:08.618822: step: 1960/530, loss: 0.03998398408293724
2023-01-23 01:03:09.768941: step: 1964/530, loss: 0.03222661092877388
2023-01-23 01:03:10.948154: step: 1968/530, loss: 0.12599678337574005
2023-01-23 01:03:12.121750: step: 1972/530, loss: 0.177737295627594
2023-01-23 01:03:13.274978: step: 1976/530, loss: 0.11004161834716797
2023-01-23 01:03:14.462191: step: 1980/530, loss: 0.0833350270986557
2023-01-23 01:03:15.635262: step: 1984/530, loss: 0.025358010083436966
2023-01-23 01:03:16.798189: step: 1988/530, loss: 0.013653278350830078
2023-01-23 01:03:17.958399: step: 1992/530, loss: 0.10583829879760742
2023-01-23 01:03:19.186941: step: 1996/530, loss: 0.2545835077762604
2023-01-23 01:03:20.350247: step: 2000/530, loss: 0.08382701873779297
2023-01-23 01:03:21.502849: step: 2004/530, loss: 0.056943416595458984
2023-01-23 01:03:22.662263: step: 2008/530, loss: 0.7045565843582153
2023-01-23 01:03:23.800428: step: 2012/530, loss: 0.28513795137405396
2023-01-23 01:03:24.979326: step: 2016/530, loss: 0.0303936954587698
2023-01-23 01:03:26.165690: step: 2020/530, loss: 0.11185251176357269
2023-01-23 01:03:27.310782: step: 2024/530, loss: 0.035360146313905716
2023-01-23 01:03:28.479224: step: 2028/530, loss: 0.03566727787256241
2023-01-23 01:03:29.686590: step: 2032/530, loss: 0.0769142135977745
2023-01-23 01:03:30.866919: step: 2036/530, loss: 0.09557457268238068
2023-01-23 01:03:32.136862: step: 2040/530, loss: 0.19323205947875977
2023-01-23 01:03:33.296867: step: 2044/530, loss: 0.13688507676124573
2023-01-23 01:03:34.472436: step: 2048/530, loss: 0.05665607750415802
2023-01-23 01:03:35.655007: step: 2052/530, loss: 0.5991809964179993
2023-01-23 01:03:36.802993: step: 2056/530, loss: 0.08317652344703674
2023-01-23 01:03:37.923671: step: 2060/530, loss: 1.5039992332458496
2023-01-23 01:03:39.105814: step: 2064/530, loss: 0.5881873369216919
2023-01-23 01:03:40.296100: step: 2068/530, loss: 0.0783659964799881
2023-01-23 01:03:41.455225: step: 2072/530, loss: 1.1040942668914795
2023-01-23 01:03:42.653328: step: 2076/530, loss: 0.20615653693675995
2023-01-23 01:03:43.837786: step: 2080/530, loss: 0.30007848143577576
2023-01-23 01:03:44.977855: step: 2084/530, loss: 0.2076784372329712
2023-01-23 01:03:46.169494: step: 2088/530, loss: 0.05692634731531143
2023-01-23 01:03:47.292058: step: 2092/530, loss: 0.30436134338378906
2023-01-23 01:03:48.449677: step: 2096/530, loss: 0.04967451095581055
2023-01-23 01:03:49.612443: step: 2100/530, loss: 0.01955242082476616
2023-01-23 01:03:50.842374: step: 2104/530, loss: 0.09320392459630966
2023-01-23 01:03:52.005056: step: 2108/530, loss: 0.11518576741218567
2023-01-23 01:03:53.211743: step: 2112/530, loss: 0.0668947696685791
2023-01-23 01:03:54.413702: step: 2116/530, loss: 0.7096875309944153
2023-01-23 01:03:55.642299: step: 2120/530, loss: 0.24146023392677307
==================================================
Loss: 0.140
--------------------
Dev: {'event': {'p': 0.6351501668520578, 'r': 0.7603195739014648, 'f1': 0.6921212121212121}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Test: {'event': {'p': 0.6373175182481752, 'r': 0.8033352501437608, 'f1': 0.7107606207071993}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Chinese: {'event': {'p': 0.5903614457831325, 'r': 0.9074074074074074, 'f1': 0.7153284671532847}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Korean: {'event': {'p': 0.6379310344827587, 'r': 0.5873015873015873, 'f1': 0.6115702479338844}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Russian: {'event': {'p': 0.40476190476190477, 'r': 0.4722222222222222, 'f1': 0.4358974358974359}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
New best chinese model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6351501668520578, 'r': 0.7603195739014648, 'f1': 0.6921212121212121}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Chinese: {'event': {'p': 0.6373175182481752, 'r': 0.8033352501437608, 'f1': 0.7107606207071993}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Chinese: {'event': {'p': 0.5903614457831325, 'r': 0.9074074074074074, 'f1': 0.7153284671532847}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5875251509054326, 'r': 0.7776298268974701, 'f1': 0.6693409742120344}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Eng Test for Korean: {'event': {'p': 0.6419294990723562, 'r': 0.7958596894767107, 'f1': 0.7106546854942234}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Sample Korean: {'event': {'p': 0.7727272727272727, 'r': 0.5396825396825397, 'f1': 0.6355140186915886}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5951882845188284, 'r': 0.7576564580559254, 'f1': 0.6666666666666666}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6663405088062623, 'r': 0.7832087406555491, 'f1': 0.7200634417129264}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5, 'r': 0.6666666666666666, 'f1': 0.5714285714285715}, '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 01:04:47.999227: step: 4/530, loss: 0.15845279395580292
2023-01-23 01:04:49.201531: step: 8/530, loss: 1.622707724571228
2023-01-23 01:04:50.394734: step: 12/530, loss: 0.33869075775146484
2023-01-23 01:04:51.538150: step: 16/530, loss: 0.08766070008277893
2023-01-23 01:04:52.677872: step: 20/530, loss: 0.06736107170581818
2023-01-23 01:04:53.850248: step: 24/530, loss: 0.039551734924316406
2023-01-23 01:04:55.047327: step: 28/530, loss: 0.08271016925573349
2023-01-23 01:04:56.182638: step: 32/530, loss: 0.044249631464481354
2023-01-23 01:04:57.358904: step: 36/530, loss: 0.0416165366768837
2023-01-23 01:04:58.539702: step: 40/530, loss: 0.0295378677546978
2023-01-23 01:04:59.702251: step: 44/530, loss: 0.03457288816571236
2023-01-23 01:05:00.876926: step: 48/530, loss: 0.0551789253950119
2023-01-23 01:05:02.057137: step: 52/530, loss: 0.28563404083251953
2023-01-23 01:05:03.221315: step: 56/530, loss: 0.1284927874803543
2023-01-23 01:05:04.396370: step: 60/530, loss: 0.03176317363977432
2023-01-23 01:05:05.531993: step: 64/530, loss: 0.22944431006908417
2023-01-23 01:05:06.674355: step: 68/530, loss: 0.0471712090075016
2023-01-23 01:05:07.881299: step: 72/530, loss: 0.07176385819911957
2023-01-23 01:05:09.074791: step: 76/530, loss: 0.07358169555664062
2023-01-23 01:05:10.329956: step: 80/530, loss: 0.051629211753606796
2023-01-23 01:05:11.502954: step: 84/530, loss: 0.03616919368505478
2023-01-23 01:05:12.663126: step: 88/530, loss: 0.08161049336194992
2023-01-23 01:05:13.812069: step: 92/530, loss: 0.0617462694644928
2023-01-23 01:05:14.973779: step: 96/530, loss: 0.1673245131969452
2023-01-23 01:05:16.147513: step: 100/530, loss: 0.059185028076171875
2023-01-23 01:05:17.305685: step: 104/530, loss: 0.017926884815096855
2023-01-23 01:05:18.465635: step: 108/530, loss: 0.0749857947230339
2023-01-23 01:05:19.642053: step: 112/530, loss: 0.04163084179162979
2023-01-23 01:05:20.835891: step: 116/530, loss: 0.18099918961524963
2023-01-23 01:05:22.006133: step: 120/530, loss: 0.9036290049552917
2023-01-23 01:05:23.159485: step: 124/530, loss: 0.09026701748371124
2023-01-23 01:05:24.345835: step: 128/530, loss: 0.03945193439722061
2023-01-23 01:05:25.515077: step: 132/530, loss: 0.11284341663122177
2023-01-23 01:05:26.705260: step: 136/530, loss: 0.05342855677008629
2023-01-23 01:05:27.850317: step: 140/530, loss: 0.012876033782958984
2023-01-23 01:05:29.054120: step: 144/530, loss: 0.07015285640954971
2023-01-23 01:05:30.267220: step: 148/530, loss: 0.16492271423339844
2023-01-23 01:05:31.444288: step: 152/530, loss: 0.4989575445652008
2023-01-23 01:05:32.678360: step: 156/530, loss: 0.2948346436023712
2023-01-23 01:05:33.840788: step: 160/530, loss: 0.04725055769085884
2023-01-23 01:05:35.098734: step: 164/530, loss: 0.011922741308808327
2023-01-23 01:05:36.290714: step: 168/530, loss: 0.12056002765893936
2023-01-23 01:05:37.486041: step: 172/530, loss: 0.028836537152528763
2023-01-23 01:05:38.659483: step: 176/530, loss: 0.009949922561645508
2023-01-23 01:05:39.856200: step: 180/530, loss: 0.06635189056396484
2023-01-23 01:05:41.004484: step: 184/530, loss: 0.06446342170238495
2023-01-23 01:05:42.151221: step: 188/530, loss: 0.026972293853759766
2023-01-23 01:05:43.322032: step: 192/530, loss: 0.03372917324304581
2023-01-23 01:05:44.474406: step: 196/530, loss: 0.1725679486989975
2023-01-23 01:05:45.637170: step: 200/530, loss: 0.06030445173382759
2023-01-23 01:05:46.821106: step: 204/530, loss: 0.01964731328189373
2023-01-23 01:05:47.959111: step: 208/530, loss: 0.028240298852324486
2023-01-23 01:05:49.176185: step: 212/530, loss: 0.10379738360643387
2023-01-23 01:05:50.338526: step: 216/530, loss: 0.04669012874364853
2023-01-23 01:05:51.495761: step: 220/530, loss: 0.2680344581604004
2023-01-23 01:05:52.643077: step: 224/530, loss: 0.060888100415468216
2023-01-23 01:05:53.790572: step: 228/530, loss: 0.02537250518798828
2023-01-23 01:05:54.973215: step: 232/530, loss: 0.10358190536499023
2023-01-23 01:05:56.103281: step: 236/530, loss: 0.11830854415893555
2023-01-23 01:05:57.258953: step: 240/530, loss: 0.3694027066230774
2023-01-23 01:05:58.425389: step: 244/530, loss: 0.02728118933737278
2023-01-23 01:05:59.654743: step: 248/530, loss: 0.09859142452478409
2023-01-23 01:06:00.821731: step: 252/530, loss: 0.10015678405761719
2023-01-23 01:06:02.007657: step: 256/530, loss: 0.122918039560318
2023-01-23 01:06:03.195499: step: 260/530, loss: 0.018300820142030716
2023-01-23 01:06:04.325435: step: 264/530, loss: 0.02513599582016468
2023-01-23 01:06:05.522804: step: 268/530, loss: 0.0987861156463623
2023-01-23 01:06:06.695977: step: 272/530, loss: 0.09005054831504822
2023-01-23 01:06:07.828162: step: 276/530, loss: 0.007241535000503063
2023-01-23 01:06:08.995834: step: 280/530, loss: 0.044896893203258514
2023-01-23 01:06:10.131837: step: 284/530, loss: 0.007006979547441006
2023-01-23 01:06:11.294059: step: 288/530, loss: 0.05658278614282608
2023-01-23 01:06:12.445275: step: 292/530, loss: 0.026295794174075127
2023-01-23 01:06:13.651855: step: 296/530, loss: 0.013226342387497425
2023-01-23 01:06:14.791135: step: 300/530, loss: 0.02804575115442276
2023-01-23 01:06:16.008497: step: 304/530, loss: 0.044394779950380325
2023-01-23 01:06:17.173532: step: 308/530, loss: 0.22662125527858734
2023-01-23 01:06:18.330454: step: 312/530, loss: 0.043686769902706146
2023-01-23 01:06:19.522397: step: 316/530, loss: 0.058339785784482956
2023-01-23 01:06:20.741746: step: 320/530, loss: 0.20755872130393982
2023-01-23 01:06:21.874913: step: 324/530, loss: 0.10466700047254562
2023-01-23 01:06:23.089201: step: 328/530, loss: 0.06837377697229385
2023-01-23 01:06:24.239450: step: 332/530, loss: 0.07297305762767792
2023-01-23 01:06:25.377735: step: 336/530, loss: 0.03483028709888458
2023-01-23 01:06:26.574328: step: 340/530, loss: 0.06621008366346359
2023-01-23 01:06:27.752309: step: 344/530, loss: 0.3091033399105072
2023-01-23 01:06:28.901843: step: 348/530, loss: 0.015868376940488815
2023-01-23 01:06:30.039736: step: 352/530, loss: 0.019069766625761986
2023-01-23 01:06:31.202798: step: 356/530, loss: 0.014092206954956055
2023-01-23 01:06:32.404823: step: 360/530, loss: 0.010200024582445621
2023-01-23 01:06:33.578473: step: 364/530, loss: 0.04045286029577255
2023-01-23 01:06:34.735061: step: 368/530, loss: 0.10821942985057831
2023-01-23 01:06:35.873149: step: 372/530, loss: 0.04107093811035156
2023-01-23 01:06:37.024894: step: 376/530, loss: 0.13373327255249023
2023-01-23 01:06:38.216904: step: 380/530, loss: 0.01893320120871067
2023-01-23 01:06:39.375547: step: 384/530, loss: 0.09141799807548523
2023-01-23 01:06:40.525665: step: 388/530, loss: 0.015536022372543812
2023-01-23 01:06:41.659048: step: 392/530, loss: 0.060567498207092285
2023-01-23 01:06:42.863670: step: 396/530, loss: 0.04974031448364258
2023-01-23 01:06:44.055423: step: 400/530, loss: 0.06978759914636612
2023-01-23 01:06:45.227834: step: 404/530, loss: 0.07836513221263885
2023-01-23 01:06:46.372543: step: 408/530, loss: 0.048665713518857956
2023-01-23 01:06:47.528853: step: 412/530, loss: 0.03707246854901314
2023-01-23 01:06:48.708223: step: 416/530, loss: 0.03857602924108505
2023-01-23 01:06:49.851655: step: 420/530, loss: 0.04320202022790909
2023-01-23 01:06:50.982939: step: 424/530, loss: 0.06060810014605522
2023-01-23 01:06:52.157060: step: 428/530, loss: 0.032482028007507324
2023-01-23 01:06:53.329722: step: 432/530, loss: 0.021082688122987747
2023-01-23 01:06:54.506963: step: 436/530, loss: 0.006242180243134499
2023-01-23 01:06:55.682869: step: 440/530, loss: 0.03648901358246803
2023-01-23 01:06:56.832961: step: 444/530, loss: 0.10904040187597275
2023-01-23 01:06:58.005332: step: 448/530, loss: 0.04181623458862305
2023-01-23 01:06:59.200423: step: 452/530, loss: 0.06782789528369904
2023-01-23 01:07:00.382070: step: 456/530, loss: 0.04444284737110138
2023-01-23 01:07:01.603679: step: 460/530, loss: 0.08857281506061554
2023-01-23 01:07:02.783200: step: 464/530, loss: 0.015480137430131435
2023-01-23 01:07:03.986385: step: 468/530, loss: 0.04405803605914116
2023-01-23 01:07:05.203577: step: 472/530, loss: 0.06597767025232315
2023-01-23 01:07:06.415828: step: 476/530, loss: 0.25855541229248047
2023-01-23 01:07:07.604997: step: 480/530, loss: 0.09969902038574219
2023-01-23 01:07:08.771309: step: 484/530, loss: 0.07222404330968857
2023-01-23 01:07:09.932916: step: 488/530, loss: 0.05053606256842613
2023-01-23 01:07:11.099486: step: 492/530, loss: 0.8873142004013062
2023-01-23 01:07:12.322146: step: 496/530, loss: 0.1109904795885086
2023-01-23 01:07:13.493192: step: 500/530, loss: 0.1378006935119629
2023-01-23 01:07:14.666417: step: 504/530, loss: 0.031890176236629486
2023-01-23 01:07:15.809337: step: 508/530, loss: 0.021184062585234642
2023-01-23 01:07:17.020940: step: 512/530, loss: 0.07848325371742249
2023-01-23 01:07:18.161539: step: 516/530, loss: 0.1467302292585373
2023-01-23 01:07:19.325559: step: 520/530, loss: 0.10992298275232315
2023-01-23 01:07:20.490828: step: 524/530, loss: 0.0708930492401123
2023-01-23 01:07:21.665701: step: 528/530, loss: 0.08113260567188263
2023-01-23 01:07:22.797592: step: 532/530, loss: 0.06294284015893936
2023-01-23 01:07:23.951263: step: 536/530, loss: 0.134280726313591
2023-01-23 01:07:25.166394: step: 540/530, loss: 0.0459783561527729
2023-01-23 01:07:26.350462: step: 544/530, loss: 0.025130653753876686
2023-01-23 01:07:27.536537: step: 548/530, loss: 0.17327946424484253
2023-01-23 01:07:28.711069: step: 552/530, loss: 0.004549503326416016
2023-01-23 01:07:29.924459: step: 556/530, loss: 0.11944351345300674
2023-01-23 01:07:31.073265: step: 560/530, loss: 0.04510369524359703
2023-01-23 01:07:32.249961: step: 564/530, loss: 0.24413014948368073
2023-01-23 01:07:33.403039: step: 568/530, loss: 0.053214170038700104
2023-01-23 01:07:34.574930: step: 572/530, loss: 0.04179535061120987
2023-01-23 01:07:35.733178: step: 576/530, loss: 0.028563402593135834
2023-01-23 01:07:36.933572: step: 580/530, loss: 0.10005893558263779
2023-01-23 01:07:38.107929: step: 584/530, loss: 0.06685810536146164
2023-01-23 01:07:39.263882: step: 588/530, loss: 0.04205475002527237
2023-01-23 01:07:40.400975: step: 592/530, loss: 0.00614776648581028
2023-01-23 01:07:41.606625: step: 596/530, loss: 0.04956074059009552
2023-01-23 01:07:42.777985: step: 600/530, loss: 0.1447279006242752
2023-01-23 01:07:43.996706: step: 604/530, loss: 0.01263275183737278
2023-01-23 01:07:45.122591: step: 608/530, loss: 0.011170101352036
2023-01-23 01:07:46.269479: step: 612/530, loss: 0.06403732299804688
2023-01-23 01:07:47.471558: step: 616/530, loss: 0.035303402692079544
2023-01-23 01:07:48.638798: step: 620/530, loss: 0.129747673869133
2023-01-23 01:07:49.826821: step: 624/530, loss: 0.10466757416725159
2023-01-23 01:07:51.017412: step: 628/530, loss: 0.022001981735229492
2023-01-23 01:07:52.140789: step: 632/530, loss: 0.0452788844704628
2023-01-23 01:07:53.306543: step: 636/530, loss: 0.040712930262088776
2023-01-23 01:07:54.486223: step: 640/530, loss: 0.041222475469112396
2023-01-23 01:07:55.639734: step: 644/530, loss: 0.1497552990913391
2023-01-23 01:07:56.796221: step: 648/530, loss: 0.06223516911268234
2023-01-23 01:07:57.947243: step: 652/530, loss: 0.07656240463256836
2023-01-23 01:07:59.111264: step: 656/530, loss: 0.0846463292837143
2023-01-23 01:08:00.275758: step: 660/530, loss: 0.09599395096302032
2023-01-23 01:08:01.450569: step: 664/530, loss: 0.10290992259979248
2023-01-23 01:08:02.614278: step: 668/530, loss: 0.07619600743055344
2023-01-23 01:08:03.767045: step: 672/530, loss: 0.03589000552892685
2023-01-23 01:08:04.929622: step: 676/530, loss: 0.07724523544311523
2023-01-23 01:08:06.139492: step: 680/530, loss: 0.05449113994836807
2023-01-23 01:08:07.324854: step: 684/530, loss: 0.06263675540685654
2023-01-23 01:08:08.502993: step: 688/530, loss: 0.04581804573535919
2023-01-23 01:08:09.651576: step: 692/530, loss: 0.01583724096417427
2023-01-23 01:08:10.841722: step: 696/530, loss: 0.13324417173862457
2023-01-23 01:08:12.055716: step: 700/530, loss: 0.03744878992438316
2023-01-23 01:08:13.243693: step: 704/530, loss: 0.03915085643529892
2023-01-23 01:08:14.447613: step: 708/530, loss: 0.06985321640968323
2023-01-23 01:08:15.591383: step: 712/530, loss: 0.02766655758023262
2023-01-23 01:08:16.811507: step: 716/530, loss: 0.061554476618766785
2023-01-23 01:08:17.996057: step: 720/530, loss: 0.08023491501808167
2023-01-23 01:08:19.154544: step: 724/530, loss: 0.17367896437644958
2023-01-23 01:08:20.358147: step: 728/530, loss: 0.1662307232618332
2023-01-23 01:08:21.551464: step: 732/530, loss: 0.036238670349121094
2023-01-23 01:08:22.750286: step: 736/530, loss: 0.07550239562988281
2023-01-23 01:08:23.891414: step: 740/530, loss: 0.020705081522464752
2023-01-23 01:08:25.072500: step: 744/530, loss: 0.032326020300388336
2023-01-23 01:08:26.235975: step: 748/530, loss: 0.2889842987060547
2023-01-23 01:08:27.429229: step: 752/530, loss: 0.038077257573604584
2023-01-23 01:08:28.585786: step: 756/530, loss: 0.020296193659305573
2023-01-23 01:08:29.742445: step: 760/530, loss: 0.12724390625953674
2023-01-23 01:08:30.941866: step: 764/530, loss: 6.227782726287842
2023-01-23 01:08:32.127218: step: 768/530, loss: 0.0704723373055458
2023-01-23 01:08:33.270129: step: 772/530, loss: 0.010985375382006168
2023-01-23 01:08:34.461839: step: 776/530, loss: 0.035125862807035446
2023-01-23 01:08:35.656211: step: 780/530, loss: 0.02393341064453125
2023-01-23 01:08:36.825853: step: 784/530, loss: 0.03975982964038849
2023-01-23 01:08:37.964045: step: 788/530, loss: 0.1708083152770996
2023-01-23 01:08:39.127041: step: 792/530, loss: 0.547723114490509
2023-01-23 01:08:40.280066: step: 796/530, loss: 0.14834804832935333
2023-01-23 01:08:41.469337: step: 800/530, loss: 0.19332151114940643
2023-01-23 01:08:42.613323: step: 804/530, loss: 1.8239805698394775
2023-01-23 01:08:43.762060: step: 808/530, loss: 0.08215799927711487
2023-01-23 01:08:45.040971: step: 812/530, loss: 0.06138224899768829
2023-01-23 01:08:46.180505: step: 816/530, loss: 0.041655588895082474
2023-01-23 01:08:47.390993: step: 820/530, loss: 0.051939964294433594
2023-01-23 01:08:48.553343: step: 824/530, loss: 0.03875446319580078
2023-01-23 01:08:49.712913: step: 828/530, loss: 0.09748440235853195
2023-01-23 01:08:50.885958: step: 832/530, loss: 0.06202840805053711
2023-01-23 01:08:52.088041: step: 836/530, loss: 0.06961822509765625
2023-01-23 01:08:53.291618: step: 840/530, loss: 0.016143132001161575
2023-01-23 01:08:54.456866: step: 844/530, loss: 0.004495430272072554
2023-01-23 01:08:55.610992: step: 848/530, loss: 0.007852828130126
2023-01-23 01:08:56.803429: step: 852/530, loss: 0.049698878079652786
2023-01-23 01:08:58.026295: step: 856/530, loss: 0.12559108436107635
2023-01-23 01:08:59.226883: step: 860/530, loss: 0.00766568211838603
2023-01-23 01:09:00.400984: step: 864/530, loss: 0.09925498813390732
2023-01-23 01:09:01.566189: step: 868/530, loss: 0.03700599819421768
2023-01-23 01:09:02.715728: step: 872/530, loss: 0.014387035742402077
2023-01-23 01:09:03.910773: step: 876/530, loss: 0.016269970685243607
2023-01-23 01:09:05.105906: step: 880/530, loss: 0.03401973471045494
2023-01-23 01:09:06.259699: step: 884/530, loss: 0.039260294288396835
2023-01-23 01:09:07.444464: step: 888/530, loss: 0.05661635473370552
2023-01-23 01:09:08.600774: step: 892/530, loss: 0.08707509189844131
2023-01-23 01:09:09.764714: step: 896/530, loss: 0.0644037276506424
2023-01-23 01:09:10.925742: step: 900/530, loss: 0.11059337109327316
2023-01-23 01:09:12.091586: step: 904/530, loss: 0.5515964031219482
2023-01-23 01:09:13.242128: step: 908/530, loss: 0.05791626125574112
2023-01-23 01:09:14.421741: step: 912/530, loss: 0.094445139169693
2023-01-23 01:09:15.604451: step: 916/530, loss: 0.10451459884643555
2023-01-23 01:09:16.831653: step: 920/530, loss: 0.07610253989696503
2023-01-23 01:09:18.086156: step: 924/530, loss: 0.2037479430437088
2023-01-23 01:09:19.281510: step: 928/530, loss: 0.09647388756275177
2023-01-23 01:09:20.463831: step: 932/530, loss: 0.02946005016565323
2023-01-23 01:09:21.655745: step: 936/530, loss: 0.10217857360839844
2023-01-23 01:09:22.824935: step: 940/530, loss: 0.009791946038603783
2023-01-23 01:09:23.988394: step: 944/530, loss: 0.07124662399291992
2023-01-23 01:09:25.169085: step: 948/530, loss: 0.01458120346069336
2023-01-23 01:09:26.360574: step: 952/530, loss: 0.266981303691864
2023-01-23 01:09:27.570139: step: 956/530, loss: 0.07228453457355499
2023-01-23 01:09:28.731175: step: 960/530, loss: 0.022940827533602715
2023-01-23 01:09:29.870237: step: 964/530, loss: 0.15632718801498413
2023-01-23 01:09:31.044186: step: 968/530, loss: 0.16595040261745453
2023-01-23 01:09:32.197839: step: 972/530, loss: 0.02584867551922798
2023-01-23 01:09:33.341480: step: 976/530, loss: 0.040729425847530365
2023-01-23 01:09:34.529351: step: 980/530, loss: 0.06620617210865021
2023-01-23 01:09:35.689489: step: 984/530, loss: 0.6692536473274231
2023-01-23 01:09:36.826311: step: 988/530, loss: 0.10619039833545685
2023-01-23 01:09:38.006773: step: 992/530, loss: 0.021389387547969818
2023-01-23 01:09:39.196284: step: 996/530, loss: 0.09521007537841797
2023-01-23 01:09:40.354502: step: 1000/530, loss: 0.12559795379638672
2023-01-23 01:09:41.528784: step: 1004/530, loss: 0.10956211388111115
2023-01-23 01:09:42.684648: step: 1008/530, loss: 0.025915145874023438
2023-01-23 01:09:43.854871: step: 1012/530, loss: 0.7702674269676208
2023-01-23 01:09:44.989580: step: 1016/530, loss: 0.07918114960193634
2023-01-23 01:09:46.139248: step: 1020/530, loss: 0.09994392096996307
2023-01-23 01:09:47.289470: step: 1024/530, loss: 0.018405748531222343
2023-01-23 01:09:48.460031: step: 1028/530, loss: 0.06505708396434784
2023-01-23 01:09:49.598589: step: 1032/530, loss: 0.05158384144306183
2023-01-23 01:09:50.787064: step: 1036/530, loss: 0.013117790222167969
2023-01-23 01:09:51.955367: step: 1040/530, loss: 0.053784895688295364
2023-01-23 01:09:53.152340: step: 1044/530, loss: 0.0009424209711141884
2023-01-23 01:09:54.310298: step: 1048/530, loss: 0.028988217934966087
2023-01-23 01:09:55.494102: step: 1052/530, loss: 0.09882692992687225
2023-01-23 01:09:56.695033: step: 1056/530, loss: 0.10553894191980362
2023-01-23 01:09:57.869269: step: 1060/530, loss: 0.03369283676147461
2023-01-23 01:09:59.073210: step: 1064/530, loss: 0.10636568069458008
2023-01-23 01:10:00.297194: step: 1068/530, loss: 0.09341640770435333
2023-01-23 01:10:01.463904: step: 1072/530, loss: 0.0036599875893443823
2023-01-23 01:10:02.647760: step: 1076/530, loss: 0.041690826416015625
2023-01-23 01:10:03.832308: step: 1080/530, loss: 0.01931467279791832
2023-01-23 01:10:05.024247: step: 1084/530, loss: 0.07385434955358505
2023-01-23 01:10:06.208522: step: 1088/530, loss: 0.028326798230409622
2023-01-23 01:10:07.351485: step: 1092/530, loss: 0.0036805630661547184
2023-01-23 01:10:08.534518: step: 1096/530, loss: 0.06924257427453995
2023-01-23 01:10:09.646968: step: 1100/530, loss: 0.040366724133491516
2023-01-23 01:10:10.836299: step: 1104/530, loss: 0.015607595443725586
2023-01-23 01:10:12.032314: step: 1108/530, loss: 0.1588093787431717
2023-01-23 01:10:13.223055: step: 1112/530, loss: 0.021831322461366653
2023-01-23 01:10:14.377823: step: 1116/530, loss: 0.1833307147026062
2023-01-23 01:10:15.547834: step: 1120/530, loss: 0.04198112338781357
2023-01-23 01:10:16.703976: step: 1124/530, loss: 0.018747713416814804
2023-01-23 01:10:17.875841: step: 1128/530, loss: 0.058507729321718216
2023-01-23 01:10:19.067390: step: 1132/530, loss: 0.04667625576257706
2023-01-23 01:10:20.243228: step: 1136/530, loss: 0.14336252212524414
2023-01-23 01:10:21.419960: step: 1140/530, loss: 0.03824019432067871
2023-01-23 01:10:22.611344: step: 1144/530, loss: 0.039048388600349426
2023-01-23 01:10:23.812443: step: 1148/530, loss: 0.10422239452600479
2023-01-23 01:10:24.999518: step: 1152/530, loss: 0.10801353305578232
2023-01-23 01:10:26.207171: step: 1156/530, loss: 0.26632562279701233
2023-01-23 01:10:27.400363: step: 1160/530, loss: 0.07175872474908829
2023-01-23 01:10:28.618460: step: 1164/530, loss: 0.0644746795296669
2023-01-23 01:10:29.775243: step: 1168/530, loss: 0.19294533133506775
2023-01-23 01:10:30.964617: step: 1172/530, loss: 0.21934567391872406
2023-01-23 01:10:32.096732: step: 1176/530, loss: 0.022718096151947975
2023-01-23 01:10:33.266203: step: 1180/530, loss: 0.11897353827953339
2023-01-23 01:10:34.445027: step: 1184/530, loss: 0.0520656555891037
2023-01-23 01:10:35.590873: step: 1188/530, loss: 0.21914702653884888
2023-01-23 01:10:36.800787: step: 1192/530, loss: 0.09227696061134338
2023-01-23 01:10:37.968728: step: 1196/530, loss: 0.06390824168920517
2023-01-23 01:10:39.177763: step: 1200/530, loss: 0.08842983841896057
2023-01-23 01:10:40.335519: step: 1204/530, loss: 0.057123471051454544
2023-01-23 01:10:41.506525: step: 1208/530, loss: 0.1228095144033432
2023-01-23 01:10:42.683083: step: 1212/530, loss: 0.08844508975744247
2023-01-23 01:10:43.843883: step: 1216/530, loss: 0.011104035191237926
2023-01-23 01:10:44.983616: step: 1220/530, loss: 0.014559745788574219
2023-01-23 01:10:46.149332: step: 1224/530, loss: 0.09527621418237686
2023-01-23 01:10:47.315274: step: 1228/530, loss: 0.021008683368563652
2023-01-23 01:10:48.518937: step: 1232/530, loss: 0.13089609146118164
2023-01-23 01:10:49.705583: step: 1236/530, loss: 0.018972396850585938
2023-01-23 01:10:50.880983: step: 1240/530, loss: 0.12789621949195862
2023-01-23 01:10:52.087320: step: 1244/530, loss: 0.1727897673845291
2023-01-23 01:10:53.263720: step: 1248/530, loss: 0.14199848473072052
2023-01-23 01:10:54.476100: step: 1252/530, loss: 0.014613533392548561
2023-01-23 01:10:55.662224: step: 1256/530, loss: 0.08304043114185333
2023-01-23 01:10:56.839363: step: 1260/530, loss: 0.0358274020254612
2023-01-23 01:10:57.965709: step: 1264/530, loss: 0.062093257904052734
2023-01-23 01:10:59.139894: step: 1268/530, loss: 0.1521453857421875
2023-01-23 01:11:00.320087: step: 1272/530, loss: 0.41924938559532166
2023-01-23 01:11:01.495355: step: 1276/530, loss: 0.06571187824010849
2023-01-23 01:11:02.667960: step: 1280/530, loss: 0.050582122057676315
2023-01-23 01:11:03.837194: step: 1284/530, loss: 0.037352561950683594
2023-01-23 01:11:05.056533: step: 1288/530, loss: 0.1718570739030838
2023-01-23 01:11:06.243010: step: 1292/530, loss: 0.05200400575995445
2023-01-23 01:11:07.420604: step: 1296/530, loss: 0.045015908777713776
2023-01-23 01:11:08.556286: step: 1300/530, loss: 0.22699260711669922
2023-01-23 01:11:09.716620: step: 1304/530, loss: 0.05964255705475807
2023-01-23 01:11:10.936873: step: 1308/530, loss: 0.21141637861728668
2023-01-23 01:11:12.144301: step: 1312/530, loss: 0.04659365862607956
2023-01-23 01:11:13.299670: step: 1316/530, loss: 0.007095909211784601
2023-01-23 01:11:14.489619: step: 1320/530, loss: 0.009560060687363148
2023-01-23 01:11:15.672909: step: 1324/530, loss: 0.0548061840236187
2023-01-23 01:11:16.875507: step: 1328/530, loss: 0.03962211683392525
2023-01-23 01:11:18.058970: step: 1332/530, loss: 0.024711133912205696
2023-01-23 01:11:19.214288: step: 1336/530, loss: 0.014567517675459385
2023-01-23 01:11:20.379246: step: 1340/530, loss: 0.36985188722610474
2023-01-23 01:11:21.526726: step: 1344/530, loss: 0.18090248107910156
2023-01-23 01:11:22.733364: step: 1348/530, loss: 0.20969204604625702
2023-01-23 01:11:23.892100: step: 1352/530, loss: 0.12543784081935883
2023-01-23 01:11:25.055563: step: 1356/530, loss: 0.21262595057487488
2023-01-23 01:11:26.221686: step: 1360/530, loss: 0.005930805113166571
2023-01-23 01:11:27.403801: step: 1364/530, loss: 0.031262971460819244
2023-01-23 01:11:28.585117: step: 1368/530, loss: 0.054126814007759094
2023-01-23 01:11:29.711535: step: 1372/530, loss: 0.052906036376953125
2023-01-23 01:11:30.896400: step: 1376/530, loss: 0.09675750881433487
2023-01-23 01:11:32.090264: step: 1380/530, loss: 0.03650627285242081
2023-01-23 01:11:33.271636: step: 1384/530, loss: 0.14927463233470917
2023-01-23 01:11:34.426446: step: 1388/530, loss: 0.022114086896181107
2023-01-23 01:11:35.609660: step: 1392/530, loss: 0.14367036521434784
2023-01-23 01:11:36.746958: step: 1396/530, loss: 0.08893384784460068
2023-01-23 01:11:37.900331: step: 1400/530, loss: 0.036626528948545456
2023-01-23 01:11:39.066623: step: 1404/530, loss: 0.02657156065106392
2023-01-23 01:11:40.250439: step: 1408/530, loss: 0.06285410374403
2023-01-23 01:11:41.449884: step: 1412/530, loss: 0.0449947826564312
2023-01-23 01:11:42.614413: step: 1416/530, loss: 0.05079841613769531
2023-01-23 01:11:43.806895: step: 1420/530, loss: 0.007391166873276234
2023-01-23 01:11:45.029058: step: 1424/530, loss: 0.19784145057201385
2023-01-23 01:11:46.226437: step: 1428/530, loss: 0.07485189288854599
2023-01-23 01:11:47.414830: step: 1432/530, loss: 0.11022701114416122
2023-01-23 01:11:48.618808: step: 1436/530, loss: 0.14997348189353943
2023-01-23 01:11:49.789935: step: 1440/530, loss: 0.018115997314453125
2023-01-23 01:11:50.951470: step: 1444/530, loss: 0.028583623468875885
2023-01-23 01:11:52.167578: step: 1448/530, loss: 0.16174563765525818
2023-01-23 01:11:53.380517: step: 1452/530, loss: 0.07666949927806854
2023-01-23 01:11:54.550399: step: 1456/530, loss: 0.07380715757608414
2023-01-23 01:11:55.714745: step: 1460/530, loss: 0.00554580707103014
2023-01-23 01:11:56.897035: step: 1464/530, loss: 0.05170736089348793
2023-01-23 01:11:58.127518: step: 1468/530, loss: 0.06031398847699165
2023-01-23 01:11:59.306312: step: 1472/530, loss: 0.055828481912612915
2023-01-23 01:12:00.467465: step: 1476/530, loss: 0.05847177654504776
2023-01-23 01:12:01.660146: step: 1480/530, loss: 0.04697704687714577
2023-01-23 01:12:02.846895: step: 1484/530, loss: 0.057266999036073685
2023-01-23 01:12:04.047243: step: 1488/530, loss: 0.18401594460010529
2023-01-23 01:12:05.246487: step: 1492/530, loss: 0.0021869661286473274
2023-01-23 01:12:06.443233: step: 1496/530, loss: 0.1832314431667328
2023-01-23 01:12:07.635594: step: 1500/530, loss: 0.05921168625354767
2023-01-23 01:12:08.796634: step: 1504/530, loss: 0.039419081062078476
2023-01-23 01:12:09.977436: step: 1508/530, loss: 0.066564179956913
2023-01-23 01:12:11.128769: step: 1512/530, loss: 0.1521112471818924
2023-01-23 01:12:12.344900: step: 1516/530, loss: 0.17261992394924164
2023-01-23 01:12:13.499603: step: 1520/530, loss: 0.14822015166282654
2023-01-23 01:12:14.673438: step: 1524/530, loss: 0.15001411736011505
2023-01-23 01:12:15.846957: step: 1528/530, loss: 0.12929821014404297
2023-01-23 01:12:17.017009: step: 1532/530, loss: 0.008008575066924095
2023-01-23 01:12:18.188053: step: 1536/530, loss: 0.08087348937988281
2023-01-23 01:12:19.359504: step: 1540/530, loss: 0.046652697026729584
2023-01-23 01:12:20.527947: step: 1544/530, loss: 0.03032541275024414
2023-01-23 01:12:21.718043: step: 1548/530, loss: 0.018466543406248093
2023-01-23 01:12:22.853311: step: 1552/530, loss: 0.07086333632469177
2023-01-23 01:12:24.011446: step: 1556/530, loss: 0.006249618250876665
2023-01-23 01:12:25.198316: step: 1560/530, loss: 0.0755847916007042
2023-01-23 01:12:26.360923: step: 1564/530, loss: 0.1146155372262001
2023-01-23 01:12:27.551255: step: 1568/530, loss: 0.10537935048341751
2023-01-23 01:12:28.705660: step: 1572/530, loss: 0.1913030594587326
2023-01-23 01:12:29.894231: step: 1576/530, loss: 0.11692734062671661
2023-01-23 01:12:31.061227: step: 1580/530, loss: 0.014831018634140491
2023-01-23 01:12:32.218201: step: 1584/530, loss: 0.008850526995956898
2023-01-23 01:12:33.377402: step: 1588/530, loss: 0.03558092191815376
2023-01-23 01:12:34.558400: step: 1592/530, loss: 0.16514739394187927
2023-01-23 01:12:35.688686: step: 1596/530, loss: 0.008432770147919655
2023-01-23 01:12:36.821871: step: 1600/530, loss: 0.05681314319372177
2023-01-23 01:12:38.000133: step: 1604/530, loss: 0.04270324856042862
2023-01-23 01:12:39.194571: step: 1608/530, loss: 0.08593006432056427
2023-01-23 01:12:40.397804: step: 1612/530, loss: 0.08044710755348206
2023-01-23 01:12:41.615308: step: 1616/530, loss: 0.05296144634485245
2023-01-23 01:12:42.741590: step: 1620/530, loss: 0.05182352289557457
2023-01-23 01:12:43.974195: step: 1624/530, loss: 0.06678536534309387
2023-01-23 01:12:45.135793: step: 1628/530, loss: 0.061350204050540924
2023-01-23 01:12:46.306903: step: 1632/530, loss: 0.08674897998571396
2023-01-23 01:12:47.545532: step: 1636/530, loss: 0.41009101271629333
2023-01-23 01:12:48.760679: step: 1640/530, loss: 0.10833082348108292
2023-01-23 01:12:49.951355: step: 1644/530, loss: 0.02701597288250923
2023-01-23 01:12:51.115823: step: 1648/530, loss: 0.11499843746423721
2023-01-23 01:12:52.321912: step: 1652/530, loss: 0.021666662767529488
2023-01-23 01:12:53.505181: step: 1656/530, loss: 0.06022052839398384
2023-01-23 01:12:54.675716: step: 1660/530, loss: 0.05260324478149414
2023-01-23 01:12:55.850451: step: 1664/530, loss: 0.028481770306825638
2023-01-23 01:12:57.063494: step: 1668/530, loss: 0.026079367846250534
2023-01-23 01:12:58.232052: step: 1672/530, loss: 0.028040314093232155
2023-01-23 01:12:59.405132: step: 1676/530, loss: 0.038277626037597656
2023-01-23 01:13:00.572540: step: 1680/530, loss: 0.087426096200943
2023-01-23 01:13:01.765861: step: 1684/530, loss: 0.04134349897503853
2023-01-23 01:13:02.969344: step: 1688/530, loss: 0.05519428104162216
2023-01-23 01:13:04.159932: step: 1692/530, loss: 0.033372119069099426
2023-01-23 01:13:05.342575: step: 1696/530, loss: 0.3449346423149109
2023-01-23 01:13:06.488442: step: 1700/530, loss: 0.08747806400060654
2023-01-23 01:13:07.658831: step: 1704/530, loss: 0.25175362825393677
2023-01-23 01:13:08.840053: step: 1708/530, loss: 0.04997234418988228
2023-01-23 01:13:09.996646: step: 1712/530, loss: 0.04796609655022621
2023-01-23 01:13:11.188234: step: 1716/530, loss: 0.016085529699921608
2023-01-23 01:13:12.328322: step: 1720/530, loss: 0.0825173407793045
2023-01-23 01:13:13.503116: step: 1724/530, loss: 0.04569091647863388
2023-01-23 01:13:14.727317: step: 1728/530, loss: 0.24064083397388458
2023-01-23 01:13:15.890187: step: 1732/530, loss: 0.0712437629699707
2023-01-23 01:13:17.037773: step: 1736/530, loss: 0.04602022469043732
2023-01-23 01:13:18.219916: step: 1740/530, loss: 0.0920473113656044
2023-01-23 01:13:19.401708: step: 1744/530, loss: 0.05632515251636505
2023-01-23 01:13:20.567098: step: 1748/530, loss: 0.13201884925365448
2023-01-23 01:13:21.761336: step: 1752/530, loss: 0.03179903328418732
2023-01-23 01:13:22.927417: step: 1756/530, loss: 0.04840269312262535
2023-01-23 01:13:24.131096: step: 1760/530, loss: 0.03660087659955025
2023-01-23 01:13:25.299796: step: 1764/530, loss: 0.04072270542383194
2023-01-23 01:13:26.452721: step: 1768/530, loss: 0.07305145263671875
2023-01-23 01:13:27.618476: step: 1772/530, loss: 0.04337292164564133
2023-01-23 01:13:28.793244: step: 1776/530, loss: 0.1968904435634613
2023-01-23 01:13:29.999672: step: 1780/530, loss: 0.0230241771787405
2023-01-23 01:13:31.219437: step: 1784/530, loss: 0.06974849849939346
2023-01-23 01:13:32.392288: step: 1788/530, loss: 0.05908184498548508
2023-01-23 01:13:33.555807: step: 1792/530, loss: 0.36147913336753845
2023-01-23 01:13:34.771641: step: 1796/530, loss: 0.0768955796957016
2023-01-23 01:13:35.934780: step: 1800/530, loss: 0.06698283553123474
2023-01-23 01:13:37.118885: step: 1804/530, loss: 0.6433885097503662
2023-01-23 01:13:38.280000: step: 1808/530, loss: 0.10862883925437927
2023-01-23 01:13:39.461144: step: 1812/530, loss: 0.06186265870928764
2023-01-23 01:13:40.639836: step: 1816/530, loss: 0.16273097693920135
2023-01-23 01:13:41.851590: step: 1820/530, loss: 0.04408147558569908
2023-01-23 01:13:43.089805: step: 1824/530, loss: 0.025667190551757812
2023-01-23 01:13:44.236315: step: 1828/530, loss: 0.02391096204519272
2023-01-23 01:13:45.459837: step: 1832/530, loss: 0.07087206840515137
2023-01-23 01:13:46.623494: step: 1836/530, loss: 0.0404149554669857
2023-01-23 01:13:47.789464: step: 1840/530, loss: 0.02362379990518093
2023-01-23 01:13:48.981823: step: 1844/530, loss: 0.02720470353960991
2023-01-23 01:13:50.135242: step: 1848/530, loss: 0.02001953125
2023-01-23 01:13:51.307732: step: 1852/530, loss: 0.12756028771400452
2023-01-23 01:13:52.478785: step: 1856/530, loss: 0.006270814221352339
2023-01-23 01:13:53.650379: step: 1860/530, loss: 0.06130991131067276
2023-01-23 01:13:54.879084: step: 1864/530, loss: 0.013648796826601028
2023-01-23 01:13:56.076956: step: 1868/530, loss: 0.047820866107940674
2023-01-23 01:13:57.260503: step: 1872/530, loss: 0.06345033645629883
2023-01-23 01:13:58.451163: step: 1876/530, loss: 0.13459205627441406
2023-01-23 01:13:59.630883: step: 1880/530, loss: 0.034517861902713776
2023-01-23 01:14:00.785867: step: 1884/530, loss: 0.148609921336174
2023-01-23 01:14:01.993749: step: 1888/530, loss: 0.0062687876634299755
2023-01-23 01:14:03.157770: step: 1892/530, loss: 0.10174808651208878
2023-01-23 01:14:04.341169: step: 1896/530, loss: 0.18933601677417755
2023-01-23 01:14:05.482837: step: 1900/530, loss: 0.04540596157312393
2023-01-23 01:14:06.670794: step: 1904/530, loss: 0.11992726475000381
2023-01-23 01:14:07.842632: step: 1908/530, loss: 0.06002183258533478
2023-01-23 01:14:09.032357: step: 1912/530, loss: 0.11655215919017792
2023-01-23 01:14:10.270103: step: 1916/530, loss: 0.027437781915068626
2023-01-23 01:14:11.457809: step: 1920/530, loss: 0.38339102268218994
2023-01-23 01:14:12.657560: step: 1924/530, loss: 0.040841199457645416
2023-01-23 01:14:13.827479: step: 1928/530, loss: 0.16949692368507385
2023-01-23 01:14:14.975011: step: 1932/530, loss: 0.014570236206054688
2023-01-23 01:14:16.154218: step: 1936/530, loss: 0.14264750480651855
2023-01-23 01:14:17.330711: step: 1940/530, loss: 0.17664670944213867
2023-01-23 01:14:18.464224: step: 1944/530, loss: 0.04278526455163956
2023-01-23 01:14:19.613856: step: 1948/530, loss: 0.020009517669677734
2023-01-23 01:14:20.781696: step: 1952/530, loss: 0.11989088356494904
2023-01-23 01:14:21.971892: step: 1956/530, loss: 0.22997474670410156
2023-01-23 01:14:23.129044: step: 1960/530, loss: 0.003576564835384488
2023-01-23 01:14:24.330238: step: 1964/530, loss: 0.0026226998306810856
2023-01-23 01:14:25.561365: step: 1968/530, loss: 0.1358516663312912
2023-01-23 01:14:26.821379: step: 1972/530, loss: 0.0023416520562022924
2023-01-23 01:14:27.986916: step: 1976/530, loss: 0.05554056167602539
2023-01-23 01:14:29.124927: step: 1980/530, loss: 0.0629308745265007
2023-01-23 01:14:30.328935: step: 1984/530, loss: 0.038582898676395416
2023-01-23 01:14:31.480295: step: 1988/530, loss: 0.04458275064826012
2023-01-23 01:14:32.654621: step: 1992/530, loss: 0.07219496369361877
2023-01-23 01:14:33.851060: step: 1996/530, loss: 0.0581677183508873
2023-01-23 01:14:35.040109: step: 2000/530, loss: 0.057827189564704895
2023-01-23 01:14:36.194743: step: 2004/530, loss: 0.05950207635760307
2023-01-23 01:14:37.335326: step: 2008/530, loss: 0.07835781574249268
2023-01-23 01:14:38.502621: step: 2012/530, loss: 0.35049229860305786
2023-01-23 01:14:39.672813: step: 2016/530, loss: 0.24317531287670135
2023-01-23 01:14:40.869182: step: 2020/530, loss: 0.04514484480023384
2023-01-23 01:14:42.082407: step: 2024/530, loss: 0.10570144653320312
2023-01-23 01:14:43.254564: step: 2028/530, loss: 0.08636656403541565
2023-01-23 01:14:44.415254: step: 2032/530, loss: 0.18950310349464417
2023-01-23 01:14:45.594479: step: 2036/530, loss: 0.5444737076759338
2023-01-23 01:14:46.752584: step: 2040/530, loss: 0.06467919051647186
2023-01-23 01:14:47.912552: step: 2044/530, loss: 0.011122465133666992
2023-01-23 01:14:49.064917: step: 2048/530, loss: 0.05856190249323845
2023-01-23 01:14:50.243956: step: 2052/530, loss: 0.030113743618130684
2023-01-23 01:14:51.371237: step: 2056/530, loss: 0.09080362319946289
2023-01-23 01:14:52.545063: step: 2060/530, loss: 0.03609485551714897
2023-01-23 01:14:53.705367: step: 2064/530, loss: 0.07069520652294159
2023-01-23 01:14:54.873527: step: 2068/530, loss: 0.10094308853149414
2023-01-23 01:14:56.027755: step: 2072/530, loss: 0.052832603454589844
2023-01-23 01:14:57.161665: step: 2076/530, loss: 0.07048521190881729
2023-01-23 01:14:58.309212: step: 2080/530, loss: 0.03262443467974663
2023-01-23 01:14:59.503123: step: 2084/530, loss: 0.10793952643871307
2023-01-23 01:15:00.668959: step: 2088/530, loss: 0.027028562501072884
2023-01-23 01:15:01.836555: step: 2092/530, loss: 0.04333266615867615
2023-01-23 01:15:03.005159: step: 2096/530, loss: 0.47791871428489685
2023-01-23 01:15:04.221155: step: 2100/530, loss: 0.023774243891239166
2023-01-23 01:15:05.346476: step: 2104/530, loss: 0.11566973477602005
2023-01-23 01:15:06.484671: step: 2108/530, loss: 0.14222422242164612
2023-01-23 01:15:07.653867: step: 2112/530, loss: 0.2880805432796478
2023-01-23 01:15:08.841594: step: 2116/530, loss: 0.01856517791748047
2023-01-23 01:15:09.993046: step: 2120/530, loss: 0.008118415251374245
==================================================
Loss: 0.108
--------------------
Dev: {'event': {'p': 0.5834186284544524, 'r': 0.758988015978695, 'f1': 0.6597222222222223}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Test: {'event': {'p': 0.623550401427297, 'r': 0.8039102932719954, 'f1': 0.7023360964581763}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Chinese: {'event': {'p': 0.5930232558139535, 'r': 0.9444444444444444, 'f1': 0.7285714285714286}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Korean: {'event': {'p': 0.6060606060606061, 'r': 0.6349206349206349, 'f1': 0.62015503875969}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Russian: {'event': {'p': 0.37777777777777777, 'r': 0.4722222222222222, 'f1': 0.4197530864197531}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6351501668520578, 'r': 0.7603195739014648, 'f1': 0.6921212121212121}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Chinese: {'event': {'p': 0.6373175182481752, 'r': 0.8033352501437608, 'f1': 0.7107606207071993}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Chinese: {'event': {'p': 0.5903614457831325, 'r': 0.9074074074074074, 'f1': 0.7153284671532847}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5875251509054326, 'r': 0.7776298268974701, 'f1': 0.6693409742120344}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Eng Test for Korean: {'event': {'p': 0.6419294990723562, 'r': 0.7958596894767107, 'f1': 0.7106546854942234}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Sample Korean: {'event': {'p': 0.7727272727272727, 'r': 0.5396825396825397, 'f1': 0.6355140186915886}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5951882845188284, 'r': 0.7576564580559254, 'f1': 0.6666666666666666}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6663405088062623, 'r': 0.7832087406555491, 'f1': 0.7200634417129264}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5, 'r': 0.6666666666666666, 'f1': 0.5714285714285715}, '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 01:15:53.357100: step: 4/530, loss: 0.01724863052368164
2023-01-23 01:15:54.519750: step: 8/530, loss: 0.02831430360674858
2023-01-23 01:15:55.704932: step: 12/530, loss: 0.12746620178222656
2023-01-23 01:15:56.896344: step: 16/530, loss: 0.1962868869304657
2023-01-23 01:15:58.067359: step: 20/530, loss: 0.05674343183636665
2023-01-23 01:15:59.303620: step: 24/530, loss: 0.03981733322143555
2023-01-23 01:16:00.476312: step: 28/530, loss: 0.04937954246997833
2023-01-23 01:16:01.671473: step: 32/530, loss: 0.008655572310090065
2023-01-23 01:16:02.844620: step: 36/530, loss: 0.2705986201763153
2023-01-23 01:16:03.967903: step: 40/530, loss: 0.013779735192656517
2023-01-23 01:16:05.108847: step: 44/530, loss: 0.03335609659552574
2023-01-23 01:16:06.234481: step: 48/530, loss: 0.10728330165147781
2023-01-23 01:16:07.388022: step: 52/530, loss: 0.01455383375287056
2023-01-23 01:16:08.568176: step: 56/530, loss: 0.007962417788803577
2023-01-23 01:16:09.754519: step: 60/530, loss: 0.018001843243837357
2023-01-23 01:16:10.970060: step: 64/530, loss: 0.050893403589725494
2023-01-23 01:16:12.140387: step: 68/530, loss: 0.020572280511260033
2023-01-23 01:16:13.307429: step: 72/530, loss: 0.06465578079223633
2023-01-23 01:16:14.498412: step: 76/530, loss: 0.592059314250946
2023-01-23 01:16:15.662246: step: 80/530, loss: 0.002903556916862726
2023-01-23 01:16:16.849117: step: 84/530, loss: 0.07494659721851349
2023-01-23 01:16:18.016711: step: 88/530, loss: 0.008433056063950062
2023-01-23 01:16:19.197956: step: 92/530, loss: 0.05218029022216797
2023-01-23 01:16:20.364989: step: 96/530, loss: 0.0011052608024328947
2023-01-23 01:16:21.556245: step: 100/530, loss: 0.0492280051112175
2023-01-23 01:16:22.749486: step: 104/530, loss: 0.08444013446569443
2023-01-23 01:16:23.937339: step: 108/530, loss: 0.015472030267119408
2023-01-23 01:16:25.083532: step: 112/530, loss: 0.006947898771613836
2023-01-23 01:16:26.266811: step: 116/530, loss: 0.07498826831579208
2023-01-23 01:16:27.443433: step: 120/530, loss: 0.03549976274371147
2023-01-23 01:16:28.608744: step: 124/530, loss: 0.0013807297218590975
2023-01-23 01:16:29.755643: step: 128/530, loss: 0.05237922817468643
2023-01-23 01:16:30.922656: step: 132/530, loss: 0.20397034287452698
2023-01-23 01:16:32.061079: step: 136/530, loss: 0.042256928980350494
2023-01-23 01:16:33.230210: step: 140/530, loss: 0.05582446977496147
2023-01-23 01:16:34.442891: step: 144/530, loss: 0.4282020032405853
2023-01-23 01:16:35.588806: step: 148/530, loss: 0.010433197021484375
2023-01-23 01:16:36.770671: step: 152/530, loss: 0.20721034705638885
2023-01-23 01:16:37.934668: step: 156/530, loss: 0.08617058396339417
2023-01-23 01:16:39.084707: step: 160/530, loss: 0.004367637448012829
2023-01-23 01:16:40.267785: step: 164/530, loss: 0.1405675858259201
2023-01-23 01:16:41.404923: step: 168/530, loss: 0.0006777763483114541
2023-01-23 01:16:42.601883: step: 172/530, loss: 0.042293451726436615
2023-01-23 01:16:43.758223: step: 176/530, loss: 0.07939940690994263
2023-01-23 01:16:44.942036: step: 180/530, loss: 0.017889689654111862
2023-01-23 01:16:46.132647: step: 184/530, loss: 0.01557769812643528
2023-01-23 01:16:47.266572: step: 188/530, loss: 0.025629043579101562
2023-01-23 01:16:48.414270: step: 192/530, loss: 0.017916537821292877
2023-01-23 01:16:49.567057: step: 196/530, loss: 0.06513328850269318
2023-01-23 01:16:50.757942: step: 200/530, loss: 0.09142618626356125
2023-01-23 01:16:51.933671: step: 204/530, loss: 0.02312469482421875
2023-01-23 01:16:53.086608: step: 208/530, loss: 0.002872276119887829
2023-01-23 01:16:54.277389: step: 212/530, loss: 0.10064974427223206
2023-01-23 01:16:55.430531: step: 216/530, loss: 0.07517509162425995
2023-01-23 01:16:56.628809: step: 220/530, loss: 0.016412019729614258
2023-01-23 01:16:57.786489: step: 224/530, loss: 0.01306695956736803
2023-01-23 01:16:58.967264: step: 228/530, loss: 0.03495984151959419
2023-01-23 01:17:00.105798: step: 232/530, loss: 0.007014179136604071
2023-01-23 01:17:01.255217: step: 236/530, loss: 0.04804863780736923
2023-01-23 01:17:02.448171: step: 240/530, loss: 0.17407149076461792
2023-01-23 01:17:03.590621: step: 244/530, loss: 0.033547498285770416
2023-01-23 01:17:04.707813: step: 248/530, loss: 0.1131671890616417
2023-01-23 01:17:05.897799: step: 252/530, loss: 0.040595244616270065
2023-01-23 01:17:07.098861: step: 256/530, loss: 0.06128682941198349
2023-01-23 01:17:08.286255: step: 260/530, loss: 0.3505368232727051
2023-01-23 01:17:09.487107: step: 264/530, loss: 0.01635713502764702
2023-01-23 01:17:10.655827: step: 268/530, loss: 0.1656968593597412
2023-01-23 01:17:11.808374: step: 272/530, loss: 0.005596351809799671
2023-01-23 01:17:12.991893: step: 276/530, loss: 0.021594811230897903
2023-01-23 01:17:14.121009: step: 280/530, loss: 0.02822094038128853
2023-01-23 01:17:15.252105: step: 284/530, loss: 0.06556282192468643
2023-01-23 01:17:16.413202: step: 288/530, loss: 0.1060771495103836
2023-01-23 01:17:17.576266: step: 292/530, loss: 0.09458567947149277
2023-01-23 01:17:18.787820: step: 296/530, loss: 0.09363172948360443
2023-01-23 01:17:20.009323: step: 300/530, loss: 0.05049190670251846
2023-01-23 01:17:21.164221: step: 304/530, loss: 0.02804236300289631
2023-01-23 01:17:22.313036: step: 308/530, loss: 0.15031220018863678
2023-01-23 01:17:23.475720: step: 312/530, loss: 0.039809297770261765
2023-01-23 01:17:24.656031: step: 316/530, loss: 0.04465942457318306
2023-01-23 01:17:25.837717: step: 320/530, loss: 0.007391166873276234
2023-01-23 01:17:27.035917: step: 324/530, loss: 0.07422886043787003
2023-01-23 01:17:28.177889: step: 328/530, loss: 0.07546120136976242
2023-01-23 01:17:29.336965: step: 332/530, loss: 0.07228565216064453
2023-01-23 01:17:30.478099: step: 336/530, loss: 0.026609230786561966
2023-01-23 01:17:31.655399: step: 340/530, loss: 0.04048290103673935
2023-01-23 01:17:32.839013: step: 344/530, loss: 0.19356565177440643
2023-01-23 01:17:34.031976: step: 348/530, loss: 0.057354070246219635
2023-01-23 01:17:35.188644: step: 352/530, loss: 0.05328512564301491
2023-01-23 01:17:36.375950: step: 356/530, loss: 0.08446156978607178
2023-01-23 01:17:37.577619: step: 360/530, loss: 0.11063873767852783
2023-01-23 01:17:38.740601: step: 364/530, loss: 0.053235720843076706
2023-01-23 01:17:39.893776: step: 368/530, loss: 0.03223447874188423
2023-01-23 01:17:41.105222: step: 372/530, loss: 0.29909753799438477
2023-01-23 01:17:42.320870: step: 376/530, loss: 0.04627084359526634
2023-01-23 01:17:43.485453: step: 380/530, loss: 0.10767688602209091
2023-01-23 01:17:44.655825: step: 384/530, loss: 0.00654982915148139
2023-01-23 01:17:45.810057: step: 388/530, loss: 0.028128528967499733
2023-01-23 01:17:47.000577: step: 392/530, loss: 0.06355457007884979
2023-01-23 01:17:48.246772: step: 396/530, loss: 0.13125677406787872
2023-01-23 01:17:49.425221: step: 400/530, loss: 0.0123145105317235
2023-01-23 01:17:50.627634: step: 404/530, loss: 0.11665716022253036
2023-01-23 01:17:51.792117: step: 408/530, loss: 0.05518064275383949
2023-01-23 01:17:52.914885: step: 412/530, loss: 0.09190237522125244
2023-01-23 01:17:54.109115: step: 416/530, loss: 0.09520454704761505
2023-01-23 01:17:55.259802: step: 420/530, loss: 0.04104652628302574
2023-01-23 01:17:56.497996: step: 424/530, loss: 0.10428936779499054
2023-01-23 01:17:57.696427: step: 428/530, loss: 0.014971543103456497
2023-01-23 01:17:58.856515: step: 432/530, loss: 0.0654086172580719
2023-01-23 01:18:00.007927: step: 436/530, loss: 0.05611314997076988
2023-01-23 01:18:01.166427: step: 440/530, loss: 0.03765372931957245
2023-01-23 01:18:02.326690: step: 444/530, loss: 0.013609791174530983
2023-01-23 01:18:03.483978: step: 448/530, loss: 0.012603759765625
2023-01-23 01:18:04.661074: step: 452/530, loss: 0.010480445809662342
2023-01-23 01:18:05.866202: step: 456/530, loss: 0.02486448362469673
2023-01-23 01:18:07.009232: step: 460/530, loss: 0.04601473733782768
2023-01-23 01:18:08.158042: step: 464/530, loss: 0.005935740657150745
2023-01-23 01:18:09.350970: step: 468/530, loss: 0.06262693554162979
2023-01-23 01:18:10.540147: step: 472/530, loss: 0.06066951900720596
2023-01-23 01:18:11.732048: step: 476/530, loss: 0.108167365193367
2023-01-23 01:18:12.880580: step: 480/530, loss: 0.013270283117890358
2023-01-23 01:18:14.060073: step: 484/530, loss: 0.08028535544872284
2023-01-23 01:18:15.253190: step: 488/530, loss: 0.010606765747070312
2023-01-23 01:18:16.405401: step: 492/530, loss: 0.029518771916627884
2023-01-23 01:18:17.581677: step: 496/530, loss: 0.020072175189852715
2023-01-23 01:18:18.746497: step: 500/530, loss: 0.028275348246097565
2023-01-23 01:18:19.902851: step: 504/530, loss: 0.011164498515427113
2023-01-23 01:18:21.118385: step: 508/530, loss: 0.18622688949108124
2023-01-23 01:18:22.300989: step: 512/530, loss: 0.07147254794836044
2023-01-23 01:18:23.463053: step: 516/530, loss: 0.040113065391778946
2023-01-23 01:18:24.634315: step: 520/530, loss: 0.07017207145690918
2023-01-23 01:18:25.787044: step: 524/530, loss: 0.12066469341516495
2023-01-23 01:18:27.003059: step: 528/530, loss: 0.1344621479511261
2023-01-23 01:18:28.224344: step: 532/530, loss: 0.13251782953739166
2023-01-23 01:18:29.411532: step: 536/530, loss: 0.033727504312992096
2023-01-23 01:18:30.575777: step: 540/530, loss: 0.011449622921645641
2023-01-23 01:18:31.767476: step: 544/530, loss: 0.056689146906137466
2023-01-23 01:18:32.898303: step: 548/530, loss: 0.03570260852575302
2023-01-23 01:18:34.045152: step: 552/530, loss: 0.12402161955833435
2023-01-23 01:18:35.259126: step: 556/530, loss: 0.04676799848675728
2023-01-23 01:18:36.422247: step: 560/530, loss: 0.04755821079015732
2023-01-23 01:18:37.603917: step: 564/530, loss: 0.05337581783533096
2023-01-23 01:18:38.762379: step: 568/530, loss: 0.14718575775623322
2023-01-23 01:18:39.946418: step: 572/530, loss: 0.12984544038772583
2023-01-23 01:18:41.144403: step: 576/530, loss: 0.033028747886419296
2023-01-23 01:18:42.319783: step: 580/530, loss: 0.06339607387781143
2023-01-23 01:18:43.494530: step: 584/530, loss: 0.0584142692387104
2023-01-23 01:18:44.718415: step: 588/530, loss: 0.03812151029706001
2023-01-23 01:18:45.907087: step: 592/530, loss: 0.19748754799365997
2023-01-23 01:18:47.079531: step: 596/530, loss: 0.025906803086400032
2023-01-23 01:18:48.265025: step: 600/530, loss: 0.023184681311249733
2023-01-23 01:18:49.447075: step: 604/530, loss: 0.06471939384937286
2023-01-23 01:18:50.591013: step: 608/530, loss: 0.22061358392238617
2023-01-23 01:18:51.743260: step: 612/530, loss: 0.04676113277673721
2023-01-23 01:18:52.929027: step: 616/530, loss: 0.008520555682480335
2023-01-23 01:18:54.121286: step: 620/530, loss: 0.12434607744216919
2023-01-23 01:18:55.271114: step: 624/530, loss: 0.012760735116899014
2023-01-23 01:18:56.501707: step: 628/530, loss: 0.013706875964999199
2023-01-23 01:18:57.677793: step: 632/530, loss: 0.008645439520478249
2023-01-23 01:18:58.851952: step: 636/530, loss: 0.06543731689453125
2023-01-23 01:19:00.044620: step: 640/530, loss: 0.03377361595630646
2023-01-23 01:19:01.272461: step: 644/530, loss: 0.04126129299402237
2023-01-23 01:19:02.442330: step: 648/530, loss: 0.13894999027252197
2023-01-23 01:19:03.613162: step: 652/530, loss: 0.04044799879193306
2023-01-23 01:19:04.805864: step: 656/530, loss: 0.0208453182131052
2023-01-23 01:19:05.999805: step: 660/530, loss: 0.1356370896100998
2023-01-23 01:19:07.151731: step: 664/530, loss: 0.05513763427734375
2023-01-23 01:19:08.349672: step: 668/530, loss: 0.1295255720615387
2023-01-23 01:19:09.508558: step: 672/530, loss: 0.06747493892908096
2023-01-23 01:19:10.677531: step: 676/530, loss: 0.020699406042695045
2023-01-23 01:19:11.864562: step: 680/530, loss: 0.05589151382446289
2023-01-23 01:19:13.040249: step: 684/530, loss: 0.027169611304998398
2023-01-23 01:19:14.251172: step: 688/530, loss: 0.07688884437084198
2023-01-23 01:19:15.423866: step: 692/530, loss: 0.05237884446978569
2023-01-23 01:19:16.573025: step: 696/530, loss: 0.04485531151294708
2023-01-23 01:19:17.739529: step: 700/530, loss: 0.052571870386600494
2023-01-23 01:19:18.913369: step: 704/530, loss: 0.035965196788311005
2023-01-23 01:19:20.053264: step: 708/530, loss: 0.024704838171601295
2023-01-23 01:19:21.190619: step: 712/530, loss: 0.11405421048402786
2023-01-23 01:19:22.386598: step: 716/530, loss: 0.023207854479551315
2023-01-23 01:19:23.566522: step: 720/530, loss: 0.0046422481536865234
2023-01-23 01:19:24.791698: step: 724/530, loss: 0.09927954524755478
2023-01-23 01:19:25.951185: step: 728/530, loss: 0.16773834824562073
2023-01-23 01:19:27.099110: step: 732/530, loss: 0.08033790439367294
2023-01-23 01:19:28.283682: step: 736/530, loss: 0.11824969947338104
2023-01-23 01:19:29.438851: step: 740/530, loss: 0.0571625679731369
2023-01-23 01:19:30.602339: step: 744/530, loss: 0.1755337119102478
2023-01-23 01:19:31.808552: step: 748/530, loss: 0.22712059319019318
2023-01-23 01:19:33.015926: step: 752/530, loss: 0.07328605651855469
2023-01-23 01:19:34.181009: step: 756/530, loss: 0.0854150801897049
2023-01-23 01:19:35.345340: step: 760/530, loss: 0.04586320370435715
2023-01-23 01:19:36.598289: step: 764/530, loss: 0.08389168232679367
2023-01-23 01:19:37.844366: step: 768/530, loss: 0.06492657959461212
2023-01-23 01:19:39.047997: step: 772/530, loss: 0.11090469360351562
2023-01-23 01:19:40.245534: step: 776/530, loss: 0.0945672020316124
2023-01-23 01:19:41.438610: step: 780/530, loss: 0.033510398119688034
2023-01-23 01:19:42.598198: step: 784/530, loss: 0.032225608825683594
2023-01-23 01:19:43.768296: step: 788/530, loss: 0.08912887424230576
2023-01-23 01:19:44.947364: step: 792/530, loss: 0.012789726257324219
2023-01-23 01:19:46.154514: step: 796/530, loss: 0.056162264198064804
2023-01-23 01:19:47.309876: step: 800/530, loss: 0.06724796444177628
2023-01-23 01:19:48.474264: step: 804/530, loss: 0.07631473243236542
2023-01-23 01:19:49.621688: step: 808/530, loss: 0.06719360500574112
2023-01-23 01:19:50.772368: step: 812/530, loss: 0.006159019656479359
2023-01-23 01:19:51.940383: step: 816/530, loss: 0.5959426164627075
2023-01-23 01:19:53.123849: step: 820/530, loss: 0.0058693294413387775
2023-01-23 01:19:54.301306: step: 824/530, loss: 0.5219763517379761
2023-01-23 01:19:55.495941: step: 828/530, loss: 0.1250920295715332
2023-01-23 01:19:56.650506: step: 832/530, loss: 0.2410951554775238
2023-01-23 01:19:57.838390: step: 836/530, loss: 0.12463503330945969
2023-01-23 01:19:58.999874: step: 840/530, loss: 0.0956411361694336
2023-01-23 01:20:00.201452: step: 844/530, loss: 0.04549875482916832
2023-01-23 01:20:01.416009: step: 848/530, loss: 0.004123210906982422
2023-01-23 01:20:02.587488: step: 852/530, loss: 0.03239774703979492
2023-01-23 01:20:03.745840: step: 856/530, loss: 0.010679817758500576
2023-01-23 01:20:04.885803: step: 860/530, loss: 0.07902240753173828
2023-01-23 01:20:06.062957: step: 864/530, loss: 0.039153192192316055
2023-01-23 01:20:07.218345: step: 868/530, loss: 0.047776032239198685
2023-01-23 01:20:08.362655: step: 872/530, loss: 0.202616885304451
2023-01-23 01:20:09.488977: step: 876/530, loss: 0.04760284349322319
2023-01-23 01:20:10.657319: step: 880/530, loss: 0.05202331766486168
2023-01-23 01:20:11.879590: step: 884/530, loss: 0.06067085266113281
2023-01-23 01:20:13.033790: step: 888/530, loss: 0.03496084362268448
2023-01-23 01:20:14.234975: step: 892/530, loss: 0.2139906883239746
2023-01-23 01:20:15.390231: step: 896/530, loss: 0.04800615459680557
2023-01-23 01:20:16.598636: step: 900/530, loss: 0.10639762878417969
2023-01-23 01:20:17.758685: step: 904/530, loss: 1.106414794921875
2023-01-23 01:20:18.973009: step: 908/530, loss: 0.020794104784727097
2023-01-23 01:20:20.144195: step: 912/530, loss: 0.00787506066262722
2023-01-23 01:20:21.307948: step: 916/530, loss: 0.032620809972286224
2023-01-23 01:20:22.490742: step: 920/530, loss: 0.11377029120922089
2023-01-23 01:20:23.655542: step: 924/530, loss: 0.054822731763124466
2023-01-23 01:20:24.841715: step: 928/530, loss: 0.08924436569213867
2023-01-23 01:20:26.030645: step: 932/530, loss: 0.04892902448773384
2023-01-23 01:20:27.175234: step: 936/530, loss: 0.01841592788696289
2023-01-23 01:20:28.323639: step: 940/530, loss: 0.03619947284460068
2023-01-23 01:20:29.523948: step: 944/530, loss: 0.035985372960567474
2023-01-23 01:20:30.682446: step: 948/530, loss: 0.09846987575292587
2023-01-23 01:20:31.874546: step: 952/530, loss: 0.07159604877233505
2023-01-23 01:20:33.019994: step: 956/530, loss: 0.05185890197753906
2023-01-23 01:20:34.183255: step: 960/530, loss: 0.026017475873231888
2023-01-23 01:20:35.367176: step: 964/530, loss: 0.05558224022388458
2023-01-23 01:20:36.526275: step: 968/530, loss: 0.02276439592242241
2023-01-23 01:20:37.725843: step: 972/530, loss: 0.0960446447134018
2023-01-23 01:20:38.899532: step: 976/530, loss: 0.2156790792942047
2023-01-23 01:20:40.118294: step: 980/530, loss: 0.0681055560708046
2023-01-23 01:20:41.276437: step: 984/530, loss: 0.003368377685546875
2023-01-23 01:20:42.427056: step: 988/530, loss: 0.1347332000732422
2023-01-23 01:20:43.593642: step: 992/530, loss: 0.05170693248510361
2023-01-23 01:20:44.755751: step: 996/530, loss: 0.07851582020521164
2023-01-23 01:20:45.950675: step: 1000/530, loss: 0.04718971252441406
2023-01-23 01:20:47.117555: step: 1004/530, loss: 0.003913402557373047
2023-01-23 01:20:48.294100: step: 1008/530, loss: 0.04754600673913956
2023-01-23 01:20:49.484121: step: 1012/530, loss: 0.20470334589481354
2023-01-23 01:20:50.666165: step: 1016/530, loss: 0.07396507263183594
2023-01-23 01:20:51.857931: step: 1020/530, loss: 0.06888275593519211
2023-01-23 01:20:53.085605: step: 1024/530, loss: 0.09839210659265518
2023-01-23 01:20:54.331229: step: 1028/530, loss: 0.09046640247106552
2023-01-23 01:20:55.498535: step: 1032/530, loss: 0.15365830063819885
2023-01-23 01:20:56.641723: step: 1036/530, loss: 0.08798447251319885
2023-01-23 01:20:57.810589: step: 1040/530, loss: 0.13328266143798828
2023-01-23 01:20:59.002263: step: 1044/530, loss: 0.030314160510897636
2023-01-23 01:21:00.163189: step: 1048/530, loss: 0.19902487099170685
2023-01-23 01:21:01.321476: step: 1052/530, loss: 0.30601128935813904
2023-01-23 01:21:02.474600: step: 1056/530, loss: 0.05362368002533913
2023-01-23 01:21:03.611911: step: 1060/530, loss: 0.024675512686371803
2023-01-23 01:21:04.783742: step: 1064/530, loss: 0.047141171991825104
2023-01-23 01:21:05.961909: step: 1068/530, loss: 0.1619092971086502
2023-01-23 01:21:07.135032: step: 1072/530, loss: 0.0459468849003315
2023-01-23 01:21:08.305511: step: 1076/530, loss: 0.014123057946562767
2023-01-23 01:21:09.482242: step: 1080/530, loss: 0.09126348793506622
2023-01-23 01:21:10.664290: step: 1084/530, loss: 0.06287689507007599
2023-01-23 01:21:11.820684: step: 1088/530, loss: 0.03245840221643448
2023-01-23 01:21:13.012306: step: 1092/530, loss: 0.06365213543176651
2023-01-23 01:21:14.135096: step: 1096/530, loss: 0.0748106986284256
2023-01-23 01:21:15.306450: step: 1100/530, loss: 0.0904294103384018
2023-01-23 01:21:16.472808: step: 1104/530, loss: 0.04335784912109375
2023-01-23 01:21:17.667344: step: 1108/530, loss: 0.04181699827313423
2023-01-23 01:21:18.860910: step: 1112/530, loss: 0.01370248757302761
2023-01-23 01:21:20.041490: step: 1116/530, loss: 0.09755287319421768
2023-01-23 01:21:21.199453: step: 1120/530, loss: 0.08494433760643005
2023-01-23 01:21:22.355486: step: 1124/530, loss: 0.07433262467384338
2023-01-23 01:21:23.531462: step: 1128/530, loss: 0.05076246336102486
2023-01-23 01:21:24.710098: step: 1132/530, loss: 0.36004361510276794
2023-01-23 01:21:25.923044: step: 1136/530, loss: 0.08949871361255646
2023-01-23 01:21:27.117969: step: 1140/530, loss: 0.05878668278455734
2023-01-23 01:21:28.303746: step: 1144/530, loss: 0.19234934449195862
2023-01-23 01:21:29.461348: step: 1148/530, loss: 0.09683246910572052
2023-01-23 01:21:30.654634: step: 1152/530, loss: 0.045394137501716614
2023-01-23 01:21:31.820231: step: 1156/530, loss: 2.4003026485443115
2023-01-23 01:21:33.012585: step: 1160/530, loss: 0.12414245307445526
2023-01-23 01:21:34.167314: step: 1164/530, loss: 0.16744832694530487
2023-01-23 01:21:35.346064: step: 1168/530, loss: 0.02402791939675808
2023-01-23 01:21:36.549249: step: 1172/530, loss: 0.05656109005212784
2023-01-23 01:21:37.730444: step: 1176/530, loss: 0.815133810043335
2023-01-23 01:21:38.985810: step: 1180/530, loss: 0.047041893005371094
2023-01-23 01:21:40.169119: step: 1184/530, loss: 0.18938890099525452
2023-01-23 01:21:41.313389: step: 1188/530, loss: 0.034436848014593124
2023-01-23 01:21:42.481885: step: 1192/530, loss: 0.029060842469334602
2023-01-23 01:21:43.669412: step: 1196/530, loss: 0.1083468422293663
2023-01-23 01:21:44.830048: step: 1200/530, loss: 0.057347677648067474
2023-01-23 01:21:46.027300: step: 1204/530, loss: 0.10239878296852112
2023-01-23 01:21:47.189399: step: 1208/530, loss: 0.051899053156375885
2023-01-23 01:21:48.363494: step: 1212/530, loss: 0.021032335236668587
2023-01-23 01:21:49.526261: step: 1216/530, loss: 0.08539314568042755
2023-01-23 01:21:50.687888: step: 1220/530, loss: 0.05260924994945526
2023-01-23 01:21:51.838561: step: 1224/530, loss: 0.010612296871840954
2023-01-23 01:21:52.998617: step: 1228/530, loss: 0.09653019905090332
2023-01-23 01:21:54.140642: step: 1232/530, loss: 0.08067398518323898
2023-01-23 01:21:55.294604: step: 1236/530, loss: 0.03993654251098633
2023-01-23 01:21:56.425800: step: 1240/530, loss: 0.014272928237915039
2023-01-23 01:21:57.604559: step: 1244/530, loss: 0.08701524883508682
2023-01-23 01:21:58.886272: step: 1248/530, loss: 0.09620419144630432
2023-01-23 01:22:00.091428: step: 1252/530, loss: 0.020607758313417435
2023-01-23 01:22:01.269766: step: 1256/530, loss: 0.06554222106933594
2023-01-23 01:22:02.439046: step: 1260/530, loss: 0.03748941421508789
2023-01-23 01:22:03.598338: step: 1264/530, loss: 0.07038598507642746
2023-01-23 01:22:04.760342: step: 1268/530, loss: 0.1546599417924881
2023-01-23 01:22:05.927192: step: 1272/530, loss: 0.05877971649169922
2023-01-23 01:22:07.102526: step: 1276/530, loss: 0.05580444261431694
2023-01-23 01:22:08.327477: step: 1280/530, loss: 0.0535161979496479
2023-01-23 01:22:09.558076: step: 1284/530, loss: 0.3063715398311615
2023-01-23 01:22:10.707987: step: 1288/530, loss: 0.06162700802087784
2023-01-23 01:22:11.877049: step: 1292/530, loss: 0.021173954010009766
2023-01-23 01:22:13.051778: step: 1296/530, loss: 0.025942610576748848
2023-01-23 01:22:14.209458: step: 1300/530, loss: 0.03369879722595215
2023-01-23 01:22:15.388728: step: 1304/530, loss: 0.041750337928533554
2023-01-23 01:22:16.543565: step: 1308/530, loss: 0.06596679985523224
2023-01-23 01:22:17.684796: step: 1312/530, loss: 0.03637304529547691
2023-01-23 01:22:18.853701: step: 1316/530, loss: 0.056120872497558594
2023-01-23 01:22:20.025158: step: 1320/530, loss: 0.16436100006103516
2023-01-23 01:22:21.233029: step: 1324/530, loss: 0.0427798293530941
2023-01-23 01:22:22.387046: step: 1328/530, loss: 0.07775650173425674
2023-01-23 01:22:23.551156: step: 1332/530, loss: 0.07776966691017151
2023-01-23 01:22:24.714617: step: 1336/530, loss: 0.03252077102661133
2023-01-23 01:22:25.893011: step: 1340/530, loss: 0.0487859733402729
2023-01-23 01:22:27.078657: step: 1344/530, loss: 0.14479666948318481
2023-01-23 01:22:28.298343: step: 1348/530, loss: 0.06095452606678009
2023-01-23 01:22:29.457657: step: 1352/530, loss: 0.05956869199872017
2023-01-23 01:22:30.621062: step: 1356/530, loss: 0.004472017288208008
2023-01-23 01:22:31.804835: step: 1360/530, loss: 0.5448311567306519
2023-01-23 01:22:32.988420: step: 1364/530, loss: 0.195135697722435
2023-01-23 01:22:34.133540: step: 1368/530, loss: 0.13340425491333008
2023-01-23 01:22:35.318634: step: 1372/530, loss: 0.025561904534697533
2023-01-23 01:22:36.462509: step: 1376/530, loss: 0.06085491180419922
2023-01-23 01:22:37.630686: step: 1380/530, loss: 0.060906507074832916
2023-01-23 01:22:38.771897: step: 1384/530, loss: 0.044223833829164505
2023-01-23 01:22:39.951549: step: 1388/530, loss: 0.010550260543823242
2023-01-23 01:22:41.148717: step: 1392/530, loss: 0.008985948748886585
2023-01-23 01:22:42.321192: step: 1396/530, loss: 0.022893667221069336
2023-01-23 01:22:43.512215: step: 1400/530, loss: 0.015783309936523438
2023-01-23 01:22:44.690795: step: 1404/530, loss: 0.059556104242801666
2023-01-23 01:22:45.836607: step: 1408/530, loss: 0.11742211878299713
2023-01-23 01:22:47.036934: step: 1412/530, loss: 0.05485473573207855
2023-01-23 01:22:48.213949: step: 1416/530, loss: 0.1685360074043274
2023-01-23 01:22:49.371043: step: 1420/530, loss: 0.008082007989287376
2023-01-23 01:22:50.529313: step: 1424/530, loss: 0.006194782443344593
2023-01-23 01:22:51.681019: step: 1428/530, loss: 0.0527895912528038
2023-01-23 01:22:52.884515: step: 1432/530, loss: 0.037615206092596054
2023-01-23 01:22:54.058178: step: 1436/530, loss: 0.03121013753116131
2023-01-23 01:22:55.233762: step: 1440/530, loss: 0.21136683225631714
2023-01-23 01:22:56.382962: step: 1444/530, loss: 0.010770178399980068
2023-01-23 01:22:57.555369: step: 1448/530, loss: 0.027344131842255592
2023-01-23 01:22:58.726330: step: 1452/530, loss: 0.08721437305212021
2023-01-23 01:22:59.916876: step: 1456/530, loss: 0.11024856567382812
2023-01-23 01:23:01.085224: step: 1460/530, loss: 0.15505246818065643
2023-01-23 01:23:02.248178: step: 1464/530, loss: 0.16056203842163086
2023-01-23 01:23:03.427876: step: 1468/530, loss: 0.06019601970911026
2023-01-23 01:23:04.620135: step: 1472/530, loss: 0.1794138252735138
2023-01-23 01:23:05.758892: step: 1476/530, loss: 0.04733027145266533
2023-01-23 01:23:06.926333: step: 1480/530, loss: 0.7828097343444824
2023-01-23 01:23:08.093136: step: 1484/530, loss: 0.011182403191924095
2023-01-23 01:23:09.287312: step: 1488/530, loss: 0.14519082009792328
2023-01-23 01:23:10.450242: step: 1492/530, loss: 0.01148910541087389
2023-01-23 01:23:11.623236: step: 1496/530, loss: 0.052773572504520416
2023-01-23 01:23:12.791869: step: 1500/530, loss: 0.14207783341407776
2023-01-23 01:23:13.993043: step: 1504/530, loss: 0.0016389846568927169
2023-01-23 01:23:15.145546: step: 1508/530, loss: 0.015827566385269165
2023-01-23 01:23:16.334735: step: 1512/530, loss: 0.025444984436035156
2023-01-23 01:23:17.508533: step: 1516/530, loss: 0.05846209451556206
2023-01-23 01:23:18.667599: step: 1520/530, loss: 0.006419730372726917
2023-01-23 01:23:19.819318: step: 1524/530, loss: 0.17258760333061218
2023-01-23 01:23:21.002361: step: 1528/530, loss: 0.004049396608024836
2023-01-23 01:23:22.168744: step: 1532/530, loss: 0.12036866694688797
2023-01-23 01:23:23.354929: step: 1536/530, loss: 0.1664033830165863
2023-01-23 01:23:24.518575: step: 1540/530, loss: 0.13083019852638245
2023-01-23 01:23:25.681416: step: 1544/530, loss: 0.054489850997924805
2023-01-23 01:23:26.867366: step: 1548/530, loss: 0.03622307628393173
2023-01-23 01:23:28.025990: step: 1552/530, loss: 0.05670313909649849
2023-01-23 01:23:29.177116: step: 1556/530, loss: 0.13988085091114044
2023-01-23 01:23:30.338251: step: 1560/530, loss: 0.12661799788475037
2023-01-23 01:23:31.515606: step: 1564/530, loss: 0.02112302929162979
2023-01-23 01:23:32.688493: step: 1568/530, loss: 0.31534630060195923
2023-01-23 01:23:33.854829: step: 1572/530, loss: 0.05383773148059845
2023-01-23 01:23:35.017119: step: 1576/530, loss: 0.001490688300691545
2023-01-23 01:23:36.207375: step: 1580/530, loss: 0.09223737567663193
2023-01-23 01:23:37.396414: step: 1584/530, loss: 0.21165180206298828
2023-01-23 01:23:38.601848: step: 1588/530, loss: 0.05581006780266762
2023-01-23 01:23:39.777852: step: 1592/530, loss: 0.17843064665794373
2023-01-23 01:23:40.946860: step: 1596/530, loss: 0.02746429480612278
2023-01-23 01:23:42.092794: step: 1600/530, loss: 0.04981479421257973
2023-01-23 01:23:43.249324: step: 1604/530, loss: 0.054897598922252655
2023-01-23 01:23:44.407532: step: 1608/530, loss: 0.05929527431726456
2023-01-23 01:23:45.588231: step: 1612/530, loss: 0.05613088980317116
2023-01-23 01:23:46.724475: step: 1616/530, loss: 0.21645468473434448
2023-01-23 01:23:47.882312: step: 1620/530, loss: 0.05460290610790253
2023-01-23 01:23:49.054190: step: 1624/530, loss: 0.3275272250175476
2023-01-23 01:23:50.285517: step: 1628/530, loss: 0.09269952774047852
2023-01-23 01:23:51.457030: step: 1632/530, loss: 0.06183989346027374
2023-01-23 01:23:52.609664: step: 1636/530, loss: 0.12125054001808167
2023-01-23 01:23:53.823041: step: 1640/530, loss: 0.07745656371116638
2023-01-23 01:23:55.003823: step: 1644/530, loss: 0.03580541908740997
2023-01-23 01:23:56.172074: step: 1648/530, loss: 0.04462175443768501
2023-01-23 01:23:57.382873: step: 1652/530, loss: 0.07698230445384979
2023-01-23 01:23:58.580397: step: 1656/530, loss: 0.005969190504401922
2023-01-23 01:23:59.766997: step: 1660/530, loss: 0.016604041680693626
2023-01-23 01:24:00.930710: step: 1664/530, loss: 0.1795859932899475
2023-01-23 01:24:02.089130: step: 1668/530, loss: 0.0058987378142774105
2023-01-23 01:24:03.269121: step: 1672/530, loss: 0.16710853576660156
2023-01-23 01:24:04.405800: step: 1676/530, loss: 0.07736340165138245
2023-01-23 01:24:05.575903: step: 1680/530, loss: 0.0938756912946701
2023-01-23 01:24:06.746327: step: 1684/530, loss: 0.01332635898143053
2023-01-23 01:24:07.905526: step: 1688/530, loss: 0.050838373601436615
2023-01-23 01:24:09.099518: step: 1692/530, loss: 0.02434730716049671
2023-01-23 01:24:10.233122: step: 1696/530, loss: 0.04740095138549805
2023-01-23 01:24:11.399235: step: 1700/530, loss: 0.13694047927856445
2023-01-23 01:24:12.574990: step: 1704/530, loss: 0.06920366734266281
2023-01-23 01:24:13.738163: step: 1708/530, loss: 0.03885803371667862
2023-01-23 01:24:14.935442: step: 1712/530, loss: 0.03403434902429581
2023-01-23 01:24:16.131957: step: 1716/530, loss: 0.18362684547901154
2023-01-23 01:24:17.298572: step: 1720/530, loss: 0.052041344344615936
2023-01-23 01:24:18.466299: step: 1724/530, loss: 0.05599212646484375
2023-01-23 01:24:19.594997: step: 1728/530, loss: 0.05550708621740341
2023-01-23 01:24:20.789531: step: 1732/530, loss: 0.14795361459255219
2023-01-23 01:24:21.972204: step: 1736/530, loss: 0.06222677230834961
2023-01-23 01:24:23.133193: step: 1740/530, loss: 0.0858069434762001
2023-01-23 01:24:24.315144: step: 1744/530, loss: 0.03363366425037384
2023-01-23 01:24:25.482209: step: 1748/530, loss: 0.04844493791460991
2023-01-23 01:24:26.646171: step: 1752/530, loss: 0.009208870120346546
2023-01-23 01:24:27.819466: step: 1756/530, loss: 0.049422647804021835
2023-01-23 01:24:28.969251: step: 1760/530, loss: 0.02544851414859295
2023-01-23 01:24:30.135486: step: 1764/530, loss: 0.07263131439685822
2023-01-23 01:24:31.306510: step: 1768/530, loss: 0.021674538031220436
2023-01-23 01:24:32.505747: step: 1772/530, loss: 0.07274136692285538
2023-01-23 01:24:33.642806: step: 1776/530, loss: 0.0262617114931345
2023-01-23 01:24:34.825721: step: 1780/530, loss: 0.02425565756857395
2023-01-23 01:24:35.975249: step: 1784/530, loss: 0.10199139267206192
2023-01-23 01:24:37.157759: step: 1788/530, loss: 0.07866096496582031
2023-01-23 01:24:38.319446: step: 1792/530, loss: 0.03235302120447159
2023-01-23 01:24:39.501810: step: 1796/530, loss: 0.043831516057252884
2023-01-23 01:24:40.703464: step: 1800/530, loss: 0.14048424363136292
2023-01-23 01:24:41.873496: step: 1804/530, loss: 0.014882564544677734
2023-01-23 01:24:43.098034: step: 1808/530, loss: 0.11039991676807404
2023-01-23 01:24:44.296329: step: 1812/530, loss: 0.03767862170934677
2023-01-23 01:24:45.444503: step: 1816/530, loss: 0.039565566927194595
2023-01-23 01:24:46.607613: step: 1820/530, loss: 0.061238765716552734
2023-01-23 01:24:47.773008: step: 1824/530, loss: 0.14865374565124512
2023-01-23 01:24:48.951537: step: 1828/530, loss: 0.14176049828529358
2023-01-23 01:24:50.130968: step: 1832/530, loss: 0.03680315241217613
2023-01-23 01:24:51.317658: step: 1836/530, loss: 0.22869043052196503
2023-01-23 01:24:52.519288: step: 1840/530, loss: 0.059095099568367004
2023-01-23 01:24:53.721245: step: 1844/530, loss: 0.1272084265947342
2023-01-23 01:24:54.906003: step: 1848/530, loss: 0.04223337024450302
2023-01-23 01:24:56.067935: step: 1852/530, loss: 0.04227743297815323
2023-01-23 01:24:57.212308: step: 1856/530, loss: 0.02473464049398899
2023-01-23 01:24:58.377399: step: 1860/530, loss: 0.05458106845617294
2023-01-23 01:24:59.519553: step: 1864/530, loss: 0.22492027282714844
2023-01-23 01:25:00.691699: step: 1868/530, loss: 0.004879808519035578
2023-01-23 01:25:01.843832: step: 1872/530, loss: 0.02873382531106472
2023-01-23 01:25:03.027736: step: 1876/530, loss: 0.08206617087125778
2023-01-23 01:25:04.159675: step: 1880/530, loss: 0.11475200951099396
2023-01-23 01:25:05.320954: step: 1884/530, loss: 0.16529321670532227
2023-01-23 01:25:06.521903: step: 1888/530, loss: 0.16822001338005066
2023-01-23 01:25:07.676978: step: 1892/530, loss: 0.08461141586303711
2023-01-23 01:25:08.871810: step: 1896/530, loss: 0.05309484153985977
2023-01-23 01:25:10.006749: step: 1900/530, loss: 0.0037692070472985506
2023-01-23 01:25:11.235155: step: 1904/530, loss: 0.03453955799341202
2023-01-23 01:25:12.398410: step: 1908/530, loss: 0.011183738708496094
2023-01-23 01:25:13.579848: step: 1912/530, loss: 0.11309614777565002
2023-01-23 01:25:14.756750: step: 1916/530, loss: 0.11008176952600479
2023-01-23 01:25:15.965295: step: 1920/530, loss: 0.05488453060388565
2023-01-23 01:25:17.113635: step: 1924/530, loss: 0.08474178612232208
2023-01-23 01:25:18.326554: step: 1928/530, loss: 0.04155416786670685
2023-01-23 01:25:19.493674: step: 1932/530, loss: 0.01725912094116211
2023-01-23 01:25:20.662117: step: 1936/530, loss: 0.1406540870666504
2023-01-23 01:25:21.851239: step: 1940/530, loss: 0.5332380533218384
2023-01-23 01:25:23.023551: step: 1944/530, loss: 0.7421558499336243
2023-01-23 01:25:24.216634: step: 1948/530, loss: 0.40126684308052063
2023-01-23 01:25:25.380747: step: 1952/530, loss: 0.07025952637195587
2023-01-23 01:25:26.525041: step: 1956/530, loss: 0.10136280953884125
2023-01-23 01:25:27.691263: step: 1960/530, loss: 0.041923485696315765
2023-01-23 01:25:28.924033: step: 1964/530, loss: 0.1143888384103775
2023-01-23 01:25:30.100677: step: 1968/530, loss: 0.0618954673409462
2023-01-23 01:25:31.261762: step: 1972/530, loss: 0.11773848533630371
2023-01-23 01:25:32.426040: step: 1976/530, loss: 0.02304256148636341
2023-01-23 01:25:33.571845: step: 1980/530, loss: 0.03841280937194824
2023-01-23 01:25:34.705581: step: 1984/530, loss: 0.11073608696460724
2023-01-23 01:25:35.876722: step: 1988/530, loss: 0.08356142044067383
2023-01-23 01:25:37.052837: step: 1992/530, loss: 0.013243008404970169
2023-01-23 01:25:38.215359: step: 1996/530, loss: 0.10953474789857864
2023-01-23 01:25:39.411057: step: 2000/530, loss: 0.08240146934986115
2023-01-23 01:25:40.599899: step: 2004/530, loss: 0.03070373460650444
2023-01-23 01:25:41.800930: step: 2008/530, loss: 0.10049595683813095
2023-01-23 01:25:42.979489: step: 2012/530, loss: 0.0011981010902673006
2023-01-23 01:25:44.182058: step: 2016/530, loss: 0.008508492261171341
2023-01-23 01:25:45.329699: step: 2020/530, loss: 1.1270250082015991
2023-01-23 01:25:46.502845: step: 2024/530, loss: 0.049528807401657104
2023-01-23 01:25:47.676772: step: 2028/530, loss: 0.012501812539994717
2023-01-23 01:25:48.858154: step: 2032/530, loss: 0.04654979705810547
2023-01-23 01:25:50.016981: step: 2036/530, loss: 0.06385155022144318
2023-01-23 01:25:51.178408: step: 2040/530, loss: 0.5583160519599915
2023-01-23 01:25:52.317362: step: 2044/530, loss: 0.03641219064593315
2023-01-23 01:25:53.490050: step: 2048/530, loss: 0.01014785747975111
2023-01-23 01:25:54.646331: step: 2052/530, loss: 0.03515911102294922
2023-01-23 01:25:55.805129: step: 2056/530, loss: 0.025452518835663795
2023-01-23 01:25:56.999332: step: 2060/530, loss: 0.040656138211488724
2023-01-23 01:25:58.155513: step: 2064/530, loss: 0.059287551790475845
2023-01-23 01:25:59.348520: step: 2068/530, loss: 0.06181994080543518
2023-01-23 01:26:00.544526: step: 2072/530, loss: 0.1264057159423828
2023-01-23 01:26:01.699162: step: 2076/530, loss: 0.04780912399291992
2023-01-23 01:26:02.902280: step: 2080/530, loss: 0.24887514114379883
2023-01-23 01:26:04.097690: step: 2084/530, loss: 0.027864838019013405
2023-01-23 01:26:05.272558: step: 2088/530, loss: 0.024231623858213425
2023-01-23 01:26:06.415308: step: 2092/530, loss: 0.01285848394036293
2023-01-23 01:26:07.586056: step: 2096/530, loss: 0.011727189645171165
2023-01-23 01:26:08.829524: step: 2100/530, loss: 1.2780228853225708
2023-01-23 01:26:10.044049: step: 2104/530, loss: 0.1730096936225891
2023-01-23 01:26:11.247833: step: 2108/530, loss: 0.009354591369628906
2023-01-23 01:26:12.422359: step: 2112/530, loss: 0.6456766128540039
2023-01-23 01:26:13.617329: step: 2116/530, loss: 0.16068105399608612
2023-01-23 01:26:14.813480: step: 2120/530, loss: 0.03443183749914169
==================================================
Loss: 0.094
--------------------
Dev: {'event': {'p': 0.5733990147783251, 'r': 0.7749667110519307, 'f1': 0.6591166477916196}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Test: {'event': {'p': 0.6218005295675199, 'r': 0.8102357676825762, 'f1': 0.7036204744069912}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Chinese: {'event': {'p': 0.5051546391752577, 'r': 0.9074074074074074, 'f1': 0.6490066225165563}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Korean: {'event': {'p': 0.6417910447761194, 'r': 0.6825396825396826, 'f1': 0.6615384615384614}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Russian: {'event': {'p': 0.425531914893617, 'r': 0.5555555555555556, 'f1': 0.48192771084337355}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
New best korean model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6351501668520578, 'r': 0.7603195739014648, 'f1': 0.6921212121212121}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Chinese: {'event': {'p': 0.6373175182481752, 'r': 0.8033352501437608, 'f1': 0.7107606207071993}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Chinese: {'event': {'p': 0.5903614457831325, 'r': 0.9074074074074074, 'f1': 0.7153284671532847}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5733990147783251, 'r': 0.7749667110519307, 'f1': 0.6591166477916196}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Eng Test for Korean: {'event': {'p': 0.6218005295675199, 'r': 0.8102357676825762, 'f1': 0.7036204744069912}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Sample Korean: {'event': {'p': 0.6417910447761194, 'r': 0.6825396825396826, 'f1': 0.6615384615384614}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5951882845188284, 'r': 0.7576564580559254, 'f1': 0.6666666666666666}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6663405088062623, 'r': 0.7832087406555491, 'f1': 0.7200634417129264}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5, 'r': 0.6666666666666666, 'f1': 0.5714285714285715}, '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 01:27:04.831353: step: 4/530, loss: 0.040193796157836914
2023-01-23 01:27:06.027671: step: 8/530, loss: 0.1925969123840332
2023-01-23 01:27:07.216566: step: 12/530, loss: 0.008068179711699486
2023-01-23 01:27:08.395562: step: 16/530, loss: 0.054369304329156876
2023-01-23 01:27:09.552422: step: 20/530, loss: 0.03011486493051052
2023-01-23 01:27:10.688801: step: 24/530, loss: 0.008286762982606888
2023-01-23 01:27:11.873396: step: 28/530, loss: 0.0059219361282885075
2023-01-23 01:27:12.990900: step: 32/530, loss: 0.03127327188849449
2023-01-23 01:27:14.138057: step: 36/530, loss: 0.010728931054472923
2023-01-23 01:27:15.295434: step: 40/530, loss: 0.004188823979347944
2023-01-23 01:27:16.478962: step: 44/530, loss: 0.06549644470214844
2023-01-23 01:27:17.644129: step: 48/530, loss: 0.03850555419921875
2023-01-23 01:27:18.819033: step: 52/530, loss: 0.4171985685825348
2023-01-23 01:27:19.994139: step: 56/530, loss: 0.044773101806640625
2023-01-23 01:27:21.143694: step: 60/530, loss: 0.008533382788300514
2023-01-23 01:27:22.288394: step: 64/530, loss: 0.04942756146192551
2023-01-23 01:27:23.453252: step: 68/530, loss: 0.04924755543470383
2023-01-23 01:27:24.624101: step: 72/530, loss: 0.11677218228578568
2023-01-23 01:27:25.804662: step: 76/530, loss: 0.017792511731386185
2023-01-23 01:27:26.972410: step: 80/530, loss: 0.016585683450102806
2023-01-23 01:27:28.147505: step: 84/530, loss: 0.047266677021980286
2023-01-23 01:27:29.299103: step: 88/530, loss: 0.03154829517006874
2023-01-23 01:27:30.442763: step: 92/530, loss: 0.09660597145557404
2023-01-23 01:27:31.593404: step: 96/530, loss: 0.009224509820342064
2023-01-23 01:27:32.741032: step: 100/530, loss: 0.00544586218893528
2023-01-23 01:27:33.886848: step: 104/530, loss: 0.008410096168518066
2023-01-23 01:27:35.047994: step: 108/530, loss: 0.0015298842918127775
2023-01-23 01:27:36.209618: step: 112/530, loss: 0.04512796550989151
2023-01-23 01:27:37.411175: step: 116/530, loss: 0.02275524102151394
2023-01-23 01:27:38.596990: step: 120/530, loss: 0.024181652814149857
2023-01-23 01:27:39.817138: step: 124/530, loss: 0.02689342573285103
2023-01-23 01:27:40.960031: step: 128/530, loss: 0.08269882202148438
2023-01-23 01:27:42.174135: step: 132/530, loss: 0.020416259765625
2023-01-23 01:27:43.406610: step: 136/530, loss: 0.08004073798656464
2023-01-23 01:27:44.618762: step: 140/530, loss: 0.04088592529296875
2023-01-23 01:27:45.770674: step: 144/530, loss: 0.010722160339355469
2023-01-23 01:27:46.956459: step: 148/530, loss: 0.055890750139951706
2023-01-23 01:27:48.150094: step: 152/530, loss: 0.03952045738697052
2023-01-23 01:27:49.316754: step: 156/530, loss: 0.025689315050840378
2023-01-23 01:27:50.474228: step: 160/530, loss: 0.02914433553814888
2023-01-23 01:27:51.650526: step: 164/530, loss: 0.04245796054601669
2023-01-23 01:27:52.785655: step: 168/530, loss: 0.027681540697813034
2023-01-23 01:27:53.952167: step: 172/530, loss: 0.017154311761260033
2023-01-23 01:27:55.145609: step: 176/530, loss: 0.0018316268688067794
2023-01-23 01:27:56.291968: step: 180/530, loss: 0.0682210922241211
2023-01-23 01:27:57.422678: step: 184/530, loss: 0.0075341700576245785
2023-01-23 01:27:58.593514: step: 188/530, loss: 0.006522560492157936
2023-01-23 01:27:59.734453: step: 192/530, loss: 0.005253410432487726
2023-01-23 01:28:00.944751: step: 196/530, loss: 0.05427522957324982
2023-01-23 01:28:02.123315: step: 200/530, loss: 0.0073015689849853516
2023-01-23 01:28:03.273654: step: 204/530, loss: 0.05885805934667587
2023-01-23 01:28:04.469980: step: 208/530, loss: 0.02545776404440403
2023-01-23 01:28:05.617781: step: 212/530, loss: 0.07222796231508255
2023-01-23 01:28:06.795806: step: 216/530, loss: 0.07952285557985306
2023-01-23 01:28:07.996591: step: 220/530, loss: 0.07114200294017792
2023-01-23 01:28:09.158853: step: 224/530, loss: 0.3014918565750122
2023-01-23 01:28:10.347872: step: 228/530, loss: 0.017184067517518997
2023-01-23 01:28:11.526334: step: 232/530, loss: 0.026261616498231888
2023-01-23 01:28:12.692213: step: 236/530, loss: 0.06885233521461487
2023-01-23 01:28:13.877203: step: 240/530, loss: 1.225547194480896
2023-01-23 01:28:15.042368: step: 244/530, loss: 0.026362037286162376
2023-01-23 01:28:16.264735: step: 248/530, loss: 0.13645973801612854
2023-01-23 01:28:17.461339: step: 252/530, loss: 0.018175125122070312
2023-01-23 01:28:18.651578: step: 256/530, loss: 0.046091459691524506
2023-01-23 01:28:19.845711: step: 260/530, loss: 0.02972564660012722
2023-01-23 01:28:21.016159: step: 264/530, loss: 0.6121718287467957
2023-01-23 01:28:22.179683: step: 268/530, loss: 0.004268646240234375
2023-01-23 01:28:23.333429: step: 272/530, loss: 0.04567098617553711
2023-01-23 01:28:24.496796: step: 276/530, loss: 0.05156669765710831
2023-01-23 01:28:25.639430: step: 280/530, loss: 0.016278648748993874
2023-01-23 01:28:26.771720: step: 284/530, loss: 0.07722588628530502
2023-01-23 01:28:27.923251: step: 288/530, loss: 0.06531143188476562
2023-01-23 01:28:29.098687: step: 292/530, loss: 0.04064035415649414
2023-01-23 01:28:30.307518: step: 296/530, loss: 0.018720200285315514
2023-01-23 01:28:31.470815: step: 300/530, loss: 0.06329710781574249
2023-01-23 01:28:32.674174: step: 304/530, loss: 0.16408902406692505
2023-01-23 01:28:33.853258: step: 308/530, loss: 0.01277837809175253
2023-01-23 01:28:35.033573: step: 312/530, loss: 0.033989906311035156
2023-01-23 01:28:36.212694: step: 316/530, loss: 0.01437443494796753
2023-01-23 01:28:37.359384: step: 320/530, loss: 0.02835751697421074
2023-01-23 01:28:38.514192: step: 324/530, loss: 0.844908595085144
2023-01-23 01:28:39.678079: step: 328/530, loss: 0.02436971664428711
2023-01-23 01:28:40.848388: step: 332/530, loss: 0.042284537106752396
2023-01-23 01:28:42.069396: step: 336/530, loss: 0.10146990418434143
2023-01-23 01:28:43.238463: step: 340/530, loss: 0.010786056518554688
2023-01-23 01:28:44.427043: step: 344/530, loss: 0.01684265211224556
2023-01-23 01:28:45.589909: step: 348/530, loss: 0.044982150197029114
2023-01-23 01:28:46.731104: step: 352/530, loss: 0.13811969757080078
2023-01-23 01:28:47.905956: step: 356/530, loss: 0.04064645618200302
2023-01-23 01:28:49.048459: step: 360/530, loss: 0.021478652954101562
2023-01-23 01:28:50.267591: step: 364/530, loss: 0.012730216607451439
2023-01-23 01:28:51.434606: step: 368/530, loss: 0.010828971862792969
2023-01-23 01:28:52.608259: step: 372/530, loss: 0.1215810775756836
2023-01-23 01:28:53.767126: step: 376/530, loss: 0.04316148906946182
2023-01-23 01:28:54.915722: step: 380/530, loss: 1.023289442062378
2023-01-23 01:28:56.058023: step: 384/530, loss: 0.014939587563276291
2023-01-23 01:28:57.212388: step: 388/530, loss: 0.03333263844251633
2023-01-23 01:28:58.406029: step: 392/530, loss: 0.003464949317276478
2023-01-23 01:28:59.566413: step: 396/530, loss: 0.0006778717506676912
2023-01-23 01:29:00.690732: step: 400/530, loss: 0.0017789840931072831
2023-01-23 01:29:01.824244: step: 404/530, loss: 0.09073605388402939
2023-01-23 01:29:02.972875: step: 408/530, loss: 0.008330250158905983
2023-01-23 01:29:04.123436: step: 412/530, loss: 0.0416385680437088
2023-01-23 01:29:05.292689: step: 416/530, loss: 0.022292708978056908
2023-01-23 01:29:06.487831: step: 420/530, loss: 0.04284262657165527
2023-01-23 01:29:07.681884: step: 424/530, loss: 0.032215166836977005
2023-01-23 01:29:08.827768: step: 428/530, loss: 0.07145509868860245
2023-01-23 01:29:10.046099: step: 432/530, loss: 0.03559456020593643
2023-01-23 01:29:11.191610: step: 436/530, loss: 0.03545322269201279
2023-01-23 01:29:12.335366: step: 440/530, loss: 0.07624645531177521
2023-01-23 01:29:13.498230: step: 444/530, loss: 0.040876105427742004
2023-01-23 01:29:14.667233: step: 448/530, loss: 0.007582426071166992
2023-01-23 01:29:15.843680: step: 452/530, loss: 0.06753072887659073
2023-01-23 01:29:16.999385: step: 456/530, loss: 0.09264083206653595
2023-01-23 01:29:18.201656: step: 460/530, loss: 0.11387910693883896
2023-01-23 01:29:19.379746: step: 464/530, loss: 0.012487983331084251
2023-01-23 01:29:20.532976: step: 468/530, loss: 0.021651078015565872
2023-01-23 01:29:21.697272: step: 472/530, loss: 0.013079453259706497
2023-01-23 01:29:22.873964: step: 476/530, loss: 0.05984792858362198
2023-01-23 01:29:24.053715: step: 480/530, loss: 0.054645441472530365
2023-01-23 01:29:25.206760: step: 484/530, loss: 0.05262718349695206
2023-01-23 01:29:26.352274: step: 488/530, loss: 0.08547866344451904
2023-01-23 01:29:27.519275: step: 492/530, loss: 0.010970878414809704
2023-01-23 01:29:28.714038: step: 496/530, loss: 0.07885799556970596
2023-01-23 01:29:29.855503: step: 500/530, loss: 0.008196020498871803
2023-01-23 01:29:31.019155: step: 504/530, loss: 0.08262091130018234
2023-01-23 01:29:32.167489: step: 508/530, loss: 0.20434603095054626
2023-01-23 01:29:33.358444: step: 512/530, loss: 0.1378999650478363
2023-01-23 01:29:34.516342: step: 516/530, loss: 0.07595586776733398
2023-01-23 01:29:35.669953: step: 520/530, loss: 0.0707605853676796
2023-01-23 01:29:36.888557: step: 524/530, loss: 0.025089645758271217
2023-01-23 01:29:38.064483: step: 528/530, loss: 0.028089236468076706
2023-01-23 01:29:39.229846: step: 532/530, loss: 0.039298057556152344
2023-01-23 01:29:40.395535: step: 536/530, loss: 0.03831539303064346
2023-01-23 01:29:41.578112: step: 540/530, loss: 0.035120584070682526
2023-01-23 01:29:42.763747: step: 544/530, loss: 0.04647207260131836
2023-01-23 01:29:43.993343: step: 548/530, loss: 0.037885282188653946
2023-01-23 01:29:45.133880: step: 552/530, loss: 0.001146030379459262
2023-01-23 01:29:46.293100: step: 556/530, loss: 0.02865314483642578
2023-01-23 01:29:47.449745: step: 560/530, loss: 0.06953983008861542
2023-01-23 01:29:48.631597: step: 564/530, loss: 0.11244497448205948
2023-01-23 01:29:49.812398: step: 568/530, loss: 0.12538576126098633
2023-01-23 01:29:50.994687: step: 572/530, loss: 0.02740314044058323
2023-01-23 01:29:52.173973: step: 576/530, loss: 0.026177024468779564
2023-01-23 01:29:53.383315: step: 580/530, loss: 0.022669412195682526
2023-01-23 01:29:54.515418: step: 584/530, loss: 0.030486201867461205
2023-01-23 01:29:55.683673: step: 588/530, loss: 0.2832070291042328
2023-01-23 01:29:56.843881: step: 592/530, loss: 0.006395816802978516
2023-01-23 01:29:58.037572: step: 596/530, loss: 0.03436432033777237
2023-01-23 01:29:59.223994: step: 600/530, loss: 0.0880916565656662
2023-01-23 01:30:00.406050: step: 604/530, loss: 0.12265052646398544
2023-01-23 01:30:01.586173: step: 608/530, loss: 0.13371442258358002
2023-01-23 01:30:02.769894: step: 612/530, loss: 0.051534175872802734
2023-01-23 01:30:03.958748: step: 616/530, loss: 0.12401533126831055
2023-01-23 01:30:05.154545: step: 620/530, loss: 0.08221378922462463
2023-01-23 01:30:06.315415: step: 624/530, loss: 0.0038105486892163754
2023-01-23 01:30:07.474740: step: 628/530, loss: 0.04228964075446129
2023-01-23 01:30:08.639845: step: 632/530, loss: 0.03572959825396538
2023-01-23 01:30:09.902989: step: 636/530, loss: 0.04438524320721626
2023-01-23 01:30:11.064235: step: 640/530, loss: 0.01891307905316353
2023-01-23 01:30:12.236083: step: 644/530, loss: 0.05729370191693306
2023-01-23 01:30:13.501551: step: 648/530, loss: 0.04836712032556534
2023-01-23 01:30:14.699247: step: 652/530, loss: 0.10525589436292648
2023-01-23 01:30:15.874890: step: 656/530, loss: 0.0496579185128212
2023-01-23 01:30:17.099691: step: 660/530, loss: 0.015357399359345436
2023-01-23 01:30:18.270071: step: 664/530, loss: 0.06007261201739311
2023-01-23 01:30:19.504914: step: 668/530, loss: 0.026992036029696465
2023-01-23 01:30:20.635703: step: 672/530, loss: 0.0047779087908566
2023-01-23 01:30:21.810642: step: 676/530, loss: 0.0412198081612587
2023-01-23 01:30:22.998719: step: 680/530, loss: 0.04959306865930557
2023-01-23 01:30:24.169081: step: 684/530, loss: 0.0832623541355133
2023-01-23 01:30:25.375963: step: 688/530, loss: 0.03372330591082573
2023-01-23 01:30:26.548492: step: 692/530, loss: 0.008663564920425415
2023-01-23 01:30:27.679547: step: 696/530, loss: 0.08561283349990845
2023-01-23 01:30:28.841216: step: 700/530, loss: 0.12334556877613068
2023-01-23 01:30:29.998356: step: 704/530, loss: 0.011485290713608265
2023-01-23 01:30:31.195548: step: 708/530, loss: 0.033331871032714844
2023-01-23 01:30:32.364527: step: 712/530, loss: 0.03820851445198059
2023-01-23 01:30:33.525401: step: 716/530, loss: 0.01797785796225071
2023-01-23 01:30:34.715237: step: 720/530, loss: 0.050202179700136185
2023-01-23 01:30:35.921324: step: 724/530, loss: 0.05454311519861221
2023-01-23 01:30:37.071237: step: 728/530, loss: 0.007267093751579523
2023-01-23 01:30:38.213424: step: 732/530, loss: 0.003907442092895508
2023-01-23 01:30:39.380072: step: 736/530, loss: 0.02642088010907173
2023-01-23 01:30:40.539752: step: 740/530, loss: 0.03476686775684357
2023-01-23 01:30:41.756711: step: 744/530, loss: 0.00971007440239191
2023-01-23 01:30:42.945507: step: 748/530, loss: 0.15674400329589844
2023-01-23 01:30:44.109194: step: 752/530, loss: 0.0017531871562823653
2023-01-23 01:30:45.271419: step: 756/530, loss: 0.18296855688095093
2023-01-23 01:30:46.429896: step: 760/530, loss: 0.07615260779857635
2023-01-23 01:30:47.631999: step: 764/530, loss: 0.014386367984116077
2023-01-23 01:30:48.779734: step: 768/530, loss: 0.00672540720552206
2023-01-23 01:30:49.936684: step: 772/530, loss: 0.013537502847611904
2023-01-23 01:30:51.106489: step: 776/530, loss: 0.06736688315868378
2023-01-23 01:30:52.320904: step: 780/530, loss: 0.13366222381591797
2023-01-23 01:30:53.493677: step: 784/530, loss: 0.048146724700927734
2023-01-23 01:30:54.709062: step: 788/530, loss: 0.3908994197845459
2023-01-23 01:30:55.868084: step: 792/530, loss: 0.0030434608925133944
2023-01-23 01:30:57.047674: step: 796/530, loss: 0.003957939334213734
2023-01-23 01:30:58.250996: step: 800/530, loss: 0.03417949751019478
2023-01-23 01:30:59.376783: step: 804/530, loss: 0.030261993408203125
2023-01-23 01:31:00.579157: step: 808/530, loss: 0.058305174112319946
2023-01-23 01:31:01.736162: step: 812/530, loss: 0.022214507684111595
2023-01-23 01:31:02.947736: step: 816/530, loss: 0.051863860338926315
2023-01-23 01:31:04.162032: step: 820/530, loss: 0.011324597522616386
2023-01-23 01:31:05.338069: step: 824/530, loss: 0.06011686474084854
2023-01-23 01:31:06.519058: step: 828/530, loss: 0.13771677017211914
2023-01-23 01:31:07.678724: step: 832/530, loss: 0.0388481505215168
2023-01-23 01:31:08.842652: step: 836/530, loss: 0.0248087290674448
2023-01-23 01:31:10.015260: step: 840/530, loss: 0.05014844238758087
2023-01-23 01:31:11.230024: step: 844/530, loss: 0.04474234580993652
2023-01-23 01:31:12.440005: step: 848/530, loss: 0.059267617762088776
2023-01-23 01:31:13.595256: step: 852/530, loss: 0.032663822174072266
2023-01-23 01:31:14.729164: step: 856/530, loss: 0.026125334203243256
2023-01-23 01:31:15.924662: step: 860/530, loss: 0.025179481133818626
2023-01-23 01:31:17.138301: step: 864/530, loss: 0.010769093409180641
2023-01-23 01:31:18.310036: step: 868/530, loss: 0.07975830882787704
2023-01-23 01:31:19.502540: step: 872/530, loss: 0.07185707241296768
2023-01-23 01:31:20.704638: step: 876/530, loss: 0.09335789829492569
2023-01-23 01:31:21.914109: step: 880/530, loss: 0.01723327860236168
2023-01-23 01:31:23.100907: step: 884/530, loss: 0.04452686384320259
2023-01-23 01:31:24.255046: step: 888/530, loss: 0.024522019550204277
2023-01-23 01:31:25.432714: step: 892/530, loss: 0.016650009900331497
2023-01-23 01:31:26.609845: step: 896/530, loss: 0.12502537667751312
2023-01-23 01:31:27.750367: step: 900/530, loss: 0.0653235912322998
2023-01-23 01:31:28.908409: step: 904/530, loss: 0.01581707037985325
2023-01-23 01:31:30.084142: step: 908/530, loss: 0.03271684795618057
2023-01-23 01:31:31.256597: step: 912/530, loss: 0.6562553644180298
2023-01-23 01:31:32.431444: step: 916/530, loss: 0.036132145673036575
2023-01-23 01:31:33.603930: step: 920/530, loss: 0.0026128769386559725
2023-01-23 01:31:34.798515: step: 924/530, loss: 0.01007752399891615
2023-01-23 01:31:36.008891: step: 928/530, loss: 0.05231647565960884
2023-01-23 01:31:37.164698: step: 932/530, loss: 0.025013351812958717
2023-01-23 01:31:38.339271: step: 936/530, loss: 0.13412514328956604
2023-01-23 01:31:39.504994: step: 940/530, loss: 0.15119361877441406
2023-01-23 01:31:40.692230: step: 944/530, loss: 0.07803191989660263
2023-01-23 01:31:41.873399: step: 948/530, loss: 0.0067005157470703125
2023-01-23 01:31:43.049168: step: 952/530, loss: 0.036341384053230286
2023-01-23 01:31:44.229416: step: 956/530, loss: 0.04508399963378906
2023-01-23 01:31:45.461643: step: 960/530, loss: 0.10063686966896057
2023-01-23 01:31:46.626505: step: 964/530, loss: 0.00360512756742537
2023-01-23 01:31:47.779081: step: 968/530, loss: 0.020470619201660156
2023-01-23 01:31:48.968492: step: 972/530, loss: 0.006973457522690296
2023-01-23 01:31:50.150747: step: 976/530, loss: 0.023480558767914772
2023-01-23 01:31:51.323861: step: 980/530, loss: 0.029812907800078392
2023-01-23 01:31:52.486998: step: 984/530, loss: 0.04470071941614151
2023-01-23 01:31:53.636321: step: 988/530, loss: 0.03359051048755646
2023-01-23 01:31:54.854061: step: 992/530, loss: 0.4126303195953369
2023-01-23 01:31:56.042529: step: 996/530, loss: 0.018140316009521484
2023-01-23 01:31:57.179216: step: 1000/530, loss: 0.05247020721435547
2023-01-23 01:31:58.358211: step: 1004/530, loss: 0.061660218983888626
2023-01-23 01:31:59.540947: step: 1008/530, loss: 0.027158355340361595
2023-01-23 01:32:00.719046: step: 1012/530, loss: 0.016544818878173828
2023-01-23 01:32:01.944154: step: 1016/530, loss: 0.05646038055419922
2023-01-23 01:32:03.054262: step: 1020/530, loss: 0.017916489392518997
2023-01-23 01:32:04.235856: step: 1024/530, loss: 0.02293720282614231
2023-01-23 01:32:05.429524: step: 1028/530, loss: 0.21399955451488495
2023-01-23 01:32:06.625278: step: 1032/530, loss: 0.06986560672521591
2023-01-23 01:32:07.800847: step: 1036/530, loss: 0.020253753289580345
2023-01-23 01:32:08.975490: step: 1040/530, loss: 0.027814103290438652
2023-01-23 01:32:10.128482: step: 1044/530, loss: 0.26092958450317383
2023-01-23 01:32:11.313524: step: 1048/530, loss: 0.05469389259815216
2023-01-23 01:32:12.475049: step: 1052/530, loss: 0.0655149444937706
2023-01-23 01:32:13.672561: step: 1056/530, loss: 0.15257254242897034
2023-01-23 01:32:14.841329: step: 1060/530, loss: 0.04388999938964844
2023-01-23 01:32:16.023503: step: 1064/530, loss: 0.0736115425825119
2023-01-23 01:32:17.203939: step: 1068/530, loss: 0.040364883840084076
2023-01-23 01:32:18.405932: step: 1072/530, loss: 0.051200296729803085
2023-01-23 01:32:19.590410: step: 1076/530, loss: 0.18050844967365265
2023-01-23 01:32:20.721441: step: 1080/530, loss: 0.01931166648864746
2023-01-23 01:32:21.871114: step: 1084/530, loss: 0.0028374672401696444
2023-01-23 01:32:23.018142: step: 1088/530, loss: 0.025735855102539062
2023-01-23 01:32:24.203389: step: 1092/530, loss: 0.12311353534460068
2023-01-23 01:32:25.428323: step: 1096/530, loss: 0.10393076390028
2023-01-23 01:32:26.621200: step: 1100/530, loss: 0.05007191002368927
2023-01-23 01:32:27.794123: step: 1104/530, loss: 0.03162822872400284
2023-01-23 01:32:28.963043: step: 1108/530, loss: 0.01460571214556694
2023-01-23 01:32:30.128313: step: 1112/530, loss: 0.081229068338871
2023-01-23 01:32:31.306548: step: 1116/530, loss: 0.3075721263885498
2023-01-23 01:32:32.507348: step: 1120/530, loss: 0.09793069213628769
2023-01-23 01:32:33.668464: step: 1124/530, loss: 0.010797500610351562
2023-01-23 01:32:34.800298: step: 1128/530, loss: 0.009747028350830078
2023-01-23 01:32:35.991596: step: 1132/530, loss: 0.03980827331542969
2023-01-23 01:32:37.168947: step: 1136/530, loss: 0.06436280906200409
2023-01-23 01:32:38.334723: step: 1140/530, loss: 0.06997604668140411
2023-01-23 01:32:39.484139: step: 1144/530, loss: 0.0021999599412083626
2023-01-23 01:32:40.617593: step: 1148/530, loss: 0.004562473390251398
2023-01-23 01:32:41.820730: step: 1152/530, loss: 0.012472153641283512
2023-01-23 01:32:42.955573: step: 1156/530, loss: 0.008253097534179688
2023-01-23 01:32:44.114953: step: 1160/530, loss: 0.027341270819306374
2023-01-23 01:32:45.274879: step: 1164/530, loss: 0.024799823760986328
2023-01-23 01:32:46.412679: step: 1168/530, loss: 0.038684748113155365
2023-01-23 01:32:47.556948: step: 1172/530, loss: 0.24883747100830078
2023-01-23 01:32:48.707418: step: 1176/530, loss: 0.07423864305019379
2023-01-23 01:32:49.906115: step: 1180/530, loss: 0.04277057573199272
2023-01-23 01:32:51.077536: step: 1184/530, loss: 0.007458400912582874
2023-01-23 01:32:52.227530: step: 1188/530, loss: 0.0056517599150538445
2023-01-23 01:32:53.381141: step: 1192/530, loss: 0.02722902223467827
2023-01-23 01:32:54.560666: step: 1196/530, loss: 0.14411425590515137
2023-01-23 01:32:55.716116: step: 1200/530, loss: 0.06798720359802246
2023-01-23 01:32:56.888223: step: 1204/530, loss: 0.21190214157104492
2023-01-23 01:32:58.041371: step: 1208/530, loss: 0.04999339580535889
2023-01-23 01:32:59.235191: step: 1212/530, loss: 0.3592701852321625
2023-01-23 01:33:00.404293: step: 1216/530, loss: 0.0421878844499588
2023-01-23 01:33:01.593237: step: 1220/530, loss: 0.05697841942310333
2023-01-23 01:33:02.761558: step: 1224/530, loss: 0.02662830427289009
2023-01-23 01:33:04.029112: step: 1228/530, loss: 0.38961562514305115
2023-01-23 01:33:05.219224: step: 1232/530, loss: 0.014125823974609375
2023-01-23 01:33:06.389586: step: 1236/530, loss: 0.049326326698064804
2023-01-23 01:33:07.598081: step: 1240/530, loss: 0.023943709209561348
2023-01-23 01:33:08.787921: step: 1244/530, loss: 0.0799466148018837
2023-01-23 01:33:09.968734: step: 1248/530, loss: 0.05999784171581268
2023-01-23 01:33:11.162639: step: 1252/530, loss: 0.05664873495697975
2023-01-23 01:33:12.341940: step: 1256/530, loss: 0.06613197177648544
2023-01-23 01:33:13.517181: step: 1260/530, loss: 0.06309938430786133
2023-01-23 01:33:14.705891: step: 1264/530, loss: 0.006645870395004749
2023-01-23 01:33:15.934872: step: 1268/530, loss: 0.041959669440984726
2023-01-23 01:33:17.130730: step: 1272/530, loss: 0.09657907485961914
2023-01-23 01:33:18.283277: step: 1276/530, loss: 0.025110816583037376
2023-01-23 01:33:19.454350: step: 1280/530, loss: 0.05965852737426758
2023-01-23 01:33:20.618316: step: 1284/530, loss: 0.05253257602453232
2023-01-23 01:33:21.818500: step: 1288/530, loss: 0.27936476469039917
2023-01-23 01:33:23.006902: step: 1292/530, loss: 0.0941135436296463
2023-01-23 01:33:24.192254: step: 1296/530, loss: 0.006976413540542126
2023-01-23 01:33:25.368274: step: 1300/530, loss: 0.05810394510626793
2023-01-23 01:33:26.534969: step: 1304/530, loss: 0.051522161811590195
2023-01-23 01:33:27.691964: step: 1308/530, loss: 0.06858482956886292
2023-01-23 01:33:28.881989: step: 1312/530, loss: 0.018082808703184128
2023-01-23 01:33:30.073799: step: 1316/530, loss: 0.01313791237771511
2023-01-23 01:33:31.256602: step: 1320/530, loss: 0.08888392150402069
2023-01-23 01:33:32.450203: step: 1324/530, loss: 0.0287035945802927
2023-01-23 01:33:33.599845: step: 1328/530, loss: 0.10513058304786682
2023-01-23 01:33:34.792073: step: 1332/530, loss: 0.08273611217737198
2023-01-23 01:33:35.980574: step: 1336/530, loss: 0.04304981976747513
2023-01-23 01:33:37.136401: step: 1340/530, loss: 0.014644431881606579
2023-01-23 01:33:38.312029: step: 1344/530, loss: 0.03971881791949272
2023-01-23 01:33:39.482835: step: 1348/530, loss: 0.0632256492972374
2023-01-23 01:33:40.654812: step: 1352/530, loss: 0.12699586153030396
2023-01-23 01:33:41.858589: step: 1356/530, loss: 0.02354593202471733
2023-01-23 01:33:43.014733: step: 1360/530, loss: 0.04231557995080948
2023-01-23 01:33:44.170149: step: 1364/530, loss: 0.03652925416827202
2023-01-23 01:33:45.379274: step: 1368/530, loss: 0.06089644506573677
2023-01-23 01:33:46.543736: step: 1372/530, loss: 0.012512017041444778
2023-01-23 01:33:47.698077: step: 1376/530, loss: 0.0172574520111084
2023-01-23 01:33:48.813002: step: 1380/530, loss: 0.009197902865707874
2023-01-23 01:33:49.985942: step: 1384/530, loss: 0.05680666118860245
2023-01-23 01:33:51.173309: step: 1388/530, loss: 0.021976470947265625
2023-01-23 01:33:52.418155: step: 1392/530, loss: 0.05697183310985565
2023-01-23 01:33:53.554723: step: 1396/530, loss: 0.0026158331893384457
2023-01-23 01:33:54.717778: step: 1400/530, loss: 0.015715217217803
2023-01-23 01:33:55.900066: step: 1404/530, loss: 0.09058323502540588
2023-01-23 01:33:57.109298: step: 1408/530, loss: 0.29007381200790405
2023-01-23 01:33:58.249184: step: 1412/530, loss: 1.439026117324829
2023-01-23 01:33:59.415568: step: 1416/530, loss: 0.08220891654491425
2023-01-23 01:34:00.571248: step: 1420/530, loss: 0.11348428577184677
2023-01-23 01:34:01.782882: step: 1424/530, loss: 0.031708527356386185
2023-01-23 01:34:02.984087: step: 1428/530, loss: 0.30097341537475586
2023-01-23 01:34:04.135771: step: 1432/530, loss: 0.01700286753475666
2023-01-23 01:34:05.298349: step: 1436/530, loss: 0.01936321333050728
2023-01-23 01:34:06.474116: step: 1440/530, loss: 0.02789301984012127
2023-01-23 01:34:07.658358: step: 1444/530, loss: 0.04058055952191353
2023-01-23 01:34:08.814527: step: 1448/530, loss: 0.014706611633300781
2023-01-23 01:34:10.009565: step: 1452/530, loss: 0.06454400718212128
2023-01-23 01:34:11.156574: step: 1456/530, loss: 0.04108614847064018
2023-01-23 01:34:12.316142: step: 1460/530, loss: 0.029926490038633347
2023-01-23 01:34:13.529038: step: 1464/530, loss: 0.041158296167850494
2023-01-23 01:34:14.708004: step: 1468/530, loss: 0.10778876394033432
2023-01-23 01:34:15.903754: step: 1472/530, loss: 0.027494337409734726
2023-01-23 01:34:17.052472: step: 1476/530, loss: 0.020072031766176224
2023-01-23 01:34:18.245175: step: 1480/530, loss: 0.05857563018798828
2023-01-23 01:34:19.424511: step: 1484/530, loss: 0.06425486505031586
2023-01-23 01:34:20.590928: step: 1488/530, loss: 0.2647492289543152
2023-01-23 01:34:21.767427: step: 1492/530, loss: 0.0670381560921669
2023-01-23 01:34:22.944740: step: 1496/530, loss: 0.03156747668981552
2023-01-23 01:34:24.117190: step: 1500/530, loss: 0.0004258156113792211
2023-01-23 01:34:25.330950: step: 1504/530, loss: 0.002929210662841797
2023-01-23 01:34:26.496704: step: 1508/530, loss: 0.0641416609287262
2023-01-23 01:34:27.659346: step: 1512/530, loss: 0.0788789764046669
2023-01-23 01:34:28.807953: step: 1516/530, loss: 0.019392013549804688
2023-01-23 01:34:29.998905: step: 1520/530, loss: 0.35581105947494507
2023-01-23 01:34:31.186342: step: 1524/530, loss: 0.05329761654138565
2023-01-23 01:34:32.357390: step: 1528/530, loss: 0.03252973407506943
2023-01-23 01:34:33.529440: step: 1532/530, loss: 0.03524503856897354
2023-01-23 01:34:34.737270: step: 1536/530, loss: 0.043288663029670715
2023-01-23 01:34:35.925829: step: 1540/530, loss: 0.030834197998046875
2023-01-23 01:34:37.100453: step: 1544/530, loss: 0.017821885645389557
2023-01-23 01:34:38.292964: step: 1548/530, loss: 0.04443841055035591
2023-01-23 01:34:39.489297: step: 1552/530, loss: 0.11334028095006943
2023-01-23 01:34:40.643703: step: 1556/530, loss: 0.02788219414651394
2023-01-23 01:34:41.844210: step: 1560/530, loss: 0.062150001525878906
2023-01-23 01:34:43.032813: step: 1564/530, loss: 0.04017162322998047
2023-01-23 01:34:44.270109: step: 1568/530, loss: 0.05305814743041992
2023-01-23 01:34:45.485939: step: 1572/530, loss: 0.043811991810798645
2023-01-23 01:34:46.662249: step: 1576/530, loss: 0.02407817915081978
2023-01-23 01:34:47.831790: step: 1580/530, loss: 0.22694797813892365
2023-01-23 01:34:48.980299: step: 1584/530, loss: 0.04466314613819122
2023-01-23 01:34:50.131047: step: 1588/530, loss: 0.026455307379364967
2023-01-23 01:34:51.319589: step: 1592/530, loss: 0.25087910890579224
2023-01-23 01:34:52.482419: step: 1596/530, loss: 0.0790504440665245
2023-01-23 01:34:53.654896: step: 1600/530, loss: 0.0269167423248291
2023-01-23 01:34:54.828577: step: 1604/530, loss: 0.025547217577695847
2023-01-23 01:34:56.033069: step: 1608/530, loss: 0.07659397274255753
2023-01-23 01:34:57.216263: step: 1612/530, loss: 0.03527393564581871
2023-01-23 01:34:58.405036: step: 1616/530, loss: 0.07311735302209854
2023-01-23 01:34:59.579426: step: 1620/530, loss: 0.04003019258379936
2023-01-23 01:35:00.767009: step: 1624/530, loss: 0.004047393798828125
2023-01-23 01:35:01.936824: step: 1628/530, loss: 0.08315735310316086
2023-01-23 01:35:03.073539: step: 1632/530, loss: 0.09470382332801819
2023-01-23 01:35:04.271984: step: 1636/530, loss: 0.055933333933353424
2023-01-23 01:35:05.501656: step: 1640/530, loss: 0.0070473672822117805
2023-01-23 01:35:06.678622: step: 1644/530, loss: 0.034024428576231
2023-01-23 01:35:07.819642: step: 1648/530, loss: 0.08158489316701889
2023-01-23 01:35:08.967126: step: 1652/530, loss: 0.033138107508420944
2023-01-23 01:35:10.099454: step: 1656/530, loss: 0.0032841681968420744
2023-01-23 01:35:11.280595: step: 1660/530, loss: 0.0026679039001464844
2023-01-23 01:35:12.508986: step: 1664/530, loss: 0.07529354840517044
2023-01-23 01:35:13.692286: step: 1668/530, loss: 0.0316782221198082
2023-01-23 01:35:14.849478: step: 1672/530, loss: 0.03076343610882759
2023-01-23 01:35:15.991131: step: 1676/530, loss: 0.07990200817584991
2023-01-23 01:35:17.151977: step: 1680/530, loss: 0.002024746034294367
2023-01-23 01:35:18.343586: step: 1684/530, loss: 0.053371235728263855
2023-01-23 01:35:19.545259: step: 1688/530, loss: 0.003030919935554266
2023-01-23 01:35:20.696483: step: 1692/530, loss: 0.011446857824921608
2023-01-23 01:35:21.836366: step: 1696/530, loss: 0.017545366659760475
2023-01-23 01:35:22.993719: step: 1700/530, loss: 0.04211931303143501
2023-01-23 01:35:24.187892: step: 1704/530, loss: 0.09288759529590607
2023-01-23 01:35:25.384897: step: 1708/530, loss: 0.039089396595954895
2023-01-23 01:35:26.566017: step: 1712/530, loss: 0.09768429398536682
2023-01-23 01:35:27.751175: step: 1716/530, loss: 0.005444908048957586
2023-01-23 01:35:28.918181: step: 1720/530, loss: 0.042947910726070404
2023-01-23 01:35:30.107402: step: 1724/530, loss: 0.14172887802124023
2023-01-23 01:35:31.310904: step: 1728/530, loss: 0.013875866308808327
2023-01-23 01:35:32.453620: step: 1732/530, loss: 0.006092834752053022
2023-01-23 01:35:33.630193: step: 1736/530, loss: 0.12989740073680878
2023-01-23 01:35:34.803590: step: 1740/530, loss: 0.09237499535083771
2023-01-23 01:35:35.956384: step: 1744/530, loss: 0.018376445397734642
2023-01-23 01:35:37.142790: step: 1748/530, loss: 0.002489757491275668
2023-01-23 01:35:38.302031: step: 1752/530, loss: 0.026789667084813118
2023-01-23 01:35:39.430969: step: 1756/530, loss: 0.06102064624428749
2023-01-23 01:35:40.570644: step: 1760/530, loss: 0.04107780382037163
2023-01-23 01:35:41.736604: step: 1764/530, loss: 0.015265846624970436
2023-01-23 01:35:42.938654: step: 1768/530, loss: 0.010283184237778187
2023-01-23 01:35:44.105404: step: 1772/530, loss: 0.030953610315918922
2023-01-23 01:35:45.242601: step: 1776/530, loss: 0.09752622246742249
2023-01-23 01:35:46.413024: step: 1780/530, loss: 0.09758854657411575
2023-01-23 01:35:47.616998: step: 1784/530, loss: 0.07034482806921005
2023-01-23 01:35:48.820663: step: 1788/530, loss: 0.08178377151489258
2023-01-23 01:35:50.023024: step: 1792/530, loss: 0.016475582495331764
2023-01-23 01:35:51.171004: step: 1796/530, loss: 0.006459140684455633
2023-01-23 01:35:52.354008: step: 1800/530, loss: 0.0015003443695604801
2023-01-23 01:35:53.492302: step: 1804/530, loss: 0.0034512400161474943
2023-01-23 01:35:54.657480: step: 1808/530, loss: 0.0734289139509201
2023-01-23 01:35:55.865713: step: 1812/530, loss: 0.11434536427259445
2023-01-23 01:35:57.041775: step: 1816/530, loss: 0.13031813502311707
2023-01-23 01:35:58.192990: step: 1820/530, loss: 0.006575929932296276
2023-01-23 01:35:59.391641: step: 1824/530, loss: 0.201338529586792
2023-01-23 01:36:00.566010: step: 1828/530, loss: 0.009511947631835938
2023-01-23 01:36:01.726825: step: 1832/530, loss: 0.1060938835144043
2023-01-23 01:36:02.907633: step: 1836/530, loss: 0.02113560400903225
2023-01-23 01:36:04.079323: step: 1840/530, loss: 0.11078128218650818
2023-01-23 01:36:05.247976: step: 1844/530, loss: 0.013461923226714134
2023-01-23 01:36:06.494753: step: 1848/530, loss: 0.05008862167596817
2023-01-23 01:36:07.672750: step: 1852/530, loss: 0.06582939624786377
2023-01-23 01:36:08.848787: step: 1856/530, loss: 0.009858131408691406
2023-01-23 01:36:10.018471: step: 1860/530, loss: 0.060059450566768646
2023-01-23 01:36:11.187644: step: 1864/530, loss: 0.06390972435474396
2023-01-23 01:36:12.343760: step: 1868/530, loss: 0.041956402361392975
2023-01-23 01:36:13.521055: step: 1872/530, loss: 0.04145832359790802
2023-01-23 01:36:14.684037: step: 1876/530, loss: 0.016301751136779785
2023-01-23 01:36:15.860611: step: 1880/530, loss: 0.021349811926484108
2023-01-23 01:36:17.067758: step: 1884/530, loss: 0.06501074135303497
2023-01-23 01:36:18.225441: step: 1888/530, loss: 0.0013097763294354081
2023-01-23 01:36:19.405310: step: 1892/530, loss: 0.042084887623786926
2023-01-23 01:36:20.607315: step: 1896/530, loss: 0.041356779634952545
2023-01-23 01:36:21.760777: step: 1900/530, loss: 0.01663064956665039
2023-01-23 01:36:22.930990: step: 1904/530, loss: 0.07321052253246307
2023-01-23 01:36:24.087755: step: 1908/530, loss: 0.0691106766462326
2023-01-23 01:36:25.250394: step: 1912/530, loss: 0.023871900513768196
2023-01-23 01:36:26.397884: step: 1916/530, loss: 0.032453037798404694
2023-01-23 01:36:27.614519: step: 1920/530, loss: 0.10434424877166748
2023-01-23 01:36:28.814763: step: 1924/530, loss: 0.041181087493896484
2023-01-23 01:36:29.961687: step: 1928/530, loss: 0.4977661967277527
2023-01-23 01:36:31.149284: step: 1932/530, loss: 0.6903577446937561
2023-01-23 01:36:32.318301: step: 1936/530, loss: 0.016359902918338776
2023-01-23 01:36:33.490938: step: 1940/530, loss: 0.031145095825195312
2023-01-23 01:36:34.674776: step: 1944/530, loss: 0.019084835425019264
2023-01-23 01:36:35.903214: step: 1948/530, loss: 0.007791615091264248
2023-01-23 01:36:37.097805: step: 1952/530, loss: 0.093549445271492
2023-01-23 01:36:38.288062: step: 1956/530, loss: 0.08363190293312073
2023-01-23 01:36:39.464731: step: 1960/530, loss: 0.05023627355694771
2023-01-23 01:36:40.610230: step: 1964/530, loss: 0.02221975289285183
2023-01-23 01:36:41.791869: step: 1968/530, loss: 0.0067608836106956005
2023-01-23 01:36:42.971798: step: 1972/530, loss: 0.02654724195599556
2023-01-23 01:36:44.122935: step: 1976/530, loss: 0.04441361501812935
2023-01-23 01:36:45.274646: step: 1980/530, loss: 0.03865647315979004
2023-01-23 01:36:46.445435: step: 1984/530, loss: 0.09422292560338974
2023-01-23 01:36:47.622751: step: 1988/530, loss: 0.20209617912769318
2023-01-23 01:36:48.785877: step: 1992/530, loss: 0.05284881591796875
2023-01-23 01:36:49.950433: step: 1996/530, loss: 0.11346082389354706
2023-01-23 01:36:51.112359: step: 2000/530, loss: 1.0265063047409058
2023-01-23 01:36:52.289069: step: 2004/530, loss: 0.1546923667192459
2023-01-23 01:36:53.494809: step: 2008/530, loss: 0.010292625986039639
2023-01-23 01:36:54.727946: step: 2012/530, loss: 0.030474377796053886
2023-01-23 01:36:55.870089: step: 2016/530, loss: 0.050510697066783905
2023-01-23 01:36:57.055253: step: 2020/530, loss: 0.011582328006625175
2023-01-23 01:36:58.221261: step: 2024/530, loss: 0.01223988551646471
2023-01-23 01:36:59.393661: step: 2028/530, loss: 0.019549179822206497
2023-01-23 01:37:00.558264: step: 2032/530, loss: 0.06044311821460724
2023-01-23 01:37:01.758828: step: 2036/530, loss: 0.0010472774738445878
2023-01-23 01:37:02.941234: step: 2040/530, loss: 0.06650523841381073
2023-01-23 01:37:04.069826: step: 2044/530, loss: 0.0215531587600708
2023-01-23 01:37:05.278880: step: 2048/530, loss: 0.013756370171904564
2023-01-23 01:37:06.474114: step: 2052/530, loss: 0.2573811411857605
2023-01-23 01:37:07.679771: step: 2056/530, loss: 0.08275695145130157
2023-01-23 01:37:08.855693: step: 2060/530, loss: 0.023038674145936966
2023-01-23 01:37:10.024281: step: 2064/530, loss: 0.011835267767310143
2023-01-23 01:37:11.195032: step: 2068/530, loss: 0.058629799634218216
2023-01-23 01:37:12.334199: step: 2072/530, loss: 0.06076188012957573
2023-01-23 01:37:13.543322: step: 2076/530, loss: 0.08940734714269638
2023-01-23 01:37:14.738390: step: 2080/530, loss: 0.15059271454811096
2023-01-23 01:37:15.874874: step: 2084/530, loss: 0.060669708997011185
2023-01-23 01:37:17.066125: step: 2088/530, loss: 0.032352544367313385
2023-01-23 01:37:18.236542: step: 2092/530, loss: 0.04268999397754669
2023-01-23 01:37:19.389829: step: 2096/530, loss: 0.0324406661093235
2023-01-23 01:37:20.565266: step: 2100/530, loss: 0.013764763250946999
2023-01-23 01:37:21.719860: step: 2104/530, loss: 0.060739897191524506
2023-01-23 01:37:22.858740: step: 2108/530, loss: 0.05356001853942871
2023-01-23 01:37:24.016974: step: 2112/530, loss: 0.025655508041381836
2023-01-23 01:37:25.164933: step: 2116/530, loss: 0.08313503861427307
2023-01-23 01:37:26.350369: step: 2120/530, loss: 0.03332100063562393
==================================================
Loss: 0.071
--------------------
Dev: {'event': {'p': 0.5696078431372549, 'r': 0.7736351531291611, 'f1': 0.6561264822134386}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 11}
Test: {'event': {'p': 0.6341030195381883, 'r': 0.821161587119034, 'f1': 0.7156101227762465}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 11}
Chinese: {'event': {'p': 0.5609756097560976, 'r': 0.8518518518518519, 'f1': 0.6764705882352942}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 11}
Korean: {'event': {'p': 0.6440677966101694, 'r': 0.6031746031746031, 'f1': 0.6229508196721311}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 11}
Russian: {'event': {'p': 0.40816326530612246, 'r': 0.5555555555555556, 'f1': 0.47058823529411764}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 11}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6351501668520578, 'r': 0.7603195739014648, 'f1': 0.6921212121212121}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Chinese: {'event': {'p': 0.6373175182481752, 'r': 0.8033352501437608, 'f1': 0.7107606207071993}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Chinese: {'event': {'p': 0.5903614457831325, 'r': 0.9074074074074074, 'f1': 0.7153284671532847}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5733990147783251, 'r': 0.7749667110519307, 'f1': 0.6591166477916196}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Eng Test for Korean: {'event': {'p': 0.6218005295675199, 'r': 0.8102357676825762, 'f1': 0.7036204744069912}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Sample Korean: {'event': {'p': 0.6417910447761194, 'r': 0.6825396825396826, 'f1': 0.6615384615384614}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5951882845188284, 'r': 0.7576564580559254, 'f1': 0.6666666666666666}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6663405088062623, 'r': 0.7832087406555491, 'f1': 0.7200634417129264}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5, 'r': 0.6666666666666666, 'f1': 0.5714285714285715}, '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 01:38:09.502032: step: 4/530, loss: 0.024462318047881126
2023-01-23 01:38:10.677404: step: 8/530, loss: 0.03063955530524254
2023-01-23 01:38:11.852092: step: 12/530, loss: 0.059737205505371094
2023-01-23 01:38:12.992889: step: 16/530, loss: 0.0403805747628212
2023-01-23 01:38:14.160557: step: 20/530, loss: 0.06500382721424103
2023-01-23 01:38:15.324084: step: 24/530, loss: 0.04639950022101402
2023-01-23 01:38:16.474280: step: 28/530, loss: 0.019774341955780983
2023-01-23 01:38:17.629016: step: 32/530, loss: 0.0008297919994220138
2023-01-23 01:38:18.792315: step: 36/530, loss: 0.05206584930419922
2023-01-23 01:38:19.969287: step: 40/530, loss: 0.04238710552453995
2023-01-23 01:38:21.128749: step: 44/530, loss: 0.0064720152877271175
2023-01-23 01:38:22.277832: step: 48/530, loss: 0.013050651177763939
2023-01-23 01:38:23.471621: step: 52/530, loss: 0.0268115047365427
2023-01-23 01:38:24.633957: step: 56/530, loss: 0.07062749564647675
2023-01-23 01:38:25.797466: step: 60/530, loss: 0.011003971099853516
2023-01-23 01:38:26.948447: step: 64/530, loss: 0.04203391075134277
2023-01-23 01:38:28.137181: step: 68/530, loss: 0.06764745712280273
2023-01-23 01:38:29.317577: step: 72/530, loss: 0.005010748282074928
2023-01-23 01:38:30.475111: step: 76/530, loss: 0.0831761360168457
2023-01-23 01:38:31.659880: step: 80/530, loss: 0.03619890287518501
2023-01-23 01:38:32.815915: step: 84/530, loss: 0.2614557147026062
2023-01-23 01:38:34.030139: step: 88/530, loss: 0.1391127109527588
2023-01-23 01:38:35.174198: step: 92/530, loss: 0.19704437255859375
2023-01-23 01:38:36.382437: step: 96/530, loss: 0.06112007796764374
2023-01-23 01:38:37.555734: step: 100/530, loss: 0.013515233993530273
2023-01-23 01:38:38.739321: step: 104/530, loss: 0.008998489938676357
2023-01-23 01:38:39.904896: step: 108/530, loss: 0.03343706205487251
2023-01-23 01:38:41.057320: step: 112/530, loss: 0.045110419392585754
2023-01-23 01:38:42.247762: step: 116/530, loss: 0.03110809437930584
2023-01-23 01:38:43.437537: step: 120/530, loss: 0.045696452260017395
2023-01-23 01:38:44.619657: step: 124/530, loss: 0.01875128783285618
2023-01-23 01:38:45.831614: step: 128/530, loss: 0.10756778717041016
2023-01-23 01:38:47.042131: step: 132/530, loss: 0.03836381435394287
2023-01-23 01:38:48.217285: step: 136/530, loss: 0.013095664791762829
2023-01-23 01:38:49.381581: step: 140/530, loss: 0.022331714630126953
2023-01-23 01:38:50.537769: step: 144/530, loss: 0.09740018844604492
2023-01-23 01:38:51.706919: step: 148/530, loss: 0.04224729537963867
2023-01-23 01:38:52.867630: step: 152/530, loss: 0.04394712671637535
2023-01-23 01:38:54.076560: step: 156/530, loss: 0.010960674844682217
2023-01-23 01:38:55.229941: step: 160/530, loss: 0.019486237317323685
2023-01-23 01:38:56.380830: step: 164/530, loss: 0.0024688243865966797
2023-01-23 01:38:57.543129: step: 168/530, loss: 0.12375736236572266
2023-01-23 01:38:58.714395: step: 172/530, loss: 0.3049488067626953
2023-01-23 01:38:59.906211: step: 176/530, loss: 0.034240055829286575
2023-01-23 01:39:01.106463: step: 180/530, loss: 0.0414159782230854
2023-01-23 01:39:02.285689: step: 184/530, loss: 0.004829215817153454
2023-01-23 01:39:03.481640: step: 188/530, loss: 0.024098610505461693
2023-01-23 01:39:04.663096: step: 192/530, loss: 0.003087806748226285
2023-01-23 01:39:05.840120: step: 196/530, loss: 0.00571055430918932
2023-01-23 01:39:06.981523: step: 200/530, loss: 0.1995992660522461
2023-01-23 01:39:08.137971: step: 204/530, loss: 0.00910644605755806
2023-01-23 01:39:09.286366: step: 208/530, loss: 0.01604452170431614
2023-01-23 01:39:10.420441: step: 212/530, loss: 0.008992671966552734
2023-01-23 01:39:11.639603: step: 216/530, loss: 0.002522754715755582
2023-01-23 01:39:12.840500: step: 220/530, loss: 0.008598709478974342
2023-01-23 01:39:14.029054: step: 224/530, loss: 0.003578758332878351
2023-01-23 01:39:15.183472: step: 228/530, loss: 0.4370637834072113
2023-01-23 01:39:16.352895: step: 232/530, loss: 0.042026713490486145
2023-01-23 01:39:17.508656: step: 236/530, loss: 0.010769224725663662
2023-01-23 01:39:18.680485: step: 240/530, loss: 0.21128864586353302
2023-01-23 01:39:19.862139: step: 244/530, loss: 0.03635769337415695
2023-01-23 01:39:21.069548: step: 248/530, loss: 0.43219661712646484
2023-01-23 01:39:22.247435: step: 252/530, loss: 0.017505455762147903
2023-01-23 01:39:23.433016: step: 256/530, loss: 0.10922101140022278
2023-01-23 01:39:24.619349: step: 260/530, loss: 0.12193422019481659
2023-01-23 01:39:25.770530: step: 264/530, loss: 0.01462103147059679
2023-01-23 01:39:26.993700: step: 268/530, loss: 0.0011726856464520097
2023-01-23 01:39:28.147262: step: 272/530, loss: 0.028221370652318
2023-01-23 01:39:29.337516: step: 276/530, loss: 0.06637678295373917
2023-01-23 01:39:30.508172: step: 280/530, loss: 0.030428696423768997
2023-01-23 01:39:31.679625: step: 284/530, loss: 0.0801229476928711
2023-01-23 01:39:32.826949: step: 288/530, loss: 0.06152982637286186
2023-01-23 01:39:33.982116: step: 292/530, loss: 0.0646093338727951
2023-01-23 01:39:35.113594: step: 296/530, loss: 0.20765258371829987
2023-01-23 01:39:36.251169: step: 300/530, loss: 0.0019983293022960424
2023-01-23 01:39:37.443331: step: 304/530, loss: 0.10155663639307022
2023-01-23 01:39:38.653974: step: 308/530, loss: 0.04324297979474068
2023-01-23 01:39:39.815943: step: 312/530, loss: 0.06972108036279678
2023-01-23 01:39:40.982209: step: 316/530, loss: 0.002707576612010598
2023-01-23 01:39:42.137896: step: 320/530, loss: 0.00304832449182868
2023-01-23 01:39:43.309752: step: 324/530, loss: 0.051827143877744675
2023-01-23 01:39:44.480080: step: 328/530, loss: 0.001095676445402205
2023-01-23 01:39:45.657574: step: 332/530, loss: 0.0332825668156147
2023-01-23 01:39:46.839160: step: 336/530, loss: 0.2149837464094162
2023-01-23 01:39:47.976056: step: 340/530, loss: 0.011190223507583141
2023-01-23 01:39:49.118572: step: 344/530, loss: 0.03393860533833504
2023-01-23 01:39:50.270562: step: 348/530, loss: 0.0016100406646728516
2023-01-23 01:39:51.429629: step: 352/530, loss: 0.06353874504566193
2023-01-23 01:39:52.576135: step: 356/530, loss: 0.1105077788233757
2023-01-23 01:39:53.716637: step: 360/530, loss: 0.07435036450624466
2023-01-23 01:39:54.905958: step: 364/530, loss: 0.1421651989221573
2023-01-23 01:39:56.120276: step: 368/530, loss: 0.04711031913757324
2023-01-23 01:39:57.313305: step: 372/530, loss: 0.07570686936378479
2023-01-23 01:39:58.545410: step: 376/530, loss: 0.02117910422384739
2023-01-23 01:39:59.698544: step: 380/530, loss: 0.042621612548828125
2023-01-23 01:40:00.870132: step: 384/530, loss: 0.016769981011748314
2023-01-23 01:40:02.088896: step: 388/530, loss: 0.020130634307861328
2023-01-23 01:40:03.282338: step: 392/530, loss: 0.05519914627075195
2023-01-23 01:40:04.461532: step: 396/530, loss: 0.009591380134224892
2023-01-23 01:40:05.659208: step: 400/530, loss: 0.007009029854089022
2023-01-23 01:40:06.840960: step: 404/530, loss: 0.012728119269013405
2023-01-23 01:40:08.000010: step: 408/530, loss: 0.28795239329338074
2023-01-23 01:40:09.169130: step: 412/530, loss: 0.11612376570701599
2023-01-23 01:40:10.367926: step: 416/530, loss: 0.019542407244443893
2023-01-23 01:40:11.540286: step: 420/530, loss: 0.038088224828243256
2023-01-23 01:40:12.677435: step: 424/530, loss: 0.05726051330566406
2023-01-23 01:40:13.830944: step: 428/530, loss: 0.08280525356531143
2023-01-23 01:40:15.063529: step: 432/530, loss: 0.005053329281508923
2023-01-23 01:40:16.264456: step: 436/530, loss: 0.021277904510498047
2023-01-23 01:40:17.488346: step: 440/530, loss: 0.022490881383419037
2023-01-23 01:40:18.735536: step: 444/530, loss: 0.034426119178533554
2023-01-23 01:40:19.931635: step: 448/530, loss: 0.057691000401973724
2023-01-23 01:40:21.056311: step: 452/530, loss: 0.006224251352250576
2023-01-23 01:40:22.217104: step: 456/530, loss: 0.02741699293255806
2023-01-23 01:40:23.404320: step: 460/530, loss: 0.022504711523652077
2023-01-23 01:40:24.573641: step: 464/530, loss: 0.07245273888111115
2023-01-23 01:40:25.721596: step: 468/530, loss: 0.02529410645365715
2023-01-23 01:40:26.948312: step: 472/530, loss: 0.11218996345996857
2023-01-23 01:40:28.177364: step: 476/530, loss: 0.026621198281645775
2023-01-23 01:40:29.300248: step: 480/530, loss: 0.05628928542137146
2023-01-23 01:40:30.518507: step: 484/530, loss: 0.037410296499729156
2023-01-23 01:40:31.673087: step: 488/530, loss: 0.02455887757241726
2023-01-23 01:40:32.859344: step: 492/530, loss: 0.016309548169374466
2023-01-23 01:40:34.059353: step: 496/530, loss: 0.020999910309910774
2023-01-23 01:40:35.253711: step: 500/530, loss: 0.03327415883541107
2023-01-23 01:40:36.417281: step: 504/530, loss: 0.003995752427726984
2023-01-23 01:40:37.582737: step: 508/530, loss: 0.026255905628204346
2023-01-23 01:40:38.796177: step: 512/530, loss: 0.016110897064208984
2023-01-23 01:40:40.019201: step: 516/530, loss: 0.0024173737037926912
2023-01-23 01:40:41.171264: step: 520/530, loss: 0.04227790981531143
2023-01-23 01:40:42.353381: step: 524/530, loss: 0.1289207488298416
2023-01-23 01:40:43.528200: step: 528/530, loss: 0.008456182666122913
2023-01-23 01:40:44.711651: step: 532/530, loss: 0.027797795832157135
2023-01-23 01:40:45.889957: step: 536/530, loss: 0.3915892541408539
2023-01-23 01:40:47.106869: step: 540/530, loss: 0.05391325801610947
2023-01-23 01:40:48.275876: step: 544/530, loss: 0.03055262565612793
2023-01-23 01:40:49.428815: step: 548/530, loss: 0.034409474581480026
2023-01-23 01:40:50.615527: step: 552/530, loss: 0.05485954508185387
2023-01-23 01:40:51.788106: step: 556/530, loss: 0.004934406373649836
2023-01-23 01:40:52.989066: step: 560/530, loss: 0.020502185449004173
2023-01-23 01:40:54.163266: step: 564/530, loss: 0.0009262085077352822
2023-01-23 01:40:55.303994: step: 568/530, loss: 0.024689245969057083
2023-01-23 01:40:56.475184: step: 572/530, loss: 0.0005736351013183594
2023-01-23 01:40:57.651095: step: 576/530, loss: 0.0663721114397049
2023-01-23 01:40:58.852285: step: 580/530, loss: 0.035083651542663574
2023-01-23 01:41:00.009826: step: 584/530, loss: 0.12485088407993317
2023-01-23 01:41:01.246264: step: 588/530, loss: 0.036413952708244324
2023-01-23 01:41:02.403632: step: 592/530, loss: 0.06369476020336151
2023-01-23 01:41:03.608967: step: 596/530, loss: 0.4337177276611328
2023-01-23 01:41:04.771787: step: 600/530, loss: 0.03700428083539009
2023-01-23 01:41:05.918062: step: 604/530, loss: 0.0948781967163086
2023-01-23 01:41:07.081904: step: 608/530, loss: 0.040070436894893646
2023-01-23 01:41:08.236718: step: 612/530, loss: 0.01448822021484375
2023-01-23 01:41:09.406901: step: 616/530, loss: 0.09405727684497833
2023-01-23 01:41:10.576940: step: 620/530, loss: 0.07676973193883896
2023-01-23 01:41:11.736803: step: 624/530, loss: 0.03575315326452255
2023-01-23 01:41:12.926932: step: 628/530, loss: 0.01336002442985773
2023-01-23 01:41:14.113411: step: 632/530, loss: 0.09158401191234589
2023-01-23 01:41:15.305072: step: 636/530, loss: 0.1506001502275467
2023-01-23 01:41:16.494618: step: 640/530, loss: 0.00036334991455078125
2023-01-23 01:41:17.678662: step: 644/530, loss: 0.017335128039121628
2023-01-23 01:41:18.887790: step: 648/530, loss: 0.07724962383508682
2023-01-23 01:41:20.113332: step: 652/530, loss: 0.03686952590942383
2023-01-23 01:41:21.257857: step: 656/530, loss: 0.007498836610466242
2023-01-23 01:41:22.395422: step: 660/530, loss: 0.0023681640159338713
2023-01-23 01:41:23.564014: step: 664/530, loss: 0.09923629462718964
2023-01-23 01:41:24.778050: step: 668/530, loss: 0.1940900832414627
2023-01-23 01:41:25.922725: step: 672/530, loss: 0.3107105791568756
2023-01-23 01:41:27.125642: step: 676/530, loss: 0.040271710604429245
2023-01-23 01:41:28.288779: step: 680/530, loss: 0.07214327156543732
2023-01-23 01:41:29.482924: step: 684/530, loss: 0.05121020972728729
2023-01-23 01:41:30.697489: step: 688/530, loss: 0.16968250274658203
2023-01-23 01:41:31.864255: step: 692/530, loss: 0.03649099916219711
2023-01-23 01:41:33.013567: step: 696/530, loss: 0.014024162665009499
2023-01-23 01:41:34.184105: step: 700/530, loss: 0.08287516236305237
2023-01-23 01:41:35.351377: step: 704/530, loss: 0.08042984455823898
2023-01-23 01:41:36.489755: step: 708/530, loss: 0.017436029389500618
2023-01-23 01:41:37.647127: step: 712/530, loss: 0.04657535254955292
2023-01-23 01:41:38.864662: step: 716/530, loss: 0.007133293431252241
2023-01-23 01:41:40.055178: step: 720/530, loss: 0.09057764708995819
2023-01-23 01:41:41.184429: step: 724/530, loss: 0.38073357939720154
2023-01-23 01:41:42.321151: step: 728/530, loss: 0.027993202209472656
2023-01-23 01:41:43.542387: step: 732/530, loss: 0.01594400405883789
2023-01-23 01:41:44.718247: step: 736/530, loss: 0.08512210845947266
2023-01-23 01:41:45.874692: step: 740/530, loss: 0.08581963181495667
2023-01-23 01:41:47.037505: step: 744/530, loss: 0.011951255612075329
2023-01-23 01:41:48.177938: step: 748/530, loss: 0.025553178042173386
2023-01-23 01:41:49.314531: step: 752/530, loss: 0.015233802609145641
2023-01-23 01:41:50.495124: step: 756/530, loss: 0.14278145134449005
2023-01-23 01:41:51.644901: step: 760/530, loss: 0.02860584296286106
2023-01-23 01:41:52.852016: step: 764/530, loss: 0.031369470059871674
2023-01-23 01:41:54.053243: step: 768/530, loss: 0.006991863716393709
2023-01-23 01:41:55.237156: step: 772/530, loss: 0.03998298943042755
2023-01-23 01:41:56.409898: step: 776/530, loss: 0.09617214649915695
2023-01-23 01:41:57.564981: step: 780/530, loss: 0.022068094462156296
2023-01-23 01:41:58.733293: step: 784/530, loss: 0.03673537075519562
2023-01-23 01:41:59.949001: step: 788/530, loss: 0.05624890327453613
2023-01-23 01:42:01.131979: step: 792/530, loss: 0.09052152931690216
2023-01-23 01:42:02.317186: step: 796/530, loss: 0.028404809534549713
2023-01-23 01:42:03.506603: step: 800/530, loss: 0.02178099751472473
2023-01-23 01:42:04.697339: step: 804/530, loss: 0.08674298226833344
2023-01-23 01:42:05.828907: step: 808/530, loss: 0.028924845159053802
2023-01-23 01:42:06.992259: step: 812/530, loss: 0.016021061688661575
2023-01-23 01:42:08.152490: step: 816/530, loss: 0.010581493377685547
2023-01-23 01:42:09.333107: step: 820/530, loss: 0.0057665822096168995
2023-01-23 01:42:10.486726: step: 824/530, loss: 0.0019457817543298006
2023-01-23 01:42:11.631706: step: 828/530, loss: 0.025056075304746628
2023-01-23 01:42:12.811592: step: 832/530, loss: 0.01484451349824667
2023-01-23 01:42:13.967294: step: 836/530, loss: 0.01619718223810196
2023-01-23 01:42:15.143139: step: 840/530, loss: 0.6925919055938721
2023-01-23 01:42:16.300940: step: 844/530, loss: 0.022851943969726562
2023-01-23 01:42:17.435978: step: 848/530, loss: 0.025740433484315872
2023-01-23 01:42:18.593633: step: 852/530, loss: 0.02863183058798313
2023-01-23 01:42:19.779112: step: 856/530, loss: 0.04468078538775444
2023-01-23 01:42:20.938100: step: 860/530, loss: 0.6452530026435852
2023-01-23 01:42:22.092594: step: 864/530, loss: 0.10894642025232315
2023-01-23 01:42:23.242869: step: 868/530, loss: 0.03668703883886337
2023-01-23 01:42:24.479840: step: 872/530, loss: 0.019786452874541283
2023-01-23 01:42:25.638498: step: 876/530, loss: 0.178480327129364
2023-01-23 01:42:26.800598: step: 880/530, loss: 0.041542910039424896
2023-01-23 01:42:27.985930: step: 884/530, loss: 0.06218691170215607
2023-01-23 01:42:29.161889: step: 888/530, loss: 0.13452640175819397
2023-01-23 01:42:30.324207: step: 892/530, loss: 0.00818262156099081
2023-01-23 01:42:31.460874: step: 896/530, loss: 0.0510527640581131
2023-01-23 01:42:32.632207: step: 900/530, loss: 0.015603447332978249
2023-01-23 01:42:33.786007: step: 904/530, loss: 0.01901698112487793
2023-01-23 01:42:34.916403: step: 908/530, loss: 0.025200653821229935
2023-01-23 01:42:36.122511: step: 912/530, loss: 0.21242503821849823
2023-01-23 01:42:37.265391: step: 916/530, loss: 0.09054295718669891
2023-01-23 01:42:38.481316: step: 920/530, loss: 0.02290968969464302
2023-01-23 01:42:39.635567: step: 924/530, loss: 0.006038284860551357
2023-01-23 01:42:40.828159: step: 928/530, loss: 0.03223858028650284
2023-01-23 01:42:42.031813: step: 932/530, loss: 0.01874389685690403
2023-01-23 01:42:43.192475: step: 936/530, loss: 0.01884441450238228
2023-01-23 01:42:44.361598: step: 940/530, loss: 0.1289457380771637
2023-01-23 01:42:45.534268: step: 944/530, loss: 0.027230119332671165
2023-01-23 01:42:46.687194: step: 948/530, loss: 0.01578826829791069
2023-01-23 01:42:47.843023: step: 952/530, loss: 0.03889884799718857
2023-01-23 01:42:49.034119: step: 956/530, loss: 0.0486997589468956
2023-01-23 01:42:50.183449: step: 960/530, loss: 0.015480756759643555
2023-01-23 01:42:51.319502: step: 964/530, loss: 0.030515480786561966
2023-01-23 01:42:52.503912: step: 968/530, loss: 0.01985769346356392
2023-01-23 01:42:53.667030: step: 972/530, loss: 0.010434722527861595
2023-01-23 01:42:54.811059: step: 976/530, loss: 0.03141918033361435
2023-01-23 01:42:55.972068: step: 980/530, loss: 0.11138935387134552
2023-01-23 01:42:57.156565: step: 984/530, loss: 0.09267683327198029
2023-01-23 01:42:58.371638: step: 988/530, loss: 0.1321854591369629
2023-01-23 01:42:59.520636: step: 992/530, loss: 0.03175229951739311
2023-01-23 01:43:00.652538: step: 996/530, loss: 0.0025769234634935856
2023-01-23 01:43:01.842175: step: 1000/530, loss: 0.044530682265758514
2023-01-23 01:43:03.028630: step: 1004/530, loss: 0.06598120182752609
2023-01-23 01:43:04.190073: step: 1008/530, loss: 0.04920005798339844
2023-01-23 01:43:05.350579: step: 1012/530, loss: 0.11480160057544708
2023-01-23 01:43:06.521668: step: 1016/530, loss: 0.059511661529541016
2023-01-23 01:43:07.705570: step: 1020/530, loss: 0.05797595903277397
2023-01-23 01:43:08.837636: step: 1024/530, loss: 0.3179432153701782
2023-01-23 01:43:10.017116: step: 1028/530, loss: 0.0350956916809082
2023-01-23 01:43:11.229047: step: 1032/530, loss: 0.05184021592140198
2023-01-23 01:43:12.401167: step: 1036/530, loss: 0.6203622221946716
2023-01-23 01:43:13.576921: step: 1040/530, loss: 0.027121830731630325
2023-01-23 01:43:14.761883: step: 1044/530, loss: 0.028993798419833183
2023-01-23 01:43:15.941469: step: 1048/530, loss: 0.009817314334213734
2023-01-23 01:43:17.153783: step: 1052/530, loss: 0.007053375244140625
2023-01-23 01:43:18.308007: step: 1056/530, loss: 0.0008881569374352694
2023-01-23 01:43:19.493123: step: 1060/530, loss: 0.00042247772216796875
2023-01-23 01:43:20.663613: step: 1064/530, loss: 0.026148509234189987
2023-01-23 01:43:21.819024: step: 1068/530, loss: 0.03257717937231064
2023-01-23 01:43:22.994417: step: 1072/530, loss: 0.028539754450321198
2023-01-23 01:43:24.179832: step: 1076/530, loss: 0.029815007001161575
2023-01-23 01:43:25.366055: step: 1080/530, loss: 0.042229365557432175
2023-01-23 01:43:26.550985: step: 1084/530, loss: 0.021835900843143463
2023-01-23 01:43:27.729680: step: 1088/530, loss: 0.022199153900146484
2023-01-23 01:43:28.984942: step: 1092/530, loss: 0.059502504765987396
2023-01-23 01:43:30.114687: step: 1096/530, loss: 0.013970565982162952
2023-01-23 01:43:31.292987: step: 1100/530, loss: 0.037641432136297226
2023-01-23 01:43:32.445097: step: 1104/530, loss: 0.02053070068359375
2023-01-23 01:43:33.654387: step: 1108/530, loss: 0.06871071457862854
2023-01-23 01:43:34.828160: step: 1112/530, loss: 0.028432369232177734
2023-01-23 01:43:35.993790: step: 1116/530, loss: 0.0015053749084472656
2023-01-23 01:43:37.192974: step: 1120/530, loss: 0.03856716305017471
2023-01-23 01:43:38.341745: step: 1124/530, loss: 0.3286478817462921
2023-01-23 01:43:39.518420: step: 1128/530, loss: 0.09284524619579315
2023-01-23 01:43:40.682681: step: 1132/530, loss: 0.1529906690120697
2023-01-23 01:43:41.920217: step: 1136/530, loss: 0.05006694793701172
2023-01-23 01:43:43.104489: step: 1140/530, loss: 0.03011941909790039
2023-01-23 01:43:44.271474: step: 1144/530, loss: 0.027724076062440872
2023-01-23 01:43:45.448879: step: 1148/530, loss: 0.010067653842270374
2023-01-23 01:43:46.634083: step: 1152/530, loss: 0.08774032443761826
2023-01-23 01:43:47.802598: step: 1156/530, loss: 0.014690971933305264
2023-01-23 01:43:48.970240: step: 1160/530, loss: 0.04390373453497887
2023-01-23 01:43:50.116352: step: 1164/530, loss: 0.014396476559340954
2023-01-23 01:43:51.295419: step: 1168/530, loss: 0.0015263557434082031
2023-01-23 01:43:52.457936: step: 1172/530, loss: 0.3092660903930664
2023-01-23 01:43:53.601815: step: 1176/530, loss: 0.07040061801671982
2023-01-23 01:43:54.756147: step: 1180/530, loss: 0.06930504739284515
2023-01-23 01:43:55.961039: step: 1184/530, loss: 0.12530136108398438
2023-01-23 01:43:57.142027: step: 1188/530, loss: 0.02728099748492241
2023-01-23 01:43:58.377294: step: 1192/530, loss: 0.023624612018465996
2023-01-23 01:43:59.560716: step: 1196/530, loss: 0.011436653323471546
2023-01-23 01:44:00.752563: step: 1200/530, loss: 0.13145150244235992
2023-01-23 01:44:01.962943: step: 1204/530, loss: 0.027723979204893112
2023-01-23 01:44:03.129299: step: 1208/530, loss: 0.03562593460083008
2023-01-23 01:44:04.320113: step: 1212/530, loss: 0.03561554104089737
2023-01-23 01:44:05.536492: step: 1216/530, loss: 0.14709243178367615
2023-01-23 01:44:06.677515: step: 1220/530, loss: 0.018868446350097656
2023-01-23 01:44:07.850296: step: 1224/530, loss: 0.12849688529968262
2023-01-23 01:44:08.938809: step: 1228/530, loss: 0.24895787239074707
2023-01-23 01:44:10.115703: step: 1232/530, loss: 0.057883549481630325
2023-01-23 01:44:11.263846: step: 1236/530, loss: 0.01187057513743639
2023-01-23 01:44:12.486634: step: 1240/530, loss: 0.08269357681274414
2023-01-23 01:44:13.655816: step: 1244/530, loss: 0.13768616318702698
2023-01-23 01:44:14.797672: step: 1248/530, loss: 0.058997154235839844
2023-01-23 01:44:15.918864: step: 1252/530, loss: 0.006998920813202858
2023-01-23 01:44:17.091278: step: 1256/530, loss: 0.0534726157784462
2023-01-23 01:44:18.268930: step: 1260/530, loss: 0.06270293891429901
2023-01-23 01:44:19.486190: step: 1264/530, loss: 0.03356628492474556
2023-01-23 01:44:20.663472: step: 1268/530, loss: 0.04385986551642418
2023-01-23 01:44:21.859807: step: 1272/530, loss: 0.04401206970214844
2023-01-23 01:44:23.036370: step: 1276/530, loss: 0.05171527713537216
2023-01-23 01:44:24.226058: step: 1280/530, loss: 0.0045986175537109375
2023-01-23 01:44:25.381946: step: 1284/530, loss: 0.11496009677648544
2023-01-23 01:44:26.581845: step: 1288/530, loss: 0.49679192900657654
2023-01-23 01:44:27.786439: step: 1292/530, loss: 0.053171444684267044
2023-01-23 01:44:28.915902: step: 1296/530, loss: 0.0331995002925396
2023-01-23 01:44:30.096395: step: 1300/530, loss: 0.04196282476186752
2023-01-23 01:44:31.265723: step: 1304/530, loss: 0.046031951904296875
2023-01-23 01:44:32.444307: step: 1308/530, loss: 0.05271158367395401
2023-01-23 01:44:33.566603: step: 1312/530, loss: 0.014488077722489834
2023-01-23 01:44:34.742703: step: 1316/530, loss: 0.12147287279367447
2023-01-23 01:44:35.888764: step: 1320/530, loss: 0.015043068677186966
2023-01-23 01:44:37.088377: step: 1324/530, loss: 0.007552719675004482
2023-01-23 01:44:38.257093: step: 1328/530, loss: 0.0784931629896164
2023-01-23 01:44:39.434764: step: 1332/530, loss: 0.03740081936120987
2023-01-23 01:44:40.634099: step: 1336/530, loss: 0.08213372528553009
2023-01-23 01:44:41.811392: step: 1340/530, loss: 0.0034474849235266447
2023-01-23 01:44:42.971120: step: 1344/530, loss: 0.023669052869081497
2023-01-23 01:44:44.141211: step: 1348/530, loss: 0.02259860187768936
2023-01-23 01:44:45.291248: step: 1352/530, loss: 0.0017702102195471525
2023-01-23 01:44:46.496395: step: 1356/530, loss: 0.01809997484087944
2023-01-23 01:44:47.639701: step: 1360/530, loss: 0.009166574105620384
2023-01-23 01:44:48.832850: step: 1364/530, loss: 0.0018199920887127519
2023-01-23 01:44:50.015953: step: 1368/530, loss: 0.036254025995731354
2023-01-23 01:44:51.165148: step: 1372/530, loss: 0.14995098114013672
2023-01-23 01:44:52.330689: step: 1376/530, loss: 0.049860481172800064
2023-01-23 01:44:53.510630: step: 1380/530, loss: 0.09892406314611435
2023-01-23 01:44:54.709426: step: 1384/530, loss: 0.051728107035160065
2023-01-23 01:44:55.879347: step: 1388/530, loss: 0.03571796417236328
2023-01-23 01:44:57.109806: step: 1392/530, loss: 0.01592540740966797
2023-01-23 01:44:58.289483: step: 1396/530, loss: 0.10455093532800674
2023-01-23 01:44:59.471277: step: 1400/530, loss: 0.0336456298828125
2023-01-23 01:45:00.682244: step: 1404/530, loss: 0.00734257698059082
2023-01-23 01:45:01.801672: step: 1408/530, loss: 0.0019296170212328434
2023-01-23 01:45:03.002395: step: 1412/530, loss: 0.04238548129796982
2023-01-23 01:45:04.170070: step: 1416/530, loss: 0.01978015899658203
2023-01-23 01:45:05.353948: step: 1420/530, loss: 0.003333187196403742
2023-01-23 01:45:06.516679: step: 1424/530, loss: 0.032706644386053085
2023-01-23 01:45:07.680682: step: 1428/530, loss: 0.03811168670654297
2023-01-23 01:45:08.873612: step: 1432/530, loss: 0.04100990295410156
2023-01-23 01:45:10.050839: step: 1436/530, loss: 0.04443030431866646
2023-01-23 01:45:11.242306: step: 1440/530, loss: 0.11495628952980042
2023-01-23 01:45:12.416646: step: 1444/530, loss: 0.06092806160449982
2023-01-23 01:45:13.651587: step: 1448/530, loss: 0.005843162536621094
2023-01-23 01:45:14.835773: step: 1452/530, loss: 0.01743488386273384
2023-01-23 01:45:16.044767: step: 1456/530, loss: 0.01626911200582981
2023-01-23 01:45:17.199633: step: 1460/530, loss: 0.0010963440872728825
2023-01-23 01:45:18.327756: step: 1464/530, loss: 0.12800416350364685
2023-01-23 01:45:19.489655: step: 1468/530, loss: 0.1337384283542633
2023-01-23 01:45:20.657984: step: 1472/530, loss: 0.08809986710548401
2023-01-23 01:45:21.821333: step: 1476/530, loss: 0.009561014361679554
2023-01-23 01:45:22.992157: step: 1480/530, loss: 0.008875560946762562
2023-01-23 01:45:24.223274: step: 1484/530, loss: 0.05440826714038849
2023-01-23 01:45:25.393731: step: 1488/530, loss: 0.006898260209709406
2023-01-23 01:45:26.529335: step: 1492/530, loss: 0.0025392533279955387
2023-01-23 01:45:27.696936: step: 1496/530, loss: 0.04414825513958931
2023-01-23 01:45:28.880214: step: 1500/530, loss: 0.06434217095375061
2023-01-23 01:45:30.023427: step: 1504/530, loss: 0.0708681121468544
2023-01-23 01:45:31.195404: step: 1508/530, loss: 0.010440731421113014
2023-01-23 01:45:32.353372: step: 1512/530, loss: 0.020683003589510918
2023-01-23 01:45:33.506287: step: 1516/530, loss: 0.042055319994688034
2023-01-23 01:45:34.666874: step: 1520/530, loss: 0.002170658204704523
2023-01-23 01:45:35.840275: step: 1524/530, loss: 0.007885932922363281
2023-01-23 01:45:37.039499: step: 1528/530, loss: 0.060408446937799454
2023-01-23 01:45:38.227072: step: 1532/530, loss: 0.30674201250076294
2023-01-23 01:45:39.403281: step: 1536/530, loss: 0.045743562281131744
2023-01-23 01:45:40.637278: step: 1540/530, loss: 0.003758716629818082
2023-01-23 01:45:41.809495: step: 1544/530, loss: 0.20081281661987305
2023-01-23 01:45:43.014573: step: 1548/530, loss: 0.0011451721657067537
2023-01-23 01:45:44.167542: step: 1552/530, loss: 0.010481643490493298
2023-01-23 01:45:45.355531: step: 1556/530, loss: 0.05293922498822212
2023-01-23 01:45:46.520599: step: 1560/530, loss: 0.05506305396556854
2023-01-23 01:45:47.690782: step: 1564/530, loss: 0.2520160675048828
2023-01-23 01:45:48.824628: step: 1568/530, loss: 0.008435058407485485
2023-01-23 01:45:50.005972: step: 1572/530, loss: 0.11139583587646484
2023-01-23 01:45:51.164440: step: 1576/530, loss: 0.07586231827735901
2023-01-23 01:45:52.350798: step: 1580/530, loss: 0.05974731594324112
2023-01-23 01:45:53.540886: step: 1584/530, loss: 0.137461856007576
2023-01-23 01:45:54.690020: step: 1588/530, loss: 0.003940105438232422
2023-01-23 01:45:55.873156: step: 1592/530, loss: 0.23871584236621857
2023-01-23 01:45:57.019679: step: 1596/530, loss: 0.03643636777997017
2023-01-23 01:45:58.204139: step: 1600/530, loss: 0.08828411996364594
2023-01-23 01:45:59.345820: step: 1604/530, loss: 0.022249555215239525
2023-01-23 01:46:00.524766: step: 1608/530, loss: 0.03384866565465927
2023-01-23 01:46:01.721238: step: 1612/530, loss: 0.024793434888124466
2023-01-23 01:46:02.877724: step: 1616/530, loss: 0.026638220995664597
2023-01-23 01:46:04.029148: step: 1620/530, loss: 0.03290840610861778
2023-01-23 01:46:05.204447: step: 1624/530, loss: 0.0743323341012001
2023-01-23 01:46:06.357924: step: 1628/530, loss: 0.007764172274619341
2023-01-23 01:46:07.521410: step: 1632/530, loss: 0.023153383284807205
2023-01-23 01:46:08.680012: step: 1636/530, loss: 0.03600792959332466
2023-01-23 01:46:09.866439: step: 1640/530, loss: 0.019744111225008965
2023-01-23 01:46:11.034317: step: 1644/530, loss: 0.7204625606536865
2023-01-23 01:46:12.224553: step: 1648/530, loss: 0.009069632738828659
2023-01-23 01:46:13.381647: step: 1652/530, loss: 0.031119156628847122
2023-01-23 01:46:14.543674: step: 1656/530, loss: 0.06660900264978409
2023-01-23 01:46:15.745011: step: 1660/530, loss: 0.03832855448126793
2023-01-23 01:46:16.897485: step: 1664/530, loss: 0.003734111785888672
2023-01-23 01:46:18.044505: step: 1668/530, loss: 0.019800137728452682
2023-01-23 01:46:19.203660: step: 1672/530, loss: 0.030502988025546074
2023-01-23 01:46:20.376238: step: 1676/530, loss: 0.025876712054014206
2023-01-23 01:46:21.506048: step: 1680/530, loss: 1.0191471576690674
2023-01-23 01:46:22.675532: step: 1684/530, loss: 0.2799045443534851
2023-01-23 01:46:23.837910: step: 1688/530, loss: 0.00604515103623271
2023-01-23 01:46:24.998216: step: 1692/530, loss: 0.03718767315149307
2023-01-23 01:46:26.160666: step: 1696/530, loss: 0.0032772065605968237
2023-01-23 01:46:27.368330: step: 1700/530, loss: 0.004082870204001665
2023-01-23 01:46:28.543197: step: 1704/530, loss: 0.017443466931581497
2023-01-23 01:46:29.708529: step: 1708/530, loss: 0.01168594416230917
2023-01-23 01:46:30.842574: step: 1712/530, loss: 0.04617633670568466
2023-01-23 01:46:32.034349: step: 1716/530, loss: 0.007175922393798828
2023-01-23 01:46:33.198400: step: 1720/530, loss: 0.06403732299804688
2023-01-23 01:46:34.360712: step: 1724/530, loss: 0.05706648901104927
2023-01-23 01:46:35.525403: step: 1728/530, loss: 0.06196889653801918
2023-01-23 01:46:36.724088: step: 1732/530, loss: 0.03970861807465553
2023-01-23 01:46:37.910468: step: 1736/530, loss: 0.037124063819646835
2023-01-23 01:46:39.092858: step: 1740/530, loss: 0.1004679948091507
2023-01-23 01:46:40.303003: step: 1744/530, loss: 0.05444078519940376
2023-01-23 01:46:41.463746: step: 1748/530, loss: 0.001445674803107977
2023-01-23 01:46:42.620197: step: 1752/530, loss: 0.0017767907120287418
2023-01-23 01:46:43.815077: step: 1756/530, loss: 0.10406875610351562
2023-01-23 01:46:44.988636: step: 1760/530, loss: 0.06995449215173721
2023-01-23 01:46:46.166759: step: 1764/530, loss: 0.048447802662849426
2023-01-23 01:46:47.319561: step: 1768/530, loss: 0.006215381436049938
2023-01-23 01:46:48.519005: step: 1772/530, loss: 0.017821885645389557
2023-01-23 01:46:49.651016: step: 1776/530, loss: 0.06677103042602539
2023-01-23 01:46:50.821894: step: 1780/530, loss: 0.04962186887860298
2023-01-23 01:46:51.976197: step: 1784/530, loss: 0.05091610178351402
2023-01-23 01:46:53.159769: step: 1788/530, loss: 0.0028972148429602385
2023-01-23 01:46:54.327878: step: 1792/530, loss: 0.04090538248419762
2023-01-23 01:46:55.514768: step: 1796/530, loss: 0.08588724583387375
2023-01-23 01:46:56.674852: step: 1800/530, loss: 0.03419294208288193
2023-01-23 01:46:57.899603: step: 1804/530, loss: 0.07059574872255325
2023-01-23 01:46:59.109555: step: 1808/530, loss: 0.0495111458003521
2023-01-23 01:47:00.237392: step: 1812/530, loss: 0.025900650769472122
2023-01-23 01:47:01.388249: step: 1816/530, loss: 0.007955646142363548
2023-01-23 01:47:02.537049: step: 1820/530, loss: 0.25032874941825867
2023-01-23 01:47:03.707031: step: 1824/530, loss: 0.04907378926873207
2023-01-23 01:47:04.829199: step: 1828/530, loss: 0.046205878257751465
2023-01-23 01:47:06.014351: step: 1832/530, loss: 0.012538003735244274
2023-01-23 01:47:07.204671: step: 1836/530, loss: 0.02088012732565403
2023-01-23 01:47:08.367429: step: 1840/530, loss: 0.11699561774730682
2023-01-23 01:47:09.515874: step: 1844/530, loss: 0.07212080806493759
2023-01-23 01:47:10.678388: step: 1848/530, loss: 0.05207099765539169
2023-01-23 01:47:11.872911: step: 1852/530, loss: 0.2666931748390198
2023-01-23 01:47:13.078962: step: 1856/530, loss: 0.00173187255859375
2023-01-23 01:47:14.243734: step: 1860/530, loss: 0.014516020193696022
2023-01-23 01:47:15.391985: step: 1864/530, loss: 0.028429605066776276
2023-01-23 01:47:16.560596: step: 1868/530, loss: 0.11363282054662704
2023-01-23 01:47:17.751880: step: 1872/530, loss: 0.0284334197640419
2023-01-23 01:47:18.972133: step: 1876/530, loss: 0.12160587310791016
2023-01-23 01:47:20.133034: step: 1880/530, loss: 0.005965805146843195
2023-01-23 01:47:21.330025: step: 1884/530, loss: 0.02010345458984375
2023-01-23 01:47:22.535897: step: 1888/530, loss: 0.16943226754665375
2023-01-23 01:47:23.687777: step: 1892/530, loss: 0.04083843156695366
2023-01-23 01:47:24.845296: step: 1896/530, loss: 0.02916259877383709
2023-01-23 01:47:26.051445: step: 1900/530, loss: 0.041333675384521484
2023-01-23 01:47:27.224929: step: 1904/530, loss: 0.029887771233916283
2023-01-23 01:47:28.410123: step: 1908/530, loss: 0.005649471189826727
2023-01-23 01:47:29.623496: step: 1912/530, loss: 0.004815483465790749
2023-01-23 01:47:30.764121: step: 1916/530, loss: 0.05436267703771591
2023-01-23 01:47:31.938661: step: 1920/530, loss: 0.030610179528594017
2023-01-23 01:47:33.117079: step: 1924/530, loss: 0.0032792091369628906
2023-01-23 01:47:34.329597: step: 1928/530, loss: 0.10347528755664825
2023-01-23 01:47:35.493162: step: 1932/530, loss: 0.0426909439265728
2023-01-23 01:47:36.688297: step: 1936/530, loss: 0.029197216033935547
2023-01-23 01:47:37.848735: step: 1940/530, loss: 0.03308119997382164
2023-01-23 01:47:39.028395: step: 1944/530, loss: 0.02516203001141548
2023-01-23 01:47:40.172960: step: 1948/530, loss: 0.003335380693897605
2023-01-23 01:47:41.333597: step: 1952/530, loss: 0.08260011672973633
2023-01-23 01:47:42.580219: step: 1956/530, loss: 0.03425408899784088
2023-01-23 01:47:43.796938: step: 1960/530, loss: 0.04768028110265732
2023-01-23 01:47:44.963144: step: 1964/530, loss: 0.0680142417550087
2023-01-23 01:47:46.153654: step: 1968/530, loss: 0.12147045135498047
2023-01-23 01:47:47.335216: step: 1972/530, loss: 0.014282465912401676
2023-01-23 01:47:48.491157: step: 1976/530, loss: 0.014441777020692825
2023-01-23 01:47:49.623031: step: 1980/530, loss: 0.029783153906464577
2023-01-23 01:47:50.798423: step: 1984/530, loss: 0.07527198642492294
2023-01-23 01:47:51.975679: step: 1988/530, loss: 0.1627923995256424
2023-01-23 01:47:53.149596: step: 1992/530, loss: 0.01703643798828125
2023-01-23 01:47:54.330409: step: 1996/530, loss: 0.04784107208251953
2023-01-23 01:47:55.470742: step: 2000/530, loss: 0.03609418869018555
2023-01-23 01:47:56.653314: step: 2004/530, loss: 0.00937950611114502
2023-01-23 01:47:57.826230: step: 2008/530, loss: 0.04931154474616051
2023-01-23 01:47:59.022355: step: 2012/530, loss: 0.049268245697021484
2023-01-23 01:48:00.211130: step: 2016/530, loss: 0.2753294110298157
2023-01-23 01:48:01.401045: step: 2020/530, loss: 0.024842072278261185
2023-01-23 01:48:02.577168: step: 2024/530, loss: 0.007775783538818359
2023-01-23 01:48:03.699087: step: 2028/530, loss: 0.04651632159948349
2023-01-23 01:48:04.894741: step: 2032/530, loss: 0.015264129266142845
2023-01-23 01:48:06.072552: step: 2036/530, loss: 0.05563822016119957
2023-01-23 01:48:07.235604: step: 2040/530, loss: 0.020015764981508255
2023-01-23 01:48:08.424137: step: 2044/530, loss: 0.023726463317871094
2023-01-23 01:48:09.618870: step: 2048/530, loss: 0.06632719188928604
2023-01-23 01:48:10.759632: step: 2052/530, loss: 0.01572251319885254
2023-01-23 01:48:11.898351: step: 2056/530, loss: 0.004071235656738281
2023-01-23 01:48:13.048377: step: 2060/530, loss: 0.03538046032190323
2023-01-23 01:48:14.244571: step: 2064/530, loss: 0.021763324737548828
2023-01-23 01:48:15.413880: step: 2068/530, loss: 0.11623821407556534
2023-01-23 01:48:16.629969: step: 2072/530, loss: 0.07619114220142365
2023-01-23 01:48:17.873952: step: 2076/530, loss: 0.002701377961784601
2023-01-23 01:48:19.080095: step: 2080/530, loss: 0.10796938091516495
2023-01-23 01:48:20.284594: step: 2084/530, loss: 0.015152215957641602
2023-01-23 01:48:21.436709: step: 2088/530, loss: 0.06803421676158905
2023-01-23 01:48:22.607595: step: 2092/530, loss: 0.0671718567609787
2023-01-23 01:48:23.788685: step: 2096/530, loss: 0.026571083813905716
2023-01-23 01:48:24.963595: step: 2100/530, loss: 0.004444885067641735
2023-01-23 01:48:26.199746: step: 2104/530, loss: 0.08730068057775497
2023-01-23 01:48:27.428890: step: 2108/530, loss: 0.028656387701630592
2023-01-23 01:48:28.572623: step: 2112/530, loss: 0.19828014075756073
2023-01-23 01:48:29.760744: step: 2116/530, loss: 0.11132355034351349
2023-01-23 01:48:30.938959: step: 2120/530, loss: 0.08427419513463974
==================================================
Loss: 0.063
--------------------
Dev: {'event': {'p': 0.5873493975903614, 'r': 0.7789613848202397, 'f1': 0.6697195191757298}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Test: {'event': {'p': 0.6369020501138952, 'r': 0.8039102932719954, 'f1': 0.7107269954245043}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Chinese: {'event': {'p': 0.5280898876404494, 'r': 0.8703703703703703, 'f1': 0.6573426573426573}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Korean: {'event': {'p': 0.5230769230769231, 'r': 0.5396825396825397, 'f1': 0.53125}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Russian: {'event': {'p': 0.44, 'r': 0.6111111111111112, 'f1': 0.5116279069767442}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6351501668520578, 'r': 0.7603195739014648, 'f1': 0.6921212121212121}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Chinese: {'event': {'p': 0.6373175182481752, 'r': 0.8033352501437608, 'f1': 0.7107606207071993}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Chinese: {'event': {'p': 0.5903614457831325, 'r': 0.9074074074074074, 'f1': 0.7153284671532847}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5733990147783251, 'r': 0.7749667110519307, 'f1': 0.6591166477916196}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Eng Test for Korean: {'event': {'p': 0.6218005295675199, 'r': 0.8102357676825762, 'f1': 0.7036204744069912}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Sample Korean: {'event': {'p': 0.6417910447761194, 'r': 0.6825396825396826, 'f1': 0.6615384615384614}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5951882845188284, 'r': 0.7576564580559254, 'f1': 0.6666666666666666}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6663405088062623, 'r': 0.7832087406555491, 'f1': 0.7200634417129264}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5, 'r': 0.6666666666666666, 'f1': 0.5714285714285715}, '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 01:49:13.696317: step: 4/530, loss: 0.10004901885986328
2023-01-23 01:49:14.848672: step: 8/530, loss: 0.0032314301934093237
2023-01-23 01:49:16.156864: step: 12/530, loss: 0.01663847081363201
2023-01-23 01:49:17.354648: step: 16/530, loss: 0.050066664814949036
2023-01-23 01:49:18.525151: step: 20/530, loss: 0.006414985749870539
2023-01-23 01:49:19.667860: step: 24/530, loss: 0.03378744050860405
2023-01-23 01:49:20.861922: step: 28/530, loss: 0.05332126468420029
2023-01-23 01:49:22.053332: step: 32/530, loss: 0.018777180463075638
2023-01-23 01:49:23.183543: step: 36/530, loss: 0.022528838366270065
2023-01-23 01:49:24.370073: step: 40/530, loss: 0.0068946839310228825
2023-01-23 01:49:25.532753: step: 44/530, loss: 0.0207716953009367
2023-01-23 01:49:26.686818: step: 48/530, loss: 0.04573841020464897
2023-01-23 01:49:27.868577: step: 52/530, loss: 0.0004903793451376259
2023-01-23 01:49:29.075601: step: 56/530, loss: 0.05951228365302086
2023-01-23 01:49:30.224385: step: 60/530, loss: 0.027296876534819603
2023-01-23 01:49:31.428180: step: 64/530, loss: 0.13644734025001526
2023-01-23 01:49:32.590256: step: 68/530, loss: 0.08791694790124893
2023-01-23 01:49:33.762321: step: 72/530, loss: 0.0009687423589639366
2023-01-23 01:49:34.878463: step: 76/530, loss: 0.016785193234682083
2023-01-23 01:49:36.049578: step: 80/530, loss: 0.0002639770391397178
2023-01-23 01:49:37.247440: step: 84/530, loss: 0.06766338646411896
2023-01-23 01:49:38.423048: step: 88/530, loss: 0.018208885565400124
2023-01-23 01:49:39.619883: step: 92/530, loss: 0.003375721164047718
2023-01-23 01:49:40.785659: step: 96/530, loss: 0.018230963498353958
2023-01-23 01:49:41.960056: step: 100/530, loss: 0.009283924475312233
2023-01-23 01:49:43.072600: step: 104/530, loss: 0.007732391823083162
2023-01-23 01:49:44.256913: step: 108/530, loss: 0.004638290032744408
2023-01-23 01:49:45.408420: step: 112/530, loss: 0.015256499871611595
2023-01-23 01:49:46.575692: step: 116/530, loss: 0.02787327766418457
2023-01-23 01:49:47.746094: step: 120/530, loss: 0.053221896290779114
2023-01-23 01:49:48.914327: step: 124/530, loss: 0.4339471757411957
2023-01-23 01:49:50.100923: step: 128/530, loss: 0.013323593884706497
2023-01-23 01:49:51.256065: step: 132/530, loss: 0.013069534674286842
2023-01-23 01:49:52.440476: step: 136/530, loss: 0.011860084719955921
2023-01-23 01:49:53.569342: step: 140/530, loss: 0.00010271072096657008
2023-01-23 01:49:54.713660: step: 144/530, loss: 7.853508577682078e-05
2023-01-23 01:49:55.933636: step: 148/530, loss: 0.072441965341568
2023-01-23 01:49:57.091342: step: 152/530, loss: 0.010389899834990501
2023-01-23 01:49:58.243372: step: 156/530, loss: 0.001139831612817943
2023-01-23 01:49:59.402768: step: 160/530, loss: 0.002760601229965687
2023-01-23 01:50:00.569412: step: 164/530, loss: 0.013921737670898438
2023-01-23 01:50:01.716579: step: 168/530, loss: 0.060849953442811966
2023-01-23 01:50:02.909697: step: 172/530, loss: 0.0037219999358057976
2023-01-23 01:50:04.092744: step: 176/530, loss: 0.014375877566635609
2023-01-23 01:50:05.320307: step: 180/530, loss: 0.006615448277443647
2023-01-23 01:50:06.485892: step: 184/530, loss: 0.005596637260168791
2023-01-23 01:50:07.621469: step: 188/530, loss: 0.008048344403505325
2023-01-23 01:50:08.780415: step: 192/530, loss: 0.0310808178037405
2023-01-23 01:50:09.920052: step: 196/530, loss: 0.01149530429393053
2023-01-23 01:50:11.098382: step: 200/530, loss: 0.522605836391449
2023-01-23 01:50:12.291525: step: 204/530, loss: 0.004442119505256414
2023-01-23 01:50:13.478782: step: 208/530, loss: 0.024345552548766136
2023-01-23 01:50:14.647894: step: 212/530, loss: 0.03595466911792755
2023-01-23 01:50:15.857407: step: 216/530, loss: 0.028559112921357155
2023-01-23 01:50:17.127372: step: 220/530, loss: 0.008593273349106312
2023-01-23 01:50:18.282596: step: 224/530, loss: 0.005396169610321522
2023-01-23 01:50:19.472951: step: 228/530, loss: 0.002710628556087613
2023-01-23 01:50:20.647801: step: 232/530, loss: 0.007542658131569624
2023-01-23 01:50:21.855104: step: 236/530, loss: 0.02953367307782173
2023-01-23 01:50:23.025983: step: 240/530, loss: 0.06640129536390305
2023-01-23 01:50:24.241158: step: 244/530, loss: 0.24774475395679474
2023-01-23 01:50:25.444666: step: 248/530, loss: 0.17289294302463531
2023-01-23 01:50:26.603005: step: 252/530, loss: 0.012560653500258923
2023-01-23 01:50:27.772132: step: 256/530, loss: 0.029000377282500267
2023-01-23 01:50:28.915396: step: 260/530, loss: 0.2869914174079895
2023-01-23 01:50:30.082515: step: 264/530, loss: 0.0010747909545898438
2023-01-23 01:50:31.244667: step: 268/530, loss: 0.012018776498734951
2023-01-23 01:50:32.391520: step: 272/530, loss: 0.01170129794627428
2023-01-23 01:50:33.568480: step: 276/530, loss: 0.019718552008271217
2023-01-23 01:50:34.747413: step: 280/530, loss: 0.017036771401762962
2023-01-23 01:50:35.920880: step: 284/530, loss: 0.05658683925867081
2023-01-23 01:50:37.069939: step: 288/530, loss: 0.010839272290468216
2023-01-23 01:50:38.210821: step: 292/530, loss: 0.0033249855041503906
2023-01-23 01:50:39.351270: step: 296/530, loss: 0.03097391128540039
2023-01-23 01:50:40.514434: step: 300/530, loss: 0.10082073509693146
2023-01-23 01:50:41.706225: step: 304/530, loss: 0.019155312329530716
2023-01-23 01:50:42.853964: step: 308/530, loss: 0.018297338858246803
2023-01-23 01:50:44.058581: step: 312/530, loss: 0.0992591381072998
2023-01-23 01:50:45.198852: step: 316/530, loss: 0.04467001557350159
2023-01-23 01:50:46.366016: step: 320/530, loss: 0.02350912056863308
2023-01-23 01:50:47.556997: step: 324/530, loss: 0.02422504313290119
2023-01-23 01:50:48.785165: step: 328/530, loss: 0.14950066804885864
2023-01-23 01:50:49.949690: step: 332/530, loss: 0.00955190695822239
2023-01-23 01:50:51.159516: step: 336/530, loss: 0.2741892337799072
2023-01-23 01:50:52.368503: step: 340/530, loss: 0.012942124158143997
2023-01-23 01:50:53.583648: step: 344/530, loss: 0.07776851952075958
2023-01-23 01:50:54.766704: step: 348/530, loss: 0.04230346530675888
2023-01-23 01:50:55.984386: step: 352/530, loss: 0.024175453931093216
2023-01-23 01:50:57.188071: step: 356/530, loss: 0.029779816046357155
2023-01-23 01:50:58.362922: step: 360/530, loss: 0.03215289115905762
2023-01-23 01:50:59.492519: step: 364/530, loss: 0.03753085061907768
2023-01-23 01:51:00.642981: step: 368/530, loss: 0.0011881828540936112
2023-01-23 01:51:01.816291: step: 372/530, loss: 0.045100972056388855
2023-01-23 01:51:02.972256: step: 376/530, loss: 0.001973915146663785
2023-01-23 01:51:04.140944: step: 380/530, loss: 0.013695812784135342
2023-01-23 01:51:05.350725: step: 384/530, loss: 0.002600813051685691
2023-01-23 01:51:06.540335: step: 388/530, loss: 5.380776882171631
2023-01-23 01:51:07.748461: step: 392/530, loss: 0.00581812858581543
2023-01-23 01:51:08.929431: step: 396/530, loss: 0.0007762908935546875
2023-01-23 01:51:10.080170: step: 400/530, loss: 0.07800697535276413
2023-01-23 01:51:11.253057: step: 404/530, loss: 0.0460878387093544
2023-01-23 01:51:12.426474: step: 408/530, loss: 0.010218143463134766
2023-01-23 01:51:13.603652: step: 412/530, loss: 0.012431908398866653
2023-01-23 01:51:14.777830: step: 416/530, loss: 0.03949098661541939
2023-01-23 01:51:16.003460: step: 420/530, loss: 0.037775516510009766
2023-01-23 01:51:17.182663: step: 424/530, loss: 0.06238670274615288
2023-01-23 01:51:18.367974: step: 428/530, loss: 0.09127922356128693
2023-01-23 01:51:19.545680: step: 432/530, loss: 0.042136095464229584
2023-01-23 01:51:20.693521: step: 436/530, loss: 0.0070014954544603825
2023-01-23 01:51:21.851020: step: 440/530, loss: 0.019686413928866386
2023-01-23 01:51:22.988637: step: 444/530, loss: 0.002402782440185547
2023-01-23 01:51:24.164081: step: 448/530, loss: 0.006447506137192249
2023-01-23 01:51:25.297395: step: 452/530, loss: 0.014334345236420631
2023-01-23 01:51:26.488370: step: 456/530, loss: 0.049262333661317825
2023-01-23 01:51:27.646926: step: 460/530, loss: 0.009968224912881851
2023-01-23 01:51:28.797877: step: 464/530, loss: 0.006039619445800781
2023-01-23 01:51:29.986728: step: 468/530, loss: 0.00283393869176507
2023-01-23 01:51:31.157135: step: 472/530, loss: 0.010063457302749157
2023-01-23 01:51:32.354475: step: 476/530, loss: 0.04533147066831589
2023-01-23 01:51:33.531141: step: 480/530, loss: 0.0342344269156456
2023-01-23 01:51:34.667818: step: 484/530, loss: 0.041109848767519
2023-01-23 01:51:35.795864: step: 488/530, loss: 0.002376079559326172
2023-01-23 01:51:36.981554: step: 492/530, loss: 0.10553179681301117
2023-01-23 01:51:38.152589: step: 496/530, loss: 0.002952003385871649
2023-01-23 01:51:39.281595: step: 500/530, loss: 0.06091776490211487
2023-01-23 01:51:40.472006: step: 504/530, loss: 0.0035951617173850536
2023-01-23 01:51:41.629142: step: 508/530, loss: 0.0022552490700036287
2023-01-23 01:51:42.794985: step: 512/530, loss: 0.015830958262085915
2023-01-23 01:51:43.952051: step: 516/530, loss: 0.07178954780101776
2023-01-23 01:51:45.133590: step: 520/530, loss: 0.0045768022537231445
2023-01-23 01:51:46.317030: step: 524/530, loss: 0.04773874208331108
2023-01-23 01:51:47.492242: step: 528/530, loss: 0.09525977075099945
2023-01-23 01:51:48.682624: step: 532/530, loss: 0.013391494750976562
2023-01-23 01:51:49.880351: step: 536/530, loss: 0.16305142641067505
2023-01-23 01:51:51.045534: step: 540/530, loss: 0.15200833976268768
2023-01-23 01:51:52.206345: step: 544/530, loss: 0.08344488590955734
2023-01-23 01:51:53.376173: step: 548/530, loss: 0.06466970592737198
2023-01-23 01:51:54.529536: step: 552/530, loss: 0.008684491738677025
2023-01-23 01:51:55.703950: step: 556/530, loss: 0.05092290788888931
2023-01-23 01:51:56.884695: step: 560/530, loss: 0.03428792580962181
2023-01-23 01:51:58.054367: step: 564/530, loss: 0.04535084217786789
2023-01-23 01:51:59.225518: step: 568/530, loss: 0.06685533374547958
2023-01-23 01:52:00.416018: step: 572/530, loss: 0.03615257143974304
2023-01-23 01:52:01.574570: step: 576/530, loss: 0.014024496078491211
2023-01-23 01:52:02.757851: step: 580/530, loss: 0.008629703894257545
2023-01-23 01:52:03.958850: step: 584/530, loss: 0.010449028573930264
2023-01-23 01:52:05.102468: step: 588/530, loss: 0.0018483161693438888
2023-01-23 01:52:06.241185: step: 592/530, loss: 0.07983622699975967
2023-01-23 01:52:07.398850: step: 596/530, loss: 0.0014098406536504626
2023-01-23 01:52:08.553788: step: 600/530, loss: 0.046735286712646484
2023-01-23 01:52:09.700217: step: 604/530, loss: 0.041312411427497864
2023-01-23 01:52:10.855006: step: 608/530, loss: 0.005254650022834539
2023-01-23 01:52:12.076381: step: 612/530, loss: 0.006469822023063898
2023-01-23 01:52:13.266553: step: 616/530, loss: 0.023212242871522903
2023-01-23 01:52:14.442284: step: 620/530, loss: 0.023560047149658203
2023-01-23 01:52:15.613059: step: 624/530, loss: 0.00410385150462389
2023-01-23 01:52:16.762222: step: 628/530, loss: 0.0017523765563964844
2023-01-23 01:52:17.930301: step: 632/530, loss: 0.03904438018798828
2023-01-23 01:52:19.102286: step: 636/530, loss: 0.006707191467285156
2023-01-23 01:52:20.276648: step: 640/530, loss: 0.016329193487763405
2023-01-23 01:52:21.537179: step: 644/530, loss: 0.016475772485136986
2023-01-23 01:52:22.689524: step: 648/530, loss: 0.02250981330871582
2023-01-23 01:52:23.888586: step: 652/530, loss: 0.08036527037620544
2023-01-23 01:52:25.034844: step: 656/530, loss: 0.0514252632856369
2023-01-23 01:52:26.222565: step: 660/530, loss: 0.027327824383974075
2023-01-23 01:52:27.388141: step: 664/530, loss: 0.01322789117693901
2023-01-23 01:52:28.610611: step: 668/530, loss: 0.08221215754747391
2023-01-23 01:52:29.773396: step: 672/530, loss: 0.047343090176582336
2023-01-23 01:52:30.934345: step: 676/530, loss: 0.12078670412302017
2023-01-23 01:52:32.088488: step: 680/530, loss: 0.18680067360401154
2023-01-23 01:52:33.307459: step: 684/530, loss: 0.0060790060088038445
2023-01-23 01:52:34.503485: step: 688/530, loss: 0.07895335555076599
2023-01-23 01:52:35.693851: step: 692/530, loss: 0.0226606372743845
2023-01-23 01:52:36.805944: step: 696/530, loss: 0.020711231976747513
2023-01-23 01:52:37.988591: step: 700/530, loss: 0.014370870776474476
2023-01-23 01:52:39.156317: step: 704/530, loss: 0.022214699536561966
2023-01-23 01:52:40.301665: step: 708/530, loss: 0.008092308416962624
2023-01-23 01:52:41.439358: step: 712/530, loss: 0.01620025746524334
2023-01-23 01:52:42.632117: step: 716/530, loss: 0.031725216656923294
2023-01-23 01:52:43.802363: step: 720/530, loss: 0.22083044052124023
2023-01-23 01:52:44.996930: step: 724/530, loss: 0.04113359749317169
2023-01-23 01:52:46.152598: step: 728/530, loss: 0.0027060983702540398
2023-01-23 01:52:47.344478: step: 732/530, loss: 0.059975381940603256
2023-01-23 01:52:48.505128: step: 736/530, loss: 0.01000213623046875
2023-01-23 01:52:49.695851: step: 740/530, loss: 0.03115234524011612
2023-01-23 01:52:50.878577: step: 744/530, loss: 0.03276796638965607
2023-01-23 01:52:52.049302: step: 748/530, loss: 0.011308098211884499
2023-01-23 01:52:53.231375: step: 752/530, loss: 0.06421995162963867
2023-01-23 01:52:54.386616: step: 756/530, loss: 0.004058361053466797
2023-01-23 01:52:55.571243: step: 760/530, loss: 0.4870767593383789
2023-01-23 01:52:56.779981: step: 764/530, loss: 0.04728507995605469
2023-01-23 01:52:57.937474: step: 768/530, loss: 0.004268193151801825
2023-01-23 01:52:59.119128: step: 772/530, loss: 0.030767250806093216
2023-01-23 01:53:00.297179: step: 776/530, loss: 0.05232071876525879
2023-01-23 01:53:01.474896: step: 780/530, loss: 0.1106410026550293
2023-01-23 01:53:02.671660: step: 784/530, loss: 0.020158957690000534
2023-01-23 01:53:03.867382: step: 788/530, loss: 0.012179374694824219
2023-01-23 01:53:05.117952: step: 792/530, loss: 0.036643028259277344
2023-01-23 01:53:06.250438: step: 796/530, loss: 0.0234514232724905
2023-01-23 01:53:07.429170: step: 800/530, loss: 0.05611305311322212
2023-01-23 01:53:08.605056: step: 804/530, loss: 0.020201683044433594
2023-01-23 01:53:09.802464: step: 808/530, loss: 0.0027421952690929174
2023-01-23 01:53:10.967817: step: 812/530, loss: 0.05255298689007759
2023-01-23 01:53:12.160463: step: 816/530, loss: 0.05241432413458824
2023-01-23 01:53:13.411079: step: 820/530, loss: 0.030003929510712624
2023-01-23 01:53:14.572269: step: 824/530, loss: 0.00626482954248786
2023-01-23 01:53:15.803124: step: 828/530, loss: 0.04351654276251793
2023-01-23 01:53:16.972242: step: 832/530, loss: 0.07517804950475693
2023-01-23 01:53:18.124084: step: 836/530, loss: 0.012499428354203701
2023-01-23 01:53:19.296396: step: 840/530, loss: 0.014498806558549404
2023-01-23 01:53:20.491345: step: 844/530, loss: 0.03977778181433678
2023-01-23 01:53:21.667008: step: 848/530, loss: 0.028492452576756477
2023-01-23 01:53:22.848676: step: 852/530, loss: 0.015743732452392578
2023-01-23 01:53:24.018048: step: 856/530, loss: 0.015134715475142002
2023-01-23 01:53:25.214545: step: 860/530, loss: 0.08751964569091797
2023-01-23 01:53:26.362550: step: 864/530, loss: 0.1088382676243782
2023-01-23 01:53:27.560050: step: 868/530, loss: 0.0007902145152911544
2023-01-23 01:53:28.719381: step: 872/530, loss: 0.06449051201343536
2023-01-23 01:53:29.939420: step: 876/530, loss: 0.06290464848279953
2023-01-23 01:53:31.131770: step: 880/530, loss: 0.03508930280804634
2023-01-23 01:53:32.309992: step: 884/530, loss: 0.016158677637577057
2023-01-23 01:53:33.478296: step: 888/530, loss: 0.023266160860657692
2023-01-23 01:53:34.634106: step: 892/530, loss: 0.02097930945456028
2023-01-23 01:53:35.876628: step: 896/530, loss: 0.04954729229211807
2023-01-23 01:53:37.024194: step: 900/530, loss: 0.0018979072337970138
2023-01-23 01:53:38.190710: step: 904/530, loss: 0.0040073394775390625
2023-01-23 01:53:39.373825: step: 908/530, loss: 0.06982593238353729
2023-01-23 01:53:40.549904: step: 912/530, loss: 0.05851898342370987
2023-01-23 01:53:41.717515: step: 916/530, loss: 0.019919872283935547
2023-01-23 01:53:42.911571: step: 920/530, loss: 0.014957617968320847
2023-01-23 01:53:44.074133: step: 924/530, loss: 0.013622093014419079
2023-01-23 01:53:45.261571: step: 928/530, loss: 0.09099216014146805
2023-01-23 01:53:46.437750: step: 932/530, loss: 0.6720672249794006
2023-01-23 01:53:47.620151: step: 936/530, loss: 0.9447656869888306
2023-01-23 01:53:48.818893: step: 940/530, loss: 0.019492723047733307
2023-01-23 01:53:49.967924: step: 944/530, loss: 0.02751283533871174
2023-01-23 01:53:51.127852: step: 948/530, loss: 0.029192639514803886
2023-01-23 01:53:52.273349: step: 952/530, loss: 0.015758514404296875
2023-01-23 01:53:53.454973: step: 956/530, loss: 0.062221623957157135
2023-01-23 01:53:54.609574: step: 960/530, loss: 0.015386056154966354
2023-01-23 01:53:55.853618: step: 964/530, loss: 0.018376445397734642
2023-01-23 01:53:57.047868: step: 968/530, loss: 0.020078659057617188
2023-01-23 01:53:58.224318: step: 972/530, loss: 0.0668155699968338
2023-01-23 01:53:59.404056: step: 976/530, loss: 0.005804157815873623
2023-01-23 01:54:00.553000: step: 980/530, loss: 0.02291693538427353
2023-01-23 01:54:01.744287: step: 984/530, loss: 0.029445840045809746
2023-01-23 01:54:02.900650: step: 988/530, loss: 0.05299568176269531
2023-01-23 01:54:04.059480: step: 992/530, loss: 0.008049249649047852
2023-01-23 01:54:05.210264: step: 996/530, loss: 0.06351175159215927
2023-01-23 01:54:06.410146: step: 1000/530, loss: 0.013764381408691406
2023-01-23 01:54:07.556352: step: 1004/530, loss: 0.10248871147632599
2023-01-23 01:54:08.702284: step: 1008/530, loss: 0.05187620967626572
2023-01-23 01:54:09.863890: step: 1012/530, loss: 0.04626312106847763
2023-01-23 01:54:11.006564: step: 1016/530, loss: 0.10064688324928284
2023-01-23 01:54:12.165895: step: 1020/530, loss: 0.0583617240190506
2023-01-23 01:54:13.302774: step: 1024/530, loss: 0.038388825953006744
2023-01-23 01:54:14.443260: step: 1028/530, loss: 0.0027133943513035774
2023-01-23 01:54:15.583632: step: 1032/530, loss: 1.5873178243637085
2023-01-23 01:54:16.730581: step: 1036/530, loss: 0.002054405165836215
2023-01-23 01:54:17.891743: step: 1040/530, loss: 0.0008842468378134072
2023-01-23 01:54:19.109899: step: 1044/530, loss: 0.036200523376464844
2023-01-23 01:54:20.268937: step: 1048/530, loss: 0.03912096098065376
2023-01-23 01:54:21.422686: step: 1052/530, loss: 0.014590168371796608
2023-01-23 01:54:22.590942: step: 1056/530, loss: 0.004029273986816406
2023-01-23 01:54:23.828008: step: 1060/530, loss: 0.10773029923439026
2023-01-23 01:54:24.992759: step: 1064/530, loss: 0.0009130954276770353
2023-01-23 01:54:26.162812: step: 1068/530, loss: 0.0750865712761879
2023-01-23 01:54:27.314834: step: 1072/530, loss: 0.0032346248626708984
2023-01-23 01:54:28.486641: step: 1076/530, loss: 0.024076366797089577
2023-01-23 01:54:29.674452: step: 1080/530, loss: 0.052799418568611145
2023-01-23 01:54:30.854494: step: 1084/530, loss: 0.08912745118141174
2023-01-23 01:54:32.044697: step: 1088/530, loss: 0.0533411018550396
2023-01-23 01:54:33.199134: step: 1092/530, loss: 0.009787846356630325
2023-01-23 01:54:34.372844: step: 1096/530, loss: 0.05474109947681427
2023-01-23 01:54:35.509554: step: 1100/530, loss: 0.03139081224799156
2023-01-23 01:54:36.667663: step: 1104/530, loss: 0.04499571770429611
2023-01-23 01:54:37.861888: step: 1108/530, loss: 0.06426601111888885
2023-01-23 01:54:39.058150: step: 1112/530, loss: 0.0022789002396166325
2023-01-23 01:54:40.213651: step: 1116/530, loss: 0.007829046808183193
2023-01-23 01:54:41.353286: step: 1120/530, loss: 0.04881773144006729
2023-01-23 01:54:42.550897: step: 1124/530, loss: 0.017742061987519264
2023-01-23 01:54:43.693012: step: 1128/530, loss: 0.0024471282958984375
2023-01-23 01:54:44.830264: step: 1132/530, loss: 0.0405152402818203
2023-01-23 01:54:46.033197: step: 1136/530, loss: 0.004213142208755016
2023-01-23 01:54:47.214549: step: 1140/530, loss: 0.04712200164794922
2023-01-23 01:54:48.389566: step: 1144/530, loss: 0.04386615753173828
2023-01-23 01:54:49.531215: step: 1148/530, loss: 0.029075050726532936
2023-01-23 01:54:50.684778: step: 1152/530, loss: 0.0013036727905273438
2023-01-23 01:54:51.860602: step: 1156/530, loss: 0.1572185605764389
2023-01-23 01:54:53.026907: step: 1160/530, loss: 0.015713881701231003
2023-01-23 01:54:54.173849: step: 1164/530, loss: 0.15891484916210175
2023-01-23 01:54:55.370512: step: 1168/530, loss: 0.01745147630572319
2023-01-23 01:54:56.549392: step: 1172/530, loss: 0.22228102385997772
2023-01-23 01:54:57.781897: step: 1176/530, loss: 0.06579075008630753
2023-01-23 01:54:58.946502: step: 1180/530, loss: 0.030608560889959335
2023-01-23 01:55:00.142052: step: 1184/530, loss: 0.005961370188742876
2023-01-23 01:55:01.290961: step: 1188/530, loss: 0.01275491714477539
2023-01-23 01:55:02.498054: step: 1192/530, loss: 0.028139973059296608
2023-01-23 01:55:03.665682: step: 1196/530, loss: 0.0005164146423339844
2023-01-23 01:55:04.839218: step: 1200/530, loss: 0.09835916012525558
2023-01-23 01:55:05.977167: step: 1204/530, loss: 0.07554474472999573
2023-01-23 01:55:07.160504: step: 1208/530, loss: 0.060419656336307526
2023-01-23 01:55:08.357075: step: 1212/530, loss: 0.01329116802662611
2023-01-23 01:55:09.532875: step: 1216/530, loss: 0.28663673996925354
2023-01-23 01:55:10.687334: step: 1220/530, loss: 0.05301990732550621
2023-01-23 01:55:11.874458: step: 1224/530, loss: 0.006135368254035711
2023-01-23 01:55:13.023072: step: 1228/530, loss: 0.053505513817071915
2023-01-23 01:55:14.188488: step: 1232/530, loss: 0.02897033840417862
2023-01-23 01:55:15.330384: step: 1236/530, loss: 0.04241809993982315
2023-01-23 01:55:16.514262: step: 1240/530, loss: 0.08190841972827911
2023-01-23 01:55:17.698581: step: 1244/530, loss: 0.01678771898150444
2023-01-23 01:55:18.889435: step: 1248/530, loss: 0.08135394752025604
2023-01-23 01:55:20.032088: step: 1252/530, loss: 0.00514831580221653
2023-01-23 01:55:21.238115: step: 1256/530, loss: 0.0794924721121788
2023-01-23 01:55:22.395906: step: 1260/530, loss: 0.10486526787281036
2023-01-23 01:55:23.549994: step: 1264/530, loss: 0.011802387423813343
2023-01-23 01:55:24.729452: step: 1268/530, loss: 0.06461963802576065
2023-01-23 01:55:25.891797: step: 1272/530, loss: 0.024094581604003906
2023-01-23 01:55:27.077419: step: 1276/530, loss: 0.29612845182418823
2023-01-23 01:55:28.218948: step: 1280/530, loss: 0.015963125973939896
2023-01-23 01:55:29.360642: step: 1284/530, loss: 0.14036236703395844
2023-01-23 01:55:30.534727: step: 1288/530, loss: 0.02286829985678196
2023-01-23 01:55:31.734632: step: 1292/530, loss: 0.08441717177629471
2023-01-23 01:55:32.885224: step: 1296/530, loss: 0.13040542602539062
2023-01-23 01:55:34.067742: step: 1300/530, loss: 0.046560097485780716
2023-01-23 01:55:35.221083: step: 1304/530, loss: 0.057631492614746094
2023-01-23 01:55:36.396061: step: 1308/530, loss: 0.05217113718390465
2023-01-23 01:55:37.563393: step: 1312/530, loss: 0.01954355277121067
2023-01-23 01:55:38.731892: step: 1316/530, loss: 0.018437959253787994
2023-01-23 01:55:39.988342: step: 1320/530, loss: 0.10287466645240784
2023-01-23 01:55:41.157487: step: 1324/530, loss: 0.010599995031952858
2023-01-23 01:55:42.345131: step: 1328/530, loss: 0.005822325125336647
2023-01-23 01:55:43.560577: step: 1332/530, loss: 0.0163711067289114
2023-01-23 01:55:44.730886: step: 1336/530, loss: 0.009173489175736904
2023-01-23 01:55:45.929974: step: 1340/530, loss: 0.0920533686876297
2023-01-23 01:55:47.100485: step: 1344/530, loss: 0.09542389214038849
2023-01-23 01:55:48.291479: step: 1348/530, loss: 0.010265350341796875
2023-01-23 01:55:49.447791: step: 1352/530, loss: 0.022735118865966797
2023-01-23 01:55:50.589568: step: 1356/530, loss: 0.011389637365937233
2023-01-23 01:55:51.743079: step: 1360/530, loss: 0.4217488467693329
2023-01-23 01:55:52.937997: step: 1364/530, loss: 0.027636338025331497
2023-01-23 01:55:54.077381: step: 1368/530, loss: 0.010472583584487438
2023-01-23 01:55:55.263510: step: 1372/530, loss: 0.03571949154138565
2023-01-23 01:55:56.410600: step: 1376/530, loss: 0.0035711764357984066
2023-01-23 01:55:57.598987: step: 1380/530, loss: 0.03551464155316353
2023-01-23 01:55:58.786457: step: 1384/530, loss: 0.010649300180375576
2023-01-23 01:55:59.929800: step: 1388/530, loss: 0.021372605115175247
2023-01-23 01:56:01.093856: step: 1392/530, loss: 0.02072601392865181
2023-01-23 01:56:02.236842: step: 1396/530, loss: 0.00197601318359375
2023-01-23 01:56:03.415454: step: 1400/530, loss: 0.03057580068707466
2023-01-23 01:56:04.561786: step: 1404/530, loss: 0.0018190384143963456
2023-01-23 01:56:05.700593: step: 1408/530, loss: 0.00015096664719749242
2023-01-23 01:56:06.861663: step: 1412/530, loss: 0.01744537428021431
2023-01-23 01:56:08.002096: step: 1416/530, loss: 0.002832174301147461
2023-01-23 01:56:09.178384: step: 1420/530, loss: 0.09745007008314133
2023-01-23 01:56:10.374104: step: 1424/530, loss: 0.06458606570959091
2023-01-23 01:56:11.583237: step: 1428/530, loss: 0.041750334203243256
2023-01-23 01:56:12.762566: step: 1432/530, loss: 0.004408073145896196
2023-01-23 01:56:13.943298: step: 1436/530, loss: 0.048647500574588776
2023-01-23 01:56:15.076358: step: 1440/530, loss: 0.01678643375635147
2023-01-23 01:56:16.283473: step: 1444/530, loss: 0.028554726392030716
2023-01-23 01:56:17.476629: step: 1448/530, loss: 0.03467092290520668
2023-01-23 01:56:18.625380: step: 1452/530, loss: 0.10060329735279083
2023-01-23 01:56:19.821741: step: 1456/530, loss: 0.05347652733325958
2023-01-23 01:56:20.979666: step: 1460/530, loss: 0.022730637341737747
2023-01-23 01:56:22.172434: step: 1464/530, loss: 0.07542820274829865
2023-01-23 01:56:23.342803: step: 1468/530, loss: 0.07027512043714523
2023-01-23 01:56:24.501044: step: 1472/530, loss: 0.005811500828713179
2023-01-23 01:56:25.624236: step: 1476/530, loss: 0.006807804107666016
2023-01-23 01:56:26.769171: step: 1480/530, loss: 0.07120266556739807
2023-01-23 01:56:27.916769: step: 1484/530, loss: 0.03455333784222603
2023-01-23 01:56:29.068861: step: 1488/530, loss: 0.01606917381286621
2023-01-23 01:56:30.207386: step: 1492/530, loss: 0.001522064208984375
2023-01-23 01:56:31.362386: step: 1496/530, loss: 0.01781024970114231
2023-01-23 01:56:32.511047: step: 1500/530, loss: 0.00594177283346653
2023-01-23 01:56:33.671775: step: 1504/530, loss: 0.03657646104693413
2023-01-23 01:56:34.848208: step: 1508/530, loss: 0.00032749175443314016
2023-01-23 01:56:36.067401: step: 1512/530, loss: 0.055272672325372696
2023-01-23 01:56:37.268948: step: 1516/530, loss: 0.021250629797577858
2023-01-23 01:56:38.451948: step: 1520/530, loss: 0.14078053832054138
2023-01-23 01:56:39.639343: step: 1524/530, loss: 0.020298361778259277
2023-01-23 01:56:40.842439: step: 1528/530, loss: 0.011423206888139248
2023-01-23 01:56:42.063613: step: 1532/530, loss: 0.002498626708984375
2023-01-23 01:56:43.216974: step: 1536/530, loss: 0.264875590801239
2023-01-23 01:56:44.411018: step: 1540/530, loss: 0.10807070881128311
2023-01-23 01:56:45.564572: step: 1544/530, loss: 0.009528923779726028
2023-01-23 01:56:46.715646: step: 1548/530, loss: 0.04711608961224556
2023-01-23 01:56:47.903638: step: 1552/530, loss: 0.03205166012048721
2023-01-23 01:56:49.080169: step: 1556/530, loss: 0.014445686712861061
2023-01-23 01:56:50.276574: step: 1560/530, loss: 0.03359420225024223
2023-01-23 01:56:51.471457: step: 1564/530, loss: 0.10994544625282288
2023-01-23 01:56:52.642438: step: 1568/530, loss: 0.01910562440752983
2023-01-23 01:56:53.810321: step: 1572/530, loss: 0.05439586937427521
2023-01-23 01:56:54.994729: step: 1576/530, loss: 0.08284874260425568
2023-01-23 01:56:56.191065: step: 1580/530, loss: 0.030953358858823776
2023-01-23 01:56:57.350134: step: 1584/530, loss: 0.004668903537094593
2023-01-23 01:56:58.503310: step: 1588/530, loss: 0.0002803802490234375
2023-01-23 01:56:59.709133: step: 1592/530, loss: 0.02082977443933487
2023-01-23 01:57:00.915427: step: 1596/530, loss: 0.02744166925549507
2023-01-23 01:57:02.093581: step: 1600/530, loss: 0.012082099914550781
2023-01-23 01:57:03.236523: step: 1604/530, loss: 0.03174562379717827
2023-01-23 01:57:04.395509: step: 1608/530, loss: 0.0059739588759839535
2023-01-23 01:57:05.568131: step: 1612/530, loss: 0.028591632843017578
2023-01-23 01:57:06.755976: step: 1616/530, loss: 0.03705187141895294
2023-01-23 01:57:07.914320: step: 1620/530, loss: 0.008844435214996338
2023-01-23 01:57:09.110838: step: 1624/530, loss: 0.03221893310546875
2023-01-23 01:57:10.296954: step: 1628/530, loss: 0.04294948652386665
2023-01-23 01:57:11.443014: step: 1632/530, loss: 0.06609401851892471
2023-01-23 01:57:12.636095: step: 1636/530, loss: 0.04906740039587021
2023-01-23 01:57:13.808351: step: 1640/530, loss: 0.009540081024169922
2023-01-23 01:57:14.937694: step: 1644/530, loss: 0.15140044689178467
2023-01-23 01:57:16.089865: step: 1648/530, loss: 0.0717153549194336
2023-01-23 01:57:17.277539: step: 1652/530, loss: 0.12203264236450195
2023-01-23 01:57:18.453776: step: 1656/530, loss: 0.02027897723019123
2023-01-23 01:57:19.611905: step: 1660/530, loss: 0.03621573746204376
2023-01-23 01:57:20.768625: step: 1664/530, loss: 0.01602344587445259
2023-01-23 01:57:21.961401: step: 1668/530, loss: 0.003793239826336503
2023-01-23 01:57:23.154208: step: 1672/530, loss: 0.1169290542602539
2023-01-23 01:57:24.390830: step: 1676/530, loss: 0.05004744604229927
2023-01-23 01:57:25.583443: step: 1680/530, loss: 0.006236935034394264
2023-01-23 01:57:26.813192: step: 1684/530, loss: 0.01991911046206951
2023-01-23 01:57:27.971519: step: 1688/530, loss: 0.02226683869957924
2023-01-23 01:57:29.194131: step: 1692/530, loss: 0.015440368093550205
2023-01-23 01:57:30.340648: step: 1696/530, loss: 0.08121337741613388
2023-01-23 01:57:31.519689: step: 1700/530, loss: 0.0019536970648914576
2023-01-23 01:57:32.733076: step: 1704/530, loss: 0.1464221477508545
2023-01-23 01:57:33.896641: step: 1708/530, loss: 0.04672107845544815
2023-01-23 01:57:35.060037: step: 1712/530, loss: 0.01932978630065918
2023-01-23 01:57:36.244716: step: 1716/530, loss: 0.07145671546459198
2023-01-23 01:57:37.382242: step: 1720/530, loss: 0.004661274142563343
2023-01-23 01:57:38.543651: step: 1724/530, loss: 0.037697192281484604
2023-01-23 01:57:39.685883: step: 1728/530, loss: 0.04180178791284561
2023-01-23 01:57:40.935768: step: 1732/530, loss: 0.06022663414478302
2023-01-23 01:57:42.126999: step: 1736/530, loss: 0.02742767333984375
2023-01-23 01:57:43.268414: step: 1740/530, loss: 0.021106483414769173
2023-01-23 01:57:44.457475: step: 1744/530, loss: 0.028363609686493874
2023-01-23 01:57:45.649975: step: 1748/530, loss: 0.0025877952575683594
2023-01-23 01:57:46.829701: step: 1752/530, loss: 0.008541298098862171
2023-01-23 01:57:48.010626: step: 1756/530, loss: 0.00593718932941556
2023-01-23 01:57:49.142528: step: 1760/530, loss: 0.028662586584687233
2023-01-23 01:57:50.327830: step: 1764/530, loss: 0.00020494460477493703
2023-01-23 01:57:51.475877: step: 1768/530, loss: 0.14434394240379333
2023-01-23 01:57:52.673430: step: 1772/530, loss: 0.030316734686493874
2023-01-23 01:57:53.875569: step: 1776/530, loss: 0.0392146110534668
2023-01-23 01:57:55.028186: step: 1780/530, loss: 0.0064931875094771385
2023-01-23 01:57:56.234074: step: 1784/530, loss: 0.006567955017089844
2023-01-23 01:57:57.412481: step: 1788/530, loss: 0.08336534351110458
2023-01-23 01:57:58.562149: step: 1792/530, loss: 0.007630825042724609
2023-01-23 01:57:59.722162: step: 1796/530, loss: 0.10943537205457687
2023-01-23 01:58:00.905071: step: 1800/530, loss: 0.007854938507080078
2023-01-23 01:58:02.077246: step: 1804/530, loss: 0.025266695767641068
2023-01-23 01:58:03.242110: step: 1808/530, loss: 0.09107495099306107
2023-01-23 01:58:04.438080: step: 1812/530, loss: 0.026578523218631744
2023-01-23 01:58:05.648957: step: 1816/530, loss: 0.0011942863930016756
2023-01-23 01:58:06.881203: step: 1820/530, loss: 0.010960960760712624
2023-01-23 01:58:08.054103: step: 1824/530, loss: 0.021959686651825905
2023-01-23 01:58:09.273774: step: 1828/530, loss: 0.005299925804138184
2023-01-23 01:58:10.438363: step: 1832/530, loss: 0.030454635620117188
2023-01-23 01:58:11.584632: step: 1836/530, loss: 0.005831241607666016
2023-01-23 01:58:12.708667: step: 1840/530, loss: 0.028088664636015892
2023-01-23 01:58:13.897003: step: 1844/530, loss: 0.038376886397600174
2023-01-23 01:58:15.066925: step: 1848/530, loss: 0.004767322447150946
2023-01-23 01:58:16.261930: step: 1852/530, loss: 0.04879160225391388
2023-01-23 01:58:17.434519: step: 1856/530, loss: 0.0028648721054196358
2023-01-23 01:58:18.622363: step: 1860/530, loss: 0.11395607888698578
2023-01-23 01:58:19.809632: step: 1864/530, loss: 0.010779762640595436
2023-01-23 01:58:20.932624: step: 1868/530, loss: 0.8157111406326294
2023-01-23 01:58:22.080467: step: 1872/530, loss: 0.07138185948133469
2023-01-23 01:58:23.287708: step: 1876/530, loss: 0.0043167113326489925
2023-01-23 01:58:24.472556: step: 1880/530, loss: 0.006344032008200884
2023-01-23 01:58:25.706433: step: 1884/530, loss: 0.20362864434719086
2023-01-23 01:58:26.884897: step: 1888/530, loss: 0.004898118786513805
2023-01-23 01:58:28.082389: step: 1892/530, loss: 0.022330617532134056
2023-01-23 01:58:29.257310: step: 1896/530, loss: 0.004425049293786287
2023-01-23 01:58:30.403504: step: 1900/530, loss: 0.6054101586341858
2023-01-23 01:58:31.564908: step: 1904/530, loss: 0.049509335309267044
2023-01-23 01:58:32.782156: step: 1908/530, loss: 0.07069572061300278
2023-01-23 01:58:33.945785: step: 1912/530, loss: 0.06323103606700897
2023-01-23 01:58:35.112294: step: 1916/530, loss: 0.12586307525634766
2023-01-23 01:58:36.295158: step: 1920/530, loss: 0.014882659539580345
2023-01-23 01:58:37.455000: step: 1924/530, loss: 0.026545144617557526
2023-01-23 01:58:38.624280: step: 1928/530, loss: 0.0905529037117958
2023-01-23 01:58:39.785869: step: 1932/530, loss: 0.0048423768021166325
2023-01-23 01:58:40.958076: step: 1936/530, loss: 0.06902284920215607
2023-01-23 01:58:42.171984: step: 1940/530, loss: 0.028437232598662376
2023-01-23 01:58:43.322975: step: 1944/530, loss: 0.2937842309474945
2023-01-23 01:58:44.502264: step: 1948/530, loss: 0.03400421142578125
2023-01-23 01:58:45.681283: step: 1952/530, loss: 0.047776319086551666
2023-01-23 01:58:46.812418: step: 1956/530, loss: 0.34312230348587036
2023-01-23 01:58:48.022330: step: 1960/530, loss: 0.011840534396469593
2023-01-23 01:58:49.185259: step: 1964/530, loss: 0.004528999328613281
2023-01-23 01:58:50.334399: step: 1968/530, loss: 0.016599083319306374
2023-01-23 01:58:51.478492: step: 1972/530, loss: 0.008021545596420765
2023-01-23 01:58:52.638799: step: 1976/530, loss: 0.03904872015118599
2023-01-23 01:58:53.814235: step: 1980/530, loss: 0.2406059205532074
2023-01-23 01:58:54.995675: step: 1984/530, loss: 0.09173736721277237
2023-01-23 01:58:56.130676: step: 1988/530, loss: 0.07246027141809464
2023-01-23 01:58:57.269191: step: 1992/530, loss: 0.0022140503861010075
2023-01-23 01:58:58.406115: step: 1996/530, loss: 0.0005724430084228516
2023-01-23 01:58:59.538631: step: 2000/530, loss: 0.0006843566661700606
2023-01-23 01:59:00.707389: step: 2004/530, loss: 0.006539082620292902
2023-01-23 01:59:01.890852: step: 2008/530, loss: 0.021462690085172653
2023-01-23 01:59:03.073999: step: 2012/530, loss: 0.0559362918138504
2023-01-23 01:59:04.204640: step: 2016/530, loss: 0.010561943054199219
2023-01-23 01:59:05.390012: step: 2020/530, loss: 0.0350530631840229
2023-01-23 01:59:06.567213: step: 2024/530, loss: 0.014557457529008389
2023-01-23 01:59:07.751145: step: 2028/530, loss: 0.15231746435165405
2023-01-23 01:59:08.902722: step: 2032/530, loss: 0.06092491373419762
2023-01-23 01:59:10.065273: step: 2036/530, loss: 0.05775924026966095
2023-01-23 01:59:11.245715: step: 2040/530, loss: 0.12214555591344833
2023-01-23 01:59:12.387346: step: 2044/530, loss: 0.12388335168361664
2023-01-23 01:59:13.560377: step: 2048/530, loss: 1.0693259239196777
2023-01-23 01:59:14.781243: step: 2052/530, loss: 0.05169949680566788
2023-01-23 01:59:15.981406: step: 2056/530, loss: 0.006696128752082586
2023-01-23 01:59:17.160228: step: 2060/530, loss: 0.03417492285370827
2023-01-23 01:59:18.368267: step: 2064/530, loss: 0.04913969337940216
2023-01-23 01:59:19.563380: step: 2068/530, loss: 0.0028133392333984375
2023-01-23 01:59:20.738331: step: 2072/530, loss: 0.005373859778046608
2023-01-23 01:59:21.912518: step: 2076/530, loss: 0.050955869257450104
2023-01-23 01:59:23.069699: step: 2080/530, loss: 0.012179946526885033
2023-01-23 01:59:24.260944: step: 2084/530, loss: 0.057327937334775925
2023-01-23 01:59:25.443814: step: 2088/530, loss: 0.15411490201950073
2023-01-23 01:59:26.629123: step: 2092/530, loss: 0.028712939471006393
2023-01-23 01:59:27.829463: step: 2096/530, loss: 0.02039518393576145
2023-01-23 01:59:29.056962: step: 2100/530, loss: 0.04087676852941513
2023-01-23 01:59:30.248037: step: 2104/530, loss: 0.0045900107361376286
2023-01-23 01:59:31.471587: step: 2108/530, loss: 0.08083444088697433
2023-01-23 01:59:32.637102: step: 2112/530, loss: 0.7785191535949707
2023-01-23 01:59:33.784919: step: 2116/530, loss: 0.02292471006512642
2023-01-23 01:59:34.979651: step: 2120/530, loss: 0.046098992228507996
==================================================
Loss: 0.067
--------------------
Dev: {'event': {'p': 0.613588110403397, 'r': 0.7696404793608522, 'f1': 0.6828115770821027}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Test: {'event': {'p': 0.6631878557874763, 'r': 0.8039102932719954, 'f1': 0.726800103977125}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Chinese: {'event': {'p': 0.5975609756097561, 'r': 0.9074074074074074, 'f1': 0.7205882352941176}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Korean: {'event': {'p': 0.6326530612244898, 'r': 0.49206349206349204, 'f1': 0.5535714285714285}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Russian: {'event': {'p': 0.4888888888888889, 'r': 0.6111111111111112, 'f1': 0.5432098765432098}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6351501668520578, 'r': 0.7603195739014648, 'f1': 0.6921212121212121}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Chinese: {'event': {'p': 0.6373175182481752, 'r': 0.8033352501437608, 'f1': 0.7107606207071993}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Chinese: {'event': {'p': 0.5903614457831325, 'r': 0.9074074074074074, 'f1': 0.7153284671532847}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5733990147783251, 'r': 0.7749667110519307, 'f1': 0.6591166477916196}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Eng Test for Korean: {'event': {'p': 0.6218005295675199, 'r': 0.8102357676825762, 'f1': 0.7036204744069912}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Sample Korean: {'event': {'p': 0.6417910447761194, 'r': 0.6825396825396826, 'f1': 0.6615384615384614}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5951882845188284, 'r': 0.7576564580559254, 'f1': 0.6666666666666666}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6663405088062623, 'r': 0.7832087406555491, 'f1': 0.7200634417129264}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5, 'r': 0.6666666666666666, 'f1': 0.5714285714285715}, '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 02:00:17.501389: step: 4/530, loss: 0.02861766889691353
2023-01-23 02:00:18.650401: step: 8/530, loss: 0.007576751988381147
2023-01-23 02:00:19.804223: step: 12/530, loss: 0.009433556348085403
2023-01-23 02:00:20.948717: step: 16/530, loss: 0.048389531672000885
2023-01-23 02:00:22.103440: step: 20/530, loss: 0.015052604489028454
2023-01-23 02:00:23.324120: step: 24/530, loss: 0.025703048333525658
2023-01-23 02:00:24.505447: step: 28/530, loss: 0.06493663787841797
2023-01-23 02:00:25.712307: step: 32/530, loss: 0.03152313083410263
2023-01-23 02:00:26.876732: step: 36/530, loss: 0.006931495852768421
2023-01-23 02:00:28.040046: step: 40/530, loss: 0.018326856195926666
2023-01-23 02:00:29.214226: step: 44/530, loss: 0.016199683770537376
2023-01-23 02:00:30.390781: step: 48/530, loss: 0.05742035061120987
2023-01-23 02:00:31.589058: step: 52/530, loss: 0.05046539381146431
2023-01-23 02:00:32.799640: step: 56/530, loss: 0.022667884826660156
2023-01-23 02:00:33.895207: step: 60/530, loss: 0.010160446166992188
2023-01-23 02:00:35.064823: step: 64/530, loss: 0.0015917777782306075
2023-01-23 02:00:36.203149: step: 68/530, loss: 0.01690683513879776
2023-01-23 02:00:37.367611: step: 72/530, loss: 0.02967357635498047
2023-01-23 02:00:38.550784: step: 76/530, loss: 0.05246458202600479
2023-01-23 02:00:39.733369: step: 80/530, loss: 0.0419306755065918
2023-01-23 02:00:40.875988: step: 84/530, loss: 0.04666309431195259
2023-01-23 02:00:42.078295: step: 88/530, loss: 0.001583099365234375
2023-01-23 02:00:43.229459: step: 92/530, loss: 0.0532168410718441
2023-01-23 02:00:44.419457: step: 96/530, loss: 0.2235923707485199
2023-01-23 02:00:45.566510: step: 100/530, loss: 0.12930116057395935
2023-01-23 02:00:46.734603: step: 104/530, loss: 0.0007921606302261353
2023-01-23 02:00:47.924390: step: 108/530, loss: 0.022526836022734642
2023-01-23 02:00:49.074578: step: 112/530, loss: 0.00994100607931614
2023-01-23 02:00:50.280093: step: 116/530, loss: 0.036127280443906784
2023-01-23 02:00:51.430175: step: 120/530, loss: 0.001628446625545621
2023-01-23 02:00:52.647060: step: 124/530, loss: 0.03671570122241974
2023-01-23 02:00:53.831250: step: 128/530, loss: 0.0697443038225174
2023-01-23 02:00:55.003098: step: 132/530, loss: 0.014757538214325905
2023-01-23 02:00:56.175860: step: 136/530, loss: 0.04543915018439293
2023-01-23 02:00:57.339003: step: 140/530, loss: 0.032637644559144974
2023-01-23 02:00:58.494671: step: 144/530, loss: 0.019971562549471855
2023-01-23 02:00:59.694576: step: 148/530, loss: 0.3105713725090027
2023-01-23 02:01:00.851127: step: 152/530, loss: 0.010465716943144798
2023-01-23 02:01:02.042226: step: 156/530, loss: 0.007421970367431641
2023-01-23 02:01:03.220112: step: 160/530, loss: 0.024837683886289597
2023-01-23 02:01:04.415870: step: 164/530, loss: 0.05188927799463272
2023-01-23 02:01:05.566950: step: 168/530, loss: 0.019368935376405716
2023-01-23 02:01:06.740554: step: 172/530, loss: 0.010196780785918236
2023-01-23 02:01:07.917118: step: 176/530, loss: 0.03295879438519478
2023-01-23 02:01:09.099047: step: 180/530, loss: 0.014865444973111153
2023-01-23 02:01:10.252284: step: 184/530, loss: 0.02180042304098606
2023-01-23 02:01:11.423337: step: 188/530, loss: 0.011869240552186966
2023-01-23 02:01:12.593746: step: 192/530, loss: 0.013792610727250576
2023-01-23 02:01:13.782512: step: 196/530, loss: 0.004962635226547718
2023-01-23 02:01:15.052656: step: 200/530, loss: 0.435743510723114
2023-01-23 02:01:16.212352: step: 204/530, loss: 0.16979655623435974
2023-01-23 02:01:17.397458: step: 208/530, loss: 0.0030931474175304174
2023-01-23 02:01:18.589383: step: 212/530, loss: 0.04576960578560829
2023-01-23 02:01:19.755774: step: 216/530, loss: 0.00040149688720703125
2023-01-23 02:01:20.955585: step: 220/530, loss: 0.03708569332957268
2023-01-23 02:01:22.121105: step: 224/530, loss: 0.0022191046737134457
2023-01-23 02:01:23.330882: step: 228/530, loss: 0.0016133307944983244
2023-01-23 02:01:24.520049: step: 232/530, loss: 0.0034082415513694286
2023-01-23 02:01:25.688164: step: 236/530, loss: 0.01021347101777792
2023-01-23 02:01:26.835912: step: 240/530, loss: 0.011389371007680893
2023-01-23 02:01:28.010917: step: 244/530, loss: 0.0029294968117028475
2023-01-23 02:01:29.184513: step: 248/530, loss: 0.009447479620575905
2023-01-23 02:01:30.334549: step: 252/530, loss: 0.01544799841940403
2023-01-23 02:01:31.533716: step: 256/530, loss: 0.06333966553211212
2023-01-23 02:01:32.692619: step: 260/530, loss: 0.06411246955394745
2023-01-23 02:01:33.854954: step: 264/530, loss: 0.03105149231851101
2023-01-23 02:01:35.012313: step: 268/530, loss: 0.0003105163632426411
2023-01-23 02:01:36.226994: step: 272/530, loss: 0.02781658060848713
2023-01-23 02:01:37.425080: step: 276/530, loss: 0.03851080313324928
2023-01-23 02:01:38.582872: step: 280/530, loss: 0.014957237057387829
2023-01-23 02:01:39.782910: step: 284/530, loss: 0.05188131704926491
2023-01-23 02:01:40.974795: step: 288/530, loss: 0.03757172077894211
2023-01-23 02:01:42.154686: step: 292/530, loss: 0.02761058881878853
2023-01-23 02:01:43.362483: step: 296/530, loss: 0.01653881184756756
2023-01-23 02:01:44.534181: step: 300/530, loss: 0.016524937003850937
2023-01-23 02:01:45.672988: step: 304/530, loss: 0.008461189456284046
2023-01-23 02:01:46.873598: step: 308/530, loss: 8.053779311012477e-05
2023-01-23 02:01:48.036377: step: 312/530, loss: 0.0366273894906044
2023-01-23 02:01:49.199410: step: 316/530, loss: 0.0012909173965454102
2023-01-23 02:01:50.405358: step: 320/530, loss: 0.023801803588867188
2023-01-23 02:01:51.563395: step: 324/530, loss: 0.0008293151622638106
2023-01-23 02:01:52.745696: step: 328/530, loss: 0.03199362754821777
2023-01-23 02:01:53.911168: step: 332/530, loss: 0.13491645455360413
2023-01-23 02:01:55.095051: step: 336/530, loss: 0.011737728491425514
2023-01-23 02:01:56.235020: step: 340/530, loss: 0.024299239739775658
2023-01-23 02:01:57.378203: step: 344/530, loss: 0.09101152420043945
2023-01-23 02:01:58.530874: step: 348/530, loss: 0.026349259540438652
2023-01-23 02:01:59.710719: step: 352/530, loss: 0.031373120844364166
2023-01-23 02:02:00.893680: step: 356/530, loss: 0.03548755869269371
2023-01-23 02:02:02.050135: step: 360/530, loss: 0.00036029814509674907
2023-01-23 02:02:03.224443: step: 364/530, loss: 0.00864486675709486
2023-01-23 02:02:04.400040: step: 368/530, loss: 0.009332561865448952
2023-01-23 02:02:05.651984: step: 372/530, loss: 0.07937565445899963
2023-01-23 02:02:06.807315: step: 376/530, loss: 0.0010450363624840975
2023-01-23 02:02:07.961061: step: 380/530, loss: 0.06399812549352646
2023-01-23 02:02:09.138832: step: 384/530, loss: 0.0003124237118754536
2023-01-23 02:02:10.325356: step: 388/530, loss: 0.01813633367419243
2023-01-23 02:02:11.483244: step: 392/530, loss: 0.01724863052368164
2023-01-23 02:02:12.651248: step: 396/530, loss: 0.011632204055786133
2023-01-23 02:02:13.837274: step: 400/530, loss: 0.01971001736819744
2023-01-23 02:02:15.004674: step: 404/530, loss: 0.046515464782714844
2023-01-23 02:02:16.110456: step: 408/530, loss: 0.030553722754120827
2023-01-23 02:02:17.292332: step: 412/530, loss: 0.07802248001098633
2023-01-23 02:02:18.493900: step: 416/530, loss: 0.08156929165124893
2023-01-23 02:02:19.664390: step: 420/530, loss: 0.05500011891126633
2023-01-23 02:02:20.853984: step: 424/530, loss: 0.003023648401722312
2023-01-23 02:02:22.010277: step: 428/530, loss: 0.007271194364875555
2023-01-23 02:02:23.176561: step: 432/530, loss: 0.006418276112526655
2023-01-23 02:02:24.350780: step: 436/530, loss: 9.250640869140625e-05
2023-01-23 02:02:25.511928: step: 440/530, loss: 0.018711091950535774
2023-01-23 02:02:26.712889: step: 444/530, loss: 0.002716541290283203
2023-01-23 02:02:27.883808: step: 448/530, loss: 0.12147793918848038
2023-01-23 02:02:29.093101: step: 452/530, loss: 0.018365859985351562
2023-01-23 02:02:30.273774: step: 456/530, loss: 0.044822487980127335
2023-01-23 02:02:31.419943: step: 460/530, loss: 0.003572750138118863
2023-01-23 02:02:32.593729: step: 464/530, loss: 0.7648254632949829
2023-01-23 02:02:33.765409: step: 468/530, loss: 0.03791303560137749
2023-01-23 02:02:34.930512: step: 472/530, loss: 0.21308287978172302
2023-01-23 02:02:36.087557: step: 476/530, loss: 0.041108131408691406
2023-01-23 02:02:37.241515: step: 480/530, loss: 0.007944297976791859
2023-01-23 02:02:38.387993: step: 484/530, loss: 0.9014477133750916
2023-01-23 02:02:39.565958: step: 488/530, loss: 0.00682024983689189
2023-01-23 02:02:40.722730: step: 492/530, loss: 0.030964158475399017
2023-01-23 02:02:41.885252: step: 496/530, loss: 0.05017905309796333
2023-01-23 02:02:43.046876: step: 500/530, loss: 0.0033727409318089485
2023-01-23 02:02:44.228929: step: 504/530, loss: 0.016001766547560692
2023-01-23 02:02:45.409774: step: 508/530, loss: 0.0001224517764057964
2023-01-23 02:02:46.590078: step: 512/530, loss: 0.07434673607349396
2023-01-23 02:02:47.769911: step: 516/530, loss: 0.04481200873851776
2023-01-23 02:02:48.971332: step: 520/530, loss: 0.0011455535423010588
2023-01-23 02:02:50.136590: step: 524/530, loss: 0.021541310474276543
2023-01-23 02:02:51.327393: step: 528/530, loss: 0.043240927159786224
2023-01-23 02:02:52.504105: step: 532/530, loss: 0.030040359124541283
2023-01-23 02:02:53.692928: step: 536/530, loss: 0.04299335554242134
2023-01-23 02:02:54.927511: step: 540/530, loss: 0.003161621280014515
2023-01-23 02:02:56.083928: step: 544/530, loss: 0.006895989179611206
2023-01-23 02:02:57.216795: step: 548/530, loss: 0.005281686782836914
2023-01-23 02:02:58.388526: step: 552/530, loss: 0.00727005023509264
2023-01-23 02:02:59.565232: step: 556/530, loss: 0.003036069916561246
2023-01-23 02:03:00.739743: step: 560/530, loss: 0.2000894546508789
2023-01-23 02:03:01.919388: step: 564/530, loss: 0.0015523433685302734
2023-01-23 02:03:03.142522: step: 568/530, loss: 0.03081808239221573
2023-01-23 02:03:04.319799: step: 572/530, loss: 0.04420357197523117
2023-01-23 02:03:05.491247: step: 576/530, loss: 0.09724970161914825
2023-01-23 02:03:06.676291: step: 580/530, loss: 0.0021519423462450504
2023-01-23 02:03:07.878925: step: 584/530, loss: 0.04981289058923721
2023-01-23 02:03:09.060032: step: 588/530, loss: 0.0010624408023431897
2023-01-23 02:03:10.230003: step: 592/530, loss: 0.15844625234603882
2023-01-23 02:03:11.391326: step: 596/530, loss: 0.1504998356103897
2023-01-23 02:03:12.549543: step: 600/530, loss: 0.08084221184253693
2023-01-23 02:03:13.712084: step: 604/530, loss: 0.00318489084020257
2023-01-23 02:03:14.888072: step: 608/530, loss: 0.036949921399354935
2023-01-23 02:03:16.079215: step: 612/530, loss: 0.016592122614383698
2023-01-23 02:03:17.261534: step: 616/530, loss: 0.08017349243164062
2023-01-23 02:03:18.429031: step: 620/530, loss: 0.06752233952283859
2023-01-23 02:03:19.585261: step: 624/530, loss: 0.0604739673435688
2023-01-23 02:03:20.753041: step: 628/530, loss: 0.08401575684547424
2023-01-23 02:03:21.970459: step: 632/530, loss: 0.05499892309308052
2023-01-23 02:03:23.156056: step: 636/530, loss: 0.031900547444820404
2023-01-23 02:03:24.344686: step: 640/530, loss: 0.002302026841789484
2023-01-23 02:03:25.530294: step: 644/530, loss: 0.009116267785429955
2023-01-23 02:03:26.723617: step: 648/530, loss: 0.07885608822107315
2023-01-23 02:03:27.872613: step: 652/530, loss: 0.02750530280172825
2023-01-23 02:03:29.032918: step: 656/530, loss: 0.012879181653261185
2023-01-23 02:03:30.210520: step: 660/530, loss: 0.03186340257525444
2023-01-23 02:03:31.392329: step: 664/530, loss: 0.005229854956269264
2023-01-23 02:03:32.559442: step: 668/530, loss: 0.0010556221241131425
2023-01-23 02:03:33.750130: step: 672/530, loss: 0.19363000988960266
2023-01-23 02:03:34.918930: step: 676/530, loss: 0.04679255187511444
2023-01-23 02:03:36.078742: step: 680/530, loss: 0.05420274659991264
2023-01-23 02:03:37.247207: step: 684/530, loss: 0.018144989386200905
2023-01-23 02:03:38.444147: step: 688/530, loss: 0.02951631508767605
2023-01-23 02:03:39.649767: step: 692/530, loss: 0.01581134833395481
2023-01-23 02:03:40.821518: step: 696/530, loss: 0.056913089007139206
2023-01-23 02:03:42.018522: step: 700/530, loss: 0.02740616723895073
2023-01-23 02:03:43.182907: step: 704/530, loss: 0.0027685165405273438
2023-01-23 02:03:44.369856: step: 708/530, loss: 0.02155456691980362
2023-01-23 02:03:45.533360: step: 712/530, loss: 0.5384508967399597
2023-01-23 02:03:46.766086: step: 716/530, loss: 0.057607077062129974
2023-01-23 02:03:47.973710: step: 720/530, loss: 0.03325338289141655
2023-01-23 02:03:49.151128: step: 724/530, loss: 0.06819362938404083
2023-01-23 02:03:50.302796: step: 728/530, loss: 0.01794595830142498
2023-01-23 02:03:51.480432: step: 732/530, loss: 0.047089386731386185
2023-01-23 02:03:52.646946: step: 736/530, loss: 0.039314351975917816
2023-01-23 02:03:53.844774: step: 740/530, loss: 0.1279180943965912
2023-01-23 02:03:55.049698: step: 744/530, loss: 0.025859545916318893
2023-01-23 02:03:56.193739: step: 748/530, loss: 0.008913707919418812
2023-01-23 02:03:57.350809: step: 752/530, loss: 0.01743330992758274
2023-01-23 02:03:58.542895: step: 756/530, loss: 0.0414886474609375
2023-01-23 02:03:59.713357: step: 760/530, loss: 0.0010725022293627262
2023-01-23 02:04:00.885805: step: 764/530, loss: 0.04817771911621094
2023-01-23 02:04:02.072948: step: 768/530, loss: 0.003217315534129739
2023-01-23 02:04:03.257191: step: 772/530, loss: 0.07857837527990341
2023-01-23 02:04:04.456871: step: 776/530, loss: 0.017726801335811615
2023-01-23 02:04:05.631037: step: 780/530, loss: 0.030484486371278763
2023-01-23 02:04:06.796542: step: 784/530, loss: 0.02863159216940403
2023-01-23 02:04:07.968041: step: 788/530, loss: 0.0013018609024584293
2023-01-23 02:04:09.117547: step: 792/530, loss: 0.010592461563646793
2023-01-23 02:04:10.331576: step: 796/530, loss: 0.01967344433069229
2023-01-23 02:04:11.496479: step: 800/530, loss: 0.04925537109375
2023-01-23 02:04:12.699838: step: 804/530, loss: 0.0899820402264595
2023-01-23 02:04:13.844308: step: 808/530, loss: 0.03359708935022354
2023-01-23 02:04:15.031741: step: 812/530, loss: 0.00382652273401618
2023-01-23 02:04:16.187897: step: 816/530, loss: 0.05983119085431099
2023-01-23 02:04:17.379076: step: 820/530, loss: 0.003077983856201172
2023-01-23 02:04:18.542051: step: 824/530, loss: 0.05077343061566353
2023-01-23 02:04:19.692971: step: 828/530, loss: 0.006889295764267445
2023-01-23 02:04:20.869276: step: 832/530, loss: 0.09661149978637695
2023-01-23 02:04:22.016972: step: 836/530, loss: 0.031653691083192825
2023-01-23 02:04:23.197526: step: 840/530, loss: 0.04574785381555557
2023-01-23 02:04:24.388208: step: 844/530, loss: 0.044326018542051315
2023-01-23 02:04:25.534017: step: 848/530, loss: 0.005500888917595148
2023-01-23 02:04:26.706847: step: 852/530, loss: 0.003118896624073386
2023-01-23 02:04:27.859710: step: 856/530, loss: 0.0013906002277508378
2023-01-23 02:04:29.066413: step: 860/530, loss: 0.0016504287486895919
2023-01-23 02:04:30.239449: step: 864/530, loss: 0.5100079774856567
2023-01-23 02:04:31.430711: step: 868/530, loss: 0.022423982620239258
2023-01-23 02:04:32.658931: step: 872/530, loss: 0.027982044965028763
2023-01-23 02:04:33.861235: step: 876/530, loss: 0.14508409798145294
2023-01-23 02:04:35.034563: step: 880/530, loss: 0.04071082919836044
2023-01-23 02:04:36.201902: step: 884/530, loss: 0.06281118094921112
2023-01-23 02:04:37.429354: step: 888/530, loss: 0.04635439068078995
2023-01-23 02:04:38.604985: step: 892/530, loss: 0.0015818595420569181
2023-01-23 02:04:39.724918: step: 896/530, loss: 0.06765918433666229
2023-01-23 02:04:40.904800: step: 900/530, loss: 0.0043177129700779915
2023-01-23 02:04:42.063568: step: 904/530, loss: 0.0007412910345010459
2023-01-23 02:04:43.227615: step: 908/530, loss: 0.004104328341782093
2023-01-23 02:04:44.441039: step: 912/530, loss: 0.1634574830532074
2023-01-23 02:04:45.580697: step: 916/530, loss: 0.015868186950683594
2023-01-23 02:04:46.740834: step: 920/530, loss: 0.1938001662492752
2023-01-23 02:04:47.902572: step: 924/530, loss: 0.005743575282394886
2023-01-23 02:04:49.043449: step: 928/530, loss: 0.01637239381670952
2023-01-23 02:04:50.190718: step: 932/530, loss: 0.12501315772533417
2023-01-23 02:04:51.331393: step: 936/530, loss: 0.07079906761646271
2023-01-23 02:04:52.472069: step: 940/530, loss: 0.022710038349032402
2023-01-23 02:04:53.711583: step: 944/530, loss: 0.00318660750053823
2023-01-23 02:04:54.878253: step: 948/530, loss: 0.05477261543273926
2023-01-23 02:04:56.040291: step: 952/530, loss: 0.005396461579948664
2023-01-23 02:04:57.250491: step: 956/530, loss: 0.022456789389252663
2023-01-23 02:04:58.434885: step: 960/530, loss: 0.0454380065202713
2023-01-23 02:04:59.613173: step: 964/530, loss: 0.0349576473236084
2023-01-23 02:05:00.765418: step: 968/530, loss: 0.2040906846523285
2023-01-23 02:05:01.934200: step: 972/530, loss: 0.03086109273135662
2023-01-23 02:05:03.111725: step: 976/530, loss: 0.001462745713070035
2023-01-23 02:05:04.297293: step: 980/530, loss: 0.006218624301254749
2023-01-23 02:05:05.461932: step: 984/530, loss: 0.012676960788667202
2023-01-23 02:05:06.622158: step: 988/530, loss: 0.030625535175204277
2023-01-23 02:05:07.771258: step: 992/530, loss: 0.006389808841049671
2023-01-23 02:05:08.926272: step: 996/530, loss: 0.03521919250488281
2023-01-23 02:05:10.126381: step: 1000/530, loss: 0.0711248368024826
2023-01-23 02:05:11.310660: step: 1004/530, loss: 0.4516476094722748
2023-01-23 02:05:12.472869: step: 1008/530, loss: 0.08084497600793839
2023-01-23 02:05:13.628873: step: 1012/530, loss: 0.037183571606874466
2023-01-23 02:05:14.838991: step: 1016/530, loss: 0.02343006245791912
2023-01-23 02:05:15.976873: step: 1020/530, loss: 0.030205916613340378
2023-01-23 02:05:17.148793: step: 1024/530, loss: 0.0069265603087842464
2023-01-23 02:05:18.324810: step: 1028/530, loss: 0.03138399124145508
2023-01-23 02:05:19.487239: step: 1032/530, loss: 0.2080448567867279
2023-01-23 02:05:20.661206: step: 1036/530, loss: 0.016057683154940605
2023-01-23 02:05:21.824802: step: 1040/530, loss: 0.009854758158326149
2023-01-23 02:05:23.013473: step: 1044/530, loss: 0.0025699613615870476
2023-01-23 02:05:24.203487: step: 1048/530, loss: 0.007089519873261452
2023-01-23 02:05:25.388098: step: 1052/530, loss: 0.001720094820484519
2023-01-23 02:05:26.597625: step: 1056/530, loss: 0.03613109886646271
2023-01-23 02:05:27.779975: step: 1060/530, loss: 0.05500316619873047
2023-01-23 02:05:28.953489: step: 1064/530, loss: 0.02976360358297825
2023-01-23 02:05:30.098538: step: 1068/530, loss: 0.04345393180847168
2023-01-23 02:05:31.265009: step: 1072/530, loss: 0.018426895141601562
2023-01-23 02:05:32.433141: step: 1076/530, loss: 0.027219295501708984
2023-01-23 02:05:33.611243: step: 1080/530, loss: 0.05236215889453888
2023-01-23 02:05:34.770123: step: 1084/530, loss: 0.004300212953239679
2023-01-23 02:05:35.937937: step: 1088/530, loss: 0.008438682183623314
2023-01-23 02:05:37.093060: step: 1092/530, loss: 0.05838584899902344
2023-01-23 02:05:38.228455: step: 1096/530, loss: 0.015949105843901634
2023-01-23 02:05:39.382449: step: 1100/530, loss: 0.018606949597597122
2023-01-23 02:05:40.544792: step: 1104/530, loss: 0.01111612282693386
2023-01-23 02:05:41.719444: step: 1108/530, loss: 0.034040018916130066
2023-01-23 02:05:42.903161: step: 1112/530, loss: 0.02906627580523491
2023-01-23 02:05:44.038642: step: 1116/530, loss: 0.0007879257318563759
2023-01-23 02:05:45.180502: step: 1120/530, loss: 0.026818467304110527
2023-01-23 02:05:46.341634: step: 1124/530, loss: 0.011390876956284046
2023-01-23 02:05:47.514622: step: 1128/530, loss: 0.07379169017076492
2023-01-23 02:05:48.701939: step: 1132/530, loss: 0.027565576136112213
2023-01-23 02:05:49.844862: step: 1136/530, loss: 0.04830484092235565
2023-01-23 02:05:50.984974: step: 1140/530, loss: 0.011463964357972145
2023-01-23 02:05:52.135682: step: 1144/530, loss: 0.0051781656220555305
2023-01-23 02:05:53.326272: step: 1148/530, loss: 0.028452303260564804
2023-01-23 02:05:54.485800: step: 1152/530, loss: 0.0016143799293786287
2023-01-23 02:05:55.661609: step: 1156/530, loss: 0.0073677063919603825
2023-01-23 02:05:56.816111: step: 1160/530, loss: 0.004320573527365923
2023-01-23 02:05:57.988933: step: 1164/530, loss: 0.0498235709965229
2023-01-23 02:05:59.105019: step: 1168/530, loss: 0.02599926106631756
2023-01-23 02:06:00.338065: step: 1172/530, loss: 0.006445980165153742
2023-01-23 02:06:01.481336: step: 1176/530, loss: 0.06946630775928497
2023-01-23 02:06:02.634398: step: 1180/530, loss: 0.04059161990880966
2023-01-23 02:06:03.828342: step: 1184/530, loss: 0.7745113372802734
2023-01-23 02:06:05.027832: step: 1188/530, loss: 0.004688644781708717
2023-01-23 02:06:06.176318: step: 1192/530, loss: 0.05381498485803604
2023-01-23 02:06:07.319561: step: 1196/530, loss: 0.12576213479042053
2023-01-23 02:06:08.518696: step: 1200/530, loss: 0.055941104888916016
2023-01-23 02:06:09.680249: step: 1204/530, loss: 0.0019638061057776213
2023-01-23 02:06:10.862777: step: 1208/530, loss: 0.0069900513626635075
2023-01-23 02:06:12.051431: step: 1212/530, loss: 0.025630176067352295
2023-01-23 02:06:13.208093: step: 1216/530, loss: 0.008081626147031784
2023-01-23 02:06:14.387235: step: 1220/530, loss: 0.197139173746109
2023-01-23 02:06:15.572764: step: 1224/530, loss: 0.21018867194652557
2023-01-23 02:06:16.794470: step: 1228/530, loss: 0.03912658616900444
2023-01-23 02:06:18.012453: step: 1232/530, loss: 0.009834576398134232
2023-01-23 02:06:19.184159: step: 1236/530, loss: 0.022298814728856087
2023-01-23 02:06:20.421132: step: 1240/530, loss: 0.04949913173913956
2023-01-23 02:06:21.644070: step: 1244/530, loss: 0.0898275375366211
2023-01-23 02:06:22.799177: step: 1248/530, loss: 0.015247059054672718
2023-01-23 02:06:23.920695: step: 1252/530, loss: 0.0723399668931961
2023-01-23 02:06:25.085953: step: 1256/530, loss: 0.06293907016515732
2023-01-23 02:06:26.260949: step: 1260/530, loss: 0.0009050369262695312
2023-01-23 02:06:27.455969: step: 1264/530, loss: 0.002594518708065152
2023-01-23 02:06:28.573552: step: 1268/530, loss: 0.002685463521629572
2023-01-23 02:06:29.775113: step: 1272/530, loss: 0.057027675211429596
2023-01-23 02:06:30.947847: step: 1276/530, loss: 0.08052831143140793
2023-01-23 02:06:32.085909: step: 1280/530, loss: 0.01505060214549303
2023-01-23 02:06:33.225184: step: 1284/530, loss: 0.029803801327943802
2023-01-23 02:06:34.420072: step: 1288/530, loss: 0.025468112900853157
2023-01-23 02:06:35.553262: step: 1292/530, loss: 0.00043969156104139984
2023-01-23 02:06:36.711429: step: 1296/530, loss: 0.010682773776352406
2023-01-23 02:06:37.874322: step: 1300/530, loss: 0.1137937605381012
2023-01-23 02:06:39.067702: step: 1304/530, loss: 0.027657128870487213
2023-01-23 02:06:40.227835: step: 1308/530, loss: 0.011874580755829811
2023-01-23 02:06:41.429197: step: 1312/530, loss: 0.04600878059864044
2023-01-23 02:06:42.631212: step: 1316/530, loss: 0.0014074326027184725
2023-01-23 02:06:43.775157: step: 1320/530, loss: 0.021350719034671783
2023-01-23 02:06:44.954978: step: 1324/530, loss: 0.012481975369155407
2023-01-23 02:06:46.114392: step: 1328/530, loss: 0.0025527954567223787
2023-01-23 02:06:47.276255: step: 1332/530, loss: 0.047113802284002304
2023-01-23 02:06:48.426591: step: 1336/530, loss: 0.0023443223908543587
2023-01-23 02:06:49.599698: step: 1340/530, loss: 0.008775711059570312
2023-01-23 02:06:50.779994: step: 1344/530, loss: 0.0011129856575280428
2023-01-23 02:06:51.952239: step: 1348/530, loss: 0.009422589093446732
2023-01-23 02:06:53.098046: step: 1352/530, loss: 0.018490411341190338
2023-01-23 02:06:54.259173: step: 1356/530, loss: 0.09592895954847336
2023-01-23 02:06:55.439518: step: 1360/530, loss: 0.012968159280717373
2023-01-23 02:06:56.654198: step: 1364/530, loss: 0.030870914459228516
2023-01-23 02:06:57.829308: step: 1368/530, loss: 0.0030160904861986637
2023-01-23 02:06:59.006363: step: 1372/530, loss: 0.055434610694646835
2023-01-23 02:07:00.215703: step: 1376/530, loss: 0.016527557745575905
2023-01-23 02:07:01.435470: step: 1380/530, loss: 0.020285796374082565
2023-01-23 02:07:02.625007: step: 1384/530, loss: 0.004257965367287397
2023-01-23 02:07:03.836877: step: 1388/530, loss: 0.07973413169384003
2023-01-23 02:07:04.967530: step: 1392/530, loss: 0.015843581408262253
2023-01-23 02:07:06.131502: step: 1396/530, loss: 0.035280752927064896
2023-01-23 02:07:07.311221: step: 1400/530, loss: 0.05140829086303711
2023-01-23 02:07:08.475953: step: 1404/530, loss: 0.024033930152654648
2023-01-23 02:07:09.668408: step: 1408/530, loss: 0.02801494486629963
2023-01-23 02:07:10.824149: step: 1412/530, loss: 0.01301121711730957
2023-01-23 02:07:12.036989: step: 1416/530, loss: 0.03600273281335831
2023-01-23 02:07:13.203378: step: 1420/530, loss: 0.013945722952485085
2023-01-23 02:07:14.413633: step: 1424/530, loss: 0.02272195927798748
2023-01-23 02:07:15.590653: step: 1428/530, loss: 0.006911754608154297
2023-01-23 02:07:16.741052: step: 1432/530, loss: 0.0638633742928505
2023-01-23 02:07:17.914155: step: 1436/530, loss: 0.04619426652789116
2023-01-23 02:07:19.069968: step: 1440/530, loss: 0.07546253502368927
2023-01-23 02:07:20.295720: step: 1444/530, loss: 0.02346172370016575
2023-01-23 02:07:21.433292: step: 1448/530, loss: 6.341934204101562e-05
2023-01-23 02:07:22.618801: step: 1452/530, loss: 0.0018310786690562963
2023-01-23 02:07:23.828400: step: 1456/530, loss: 0.031105805188417435
2023-01-23 02:07:25.001599: step: 1460/530, loss: 0.02681441232562065
2023-01-23 02:07:26.148700: step: 1464/530, loss: 0.0038092555478215218
2023-01-23 02:07:27.326853: step: 1468/530, loss: 0.05331917107105255
2023-01-23 02:07:28.500548: step: 1472/530, loss: 0.03397655487060547
2023-01-23 02:07:29.654095: step: 1476/530, loss: 0.015234089456498623
2023-01-23 02:07:30.816249: step: 1480/530, loss: 0.026860762387514114
2023-01-23 02:07:32.038123: step: 1484/530, loss: 0.027602292597293854
2023-01-23 02:07:33.194718: step: 1488/530, loss: 0.0027087214402854443
2023-01-23 02:07:34.335874: step: 1492/530, loss: 0.024042701348662376
2023-01-23 02:07:35.496077: step: 1496/530, loss: 0.038811683654785156
2023-01-23 02:07:36.689337: step: 1500/530, loss: 0.1528741866350174
2023-01-23 02:07:37.880395: step: 1504/530, loss: 0.00217189802788198
2023-01-23 02:07:39.133415: step: 1508/530, loss: 0.06387176364660263
2023-01-23 02:07:40.344452: step: 1512/530, loss: 0.0021766661666333675
2023-01-23 02:07:41.551551: step: 1516/530, loss: 0.1542484313249588
2023-01-23 02:07:42.723755: step: 1520/530, loss: 0.010139275342226028
2023-01-23 02:07:43.868311: step: 1524/530, loss: 0.011534690856933594
2023-01-23 02:07:45.033277: step: 1528/530, loss: 0.0005631446838378906
2023-01-23 02:07:46.145084: step: 1532/530, loss: 0.004104232881218195
2023-01-23 02:07:47.464192: step: 1536/530, loss: 0.009630585089325905
2023-01-23 02:07:48.651008: step: 1540/530, loss: 0.0017056465148925781
2023-01-23 02:07:49.781318: step: 1544/530, loss: 0.0388704314827919
2023-01-23 02:07:50.950149: step: 1548/530, loss: 0.033559419214725494
2023-01-23 02:07:52.119020: step: 1552/530, loss: 0.018369292840361595
2023-01-23 02:07:53.315005: step: 1556/530, loss: 0.043837834149599075
2023-01-23 02:07:54.452236: step: 1560/530, loss: 0.03452129662036896
2023-01-23 02:07:55.578848: step: 1564/530, loss: 0.0033347131684422493
2023-01-23 02:07:56.713298: step: 1568/530, loss: 0.012446403503417969
2023-01-23 02:07:57.899909: step: 1572/530, loss: 0.0006779670948162675
2023-01-23 02:07:59.079168: step: 1576/530, loss: 0.043444253504276276
2023-01-23 02:08:00.242943: step: 1580/530, loss: 0.03304595872759819
2023-01-23 02:08:01.415817: step: 1584/530, loss: 0.03993959352374077
2023-01-23 02:08:02.536234: step: 1588/530, loss: 0.08206450939178467
2023-01-23 02:08:03.707009: step: 1592/530, loss: 0.10245351493358612
2023-01-23 02:08:04.883907: step: 1596/530, loss: 0.08339233696460724
2023-01-23 02:08:06.028524: step: 1600/530, loss: 0.18985921144485474
2023-01-23 02:08:07.204205: step: 1604/530, loss: 0.033182334154844284
2023-01-23 02:08:08.349182: step: 1608/530, loss: 0.02825145795941353
2023-01-23 02:08:09.523853: step: 1612/530, loss: 0.021605681627988815
2023-01-23 02:08:10.686485: step: 1616/530, loss: 0.003261566162109375
2023-01-23 02:08:11.873956: step: 1620/530, loss: 0.03140435367822647
2023-01-23 02:08:13.075601: step: 1624/530, loss: 0.04887790605425835
2023-01-23 02:08:14.236527: step: 1628/530, loss: 0.08900509029626846
2023-01-23 02:08:15.402579: step: 1632/530, loss: 0.05209656059741974
2023-01-23 02:08:16.572269: step: 1636/530, loss: 0.0017317772144451737
2023-01-23 02:08:17.751497: step: 1640/530, loss: 0.004494285676628351
2023-01-23 02:08:18.937610: step: 1644/530, loss: 0.003970908932387829
2023-01-23 02:08:20.111590: step: 1648/530, loss: 0.45489102602005005
2023-01-23 02:08:21.303297: step: 1652/530, loss: 0.06994466483592987
2023-01-23 02:08:22.454914: step: 1656/530, loss: 0.001082003116607666
2023-01-23 02:08:23.630887: step: 1660/530, loss: 0.0005039215320721269
2023-01-23 02:08:24.785962: step: 1664/530, loss: 0.3520415127277374
2023-01-23 02:08:25.977231: step: 1668/530, loss: 0.19139176607131958
2023-01-23 02:08:27.125014: step: 1672/530, loss: 0.0066697122529149055
2023-01-23 02:08:28.299680: step: 1676/530, loss: 0.039824679493904114
2023-01-23 02:08:29.435307: step: 1680/530, loss: 0.011526679620146751
2023-01-23 02:08:30.619607: step: 1684/530, loss: 0.0436711311340332
2023-01-23 02:08:31.780819: step: 1688/530, loss: 0.0016387939685955644
2023-01-23 02:08:32.946811: step: 1692/530, loss: 0.05077200010418892
2023-01-23 02:08:34.129234: step: 1696/530, loss: 0.3122484087944031
2023-01-23 02:08:35.299730: step: 1700/530, loss: 0.012789345346391201
2023-01-23 02:08:36.526750: step: 1704/530, loss: 0.0004842162015847862
2023-01-23 02:08:37.761955: step: 1708/530, loss: 0.040705014020204544
2023-01-23 02:08:38.956583: step: 1712/530, loss: 0.002182579133659601
2023-01-23 02:08:40.130994: step: 1716/530, loss: 0.006494331639260054
2023-01-23 02:08:41.282060: step: 1720/530, loss: 0.04466447979211807
2023-01-23 02:08:42.461499: step: 1724/530, loss: 0.031276896595954895
2023-01-23 02:08:43.675459: step: 1728/530, loss: 0.019397640600800514
2023-01-23 02:08:44.835177: step: 1732/530, loss: 0.00012817383685614914
2023-01-23 02:08:46.034117: step: 1736/530, loss: 0.05592556297779083
2023-01-23 02:08:47.177093: step: 1740/530, loss: 0.009619355201721191
2023-01-23 02:08:48.329366: step: 1744/530, loss: 0.012849295511841774
2023-01-23 02:08:49.535103: step: 1748/530, loss: 0.09731273353099823
2023-01-23 02:08:50.701226: step: 1752/530, loss: 0.008343554101884365
2023-01-23 02:08:51.866985: step: 1756/530, loss: 0.021152783185243607
2023-01-23 02:08:53.073648: step: 1760/530, loss: 0.10981273651123047
2023-01-23 02:08:54.214083: step: 1764/530, loss: 0.020770955830812454
2023-01-23 02:08:55.374351: step: 1768/530, loss: 0.00115547189489007
2023-01-23 02:08:56.583657: step: 1772/530, loss: 0.0037407875061035156
2023-01-23 02:08:57.712565: step: 1776/530, loss: 0.32936277985572815
2023-01-23 02:08:58.878314: step: 1780/530, loss: 0.0162995345890522
2023-01-23 02:09:00.078531: step: 1784/530, loss: 0.029982376843690872
2023-01-23 02:09:01.198580: step: 1788/530, loss: 0.02543935924768448
2023-01-23 02:09:02.411669: step: 1792/530, loss: 0.37025895714759827
2023-01-23 02:09:03.559069: step: 1796/530, loss: 0.05530863255262375
2023-01-23 02:09:04.720749: step: 1800/530, loss: 0.01102457009255886
2023-01-23 02:09:05.873945: step: 1804/530, loss: 0.04209136962890625
2023-01-23 02:09:07.113421: step: 1808/530, loss: 0.08808784186840057
2023-01-23 02:09:08.296733: step: 1812/530, loss: 0.0662657767534256
2023-01-23 02:09:09.476475: step: 1816/530, loss: 0.03845701366662979
2023-01-23 02:09:10.641101: step: 1820/530, loss: 0.2588590979576111
2023-01-23 02:09:11.812231: step: 1824/530, loss: 0.010533714666962624
2023-01-23 02:09:13.012059: step: 1828/530, loss: 0.06527681648731232
2023-01-23 02:09:14.159809: step: 1832/530, loss: 0.03574400022625923
2023-01-23 02:09:15.343951: step: 1836/530, loss: 0.006679725833237171
2023-01-23 02:09:16.559563: step: 1840/530, loss: 0.07653055340051651
2023-01-23 02:09:17.761411: step: 1844/530, loss: 0.039412688463926315
2023-01-23 02:09:18.934881: step: 1848/530, loss: 0.10504503548145294
2023-01-23 02:09:20.115566: step: 1852/530, loss: 0.03179464116692543
2023-01-23 02:09:21.273549: step: 1856/530, loss: 0.002290058182552457
2023-01-23 02:09:22.450790: step: 1860/530, loss: 0.046096041798591614
2023-01-23 02:09:23.655663: step: 1864/530, loss: 0.008079242892563343
2023-01-23 02:09:24.837473: step: 1868/530, loss: 0.050446607172489166
2023-01-23 02:09:25.981065: step: 1872/530, loss: 0.02783660776913166
2023-01-23 02:09:27.148513: step: 1876/530, loss: 0.35977888107299805
2023-01-23 02:09:28.310072: step: 1880/530, loss: 0.003995847888290882
2023-01-23 02:09:29.470034: step: 1884/530, loss: 0.0009283066028729081
2023-01-23 02:09:30.630255: step: 1888/530, loss: 0.0012603760696947575
2023-01-23 02:09:31.806721: step: 1892/530, loss: 0.0046125175431370735
2023-01-23 02:09:32.986262: step: 1896/530, loss: 0.043888092041015625
2023-01-23 02:09:34.184468: step: 1900/530, loss: 0.045587629079818726
2023-01-23 02:09:35.363066: step: 1904/530, loss: 0.028281785547733307
2023-01-23 02:09:36.522916: step: 1908/530, loss: 0.05299057811498642
2023-01-23 02:09:37.688324: step: 1912/530, loss: 0.0056397439911961555
2023-01-23 02:09:38.871443: step: 1916/530, loss: 0.038083840161561966
2023-01-23 02:09:40.096118: step: 1920/530, loss: 0.017345238476991653
2023-01-23 02:09:41.248963: step: 1924/530, loss: 0.012544489465653896
2023-01-23 02:09:42.411217: step: 1928/530, loss: 0.0034304617438465357
2023-01-23 02:09:43.539420: step: 1932/530, loss: 0.020808935165405273
2023-01-23 02:09:44.719958: step: 1936/530, loss: 0.18250125646591187
2023-01-23 02:09:45.894393: step: 1940/530, loss: 0.09156279265880585
2023-01-23 02:09:47.055979: step: 1944/530, loss: 0.0009279251098632812
2023-01-23 02:09:48.258358: step: 1948/530, loss: 5.1116945542162284e-05
2023-01-23 02:09:49.466700: step: 1952/530, loss: 0.0040187835693359375
2023-01-23 02:09:50.610537: step: 1956/530, loss: 0.07841896265745163
2023-01-23 02:09:51.776243: step: 1960/530, loss: 0.007194042205810547
2023-01-23 02:09:52.947044: step: 1964/530, loss: 0.19128721952438354
2023-01-23 02:09:54.123485: step: 1968/530, loss: 0.12925635278224945
2023-01-23 02:09:55.304102: step: 1972/530, loss: 0.02354593202471733
2023-01-23 02:09:56.460667: step: 1976/530, loss: 0.010048103518784046
2023-01-23 02:09:57.604353: step: 1980/530, loss: 0.027831651270389557
2023-01-23 02:09:58.750683: step: 1984/530, loss: 0.006035804748535156
2023-01-23 02:09:59.937298: step: 1988/530, loss: 0.02407665178179741
2023-01-23 02:10:01.144717: step: 1992/530, loss: 0.004284668248146772
2023-01-23 02:10:02.266701: step: 1996/530, loss: 0.01672450266778469
2023-01-23 02:10:03.473846: step: 2000/530, loss: 0.08963127434253693
2023-01-23 02:10:04.676365: step: 2004/530, loss: 0.07505510747432709
2023-01-23 02:10:05.851602: step: 2008/530, loss: 0.02849707566201687
2023-01-23 02:10:06.989541: step: 2012/530, loss: 0.029717542231082916
2023-01-23 02:10:08.179296: step: 2016/530, loss: 0.06522579491138458
2023-01-23 02:10:09.376824: step: 2020/530, loss: 0.009841347113251686
2023-01-23 02:10:10.528865: step: 2024/530, loss: 0.0014075279468670487
2023-01-23 02:10:11.696811: step: 2028/530, loss: 0.06392069160938263
2023-01-23 02:10:12.870138: step: 2032/530, loss: 0.0010433197021484375
2023-01-23 02:10:14.052911: step: 2036/530, loss: 0.0015927791828289628
2023-01-23 02:10:15.201045: step: 2040/530, loss: 0.035505104809999466
2023-01-23 02:10:16.327945: step: 2044/530, loss: 0.0015538216102868319
2023-01-23 02:10:17.511963: step: 2048/530, loss: 0.01734161376953125
2023-01-23 02:10:18.705124: step: 2052/530, loss: 0.02013712003827095
2023-01-23 02:10:19.883046: step: 2056/530, loss: 0.02535095438361168
2023-01-23 02:10:21.056579: step: 2060/530, loss: 0.051574040204286575
2023-01-23 02:10:22.209309: step: 2064/530, loss: 0.00611190777271986
2023-01-23 02:10:23.421351: step: 2068/530, loss: 0.006221341900527477
2023-01-23 02:10:24.588940: step: 2072/530, loss: 0.006866836920380592
2023-01-23 02:10:25.783610: step: 2076/530, loss: 0.004740429110825062
2023-01-23 02:10:26.943296: step: 2080/530, loss: 0.002010345458984375
2023-01-23 02:10:28.078750: step: 2084/530, loss: 0.01877002604305744
2023-01-23 02:10:29.275543: step: 2088/530, loss: 0.03775526210665703
2023-01-23 02:10:30.458951: step: 2092/530, loss: 0.5075481534004211
2023-01-23 02:10:31.679317: step: 2096/530, loss: 0.005015468690544367
2023-01-23 02:10:32.814891: step: 2100/530, loss: 0.08266053348779678
2023-01-23 02:10:33.969237: step: 2104/530, loss: 0.05380840227007866
2023-01-23 02:10:35.155387: step: 2108/530, loss: 0.07045798748731613
2023-01-23 02:10:36.320261: step: 2112/530, loss: 0.09061752259731293
2023-01-23 02:10:37.472593: step: 2116/530, loss: 0.008649301715195179
2023-01-23 02:10:38.672535: step: 2120/530, loss: 0.10937127470970154
==================================================
Loss: 0.049
--------------------
Dev: {'event': {'p': 0.5811088295687885, 'r': 0.7536617842876165, 'f1': 0.6562318840579711}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 14}
Test: {'event': {'p': 0.6560747663551402, 'r': 0.8073605520414031, 'f1': 0.7238979118329466}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 14}
Chinese: {'event': {'p': 0.5632183908045977, 'r': 0.9074074074074074, 'f1': 0.6950354609929078}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 14}
Korean: {'event': {'p': 0.631578947368421, 'r': 0.5714285714285714, 'f1': 0.6}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 14}
Russian: {'event': {'p': 0.40384615384615385, 'r': 0.5833333333333334, 'f1': 0.4772727272727273}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 14}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6351501668520578, 'r': 0.7603195739014648, 'f1': 0.6921212121212121}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Chinese: {'event': {'p': 0.6373175182481752, 'r': 0.8033352501437608, 'f1': 0.7107606207071993}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Chinese: {'event': {'p': 0.5903614457831325, 'r': 0.9074074074074074, 'f1': 0.7153284671532847}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5733990147783251, 'r': 0.7749667110519307, 'f1': 0.6591166477916196}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Eng Test for Korean: {'event': {'p': 0.6218005295675199, 'r': 0.8102357676825762, 'f1': 0.7036204744069912}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Sample Korean: {'event': {'p': 0.6417910447761194, 'r': 0.6825396825396826, 'f1': 0.6615384615384614}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5951882845188284, 'r': 0.7576564580559254, 'f1': 0.6666666666666666}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6663405088062623, 'r': 0.7832087406555491, 'f1': 0.7200634417129264}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5, 'r': 0.6666666666666666, 'f1': 0.5714285714285715}, '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 02:11:21.689671: step: 4/530, loss: 0.012654876336455345
2023-01-23 02:11:22.836036: step: 8/530, loss: 0.031279660761356354
2023-01-23 02:11:24.043998: step: 12/530, loss: 0.0005647659418173134
2023-01-23 02:11:25.207211: step: 16/530, loss: 0.03277578204870224
2023-01-23 02:11:26.378951: step: 20/530, loss: 0.00781717337667942
2023-01-23 02:11:27.550897: step: 24/530, loss: 0.014646721072494984
2023-01-23 02:11:28.704646: step: 28/530, loss: 0.05620861425995827
2023-01-23 02:11:29.848825: step: 32/530, loss: 0.0042243958450853825
2023-01-23 02:11:31.004788: step: 36/530, loss: 0.0020406723488122225
2023-01-23 02:11:32.171901: step: 40/530, loss: 0.2573424279689789
2023-01-23 02:11:33.354876: step: 44/530, loss: 0.026294900104403496
2023-01-23 02:11:34.531418: step: 48/530, loss: 0.037817955017089844
2023-01-23 02:11:35.713148: step: 52/530, loss: 0.021404219791293144
2023-01-23 02:11:36.856276: step: 56/530, loss: 0.008617496117949486
2023-01-23 02:11:38.013563: step: 60/530, loss: 0.002383756684139371
2023-01-23 02:11:39.190670: step: 64/530, loss: 0.009491157718002796
2023-01-23 02:11:40.367008: step: 68/530, loss: 0.002452754881232977
2023-01-23 02:11:41.583649: step: 72/530, loss: 0.008034229278564453
2023-01-23 02:11:42.811365: step: 76/530, loss: 0.011966134421527386
2023-01-23 02:11:43.990384: step: 80/530, loss: 0.0012308120494708419
2023-01-23 02:11:45.144995: step: 84/530, loss: 0.03331294283270836
2023-01-23 02:11:46.318639: step: 88/530, loss: 0.015697766095399857
2023-01-23 02:11:47.499517: step: 92/530, loss: 0.00083074567373842
2023-01-23 02:11:48.661738: step: 96/530, loss: 0.0025950432755053043
2023-01-23 02:11:49.832425: step: 100/530, loss: 0.025836946442723274
2023-01-23 02:11:51.017397: step: 104/530, loss: 0.016163254156708717
2023-01-23 02:11:52.204648: step: 108/530, loss: 0.011761380359530449
2023-01-23 02:11:53.392070: step: 112/530, loss: 0.011208630166947842
2023-01-23 02:11:54.578874: step: 116/530, loss: 0.017702102661132812
2023-01-23 02:11:55.737314: step: 120/530, loss: 0.008686828427016735
2023-01-23 02:11:56.893153: step: 124/530, loss: 0.048345375806093216
2023-01-23 02:11:58.041274: step: 128/530, loss: 0.015298986807465553
2023-01-23 02:11:59.206045: step: 132/530, loss: 0.00019350052752997726
2023-01-23 02:12:00.346494: step: 136/530, loss: 0.04834280163049698
2023-01-23 02:12:01.498764: step: 140/530, loss: 0.004429721739143133
2023-01-23 02:12:02.663788: step: 144/530, loss: 0.004958629608154297
2023-01-23 02:12:03.830698: step: 148/530, loss: 0.018026161938905716
2023-01-23 02:12:04.965791: step: 152/530, loss: 0.010579586029052734
2023-01-23 02:12:06.115178: step: 156/530, loss: 0.05545216053724289
2023-01-23 02:12:07.289787: step: 160/530, loss: 0.06578245759010315
2023-01-23 02:12:08.488185: step: 164/530, loss: 0.006092071998864412
2023-01-23 02:12:09.661219: step: 168/530, loss: 0.002249217126518488
2023-01-23 02:12:10.805371: step: 172/530, loss: 0.16732731461524963
2023-01-23 02:12:12.000177: step: 176/530, loss: 0.0009834289085119963
2023-01-23 02:12:13.204045: step: 180/530, loss: 0.04420214146375656
2023-01-23 02:12:14.413317: step: 184/530, loss: 0.009236622601747513
2023-01-23 02:12:15.611641: step: 188/530, loss: 0.006926822941750288
2023-01-23 02:12:16.769074: step: 192/530, loss: 0.08704390376806259
2023-01-23 02:12:17.919355: step: 196/530, loss: 0.23478154838085175
2023-01-23 02:12:19.071672: step: 200/530, loss: 0.0037170888390392065
2023-01-23 02:12:20.244415: step: 204/530, loss: 0.01519470289349556
2023-01-23 02:12:21.413704: step: 208/530, loss: 0.0004727363702841103
2023-01-23 02:12:22.563622: step: 212/530, loss: 0.0274276752024889
2023-01-23 02:12:23.709539: step: 216/530, loss: 0.009050226770341396
2023-01-23 02:12:24.882731: step: 220/530, loss: 0.0006450176006183028
2023-01-23 02:12:26.080276: step: 224/530, loss: 0.02561969682574272
2023-01-23 02:12:27.226524: step: 228/530, loss: 0.3448448181152344
2023-01-23 02:12:28.452426: step: 232/530, loss: 0.006799316965043545
2023-01-23 02:12:29.625399: step: 236/530, loss: 0.009489583782851696
2023-01-23 02:12:30.831211: step: 240/530, loss: 0.07019881904125214
2023-01-23 02:12:32.003304: step: 244/530, loss: 0.05946674197912216
2023-01-23 02:12:33.196650: step: 248/530, loss: 0.016806412488222122
2023-01-23 02:12:34.328685: step: 252/530, loss: 0.009386825375258923
2023-01-23 02:12:35.493876: step: 256/530, loss: 0.01936502568423748
2023-01-23 02:12:36.679763: step: 260/530, loss: 0.017323780804872513
2023-01-23 02:12:37.888336: step: 264/530, loss: 0.05763149634003639
2023-01-23 02:12:39.053990: step: 268/530, loss: 0.04225483164191246
2023-01-23 02:12:40.253537: step: 272/530, loss: 0.04228649288415909
2023-01-23 02:12:41.460131: step: 276/530, loss: 0.0956106185913086
2023-01-23 02:12:42.636760: step: 280/530, loss: 0.008332252502441406
2023-01-23 02:12:43.805415: step: 284/530, loss: 0.00016369820514228195
2023-01-23 02:12:44.939817: step: 288/530, loss: 0.02782316319644451
2023-01-23 02:12:46.154458: step: 292/530, loss: 0.0020324706565588713
2023-01-23 02:12:47.310976: step: 296/530, loss: 0.0034954072907567024
2023-01-23 02:12:48.500198: step: 300/530, loss: 0.023395443335175514
2023-01-23 02:12:49.660895: step: 304/530, loss: 0.2527715563774109
2023-01-23 02:12:50.835406: step: 308/530, loss: 0.05603041499853134
2023-01-23 02:12:51.986210: step: 312/530, loss: 0.047674939036369324
2023-01-23 02:12:53.174911: step: 316/530, loss: 0.0010286332108080387
2023-01-23 02:12:54.341535: step: 320/530, loss: 0.014490891247987747
2023-01-23 02:12:55.496188: step: 324/530, loss: 0.04193086549639702
2023-01-23 02:12:56.696265: step: 328/530, loss: 0.0021026611793786287
2023-01-23 02:12:57.843573: step: 332/530, loss: 0.0035626888275146484
2023-01-23 02:12:59.009821: step: 336/530, loss: 0.005678844638168812
2023-01-23 02:13:00.172523: step: 340/530, loss: 0.004150486085563898
2023-01-23 02:13:01.357816: step: 344/530, loss: 0.04954977333545685
2023-01-23 02:13:02.536977: step: 348/530, loss: 0.02667227014899254
2023-01-23 02:13:03.671926: step: 352/530, loss: 0.01735091209411621
2023-01-23 02:13:04.795600: step: 356/530, loss: 4.625320798368193e-06
2023-01-23 02:13:05.971334: step: 360/530, loss: 0.015119648538529873
2023-01-23 02:13:07.122554: step: 364/530, loss: 0.010033035650849342
2023-01-23 02:13:08.274649: step: 368/530, loss: 0.0030927658081054688
2023-01-23 02:13:09.416689: step: 372/530, loss: 0.0001960754452738911
2023-01-23 02:13:10.567023: step: 376/530, loss: 0.03287315368652344
2023-01-23 02:13:11.810239: step: 380/530, loss: 0.00011978149996139109
2023-01-23 02:13:12.962624: step: 384/530, loss: 0.0042085652239620686
2023-01-23 02:13:14.179339: step: 388/530, loss: 0.21089357137680054
2023-01-23 02:13:15.336801: step: 392/530, loss: 0.003231048583984375
2023-01-23 02:13:16.481543: step: 396/530, loss: 0.015334648080170155
2023-01-23 02:13:17.666051: step: 400/530, loss: 0.07846460491418839
2023-01-23 02:13:18.834534: step: 404/530, loss: 0.006622791290283203
2023-01-23 02:13:20.046928: step: 408/530, loss: 0.013403129763901234
2023-01-23 02:13:21.198642: step: 412/530, loss: 0.009992408566176891
2023-01-23 02:13:22.364912: step: 416/530, loss: 0.004206848330795765
2023-01-23 02:13:23.568678: step: 420/530, loss: 0.05643749237060547
2023-01-23 02:13:24.701961: step: 424/530, loss: 0.003478717990219593
2023-01-23 02:13:25.862991: step: 428/530, loss: 0.1259908676147461
2023-01-23 02:13:27.036131: step: 432/530, loss: 0.0066762929782271385
2023-01-23 02:13:28.159670: step: 436/530, loss: 0.0040524485521018505
2023-01-23 02:13:29.333081: step: 440/530, loss: 0.43678951263427734
2023-01-23 02:13:30.512677: step: 444/530, loss: 0.0006047248607501388
2023-01-23 02:13:31.667248: step: 448/530, loss: 0.012568474747240543
2023-01-23 02:13:32.837830: step: 452/530, loss: 0.03447742387652397
2023-01-23 02:13:33.991583: step: 456/530, loss: 0.04041357338428497
2023-01-23 02:13:35.180323: step: 460/530, loss: 0.05601387098431587
2023-01-23 02:13:36.371383: step: 464/530, loss: 0.037675097584724426
2023-01-23 02:13:37.504938: step: 468/530, loss: 0.013876628130674362
2023-01-23 02:13:38.679320: step: 472/530, loss: 0.022797204554080963
2023-01-23 02:13:39.897485: step: 476/530, loss: 0.0006576537853106856
2023-01-23 02:13:41.060064: step: 480/530, loss: 0.0031648636795580387
2023-01-23 02:13:42.267727: step: 484/530, loss: 0.005390929989516735
2023-01-23 02:13:43.431387: step: 488/530, loss: 0.012403489090502262
2023-01-23 02:13:44.601953: step: 492/530, loss: 0.00010180473327636719
2023-01-23 02:13:45.748548: step: 496/530, loss: 0.0017448425060138106
2023-01-23 02:13:46.928573: step: 500/530, loss: 0.043985940515995026
2023-01-23 02:13:48.153401: step: 504/530, loss: 0.10576958954334259
2023-01-23 02:13:49.331000: step: 508/530, loss: 0.014014530926942825
2023-01-23 02:13:50.492040: step: 512/530, loss: 0.006882572080940008
2023-01-23 02:13:51.646842: step: 516/530, loss: 0.007848501205444336
2023-01-23 02:13:52.865971: step: 520/530, loss: 0.030147362500429153
2023-01-23 02:13:54.021543: step: 524/530, loss: 0.0665828213095665
2023-01-23 02:13:55.230858: step: 528/530, loss: 0.08908043056726456
2023-01-23 02:13:56.404285: step: 532/530, loss: 0.07072629779577255
2023-01-23 02:13:57.545239: step: 536/530, loss: 0.001459753606468439
2023-01-23 02:13:58.717018: step: 540/530, loss: 0.005664253607392311
2023-01-23 02:13:59.890672: step: 544/530, loss: 0.018787814304232597
2023-01-23 02:14:01.063857: step: 548/530, loss: 0.004755973815917969
2023-01-23 02:14:02.244371: step: 552/530, loss: 0.011046791449189186
2023-01-23 02:14:03.368410: step: 556/530, loss: 0.0003834724775515497
2023-01-23 02:14:04.538991: step: 560/530, loss: 0.0006870270008221269
2023-01-23 02:14:05.743705: step: 564/530, loss: 0.14744997024536133
2023-01-23 02:14:06.913579: step: 568/530, loss: 0.013215637765824795
2023-01-23 02:14:08.108555: step: 572/530, loss: 0.003654909087345004
2023-01-23 02:14:09.328939: step: 576/530, loss: 0.03262438625097275
2023-01-23 02:14:10.470028: step: 580/530, loss: 0.0033113479148596525
2023-01-23 02:14:11.672731: step: 584/530, loss: 0.005275154486298561
2023-01-23 02:14:12.880066: step: 588/530, loss: 0.035724833607673645
2023-01-23 02:14:14.037813: step: 592/530, loss: 0.0021162033081054688
2023-01-23 02:14:15.198122: step: 596/530, loss: 0.00311279296875
2023-01-23 02:14:16.363011: step: 600/530, loss: 0.03542747348546982
2023-01-23 02:14:17.575000: step: 604/530, loss: 0.01597623899579048
2023-01-23 02:14:18.736968: step: 608/530, loss: 0.09174209833145142
2023-01-23 02:14:19.932707: step: 612/530, loss: 0.00562818069010973
2023-01-23 02:14:21.095134: step: 616/530, loss: 0.17554599046707153
2023-01-23 02:14:22.251506: step: 620/530, loss: 0.0260409377515316
2023-01-23 02:14:23.409001: step: 624/530, loss: 0.01264200173318386
2023-01-23 02:14:24.597320: step: 628/530, loss: 0.030210303142666817
2023-01-23 02:14:25.741731: step: 632/530, loss: 0.010682869702577591
2023-01-23 02:14:26.919368: step: 636/530, loss: 0.007931518368422985
2023-01-23 02:14:28.066446: step: 640/530, loss: 0.0005447864532470703
2023-01-23 02:14:29.235510: step: 644/530, loss: 0.06788110733032227
2023-01-23 02:14:30.469380: step: 648/530, loss: 0.02107849158346653
2023-01-23 02:14:31.618794: step: 652/530, loss: 0.007168483920395374
2023-01-23 02:14:32.761013: step: 656/530, loss: 0.04241933673620224
2023-01-23 02:14:33.922916: step: 660/530, loss: 0.006088686175644398
2023-01-23 02:14:35.110857: step: 664/530, loss: 0.025698376819491386
2023-01-23 02:14:36.283774: step: 668/530, loss: 0.0009649277199059725
2023-01-23 02:14:37.430311: step: 672/530, loss: 0.04045810550451279
2023-01-23 02:14:38.598792: step: 676/530, loss: 0.010532474145293236
2023-01-23 02:14:39.779792: step: 680/530, loss: 0.09343662858009338
2023-01-23 02:14:40.965846: step: 684/530, loss: 0.10690422356128693
2023-01-23 02:14:42.140777: step: 688/530, loss: 0.0028802871238440275
2023-01-23 02:14:43.325924: step: 692/530, loss: 0.02251739613711834
2023-01-23 02:14:44.508078: step: 696/530, loss: 0.03548593819141388
2023-01-23 02:14:45.687071: step: 700/530, loss: 0.017038345336914062
2023-01-23 02:14:46.830549: step: 704/530, loss: 0.05795764923095703
2023-01-23 02:14:48.012637: step: 708/530, loss: 0.00128765101544559
2023-01-23 02:14:49.181488: step: 712/530, loss: 0.0012988090747967362
2023-01-23 02:14:50.356817: step: 716/530, loss: 0.024661827832460403
2023-01-23 02:14:51.540881: step: 720/530, loss: 0.009413433261215687
2023-01-23 02:14:52.749510: step: 724/530, loss: 0.019054986536502838
2023-01-23 02:14:53.909529: step: 728/530, loss: 0.00013999939255882055
2023-01-23 02:14:55.136929: step: 732/530, loss: 0.020264435559511185
2023-01-23 02:14:56.313229: step: 736/530, loss: 0.0062163835391402245
2023-01-23 02:14:57.471183: step: 740/530, loss: 0.011188221164047718
2023-01-23 02:14:58.655415: step: 744/530, loss: 0.038249969482421875
2023-01-23 02:14:59.883852: step: 748/530, loss: 0.036637209355831146
2023-01-23 02:15:01.075268: step: 752/530, loss: 0.018723011016845703
2023-01-23 02:15:02.277707: step: 756/530, loss: 0.0005800247308798134
2023-01-23 02:15:03.442431: step: 760/530, loss: 0.0024306653067469597
2023-01-23 02:15:04.596845: step: 764/530, loss: 0.06122121959924698
2023-01-23 02:15:05.782548: step: 768/530, loss: 0.0048798564821481705
2023-01-23 02:15:06.963194: step: 772/530, loss: 0.006002235226333141
2023-01-23 02:15:08.141443: step: 776/530, loss: 0.01686248928308487
2023-01-23 02:15:09.324684: step: 780/530, loss: 0.051540806889534
2023-01-23 02:15:10.480172: step: 784/530, loss: 0.0017980575794354081
2023-01-23 02:15:11.668912: step: 788/530, loss: 0.06205444410443306
2023-01-23 02:15:12.901394: step: 792/530, loss: 0.04071769490838051
2023-01-23 02:15:14.045862: step: 796/530, loss: 0.009892559610307217
2023-01-23 02:15:15.201540: step: 800/530, loss: 0.02321958728134632
2023-01-23 02:15:16.350932: step: 804/530, loss: 0.0025775909889489412
2023-01-23 02:15:17.547997: step: 808/530, loss: 0.041968539357185364
2023-01-23 02:15:18.760932: step: 812/530, loss: 0.025341510772705078
2023-01-23 02:15:19.937636: step: 816/530, loss: 0.02298135682940483
2023-01-23 02:15:21.135469: step: 820/530, loss: 0.07093129307031631
2023-01-23 02:15:22.259352: step: 824/530, loss: 0.0012752532493323088
2023-01-23 02:15:23.456212: step: 828/530, loss: 0.01823444291949272
2023-01-23 02:15:24.612740: step: 832/530, loss: 0.004504871554672718
2023-01-23 02:15:25.785677: step: 836/530, loss: 0.000941848789807409
2023-01-23 02:15:26.932867: step: 840/530, loss: 0.0036214827559888363
2023-01-23 02:15:28.120249: step: 844/530, loss: 0.01453180331736803
2023-01-23 02:15:29.296859: step: 848/530, loss: 0.002618122147396207
2023-01-23 02:15:30.496942: step: 852/530, loss: 0.02101287804543972
2023-01-23 02:15:31.661054: step: 856/530, loss: 0.02105426788330078
2023-01-23 02:15:32.830750: step: 860/530, loss: 0.028368568047881126
2023-01-23 02:15:33.993577: step: 864/530, loss: 0.03912219777703285
2023-01-23 02:15:35.165266: step: 868/530, loss: 0.013689327985048294
2023-01-23 02:15:36.398331: step: 872/530, loss: 0.004489898681640625
2023-01-23 02:15:37.573623: step: 876/530, loss: 0.017798805609345436
2023-01-23 02:15:38.767497: step: 880/530, loss: 0.0041713714599609375
2023-01-23 02:15:39.981847: step: 884/530, loss: 0.020096778869628906
2023-01-23 02:15:41.192335: step: 888/530, loss: 0.01844024658203125
2023-01-23 02:15:42.457705: step: 892/530, loss: 0.0007258414989337325
2023-01-23 02:15:43.659588: step: 896/530, loss: 0.0017194747924804688
2023-01-23 02:15:44.852055: step: 900/530, loss: 0.024099256843328476
2023-01-23 02:15:45.995530: step: 904/530, loss: 0.07320012897253036
2023-01-23 02:15:47.169739: step: 908/530, loss: 0.00770492572337389
2023-01-23 02:15:48.308191: step: 912/530, loss: 0.042348992079496384
2023-01-23 02:15:49.431572: step: 916/530, loss: 0.0009481400484219193
2023-01-23 02:15:50.538303: step: 920/530, loss: 0.02439560927450657
2023-01-23 02:15:51.722813: step: 924/530, loss: 0.005425167270004749
2023-01-23 02:15:52.889697: step: 928/530, loss: 0.039430998265743256
2023-01-23 02:15:54.052575: step: 932/530, loss: 0.0010271549690514803
2023-01-23 02:15:55.217881: step: 936/530, loss: 0.306428998708725
2023-01-23 02:15:56.404705: step: 940/530, loss: 0.005414772313088179
2023-01-23 02:15:57.607140: step: 944/530, loss: 0.003547191619873047
2023-01-23 02:15:58.762113: step: 948/530, loss: 0.0031862258911132812
2023-01-23 02:15:59.961653: step: 952/530, loss: 0.01693754270672798
2023-01-23 02:16:01.145270: step: 956/530, loss: 0.00015716553025413305
2023-01-23 02:16:02.303983: step: 960/530, loss: 0.04472498968243599
2023-01-23 02:16:03.453831: step: 964/530, loss: 0.034920599311590195
2023-01-23 02:16:04.614699: step: 968/530, loss: 0.0015779496170580387
2023-01-23 02:16:05.776873: step: 972/530, loss: 0.00012636184692382812
2023-01-23 02:16:06.929661: step: 976/530, loss: 0.07393258064985275
2023-01-23 02:16:08.135880: step: 980/530, loss: 0.010555935092270374
2023-01-23 02:16:09.315893: step: 984/530, loss: 0.020491981878876686
2023-01-23 02:16:10.470381: step: 988/530, loss: 0.011789131909608841
2023-01-23 02:16:11.678400: step: 992/530, loss: 0.6844971179962158
2023-01-23 02:16:12.875275: step: 996/530, loss: 0.04599914699792862
2023-01-23 02:16:14.038070: step: 1000/530, loss: 0.058066368103027344
2023-01-23 02:16:15.176577: step: 1004/530, loss: 0.0029382705688476562
2023-01-23 02:16:16.390644: step: 1008/530, loss: 0.09489412605762482
2023-01-23 02:16:17.569592: step: 1012/530, loss: 0.019968414679169655
2023-01-23 02:16:18.758007: step: 1016/530, loss: 0.011318398639559746
2023-01-23 02:16:19.930870: step: 1020/530, loss: 0.03294200822710991
2023-01-23 02:16:21.125952: step: 1024/530, loss: 0.003685188479721546
2023-01-23 02:16:22.273376: step: 1028/530, loss: 0.00701828021556139
2023-01-23 02:16:23.416774: step: 1032/530, loss: 0.03197135776281357
2023-01-23 02:16:24.573741: step: 1036/530, loss: 0.09321308135986328
2023-01-23 02:16:25.728671: step: 1040/530, loss: 0.013440227136015892
2023-01-23 02:16:26.896341: step: 1044/530, loss: 0.055948637425899506
2023-01-23 02:16:28.076820: step: 1048/530, loss: 0.019626524299383163
2023-01-23 02:16:29.218242: step: 1052/530, loss: 0.036977577954530716
2023-01-23 02:16:30.384095: step: 1056/530, loss: 0.1333375871181488
2023-01-23 02:16:31.580342: step: 1060/530, loss: 0.05495653301477432
2023-01-23 02:16:32.777001: step: 1064/530, loss: 0.0007682800642214715
2023-01-23 02:16:33.898340: step: 1068/530, loss: 0.006464672274887562
2023-01-23 02:16:35.065616: step: 1072/530, loss: 0.022063732147216797
2023-01-23 02:16:36.231526: step: 1076/530, loss: 0.008932113647460938
2023-01-23 02:16:37.415268: step: 1080/530, loss: 0.05643606185913086
2023-01-23 02:16:38.547410: step: 1084/530, loss: 0.008454227820038795
2023-01-23 02:16:39.728121: step: 1088/530, loss: 0.020166300237178802
2023-01-23 02:16:40.910611: step: 1092/530, loss: 0.0007686614990234375
2023-01-23 02:16:42.081680: step: 1096/530, loss: 0.04031772539019585
2023-01-23 02:16:43.260854: step: 1100/530, loss: 0.12108192592859268
2023-01-23 02:16:44.439753: step: 1104/530, loss: 0.03692259639501572
2023-01-23 02:16:45.618539: step: 1108/530, loss: 0.011994552798569202
2023-01-23 02:16:46.815050: step: 1112/530, loss: 0.0023777009919285774
2023-01-23 02:16:47.949668: step: 1116/530, loss: 0.0017195702530443668
2023-01-23 02:16:49.130069: step: 1120/530, loss: 0.1961696743965149
2023-01-23 02:16:50.311767: step: 1124/530, loss: 0.01551288366317749
2023-01-23 02:16:51.489104: step: 1128/530, loss: 0.004374122712761164
2023-01-23 02:16:52.678970: step: 1132/530, loss: 0.005787849426269531
2023-01-23 02:16:53.941883: step: 1136/530, loss: 0.0037231924943625927
2023-01-23 02:16:55.146196: step: 1140/530, loss: 0.027016736567020416
2023-01-23 02:16:56.317927: step: 1144/530, loss: 0.03674974665045738
2023-01-23 02:16:57.473590: step: 1148/530, loss: 0.012103271670639515
2023-01-23 02:16:58.637457: step: 1152/530, loss: 0.013294410891830921
2023-01-23 02:16:59.789057: step: 1156/530, loss: 0.027155304327607155
2023-01-23 02:17:00.980622: step: 1160/530, loss: 0.04994478076696396
2023-01-23 02:17:02.177780: step: 1164/530, loss: 0.02293793112039566
2023-01-23 02:17:03.333045: step: 1168/530, loss: 0.001960182096809149
2023-01-23 02:17:04.492141: step: 1172/530, loss: 0.007164096925407648
2023-01-23 02:17:05.605541: step: 1176/530, loss: 0.03467082977294922
2023-01-23 02:17:06.761369: step: 1180/530, loss: 0.01048965472728014
2023-01-23 02:17:07.956930: step: 1184/530, loss: 0.0013591767055913806
2023-01-23 02:17:09.123130: step: 1188/530, loss: 6.84738188283518e-05
2023-01-23 02:17:10.338087: step: 1192/530, loss: 0.04931678622961044
2023-01-23 02:17:11.495788: step: 1196/530, loss: 0.005214023403823376
2023-01-23 02:17:12.679768: step: 1200/530, loss: 0.005885124206542969
2023-01-23 02:17:13.826744: step: 1204/530, loss: 0.023368261754512787
2023-01-23 02:17:14.984542: step: 1208/530, loss: 0.013084601610898972
2023-01-23 02:17:16.158679: step: 1212/530, loss: 0.1076413244009018
2023-01-23 02:17:17.287159: step: 1216/530, loss: 0.015424060635268688
2023-01-23 02:17:18.451847: step: 1220/530, loss: 0.001622915267944336
2023-01-23 02:17:19.606059: step: 1224/530, loss: 0.012215042486786842
2023-01-23 02:17:20.753541: step: 1228/530, loss: 0.004709053318947554
2023-01-23 02:17:21.979568: step: 1232/530, loss: 0.0017198562854900956
2023-01-23 02:17:23.152072: step: 1236/530, loss: 0.0006405830499716103
2023-01-23 02:17:24.289875: step: 1240/530, loss: 0.010349464602768421
2023-01-23 02:17:25.484380: step: 1244/530, loss: 0.021033668890595436
2023-01-23 02:17:26.655582: step: 1248/530, loss: 0.04518537595868111
2023-01-23 02:17:27.856056: step: 1252/530, loss: 0.625317394733429
2023-01-23 02:17:29.043459: step: 1256/530, loss: 0.005292702000588179
2023-01-23 02:17:30.200873: step: 1260/530, loss: 0.012545967474579811
2023-01-23 02:17:31.400715: step: 1264/530, loss: 0.02051258087158203
2023-01-23 02:17:32.560825: step: 1268/530, loss: 0.021819496527314186
2023-01-23 02:17:33.695460: step: 1272/530, loss: 0.09733696281909943
2023-01-23 02:17:34.827882: step: 1276/530, loss: 0.005890846252441406
2023-01-23 02:17:35.976643: step: 1280/530, loss: 0.00023155212693382055
2023-01-23 02:17:37.126805: step: 1284/530, loss: 0.0027832984924316406
2023-01-23 02:17:38.271238: step: 1288/530, loss: 0.029402637854218483
2023-01-23 02:17:39.411324: step: 1292/530, loss: 0.02575240284204483
2023-01-23 02:17:40.573055: step: 1296/530, loss: 0.0042739869095385075
2023-01-23 02:17:41.733215: step: 1300/530, loss: 0.0070213316939771175
2023-01-23 02:17:42.901621: step: 1304/530, loss: 0.11288128048181534
2023-01-23 02:17:44.061627: step: 1308/530, loss: 0.056291960179805756
2023-01-23 02:17:45.220173: step: 1312/530, loss: 0.005570841021835804
2023-01-23 02:17:46.438797: step: 1316/530, loss: 0.022466612979769707
2023-01-23 02:17:47.639809: step: 1320/530, loss: 0.008124351501464844
2023-01-23 02:17:48.798975: step: 1324/530, loss: 0.007206821348518133
2023-01-23 02:17:49.961084: step: 1328/530, loss: 0.024521350860595703
2023-01-23 02:17:51.165253: step: 1332/530, loss: 0.008456707000732422
2023-01-23 02:17:52.355477: step: 1336/530, loss: 0.015303420834243298
2023-01-23 02:17:53.486984: step: 1340/530, loss: 0.010968446731567383
2023-01-23 02:17:54.651386: step: 1344/530, loss: 0.00046405792818404734
2023-01-23 02:17:55.804732: step: 1348/530, loss: 0.0011665343772619963
2023-01-23 02:17:56.997182: step: 1352/530, loss: 0.027378272265195847
2023-01-23 02:17:58.145126: step: 1356/530, loss: 0.00821993313729763
2023-01-23 02:17:59.362615: step: 1360/530, loss: 0.00512771587818861
2023-01-23 02:18:00.515843: step: 1364/530, loss: 0.04418068006634712
2023-01-23 02:18:01.672286: step: 1368/530, loss: 0.04472227394580841
2023-01-23 02:18:02.825653: step: 1372/530, loss: 0.005098152440041304
2023-01-23 02:18:04.053758: step: 1376/530, loss: 0.0019210814498364925
2023-01-23 02:18:05.232920: step: 1380/530, loss: 0.002780771115794778
2023-01-23 02:18:06.405368: step: 1384/530, loss: 0.01731429062783718
2023-01-23 02:18:07.543720: step: 1388/530, loss: 0.00202598562464118
2023-01-23 02:18:08.707849: step: 1392/530, loss: 0.0401521660387516
2023-01-23 02:18:09.905548: step: 1396/530, loss: 0.005263328552246094
2023-01-23 02:18:11.094980: step: 1400/530, loss: 0.03058786317706108
2023-01-23 02:18:12.306796: step: 1404/530, loss: 0.006046962924301624
2023-01-23 02:18:13.514268: step: 1408/530, loss: 0.0058114053681492805
2023-01-23 02:18:14.701879: step: 1412/530, loss: 0.011354636400938034
2023-01-23 02:18:15.897423: step: 1416/530, loss: 0.003282785415649414
2023-01-23 02:18:17.046035: step: 1420/530, loss: 0.02545480988919735
2023-01-23 02:18:18.229237: step: 1424/530, loss: 0.034707069396972656
2023-01-23 02:18:19.380781: step: 1428/530, loss: 0.012260722927749157
2023-01-23 02:18:20.545189: step: 1432/530, loss: 0.02743072435259819
2023-01-23 02:18:21.703029: step: 1436/530, loss: 0.022022631019353867
2023-01-23 02:18:22.862359: step: 1440/530, loss: 0.0008210659143514931
2023-01-23 02:18:24.054072: step: 1444/530, loss: 0.04298248142004013
2023-01-23 02:18:25.231234: step: 1448/530, loss: 0.04845009371638298
2023-01-23 02:18:26.445991: step: 1452/530, loss: 0.01199264544993639
2023-01-23 02:18:27.652500: step: 1456/530, loss: 0.013561058789491653
2023-01-23 02:18:28.858684: step: 1460/530, loss: 0.16061095893383026
2023-01-23 02:18:30.042902: step: 1464/530, loss: 0.009313154965639114
2023-01-23 02:18:31.214709: step: 1468/530, loss: 0.02491474151611328
2023-01-23 02:18:32.383530: step: 1472/530, loss: 0.044518373906612396
2023-01-23 02:18:33.580946: step: 1476/530, loss: 0.004079150967299938
2023-01-23 02:18:34.785015: step: 1480/530, loss: 0.05116147920489311
2023-01-23 02:18:35.937700: step: 1484/530, loss: 0.00825490988790989
2023-01-23 02:18:37.136032: step: 1488/530, loss: 0.2474052459001541
2023-01-23 02:18:38.341776: step: 1492/530, loss: 0.02437744289636612
2023-01-23 02:18:39.451602: step: 1496/530, loss: 0.006059599108994007
2023-01-23 02:18:40.601888: step: 1500/530, loss: 0.011619377881288528
2023-01-23 02:18:41.751973: step: 1504/530, loss: 0.011385059915482998
2023-01-23 02:18:42.968451: step: 1508/530, loss: 0.019226456061005592
2023-01-23 02:18:44.171568: step: 1512/530, loss: 0.009076881222426891
2023-01-23 02:18:45.344913: step: 1516/530, loss: 0.02951965481042862
2023-01-23 02:18:46.523318: step: 1520/530, loss: 0.0048542022705078125
2023-01-23 02:18:47.702532: step: 1524/530, loss: 0.0008575438987463713
2023-01-23 02:18:48.895803: step: 1528/530, loss: 0.0030071260407567024
2023-01-23 02:18:50.072496: step: 1532/530, loss: 0.00035090447636321187
2023-01-23 02:18:51.252934: step: 1536/530, loss: 0.4376121759414673
2023-01-23 02:18:52.499133: step: 1540/530, loss: 0.01397705078125
2023-01-23 02:18:53.659413: step: 1544/530, loss: 0.0660494863986969
2023-01-23 02:18:54.827759: step: 1548/530, loss: 0.006846904754638672
2023-01-23 02:18:55.998107: step: 1552/530, loss: 0.028004836291074753
2023-01-23 02:18:57.181276: step: 1556/530, loss: 0.13076430559158325
2023-01-23 02:18:58.344855: step: 1560/530, loss: 3.346204903209582e-05
2023-01-23 02:18:59.525387: step: 1564/530, loss: 0.09946969151496887
2023-01-23 02:19:00.700685: step: 1568/530, loss: 0.014598274603486061
2023-01-23 02:19:01.865570: step: 1572/530, loss: 0.06793287396430969
2023-01-23 02:19:03.067333: step: 1576/530, loss: 0.0005762100336141884
2023-01-23 02:19:04.200566: step: 1580/530, loss: 0.01329183578491211
2023-01-23 02:19:05.385698: step: 1584/530, loss: 0.002945327665656805
2023-01-23 02:19:06.533896: step: 1588/530, loss: 0.03671465069055557
2023-01-23 02:19:07.719488: step: 1592/530, loss: 0.061001114547252655
2023-01-23 02:19:08.868909: step: 1596/530, loss: 0.011157846078276634
2023-01-23 02:19:10.045820: step: 1600/530, loss: 0.056175995618104935
2023-01-23 02:19:11.245899: step: 1604/530, loss: 0.06539420038461685
2023-01-23 02:19:12.391341: step: 1608/530, loss: 0.02539801597595215
2023-01-23 02:19:13.527886: step: 1612/530, loss: 0.005995273590087891
2023-01-23 02:19:14.647170: step: 1616/530, loss: 0.030515670776367188
2023-01-23 02:19:15.808388: step: 1620/530, loss: 0.0030109405051916838
2023-01-23 02:19:17.014036: step: 1624/530, loss: 0.004905032925307751
2023-01-23 02:19:18.203485: step: 1628/530, loss: 0.002255058381706476
2023-01-23 02:19:19.374388: step: 1632/530, loss: 0.0013852119445800781
2023-01-23 02:19:20.510931: step: 1636/530, loss: 0.006510257720947266
2023-01-23 02:19:21.682211: step: 1640/530, loss: 0.03111858293414116
2023-01-23 02:19:22.837555: step: 1644/530, loss: 0.018669437617063522
2023-01-23 02:19:24.028793: step: 1648/530, loss: 0.017412565648555756
2023-01-23 02:19:25.262368: step: 1652/530, loss: 0.07824277877807617
2023-01-23 02:19:26.434895: step: 1656/530, loss: 0.03162670135498047
2023-01-23 02:19:27.624120: step: 1660/530, loss: 0.012016773223876953
2023-01-23 02:19:28.853187: step: 1664/530, loss: 0.035002708435058594
2023-01-23 02:19:30.013482: step: 1668/530, loss: 0.007636070717126131
2023-01-23 02:19:31.162124: step: 1672/530, loss: 0.021028518676757812
2023-01-23 02:19:32.336488: step: 1676/530, loss: 0.02408733405172825
2023-01-23 02:19:33.493292: step: 1680/530, loss: 0.018557453528046608
2023-01-23 02:19:34.654173: step: 1684/530, loss: 0.05541520193219185
2023-01-23 02:19:35.793317: step: 1688/530, loss: 0.046256162226200104
2023-01-23 02:19:36.985965: step: 1692/530, loss: 0.04626293107867241
2023-01-23 02:19:38.204036: step: 1696/530, loss: 0.0016172886826097965
2023-01-23 02:19:39.408645: step: 1700/530, loss: 0.015532302670180798
2023-01-23 02:19:40.575632: step: 1704/530, loss: 0.03680257871747017
2023-01-23 02:19:41.791840: step: 1708/530, loss: 0.0017576217651367188
2023-01-23 02:19:42.947784: step: 1712/530, loss: 0.011650944128632545
2023-01-23 02:19:44.118629: step: 1716/530, loss: 0.012157249264419079
2023-01-23 02:19:45.256167: step: 1720/530, loss: 0.07267945259809494
2023-01-23 02:19:46.443076: step: 1724/530, loss: 0.11174774169921875
2023-01-23 02:19:47.616890: step: 1728/530, loss: 0.059250928461551666
2023-01-23 02:19:48.818083: step: 1732/530, loss: 0.0023828507401049137
2023-01-23 02:19:49.973319: step: 1736/530, loss: 0.028647232800722122
2023-01-23 02:19:51.158157: step: 1740/530, loss: 0.02377491071820259
2023-01-23 02:19:52.340302: step: 1744/530, loss: 0.026944447308778763
2023-01-23 02:19:53.522234: step: 1748/530, loss: 0.04197101667523384
2023-01-23 02:19:54.708771: step: 1752/530, loss: 0.009521770291030407
2023-01-23 02:19:55.896523: step: 1756/530, loss: 0.015687942504882812
2023-01-23 02:19:57.078629: step: 1760/530, loss: 0.0007885455852374434
2023-01-23 02:19:58.312490: step: 1764/530, loss: 0.017133712768554688
2023-01-23 02:19:59.483938: step: 1768/530, loss: 0.06792526692152023
2023-01-23 02:20:00.653168: step: 1772/530, loss: 0.04724464565515518
2023-01-23 02:20:01.866102: step: 1776/530, loss: 0.00868368148803711
2023-01-23 02:20:03.036273: step: 1780/530, loss: 0.058907441794872284
2023-01-23 02:20:04.240734: step: 1784/530, loss: 0.03559083864092827
2023-01-23 02:20:05.381107: step: 1788/530, loss: 0.003754949662834406
2023-01-23 02:20:06.556481: step: 1792/530, loss: 0.02006373554468155
2023-01-23 02:20:07.760551: step: 1796/530, loss: 0.16541346907615662
2023-01-23 02:20:08.897477: step: 1800/530, loss: 0.014510631561279297
2023-01-23 02:20:10.087749: step: 1804/530, loss: 0.06074199452996254
2023-01-23 02:20:11.308412: step: 1808/530, loss: 0.06244392693042755
2023-01-23 02:20:12.457507: step: 1812/530, loss: 0.0705965980887413
2023-01-23 02:20:13.603518: step: 1816/530, loss: 0.01542677916586399
2023-01-23 02:20:14.765418: step: 1820/530, loss: 0.008545017801225185
2023-01-23 02:20:15.915869: step: 1824/530, loss: 0.04546041414141655
2023-01-23 02:20:17.097065: step: 1828/530, loss: 0.0012052536476403475
2023-01-23 02:20:18.289725: step: 1832/530, loss: 0.0013606548309326172
2023-01-23 02:20:19.444332: step: 1836/530, loss: 0.009883594699203968
2023-01-23 02:20:20.622369: step: 1840/530, loss: 0.027675915509462357
2023-01-23 02:20:21.782434: step: 1844/530, loss: 0.02069096639752388
2023-01-23 02:20:22.954565: step: 1848/530, loss: 0.01460037287324667
2023-01-23 02:20:24.133828: step: 1852/530, loss: 0.02677288092672825
2023-01-23 02:20:25.299539: step: 1856/530, loss: 0.05374555662274361
2023-01-23 02:20:26.487118: step: 1860/530, loss: 0.00589985866099596
2023-01-23 02:20:27.648792: step: 1864/530, loss: 0.20721390843391418
2023-01-23 02:20:28.805239: step: 1868/530, loss: 0.003643464995548129
2023-01-23 02:20:30.000092: step: 1872/530, loss: 0.2724662721157074
2023-01-23 02:20:31.159297: step: 1876/530, loss: 0.14786000549793243
2023-01-23 02:20:32.332203: step: 1880/530, loss: 0.044640734791755676
2023-01-23 02:20:33.502157: step: 1884/530, loss: 0.01991119422018528
2023-01-23 02:20:34.656010: step: 1888/530, loss: 0.05913801118731499
2023-01-23 02:20:35.791762: step: 1892/530, loss: 0.015214063227176666
2023-01-23 02:20:36.935635: step: 1896/530, loss: 0.0004913330194540322
2023-01-23 02:20:38.093892: step: 1900/530, loss: 0.04687690734863281
2023-01-23 02:20:39.301858: step: 1904/530, loss: 0.041098594665527344
2023-01-23 02:20:40.442705: step: 1908/530, loss: 0.0007665634038858116
2023-01-23 02:20:41.639322: step: 1912/530, loss: 0.5281286239624023
2023-01-23 02:20:42.787082: step: 1916/530, loss: 0.013698577880859375
2023-01-23 02:20:43.927316: step: 1920/530, loss: 0.002680110977962613
2023-01-23 02:20:45.140321: step: 1924/530, loss: 0.015740156173706055
2023-01-23 02:20:46.299056: step: 1928/530, loss: 0.06741566956043243
2023-01-23 02:20:47.490417: step: 1932/530, loss: 0.0037709237076342106
2023-01-23 02:20:48.652138: step: 1936/530, loss: 0.03297100216150284
2023-01-23 02:20:49.834246: step: 1940/530, loss: 0.1535823792219162
2023-01-23 02:20:50.995974: step: 1944/530, loss: 0.0005600929143838584
2023-01-23 02:20:52.209398: step: 1948/530, loss: 0.043232060968875885
2023-01-23 02:20:53.380368: step: 1952/530, loss: 0.06583947688341141
2023-01-23 02:20:54.536989: step: 1956/530, loss: 0.015571403317153454
2023-01-23 02:20:55.666717: step: 1960/530, loss: 0.04037804529070854
2023-01-23 02:20:56.821888: step: 1964/530, loss: 0.0501251220703125
2023-01-23 02:20:57.970043: step: 1968/530, loss: 0.05025177076458931
2023-01-23 02:20:59.153028: step: 1972/530, loss: 0.08445396274328232
2023-01-23 02:21:00.328387: step: 1976/530, loss: 0.0317777618765831
2023-01-23 02:21:01.485831: step: 1980/530, loss: 0.006000423803925514
2023-01-23 02:21:02.633188: step: 1984/530, loss: 0.002723979763686657
2023-01-23 02:21:03.806348: step: 1988/530, loss: 0.004843807313591242
2023-01-23 02:21:04.972818: step: 1992/530, loss: 0.00908117275685072
2023-01-23 02:21:06.112656: step: 1996/530, loss: 0.0045393467880785465
2023-01-23 02:21:07.265614: step: 2000/530, loss: 0.008316230960190296
2023-01-23 02:21:08.432809: step: 2004/530, loss: 0.0024831772316247225
2023-01-23 02:21:09.688149: step: 2008/530, loss: 0.04654483497142792
2023-01-23 02:21:10.858135: step: 2012/530, loss: 0.020674800500273705
2023-01-23 02:21:12.079635: step: 2016/530, loss: 0.0249481201171875
2023-01-23 02:21:13.205271: step: 2020/530, loss: 0.026296233758330345
2023-01-23 02:21:14.407657: step: 2024/530, loss: 0.003978157415986061
2023-01-23 02:21:15.594009: step: 2028/530, loss: 0.063909150660038
2023-01-23 02:21:16.767729: step: 2032/530, loss: 0.08801212906837463
2023-01-23 02:21:17.922407: step: 2036/530, loss: 0.06461877375841141
2023-01-23 02:21:19.085645: step: 2040/530, loss: 0.01748828962445259
2023-01-23 02:21:20.271659: step: 2044/530, loss: 0.04268608242273331
2023-01-23 02:21:21.469886: step: 2048/530, loss: 0.013233756646513939
2023-01-23 02:21:22.689406: step: 2052/530, loss: 0.0363675095140934
2023-01-23 02:21:23.841108: step: 2056/530, loss: 0.024119187146425247
2023-01-23 02:21:24.996711: step: 2060/530, loss: 0.009925365447998047
2023-01-23 02:21:26.136853: step: 2064/530, loss: 0.23151855170726776
2023-01-23 02:21:27.303203: step: 2068/530, loss: 0.003927039913833141
2023-01-23 02:21:28.469653: step: 2072/530, loss: 1.1240531206130981
2023-01-23 02:21:29.660838: step: 2076/530, loss: 0.04476910084486008
2023-01-23 02:21:30.809097: step: 2080/530, loss: 0.06811833381652832
2023-01-23 02:21:32.015330: step: 2084/530, loss: 0.02093934826552868
2023-01-23 02:21:33.208016: step: 2088/530, loss: 0.1123688668012619
2023-01-23 02:21:34.381774: step: 2092/530, loss: 0.03959079086780548
2023-01-23 02:21:35.588606: step: 2096/530, loss: 0.10957165062427521
2023-01-23 02:21:36.743881: step: 2100/530, loss: 0.026591815054416656
2023-01-23 02:21:37.895658: step: 2104/530, loss: 0.009633541107177734
2023-01-23 02:21:39.062927: step: 2108/530, loss: 0.0009563446510583162
2023-01-23 02:21:40.231776: step: 2112/530, loss: 0.24887028336524963
2023-01-23 02:21:41.402106: step: 2116/530, loss: 0.021060658618807793
2023-01-23 02:21:42.579634: step: 2120/530, loss: 0.10740356892347336
==================================================
Loss: 0.038
--------------------
Dev: {'event': {'p': 0.6142241379310345, 'r': 0.758988015978695, 'f1': 0.6789755807027993}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Test: {'event': {'p': 0.6543671181690799, 'r': 0.8056354226566993, 'f1': 0.7221649484536083}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Chinese: {'event': {'p': 0.5581395348837209, 'r': 0.8888888888888888, 'f1': 0.6857142857142857}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Korean: {'event': {'p': 0.6875, 'r': 0.5238095238095238, 'f1': 0.5945945945945946}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Russian: {'event': {'p': 0.4318181818181818, 'r': 0.5277777777777778, 'f1': 0.47500000000000003}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6351501668520578, 'r': 0.7603195739014648, 'f1': 0.6921212121212121}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Chinese: {'event': {'p': 0.6373175182481752, 'r': 0.8033352501437608, 'f1': 0.7107606207071993}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Chinese: {'event': {'p': 0.5903614457831325, 'r': 0.9074074074074074, 'f1': 0.7153284671532847}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5733990147783251, 'r': 0.7749667110519307, 'f1': 0.6591166477916196}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Eng Test for Korean: {'event': {'p': 0.6218005295675199, 'r': 0.8102357676825762, 'f1': 0.7036204744069912}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Sample Korean: {'event': {'p': 0.6417910447761194, 'r': 0.6825396825396826, 'f1': 0.6615384615384614}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5951882845188284, 'r': 0.7576564580559254, 'f1': 0.6666666666666666}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6663405088062623, 'r': 0.7832087406555491, 'f1': 0.7200634417129264}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5, 'r': 0.6666666666666666, 'f1': 0.5714285714285715}, '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 02:22:25.100400: step: 4/530, loss: 0.011803912930190563
2023-01-23 02:22:26.261302: step: 8/530, loss: 0.0008389592403545976
2023-01-23 02:22:27.438050: step: 12/530, loss: 0.08594093471765518
2023-01-23 02:22:28.630402: step: 16/530, loss: 0.046112824231386185
2023-01-23 02:22:29.777330: step: 20/530, loss: 0.03667163848876953
2023-01-23 02:22:30.980588: step: 24/530, loss: 0.016068458557128906
2023-01-23 02:22:32.165049: step: 28/530, loss: 0.017540359869599342
2023-01-23 02:22:33.387192: step: 32/530, loss: 0.02059049718081951
2023-01-23 02:22:34.576079: step: 36/530, loss: 0.036649420857429504
2023-01-23 02:22:35.790930: step: 40/530, loss: 0.07989444583654404
2023-01-23 02:22:36.964847: step: 44/530, loss: 0.007925743237137794
2023-01-23 02:22:38.172639: step: 48/530, loss: 0.010995388962328434
2023-01-23 02:22:39.348994: step: 52/530, loss: 0.008009719662368298
2023-01-23 02:22:40.547133: step: 56/530, loss: 0.02074756659567356
2023-01-23 02:22:41.740382: step: 60/530, loss: 0.0020765303634107113
2023-01-23 02:22:42.904874: step: 64/530, loss: 0.001609897706657648
2023-01-23 02:22:44.079323: step: 68/530, loss: 0.008221626281738281
2023-01-23 02:22:45.216859: step: 72/530, loss: 0.0015018940903246403
2023-01-23 02:22:46.435786: step: 76/530, loss: 0.05179624259471893
2023-01-23 02:22:47.619037: step: 80/530, loss: 0.044583775103092194
2023-01-23 02:22:48.823208: step: 84/530, loss: 0.013353920541703701
2023-01-23 02:22:50.010393: step: 88/530, loss: 2.2262661457061768
2023-01-23 02:22:51.196901: step: 92/530, loss: 0.03757190704345703
2023-01-23 02:22:52.399379: step: 96/530, loss: 0.2614215314388275
2023-01-23 02:22:53.534721: step: 100/530, loss: 0.04515361785888672
2023-01-23 02:22:54.696931: step: 104/530, loss: 0.06762409210205078
2023-01-23 02:22:55.852631: step: 108/530, loss: 0.09645986557006836
2023-01-23 02:22:57.021290: step: 112/530, loss: 0.02139577828347683
2023-01-23 02:22:58.215662: step: 116/530, loss: 0.008649397641420364
2023-01-23 02:22:59.382652: step: 120/530, loss: 0.04417705535888672
2023-01-23 02:23:00.549411: step: 124/530, loss: 0.016556167975068092
2023-01-23 02:23:01.744457: step: 128/530, loss: 0.0041713714599609375
2023-01-23 02:23:02.920826: step: 132/530, loss: 0.0005018234369345009
2023-01-23 02:23:04.127426: step: 136/530, loss: 0.05917387083172798
2023-01-23 02:23:05.305588: step: 140/530, loss: 0.002476310823112726
2023-01-23 02:23:06.447598: step: 144/530, loss: 0.34436577558517456
2023-01-23 02:23:07.674274: step: 148/530, loss: 0.008627128787338734
2023-01-23 02:23:08.893163: step: 152/530, loss: 0.018680192530155182
2023-01-23 02:23:10.029758: step: 156/530, loss: 0.008930588141083717
2023-01-23 02:23:11.204088: step: 160/530, loss: 0.001251316163688898
2023-01-23 02:23:12.339874: step: 164/530, loss: 0.03687248006463051
2023-01-23 02:23:13.580834: step: 168/530, loss: 0.035062503069639206
2023-01-23 02:23:14.780576: step: 172/530, loss: 0.013500022701919079
2023-01-23 02:23:15.972429: step: 176/530, loss: 0.006989479064941406
2023-01-23 02:23:17.133716: step: 180/530, loss: 0.007652187719941139
2023-01-23 02:23:18.284591: step: 184/530, loss: 0.03099050372838974
2023-01-23 02:23:19.456271: step: 188/530, loss: 0.01855926588177681
2023-01-23 02:23:20.600003: step: 192/530, loss: 0.017152214422822
2023-01-23 02:23:21.748067: step: 196/530, loss: 0.014323902316391468
2023-01-23 02:23:22.966877: step: 200/530, loss: 0.13445129990577698
2023-01-23 02:23:24.150680: step: 204/530, loss: 0.00038757326547056437
2023-01-23 02:23:25.322495: step: 208/530, loss: 0.03909549489617348
2023-01-23 02:23:26.483566: step: 212/530, loss: 0.05595111846923828
2023-01-23 02:23:27.603192: step: 216/530, loss: 0.0001028060942189768
2023-01-23 02:23:28.797532: step: 220/530, loss: 0.0017253875266760588
2023-01-23 02:23:29.951457: step: 224/530, loss: 0.006760692689567804
2023-01-23 02:23:31.113029: step: 228/530, loss: 0.08616295456886292
2023-01-23 02:23:32.280328: step: 232/530, loss: 0.00025434495182707906
2023-01-23 02:23:33.414536: step: 236/530, loss: 0.010575294494628906
2023-01-23 02:23:34.614613: step: 240/530, loss: 0.027211381122469902
2023-01-23 02:23:35.780788: step: 244/530, loss: 0.0077280523255467415
2023-01-23 02:23:36.956740: step: 248/530, loss: 0.007067251019179821
2023-01-23 02:23:38.116810: step: 252/530, loss: 0.02329707145690918
2023-01-23 02:23:39.306368: step: 256/530, loss: 0.1268574744462967
2023-01-23 02:23:40.448167: step: 260/530, loss: 0.020870016887784004
2023-01-23 02:23:41.625360: step: 264/530, loss: 0.010355949401855469
2023-01-23 02:23:42.802331: step: 268/530, loss: 0.0039345743134617805
2023-01-23 02:23:44.034237: step: 272/530, loss: 0.012414741329848766
2023-01-23 02:23:45.159621: step: 276/530, loss: 0.003600740572437644
2023-01-23 02:23:46.278816: step: 280/530, loss: 0.0095360754057765
2023-01-23 02:23:47.468873: step: 284/530, loss: 0.0007090568542480469
2023-01-23 02:23:48.618529: step: 288/530, loss: 0.0001019001065287739
2023-01-23 02:23:49.848899: step: 292/530, loss: 0.012156590819358826
2023-01-23 02:23:51.001926: step: 296/530, loss: 0.004515647888183594
2023-01-23 02:23:52.181274: step: 300/530, loss: 0.0005843163235113025
2023-01-23 02:23:53.347241: step: 304/530, loss: 5.326271275407635e-05
2023-01-23 02:23:54.509837: step: 308/530, loss: 0.04109363630414009
2023-01-23 02:23:55.678491: step: 312/530, loss: 0.005698967259377241
2023-01-23 02:23:56.884188: step: 316/530, loss: 0.0011418343055993319
2023-01-23 02:23:58.033138: step: 320/530, loss: 0.06436445564031601
2023-01-23 02:23:59.217624: step: 324/530, loss: 0.002170562744140625
2023-01-23 02:24:00.397925: step: 328/530, loss: 0.007808208465576172
2023-01-23 02:24:01.518037: step: 332/530, loss: 0.014445877633988857
2023-01-23 02:24:02.737509: step: 336/530, loss: 0.01573162153363228
2023-01-23 02:24:03.925194: step: 340/530, loss: 0.02624797821044922
2023-01-23 02:24:05.102256: step: 344/530, loss: 0.0690792128443718
2023-01-23 02:24:06.279424: step: 348/530, loss: 0.04187946766614914
2023-01-23 02:24:07.432992: step: 352/530, loss: 0.06370649486780167
2023-01-23 02:24:08.604458: step: 356/530, loss: 0.0015368462773039937
2023-01-23 02:24:09.791873: step: 360/530, loss: 0.00043430327787064016
2023-01-23 02:24:10.961774: step: 364/530, loss: 0.03036670759320259
2023-01-23 02:24:12.166733: step: 368/530, loss: 0.010527038015425205
2023-01-23 02:24:13.323373: step: 372/530, loss: 0.014672852121293545
2023-01-23 02:24:14.519109: step: 376/530, loss: 0.032254885882139206
2023-01-23 02:24:15.686505: step: 380/530, loss: 0.14931999146938324
2023-01-23 02:24:16.881233: step: 384/530, loss: 0.001505136489868164
2023-01-23 02:24:18.016976: step: 388/530, loss: 0.0009296417119912803
2023-01-23 02:24:19.164243: step: 392/530, loss: 0.003215217497199774
2023-01-23 02:24:20.359418: step: 396/530, loss: 0.013692855834960938
2023-01-23 02:24:21.503970: step: 400/530, loss: 0.031210042536258698
2023-01-23 02:24:22.643461: step: 404/530, loss: 0.004226493649184704
2023-01-23 02:24:23.826107: step: 408/530, loss: 0.023108195513486862
2023-01-23 02:24:25.024938: step: 412/530, loss: 0.037575531750917435
2023-01-23 02:24:26.168121: step: 416/530, loss: 0.0019168853759765625
2023-01-23 02:24:27.303396: step: 420/530, loss: 0.015109062194824219
2023-01-23 02:24:28.459669: step: 424/530, loss: 0.010098935104906559
2023-01-23 02:24:29.630920: step: 428/530, loss: 0.01007843017578125
2023-01-23 02:24:30.802866: step: 432/530, loss: 0.005023574456572533
2023-01-23 02:24:31.950074: step: 436/530, loss: 0.054714396595954895
2023-01-23 02:24:33.142002: step: 440/530, loss: 0.0005581856239587069
2023-01-23 02:24:34.343713: step: 444/530, loss: 0.056307412683963776
2023-01-23 02:24:35.528212: step: 448/530, loss: 0.04155702888965607
2023-01-23 02:24:36.691614: step: 452/530, loss: 0.039597511291503906
2023-01-23 02:24:37.899704: step: 456/530, loss: 0.011385154910385609
2023-01-23 02:24:39.074041: step: 460/530, loss: 0.018801212310791016
2023-01-23 02:24:40.256400: step: 464/530, loss: 0.005802154541015625
2023-01-23 02:24:41.422467: step: 468/530, loss: 0.013228941708803177
2023-01-23 02:24:42.605682: step: 472/530, loss: 0.1714356392621994
2023-01-23 02:24:43.748671: step: 476/530, loss: 0.010793971829116344
2023-01-23 02:24:44.896106: step: 480/530, loss: 0.0006269455188885331
2023-01-23 02:24:46.084637: step: 484/530, loss: 0.06122856214642525
2023-01-23 02:24:47.249015: step: 488/530, loss: 0.024777555838227272
2023-01-23 02:24:48.404962: step: 492/530, loss: 0.0045528411865234375
2023-01-23 02:24:49.589495: step: 496/530, loss: 0.0003942489856854081
2023-01-23 02:24:50.751725: step: 500/530, loss: 0.08202056586742401
2023-01-23 02:24:51.906424: step: 504/530, loss: 0.0008361339569091797
2023-01-23 02:24:53.110059: step: 508/530, loss: 0.0027695419266819954
2023-01-23 02:24:54.283635: step: 512/530, loss: 0.04146299511194229
2023-01-23 02:24:55.439603: step: 516/530, loss: 0.0013261317508295178
2023-01-23 02:24:56.612257: step: 520/530, loss: 0.01635294035077095
2023-01-23 02:24:57.814122: step: 524/530, loss: 0.01120605506002903
2023-01-23 02:24:58.959127: step: 528/530, loss: 0.0028503418434411287
2023-01-23 02:25:00.114439: step: 532/530, loss: 0.004157161805778742
2023-01-23 02:25:01.266470: step: 536/530, loss: 0.0003058433358091861
2023-01-23 02:25:02.432019: step: 540/530, loss: 0.02652874030172825
2023-01-23 02:25:03.570768: step: 544/530, loss: 0.035640716552734375
2023-01-23 02:25:04.757020: step: 548/530, loss: 0.0001773834228515625
2023-01-23 02:25:05.979736: step: 552/530, loss: 0.008179092779755592
2023-01-23 02:25:07.117793: step: 556/530, loss: 0.008895683102309704
2023-01-23 02:25:08.271051: step: 560/530, loss: 0.08431173115968704
2023-01-23 02:25:09.462195: step: 564/530, loss: 0.017026519402861595
2023-01-23 02:25:10.690904: step: 568/530, loss: 0.0015573024284094572
2023-01-23 02:25:11.865330: step: 572/530, loss: 0.0261293426156044
2023-01-23 02:25:13.008486: step: 576/530, loss: 0.044504743069410324
2023-01-23 02:25:14.162771: step: 580/530, loss: 0.03055286407470703
2023-01-23 02:25:15.313815: step: 584/530, loss: 0.027416467666625977
2023-01-23 02:25:16.479101: step: 588/530, loss: 0.0003868580097332597
2023-01-23 02:25:17.636830: step: 592/530, loss: 0.13542652130126953
2023-01-23 02:25:18.839740: step: 596/530, loss: 0.006299400236457586
2023-01-23 02:25:20.025879: step: 600/530, loss: 0.0032575682271271944
2023-01-23 02:25:21.223973: step: 604/530, loss: 0.012951850891113281
2023-01-23 02:25:22.393421: step: 608/530, loss: 0.07056315243244171
2023-01-23 02:25:23.657021: step: 612/530, loss: 0.010294770821928978
2023-01-23 02:25:24.833965: step: 616/530, loss: 0.0098451878875494
2023-01-23 02:25:26.000475: step: 620/530, loss: 0.004827023018151522
2023-01-23 02:25:27.173914: step: 624/530, loss: 0.0022405623458325863
2023-01-23 02:25:28.350845: step: 628/530, loss: 0.0433996208012104
2023-01-23 02:25:29.532666: step: 632/530, loss: 0.024373246356844902
2023-01-23 02:25:30.693439: step: 636/530, loss: 0.020254040136933327
2023-01-23 02:25:31.903553: step: 640/530, loss: 0.009142017923295498
2023-01-23 02:25:33.093938: step: 644/530, loss: 0.005822372157126665
2023-01-23 02:25:34.253716: step: 648/530, loss: 0.0026299478486180305
2023-01-23 02:25:35.403741: step: 652/530, loss: 0.0027402881532907486
2023-01-23 02:25:36.585663: step: 656/530, loss: 0.01474304310977459
2023-01-23 02:25:37.774028: step: 660/530, loss: 0.02172079123556614
2023-01-23 02:25:38.932935: step: 664/530, loss: 0.053358934819698334
2023-01-23 02:25:40.135724: step: 668/530, loss: 0.009865951724350452
2023-01-23 02:25:41.305616: step: 672/530, loss: 0.0001432418794138357
2023-01-23 02:25:42.469191: step: 676/530, loss: 0.0013968468410894275
2023-01-23 02:25:43.629425: step: 680/530, loss: 0.0016103744274005294
2023-01-23 02:25:44.775714: step: 684/530, loss: 0.012549687176942825
2023-01-23 02:25:45.911115: step: 688/530, loss: 0.08399419486522675
2023-01-23 02:25:47.081295: step: 692/530, loss: 0.10415535420179367
2023-01-23 02:25:48.231472: step: 696/530, loss: 0.0022276879753917456
2023-01-23 02:25:49.390441: step: 700/530, loss: 0.020398329943418503
2023-01-23 02:25:50.552719: step: 704/530, loss: 0.0015520096058025956
2023-01-23 02:25:51.715070: step: 708/530, loss: 0.0034155845642089844
2023-01-23 02:25:52.876702: step: 712/530, loss: 0.006957626435905695
2023-01-23 02:25:54.035010: step: 716/530, loss: 0.011006355285644531
2023-01-23 02:25:55.187505: step: 720/530, loss: 0.010660839267075062
2023-01-23 02:25:56.397751: step: 724/530, loss: 0.008368397131562233
2023-01-23 02:25:57.589385: step: 728/530, loss: 0.0035962106194347143
2023-01-23 02:25:58.731878: step: 732/530, loss: 0.006811189465224743
2023-01-23 02:25:59.877708: step: 736/530, loss: 0.0031302450224757195
2023-01-23 02:26:01.036739: step: 740/530, loss: 0.0013644217979162931
2023-01-23 02:26:02.206542: step: 744/530, loss: 0.11601953208446503
2023-01-23 02:26:03.373168: step: 748/530, loss: 0.03023376502096653
2023-01-23 02:26:04.548161: step: 752/530, loss: 0.017046205699443817
2023-01-23 02:26:05.712844: step: 756/530, loss: 0.07289314270019531
2023-01-23 02:26:06.896940: step: 760/530, loss: 0.03202419355511665
2023-01-23 02:26:08.086008: step: 764/530, loss: 0.03344287723302841
2023-01-23 02:26:09.256392: step: 768/530, loss: 0.0030727863777428865
2023-01-23 02:26:10.496760: step: 772/530, loss: 0.026743507012724876
2023-01-23 02:26:11.645429: step: 776/530, loss: 0.04842090979218483
2023-01-23 02:26:12.832933: step: 780/530, loss: 0.02066974714398384
2023-01-23 02:26:14.014123: step: 784/530, loss: 0.005280685611069202
2023-01-23 02:26:15.191598: step: 788/530, loss: 0.008036899380385876
2023-01-23 02:26:16.346766: step: 792/530, loss: 0.013729572296142578
2023-01-23 02:26:17.551944: step: 796/530, loss: 0.022278975695371628
2023-01-23 02:26:18.729032: step: 800/530, loss: 0.027057457715272903
2023-01-23 02:26:19.900592: step: 804/530, loss: 0.018549634143710136
2023-01-23 02:26:21.088010: step: 808/530, loss: 0.007126140873879194
2023-01-23 02:26:22.284387: step: 812/530, loss: 0.018884658813476562
2023-01-23 02:26:23.473001: step: 816/530, loss: 0.0002930402697529644
2023-01-23 02:26:24.643028: step: 820/530, loss: 0.04835167154669762
2023-01-23 02:26:25.780370: step: 824/530, loss: 0.020741652697324753
2023-01-23 02:26:26.918956: step: 828/530, loss: 0.07707051932811737
2023-01-23 02:26:28.081869: step: 832/530, loss: 0.07047387957572937
2023-01-23 02:26:29.217398: step: 836/530, loss: 0.0033155917190015316
2023-01-23 02:26:30.385844: step: 840/530, loss: 0.001608562539331615
2023-01-23 02:26:31.511476: step: 844/530, loss: 0.0012276651104912162
2023-01-23 02:26:32.745017: step: 848/530, loss: 0.0017636299598962069
2023-01-23 02:26:33.909480: step: 852/530, loss: 0.05711803585290909
2023-01-23 02:26:35.080285: step: 856/530, loss: 0.018064118921756744
2023-01-23 02:26:36.315156: step: 860/530, loss: 0.00036964414175599813
2023-01-23 02:26:37.516699: step: 864/530, loss: 0.2907162308692932
2023-01-23 02:26:38.699174: step: 868/530, loss: 0.002490425016731024
2023-01-23 02:26:39.851274: step: 872/530, loss: 0.0352783203125
2023-01-23 02:26:41.012501: step: 876/530, loss: 0.0019029617542400956
2023-01-23 02:26:42.180522: step: 880/530, loss: 0.04857172816991806
2023-01-23 02:26:43.321820: step: 884/530, loss: 0.0005317211616784334
2023-01-23 02:26:44.490415: step: 888/530, loss: 0.05900631099939346
2023-01-23 02:26:45.653069: step: 892/530, loss: 0.003645277116447687
2023-01-23 02:26:46.819756: step: 896/530, loss: 0.052827075123786926
2023-01-23 02:26:47.957241: step: 900/530, loss: 0.004794598091393709
2023-01-23 02:26:49.107961: step: 904/530, loss: 0.0007216454250738025
2023-01-23 02:26:50.260597: step: 908/530, loss: 0.03386583551764488
2023-01-23 02:26:51.433398: step: 912/530, loss: 0.009466457180678844
2023-01-23 02:26:52.591592: step: 916/530, loss: 0.0433141253888607
2023-01-23 02:26:53.763164: step: 920/530, loss: 0.0036919594276696444
2023-01-23 02:26:54.948750: step: 924/530, loss: 0.00019907952810171992
2023-01-23 02:26:56.134543: step: 928/530, loss: 0.01747150532901287
2023-01-23 02:26:57.304025: step: 932/530, loss: 0.6426636576652527
2023-01-23 02:26:58.411392: step: 936/530, loss: 0.026026152074337006
2023-01-23 02:26:59.608877: step: 940/530, loss: 0.052445221692323685
2023-01-23 02:27:00.757058: step: 944/530, loss: 5.838871220475994e-05
2023-01-23 02:27:01.955752: step: 948/530, loss: 0.019314004108309746
2023-01-23 02:27:03.105579: step: 952/530, loss: 0.00019109249114990234
2023-01-23 02:27:04.260631: step: 956/530, loss: 0.0008402348030358553
2023-01-23 02:27:05.494040: step: 960/530, loss: 0.0036657333839684725
2023-01-23 02:27:06.676341: step: 964/530, loss: 0.012752722948789597
2023-01-23 02:27:07.859028: step: 968/530, loss: 0.03093414194881916
2023-01-23 02:27:09.074617: step: 972/530, loss: 0.06144285202026367
2023-01-23 02:27:10.198340: step: 976/530, loss: 0.06936054676771164
2023-01-23 02:27:11.426815: step: 980/530, loss: 0.025339510291814804
2023-01-23 02:27:12.633900: step: 984/530, loss: 0.01734151877462864
2023-01-23 02:27:13.812182: step: 988/530, loss: 0.036733053624629974
2023-01-23 02:27:14.992860: step: 992/530, loss: 0.019701385870575905
2023-01-23 02:27:16.217241: step: 996/530, loss: 0.025998689234256744
2023-01-23 02:27:17.398412: step: 1000/530, loss: 0.043432045727968216
2023-01-23 02:27:18.576258: step: 1004/530, loss: 0.039957426488399506
2023-01-23 02:27:19.758035: step: 1008/530, loss: 0.03496399149298668
2023-01-23 02:27:20.898573: step: 1012/530, loss: 0.017052460461854935
2023-01-23 02:27:22.117355: step: 1016/530, loss: 0.024935530498623848
2023-01-23 02:27:23.288387: step: 1020/530, loss: 0.0010368346702307463
2023-01-23 02:27:24.473893: step: 1024/530, loss: 0.026552438735961914
2023-01-23 02:27:25.657092: step: 1028/530, loss: 0.0009861945873126388
2023-01-23 02:27:26.811143: step: 1032/530, loss: 0.008784865960478783
2023-01-23 02:27:27.998984: step: 1036/530, loss: 0.1455141007900238
2023-01-23 02:27:29.157647: step: 1040/530, loss: 0.19695281982421875
2023-01-23 02:27:30.322925: step: 1044/530, loss: 0.010457802563905716
2023-01-23 02:27:31.446674: step: 1048/530, loss: 0.004074573516845703
2023-01-23 02:27:32.633398: step: 1052/530, loss: 0.0352146178483963
2023-01-23 02:27:33.862344: step: 1056/530, loss: 0.03600216284394264
2023-01-23 02:27:35.018010: step: 1060/530, loss: 0.07290458679199219
2023-01-23 02:27:36.171411: step: 1064/530, loss: 0.0008146286127157509
2023-01-23 02:27:37.332711: step: 1068/530, loss: 0.0027271269354969263
2023-01-23 02:27:38.525834: step: 1072/530, loss: 0.02322540245950222
2023-01-23 02:27:39.654500: step: 1076/530, loss: 0.012006091885268688
2023-01-23 02:27:40.830697: step: 1080/530, loss: 0.024133967235684395
2023-01-23 02:27:42.076651: step: 1084/530, loss: 0.014663697220385075
2023-01-23 02:27:43.238105: step: 1088/530, loss: 0.016333580017089844
2023-01-23 02:27:44.390690: step: 1092/530, loss: 0.008843421936035156
2023-01-23 02:27:45.553752: step: 1096/530, loss: 0.000602340733166784
2023-01-23 02:27:46.747837: step: 1100/530, loss: 0.0003247261047363281
2023-01-23 02:27:47.915931: step: 1104/530, loss: 0.010089969262480736
2023-01-23 02:27:49.111730: step: 1108/530, loss: 0.015249919146299362
2023-01-23 02:27:50.302480: step: 1112/530, loss: 0.00025005341740325093
2023-01-23 02:27:51.534908: step: 1116/530, loss: 0.5382595658302307
2023-01-23 02:27:52.710872: step: 1120/530, loss: 0.0032939910888671875
2023-01-23 02:27:53.917891: step: 1124/530, loss: 0.000779485737439245
2023-01-23 02:27:55.059048: step: 1128/530, loss: 0.008435631170868874
2023-01-23 02:27:56.249757: step: 1132/530, loss: 0.0423458106815815
2023-01-23 02:27:57.408229: step: 1136/530, loss: 0.0008742332574911416
2023-01-23 02:27:58.547685: step: 1140/530, loss: 0.06773968040943146
2023-01-23 02:27:59.724979: step: 1144/530, loss: 0.013946724124252796
2023-01-23 02:28:00.926982: step: 1148/530, loss: 0.013174057006835938
2023-01-23 02:28:02.083974: step: 1152/530, loss: 0.012566459365189075
2023-01-23 02:28:03.246771: step: 1156/530, loss: 1.621246337890625e-05
2023-01-23 02:28:04.464283: step: 1160/530, loss: 0.004331255331635475
2023-01-23 02:28:05.615460: step: 1164/530, loss: 0.01078033447265625
2023-01-23 02:28:06.791086: step: 1168/530, loss: 0.0037264826241880655
2023-01-23 02:28:07.993009: step: 1172/530, loss: 0.012298393063247204
2023-01-23 02:28:09.139888: step: 1176/530, loss: 0.005705452058464289
2023-01-23 02:28:10.317613: step: 1180/530, loss: 0.03402690961956978
2023-01-23 02:28:11.507679: step: 1184/530, loss: 0.05775032192468643
2023-01-23 02:28:12.663136: step: 1188/530, loss: 0.001377403736114502
2023-01-23 02:28:13.817466: step: 1192/530, loss: 0.02831859514117241
2023-01-23 02:28:15.009395: step: 1196/530, loss: 0.017070865258574486
2023-01-23 02:28:16.204356: step: 1200/530, loss: 0.008883858099579811
2023-01-23 02:28:17.412165: step: 1204/530, loss: 0.011878211051225662
2023-01-23 02:28:18.558197: step: 1208/530, loss: 0.002170658204704523
2023-01-23 02:28:19.742358: step: 1212/530, loss: 0.02340860292315483
2023-01-23 02:28:20.941026: step: 1216/530, loss: 8.325576345669106e-05
2023-01-23 02:28:22.089963: step: 1220/530, loss: 0.11175356060266495
2023-01-23 02:28:23.267876: step: 1224/530, loss: 0.001722145127132535
2023-01-23 02:28:24.427289: step: 1228/530, loss: 0.00021820068650413305
2023-01-23 02:28:25.595970: step: 1232/530, loss: 0.042913056910037994
2023-01-23 02:28:26.767061: step: 1236/530, loss: 0.0015806198352947831
2023-01-23 02:28:27.901189: step: 1240/530, loss: 0.0016660690307617188
2023-01-23 02:28:29.064362: step: 1244/530, loss: 0.005749988369643688
2023-01-23 02:28:30.254339: step: 1248/530, loss: 0.025263022631406784
2023-01-23 02:28:31.409720: step: 1252/530, loss: 0.015886783599853516
2023-01-23 02:28:32.548618: step: 1256/530, loss: 0.009708595462143421
2023-01-23 02:28:33.750768: step: 1260/530, loss: 0.0017901421524584293
2023-01-23 02:28:34.889031: step: 1264/530, loss: 0.1504424512386322
2023-01-23 02:28:36.057616: step: 1268/530, loss: 0.016597747802734375
2023-01-23 02:28:37.234016: step: 1272/530, loss: 6.065368506824598e-05
2023-01-23 02:28:38.416369: step: 1276/530, loss: 0.008184432983398438
2023-01-23 02:28:39.615339: step: 1280/530, loss: 0.0037690596655011177
2023-01-23 02:28:40.784442: step: 1284/530, loss: 0.007947158999741077
2023-01-23 02:28:41.993394: step: 1288/530, loss: 0.06081543117761612
2023-01-23 02:28:43.147415: step: 1292/530, loss: 0.009768009185791016
2023-01-23 02:28:44.319225: step: 1296/530, loss: 0.007707023527473211
2023-01-23 02:28:45.527567: step: 1300/530, loss: 0.0012138367164880037
2023-01-23 02:28:46.767429: step: 1304/530, loss: 0.015604686923325062
2023-01-23 02:28:47.966483: step: 1308/530, loss: 0.0006648540729656816
2023-01-23 02:28:49.187403: step: 1312/530, loss: 0.07854995876550674
2023-01-23 02:28:50.363781: step: 1316/530, loss: 0.037283897399902344
2023-01-23 02:28:51.553028: step: 1320/530, loss: 0.003159046173095703
2023-01-23 02:28:52.765133: step: 1324/530, loss: 0.0773005485534668
2023-01-23 02:28:53.928339: step: 1328/530, loss: 0.05927448347210884
2023-01-23 02:28:55.093501: step: 1332/530, loss: 0.010669517330825329
2023-01-23 02:28:56.257652: step: 1336/530, loss: 0.04663993418216705
2023-01-23 02:28:57.427099: step: 1340/530, loss: 0.03563842922449112
2023-01-23 02:28:58.593331: step: 1344/530, loss: 0.021506501361727715
2023-01-23 02:28:59.758272: step: 1348/530, loss: 0.000225067138671875
2023-01-23 02:29:00.904817: step: 1352/530, loss: 0.004286480136215687
2023-01-23 02:29:02.107745: step: 1356/530, loss: 0.02083444595336914
2023-01-23 02:29:03.298727: step: 1360/530, loss: 0.025443362072110176
2023-01-23 02:29:04.456806: step: 1364/530, loss: 0.0661352202296257
2023-01-23 02:29:05.659877: step: 1368/530, loss: 0.030336380004882812
2023-01-23 02:29:06.835927: step: 1372/530, loss: 0.0747671127319336
2023-01-23 02:29:08.005405: step: 1376/530, loss: 0.03721001371741295
2023-01-23 02:29:09.176812: step: 1380/530, loss: 0.005052948370575905
2023-01-23 02:29:10.381094: step: 1384/530, loss: 0.016537094488739967
2023-01-23 02:29:11.528409: step: 1388/530, loss: 0.03815498575568199
2023-01-23 02:29:12.738917: step: 1392/530, loss: 0.007051658816635609
2023-01-23 02:29:13.922318: step: 1396/530, loss: 0.05862021818757057
2023-01-23 02:29:15.083406: step: 1400/530, loss: 0.018903635442256927
2023-01-23 02:29:16.252544: step: 1404/530, loss: 0.0003411293146200478
2023-01-23 02:29:17.434418: step: 1408/530, loss: 0.04003643989562988
2023-01-23 02:29:18.604952: step: 1412/530, loss: 0.1779453307390213
2023-01-23 02:29:19.810411: step: 1416/530, loss: 0.03536586835980415
2023-01-23 02:29:20.977628: step: 1420/530, loss: 0.0015798569656908512
2023-01-23 02:29:22.121235: step: 1424/530, loss: 0.026375198736786842
2023-01-23 02:29:23.288355: step: 1428/530, loss: 0.0008258819580078125
2023-01-23 02:29:24.434376: step: 1432/530, loss: 0.01930971071124077
2023-01-23 02:29:25.595755: step: 1436/530, loss: 0.012260055169463158
2023-01-23 02:29:26.779468: step: 1440/530, loss: 0.06031780317425728
2023-01-23 02:29:27.922567: step: 1444/530, loss: 0.03060302883386612
2023-01-23 02:29:29.064464: step: 1448/530, loss: 0.002894878387451172
2023-01-23 02:29:30.222019: step: 1452/530, loss: 0.09255209565162659
2023-01-23 02:29:31.405349: step: 1456/530, loss: 0.014461898244917393
2023-01-23 02:29:32.585281: step: 1460/530, loss: 0.08630600571632385
2023-01-23 02:29:33.730952: step: 1464/530, loss: 0.014962387271225452
2023-01-23 02:29:34.904483: step: 1468/530, loss: 0.05495567247271538
2023-01-23 02:29:36.083974: step: 1472/530, loss: 0.00026302336482331157
2023-01-23 02:29:37.250064: step: 1476/530, loss: 0.0022361755836755037
2023-01-23 02:29:38.410761: step: 1480/530, loss: 0.009579122066497803
2023-01-23 02:29:39.581582: step: 1484/530, loss: 0.0024454116355627775
2023-01-23 02:29:40.761839: step: 1488/530, loss: 0.0028814375400543213
2023-01-23 02:29:41.924674: step: 1492/530, loss: 0.0005291939014568925
2023-01-23 02:29:43.082294: step: 1496/530, loss: 0.015950776636600494
2023-01-23 02:29:44.260771: step: 1500/530, loss: 0.004330158233642578
2023-01-23 02:29:45.430746: step: 1504/530, loss: 0.016999626532197
2023-01-23 02:29:46.559945: step: 1508/530, loss: 0.009596633724868298
2023-01-23 02:29:47.746551: step: 1512/530, loss: 0.025943376123905182
2023-01-23 02:29:48.941311: step: 1516/530, loss: 0.055799342691898346
2023-01-23 02:29:50.099605: step: 1520/530, loss: 0.00123939523473382
2023-01-23 02:29:51.325421: step: 1524/530, loss: 0.07560892403125763
2023-01-23 02:29:52.470318: step: 1528/530, loss: 0.049118999391794205
2023-01-23 02:29:53.629850: step: 1532/530, loss: 0.032479479908943176
2023-01-23 02:29:54.799185: step: 1536/530, loss: 0.1612628996372223
2023-01-23 02:29:55.957400: step: 1540/530, loss: 0.009149551391601562
2023-01-23 02:29:57.115673: step: 1544/530, loss: 0.0006500243907794356
2023-01-23 02:29:58.264219: step: 1548/530, loss: 0.018253136426210403
2023-01-23 02:29:59.468355: step: 1552/530, loss: 0.004974746610969305
2023-01-23 02:30:00.638034: step: 1556/530, loss: 0.0029735565185546875
2023-01-23 02:30:01.796286: step: 1560/530, loss: 0.013292980380356312
2023-01-23 02:30:02.969828: step: 1564/530, loss: 0.029894258826971054
2023-01-23 02:30:04.174691: step: 1568/530, loss: 0.09666679054498672
2023-01-23 02:30:05.313780: step: 1572/530, loss: 0.00869064312428236
2023-01-23 02:30:06.466153: step: 1576/530, loss: 0.04767752066254616
2023-01-23 02:30:07.624652: step: 1580/530, loss: 0.0014657974243164062
2023-01-23 02:30:08.809744: step: 1584/530, loss: 0.0024819374084472656
2023-01-23 02:30:10.035850: step: 1588/530, loss: 0.03092365339398384
2023-01-23 02:30:11.213154: step: 1592/530, loss: 0.03775196149945259
2023-01-23 02:30:12.392851: step: 1596/530, loss: 0.004747009836137295
2023-01-23 02:30:13.559480: step: 1600/530, loss: 0.0010620116954669356
2023-01-23 02:30:14.746153: step: 1604/530, loss: 0.054379653185606
2023-01-23 02:30:15.934266: step: 1608/530, loss: 0.017207050696015358
2023-01-23 02:30:17.111828: step: 1612/530, loss: 2.102851794916205e-05
2023-01-23 02:30:18.250583: step: 1616/530, loss: 0.0002582550223451108
2023-01-23 02:30:19.450848: step: 1620/530, loss: 0.0923502966761589
2023-01-23 02:30:20.640741: step: 1624/530, loss: 0.00016021728515625
2023-01-23 02:30:21.828995: step: 1628/530, loss: 0.03983049467206001
2023-01-23 02:30:23.001295: step: 1632/530, loss: 0.0005466461298055947
2023-01-23 02:30:24.189723: step: 1636/530, loss: 0.031905677169561386
2023-01-23 02:30:25.370267: step: 1640/530, loss: 2.384185791015625e-05
2023-01-23 02:30:26.598303: step: 1644/530, loss: 0.04746303707361221
2023-01-23 02:30:27.794269: step: 1648/530, loss: 0.004205894190818071
2023-01-23 02:30:28.960128: step: 1652/530, loss: 0.03114910237491131
2023-01-23 02:30:30.183566: step: 1656/530, loss: 0.006469440646469593
2023-01-23 02:30:31.350718: step: 1660/530, loss: 0.0570828914642334
2023-01-23 02:30:32.506077: step: 1664/530, loss: 0.009840392507612705
2023-01-23 02:30:33.667638: step: 1668/530, loss: 0.05516967549920082
2023-01-23 02:30:34.871705: step: 1672/530, loss: 0.04099029302597046
2023-01-23 02:30:36.015388: step: 1676/530, loss: 0.0006539345486089587
2023-01-23 02:30:37.156732: step: 1680/530, loss: 0.006010902114212513
2023-01-23 02:30:38.284413: step: 1684/530, loss: 0.3167191445827484
2023-01-23 02:30:39.463203: step: 1688/530, loss: 0.0024128914810717106
2023-01-23 02:30:40.630911: step: 1692/530, loss: 0.01779909059405327
2023-01-23 02:30:41.808141: step: 1696/530, loss: 0.021826840937137604
2023-01-23 02:30:42.991983: step: 1700/530, loss: 0.0077072144486010075
2023-01-23 02:30:44.188566: step: 1704/530, loss: 0.08192399144172668
2023-01-23 02:30:45.390159: step: 1708/530, loss: 0.0054261209443211555
2023-01-23 02:30:46.543563: step: 1712/530, loss: 0.0033092498779296875
2023-01-23 02:30:47.727510: step: 1716/530, loss: 0.015625381842255592
2023-01-23 02:30:48.889636: step: 1720/530, loss: 0.022611241787672043
2023-01-23 02:30:50.066001: step: 1724/530, loss: 0.006053256802260876
2023-01-23 02:30:51.208192: step: 1728/530, loss: 0.006259727291762829
2023-01-23 02:30:52.345352: step: 1732/530, loss: 0.016308307647705078
2023-01-23 02:30:53.520743: step: 1736/530, loss: 0.0623074509203434
2023-01-23 02:30:54.713555: step: 1740/530, loss: 0.004148387815803289
2023-01-23 02:30:55.905434: step: 1744/530, loss: 0.0021419525146484375
2023-01-23 02:30:57.059453: step: 1748/530, loss: 0.00035152435884810984
2023-01-23 02:30:58.249483: step: 1752/530, loss: 0.11254310607910156
2023-01-23 02:30:59.468738: step: 1756/530, loss: 0.003956222906708717
2023-01-23 02:31:00.596026: step: 1760/530, loss: 0.11659526824951172
2023-01-23 02:31:01.792533: step: 1764/530, loss: 0.006517505738884211
2023-01-23 02:31:02.970389: step: 1768/530, loss: 0.002696418669074774
2023-01-23 02:31:04.169040: step: 1772/530, loss: 0.00025858881417661905
2023-01-23 02:31:05.321325: step: 1776/530, loss: 0.11178121715784073
2023-01-23 02:31:06.507579: step: 1780/530, loss: 0.014124107547104359
2023-01-23 02:31:07.660122: step: 1784/530, loss: 0.003504133317619562
2023-01-23 02:31:08.814232: step: 1788/530, loss: 0.06887169182300568
2023-01-23 02:31:10.010851: step: 1792/530, loss: 0.011696148663759232
2023-01-23 02:31:11.177348: step: 1796/530, loss: 0.000327873247442767
2023-01-23 02:31:12.342711: step: 1800/530, loss: 0.006048870272934437
2023-01-23 02:31:13.517693: step: 1804/530, loss: 0.00042724609375
2023-01-23 02:31:14.695973: step: 1808/530, loss: 0.042813874781131744
2023-01-23 02:31:15.858702: step: 1812/530, loss: 0.0016523362137377262
2023-01-23 02:31:17.048171: step: 1816/530, loss: 0.0038652420043945312
2023-01-23 02:31:18.240378: step: 1820/530, loss: 0.013066863641142845
2023-01-23 02:31:19.392310: step: 1824/530, loss: 0.01873188093304634
2023-01-23 02:31:20.562956: step: 1828/530, loss: 0.0333070307970047
2023-01-23 02:31:21.723925: step: 1832/530, loss: 0.008406544104218483
2023-01-23 02:31:22.912697: step: 1836/530, loss: 0.00029211046057753265
2023-01-23 02:31:24.097868: step: 1840/530, loss: 0.06285267323255539
2023-01-23 02:31:25.284639: step: 1844/530, loss: 0.008530807681381702
2023-01-23 02:31:26.435904: step: 1848/530, loss: 0.03209518641233444
2023-01-23 02:31:27.632776: step: 1852/530, loss: 0.06368818134069443
2023-01-23 02:31:28.848232: step: 1856/530, loss: 0.06327047199010849
2023-01-23 02:31:30.038010: step: 1860/530, loss: 0.01629047468304634
2023-01-23 02:31:31.170953: step: 1864/530, loss: 0.00112323765642941
2023-01-23 02:31:32.349301: step: 1868/530, loss: 0.025887776166200638
2023-01-23 02:31:33.496236: step: 1872/530, loss: 0.002650642301887274
2023-01-23 02:31:34.684117: step: 1876/530, loss: 0.011905098333954811
2023-01-23 02:31:35.853974: step: 1880/530, loss: 0.06725392490625381
2023-01-23 02:31:37.012127: step: 1884/530, loss: 0.00947804469615221
2023-01-23 02:31:38.208633: step: 1888/530, loss: 0.002638149308040738
2023-01-23 02:31:39.387553: step: 1892/530, loss: 0.042471691966056824
2023-01-23 02:31:40.551145: step: 1896/530, loss: 0.0111083984375
2023-01-23 02:31:41.738692: step: 1900/530, loss: 0.015712358057498932
2023-01-23 02:31:42.866571: step: 1904/530, loss: 0.01514902152121067
2023-01-23 02:31:43.997236: step: 1908/530, loss: 0.004777717404067516
2023-01-23 02:31:45.144665: step: 1912/530, loss: 0.001821804093196988
2023-01-23 02:31:46.314493: step: 1916/530, loss: 0.011377525515854359
2023-01-23 02:31:47.497765: step: 1920/530, loss: 0.003170871874317527
2023-01-23 02:31:48.688000: step: 1924/530, loss: 0.016153812408447266
2023-01-23 02:31:49.912003: step: 1928/530, loss: 0.12940844893455505
2023-01-23 02:31:51.078309: step: 1932/530, loss: 0.06450223922729492
2023-01-23 02:31:52.235180: step: 1936/530, loss: 0.003084373427554965
2023-01-23 02:31:53.396161: step: 1940/530, loss: 0.02369213104248047
2023-01-23 02:31:54.611901: step: 1944/530, loss: 0.01616687700152397
2023-01-23 02:31:55.754485: step: 1948/530, loss: 0.0005153656238690019
2023-01-23 02:31:56.966554: step: 1952/530, loss: 0.049954984337091446
2023-01-23 02:31:58.115062: step: 1956/530, loss: 0.033426474779844284
2023-01-23 02:31:59.302763: step: 1960/530, loss: 0.02971637435257435
2023-01-23 02:32:00.464472: step: 1964/530, loss: 0.014287757687270641
2023-01-23 02:32:01.616136: step: 1968/530, loss: 0.10565529018640518
2023-01-23 02:32:02.735753: step: 1972/530, loss: 0.04786510393023491
2023-01-23 02:32:03.943455: step: 1976/530, loss: 0.011258697137236595
2023-01-23 02:32:05.096713: step: 1980/530, loss: 0.0031207085121423006
2023-01-23 02:32:06.270250: step: 1984/530, loss: 0.05266456678509712
2023-01-23 02:32:07.423652: step: 1988/530, loss: 0.006815433502197266
2023-01-23 02:32:08.601987: step: 1992/530, loss: 0.008387184701859951
2023-01-23 02:32:09.752409: step: 1996/530, loss: 0.004331779666244984
2023-01-23 02:32:10.946635: step: 2000/530, loss: 0.013284874148666859
2023-01-23 02:32:12.134613: step: 2004/530, loss: 0.012166202068328857
2023-01-23 02:32:13.290522: step: 2008/530, loss: 0.007929325103759766
2023-01-23 02:32:14.449919: step: 2012/530, loss: 0.004205608740448952
2023-01-23 02:32:15.647510: step: 2016/530, loss: 0.007957840338349342
2023-01-23 02:32:16.878425: step: 2020/530, loss: 0.07635222375392914
2023-01-23 02:32:18.072264: step: 2024/530, loss: 0.00010805130295921117
2023-01-23 02:32:19.206198: step: 2028/530, loss: 0.0020953179337084293
2023-01-23 02:32:20.394623: step: 2032/530, loss: 0.004692792892456055
2023-01-23 02:32:21.518383: step: 2036/530, loss: 0.06972961872816086
2023-01-23 02:32:22.700201: step: 2040/530, loss: 0.48789748549461365
2023-01-23 02:32:23.849112: step: 2044/530, loss: 0.03279144689440727
2023-01-23 02:32:25.009572: step: 2048/530, loss: 0.02361736260354519
2023-01-23 02:32:26.155366: step: 2052/530, loss: 0.00763206509873271
2023-01-23 02:32:27.313981: step: 2056/530, loss: 0.001575040863826871
2023-01-23 02:32:28.529230: step: 2060/530, loss: 0.015694810077548027
2023-01-23 02:32:29.707410: step: 2064/530, loss: 0.00690960930660367
2023-01-23 02:32:30.856611: step: 2068/530, loss: 0.016270829364657402
2023-01-23 02:32:32.026515: step: 2072/530, loss: 0.4153619706630707
2023-01-23 02:32:33.171782: step: 2076/530, loss: 0.016048477962613106
2023-01-23 02:32:34.345579: step: 2080/530, loss: 0.014982796274125576
2023-01-23 02:32:35.489385: step: 2084/530, loss: 0.023361969739198685
2023-01-23 02:32:36.667716: step: 2088/530, loss: 0.677126407623291
2023-01-23 02:32:37.898196: step: 2092/530, loss: 0.027340127155184746
2023-01-23 02:32:39.102786: step: 2096/530, loss: 0.004211426246911287
2023-01-23 02:32:40.279366: step: 2100/530, loss: 0.19484834372997284
2023-01-23 02:32:41.460743: step: 2104/530, loss: 0.26508501172065735
2023-01-23 02:32:42.661162: step: 2108/530, loss: 0.08909378200769424
2023-01-23 02:32:43.829932: step: 2112/530, loss: 0.003685093019157648
2023-01-23 02:32:45.014677: step: 2116/530, loss: 0.013727569952607155
2023-01-23 02:32:46.175694: step: 2120/530, loss: 0.008339500054717064
==================================================
Loss: 0.036
--------------------
Dev: {'event': {'p': 0.5718475073313783, 'r': 0.7789613848202397, 'f1': 0.6595264937993235}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
Test: {'event': {'p': 0.6357110812023329, 'r': 0.8148361127084531, 'f1': 0.7142137096774194}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
Chinese: {'event': {'p': 0.5494505494505495, 'r': 0.9259259259259259, 'f1': 0.6896551724137931}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
Korean: {'event': {'p': 0.6481481481481481, 'r': 0.5555555555555556, 'f1': 0.5982905982905983}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
Russian: {'event': {'p': 0.39622641509433965, 'r': 0.5833333333333334, 'f1': 0.4719101123595506}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6351501668520578, 'r': 0.7603195739014648, 'f1': 0.6921212121212121}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Chinese: {'event': {'p': 0.6373175182481752, 'r': 0.8033352501437608, 'f1': 0.7107606207071993}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Chinese: {'event': {'p': 0.5903614457831325, 'r': 0.9074074074074074, 'f1': 0.7153284671532847}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5733990147783251, 'r': 0.7749667110519307, 'f1': 0.6591166477916196}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Eng Test for Korean: {'event': {'p': 0.6218005295675199, 'r': 0.8102357676825762, 'f1': 0.7036204744069912}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Sample Korean: {'event': {'p': 0.6417910447761194, 'r': 0.6825396825396826, 'f1': 0.6615384615384614}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5951882845188284, 'r': 0.7576564580559254, 'f1': 0.6666666666666666}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6663405088062623, 'r': 0.7832087406555491, 'f1': 0.7200634417129264}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5, 'r': 0.6666666666666666, 'f1': 0.5714285714285715}, '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 02:33:29.083276: step: 4/530, loss: 0.03409166261553764
2023-01-23 02:33:30.256290: step: 8/530, loss: 0.03193025663495064
2023-01-23 02:33:31.416475: step: 12/530, loss: 0.0058532715775072575
2023-01-23 02:33:32.546402: step: 16/530, loss: 0.0021389008034020662
2023-01-23 02:33:33.720798: step: 20/530, loss: 0.018410874530673027
2023-01-23 02:33:34.856137: step: 24/530, loss: 0.07471618801355362
2023-01-23 02:33:36.019379: step: 28/530, loss: 0.014126110821962357
2023-01-23 02:33:37.180529: step: 32/530, loss: 0.0005076408269815147
2023-01-23 02:33:38.363787: step: 36/530, loss: 0.01622305065393448
2023-01-23 02:33:39.582420: step: 40/530, loss: 0.02559223212301731
2023-01-23 02:33:40.827371: step: 44/530, loss: 0.05685615539550781
2023-01-23 02:33:42.064990: step: 48/530, loss: 2.4127959477482364e-05
2023-01-23 02:33:43.217495: step: 52/530, loss: 0.361195832490921
2023-01-23 02:33:44.344034: step: 56/530, loss: 0.0036674258299171925
2023-01-23 02:33:45.533776: step: 60/530, loss: 0.002258205320686102
2023-01-23 02:33:46.699018: step: 64/530, loss: 0.0048542022705078125
2023-01-23 02:33:47.933671: step: 68/530, loss: 0.712786078453064
2023-01-23 02:33:49.143163: step: 72/530, loss: 0.00347404507920146
2023-01-23 02:33:50.289647: step: 76/530, loss: 0.020935440436005592
2023-01-23 02:33:51.444209: step: 80/530, loss: 0.02510075643658638
2023-01-23 02:33:52.611983: step: 84/530, loss: 0.027249718084931374
2023-01-23 02:33:53.772423: step: 88/530, loss: 9.51766996877268e-05
2023-01-23 02:33:54.976043: step: 92/530, loss: 0.007130766287446022
2023-01-23 02:33:56.188790: step: 96/530, loss: 0.011723709292709827
2023-01-23 02:33:57.405529: step: 100/530, loss: 0.0028701783157885075
2023-01-23 02:33:58.578108: step: 104/530, loss: 0.09053116291761398
2023-01-23 02:33:59.742588: step: 108/530, loss: 0.0027308466378599405
2023-01-23 02:34:00.882690: step: 112/530, loss: 0.020466994494199753
2023-01-23 02:34:02.055681: step: 116/530, loss: 0.0215651523321867
2023-01-23 02:34:03.194016: step: 120/530, loss: 0.0008586883777752519
2023-01-23 02:34:04.377413: step: 124/530, loss: 0.0005118370172567666
2023-01-23 02:34:05.512207: step: 128/530, loss: 0.001217794488184154
2023-01-23 02:34:06.684538: step: 132/530, loss: 0.023675061762332916
2023-01-23 02:34:07.849041: step: 136/530, loss: 5.418656349182129
2023-01-23 02:34:09.039667: step: 140/530, loss: 0.01898517645895481
2023-01-23 02:34:10.233385: step: 144/530, loss: 0.18063677847385406
2023-01-23 02:34:11.463879: step: 148/530, loss: 0.005933571141213179
2023-01-23 02:34:12.595157: step: 152/530, loss: 0.24706535041332245
2023-01-23 02:34:13.746506: step: 156/530, loss: 0.0018049239879474044
2023-01-23 02:34:14.906219: step: 160/530, loss: 0.005853462032973766
2023-01-23 02:34:16.094298: step: 164/530, loss: 0.040555190294981
2023-01-23 02:34:17.255699: step: 168/530, loss: 0.008160400204360485
2023-01-23 02:34:18.421642: step: 172/530, loss: 0.003976630978286266
2023-01-23 02:34:19.556572: step: 176/530, loss: 0.00018596649169921875
2023-01-23 02:34:20.708678: step: 180/530, loss: 0.02903003618121147
2023-01-23 02:34:21.888339: step: 184/530, loss: 0.0016951560974121094
2023-01-23 02:34:23.066900: step: 188/530, loss: 0.0027680397033691406
2023-01-23 02:34:24.246613: step: 192/530, loss: 0.010685205459594727
2023-01-23 02:34:25.446414: step: 196/530, loss: 0.025789452716708183
2023-01-23 02:34:26.589819: step: 200/530, loss: 0.0025676728691905737
2023-01-23 02:34:27.811298: step: 204/530, loss: 9.460448927711695e-05
2023-01-23 02:34:28.973951: step: 208/530, loss: 0.040413569658994675
2023-01-23 02:34:30.148750: step: 212/530, loss: 0.0002845764101948589
2023-01-23 02:34:31.304971: step: 216/530, loss: 5.550384594243951e-05
2023-01-23 02:34:32.454166: step: 220/530, loss: 0.038589004427194595
2023-01-23 02:34:33.622751: step: 224/530, loss: 0.5917990207672119
2023-01-23 02:34:34.794589: step: 228/530, loss: 0.058554936200380325
2023-01-23 02:34:35.956557: step: 232/530, loss: 0.021830368787050247
2023-01-23 02:34:37.114387: step: 236/530, loss: 0.023868178948760033
2023-01-23 02:34:38.283892: step: 240/530, loss: 0.0064521790482103825
2023-01-23 02:34:39.453519: step: 244/530, loss: 0.009249306283891201
2023-01-23 02:34:40.649503: step: 248/530, loss: 0.00765189528465271
2023-01-23 02:34:41.803767: step: 252/530, loss: 0.0023962499108165503
2023-01-23 02:34:43.015839: step: 256/530, loss: 0.023401450365781784
2023-01-23 02:34:44.190213: step: 260/530, loss: 0.1560174822807312
2023-01-23 02:34:45.360686: step: 264/530, loss: 0.012804031372070312
2023-01-23 02:34:46.572855: step: 268/530, loss: 0.027866840362548828
2023-01-23 02:34:47.764782: step: 272/530, loss: 0.00036277773324400187
2023-01-23 02:34:48.943044: step: 276/530, loss: 0.05291710048913956
2023-01-23 02:34:50.154331: step: 280/530, loss: 0.027625083923339844
2023-01-23 02:34:51.314611: step: 284/530, loss: 0.7572216987609863
2023-01-23 02:34:52.483140: step: 288/530, loss: 0.019618989899754524
2023-01-23 02:34:53.695480: step: 292/530, loss: 0.0032339096069335938
2023-01-23 02:34:54.881224: step: 296/530, loss: 0.06748094409704208
2023-01-23 02:34:56.063581: step: 300/530, loss: 0.013437843881547451
2023-01-23 02:34:57.233451: step: 304/530, loss: 0.00042190554086118937
2023-01-23 02:34:58.394416: step: 308/530, loss: 0.10079803317785263
2023-01-23 02:34:59.546221: step: 312/530, loss: 0.025503158569335938
2023-01-23 02:35:00.689843: step: 316/530, loss: 0.04629535600543022
2023-01-23 02:35:01.855766: step: 320/530, loss: 0.0031642913818359375
2023-01-23 02:35:03.007990: step: 324/530, loss: 0.01624126359820366
2023-01-23 02:35:04.205847: step: 328/530, loss: 0.02054891549050808
2023-01-23 02:35:05.344262: step: 332/530, loss: 0.0045104981400072575
2023-01-23 02:35:06.518585: step: 336/530, loss: 0.019738389179110527
2023-01-23 02:35:07.722433: step: 340/530, loss: 0.007002639584243298
2023-01-23 02:35:08.869054: step: 344/530, loss: 0.027447987347841263
2023-01-23 02:35:10.060049: step: 348/530, loss: 0.029940320178866386
2023-01-23 02:35:11.222173: step: 352/530, loss: 0.02381744422018528
2023-01-23 02:35:12.400797: step: 356/530, loss: 0.0008230209350585938
2023-01-23 02:35:13.595102: step: 360/530, loss: 0.07859973609447479
2023-01-23 02:35:14.781059: step: 364/530, loss: 0.16619901359081268
2023-01-23 02:35:15.962559: step: 368/530, loss: 0.06649179756641388
2023-01-23 02:35:17.117924: step: 372/530, loss: 0.018617724999785423
2023-01-23 02:35:18.302749: step: 376/530, loss: 0.020396994426846504
2023-01-23 02:35:19.462006: step: 380/530, loss: 0.06969738006591797
2023-01-23 02:35:20.627333: step: 384/530, loss: 0.05618009343743324
2023-01-23 02:35:21.781635: step: 388/530, loss: 0.0010696410899981856
2023-01-23 02:35:22.974618: step: 392/530, loss: 0.019032049924135208
2023-01-23 02:35:24.146050: step: 396/530, loss: 0.0017854690086096525
2023-01-23 02:35:25.301175: step: 400/530, loss: 0.017742633819580078
2023-01-23 02:35:26.435872: step: 404/530, loss: 9.34600830078125e-05
2023-01-23 02:35:27.585722: step: 408/530, loss: 0.0009266853448934853
2023-01-23 02:35:28.750949: step: 412/530, loss: 0.3445890545845032
2023-01-23 02:35:29.905766: step: 416/530, loss: 0.013064194470643997
2023-01-23 02:35:31.056948: step: 420/530, loss: 0.06865697354078293
2023-01-23 02:35:32.239757: step: 424/530, loss: 0.011952400207519531
2023-01-23 02:35:33.472039: step: 428/530, loss: 0.018743276596069336
2023-01-23 02:35:34.620508: step: 432/530, loss: 0.036884307861328125
2023-01-23 02:35:35.806317: step: 436/530, loss: 0.011086653918027878
2023-01-23 02:35:36.959133: step: 440/530, loss: 0.025307463482022285
2023-01-23 02:35:38.136331: step: 444/530, loss: 0.19674663245677948
2023-01-23 02:35:39.317954: step: 448/530, loss: 0.01050043199211359
2023-01-23 02:35:40.461480: step: 452/530, loss: 3.8433074223576114e-05
2023-01-23 02:35:41.657673: step: 456/530, loss: 0.014889050275087357
2023-01-23 02:35:42.854964: step: 460/530, loss: 0.00867157056927681
2023-01-23 02:35:43.993673: step: 464/530, loss: 0.00893030222505331
2023-01-23 02:35:45.195441: step: 468/530, loss: 0.07373370975255966
2023-01-23 02:35:46.381744: step: 472/530, loss: 0.0002017974911723286
2023-01-23 02:35:47.521354: step: 476/530, loss: 8.554458327125758e-05
2023-01-23 02:35:48.676016: step: 480/530, loss: 0.0007474839221686125
2023-01-23 02:35:49.833953: step: 484/530, loss: 0.03641033545136452
2023-01-23 02:35:50.992603: step: 488/530, loss: 0.11632471531629562
2023-01-23 02:35:52.212029: step: 492/530, loss: 0.0019572018645703793
2023-01-23 02:35:53.358667: step: 496/530, loss: 0.0012701035011559725
2023-01-23 02:35:54.546155: step: 500/530, loss: 0.001673889230005443
2023-01-23 02:35:55.724654: step: 504/530, loss: 0.026025772094726562
2023-01-23 02:35:56.890192: step: 508/530, loss: 0.10651111602783203
2023-01-23 02:35:58.062680: step: 512/530, loss: 0.02816600725054741
2023-01-23 02:35:59.230332: step: 516/530, loss: 0.028992462903261185
2023-01-23 02:36:00.427393: step: 520/530, loss: 0.0013288498157635331
2023-01-23 02:36:01.570173: step: 524/530, loss: 0.0013687133323401213
2023-01-23 02:36:02.707297: step: 528/530, loss: 0.017392253503203392
2023-01-23 02:36:03.897683: step: 532/530, loss: 0.012844085693359375
2023-01-23 02:36:05.050119: step: 536/530, loss: 0.0003517150762490928
2023-01-23 02:36:06.263818: step: 540/530, loss: 0.0005889892345294356
2023-01-23 02:36:07.444841: step: 544/530, loss: 0.0009160995250567794
2023-01-23 02:36:08.627011: step: 548/530, loss: 4.081726001459174e-05
2023-01-23 02:36:09.757195: step: 552/530, loss: 0.0008733749273233116
2023-01-23 02:36:10.928766: step: 556/530, loss: 0.0006784438737668097
2023-01-23 02:36:12.113035: step: 560/530, loss: 0.0002115249662892893
2023-01-23 02:36:13.284227: step: 564/530, loss: 0.02852792665362358
2023-01-23 02:36:14.468277: step: 568/530, loss: 0.09874648600816727
2023-01-23 02:36:15.618649: step: 572/530, loss: 0.02537374570965767
2023-01-23 02:36:16.776585: step: 576/530, loss: 0.004939270205795765
2023-01-23 02:36:17.962119: step: 580/530, loss: 0.0022682189010083675
2023-01-23 02:36:19.145929: step: 584/530, loss: 0.02480793185532093
2023-01-23 02:36:20.312386: step: 588/530, loss: 0.0007406235090456903
2023-01-23 02:36:21.493128: step: 592/530, loss: 0.0005002975813113153
2023-01-23 02:36:22.664962: step: 596/530, loss: 0.24968652427196503
2023-01-23 02:36:23.857502: step: 600/530, loss: 0.03022770956158638
2023-01-23 02:36:25.022652: step: 604/530, loss: 0.00012073517427779734
2023-01-23 02:36:26.197441: step: 608/530, loss: 0.007216072175651789
2023-01-23 02:36:27.397892: step: 612/530, loss: 0.04644498974084854
2023-01-23 02:36:28.538470: step: 616/530, loss: 0.014883232302963734
2023-01-23 02:36:29.705618: step: 620/530, loss: 0.0011398314964026213
2023-01-23 02:36:30.862653: step: 624/530, loss: 0.02005157619714737
2023-01-23 02:36:32.020767: step: 628/530, loss: 0.00032124522840604186
2023-01-23 02:36:33.234172: step: 632/530, loss: 0.00857076607644558
2023-01-23 02:36:34.402988: step: 636/530, loss: 0.07529878616333008
2023-01-23 02:36:35.535842: step: 640/530, loss: 0.0004155159112997353
2023-01-23 02:36:36.697196: step: 644/530, loss: 0.46210968494415283
2023-01-23 02:36:37.899199: step: 648/530, loss: 0.016603946685791016
2023-01-23 02:36:39.099469: step: 652/530, loss: 0.03349647670984268
2023-01-23 02:36:40.253730: step: 656/530, loss: 0.0006025314796715975
2023-01-23 02:36:41.503261: step: 660/530, loss: 0.0027688026893883944
2023-01-23 02:36:42.657743: step: 664/530, loss: 0.00572891253978014
2023-01-23 02:36:43.823708: step: 668/530, loss: 0.009322834201157093
2023-01-23 02:36:45.017244: step: 672/530, loss: 0.029540730640292168
2023-01-23 02:36:46.212725: step: 676/530, loss: 0.004547500982880592
2023-01-23 02:36:47.400790: step: 680/530, loss: 0.025919485837221146
2023-01-23 02:36:48.565880: step: 684/530, loss: 0.00589828472584486
2023-01-23 02:36:49.729020: step: 688/530, loss: 0.0010640145046636462
2023-01-23 02:36:50.889151: step: 692/530, loss: 0.0022254944778978825
2023-01-23 02:36:52.023629: step: 696/530, loss: 0.0025725364685058594
2023-01-23 02:36:53.163917: step: 700/530, loss: 0.01551666297018528
2023-01-23 02:36:54.347276: step: 704/530, loss: 0.015275193378329277
2023-01-23 02:36:55.486260: step: 708/530, loss: 0.0029155730735510588
2023-01-23 02:36:56.650992: step: 712/530, loss: 0.002224445343017578
2023-01-23 02:36:57.869718: step: 716/530, loss: 0.007357120513916016
2023-01-23 02:36:59.025163: step: 720/530, loss: 0.005003166384994984
2023-01-23 02:37:00.232561: step: 724/530, loss: 0.012697601690888405
2023-01-23 02:37:01.388468: step: 728/530, loss: 0.00424881000071764
2023-01-23 02:37:02.584301: step: 732/530, loss: 0.0032243728637695312
2023-01-23 02:37:03.811025: step: 736/530, loss: 0.009167480282485485
2023-01-23 02:37:04.973595: step: 740/530, loss: 0.01875457912683487
2023-01-23 02:37:06.125508: step: 744/530, loss: 0.005012893583625555
2023-01-23 02:37:07.286221: step: 748/530, loss: 0.02488241344690323
2023-01-23 02:37:08.451387: step: 752/530, loss: 0.00024280548677779734
2023-01-23 02:37:09.661684: step: 756/530, loss: 0.012627220712602139
2023-01-23 02:37:10.829956: step: 760/530, loss: 0.0006450653309002519
2023-01-23 02:37:11.950228: step: 764/530, loss: 0.01956338994204998
2023-01-23 02:37:13.101224: step: 768/530, loss: 0.01053008995950222
2023-01-23 02:37:14.272450: step: 772/530, loss: 0.017417192459106445
2023-01-23 02:37:15.531589: step: 776/530, loss: 0.00564079312607646
2023-01-23 02:37:16.707662: step: 780/530, loss: 0.013112401589751244
2023-01-23 02:37:17.887799: step: 784/530, loss: 0.06111655384302139
2023-01-23 02:37:19.015100: step: 788/530, loss: 0.0050394535064697266
2023-01-23 02:37:20.187788: step: 792/530, loss: 0.05225839838385582
2023-01-23 02:37:21.325937: step: 796/530, loss: 0.0040902611799538136
2023-01-23 02:37:22.497706: step: 800/530, loss: 0.04330252483487129
2023-01-23 02:37:23.653672: step: 804/530, loss: 0.007888412103056908
2023-01-23 02:37:24.800902: step: 808/530, loss: 0.004364013671875
2023-01-23 02:37:26.039445: step: 812/530, loss: 0.07257270812988281
2023-01-23 02:37:27.216977: step: 816/530, loss: 0.02567659690976143
2023-01-23 02:37:28.394512: step: 820/530, loss: 0.03379053995013237
2023-01-23 02:37:29.545859: step: 824/530, loss: 0.002023029373958707
2023-01-23 02:37:30.736779: step: 828/530, loss: 0.3274766206741333
2023-01-23 02:37:31.883011: step: 832/530, loss: 0.07246441394090652
2023-01-23 02:37:33.057381: step: 836/530, loss: 0.0022808073554188013
2023-01-23 02:37:34.240910: step: 840/530, loss: 0.003610801650211215
2023-01-23 02:37:35.376747: step: 844/530, loss: 0.05038166046142578
2023-01-23 02:37:36.523034: step: 848/530, loss: 0.0072740791365504265
2023-01-23 02:37:37.666202: step: 852/530, loss: 0.006577110383659601
2023-01-23 02:37:38.885334: step: 856/530, loss: 0.0019723891746252775
2023-01-23 02:37:40.015619: step: 860/530, loss: 0.018727827817201614
2023-01-23 02:37:41.206998: step: 864/530, loss: 0.0038949965965002775
2023-01-23 02:37:42.333045: step: 868/530, loss: 0.0062927245162427425
2023-01-23 02:37:43.524070: step: 872/530, loss: 0.0012542724143713713
2023-01-23 02:37:44.688905: step: 876/530, loss: 0.006850815378129482
2023-01-23 02:37:45.828630: step: 880/530, loss: 0.0003421783621888608
2023-01-23 02:37:47.016574: step: 884/530, loss: 0.016699600964784622
2023-01-23 02:37:48.177924: step: 888/530, loss: 0.0003110409015789628
2023-01-23 02:37:49.356934: step: 892/530, loss: 0.013224220834672451
2023-01-23 02:37:50.535610: step: 896/530, loss: 0.011777782812714577
2023-01-23 02:37:51.719616: step: 900/530, loss: 0.026536274701356888
2023-01-23 02:37:52.886032: step: 904/530, loss: 0.04967556148767471
2023-01-23 02:37:54.016704: step: 908/530, loss: 0.025925733149051666
2023-01-23 02:37:55.209474: step: 912/530, loss: 0.03671465069055557
2023-01-23 02:37:56.367720: step: 916/530, loss: 0.0023569108452647924
2023-01-23 02:37:57.541110: step: 920/530, loss: 0.03594684973359108
2023-01-23 02:37:58.707864: step: 924/530, loss: 0.0007244587177410722
2023-01-23 02:37:59.872492: step: 928/530, loss: 0.0003900528245139867
2023-01-23 02:38:01.008980: step: 932/530, loss: 0.0003909588267561048
2023-01-23 02:38:02.184511: step: 936/530, loss: 6.008148193359375e-05
2023-01-23 02:38:03.345461: step: 940/530, loss: 0.0012351989280432463
2023-01-23 02:38:04.562098: step: 944/530, loss: 0.07258529961109161
2023-01-23 02:38:05.738504: step: 948/530, loss: 0.48776674270629883
2023-01-23 02:38:06.908367: step: 952/530, loss: 0.028760481625795364
2023-01-23 02:38:08.058006: step: 956/530, loss: 0.04018354415893555
2023-01-23 02:38:09.220865: step: 960/530, loss: 0.09177380055189133
2023-01-23 02:38:10.370500: step: 964/530, loss: 0.005367851350456476
2023-01-23 02:38:11.563003: step: 968/530, loss: 0.005866051185876131
2023-01-23 02:38:12.733335: step: 972/530, loss: 0.0022155761253088713
2023-01-23 02:38:13.943825: step: 976/530, loss: 0.009877204895019531
2023-01-23 02:38:15.091424: step: 980/530, loss: 0.01565866358578205
2023-01-23 02:38:16.272944: step: 984/530, loss: 0.016060637310147285
2023-01-23 02:38:17.398785: step: 988/530, loss: 0.0008542060968466103
2023-01-23 02:38:18.559159: step: 992/530, loss: 0.008973121643066406
2023-01-23 02:38:19.751852: step: 996/530, loss: 0.024879170581698418
2023-01-23 02:38:20.917048: step: 1000/530, loss: 0.007134533021599054
2023-01-23 02:38:22.145060: step: 1004/530, loss: 0.014979267492890358
2023-01-23 02:38:23.305680: step: 1008/530, loss: 0.001429542899131775
2023-01-23 02:38:24.429400: step: 1012/530, loss: 0.00026121141854673624
2023-01-23 02:38:25.561754: step: 1016/530, loss: 0.027822017669677734
2023-01-23 02:38:26.747988: step: 1020/530, loss: 3.2043459214037284e-05
2023-01-23 02:38:27.914027: step: 1024/530, loss: 0.027243996039032936
2023-01-23 02:38:29.080593: step: 1028/530, loss: 0.029395580291748047
2023-01-23 02:38:30.289133: step: 1032/530, loss: 0.025845492258667946
2023-01-23 02:38:31.455252: step: 1036/530, loss: 0.19599103927612305
2023-01-23 02:38:32.599893: step: 1040/530, loss: 0.02287006564438343
2023-01-23 02:38:33.774741: step: 1044/530, loss: 0.010676383972167969
2023-01-23 02:38:34.963868: step: 1048/530, loss: 0.020765114575624466
2023-01-23 02:38:36.083362: step: 1052/530, loss: 0.004429960623383522
2023-01-23 02:38:37.239775: step: 1056/530, loss: 0.10266468673944473
2023-01-23 02:38:38.402050: step: 1060/530, loss: 0.1548130214214325
2023-01-23 02:38:39.589628: step: 1064/530, loss: 0.056841567158699036
2023-01-23 02:38:40.770132: step: 1068/530, loss: 0.025782013311982155
2023-01-23 02:38:41.930308: step: 1072/530, loss: 0.012751614674925804
2023-01-23 02:38:43.109381: step: 1076/530, loss: 0.014635086059570312
2023-01-23 02:38:44.210609: step: 1080/530, loss: 0.00025453566922806203
2023-01-23 02:38:45.353612: step: 1084/530, loss: 0.030837249010801315
2023-01-23 02:38:46.555301: step: 1088/530, loss: 0.008731460198760033
2023-01-23 02:38:47.717777: step: 1092/530, loss: 0.012356853112578392
2023-01-23 02:38:48.889064: step: 1096/530, loss: 0.002835512161254883
2023-01-23 02:38:50.045751: step: 1100/530, loss: 0.0010138035286217928
2023-01-23 02:38:51.249159: step: 1104/530, loss: 0.0768800750374794
2023-01-23 02:38:52.388953: step: 1108/530, loss: 0.029697705060243607
2023-01-23 02:38:53.570270: step: 1112/530, loss: 0.009760475717484951
2023-01-23 02:38:54.744867: step: 1116/530, loss: 0.0021529197692871094
2023-01-23 02:38:55.899363: step: 1120/530, loss: 0.0017699719173833728
2023-01-23 02:38:57.134852: step: 1124/530, loss: 0.0008200168376788497
2023-01-23 02:38:58.365256: step: 1128/530, loss: 0.03922557830810547
2023-01-23 02:38:59.494784: step: 1132/530, loss: 0.00019550323486328125
2023-01-23 02:39:00.637809: step: 1136/530, loss: 0.016022611409425735
2023-01-23 02:39:01.817768: step: 1140/530, loss: 0.0006153106805868447
2023-01-23 02:39:02.981712: step: 1144/530, loss: 0.016709137707948685
2023-01-23 02:39:04.199232: step: 1148/530, loss: 0.006598090752959251
2023-01-23 02:39:05.390691: step: 1152/530, loss: 0.0005770683055743575
2023-01-23 02:39:06.582548: step: 1156/530, loss: 0.006673336029052734
2023-01-23 02:39:07.740041: step: 1160/530, loss: 0.054181672632694244
2023-01-23 02:39:08.887847: step: 1164/530, loss: 0.07523231208324432
2023-01-23 02:39:10.082759: step: 1168/530, loss: 0.01913623884320259
2023-01-23 02:39:11.256922: step: 1172/530, loss: 0.018793296068906784
2023-01-23 02:39:12.444374: step: 1176/530, loss: 0.08867178112268448
2023-01-23 02:39:13.587199: step: 1180/530, loss: 0.015080690383911133
2023-01-23 02:39:14.792617: step: 1184/530, loss: 0.005277061369270086
2023-01-23 02:39:15.949748: step: 1188/530, loss: 0.0006712913163937628
2023-01-23 02:39:17.134250: step: 1192/530, loss: 0.014921379275619984
2023-01-23 02:39:18.282739: step: 1196/530, loss: 0.010855864733457565
2023-01-23 02:39:19.481453: step: 1200/530, loss: 0.0003086090146098286
2023-01-23 02:39:20.632984: step: 1204/530, loss: 0.006305694580078125
2023-01-23 02:39:21.822305: step: 1208/530, loss: 0.35740986466407776
2023-01-23 02:39:22.967709: step: 1212/530, loss: 0.00034770966158248484
2023-01-23 02:39:24.136879: step: 1216/530, loss: 0.030100345611572266
2023-01-23 02:39:25.344502: step: 1220/530, loss: 0.00037059784517623484
2023-01-23 02:39:26.508017: step: 1224/530, loss: 0.0021636963356286287
2023-01-23 02:39:27.655203: step: 1228/530, loss: 0.08790435642004013
2023-01-23 02:39:28.815050: step: 1232/530, loss: 0.011873054318130016
2023-01-23 02:39:30.008600: step: 1236/530, loss: 0.038666918873786926
2023-01-23 02:39:31.169924: step: 1240/530, loss: 0.03247880935668945
2023-01-23 02:39:32.300978: step: 1244/530, loss: 0.01125960424542427
2023-01-23 02:39:33.505263: step: 1248/530, loss: 0.042960360646247864
2023-01-23 02:39:34.704804: step: 1252/530, loss: 0.006751346401870251
2023-01-23 02:39:35.847939: step: 1256/530, loss: 0.0007349014631472528
2023-01-23 02:39:37.021568: step: 1260/530, loss: 0.036782003939151764
2023-01-23 02:39:38.201079: step: 1264/530, loss: 0.021926403045654297
2023-01-23 02:39:39.355584: step: 1268/530, loss: 0.05921068415045738
2023-01-23 02:39:40.531371: step: 1272/530, loss: 0.01248469389975071
2023-01-23 02:39:41.721450: step: 1276/530, loss: 0.004160786047577858
2023-01-23 02:39:42.903328: step: 1280/530, loss: 0.0003606796090025455
2023-01-23 02:39:44.092604: step: 1284/530, loss: 0.04645023122429848
2023-01-23 02:39:45.281900: step: 1288/530, loss: 0.0006767272716388106
2023-01-23 02:39:46.443306: step: 1292/530, loss: 0.014310074038803577
2023-01-23 02:39:47.601768: step: 1296/530, loss: 0.03072500415146351
2023-01-23 02:39:48.779100: step: 1300/530, loss: 0.02213277667760849
2023-01-23 02:39:49.927498: step: 1304/530, loss: 7.019042823230848e-05
2023-01-23 02:39:51.113517: step: 1308/530, loss: 0.008624744601547718
2023-01-23 02:39:52.273794: step: 1312/530, loss: 0.018869400024414062
2023-01-23 02:39:53.469946: step: 1316/530, loss: 0.03334398195147514
2023-01-23 02:39:54.634780: step: 1320/530, loss: 0.10556736588478088
2023-01-23 02:39:55.819391: step: 1324/530, loss: 0.0023458481300622225
2023-01-23 02:39:57.003555: step: 1328/530, loss: 0.23438234627246857
2023-01-23 02:39:58.186243: step: 1332/530, loss: 0.027270697057247162
2023-01-23 02:39:59.425726: step: 1336/530, loss: 0.0030594351701438427
2023-01-23 02:40:00.600881: step: 1340/530, loss: 0.09040413051843643
2023-01-23 02:40:01.829242: step: 1344/530, loss: 0.013030719943344593
2023-01-23 02:40:03.002322: step: 1348/530, loss: 0.015890885144472122
2023-01-23 02:40:04.186741: step: 1352/530, loss: 0.00022902488126419485
2023-01-23 02:40:05.348747: step: 1356/530, loss: 0.0072998045943677425
2023-01-23 02:40:06.541589: step: 1360/530, loss: 0.0012067795032635331
2023-01-23 02:40:07.730763: step: 1364/530, loss: 0.05865049362182617
2023-01-23 02:40:08.898839: step: 1368/530, loss: 0.0024105070624500513
2023-01-23 02:40:10.108270: step: 1372/530, loss: 0.09917287528514862
2023-01-23 02:40:11.258854: step: 1376/530, loss: 0.0225190632045269
2023-01-23 02:40:12.434551: step: 1380/530, loss: 0.028338052332401276
2023-01-23 02:40:13.631642: step: 1384/530, loss: 0.003952884580940008
2023-01-23 02:40:14.805663: step: 1388/530, loss: 0.021691275760531425
2023-01-23 02:40:16.002309: step: 1392/530, loss: 0.007308769505470991
2023-01-23 02:40:17.177978: step: 1396/530, loss: 0.025660326704382896
2023-01-23 02:40:18.348626: step: 1400/530, loss: 0.0019244194263592362
2023-01-23 02:40:19.541506: step: 1404/530, loss: 0.017899896949529648
2023-01-23 02:40:20.710763: step: 1408/530, loss: 0.0030311583541333675
2023-01-23 02:40:21.884952: step: 1412/530, loss: 0.11538705974817276
2023-01-23 02:40:23.072206: step: 1416/530, loss: 0.0010082245571538806
2023-01-23 02:40:24.236671: step: 1420/530, loss: 0.007002830505371094
2023-01-23 02:40:25.423713: step: 1424/530, loss: 0.011046027764678001
2023-01-23 02:40:26.588585: step: 1428/530, loss: 0.006727063562721014
2023-01-23 02:40:27.768389: step: 1432/530, loss: 0.01045694388449192
2023-01-23 02:40:28.967870: step: 1436/530, loss: 0.009931564331054688
2023-01-23 02:40:30.137537: step: 1440/530, loss: 0.011141682043671608
2023-01-23 02:40:31.326433: step: 1444/530, loss: 0.05917654186487198
2023-01-23 02:40:32.503543: step: 1448/530, loss: 0.015395546332001686
2023-01-23 02:40:33.687760: step: 1452/530, loss: 0.004696083255112171
2023-01-23 02:40:34.860099: step: 1456/530, loss: 0.005094051361083984
2023-01-23 02:40:36.008647: step: 1460/530, loss: 0.06597013771533966
2023-01-23 02:40:37.181593: step: 1464/530, loss: 0.007323646452277899
2023-01-23 02:40:38.310964: step: 1468/530, loss: 0.0031986236572265625
2023-01-23 02:40:39.414660: step: 1472/530, loss: 0.00027751922607421875
2023-01-23 02:40:40.582038: step: 1476/530, loss: 0.0037458420265465975
2023-01-23 02:40:41.737129: step: 1480/530, loss: 0.015252591110765934
2023-01-23 02:40:42.873502: step: 1484/530, loss: 0.08825837075710297
2023-01-23 02:40:44.025621: step: 1488/530, loss: 0.00542717007920146
2023-01-23 02:40:45.223699: step: 1492/530, loss: 0.004946994595229626
2023-01-23 02:40:46.412889: step: 1496/530, loss: 0.009145736694335938
2023-01-23 02:40:47.636122: step: 1500/530, loss: 0.014439105987548828
2023-01-23 02:40:48.789809: step: 1504/530, loss: 0.027216052636504173
2023-01-23 02:40:49.991870: step: 1508/530, loss: 0.0015636443858966231
2023-01-23 02:40:51.181805: step: 1512/530, loss: 0.0009281158563680947
2023-01-23 02:40:52.338431: step: 1516/530, loss: 0.012662316672503948
2023-01-23 02:40:53.516533: step: 1520/530, loss: 0.0018008232582360506
2023-01-23 02:40:54.687160: step: 1524/530, loss: 0.008422087877988815
2023-01-23 02:40:55.854310: step: 1528/530, loss: 0.004255390260368586
2023-01-23 02:40:57.010617: step: 1532/530, loss: 0.0756072998046875
2023-01-23 02:40:58.256608: step: 1536/530, loss: 0.00725059537217021
2023-01-23 02:40:59.407586: step: 1540/530, loss: 0.043248940259218216
2023-01-23 02:41:00.606564: step: 1544/530, loss: 0.008237838745117188
2023-01-23 02:41:01.780322: step: 1548/530, loss: 0.058585021644830704
2023-01-23 02:41:02.996669: step: 1552/530, loss: 0.003091430990025401
2023-01-23 02:41:04.196374: step: 1556/530, loss: 0.013186454772949219
2023-01-23 02:41:05.355006: step: 1560/530, loss: 0.0006245136610232294
2023-01-23 02:41:06.498146: step: 1564/530, loss: 0.2169443666934967
2023-01-23 02:41:07.695919: step: 1568/530, loss: 0.003769779345020652
2023-01-23 02:41:08.875845: step: 1572/530, loss: 0.06667595356702805
2023-01-23 02:41:10.042460: step: 1576/530, loss: 0.0017553330399096012
2023-01-23 02:41:11.212539: step: 1580/530, loss: 0.0017334461444988847
2023-01-23 02:41:12.335375: step: 1584/530, loss: 0.00016732215590309352
2023-01-23 02:41:13.493905: step: 1588/530, loss: 0.005676889326423407
2023-01-23 02:41:14.693611: step: 1592/530, loss: 0.007348823361098766
2023-01-23 02:41:15.840151: step: 1596/530, loss: 0.004650783725082874
2023-01-23 02:41:17.019587: step: 1600/530, loss: 0.0018041610019281507
2023-01-23 02:41:18.172296: step: 1604/530, loss: 0.0005546570173464715
2023-01-23 02:41:19.335612: step: 1608/530, loss: 0.04350147396326065
2023-01-23 02:41:20.552210: step: 1612/530, loss: 0.07148732990026474
2023-01-23 02:41:21.723970: step: 1616/530, loss: 0.009390450082719326
2023-01-23 02:41:22.865491: step: 1620/530, loss: 0.008351897820830345
2023-01-23 02:41:24.002284: step: 1624/530, loss: 0.03175945207476616
2023-01-23 02:41:25.195888: step: 1628/530, loss: 0.006941413506865501
2023-01-23 02:41:26.360166: step: 1632/530, loss: 0.00262966169975698
2023-01-23 02:41:27.519995: step: 1636/530, loss: 0.05688037723302841
2023-01-23 02:41:28.695761: step: 1640/530, loss: 0.011173725128173828
2023-01-23 02:41:29.910838: step: 1644/530, loss: 0.021231651306152344
2023-01-23 02:41:31.098088: step: 1648/530, loss: 0.03823218494653702
2023-01-23 02:41:32.239297: step: 1652/530, loss: 0.14542102813720703
2023-01-23 02:41:33.395534: step: 1656/530, loss: 0.019134044647216797
2023-01-23 02:41:34.613838: step: 1660/530, loss: 0.048342134803533554
2023-01-23 02:41:35.757776: step: 1664/530, loss: 0.0018748283619061112
2023-01-23 02:41:36.917786: step: 1668/530, loss: 0.004034996498376131
2023-01-23 02:41:38.050499: step: 1672/530, loss: 0.009898758493363857
2023-01-23 02:41:39.197840: step: 1676/530, loss: 0.011515664868056774
2023-01-23 02:41:40.378108: step: 1680/530, loss: 0.020786762237548828
2023-01-23 02:41:41.531354: step: 1684/530, loss: 0.0028880122117698193
2023-01-23 02:41:42.699359: step: 1688/530, loss: 0.07844944298267365
2023-01-23 02:41:43.886539: step: 1692/530, loss: 0.0007944107055664062
2023-01-23 02:41:45.080078: step: 1696/530, loss: 0.0032321931794285774
2023-01-23 02:41:46.275784: step: 1700/530, loss: 0.042591288685798645
2023-01-23 02:41:47.454907: step: 1704/530, loss: 0.006742668338119984
2023-01-23 02:41:48.623969: step: 1708/530, loss: 0.017470741644501686
2023-01-23 02:41:49.788483: step: 1712/530, loss: 0.047254037111997604
2023-01-23 02:41:50.952316: step: 1716/530, loss: 0.0626431480050087
2023-01-23 02:41:52.154177: step: 1720/530, loss: 0.022672070190310478
2023-01-23 02:41:53.354437: step: 1724/530, loss: 0.0005521774874068797
2023-01-23 02:41:54.530247: step: 1728/530, loss: 0.05224495008587837
2023-01-23 02:41:55.717875: step: 1732/530, loss: 0.01851348951458931
2023-01-23 02:41:56.892398: step: 1736/530, loss: 0.00036687852116301656
2023-01-23 02:41:58.063883: step: 1740/530, loss: 1.8119812921213452e-06
2023-01-23 02:41:59.208178: step: 1744/530, loss: 0.019431257620453835
2023-01-23 02:42:00.342974: step: 1748/530, loss: 0.0014821053482592106
2023-01-23 02:42:01.484172: step: 1752/530, loss: 0.04274740070104599
2023-01-23 02:42:02.602609: step: 1756/530, loss: 8.673667616676539e-05
2023-01-23 02:42:03.780255: step: 1760/530, loss: 0.010945415124297142
2023-01-23 02:42:04.947566: step: 1764/530, loss: 0.02131347730755806
2023-01-23 02:42:06.132488: step: 1768/530, loss: 0.07749070972204208
2023-01-23 02:42:07.336371: step: 1772/530, loss: 0.04401283338665962
2023-01-23 02:42:08.545912: step: 1776/530, loss: 0.0020021439995616674
2023-01-23 02:42:09.737445: step: 1780/530, loss: 0.07927074283361435
2023-01-23 02:42:10.893494: step: 1784/530, loss: 0.04289231449365616
2023-01-23 02:42:12.076102: step: 1788/530, loss: 9.603500075172633e-05
2023-01-23 02:42:13.225962: step: 1792/530, loss: 0.00315513601526618
2023-01-23 02:42:14.400992: step: 1796/530, loss: 0.01003656443208456
2023-01-23 02:42:15.543031: step: 1800/530, loss: 0.0033452988136559725
2023-01-23 02:42:16.718600: step: 1804/530, loss: 0.026613807305693626
2023-01-23 02:42:17.885935: step: 1808/530, loss: 0.006705951876938343
2023-01-23 02:42:19.029289: step: 1812/530, loss: 0.0038832426071166992
2023-01-23 02:42:20.190373: step: 1816/530, loss: 0.0028166770935058594
2023-01-23 02:42:21.357282: step: 1820/530, loss: 0.004704857245087624
2023-01-23 02:42:22.567377: step: 1824/530, loss: 0.2028055191040039
2023-01-23 02:42:23.718220: step: 1828/530, loss: 0.0028890608809888363
2023-01-23 02:42:24.891562: step: 1832/530, loss: 0.02939453162252903
2023-01-23 02:42:26.065310: step: 1836/530, loss: 0.004063406493514776
2023-01-23 02:42:27.215469: step: 1840/530, loss: 0.0002134323149221018
2023-01-23 02:42:28.370786: step: 1844/530, loss: 0.012526988983154297
2023-01-23 02:42:29.518033: step: 1848/530, loss: 0.00046472548274323344
2023-01-23 02:42:30.665486: step: 1852/530, loss: 0.035840511322021484
2023-01-23 02:42:31.853169: step: 1856/530, loss: 0.03174581751227379
2023-01-23 02:42:33.022196: step: 1860/530, loss: 0.005585860926657915
2023-01-23 02:42:34.142046: step: 1864/530, loss: 0.056595515459775925
2023-01-23 02:42:35.312609: step: 1868/530, loss: 0.00035982130793854594
2023-01-23 02:42:36.481197: step: 1872/530, loss: 0.02503204345703125
2023-01-23 02:42:37.689637: step: 1876/530, loss: 0.0021556855645030737
2023-01-23 02:42:38.852545: step: 1880/530, loss: 0.047197818756103516
2023-01-23 02:42:40.065617: step: 1884/530, loss: 0.044970132410526276
2023-01-23 02:42:41.254835: step: 1888/530, loss: 0.0019651411566883326
2023-01-23 02:42:42.439632: step: 1892/530, loss: 0.0014049530727788806
2023-01-23 02:42:43.576978: step: 1896/530, loss: 0.007244301028549671
2023-01-23 02:42:44.714786: step: 1900/530, loss: 0.009137631393969059
2023-01-23 02:42:45.852457: step: 1904/530, loss: 0.010827827267348766
2023-01-23 02:42:47.002886: step: 1908/530, loss: 0.03342094644904137
2023-01-23 02:42:48.150404: step: 1912/530, loss: 0.021536540240049362
2023-01-23 02:42:49.302120: step: 1916/530, loss: 0.0064296722412109375
2023-01-23 02:42:50.477353: step: 1920/530, loss: 0.000888443028088659
2023-01-23 02:42:51.679108: step: 1924/530, loss: 0.2318347990512848
2023-01-23 02:42:52.861298: step: 1928/530, loss: 0.3979606330394745
2023-01-23 02:42:54.042015: step: 1932/530, loss: 0.011769676581025124
2023-01-23 02:42:55.205863: step: 1936/530, loss: 0.06081228330731392
2023-01-23 02:42:56.389292: step: 1940/530, loss: 0.00014829635620117188
2023-01-23 02:42:57.558140: step: 1944/530, loss: 0.09364471584558487
2023-01-23 02:42:58.735063: step: 1948/530, loss: 0.003618431044742465
2023-01-23 02:42:59.911046: step: 1952/530, loss: 0.0012670516734942794
2023-01-23 02:43:01.068581: step: 1956/530, loss: 0.007540226448327303
2023-01-23 02:43:02.269475: step: 1960/530, loss: 0.08635301142930984
2023-01-23 02:43:03.410880: step: 1964/530, loss: 0.00147247314453125
2023-01-23 02:43:04.587774: step: 1968/530, loss: 0.05287675932049751
2023-01-23 02:43:05.758027: step: 1972/530, loss: 0.012066555209457874
2023-01-23 02:43:06.919654: step: 1976/530, loss: 0.6425977349281311
2023-01-23 02:43:08.092519: step: 1980/530, loss: 0.018410682678222656
2023-01-23 02:43:09.248910: step: 1984/530, loss: 0.008228874765336514
2023-01-23 02:43:10.459596: step: 1988/530, loss: 0.01911945454776287
2023-01-23 02:43:11.696468: step: 1992/530, loss: 0.013846587389707565
2023-01-23 02:43:12.864860: step: 1996/530, loss: 0.004326343536376953
2023-01-23 02:43:14.048607: step: 2000/530, loss: 0.03020191192626953
2023-01-23 02:43:15.198297: step: 2004/530, loss: 0.011449813842773438
2023-01-23 02:43:16.380470: step: 2008/530, loss: 0.010785293765366077
2023-01-23 02:43:17.552937: step: 2012/530, loss: 0.0035800933837890625
2023-01-23 02:43:18.767490: step: 2016/530, loss: 0.0015200615162029862
2023-01-23 02:43:19.927374: step: 2020/530, loss: 0.1085285171866417
2023-01-23 02:43:21.090126: step: 2024/530, loss: 0.06195516511797905
2023-01-23 02:43:22.244012: step: 2028/530, loss: 0.0003504753112792969
2023-01-23 02:43:23.434420: step: 2032/530, loss: 0.03095712512731552
2023-01-23 02:43:24.624327: step: 2036/530, loss: 0.6720864772796631
2023-01-23 02:43:25.809956: step: 2040/530, loss: 0.006118678953498602
2023-01-23 02:43:26.971541: step: 2044/530, loss: 0.0020154984667897224
2023-01-23 02:43:28.177828: step: 2048/530, loss: 0.007496452424675226
2023-01-23 02:43:29.371105: step: 2052/530, loss: 0.005424309056252241
2023-01-23 02:43:30.570727: step: 2056/530, loss: 0.0023258209694176912
2023-01-23 02:43:31.746747: step: 2060/530, loss: 0.0790325179696083
2023-01-23 02:43:32.914613: step: 2064/530, loss: 0.018455268815159798
2023-01-23 02:43:34.063658: step: 2068/530, loss: 0.01391830574721098
2023-01-23 02:43:35.227889: step: 2072/530, loss: 0.0005587577470578253
2023-01-23 02:43:36.410376: step: 2076/530, loss: 0.006535434629768133
2023-01-23 02:43:37.563486: step: 2080/530, loss: 0.004719066433608532
2023-01-23 02:43:38.784740: step: 2084/530, loss: 0.005223512649536133
2023-01-23 02:43:39.968351: step: 2088/530, loss: 0.05034293979406357
2023-01-23 02:43:41.110964: step: 2092/530, loss: 0.06583500653505325
2023-01-23 02:43:42.261250: step: 2096/530, loss: 0.5655586123466492
2023-01-23 02:43:43.538818: step: 2100/530, loss: 0.010055827908217907
2023-01-23 02:43:44.707726: step: 2104/530, loss: 0.06341762840747833
2023-01-23 02:43:45.879143: step: 2108/530, loss: 0.011020947247743607
2023-01-23 02:43:47.021350: step: 2112/530, loss: 0.016041899099946022
2023-01-23 02:43:48.174660: step: 2116/530, loss: 0.03329448774456978
2023-01-23 02:43:49.346840: step: 2120/530, loss: 0.013577270321547985
==================================================
Loss: 0.046
--------------------
Dev: {'event': {'p': 0.6067297581493165, 'r': 0.7683089214380826, 'f1': 0.6780258519388953}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
Test: {'event': {'p': 0.6593252108716027, 'r': 0.8090856814261069, 'f1': 0.7265685515104571}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
Chinese: {'event': {'p': 0.5444444444444444, 'r': 0.9074074074074074, 'f1': 0.6805555555555556}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
Korean: {'event': {'p': 0.64, 'r': 0.5079365079365079, 'f1': 0.5663716814159292}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
Russian: {'event': {'p': 0.4222222222222222, 'r': 0.5277777777777778, 'f1': 0.46913580246913583}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6351501668520578, 'r': 0.7603195739014648, 'f1': 0.6921212121212121}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Chinese: {'event': {'p': 0.6373175182481752, 'r': 0.8033352501437608, 'f1': 0.7107606207071993}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Chinese: {'event': {'p': 0.5903614457831325, 'r': 0.9074074074074074, 'f1': 0.7153284671532847}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5733990147783251, 'r': 0.7749667110519307, 'f1': 0.6591166477916196}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Eng Test for Korean: {'event': {'p': 0.6218005295675199, 'r': 0.8102357676825762, 'f1': 0.7036204744069912}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Sample Korean: {'event': {'p': 0.6417910447761194, 'r': 0.6825396825396826, 'f1': 0.6615384615384614}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5951882845188284, 'r': 0.7576564580559254, 'f1': 0.6666666666666666}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6663405088062623, 'r': 0.7832087406555491, 'f1': 0.7200634417129264}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5, 'r': 0.6666666666666666, 'f1': 0.5714285714285715}, '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 02:44:32.337581: step: 4/530, loss: 0.08731546252965927
2023-01-23 02:44:33.526139: step: 8/530, loss: 0.003211593721061945
2023-01-23 02:44:34.670630: step: 12/530, loss: 0.004882622044533491
2023-01-23 02:44:35.804510: step: 16/530, loss: 0.01626458205282688
2023-01-23 02:44:36.953619: step: 20/530, loss: 0.029093457385897636
2023-01-23 02:44:38.121452: step: 24/530, loss: 0.002319574588909745
2023-01-23 02:44:39.266319: step: 28/530, loss: 0.0018962860340252519
2023-01-23 02:44:40.440374: step: 32/530, loss: 0.06318245083093643
2023-01-23 02:44:41.677241: step: 36/530, loss: 0.011015892028808594
2023-01-23 02:44:42.885078: step: 40/530, loss: 0.012590408325195312
2023-01-23 02:44:44.065193: step: 44/530, loss: 0.0428735725581646
2023-01-23 02:44:45.244735: step: 48/530, loss: 0.00112323765642941
2023-01-23 02:44:46.393855: step: 52/530, loss: 0.0013307571643963456
2023-01-23 02:44:47.568093: step: 56/530, loss: 0.0027105333283543587
2023-01-23 02:44:48.743210: step: 60/530, loss: 0.013242721557617188
2023-01-23 02:44:49.926328: step: 64/530, loss: 0.0004644870641641319
2023-01-23 02:44:51.088874: step: 68/530, loss: 0.03787526860833168
2023-01-23 02:44:52.264469: step: 72/530, loss: 0.02538614347577095
2023-01-23 02:44:53.419304: step: 76/530, loss: 0.0003286361461505294
2023-01-23 02:44:54.609264: step: 80/530, loss: 0.05097828060388565
2023-01-23 02:44:55.821878: step: 84/530, loss: 0.021771525964140892
2023-01-23 02:44:56.984531: step: 88/530, loss: 0.009287453256547451
2023-01-23 02:44:58.148471: step: 92/530, loss: 0.005253029055893421
2023-01-23 02:44:59.338367: step: 96/530, loss: 0.0002498626708984375
2023-01-23 02:45:00.496442: step: 100/530, loss: 0.013746262528002262
2023-01-23 02:45:01.678961: step: 104/530, loss: 0.03593464195728302
2023-01-23 02:45:02.833228: step: 108/530, loss: 0.0006011963123455644
2023-01-23 02:45:04.006399: step: 112/530, loss: 0.030145931988954544
2023-01-23 02:45:05.175567: step: 116/530, loss: 0.017331600189208984
2023-01-23 02:45:06.357406: step: 120/530, loss: 0.05127163231372833
2023-01-23 02:45:07.571286: step: 124/530, loss: 0.018137622624635696
2023-01-23 02:45:08.745848: step: 128/530, loss: 0.0030530933290719986
2023-01-23 02:45:09.932210: step: 132/530, loss: 0.019689178094267845
2023-01-23 02:45:11.101382: step: 136/530, loss: 3.356933666509576e-05
2023-01-23 02:45:12.342721: step: 140/530, loss: 0.1989917755126953
2023-01-23 02:45:13.519552: step: 144/530, loss: 0.002773189451545477
2023-01-23 02:45:14.653888: step: 148/530, loss: 0.0034418106079101562
2023-01-23 02:45:15.846855: step: 152/530, loss: 0.03624439612030983
2023-01-23 02:45:17.012909: step: 156/530, loss: 0.009095477871596813
2023-01-23 02:45:18.184372: step: 160/530, loss: 0.0038116455543786287
2023-01-23 02:45:19.336543: step: 164/530, loss: 0.08015841990709305
2023-01-23 02:45:20.516553: step: 168/530, loss: 5.254745701677166e-05
2023-01-23 02:45:21.674218: step: 172/530, loss: 0.0006334304925985634
2023-01-23 02:45:22.833224: step: 176/530, loss: 0.00020904542179778218
2023-01-23 02:45:24.005599: step: 180/530, loss: 0.0017430305015295744
2023-01-23 02:45:25.208195: step: 184/530, loss: 0.02249755896627903
2023-01-23 02:45:26.370516: step: 188/530, loss: 4.19616708313697e-06
2023-01-23 02:45:27.557139: step: 192/530, loss: 0.07040786743164062
2023-01-23 02:45:28.764794: step: 196/530, loss: 2.8133392333984375e-05
2023-01-23 02:45:29.917835: step: 200/530, loss: 0.022907830774784088
2023-01-23 02:45:31.048927: step: 204/530, loss: 0.02579517476260662
2023-01-23 02:45:32.231044: step: 208/530, loss: 9.250640869140625e-05
2023-01-23 02:45:33.399019: step: 212/530, loss: 0.0026067732833325863
2023-01-23 02:45:34.564000: step: 216/530, loss: 0.002763843396678567
2023-01-23 02:45:35.744026: step: 220/530, loss: 0.0003650665166787803
2023-01-23 02:45:36.899153: step: 224/530, loss: 0.00014553070650435984
2023-01-23 02:45:38.092793: step: 228/530, loss: 0.44648706912994385
2023-01-23 02:45:39.312798: step: 232/530, loss: 0.010247325524687767
2023-01-23 02:45:40.515781: step: 236/530, loss: 0.02717571146786213
2023-01-23 02:45:41.709410: step: 240/530, loss: 0.045014671981334686
2023-01-23 02:45:42.867382: step: 244/530, loss: 0.01828632317483425
2023-01-23 02:45:44.040348: step: 248/530, loss: 0.019773244857788086
2023-01-23 02:45:45.238039: step: 252/530, loss: 0.0400753989815712
2023-01-23 02:45:46.415387: step: 256/530, loss: 0.0039421082474291325
2023-01-23 02:45:47.593544: step: 260/530, loss: 0.000270843505859375
2023-01-23 02:45:48.755603: step: 264/530, loss: 0.0023492814507335424
2023-01-23 02:45:49.969076: step: 268/530, loss: 0.0022143363021314144
2023-01-23 02:45:51.100619: step: 272/530, loss: 0.012600421905517578
2023-01-23 02:45:52.283781: step: 276/530, loss: 0.007098579779267311
2023-01-23 02:45:53.465180: step: 280/530, loss: 0.029225779697299004
2023-01-23 02:45:54.658718: step: 284/530, loss: 0.014193153008818626
2023-01-23 02:45:55.790201: step: 288/530, loss: 0.006578278727829456
2023-01-23 02:45:57.018355: step: 292/530, loss: 0.024323465302586555
2023-01-23 02:45:58.212371: step: 296/530, loss: 0.010714054107666016
2023-01-23 02:45:59.381137: step: 300/530, loss: 0.0016795634292066097
2023-01-23 02:46:00.554588: step: 304/530, loss: 0.007739448919892311
2023-01-23 02:46:01.770264: step: 308/530, loss: 0.03632774204015732
2023-01-23 02:46:02.992871: step: 312/530, loss: 0.07028522342443466
2023-01-23 02:46:04.171497: step: 316/530, loss: 0.01283121109008789
2023-01-23 02:46:05.324738: step: 320/530, loss: 1.7976761228055693e-05
2023-01-23 02:46:06.491543: step: 324/530, loss: 0.005475426092743874
2023-01-23 02:46:07.664675: step: 328/530, loss: 0.001795101212337613
2023-01-23 02:46:08.846689: step: 332/530, loss: 0.05574951320886612
2023-01-23 02:46:09.999611: step: 336/530, loss: 0.0024168016389012337
2023-01-23 02:46:11.130961: step: 340/530, loss: 0.0015208721160888672
2023-01-23 02:46:12.326496: step: 344/530, loss: 0.018105316907167435
2023-01-23 02:46:13.567002: step: 348/530, loss: 0.022140122950077057
2023-01-23 02:46:14.721723: step: 352/530, loss: 0.00022935867309570312
2023-01-23 02:46:15.944901: step: 356/530, loss: 0.010883904062211514
2023-01-23 02:46:17.084115: step: 360/530, loss: 0.0033596036955714226
2023-01-23 02:46:18.225470: step: 364/530, loss: 0.0018317699432373047
2023-01-23 02:46:19.404228: step: 368/530, loss: 0.00045940876589156687
2023-01-23 02:46:20.578312: step: 372/530, loss: 0.025650693103671074
2023-01-23 02:46:21.703176: step: 376/530, loss: 0.0007993221515789628
2023-01-23 02:46:22.851746: step: 380/530, loss: 0.0006184577941894531
2023-01-23 02:46:24.025587: step: 384/530, loss: 0.04763927683234215
2023-01-23 02:46:25.225743: step: 388/530, loss: 0.020582865923643112
2023-01-23 02:46:26.391721: step: 392/530, loss: 0.014975547790527344
2023-01-23 02:46:27.560294: step: 396/530, loss: 0.007151699159294367
2023-01-23 02:46:28.744344: step: 400/530, loss: 0.03446569666266441
2023-01-23 02:46:29.907673: step: 404/530, loss: 0.00044422148494049907
2023-01-23 02:46:31.094752: step: 408/530, loss: 0.01243667583912611
2023-01-23 02:46:32.250593: step: 412/530, loss: 0.004374218173325062
2023-01-23 02:46:33.433975: step: 416/530, loss: 0.04748735576868057
2023-01-23 02:46:34.624280: step: 420/530, loss: 0.004000854678452015
2023-01-23 02:46:35.802822: step: 424/530, loss: 0.08920669555664062
2023-01-23 02:46:36.954737: step: 428/530, loss: 0.012965393252670765
2023-01-23 02:46:38.144967: step: 432/530, loss: 0.002680206438526511
2023-01-23 02:46:39.348612: step: 436/530, loss: 0.0006181717035360634
2023-01-23 02:46:40.513787: step: 440/530, loss: 0.00045413972111418843
2023-01-23 02:46:41.651615: step: 444/530, loss: 0.018158435821533203
2023-01-23 02:46:42.845476: step: 448/530, loss: 0.011905098333954811
2023-01-23 02:46:44.011412: step: 452/530, loss: 0.05325489118695259
2023-01-23 02:46:45.194275: step: 456/530, loss: 0.0315457358956337
2023-01-23 02:46:46.378397: step: 460/530, loss: 0.012611865997314453
2023-01-23 02:46:47.554251: step: 464/530, loss: 0.05681488662958145
2023-01-23 02:46:48.674086: step: 468/530, loss: 0.00366554269567132
2023-01-23 02:46:49.863023: step: 472/530, loss: 0.04110336676239967
2023-01-23 02:46:51.013394: step: 476/530, loss: 0.04525642469525337
2023-01-23 02:46:52.200202: step: 480/530, loss: 0.02527942694723606
2023-01-23 02:46:53.335638: step: 484/530, loss: 0.010525322519242764
2023-01-23 02:46:54.514926: step: 488/530, loss: 0.0024753091856837273
2023-01-23 02:46:55.681179: step: 492/530, loss: 0.04845710098743439
2023-01-23 02:46:56.896884: step: 496/530, loss: 0.010241317562758923
2023-01-23 02:46:58.067922: step: 500/530, loss: 0.001226663589477539
2023-01-23 02:46:59.250804: step: 504/530, loss: 0.0040802001021802425
2023-01-23 02:47:00.408064: step: 508/530, loss: 0.023234035819768906
2023-01-23 02:47:01.606875: step: 512/530, loss: 0.0009370446787215769
2023-01-23 02:47:02.785461: step: 516/530, loss: 0.015886306762695312
2023-01-23 02:47:03.927648: step: 520/530, loss: 2.2792815798311494e-05
2023-01-23 02:47:05.121501: step: 524/530, loss: 0.00012149810208939016
2023-01-23 02:47:06.280314: step: 528/530, loss: 0.0004351377720013261
2023-01-23 02:47:07.444524: step: 532/530, loss: 0.004988384433090687
2023-01-23 02:47:08.610950: step: 536/530, loss: 0.009182549081742764
2023-01-23 02:47:09.825196: step: 540/530, loss: 0.006745719816535711
2023-01-23 02:47:11.007523: step: 544/530, loss: 0.00202102679759264
2023-01-23 02:47:12.168667: step: 548/530, loss: 0.012156868353486061
2023-01-23 02:47:13.345437: step: 552/530, loss: 0.0357661247253418
2023-01-23 02:47:14.523524: step: 556/530, loss: 0.0006166935199871659
2023-01-23 02:47:15.682935: step: 560/530, loss: 0.0005097389221191406
2023-01-23 02:47:16.859678: step: 564/530, loss: 0.05349559709429741
2023-01-23 02:47:17.995796: step: 568/530, loss: 0.0304655060172081
2023-01-23 02:47:19.152698: step: 572/530, loss: 0.0022071837447583675
2023-01-23 02:47:20.339573: step: 576/530, loss: 0.0023141861893236637
2023-01-23 02:47:21.513685: step: 580/530, loss: 0.11306900531053543
2023-01-23 02:47:22.694194: step: 584/530, loss: 0.03875579684972763
2023-01-23 02:47:23.840295: step: 588/530, loss: 0.0009201050270348787
2023-01-23 02:47:25.054288: step: 592/530, loss: 0.07497863471508026
2023-01-23 02:47:26.231009: step: 596/530, loss: 0.02681136131286621
2023-01-23 02:47:27.396585: step: 600/530, loss: 0.0032764433417469263
2023-01-23 02:47:28.547929: step: 604/530, loss: 0.0005930424085818231
2023-01-23 02:47:29.706981: step: 608/530, loss: 0.010728120803833008
2023-01-23 02:47:30.854311: step: 612/530, loss: 0.03666238859295845
2023-01-23 02:47:32.021540: step: 616/530, loss: 0.0005529404152184725
2023-01-23 02:47:33.239102: step: 620/530, loss: 0.006221580319106579
2023-01-23 02:47:34.395474: step: 624/530, loss: 0.0005045890575274825
2023-01-23 02:47:35.570230: step: 628/530, loss: 0.009937859140336514
2023-01-23 02:47:36.770518: step: 632/530, loss: 0.022013474255800247
2023-01-23 02:47:37.952554: step: 636/530, loss: 0.03591747209429741
2023-01-23 02:47:39.134395: step: 640/530, loss: 0.001807880587875843
2023-01-23 02:47:40.298953: step: 644/530, loss: 0.0043773651123046875
2023-01-23 02:47:41.433771: step: 648/530, loss: 0.001859378768131137
2023-01-23 02:47:42.631142: step: 652/530, loss: 8.296967280330136e-06
2023-01-23 02:47:43.801778: step: 656/530, loss: 0.0009300231467932463
2023-01-23 02:47:44.960332: step: 660/530, loss: 0.0044667720794677734
2023-01-23 02:47:46.108739: step: 664/530, loss: 0.0028631212189793587
2023-01-23 02:47:47.289646: step: 668/530, loss: 0.003362464951351285
2023-01-23 02:47:48.443908: step: 672/530, loss: 0.0015993118286132812
2023-01-23 02:47:49.634117: step: 676/530, loss: 0.013833427801728249
2023-01-23 02:47:50.876951: step: 680/530, loss: 0.015366935171186924
2023-01-23 02:47:52.113805: step: 684/530, loss: 0.0005098343244753778
2023-01-23 02:47:53.359172: step: 688/530, loss: 0.030342651531100273
2023-01-23 02:47:54.525282: step: 692/530, loss: 0.0005279064062051475
2023-01-23 02:47:55.686416: step: 696/530, loss: 0.0009313583723269403
2023-01-23 02:47:56.833701: step: 700/530, loss: 0.05742311477661133
2023-01-23 02:47:58.042339: step: 704/530, loss: 0.0004680633719544858
2023-01-23 02:47:59.193104: step: 708/530, loss: 0.04494500532746315
2023-01-23 02:48:00.381792: step: 712/530, loss: 0.007596970070153475
2023-01-23 02:48:01.519675: step: 716/530, loss: 0.00036344528780318797
2023-01-23 02:48:02.697860: step: 720/530, loss: 0.020467663183808327
2023-01-23 02:48:03.869041: step: 724/530, loss: 0.001432228134945035
2023-01-23 02:48:05.078086: step: 728/530, loss: 0.031464576721191406
2023-01-23 02:48:06.255827: step: 732/530, loss: 0.0005321502685546875
2023-01-23 02:48:07.471590: step: 736/530, loss: 5.0163271225756034e-05
2023-01-23 02:48:08.656935: step: 740/530, loss: 0.0016584396362304688
2023-01-23 02:48:09.799350: step: 744/530, loss: 0.0016854286659508944
2023-01-23 02:48:10.995933: step: 748/530, loss: 0.0001693725644145161
2023-01-23 02:48:12.184862: step: 752/530, loss: 0.00048160552978515625
2023-01-23 02:48:13.346244: step: 756/530, loss: 0.03294429928064346
2023-01-23 02:48:14.519767: step: 760/530, loss: 0.008556365966796875
2023-01-23 02:48:15.698330: step: 764/530, loss: 0.008806896395981312
2023-01-23 02:48:16.885977: step: 768/530, loss: 0.00031452177790924907
2023-01-23 02:48:18.048949: step: 772/530, loss: 0.0009295940399169922
2023-01-23 02:48:19.196945: step: 776/530, loss: 0.0005523681757040322
2023-01-23 02:48:20.378029: step: 780/530, loss: 0.0008453846094198525
2023-01-23 02:48:21.550174: step: 784/530, loss: 2.784729076665826e-05
2023-01-23 02:48:22.787750: step: 788/530, loss: 0.0005505561712197959
2023-01-23 02:48:23.940710: step: 792/530, loss: 0.026918793097138405
2023-01-23 02:48:25.097798: step: 796/530, loss: 0.049049947410821915
2023-01-23 02:48:26.299099: step: 800/530, loss: 0.03280448913574219
2023-01-23 02:48:27.446544: step: 804/530, loss: 0.0008927464368753135
2023-01-23 02:48:28.616403: step: 808/530, loss: 0.08511290699243546
2023-01-23 02:48:29.767573: step: 812/530, loss: 0.014259815216064453
2023-01-23 02:48:31.016085: step: 816/530, loss: 5.110228061676025
2023-01-23 02:48:32.171827: step: 820/530, loss: 0.015688898041844368
2023-01-23 02:48:33.357786: step: 824/530, loss: 0.034385014325380325
2023-01-23 02:48:34.562404: step: 828/530, loss: 0.001645851181820035
2023-01-23 02:48:35.770471: step: 832/530, loss: 0.0894143134355545
2023-01-23 02:48:37.008218: step: 836/530, loss: 0.09483623504638672
2023-01-23 02:48:38.148267: step: 840/530, loss: 2.746581958490424e-05
2023-01-23 02:48:39.298921: step: 844/530, loss: 0.020100880414247513
2023-01-23 02:48:40.462937: step: 848/530, loss: 0.00029392243595793843
2023-01-23 02:48:41.664839: step: 852/530, loss: 0.005130100529640913
2023-01-23 02:48:42.869125: step: 856/530, loss: 0.0003288268926553428
2023-01-23 02:48:44.021298: step: 860/530, loss: 0.00045032502384856343
2023-01-23 02:48:45.245962: step: 864/530, loss: 0.0014226913917809725
2023-01-23 02:48:46.388747: step: 868/530, loss: 0.0004946053377352655
2023-01-23 02:48:47.555118: step: 872/530, loss: 0.03552541881799698
2023-01-23 02:48:48.738883: step: 876/530, loss: 0.022655868902802467
2023-01-23 02:48:49.901443: step: 880/530, loss: 0.03164510801434517
2023-01-23 02:48:51.071413: step: 884/530, loss: 0.004130268469452858
2023-01-23 02:48:52.233368: step: 888/530, loss: 0.03041095659136772
2023-01-23 02:48:53.387240: step: 892/530, loss: 0.0012725830310955644
2023-01-23 02:48:54.545053: step: 896/530, loss: 0.015390015207231045
2023-01-23 02:48:55.709427: step: 900/530, loss: 0.0036167146172374487
2023-01-23 02:48:56.870027: step: 904/530, loss: 0.0016943454975262284
2023-01-23 02:48:58.029745: step: 908/530, loss: 0.004737281706184149
2023-01-23 02:48:59.210462: step: 912/530, loss: 0.048510171473026276
2023-01-23 02:49:00.388121: step: 916/530, loss: 0.006301784422248602
2023-01-23 02:49:01.560093: step: 920/530, loss: 0.023771096020936966
2023-01-23 02:49:02.721500: step: 924/530, loss: 0.0030157091096043587
2023-01-23 02:49:03.888563: step: 928/530, loss: 0.005428886506706476
2023-01-23 02:49:05.072598: step: 932/530, loss: 0.0027680397033691406
2023-01-23 02:49:06.242573: step: 936/530, loss: 0.19505634903907776
2023-01-23 02:49:07.421517: step: 940/530, loss: 0.0029285431373864412
2023-01-23 02:49:08.556561: step: 944/530, loss: 0.0002811432059388608
2023-01-23 02:49:09.705715: step: 948/530, loss: 0.021420670673251152
2023-01-23 02:49:10.874929: step: 952/530, loss: 0.27518805861473083
2023-01-23 02:49:12.065151: step: 956/530, loss: 0.004327869508415461
2023-01-23 02:49:13.211329: step: 960/530, loss: 0.05240326002240181
2023-01-23 02:49:14.384039: step: 964/530, loss: 0.02823205105960369
2023-01-23 02:49:15.533797: step: 968/530, loss: 0.0302321445196867
2023-01-23 02:49:16.716973: step: 972/530, loss: 7.162094698287547e-05
2023-01-23 02:49:17.870156: step: 976/530, loss: 0.005374336615204811
2023-01-23 02:49:19.062328: step: 980/530, loss: 0.004407835192978382
2023-01-23 02:49:20.210840: step: 984/530, loss: 0.00928354263305664
2023-01-23 02:49:21.371033: step: 988/530, loss: 0.008812809363007545
2023-01-23 02:49:22.554546: step: 992/530, loss: 0.0013688087929040194
2023-01-23 02:49:23.724853: step: 996/530, loss: 0.008172322064638138
2023-01-23 02:49:24.875974: step: 1000/530, loss: 0.019528580829501152
2023-01-23 02:49:26.036926: step: 1004/530, loss: 0.06174096837639809
2023-01-23 02:49:27.217693: step: 1008/530, loss: 0.049163054674863815
2023-01-23 02:49:28.401412: step: 1012/530, loss: 0.04819812998175621
2023-01-23 02:49:29.564636: step: 1016/530, loss: 0.0008571624639444053
2023-01-23 02:49:30.745666: step: 1020/530, loss: 0.044623661786317825
2023-01-23 02:49:31.942435: step: 1024/530, loss: 0.03869228437542915
2023-01-23 02:49:33.082126: step: 1028/530, loss: 3.1137467885855585e-05
2023-01-23 02:49:34.270808: step: 1032/530, loss: 0.0003068924124818295
2023-01-23 02:49:35.406825: step: 1036/530, loss: 0.16441403329372406
2023-01-23 02:49:36.556461: step: 1040/530, loss: 0.01044769398868084
2023-01-23 02:49:37.719585: step: 1044/530, loss: 0.027341080829501152
2023-01-23 02:49:38.851027: step: 1048/530, loss: 9.140968177234754e-05
2023-01-23 02:49:40.020082: step: 1052/530, loss: 9.956360008800402e-05
2023-01-23 02:49:41.185882: step: 1056/530, loss: 0.008964228443801403
2023-01-23 02:49:42.331290: step: 1060/530, loss: 0.005856752395629883
2023-01-23 02:49:43.502520: step: 1064/530, loss: 0.006365204229950905
2023-01-23 02:49:44.661559: step: 1068/530, loss: 0.05787096172571182
2023-01-23 02:49:45.805898: step: 1072/530, loss: 0.02026653289794922
2023-01-23 02:49:46.980011: step: 1076/530, loss: 0.002571678254753351
2023-01-23 02:49:48.156073: step: 1080/530, loss: 0.019018160179257393
2023-01-23 02:49:49.300015: step: 1084/530, loss: 0.049323271960020065
2023-01-23 02:49:50.594647: step: 1088/530, loss: 0.010681820102036
2023-01-23 02:49:51.734939: step: 1092/530, loss: 0.1152862161397934
2023-01-23 02:49:52.962284: step: 1096/530, loss: 0.0026620866265147924
2023-01-23 02:49:54.141352: step: 1100/530, loss: 0.0006658554193563759
2023-01-23 02:49:55.309293: step: 1104/530, loss: 0.024102210998535156
2023-01-23 02:49:56.468584: step: 1108/530, loss: 0.000375127827282995
2023-01-23 02:49:57.634893: step: 1112/530, loss: 0.0016592026222497225
2023-01-23 02:49:58.785491: step: 1116/530, loss: 0.01584625244140625
2023-01-23 02:49:59.893630: step: 1120/530, loss: 0.0037805556785315275
2023-01-23 02:50:01.087265: step: 1124/530, loss: 0.0397428534924984
2023-01-23 02:50:02.240855: step: 1128/530, loss: 0.03263077884912491
2023-01-23 02:50:03.399980: step: 1132/530, loss: 0.007448005955666304
2023-01-23 02:50:04.574593: step: 1136/530, loss: 0.0503830686211586
2023-01-23 02:50:05.758119: step: 1140/530, loss: 0.0007847309461794794
2023-01-23 02:50:06.930286: step: 1144/530, loss: 0.021022368222475052
2023-01-23 02:50:08.169841: step: 1148/530, loss: 0.018467046320438385
2023-01-23 02:50:09.347102: step: 1152/530, loss: 1.409002661705017
2023-01-23 02:50:10.546270: step: 1156/530, loss: 0.001998090883716941
2023-01-23 02:50:11.677735: step: 1160/530, loss: 0.0002550125354900956
2023-01-23 02:50:12.901270: step: 1164/530, loss: 0.0013589859008789062
2023-01-23 02:50:14.102346: step: 1168/530, loss: 0.0034727095626294613
2023-01-23 02:50:15.265030: step: 1172/530, loss: 0.016455460339784622
2023-01-23 02:50:16.445145: step: 1176/530, loss: 0.016565322875976562
2023-01-23 02:50:17.583750: step: 1180/530, loss: 0.000928688095882535
2023-01-23 02:50:18.751844: step: 1184/530, loss: 0.03171367570757866
2023-01-23 02:50:19.946828: step: 1188/530, loss: 0.0445556640625
2023-01-23 02:50:21.107174: step: 1192/530, loss: 0.049439430236816406
2023-01-23 02:50:22.249276: step: 1196/530, loss: 0.045542143285274506
2023-01-23 02:50:23.415506: step: 1200/530, loss: 0.000340366386808455
2023-01-23 02:50:24.578638: step: 1204/530, loss: 0.0007524490356445312
2023-01-23 02:50:25.759951: step: 1208/530, loss: 0.9727697372436523
2023-01-23 02:50:26.958542: step: 1212/530, loss: 0.0008098125690594316
2023-01-23 02:50:28.132728: step: 1216/530, loss: 0.018622493371367455
2023-01-23 02:50:29.307720: step: 1220/530, loss: 0.002280807588249445
2023-01-23 02:50:30.481354: step: 1224/530, loss: 0.0019449234241619706
2023-01-23 02:50:31.622432: step: 1228/530, loss: 0.026145650073885918
2023-01-23 02:50:32.783556: step: 1232/530, loss: 0.004445314407348633
2023-01-23 02:50:33.968409: step: 1236/530, loss: 0.00715904263779521
2023-01-23 02:50:35.117235: step: 1240/530, loss: 0.02207021601498127
2023-01-23 02:50:36.281499: step: 1244/530, loss: 0.002135658171027899
2023-01-23 02:50:37.445500: step: 1248/530, loss: 0.26870614290237427
2023-01-23 02:50:38.649007: step: 1252/530, loss: 0.0390925407409668
2023-01-23 02:50:39.805023: step: 1256/530, loss: 0.08327951282262802
2023-01-23 02:50:40.976045: step: 1260/530, loss: 0.03345184400677681
2023-01-23 02:50:42.154021: step: 1264/530, loss: 0.005735874176025391
2023-01-23 02:50:43.312882: step: 1268/530, loss: 0.024141598492860794
2023-01-23 02:50:44.455966: step: 1272/530, loss: 0.0002511978382244706
2023-01-23 02:50:45.641449: step: 1276/530, loss: 0.012088775634765625
2023-01-23 02:50:46.833105: step: 1280/530, loss: 0.007942485623061657
2023-01-23 02:50:48.023956: step: 1284/530, loss: 0.0340055488049984
2023-01-23 02:50:49.197294: step: 1288/530, loss: 0.013054942712187767
2023-01-23 02:50:50.439137: step: 1292/530, loss: 0.004992294125258923
2023-01-23 02:50:51.601741: step: 1296/530, loss: 0.011607075110077858
2023-01-23 02:50:52.769492: step: 1300/530, loss: 0.027545548975467682
2023-01-23 02:50:53.947046: step: 1304/530, loss: 0.10063318908214569
2023-01-23 02:50:55.129537: step: 1308/530, loss: 0.01221618615090847
2023-01-23 02:50:56.281350: step: 1312/530, loss: 0.00024127960205078125
2023-01-23 02:50:57.440302: step: 1316/530, loss: 0.06658754497766495
2023-01-23 02:50:58.613164: step: 1320/530, loss: 0.0036728859413415194
2023-01-23 02:50:59.733004: step: 1324/530, loss: 0.017569541931152344
2023-01-23 02:51:00.964993: step: 1328/530, loss: 0.000995635986328125
2023-01-23 02:51:02.181074: step: 1332/530, loss: 0.0017778397304937243
2023-01-23 02:51:03.379904: step: 1336/530, loss: 0.000975322793237865
2023-01-23 02:51:04.555020: step: 1340/530, loss: 0.03961505740880966
2023-01-23 02:51:05.785366: step: 1344/530, loss: 0.012908171862363815
2023-01-23 02:51:06.986527: step: 1348/530, loss: 0.002530860947445035
2023-01-23 02:51:08.106396: step: 1352/530, loss: 0.005012703128159046
2023-01-23 02:51:09.330426: step: 1356/530, loss: 0.00020532608323264867
2023-01-23 02:51:10.530619: step: 1360/530, loss: 1.602172778802924e-05
2023-01-23 02:51:11.734913: step: 1364/530, loss: 0.06287936866283417
2023-01-23 02:51:12.908555: step: 1368/530, loss: 0.0008691787952557206
2023-01-23 02:51:14.140786: step: 1372/530, loss: 0.0019065856467932463
2023-01-23 02:51:15.285240: step: 1376/530, loss: 0.0002633094845805317
2023-01-23 02:51:16.488919: step: 1380/530, loss: 0.0257142074406147
2023-01-23 02:51:17.694954: step: 1384/530, loss: 0.006311893463134766
2023-01-23 02:51:18.862130: step: 1388/530, loss: 0.0022490499541163445
2023-01-23 02:51:20.023169: step: 1392/530, loss: 0.04547720029950142
2023-01-23 02:51:21.204189: step: 1396/530, loss: 0.020011521875858307
2023-01-23 02:51:22.330341: step: 1400/530, loss: 0.004957866854965687
2023-01-23 02:51:23.516013: step: 1404/530, loss: 0.023298360407352448
2023-01-23 02:51:24.673632: step: 1408/530, loss: 0.042855359613895416
2023-01-23 02:51:25.842171: step: 1412/530, loss: 0.003172206925228238
2023-01-23 02:51:27.016757: step: 1416/530, loss: 0.002076101489365101
2023-01-23 02:51:28.188762: step: 1420/530, loss: 0.021920491009950638
2023-01-23 02:51:29.362906: step: 1424/530, loss: 5.3119660151423886e-05
2023-01-23 02:51:30.533689: step: 1428/530, loss: 0.011325454339385033
2023-01-23 02:51:31.685366: step: 1432/530, loss: 0.006413173861801624
2023-01-23 02:51:32.836951: step: 1436/530, loss: 0.004166030790656805
2023-01-23 02:51:33.989340: step: 1440/530, loss: 0.000537872314453125
2023-01-23 02:51:35.144346: step: 1444/530, loss: 0.00027441978454589844
2023-01-23 02:51:36.307434: step: 1448/530, loss: 0.0006131172413006425
2023-01-23 02:51:37.481409: step: 1452/530, loss: 0.01329431589692831
2023-01-23 02:51:38.664613: step: 1456/530, loss: 0.0172044038772583
2023-01-23 02:51:39.826205: step: 1460/530, loss: 0.042227938771247864
2023-01-23 02:51:41.006603: step: 1464/530, loss: 0.030699919909238815
2023-01-23 02:51:42.221745: step: 1468/530, loss: 4.301071021473035e-05
2023-01-23 02:51:43.362027: step: 1472/530, loss: 0.0022124291863292456
2023-01-23 02:51:44.538404: step: 1476/530, loss: 0.05648408085107803
2023-01-23 02:51:45.713157: step: 1480/530, loss: 0.0002058513491647318
2023-01-23 02:51:46.885594: step: 1484/530, loss: 0.07944860309362411
2023-01-23 02:51:48.043469: step: 1488/530, loss: 0.0008404732216149569
2023-01-23 02:51:49.205710: step: 1492/530, loss: 0.00016269684419967234
2023-01-23 02:51:50.364131: step: 1496/530, loss: 0.0008409500005654991
2023-01-23 02:51:51.534557: step: 1500/530, loss: 0.023110484704375267
2023-01-23 02:51:52.701177: step: 1504/530, loss: 0.049431610852479935
2023-01-23 02:51:53.910516: step: 1508/530, loss: 0.0046066283248364925
2023-01-23 02:51:55.049175: step: 1512/530, loss: 0.00780754117295146
2023-01-23 02:51:56.207062: step: 1516/530, loss: 0.03497086092829704
2023-01-23 02:51:57.351110: step: 1520/530, loss: 0.0018076419364660978
2023-01-23 02:51:58.502977: step: 1524/530, loss: 0.03642215579748154
2023-01-23 02:51:59.695824: step: 1528/530, loss: 0.04146786034107208
2023-01-23 02:52:00.869428: step: 1532/530, loss: 0.00039768218994140625
2023-01-23 02:52:02.147108: step: 1536/530, loss: 0.0009428501361981034
2023-01-23 02:52:03.335077: step: 1540/530, loss: 0.0026311874389648438
2023-01-23 02:52:04.509040: step: 1544/530, loss: 0.0003707885625772178
2023-01-23 02:52:05.645348: step: 1548/530, loss: 0.008408975787460804
2023-01-23 02:52:06.788524: step: 1552/530, loss: 0.10661526024341583
2023-01-23 02:52:07.980497: step: 1556/530, loss: 0.0005186080816201866
2023-01-23 02:52:09.159706: step: 1560/530, loss: 0.00997066404670477
2023-01-23 02:52:10.294985: step: 1564/530, loss: 0.00014500618271995336
2023-01-23 02:52:11.458565: step: 1568/530, loss: 0.07678823918104172
2023-01-23 02:52:12.619041: step: 1572/530, loss: 0.0006864547613076866
2023-01-23 02:52:13.770900: step: 1576/530, loss: 5.2070619858568534e-05
2023-01-23 02:52:14.950362: step: 1580/530, loss: 0.012794685550034046
2023-01-23 02:52:16.137441: step: 1584/530, loss: 0.01699066162109375
2023-01-23 02:52:17.322623: step: 1588/530, loss: 0.056519508361816406
2023-01-23 02:52:18.501305: step: 1592/530, loss: 0.029676057398319244
2023-01-23 02:52:19.641698: step: 1596/530, loss: 0.002719879150390625
2023-01-23 02:52:20.795362: step: 1600/530, loss: 0.0036157132126390934
2023-01-23 02:52:21.953721: step: 1604/530, loss: 0.013831853866577148
2023-01-23 02:52:23.095164: step: 1608/530, loss: 0.009747696109116077
2023-01-23 02:52:24.252871: step: 1612/530, loss: 0.08169078826904297
2023-01-23 02:52:25.423353: step: 1616/530, loss: 0.012155246920883656
2023-01-23 02:52:26.594241: step: 1620/530, loss: 0.0034214023035019636
2023-01-23 02:52:27.753060: step: 1624/530, loss: 0.29299378395080566
2023-01-23 02:52:28.918875: step: 1628/530, loss: 0.046714067459106445
2023-01-23 02:52:30.086696: step: 1632/530, loss: 0.007000541780143976
2023-01-23 02:52:31.257269: step: 1636/530, loss: 0.01271047629415989
2023-01-23 02:52:32.421353: step: 1640/530, loss: 0.040493011474609375
2023-01-23 02:52:33.594241: step: 1644/530, loss: 0.0008849144214764237
2023-01-23 02:52:34.771069: step: 1648/530, loss: 0.0005269050598144531
2023-01-23 02:52:35.936309: step: 1652/530, loss: 0.030748462304472923
2023-01-23 02:52:37.099261: step: 1656/530, loss: 0.00012483597674872726
2023-01-23 02:52:38.253010: step: 1660/530, loss: 0.03260154649615288
2023-01-23 02:52:39.428763: step: 1664/530, loss: 0.00016431808762717992
2023-01-23 02:52:40.563689: step: 1668/530, loss: 0.04968414455652237
2023-01-23 02:52:41.732263: step: 1672/530, loss: 0.009979916736483574
2023-01-23 02:52:42.900272: step: 1676/530, loss: 0.0027227401733398438
2023-01-23 02:52:44.089899: step: 1680/530, loss: 0.02227640151977539
2023-01-23 02:52:45.285468: step: 1684/530, loss: 0.004439449869096279
2023-01-23 02:52:46.451937: step: 1688/530, loss: 0.0019729614723473787
2023-01-23 02:52:47.613951: step: 1692/530, loss: 0.0036115646362304688
2023-01-23 02:52:48.816555: step: 1696/530, loss: 0.0011323929065838456
2023-01-23 02:52:49.998369: step: 1700/530, loss: 0.0008643150213174522
2023-01-23 02:52:51.126158: step: 1704/530, loss: 0.0008229255327023566
2023-01-23 02:52:52.296379: step: 1708/530, loss: 0.020559310913085938
2023-01-23 02:52:53.478755: step: 1712/530, loss: 0.021995067596435547
2023-01-23 02:52:54.662207: step: 1716/530, loss: 0.004757118411362171
2023-01-23 02:52:55.817103: step: 1720/530, loss: 0.005992698483169079
2023-01-23 02:52:56.984603: step: 1724/530, loss: 0.014645003713667393
2023-01-23 02:52:58.155127: step: 1728/530, loss: 0.011148547753691673
2023-01-23 02:52:59.326499: step: 1732/530, loss: 0.09624643623828888
2023-01-23 02:53:00.488254: step: 1736/530, loss: 0.0002323150692973286
2023-01-23 02:53:01.668593: step: 1740/530, loss: 0.008537006564438343
2023-01-23 02:53:02.826711: step: 1744/530, loss: 0.005873298738151789
2023-01-23 02:53:03.995598: step: 1748/530, loss: 0.015085887163877487
2023-01-23 02:53:05.164390: step: 1752/530, loss: 0.015697669237852097
2023-01-23 02:53:06.325617: step: 1756/530, loss: 0.04855794832110405
2023-01-23 02:53:07.465662: step: 1760/530, loss: 0.01418523769825697
2023-01-23 02:53:08.657469: step: 1764/530, loss: 0.004877185914665461
2023-01-23 02:53:09.850833: step: 1768/530, loss: 0.002104091690853238
2023-01-23 02:53:11.066467: step: 1772/530, loss: 0.007519721984863281
2023-01-23 02:53:12.294617: step: 1776/530, loss: 0.0007884979131631553
2023-01-23 02:53:13.412931: step: 1780/530, loss: 0.055056486278772354
2023-01-23 02:53:14.580247: step: 1784/530, loss: 0.0006911277887411416
2023-01-23 02:53:15.753892: step: 1788/530, loss: 0.004710960201919079
2023-01-23 02:53:17.017113: step: 1792/530, loss: 0.0025168806314468384
2023-01-23 02:53:18.190045: step: 1796/530, loss: 0.0013077259063720703
2023-01-23 02:53:19.363758: step: 1800/530, loss: 0.0004760742303915322
2023-01-23 02:53:20.533028: step: 1804/530, loss: 0.0010419845348224044
2023-01-23 02:53:21.678336: step: 1808/530, loss: 0.0015901564620435238
2023-01-23 02:53:22.849827: step: 1812/530, loss: 0.0009578705066815019
2023-01-23 02:53:24.007623: step: 1816/530, loss: 0.05409584194421768
2023-01-23 02:53:25.154584: step: 1820/530, loss: 0.010852241888642311
2023-01-23 02:53:26.308869: step: 1824/530, loss: 0.04352989047765732
2023-01-23 02:53:27.496715: step: 1828/530, loss: 0.00035147665766999125
2023-01-23 02:53:28.676709: step: 1832/530, loss: 0.03391599655151367
2023-01-23 02:53:29.857938: step: 1836/530, loss: 0.011319829151034355
2023-01-23 02:53:31.034641: step: 1840/530, loss: 0.05328173562884331
2023-01-23 02:53:32.296432: step: 1844/530, loss: 0.014373970218002796
2023-01-23 02:53:33.496582: step: 1848/530, loss: 0.0025221826508641243
2023-01-23 02:53:34.677684: step: 1852/530, loss: 0.016671180725097656
2023-01-23 02:53:35.868214: step: 1856/530, loss: 0.0016723632579669356
2023-01-23 02:53:37.066693: step: 1860/530, loss: 0.009774875827133656
2023-01-23 02:53:38.262417: step: 1864/530, loss: 0.0005865097045898438
2023-01-23 02:53:39.410027: step: 1868/530, loss: 0.03930320590734482
2023-01-23 02:53:40.577735: step: 1872/530, loss: 0.015630245208740234
2023-01-23 02:53:41.801712: step: 1876/530, loss: 0.016068650409579277
2023-01-23 02:53:42.978751: step: 1880/530, loss: 0.019454479217529297
2023-01-23 02:53:44.113724: step: 1884/530, loss: 0.0010760307777673006
2023-01-23 02:53:45.277878: step: 1888/530, loss: 0.0010229110484942794
2023-01-23 02:53:46.485327: step: 1892/530, loss: 0.0022780895233154297
2023-01-23 02:53:47.671323: step: 1896/530, loss: 0.00028991702129133046
2023-01-23 02:53:48.835418: step: 1900/530, loss: 0.07015733420848846
2023-01-23 02:53:50.004555: step: 1904/530, loss: 0.014220619574189186
2023-01-23 02:53:51.177108: step: 1908/530, loss: 0.00106048583984375
2023-01-23 02:53:52.351251: step: 1912/530, loss: 0.0021484375465661287
2023-01-23 02:53:53.500497: step: 1916/530, loss: 0.02708902396261692
2023-01-23 02:53:54.636019: step: 1920/530, loss: 0.004189205355942249
2023-01-23 02:53:55.876335: step: 1924/530, loss: 0.007980250753462315
2023-01-23 02:53:57.085491: step: 1928/530, loss: 0.006542205810546875
2023-01-23 02:53:58.286193: step: 1932/530, loss: 0.06604842841625214
2023-01-23 02:53:59.433160: step: 1936/530, loss: 0.021529199555516243
2023-01-23 02:54:00.671570: step: 1940/530, loss: 0.005999374203383923
2023-01-23 02:54:01.885494: step: 1944/530, loss: 0.021640300750732422
2023-01-23 02:54:03.069191: step: 1948/530, loss: 0.0018211365677416325
2023-01-23 02:54:04.260123: step: 1952/530, loss: 0.05754471197724342
2023-01-23 02:54:05.434934: step: 1956/530, loss: 0.02467641979455948
2023-01-23 02:54:06.589353: step: 1960/530, loss: 0.009199715219438076
2023-01-23 02:54:07.741655: step: 1964/530, loss: 0.03348889201879501
2023-01-23 02:54:08.944372: step: 1968/530, loss: 0.003810358000919223
2023-01-23 02:54:10.114825: step: 1972/530, loss: 0.0021333694458007812
2023-01-23 02:54:11.271286: step: 1976/530, loss: 0.009641265496611595
2023-01-23 02:54:12.449515: step: 1980/530, loss: 0.15017947554588318
2023-01-23 02:54:13.614707: step: 1984/530, loss: 0.0017242431640625
2023-01-23 02:54:14.770003: step: 1988/530, loss: 0.0030120848678052425
2023-01-23 02:54:15.945921: step: 1992/530, loss: 6.542206392623484e-05
2023-01-23 02:54:17.143513: step: 1996/530, loss: 0.020133592188358307
2023-01-23 02:54:18.266696: step: 2000/530, loss: 0.024538516998291016
2023-01-23 02:54:19.424995: step: 2004/530, loss: 0.04491119459271431
2023-01-23 02:54:20.592136: step: 2008/530, loss: 0.00015878677368164062
2023-01-23 02:54:21.788312: step: 2012/530, loss: 0.06429443508386612
2023-01-23 02:54:22.994033: step: 2016/530, loss: 0.014173698611557484
2023-01-23 02:54:24.141791: step: 2020/530, loss: 0.0010260583367198706
2023-01-23 02:54:25.369664: step: 2024/530, loss: 0.003909301944077015
2023-01-23 02:54:26.575833: step: 2028/530, loss: 0.09355764091014862
2023-01-23 02:54:27.774630: step: 2032/530, loss: 0.08838023990392685
2023-01-23 02:54:28.928185: step: 2036/530, loss: 0.000682020210660994
2023-01-23 02:54:30.144332: step: 2040/530, loss: 0.010965347290039062
2023-01-23 02:54:31.325604: step: 2044/530, loss: 0.03920421749353409
2023-01-23 02:54:32.463360: step: 2048/530, loss: 0.00015046595945023
2023-01-23 02:54:33.605721: step: 2052/530, loss: 0.05347251892089844
2023-01-23 02:54:34.781344: step: 2056/530, loss: 0.003849220462143421
2023-01-23 02:54:35.948050: step: 2060/530, loss: 0.004295540042221546
2023-01-23 02:54:37.108186: step: 2064/530, loss: 0.00018529893714003265
2023-01-23 02:54:38.297631: step: 2068/530, loss: 0.05057726055383682
2023-01-23 02:54:39.459076: step: 2072/530, loss: 0.010421657003462315
2023-01-23 02:54:40.640513: step: 2076/530, loss: 0.027713680639863014
2023-01-23 02:54:41.821581: step: 2080/530, loss: 0.0021997452713549137
2023-01-23 02:54:43.067633: step: 2084/530, loss: 0.00946950912475586
2023-01-23 02:54:44.215936: step: 2088/530, loss: 0.042563535273075104
2023-01-23 02:54:45.385752: step: 2092/530, loss: 0.006267261225730181
2023-01-23 02:54:46.559648: step: 2096/530, loss: 0.02116994746029377
2023-01-23 02:54:47.718312: step: 2100/530, loss: 1.0490417707842425e-06
2023-01-23 02:54:48.850467: step: 2104/530, loss: 0.0016088008414953947
2023-01-23 02:54:50.028684: step: 2108/530, loss: 0.00010561943054199219
2023-01-23 02:54:51.239813: step: 2112/530, loss: 0.037711624056100845
2023-01-23 02:54:52.436048: step: 2116/530, loss: 0.0007719993591308594
2023-01-23 02:54:53.605424: step: 2120/530, loss: 0.009385490790009499
==================================================
Loss: 0.035
--------------------
Dev: {'event': {'p': 0.6120507399577167, 'r': 0.7709720372836218, 'f1': 0.6823806717737184}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
Test: {'event': {'p': 0.6701872299567931, 'r': 0.8027602070155262, 'f1': 0.7305075876504449}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
Chinese: {'event': {'p': 0.5581395348837209, 'r': 0.8888888888888888, 'f1': 0.6857142857142857}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
Korean: {'event': {'p': 0.6041666666666666, 'r': 0.4603174603174603, 'f1': 0.5225225225225225}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
Russian: {'event': {'p': 0.4318181818181818, 'r': 0.5277777777777778, 'f1': 0.47500000000000003}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6351501668520578, 'r': 0.7603195739014648, 'f1': 0.6921212121212121}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Chinese: {'event': {'p': 0.6373175182481752, 'r': 0.8033352501437608, 'f1': 0.7107606207071993}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Chinese: {'event': {'p': 0.5903614457831325, 'r': 0.9074074074074074, 'f1': 0.7153284671532847}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5733990147783251, 'r': 0.7749667110519307, 'f1': 0.6591166477916196}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Eng Test for Korean: {'event': {'p': 0.6218005295675199, 'r': 0.8102357676825762, 'f1': 0.7036204744069912}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Sample Korean: {'event': {'p': 0.6417910447761194, 'r': 0.6825396825396826, 'f1': 0.6615384615384614}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5951882845188284, 'r': 0.7576564580559254, 'f1': 0.6666666666666666}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6663405088062623, 'r': 0.7832087406555491, 'f1': 0.7200634417129264}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5, 'r': 0.6666666666666666, 'f1': 0.5714285714285715}, '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 02:55:35.977048: step: 4/530, loss: 3.5285952435515355e-06
2023-01-23 02:55:37.132714: step: 8/530, loss: 0.004494857974350452
2023-01-23 02:55:38.262394: step: 12/530, loss: 0.009712601080536842
2023-01-23 02:55:39.435296: step: 16/530, loss: 0.017217254266142845
2023-01-23 02:55:40.600241: step: 20/530, loss: 0.017223168164491653
2023-01-23 02:55:41.832292: step: 24/530, loss: 0.007773017510771751
2023-01-23 02:55:43.006353: step: 28/530, loss: 0.024262238293886185
2023-01-23 02:55:44.176991: step: 32/530, loss: 0.01746959798038006
2023-01-23 02:55:45.389224: step: 36/530, loss: 0.015763377770781517
2023-01-23 02:55:46.554538: step: 40/530, loss: 0.016458988189697266
2023-01-23 02:55:47.755017: step: 44/530, loss: 0.0013010025722905993
2023-01-23 02:55:48.905491: step: 48/530, loss: 0.00341377267614007
2023-01-23 02:55:50.117129: step: 52/530, loss: 0.02081756666302681
2023-01-23 02:55:51.276455: step: 56/530, loss: 0.009267354384064674
2023-01-23 02:55:52.456599: step: 60/530, loss: 0.02803630940616131
2023-01-23 02:55:53.615623: step: 64/530, loss: 0.022510243579745293
2023-01-23 02:55:54.803002: step: 68/530, loss: 2.5749204723979346e-06
2023-01-23 02:55:55.961593: step: 72/530, loss: 0.016012001782655716
2023-01-23 02:55:57.156472: step: 76/530, loss: 0.007861233316361904
2023-01-23 02:55:58.324804: step: 80/530, loss: 0.0009715080377645791
2023-01-23 02:55:59.466497: step: 84/530, loss: 0.008212089538574219
2023-01-23 02:56:00.636559: step: 88/530, loss: 0.028080463409423828
2023-01-23 02:56:01.807636: step: 92/530, loss: 0.0011782168876379728
2023-01-23 02:56:02.985589: step: 96/530, loss: 0.020347023382782936
2023-01-23 02:56:04.167412: step: 100/530, loss: 0.0031574249733239412
2023-01-23 02:56:05.388148: step: 104/530, loss: 0.0009094238630495965
2023-01-23 02:56:06.622192: step: 108/530, loss: 0.0061584473587572575
2023-01-23 02:56:07.795567: step: 112/530, loss: 0.02565603330731392
2023-01-23 02:56:08.997825: step: 116/530, loss: 0.012187957763671875
2023-01-23 02:56:10.148702: step: 120/530, loss: 0.0007822036277502775
2023-01-23 02:56:11.293622: step: 124/530, loss: 0.0015838623512536287
2023-01-23 02:56:12.460075: step: 128/530, loss: 0.0011169493664056063
2023-01-23 02:56:13.618329: step: 132/530, loss: 0.00036659243050962687
2023-01-23 02:56:14.756025: step: 136/530, loss: 0.00016479491023346782
2023-01-23 02:56:15.976006: step: 140/530, loss: 0.0007848739624023438
2023-01-23 02:56:17.135437: step: 144/530, loss: 0.00011167526099598035
2023-01-23 02:56:18.296603: step: 148/530, loss: 0.048809148371219635
2023-01-23 02:56:19.451428: step: 152/530, loss: 0.001256752060726285
2023-01-23 02:56:20.607254: step: 156/530, loss: 8.301735215354711e-05
2023-01-23 02:56:21.783681: step: 160/530, loss: 0.0301374439150095
2023-01-23 02:56:22.968956: step: 164/530, loss: 0.005618393421173096
2023-01-23 02:56:24.159354: step: 168/530, loss: 0.004328918643295765
2023-01-23 02:56:25.318582: step: 172/530, loss: 0.0005311965942382812
2023-01-23 02:56:26.473425: step: 176/530, loss: 6.675720101156912e-07
2023-01-23 02:56:27.618327: step: 180/530, loss: 0.003245329950004816
2023-01-23 02:56:28.817171: step: 184/530, loss: 6.189346458995715e-05
2023-01-23 02:56:29.956134: step: 188/530, loss: 0.008834934793412685
2023-01-23 02:56:31.106421: step: 192/530, loss: 0.208173468708992
2023-01-23 02:56:32.246226: step: 196/530, loss: 0.00015182496281340718
2023-01-23 02:56:33.395062: step: 200/530, loss: 3.852844383800402e-05
2023-01-23 02:56:34.593424: step: 204/530, loss: 0.0003869056818075478
2023-01-23 02:56:35.768710: step: 208/530, loss: 0.003646707395091653
2023-01-23 02:56:36.910476: step: 212/530, loss: 0.008428382687270641
2023-01-23 02:56:38.070987: step: 216/530, loss: 0.014367103576660156
2023-01-23 02:56:39.245502: step: 220/530, loss: 0.003682899521663785
2023-01-23 02:56:40.385481: step: 224/530, loss: 0.07329835742712021
2023-01-23 02:56:41.651872: step: 228/530, loss: 0.007677114102989435
2023-01-23 02:56:42.846098: step: 232/530, loss: 0.04851233959197998
2023-01-23 02:56:44.011243: step: 236/530, loss: 0.00024595262948423624
2023-01-23 02:56:45.189462: step: 240/530, loss: 0.009625816717743874
2023-01-23 02:56:46.360978: step: 244/530, loss: 0.0015760421520099044
2023-01-23 02:56:47.480543: step: 248/530, loss: 0.3921127915382385
2023-01-23 02:56:48.653667: step: 252/530, loss: 8.440017700195312e-05
2023-01-23 02:56:49.827675: step: 256/530, loss: 0.007750320713967085
2023-01-23 02:56:51.001688: step: 260/530, loss: 0.01088562048971653
2023-01-23 02:56:52.200152: step: 264/530, loss: 0.019208908081054688
2023-01-23 02:56:53.345698: step: 268/530, loss: 0.012321185320615768
2023-01-23 02:56:54.524879: step: 272/530, loss: 0.000782394374255091
2023-01-23 02:56:55.734494: step: 276/530, loss: 0.06163006275892258
2023-01-23 02:56:56.883767: step: 280/530, loss: 0.0003364324802532792
2023-01-23 02:56:58.033194: step: 284/530, loss: 0.00047407150850631297
2023-01-23 02:56:59.189459: step: 288/530, loss: 0.003242444945499301
2023-01-23 02:57:00.366016: step: 292/530, loss: 0.015432453714311123
2023-01-23 02:57:01.535799: step: 296/530, loss: 0.012733840383589268
2023-01-23 02:57:02.656717: step: 300/530, loss: 0.0007595241186209023
2023-01-23 02:57:03.845031: step: 304/530, loss: 0.007056236267089844
2023-01-23 02:57:04.989518: step: 308/530, loss: 6.027222116244957e-05
2023-01-23 02:57:06.132321: step: 312/530, loss: 1.9550323486328125e-05
2023-01-23 02:57:07.299277: step: 316/530, loss: 0.01812438853085041
2023-01-23 02:57:08.467097: step: 320/530, loss: 0.014356661587953568
2023-01-23 02:57:09.569418: step: 324/530, loss: 0.001021957490593195
2023-01-23 02:57:10.744744: step: 328/530, loss: 0.0027439119294285774
2023-01-23 02:57:11.908544: step: 332/530, loss: 0.06676959991455078
2023-01-23 02:57:13.073121: step: 336/530, loss: 3.3140181585622486e-06
2023-01-23 02:57:14.230387: step: 340/530, loss: 6.952285912120715e-05
2023-01-23 02:57:15.408079: step: 344/530, loss: 0.0003010749933309853
2023-01-23 02:57:16.561777: step: 348/530, loss: 0.001771831652149558
2023-01-23 02:57:17.746272: step: 352/530, loss: 0.0743328109383583
2023-01-23 02:57:18.906703: step: 356/530, loss: 0.19436712563037872
2023-01-23 02:57:20.045238: step: 360/530, loss: 0.046106718480587006
2023-01-23 02:57:21.220422: step: 364/530, loss: 0.01660776138305664
2023-01-23 02:57:22.351005: step: 368/530, loss: 0.0001832962007028982
2023-01-23 02:57:23.520232: step: 372/530, loss: -1.316070574830519e-05
2023-01-23 02:57:24.704015: step: 376/530, loss: 5.5027012422215194e-05
2023-01-23 02:57:25.899571: step: 380/530, loss: 0.0018413544166833162
2023-01-23 02:57:27.075355: step: 384/530, loss: 8.997917757369578e-05
2023-01-23 02:57:28.249952: step: 388/530, loss: 0.05882210657000542
2023-01-23 02:57:29.426826: step: 392/530, loss: 0.0004989624139852822
2023-01-23 02:57:30.604525: step: 396/530, loss: 0.0647214874625206
2023-01-23 02:57:31.785100: step: 400/530, loss: 0.00033435822115279734
2023-01-23 02:57:32.974951: step: 404/530, loss: 0.007675552275031805
2023-01-23 02:57:34.122332: step: 408/530, loss: 0.00044431688729673624
2023-01-23 02:57:35.300449: step: 412/530, loss: 0.00017051697068382055
2023-01-23 02:57:36.485902: step: 416/530, loss: 0.0007219314575195312
2023-01-23 02:57:37.665691: step: 420/530, loss: 0.0005723953363485634
2023-01-23 02:57:38.835068: step: 424/530, loss: 0.08560800552368164
2023-01-23 02:57:39.995783: step: 428/530, loss: 0.0006450176588259637
2023-01-23 02:57:41.147171: step: 432/530, loss: 0.0032886506523936987
2023-01-23 02:57:42.357677: step: 436/530, loss: 0.021869469434022903
2023-01-23 02:57:43.545738: step: 440/530, loss: 0.0006940364837646484
2023-01-23 02:57:44.692167: step: 444/530, loss: 0.002557945204898715
2023-01-23 02:57:45.842885: step: 448/530, loss: 0.0019124984974041581
2023-01-23 02:57:46.992626: step: 452/530, loss: 0.005414772778749466
2023-01-23 02:57:48.176560: step: 456/530, loss: 0.006275749299675226
2023-01-23 02:57:49.339639: step: 460/530, loss: 0.0008335114107467234
2023-01-23 02:57:50.481491: step: 464/530, loss: 0.00014209747314453125
2023-01-23 02:57:51.690096: step: 468/530, loss: 0.0007354736444540322
2023-01-23 02:57:52.879165: step: 472/530, loss: 0.001516151474788785
2023-01-23 02:57:54.054933: step: 476/530, loss: 0.0055089956149458885
2023-01-23 02:57:55.223555: step: 480/530, loss: 0.00229644775390625
2023-01-23 02:57:56.383433: step: 484/530, loss: 0.0053501129150390625
2023-01-23 02:57:57.545108: step: 488/530, loss: 0.0249465461820364
2023-01-23 02:57:58.693337: step: 492/530, loss: 0.047649770975112915
2023-01-23 02:57:59.863067: step: 496/530, loss: 0.01101017091423273
2023-01-23 02:58:01.081198: step: 500/530, loss: 0.004105091094970703
2023-01-23 02:58:02.253926: step: 504/530, loss: 0.0019854544661939144
2023-01-23 02:58:03.413989: step: 508/530, loss: 0.03286914899945259
2023-01-23 02:58:04.586956: step: 512/530, loss: 0.0023729801177978516
2023-01-23 02:58:05.774841: step: 516/530, loss: 0.0030362128745764494
2023-01-23 02:58:06.930383: step: 520/530, loss: 0.00029792787972837687
2023-01-23 02:58:08.085920: step: 524/530, loss: 0.0005630493396893144
2023-01-23 02:58:09.237187: step: 528/530, loss: 0.02714099921286106
2023-01-23 02:58:10.434192: step: 532/530, loss: 0.007863807491958141
2023-01-23 02:58:11.592093: step: 536/530, loss: 0.000579833984375
2023-01-23 02:58:12.748358: step: 540/530, loss: 0.007014655973762274
2023-01-23 02:58:13.916281: step: 544/530, loss: 3.0517578125e-05
2023-01-23 02:58:15.097188: step: 548/530, loss: 0.014221764169633389
2023-01-23 02:58:16.237206: step: 552/530, loss: 0.002309560775756836
2023-01-23 02:58:17.465094: step: 556/530, loss: 0.0017877579666674137
2023-01-23 02:58:18.632899: step: 560/530, loss: 0.004434681031852961
2023-01-23 02:58:19.768298: step: 564/530, loss: 0.019142532721161842
2023-01-23 02:58:20.921348: step: 568/530, loss: -1.678466833254788e-05
2023-01-23 02:58:22.064820: step: 572/530, loss: 0.00014145375462248921
2023-01-23 02:58:23.198788: step: 576/530, loss: 0.0015735626220703125
2023-01-23 02:58:24.355967: step: 580/530, loss: 0.0017051697941496968
2023-01-23 02:58:25.526225: step: 584/530, loss: 0.0005186081398278475
2023-01-23 02:58:26.688539: step: 588/530, loss: 0.0030353544279932976
2023-01-23 02:58:27.842359: step: 592/530, loss: 9.450912330066785e-05
2023-01-23 02:58:29.007851: step: 596/530, loss: 0.006428718566894531
2023-01-23 02:58:30.151520: step: 600/530, loss: 0.0006405830499716103
2023-01-23 02:58:31.349323: step: 604/530, loss: 0.007863521575927734
2023-01-23 02:58:32.507728: step: 608/530, loss: 0.01780986785888672
2023-01-23 02:58:33.657866: step: 612/530, loss: 0.040480803698301315
2023-01-23 02:58:34.835101: step: 616/530, loss: 0.010878182016313076
2023-01-23 02:58:36.005366: step: 620/530, loss: 0.036622099578380585
2023-01-23 02:58:37.143209: step: 624/530, loss: 1.162734866142273
2023-01-23 02:58:38.302887: step: 628/530, loss: 0.00361289968714118
2023-01-23 02:58:39.434278: step: 632/530, loss: 0.00045795441837981343
2023-01-23 02:58:40.578064: step: 636/530, loss: 0.09098635613918304
2023-01-23 02:58:41.758369: step: 640/530, loss: 0.003033924149349332
2023-01-23 02:58:42.880228: step: 644/530, loss: 0.09502916038036346
2023-01-23 02:58:44.039898: step: 648/530, loss: 4.5490269258152694e-05
2023-01-23 02:58:45.188594: step: 652/530, loss: 0.009157276712357998
2023-01-23 02:58:46.341043: step: 656/530, loss: 0.007767105475068092
2023-01-23 02:58:47.466049: step: 660/530, loss: 0.0004553794860839844
2023-01-23 02:58:48.640588: step: 664/530, loss: 0.05796780437231064
2023-01-23 02:58:49.877789: step: 668/530, loss: 0.019757939502596855
2023-01-23 02:58:51.043337: step: 672/530, loss: 0.011412429623305798
2023-01-23 02:58:52.219852: step: 676/530, loss: 0.007752036675810814
2023-01-23 02:58:53.378437: step: 680/530, loss: 0.002031040145084262
2023-01-23 02:58:54.554315: step: 684/530, loss: 0.0005773544544354081
2023-01-23 02:58:55.773255: step: 688/530, loss: 0.007434464059770107
2023-01-23 02:58:56.912509: step: 692/530, loss: 0.0029165151063352823
2023-01-23 02:58:58.103401: step: 696/530, loss: 3.5691260563908145e-05
2023-01-23 02:58:59.303683: step: 700/530, loss: 0.0006225585821084678
2023-01-23 02:59:00.494794: step: 704/530, loss: 0.0008599281427450478
2023-01-23 02:59:01.655991: step: 708/530, loss: 0.14407701790332794
2023-01-23 02:59:02.829864: step: 712/530, loss: 0.000984287355095148
2023-01-23 02:59:04.007562: step: 716/530, loss: 0.015123367309570312
2023-01-23 02:59:05.181690: step: 720/530, loss: 0.05423898622393608
2023-01-23 02:59:06.336100: step: 724/530, loss: 5.7029727031476796e-05
2023-01-23 02:59:07.521285: step: 728/530, loss: 0.0016246795421466231
2023-01-23 02:59:08.703362: step: 732/530, loss: 0.0006534576532430947
2023-01-23 02:59:09.849636: step: 736/530, loss: 0.000548934971448034
2023-01-23 02:59:11.027027: step: 740/530, loss: 0.004404926206916571
2023-01-23 02:59:12.208134: step: 744/530, loss: 0.0017291069962084293
2023-01-23 02:59:13.397794: step: 748/530, loss: 0.007610893342643976
2023-01-23 02:59:14.545226: step: 752/530, loss: 0.003435039659962058
2023-01-23 02:59:15.715883: step: 756/530, loss: 0.014569473452866077
2023-01-23 02:59:16.915482: step: 760/530, loss: 0.020407389849424362
2023-01-23 02:59:18.129288: step: 764/530, loss: 0.03406648710370064
2023-01-23 02:59:19.291359: step: 768/530, loss: 0.4402596354484558
2023-01-23 02:59:20.461657: step: 772/530, loss: 0.005612373352050781
2023-01-23 02:59:21.679198: step: 776/530, loss: 0.0007963181124068797
2023-01-23 02:59:22.855197: step: 780/530, loss: 0.019199658185243607
2023-01-23 02:59:24.037121: step: 784/530, loss: 0.0001506805419921875
2023-01-23 02:59:25.201880: step: 788/530, loss: 0.0002320289786439389
2023-01-23 02:59:26.389803: step: 792/530, loss: 0.09661455452442169
2023-01-23 02:59:27.565551: step: 796/530, loss: 0.0020971298217773438
2023-01-23 02:59:28.706018: step: 800/530, loss: 0.007229995913803577
2023-01-23 02:59:29.874350: step: 804/530, loss: 0.003390503115952015
2023-01-23 02:59:31.033228: step: 808/530, loss: 0.022574711591005325
2023-01-23 02:59:32.210137: step: 812/530, loss: 0.03010106086730957
2023-01-23 02:59:33.366709: step: 816/530, loss: 0.03401822969317436
2023-01-23 02:59:34.510290: step: 820/530, loss: 0.09475937485694885
2023-01-23 02:59:35.693957: step: 824/530, loss: 0.0011989593040198088
2023-01-23 02:59:36.851993: step: 828/530, loss: 0.005826234817504883
2023-01-23 02:59:38.045936: step: 832/530, loss: 0.0003656387561932206
2023-01-23 02:59:39.239038: step: 836/530, loss: 0.003420066786929965
2023-01-23 02:59:40.423841: step: 840/530, loss: 0.00039882661076262593
2023-01-23 02:59:41.603592: step: 844/530, loss: 0.013754845596849918
2023-01-23 02:59:42.783519: step: 848/530, loss: 0.0014840603107586503
2023-01-23 02:59:43.967037: step: 852/530, loss: 0.02922821044921875
2023-01-23 02:59:45.105782: step: 856/530, loss: 0.0008815765613690019
2023-01-23 02:59:46.243863: step: 860/530, loss: 0.002232170198112726
2023-01-23 02:59:47.418864: step: 864/530, loss: 0.01718893088400364
2023-01-23 02:59:48.601174: step: 868/530, loss: 0.00629157992079854
2023-01-23 02:59:49.752598: step: 872/530, loss: 0.013038254342973232
2023-01-23 02:59:50.920441: step: 876/530, loss: 0.0005726814270019531
2023-01-23 02:59:52.096440: step: 880/530, loss: 0.007781696505844593
2023-01-23 02:59:53.278315: step: 884/530, loss: 0.013808107934892178
2023-01-23 02:59:54.419830: step: 888/530, loss: 0.023785972967743874
2023-01-23 02:59:55.592302: step: 892/530, loss: 0.030319882556796074
2023-01-23 02:59:56.774436: step: 896/530, loss: 0.02408876270055771
2023-01-23 02:59:57.945614: step: 900/530, loss: 0.018917370587587357
2023-01-23 02:59:59.083301: step: 904/530, loss: 0.005561495199799538
2023-01-23 03:00:00.281689: step: 908/530, loss: 0.05368461832404137
2023-01-23 03:00:01.453404: step: 912/530, loss: 0.0004751205269712955
2023-01-23 03:00:02.581699: step: 916/530, loss: 0.0015298842918127775
2023-01-23 03:00:03.715234: step: 920/530, loss: 0.0015491247177124023
2023-01-23 03:00:04.880757: step: 924/530, loss: 0.009456825442612171
2023-01-23 03:00:06.054462: step: 928/530, loss: 0.004016113001853228
2023-01-23 03:00:07.231906: step: 932/530, loss: 0.08811359852552414
2023-01-23 03:00:08.426560: step: 936/530, loss: 0.011536311358213425
2023-01-23 03:00:09.589856: step: 940/530, loss: 0.00014495849609375
2023-01-23 03:00:10.784205: step: 944/530, loss: 0.009525870904326439
2023-01-23 03:00:11.922480: step: 948/530, loss: 0.010910797864198685
2023-01-23 03:00:13.109351: step: 952/530, loss: 0.16003188490867615
2023-01-23 03:00:14.299587: step: 956/530, loss: 0.01636524312198162
2023-01-23 03:00:15.456428: step: 960/530, loss: 0.038251589983701706
2023-01-23 03:00:16.624820: step: 964/530, loss: 0.030727673321962357
2023-01-23 03:00:17.787070: step: 968/530, loss: 9.424686868442222e-05
2023-01-23 03:00:18.947819: step: 972/530, loss: 0.00821156520396471
2023-01-23 03:00:20.103661: step: 976/530, loss: 0.06272802501916885
2023-01-23 03:00:21.260261: step: 980/530, loss: 0.0019258500542491674
2023-01-23 03:00:22.447362: step: 984/530, loss: 0.0074707032181322575
2023-01-23 03:00:23.627373: step: 988/530, loss: 0.0007600784301757812
2023-01-23 03:00:24.764142: step: 992/530, loss: 0.002627205802127719
2023-01-23 03:00:25.884554: step: 996/530, loss: 0.0006809234619140625
2023-01-23 03:00:27.044972: step: 1000/530, loss: 0.05459868907928467
2023-01-23 03:00:28.235150: step: 1004/530, loss: 0.001634883927181363
2023-01-23 03:00:29.443509: step: 1008/530, loss: 0.004923057742416859
2023-01-23 03:00:30.593858: step: 1012/530, loss: 2.155303991457913e-05
2023-01-23 03:00:31.781393: step: 1016/530, loss: 0.00969161931425333
2023-01-23 03:00:32.982989: step: 1020/530, loss: 0.007298565004020929
2023-01-23 03:00:34.130649: step: 1024/530, loss: 0.03919525071978569
2023-01-23 03:00:35.309376: step: 1028/530, loss: 0.04719958454370499
2023-01-23 03:00:36.457083: step: 1032/530, loss: 0.018381500616669655
2023-01-23 03:00:37.607131: step: 1036/530, loss: 0.01364822406321764
2023-01-23 03:00:38.787797: step: 1040/530, loss: 0.001079988433048129
2023-01-23 03:00:40.013497: step: 1044/530, loss: 0.004852390382438898
2023-01-23 03:00:41.208626: step: 1048/530, loss: 0.0007318496936932206
2023-01-23 03:00:42.404929: step: 1052/530, loss: 0.0005678177112713456
2023-01-23 03:00:43.595210: step: 1056/530, loss: 0.03227615728974342
2023-01-23 03:00:44.756265: step: 1060/530, loss: 0.029921723529696465
2023-01-23 03:00:45.903094: step: 1064/530, loss: 0.008886338211596012
2023-01-23 03:00:47.027688: step: 1068/530, loss: 0.045716091990470886
2023-01-23 03:00:48.205869: step: 1072/530, loss: 0.00033826829167082906
2023-01-23 03:00:49.356104: step: 1076/530, loss: 0.0039396765641868114
2023-01-23 03:00:50.573191: step: 1080/530, loss: 4.043579247081652e-05
2023-01-23 03:00:51.753800: step: 1084/530, loss: 0.01632690615952015
2023-01-23 03:00:52.979750: step: 1088/530, loss: 0.006623649969696999
2023-01-23 03:00:54.163674: step: 1092/530, loss: 0.0041179656982421875
2023-01-23 03:00:55.327899: step: 1096/530, loss: 0.017409324645996094
2023-01-23 03:00:56.534840: step: 1100/530, loss: 0.0010496140457689762
2023-01-23 03:00:57.740514: step: 1104/530, loss: 0.0028597356285899878
2023-01-23 03:00:58.930163: step: 1108/530, loss: 0.0005098819965496659
2023-01-23 03:01:00.135746: step: 1112/530, loss: 0.08675575256347656
2023-01-23 03:01:01.311946: step: 1116/530, loss: 0.08679638057947159
2023-01-23 03:01:02.488697: step: 1120/530, loss: 0.006492996588349342
2023-01-23 03:01:03.647370: step: 1124/530, loss: 0.040943436324596405
2023-01-23 03:01:04.798668: step: 1128/530, loss: 0.0032581686973571777
2023-01-23 03:01:05.967403: step: 1132/530, loss: 0.0015054702525958419
2023-01-23 03:01:07.145500: step: 1136/530, loss: 0.00575304077938199
2023-01-23 03:01:08.290531: step: 1140/530, loss: 0.030535221099853516
2023-01-23 03:01:09.434562: step: 1144/530, loss: 0.0016894340515136719
2023-01-23 03:01:10.598927: step: 1148/530, loss: 0.0001939773646881804
2023-01-23 03:01:11.815122: step: 1152/530, loss: 0.0030698776245117188
2023-01-23 03:01:13.002567: step: 1156/530, loss: 0.00989003200083971
2023-01-23 03:01:14.182357: step: 1160/530, loss: 0.00016164779663085938
2023-01-23 03:01:15.348773: step: 1164/530, loss: 0.010471916757524014
2023-01-23 03:01:16.505910: step: 1168/530, loss: 0.0011441231472417712
2023-01-23 03:01:17.718069: step: 1172/530, loss: 0.028838159516453743
2023-01-23 03:01:18.932418: step: 1176/530, loss: 0.009549331851303577
2023-01-23 03:01:20.094840: step: 1180/530, loss: 0.00010185241990257055
2023-01-23 03:01:21.286378: step: 1184/530, loss: 0.047628212720155716
2023-01-23 03:01:22.433022: step: 1188/530, loss: 0.00048055651132017374
2023-01-23 03:01:23.624854: step: 1192/530, loss: 4.6157834731275216e-05
2023-01-23 03:01:24.772391: step: 1196/530, loss: 0.046483419835567474
2023-01-23 03:01:25.949427: step: 1200/530, loss: 0.030712412670254707
2023-01-23 03:01:27.124665: step: 1204/530, loss: 0.01286230143159628
2023-01-23 03:01:28.283965: step: 1208/530, loss: 0.02996654435992241
2023-01-23 03:01:29.453306: step: 1212/530, loss: 0.0013994218315929174
2023-01-23 03:01:30.652361: step: 1216/530, loss: 2.5177003408316523e-05
2023-01-23 03:01:31.802638: step: 1220/530, loss: 0.0007638931274414062
2023-01-23 03:01:33.015615: step: 1224/530, loss: 0.03564567491412163
2023-01-23 03:01:34.188967: step: 1228/530, loss: 0.0005281448247842491
2023-01-23 03:01:35.354188: step: 1232/530, loss: 0.03731689602136612
2023-01-23 03:01:36.525164: step: 1236/530, loss: 0.005178642459213734
2023-01-23 03:01:37.671543: step: 1240/530, loss: 0.07758168876171112
2023-01-23 03:01:38.852607: step: 1244/530, loss: 0.07812522351741791
2023-01-23 03:01:40.019398: step: 1248/530, loss: 0.017845438793301582
2023-01-23 03:01:41.201720: step: 1252/530, loss: 0.01222839392721653
2023-01-23 03:01:42.449825: step: 1256/530, loss: 5.974803447723389
2023-01-23 03:01:43.589160: step: 1260/530, loss: 3.5953522456111386e-05
2023-01-23 03:01:44.807910: step: 1264/530, loss: 0.0014590263599529862
2023-01-23 03:01:46.015533: step: 1268/530, loss: 0.003410005709156394
2023-01-23 03:01:47.201190: step: 1272/530, loss: 0.008798694238066673
2023-01-23 03:01:48.359987: step: 1276/530, loss: 0.0023822784423828125
2023-01-23 03:01:49.528396: step: 1280/530, loss: 0.0023009299766272306
2023-01-23 03:01:50.695032: step: 1284/530, loss: 0.0002038955717580393
2023-01-23 03:01:51.842911: step: 1288/530, loss: 0.061708737164735794
2023-01-23 03:01:53.071972: step: 1292/530, loss: 5.617141869151965e-05
2023-01-23 03:01:54.242471: step: 1296/530, loss: 4.7016143071232364e-05
2023-01-23 03:01:55.385115: step: 1300/530, loss: 0.0015858174301683903
2023-01-23 03:01:56.534168: step: 1304/530, loss: 0.027640486136078835
2023-01-23 03:01:57.706735: step: 1308/530, loss: 0.002192878630012274
2023-01-23 03:01:58.851315: step: 1312/530, loss: 0.006818199064582586
2023-01-23 03:02:00.039161: step: 1316/530, loss: 0.05095253139734268
2023-01-23 03:02:01.173295: step: 1320/530, loss: 9.918212890625e-05
2023-01-23 03:02:02.378709: step: 1324/530, loss: 0.005904293153434992
2023-01-23 03:02:03.528737: step: 1328/530, loss: 0.009035158902406693
2023-01-23 03:02:04.721532: step: 1332/530, loss: 0.06499442458152771
2023-01-23 03:02:05.919343: step: 1336/530, loss: 0.00032792091951705515
2023-01-23 03:02:07.143274: step: 1340/530, loss: 0.0007309913635253906
2023-01-23 03:02:08.278729: step: 1344/530, loss: 0.00011429786536609754
2023-01-23 03:02:09.420425: step: 1348/530, loss: 8.687973604537547e-05
2023-01-23 03:02:10.602527: step: 1352/530, loss: 0.0002700805780477822
2023-01-23 03:02:11.857416: step: 1356/530, loss: 0.005312728695571423
2023-01-23 03:02:12.993602: step: 1360/530, loss: 0.0005973816150799394
2023-01-23 03:02:14.146529: step: 1364/530, loss: 0.002830123994499445
2023-01-23 03:02:15.301048: step: 1368/530, loss: 0.03579740598797798
2023-01-23 03:02:16.423848: step: 1372/530, loss: 0.008071518503129482
2023-01-23 03:02:17.604997: step: 1376/530, loss: 0.029038619250059128
2023-01-23 03:02:18.792738: step: 1380/530, loss: 0.00737762451171875
2023-01-23 03:02:19.975349: step: 1384/530, loss: 0.0005518912803381681
2023-01-23 03:02:21.209548: step: 1388/530, loss: 0.052643775939941406
2023-01-23 03:02:22.422437: step: 1392/530, loss: 0.018905067816376686
2023-01-23 03:02:23.596315: step: 1396/530, loss: 0.009289824403822422
2023-01-23 03:02:24.762727: step: 1400/530, loss: 0.14495983719825745
2023-01-23 03:02:25.962358: step: 1404/530, loss: 0.004733848851174116
2023-01-23 03:02:27.130305: step: 1408/530, loss: 0.0007394790882244706
2023-01-23 03:02:28.321894: step: 1412/530, loss: 0.013779259286820889
2023-01-23 03:02:29.473060: step: 1416/530, loss: 0.003085231641307473
2023-01-23 03:02:30.650844: step: 1420/530, loss: 0.025857020169496536
2023-01-23 03:02:31.847309: step: 1424/530, loss: 0.00035037993802689016
2023-01-23 03:02:33.018293: step: 1428/530, loss: 0.00039310456486418843
2023-01-23 03:02:34.192126: step: 1432/530, loss: 0.013794517144560814
2023-01-23 03:02:35.335470: step: 1436/530, loss: 0.0002681732294149697
2023-01-23 03:02:36.494082: step: 1440/530, loss: 0.0009615898597985506
2023-01-23 03:02:37.686541: step: 1444/530, loss: 0.014445829205214977
2023-01-23 03:02:38.831173: step: 1448/530, loss: 0.00698509206995368
2023-01-23 03:02:40.008376: step: 1452/530, loss: 0.0188203826546669
2023-01-23 03:02:41.204115: step: 1456/530, loss: 0.0033960342407226562
2023-01-23 03:02:42.364741: step: 1460/530, loss: 0.0044970037415623665
2023-01-23 03:02:43.499997: step: 1464/530, loss: 0.05821037292480469
2023-01-23 03:02:44.637137: step: 1468/530, loss: 0.02616710588335991
2023-01-23 03:02:45.815599: step: 1472/530, loss: 0.0002674102724995464
2023-01-23 03:02:46.983829: step: 1476/530, loss: 0.020495224744081497
2023-01-23 03:02:48.229020: step: 1480/530, loss: 0.08616162091493607
2023-01-23 03:02:49.409831: step: 1484/530, loss: 0.06972980499267578
2023-01-23 03:02:50.571977: step: 1488/530, loss: 0.0006031036609783769
2023-01-23 03:02:51.786734: step: 1492/530, loss: 1.9359587895451114e-05
2023-01-23 03:02:52.977923: step: 1496/530, loss: 0.0029044151306152344
2023-01-23 03:02:54.152379: step: 1500/530, loss: 0.007088374812155962
2023-01-23 03:02:55.302880: step: 1504/530, loss: 0.01528091449290514
2023-01-23 03:02:56.461538: step: 1508/530, loss: 0.0008367538684979081
2023-01-23 03:02:57.620025: step: 1512/530, loss: 0.003276729490607977
2023-01-23 03:02:58.804021: step: 1516/530, loss: 0.01809234544634819
2023-01-23 03:03:00.007216: step: 1520/530, loss: 0.0004050254647154361
2023-01-23 03:03:01.139465: step: 1524/530, loss: 0.003694248152896762
2023-01-23 03:03:02.274433: step: 1528/530, loss: 0.004168796353042126
2023-01-23 03:03:03.463345: step: 1532/530, loss: 0.0005702972412109375
2023-01-23 03:03:04.607064: step: 1536/530, loss: 0.00012292861356399953
2023-01-23 03:03:05.782276: step: 1540/530, loss: 0.10180526226758957
2023-01-23 03:03:06.906011: step: 1544/530, loss: 0.01912846788764
2023-01-23 03:03:08.045228: step: 1548/530, loss: 0.0002604961337056011
2023-01-23 03:03:09.208591: step: 1552/530, loss: 0.01832704432308674
2023-01-23 03:03:10.381174: step: 1556/530, loss: 0.2695252001285553
2023-01-23 03:03:11.543900: step: 1560/530, loss: 0.004031944088637829
2023-01-23 03:03:12.712303: step: 1564/530, loss: 0.0027374266646802425
2023-01-23 03:03:13.934044: step: 1568/530, loss: 0.0073188780806958675
2023-01-23 03:03:15.088205: step: 1572/530, loss: 0.0001731872616801411
2023-01-23 03:03:16.239269: step: 1576/530, loss: 0.04115085303783417
2023-01-23 03:03:17.428548: step: 1580/530, loss: 0.0012755156494677067
2023-01-23 03:03:18.608044: step: 1584/530, loss: 0.0008054733625613153
2023-01-23 03:03:19.796278: step: 1588/530, loss: 0.04562988504767418
2023-01-23 03:03:20.964350: step: 1592/530, loss: 0.00011024474952137098
2023-01-23 03:03:22.125711: step: 1596/530, loss: 0.0761910229921341
2023-01-23 03:03:23.276387: step: 1600/530, loss: 0.014288950711488724
2023-01-23 03:03:24.421122: step: 1604/530, loss: 0.038820937275886536
2023-01-23 03:03:25.606422: step: 1608/530, loss: 0.002949589630588889
2023-01-23 03:03:26.800980: step: 1612/530, loss: 0.0019914626609534025
2023-01-23 03:03:27.962953: step: 1616/530, loss: 0.029420530423521996
2023-01-23 03:03:29.193178: step: 1620/530, loss: 0.03519554063677788
2023-01-23 03:03:30.360051: step: 1624/530, loss: 0.008805847726762295
2023-01-23 03:03:31.524960: step: 1628/530, loss: 0.010153960436582565
2023-01-23 03:03:32.712276: step: 1632/530, loss: 0.039067938923835754
2023-01-23 03:03:33.873606: step: 1636/530, loss: 0.06935997307300568
2023-01-23 03:03:35.060886: step: 1640/530, loss: 0.007793044671416283
2023-01-23 03:03:36.226607: step: 1644/530, loss: 0.018748190253973007
2023-01-23 03:03:37.413744: step: 1648/530, loss: 0.0021436691749840975
2023-01-23 03:03:38.588115: step: 1652/530, loss: 0.010505914688110352
2023-01-23 03:03:39.735696: step: 1656/530, loss: 0.021545004099607468
2023-01-23 03:03:40.927935: step: 1660/530, loss: 0.0010385513305664062
2023-01-23 03:03:42.132602: step: 1664/530, loss: 0.005652427673339844
2023-01-23 03:03:43.309129: step: 1668/530, loss: 0.00029277801513671875
2023-01-23 03:03:44.477908: step: 1672/530, loss: 0.001043129013851285
2023-01-23 03:03:45.650597: step: 1676/530, loss: 0.028532786294817924
2023-01-23 03:03:46.849994: step: 1680/530, loss: 0.10484028607606888
2023-01-23 03:03:48.023339: step: 1684/530, loss: 0.016578197479248047
2023-01-23 03:03:49.193391: step: 1688/530, loss: 0.0016023635398596525
2023-01-23 03:03:50.364893: step: 1692/530, loss: 0.01886424981057644
2023-01-23 03:03:51.568257: step: 1696/530, loss: 0.06792030483484268
2023-01-23 03:03:52.749929: step: 1700/530, loss: 0.0007139205699786544
2023-01-23 03:03:53.938835: step: 1704/530, loss: 0.00135040283203125
2023-01-23 03:03:55.130965: step: 1708/530, loss: 0.02439441718161106
2023-01-23 03:03:56.336059: step: 1712/530, loss: 0.007346153259277344
2023-01-23 03:03:57.480908: step: 1716/530, loss: 0.023163223639130592
2023-01-23 03:03:58.659654: step: 1720/530, loss: 0.03194904327392578
2023-01-23 03:03:59.872546: step: 1724/530, loss: 0.025572776794433594
2023-01-23 03:04:01.040446: step: 1728/530, loss: 0.0333222895860672
2023-01-23 03:04:02.154017: step: 1732/530, loss: 0.004378700163215399
2023-01-23 03:04:03.345485: step: 1736/530, loss: 0.03282938152551651
2023-01-23 03:04:04.545000: step: 1740/530, loss: 0.00011339188495185226
2023-01-23 03:04:05.719951: step: 1744/530, loss: 0.003886604215949774
2023-01-23 03:04:06.849550: step: 1748/530, loss: 0.000819349312223494
2023-01-23 03:04:08.046859: step: 1752/530, loss: 0.029551029205322266
2023-01-23 03:04:09.170813: step: 1756/530, loss: 1.1420250302762724e-05
2023-01-23 03:04:10.335519: step: 1760/530, loss: 0.01574401929974556
2023-01-23 03:04:11.483307: step: 1764/530, loss: 0.007483029738068581
2023-01-23 03:04:12.600613: step: 1768/530, loss: 0.0001947402924997732
2023-01-23 03:04:13.760032: step: 1772/530, loss: 0.02593708038330078
2023-01-23 03:04:15.010935: step: 1776/530, loss: 0.00200996408239007
2023-01-23 03:04:16.189189: step: 1780/530, loss: 0.006249618716537952
2023-01-23 03:04:17.365305: step: 1784/530, loss: 0.0024644851218909025
2023-01-23 03:04:18.529358: step: 1788/530, loss: 0.0032048227731138468
2023-01-23 03:04:19.684874: step: 1792/530, loss: 3.80516066798009e-05
2023-01-23 03:04:20.871464: step: 1796/530, loss: 0.043852902948856354
2023-01-23 03:04:22.085627: step: 1800/530, loss: 0.00013151168241165578
2023-01-23 03:04:23.289067: step: 1804/530, loss: 0.016939258202910423
2023-01-23 03:04:24.441899: step: 1808/530, loss: 0.00015897752018645406
2023-01-23 03:04:25.585321: step: 1812/530, loss: 0.0039543150924146175
2023-01-23 03:04:26.838621: step: 1816/530, loss: 0.41771575808525085
2023-01-23 03:04:28.059391: step: 1820/530, loss: 0.0004191398620605469
2023-01-23 03:04:29.317761: step: 1824/530, loss: 0.2355606108903885
2023-01-23 03:04:30.488337: step: 1828/530, loss: 0.23792299628257751
2023-01-23 03:04:31.666953: step: 1832/530, loss: 0.035604145377874374
2023-01-23 03:04:32.805754: step: 1836/530, loss: 0.0004975319025106728
2023-01-23 03:04:33.964582: step: 1840/530, loss: 0.010256576351821423
2023-01-23 03:04:35.166241: step: 1844/530, loss: 0.0014173508388921618
2023-01-23 03:04:36.314048: step: 1848/530, loss: 0.034442998468875885
2023-01-23 03:04:37.471129: step: 1852/530, loss: 0.005626392550766468
2023-01-23 03:04:38.637717: step: 1856/530, loss: 0.01870574988424778
2023-01-23 03:04:39.814995: step: 1860/530, loss: 0.0005195618141442537
2023-01-23 03:04:40.967244: step: 1864/530, loss: 0.032444193959236145
2023-01-23 03:04:42.154520: step: 1868/530, loss: 0.0003391265927348286
2023-01-23 03:04:43.342156: step: 1872/530, loss: 0.01906614378094673
2023-01-23 03:04:44.611537: step: 1876/530, loss: 0.0019253729842603207
2023-01-23 03:04:45.763312: step: 1880/530, loss: 0.015119553543627262
2023-01-23 03:04:46.958479: step: 1884/530, loss: 0.0006293296464718878
2023-01-23 03:04:48.129017: step: 1888/530, loss: 0.009006357751786709
2023-01-23 03:04:49.329102: step: 1892/530, loss: 0.0011419296497479081
2023-01-23 03:04:50.515333: step: 1896/530, loss: 0.00022153854661155492
2023-01-23 03:04:51.717589: step: 1900/530, loss: 0.0037729262840002775
2023-01-23 03:04:52.845479: step: 1904/530, loss: 0.007874870672821999
2023-01-23 03:04:53.988836: step: 1908/530, loss: 0.0003532409609761089
2023-01-23 03:04:55.175787: step: 1912/530, loss: 0.0029369352851063013
2023-01-23 03:04:56.353936: step: 1916/530, loss: 2.136230432370212e-05
2023-01-23 03:04:57.515248: step: 1920/530, loss: 0.03233680501580238
2023-01-23 03:04:58.691194: step: 1924/530, loss: 0.007155799772590399
2023-01-23 03:04:59.831566: step: 1928/530, loss: 0.004911637399345636
2023-01-23 03:05:01.006447: step: 1932/530, loss: 8.449554297840223e-05
2023-01-23 03:05:02.181876: step: 1936/530, loss: 0.03290577232837677
2023-01-23 03:05:03.329317: step: 1940/530, loss: 0.006567764095962048
2023-01-23 03:05:04.508051: step: 1944/530, loss: 0.12615303695201874
2023-01-23 03:05:05.681925: step: 1948/530, loss: 0.0009716987842693925
2023-01-23 03:05:06.868668: step: 1952/530, loss: 0.0007730245124548674
2023-01-23 03:05:08.044528: step: 1956/530, loss: 0.0009432792430743575
2023-01-23 03:05:09.238541: step: 1960/530, loss: 0.00143260951153934
2023-01-23 03:05:10.404216: step: 1964/530, loss: 0.16355854272842407
2023-01-23 03:05:11.578162: step: 1968/530, loss: 0.0006039619911462069
2023-01-23 03:05:12.762181: step: 1972/530, loss: 0.04809780418872833
2023-01-23 03:05:13.906615: step: 1976/530, loss: 0.012504005804657936
2023-01-23 03:05:15.044329: step: 1980/530, loss: 0.2107163369655609
2023-01-23 03:05:16.256881: step: 1984/530, loss: 0.0021579742897301912
2023-01-23 03:05:17.459854: step: 1988/530, loss: 0.0004529953293967992
2023-01-23 03:05:18.599629: step: 1992/530, loss: 0.025238037109375
2023-01-23 03:05:19.810328: step: 1996/530, loss: 9.613037400413305e-05
2023-01-23 03:05:20.970908: step: 2000/530, loss: 0.01381530798971653
2023-01-23 03:05:22.138408: step: 2004/530, loss: 0.0007887363317422569
2023-01-23 03:05:23.308855: step: 2008/530, loss: 0.001117706298828125
2023-01-23 03:05:24.509695: step: 2012/530, loss: 0.007008457090705633
2023-01-23 03:05:25.627773: step: 2016/530, loss: 8.859634544933215e-05
2023-01-23 03:05:26.788583: step: 2020/530, loss: 0.006595611572265625
2023-01-23 03:05:27.944374: step: 2024/530, loss: 0.08102016896009445
2023-01-23 03:05:29.130610: step: 2028/530, loss: 0.0006907939678058028
2023-01-23 03:05:30.327838: step: 2032/530, loss: 0.11535453796386719
2023-01-23 03:05:31.478839: step: 2036/530, loss: 0.03095979616045952
2023-01-23 03:05:32.626701: step: 2040/530, loss: 0.0002171516534872353
2023-01-23 03:05:33.789774: step: 2044/530, loss: 0.0011821746593341231
2023-01-23 03:05:34.935206: step: 2048/530, loss: 0.008242607116699219
2023-01-23 03:05:36.092466: step: 2052/530, loss: 0.031734466552734375
2023-01-23 03:05:37.264636: step: 2056/530, loss: 0.003280591918155551
2023-01-23 03:05:38.405859: step: 2060/530, loss: 1.7023086911649443e-05
2023-01-23 03:05:39.589147: step: 2064/530, loss: 0.015797805041074753
2023-01-23 03:05:40.764134: step: 2068/530, loss: 0.0018525600899010897
2023-01-23 03:05:41.924413: step: 2072/530, loss: 0.0034498213790357113
2023-01-23 03:05:43.119124: step: 2076/530, loss: 0.16373948752880096
2023-01-23 03:05:44.290545: step: 2080/530, loss: 5.7697296142578125e-05
2023-01-23 03:05:45.498902: step: 2084/530, loss: 0.029844429343938828
2023-01-23 03:05:46.733690: step: 2088/530, loss: 0.010340690612792969
2023-01-23 03:05:47.963989: step: 2092/530, loss: 0.051587868481874466
2023-01-23 03:05:49.133401: step: 2096/530, loss: 0.005192280281335115
2023-01-23 03:05:50.288934: step: 2100/530, loss: 0.008917141705751419
2023-01-23 03:05:51.486557: step: 2104/530, loss: 0.004713344853371382
2023-01-23 03:05:52.676357: step: 2108/530, loss: 0.0028250697068870068
2023-01-23 03:05:53.861518: step: 2112/530, loss: 0.015909289941191673
2023-01-23 03:05:55.045115: step: 2116/530, loss: 0.004019832704216242
2023-01-23 03:05:56.181811: step: 2120/530, loss: 0.00087909703142941
==================================================
Loss: 0.033
--------------------
Dev: {'event': {'p': 0.6065057712486883, 'r': 0.7696404793608522, 'f1': 0.6784037558685445}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
Test: {'event': {'p': 0.6643026004728132, 'r': 0.8079355951696378, 'f1': 0.7291126102750389}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
Chinese: {'event': {'p': 0.6024096385542169, 'r': 0.9259259259259259, 'f1': 0.7299270072992702}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
Korean: {'event': {'p': 0.5, 'r': 0.42857142857142855, 'f1': 0.4615384615384615}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
Russian: {'event': {'p': 0.4489795918367347, 'r': 0.6111111111111112, 'f1': 0.5176470588235293}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
New best chinese model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6065057712486883, 'r': 0.7696404793608522, 'f1': 0.6784037558685445}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
Eng Test for Chinese: {'event': {'p': 0.6643026004728132, 'r': 0.8079355951696378, 'f1': 0.7291126102750389}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
Sample Chinese: {'event': {'p': 0.6024096385542169, 'r': 0.9259259259259259, 'f1': 0.7299270072992702}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5733990147783251, 'r': 0.7749667110519307, 'f1': 0.6591166477916196}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Eng Test for Korean: {'event': {'p': 0.6218005295675199, 'r': 0.8102357676825762, 'f1': 0.7036204744069912}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Sample Korean: {'event': {'p': 0.6417910447761194, 'r': 0.6825396825396826, 'f1': 0.6615384615384614}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5951882845188284, 'r': 0.7576564580559254, 'f1': 0.6666666666666666}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6663405088062623, 'r': 0.7832087406555491, 'f1': 0.7200634417129264}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5, 'r': 0.6666666666666666, 'f1': 0.5714285714285715}, '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 03:06:44.725032: step: 4/530, loss: 0.0009859561687335372
2023-01-23 03:06:45.897583: step: 8/530, loss: 0.0004611969052348286
2023-01-23 03:06:47.053679: step: 12/530, loss: 0.005803633015602827
2023-01-23 03:06:48.237359: step: 16/530, loss: 0.0024608613457530737
2023-01-23 03:06:49.398105: step: 20/530, loss: 0.00018253325833939016
2023-01-23 03:06:50.540365: step: 24/530, loss: 0.00025453566922806203
2023-01-23 03:06:51.695669: step: 28/530, loss: 0.00448951730504632
2023-01-23 03:06:52.868770: step: 32/530, loss: 0.020351599901914597
2023-01-23 03:06:54.037073: step: 36/530, loss: 0.0007308960193768144
2023-01-23 03:06:55.227286: step: 40/530, loss: 0.030013561248779297
2023-01-23 03:06:56.396595: step: 44/530, loss: 0.010929679498076439
2023-01-23 03:06:57.533645: step: 48/530, loss: 0.057430051267147064
2023-01-23 03:06:58.718621: step: 52/530, loss: 0.009071302600204945
2023-01-23 03:06:59.925855: step: 56/530, loss: 0.12401314079761505
2023-01-23 03:07:01.106734: step: 60/530, loss: 0.0057014464400708675
2023-01-23 03:07:02.244105: step: 64/530, loss: 0.00044317246647551656
2023-01-23 03:07:03.428399: step: 68/530, loss: 0.0001362323819193989
2023-01-23 03:07:04.621520: step: 72/530, loss: 0.005087662022560835
2023-01-23 03:07:05.796769: step: 76/530, loss: 0.000615882920101285
2023-01-23 03:07:06.933564: step: 80/530, loss: 0.0031612396705895662
2023-01-23 03:07:08.098409: step: 84/530, loss: 0.0023467063438147306
2023-01-23 03:07:09.255524: step: 88/530, loss: 0.002280712127685547
2023-01-23 03:07:10.437344: step: 92/530, loss: 0.011156369000673294
2023-01-23 03:07:11.601649: step: 96/530, loss: 0.0005113601800985634
2023-01-23 03:07:12.760323: step: 100/530, loss: 0.0493042953312397
2023-01-23 03:07:13.949979: step: 104/530, loss: 0.02254772186279297
2023-01-23 03:07:15.175464: step: 108/530, loss: 0.04014463350176811
2023-01-23 03:07:16.383495: step: 112/530, loss: 0.006560993380844593
2023-01-23 03:07:17.525524: step: 116/530, loss: 0.023336125537753105
2023-01-23 03:07:18.691069: step: 120/530, loss: 0.0033494948875159025
2023-01-23 03:07:19.876822: step: 124/530, loss: 0.014647483825683594
2023-01-23 03:07:21.047328: step: 128/530, loss: 0.0006462097517214715
2023-01-23 03:07:22.203179: step: 132/530, loss: 0.00549087580293417
2023-01-23 03:07:23.428784: step: 136/530, loss: 0.003354978747665882
2023-01-23 03:07:24.613525: step: 140/530, loss: 0.0038183212745934725
2023-01-23 03:07:25.765713: step: 144/530, loss: 0.014656543731689453
2023-01-23 03:07:26.930898: step: 148/530, loss: 0.03089284896850586
2023-01-23 03:07:28.090728: step: 152/530, loss: 0.00040435791015625
2023-01-23 03:07:29.319550: step: 156/530, loss: 0.05603504553437233
2023-01-23 03:07:30.513047: step: 160/530, loss: 0.002738380338996649
2023-01-23 03:07:31.673117: step: 164/530, loss: 0.008289813995361328
2023-01-23 03:07:32.871725: step: 168/530, loss: 0.02258281782269478
2023-01-23 03:07:34.055015: step: 172/530, loss: 0.01887073554098606
2023-01-23 03:07:35.177749: step: 176/530, loss: 0.0010669901967048645
2023-01-23 03:07:36.305365: step: 180/530, loss: 4.8923491704044864e-05
2023-01-23 03:07:37.496825: step: 184/530, loss: 0.00024056434631347656
2023-01-23 03:07:38.661667: step: 188/530, loss: 0.0003066062927246094
2023-01-23 03:07:39.820431: step: 192/530, loss: 0.00014791489229537547
2023-01-23 03:07:40.999450: step: 196/530, loss: 0.00019302369037177414
2023-01-23 03:07:42.181362: step: 200/530, loss: 0.03316116705536842
2023-01-23 03:07:43.361339: step: 204/530, loss: 0.0014345645904541016
2023-01-23 03:07:44.538997: step: 208/530, loss: 0.024320602416992188
2023-01-23 03:07:45.702956: step: 212/530, loss: 0.5507655739784241
2023-01-23 03:07:46.887985: step: 216/530, loss: 0.01583881489932537
2023-01-23 03:07:48.096761: step: 220/530, loss: 0.001750183175317943
2023-01-23 03:07:49.276760: step: 224/530, loss: 0.027118206024169922
2023-01-23 03:07:50.438157: step: 228/530, loss: 0.0023624422028660774
2023-01-23 03:07:51.667465: step: 232/530, loss: 0.0038647176697850227
2023-01-23 03:07:52.814966: step: 236/530, loss: 0.006709098815917969
2023-01-23 03:07:53.985745: step: 240/530, loss: 0.0038623097352683544
2023-01-23 03:07:55.181398: step: 244/530, loss: 0.011791229248046875
2023-01-23 03:07:56.339099: step: 248/530, loss: 0.002817440079525113
2023-01-23 03:07:57.503934: step: 252/530, loss: 0.024173451587557793
2023-01-23 03:07:58.704675: step: 256/530, loss: 0.5827440619468689
2023-01-23 03:07:59.874202: step: 260/530, loss: 0.005282783415168524
2023-01-23 03:08:01.068350: step: 264/530, loss: 0.003753280732780695
2023-01-23 03:08:02.222760: step: 268/530, loss: 0.003345489501953125
2023-01-23 03:08:03.419457: step: 272/530, loss: 0.010146046057343483
2023-01-23 03:08:04.597201: step: 276/530, loss: 0.0002209663507528603
2023-01-23 03:08:05.769753: step: 280/530, loss: 0.04923315346240997
2023-01-23 03:08:06.914248: step: 284/530, loss: 0.01746654510498047
2023-01-23 03:08:08.102248: step: 288/530, loss: 6.160735938465223e-05
2023-01-23 03:08:09.288666: step: 292/530, loss: 0.026699448004364967
2023-01-23 03:08:10.467668: step: 296/530, loss: 0.17639006674289703
2023-01-23 03:08:11.679073: step: 300/530, loss: 0.07514934241771698
2023-01-23 03:08:12.879935: step: 304/530, loss: 0.003847312880679965
2023-01-23 03:08:14.111237: step: 308/530, loss: 0.08900833129882812
2023-01-23 03:08:15.274917: step: 312/530, loss: 0.021594716235995293
2023-01-23 03:08:16.427018: step: 316/530, loss: 0.013129020109772682
2023-01-23 03:08:17.589291: step: 320/530, loss: 0.031817153096199036
2023-01-23 03:08:18.756443: step: 324/530, loss: 9.72747784544481e-06
2023-01-23 03:08:19.913486: step: 328/530, loss: 0.003936099819839001
2023-01-23 03:08:21.122019: step: 332/530, loss: 0.004711913876235485
2023-01-23 03:08:22.263377: step: 336/530, loss: 0.00019912720017600805
2023-01-23 03:08:23.418777: step: 340/530, loss: 0.012041473761200905
2023-01-23 03:08:24.606578: step: 344/530, loss: 0.2827800512313843
2023-01-23 03:08:25.760452: step: 348/530, loss: 0.026802493259310722
2023-01-23 03:08:26.898754: step: 352/530, loss: 0.0007115363841876388
2023-01-23 03:08:28.066321: step: 356/530, loss: 0.006585312075912952
2023-01-23 03:08:29.272975: step: 360/530, loss: 0.07212667912244797
2023-01-23 03:08:30.498411: step: 364/530, loss: 0.007594108581542969
2023-01-23 03:08:31.681099: step: 368/530, loss: 0.006410980597138405
2023-01-23 03:08:32.862104: step: 372/530, loss: 0.008087086491286755
2023-01-23 03:08:34.045240: step: 376/530, loss: 0.028519250452518463
2023-01-23 03:08:35.226429: step: 380/530, loss: 0.028273582458496094
2023-01-23 03:08:36.412824: step: 384/530, loss: 0.011097913607954979
2023-01-23 03:08:37.577251: step: 388/530, loss: 0.0006882667657919228
2023-01-23 03:08:38.738513: step: 392/530, loss: 0.006953144446015358
2023-01-23 03:08:39.900506: step: 396/530, loss: 0.0012041091686114669
2023-01-23 03:08:41.068742: step: 400/530, loss: 6.66618361719884e-05
2023-01-23 03:08:42.234544: step: 404/530, loss: 5.073547799838707e-05
2023-01-23 03:08:43.350079: step: 408/530, loss: 0.0004280090215615928
2023-01-23 03:08:44.486197: step: 412/530, loss: 2.0265579223632812e-05
2023-01-23 03:08:45.665793: step: 416/530, loss: 0.022930337116122246
2023-01-23 03:08:46.811540: step: 420/530, loss: 0.006448840722441673
2023-01-23 03:08:47.976824: step: 424/530, loss: 0.035825636237859726
2023-01-23 03:08:49.125345: step: 428/530, loss: 3.6239625842426904e-06
2023-01-23 03:08:50.267449: step: 432/530, loss: 0.0040260315872728825
2023-01-23 03:08:51.449803: step: 436/530, loss: 0.0009148597600869834
2023-01-23 03:08:52.625467: step: 440/530, loss: 0.0013803958427160978
2023-01-23 03:08:53.823420: step: 444/530, loss: 0.0010945319663733244
2023-01-23 03:08:54.958733: step: 448/530, loss: 0.08560142666101456
2023-01-23 03:08:56.145002: step: 452/530, loss: 0.00021238328190520406
2023-01-23 03:08:57.364783: step: 456/530, loss: 0.0009457588312216103
2023-01-23 03:08:58.528525: step: 460/530, loss: 7.472038851119578e-05
2023-01-23 03:08:59.716871: step: 464/530, loss: 0.04912886768579483
2023-01-23 03:09:00.877763: step: 468/530, loss: 0.08537034690380096
2023-01-23 03:09:02.038551: step: 472/530, loss: 0.00047364234342239797
2023-01-23 03:09:03.195004: step: 476/530, loss: 0.0024349212180823088
2023-01-23 03:09:04.353517: step: 480/530, loss: 0.0003097534354310483
2023-01-23 03:09:05.540591: step: 484/530, loss: 0.03272075951099396
2023-01-23 03:09:06.719838: step: 488/530, loss: 0.0009326458093710244
2023-01-23 03:09:07.893483: step: 492/530, loss: 0.0007757187122479081
2023-01-23 03:09:09.064085: step: 496/530, loss: 0.04452495649456978
2023-01-23 03:09:10.228088: step: 500/530, loss: 0.004549121949821711
2023-01-23 03:09:11.383424: step: 504/530, loss: 0.008488083258271217
2023-01-23 03:09:12.528625: step: 508/530, loss: 0.08782634139060974
2023-01-23 03:09:13.686478: step: 512/530, loss: 0.009482193738222122
2023-01-23 03:09:14.828585: step: 516/530, loss: 0.0004820823669433594
2023-01-23 03:09:16.025639: step: 520/530, loss: 0.0007883548969402909
2023-01-23 03:09:17.156792: step: 524/530, loss: 0.007688951212912798
2023-01-23 03:09:18.389491: step: 528/530, loss: 0.028808021917939186
2023-01-23 03:09:19.515569: step: 532/530, loss: 0.00036077501135878265
2023-01-23 03:09:20.695226: step: 536/530, loss: 0.000591659510973841
2023-01-23 03:09:21.838637: step: 540/530, loss: 0.00047707557678222656
2023-01-23 03:09:23.045684: step: 544/530, loss: 8.593202073825523e-05
2023-01-23 03:09:24.219369: step: 548/530, loss: -5.53131121705519e-06
2023-01-23 03:09:25.390484: step: 552/530, loss: 0.003246402833610773
2023-01-23 03:09:26.574204: step: 556/530, loss: 0.0013695716625079513
2023-01-23 03:09:27.751740: step: 560/530, loss: 0.019749164581298828
2023-01-23 03:09:28.935752: step: 564/530, loss: 0.007194709964096546
2023-01-23 03:09:30.108787: step: 568/530, loss: 0.03823671489953995
2023-01-23 03:09:31.291008: step: 572/530, loss: 1.9836426872643642e-05
2023-01-23 03:09:32.463474: step: 576/530, loss: 0.00440483121201396
2023-01-23 03:09:33.575827: step: 580/530, loss: 0.009120178408920765
2023-01-23 03:09:34.715671: step: 584/530, loss: 0.011865091510117054
2023-01-23 03:09:35.900243: step: 588/530, loss: 0.00045948027400299907
2023-01-23 03:09:37.061480: step: 592/530, loss: 0.008075332269072533
2023-01-23 03:09:38.245518: step: 596/530, loss: 0.0032255174592137337
2023-01-23 03:09:39.443845: step: 600/530, loss: 0.002500343369320035
2023-01-23 03:09:40.583391: step: 604/530, loss: 0.0057840351946651936
2023-01-23 03:09:41.752746: step: 608/530, loss: 0.0650629997253418
2023-01-23 03:09:42.972453: step: 612/530, loss: 0.0005336761241778731
2023-01-23 03:09:44.151028: step: 616/530, loss: 0.017735673114657402
2023-01-23 03:09:45.304100: step: 620/530, loss: 0.015848923474550247
2023-01-23 03:09:46.458196: step: 624/530, loss: 0.05562668293714523
2023-01-23 03:09:47.635660: step: 628/530, loss: 0.003261327976360917
2023-01-23 03:09:48.830765: step: 632/530, loss: 0.0018414974911138415
2023-01-23 03:09:50.052729: step: 636/530, loss: 0.007472801487892866
2023-01-23 03:09:51.217593: step: 640/530, loss: 0.0008853912586346269
2023-01-23 03:09:52.412905: step: 644/530, loss: 0.0006452560774050653
2023-01-23 03:09:53.597009: step: 648/530, loss: 0.0010772706009447575
2023-01-23 03:09:54.802159: step: 652/530, loss: 5.674362000718247e-06
2023-01-23 03:09:56.051969: step: 656/530, loss: 0.03204202651977539
2023-01-23 03:09:57.198056: step: 660/530, loss: 0.0006127357482910156
2023-01-23 03:09:58.373756: step: 664/530, loss: 0.024794865399599075
2023-01-23 03:09:59.626895: step: 668/530, loss: 0.025270653888583183
2023-01-23 03:10:00.852427: step: 672/530, loss: 0.006105613894760609
2023-01-23 03:10:02.021942: step: 676/530, loss: 0.000266599643509835
2023-01-23 03:10:03.202895: step: 680/530, loss: 0.00750236539170146
2023-01-23 03:10:04.360705: step: 684/530, loss: 0.0028096199966967106
2023-01-23 03:10:05.523101: step: 688/530, loss: 0.0007131576421670616
2023-01-23 03:10:06.682689: step: 692/530, loss: 0.011946440674364567
2023-01-23 03:10:07.897423: step: 696/530, loss: 0.0083770751953125
2023-01-23 03:10:09.079868: step: 700/530, loss: 0.0035104751586914062
2023-01-23 03:10:10.266742: step: 704/530, loss: 0.003795719239860773
2023-01-23 03:10:11.444882: step: 708/530, loss: 0.00023136139498092234
2023-01-23 03:10:12.608706: step: 712/530, loss: 0.03469734266400337
2023-01-23 03:10:13.790355: step: 716/530, loss: 2.9659271604032256e-05
2023-01-23 03:10:14.948697: step: 720/530, loss: 0.06569528579711914
2023-01-23 03:10:16.078489: step: 724/530, loss: 0.003808403154835105
2023-01-23 03:10:17.261929: step: 728/530, loss: 0.008320235647261143
2023-01-23 03:10:18.451268: step: 732/530, loss: 0.13509120047092438
2023-01-23 03:10:19.658948: step: 736/530, loss: 0.006180953700095415
2023-01-23 03:10:20.797930: step: 740/530, loss: 0.005294227506965399
2023-01-23 03:10:21.965074: step: 744/530, loss: 0.06433287262916565
2023-01-23 03:10:23.126777: step: 748/530, loss: 0.013258743099868298
2023-01-23 03:10:24.280805: step: 752/530, loss: 0.008850479498505592
2023-01-23 03:10:25.438212: step: 756/530, loss: 0.01265049073845148
2023-01-23 03:10:26.605733: step: 760/530, loss: 0.08736009150743484
2023-01-23 03:10:27.771113: step: 764/530, loss: 0.0016738891135901213
2023-01-23 03:10:28.902240: step: 768/530, loss: 0.02806701697409153
2023-01-23 03:10:30.092500: step: 772/530, loss: 0.009701776318252087
2023-01-23 03:10:31.258218: step: 776/530, loss: 0.053648948669433594
2023-01-23 03:10:32.407428: step: 780/530, loss: 0.027636529877781868
2023-01-23 03:10:33.629690: step: 784/530, loss: 0.002396202180534601
2023-01-23 03:10:34.778359: step: 788/530, loss: 0.025104140862822533
2023-01-23 03:10:35.947477: step: 792/530, loss: 2.055168260994833e-05
2023-01-23 03:10:37.116923: step: 796/530, loss: 0.0004852295096497983
2023-01-23 03:10:38.257156: step: 800/530, loss: 0.021076299250125885
2023-01-23 03:10:39.416931: step: 804/530, loss: 0.00682754535228014
2023-01-23 03:10:40.574520: step: 808/530, loss: 0.037038229405879974
2023-01-23 03:10:41.802555: step: 812/530, loss: 0.01936950720846653
2023-01-23 03:10:43.006464: step: 816/530, loss: 0.020950699225068092
2023-01-23 03:10:44.158471: step: 820/530, loss: 0.002401161240413785
2023-01-23 03:10:45.325715: step: 824/530, loss: 0.038561251014471054
2023-01-23 03:10:46.517633: step: 828/530, loss: 0.013357257470488548
2023-01-23 03:10:47.647897: step: 832/530, loss: 3.6907196772517636e-05
2023-01-23 03:10:48.802256: step: 836/530, loss: 0.0016307830810546875
2023-01-23 03:10:49.971823: step: 840/530, loss: 0.012838936410844326
2023-01-23 03:10:51.162181: step: 844/530, loss: 0.00908727664500475
2023-01-23 03:10:52.305917: step: 848/530, loss: 0.00014972686767578125
2023-01-23 03:10:53.539413: step: 852/530, loss: 0.012853623367846012
2023-01-23 03:10:54.702844: step: 856/530, loss: 0.03035755082964897
2023-01-23 03:10:55.875358: step: 860/530, loss: 0.004576778504997492
2023-01-23 03:10:57.095892: step: 864/530, loss: 0.010898018255829811
2023-01-23 03:10:58.281150: step: 868/530, loss: 0.0003510475216899067
2023-01-23 03:10:59.442281: step: 872/530, loss: 0.00162172329146415
2023-01-23 03:11:00.640206: step: 876/530, loss: 0.015260887332260609
2023-01-23 03:11:01.827188: step: 880/530, loss: 0.007266998756676912
2023-01-23 03:11:02.977147: step: 884/530, loss: 0.030022908002138138
2023-01-23 03:11:04.132016: step: 888/530, loss: 0.030643461272120476
2023-01-23 03:11:05.296124: step: 892/530, loss: 0.008118057623505592
2023-01-23 03:11:06.469721: step: 896/530, loss: 0.006501388736069202
2023-01-23 03:11:07.669056: step: 900/530, loss: 0.00011749268014682457
2023-01-23 03:11:08.838075: step: 904/530, loss: 0.017227554693818092
2023-01-23 03:11:10.001799: step: 908/530, loss: 0.0004072189622092992
2023-01-23 03:11:11.144445: step: 912/530, loss: 0.023754358291625977
2023-01-23 03:11:12.320255: step: 916/530, loss: 2.6035308110294864e-05
2023-01-23 03:11:13.505767: step: 920/530, loss: 0.003057861467823386
2023-01-23 03:11:14.654260: step: 924/530, loss: 0.0198122039437294
2023-01-23 03:11:15.827373: step: 928/530, loss: 0.013790702447295189
2023-01-23 03:11:17.015403: step: 932/530, loss: 0.019167518243193626
2023-01-23 03:11:18.172380: step: 936/530, loss: 0.00020608902559615672
2023-01-23 03:11:19.351145: step: 940/530, loss: 0.025532031431794167
2023-01-23 03:11:20.493978: step: 944/530, loss: 0.0013461114140227437
2023-01-23 03:11:21.682118: step: 948/530, loss: 0.008386611938476562
2023-01-23 03:11:22.870082: step: 952/530, loss: 0.0004618644597940147
2023-01-23 03:11:24.018626: step: 956/530, loss: 0.005612373352050781
2023-01-23 03:11:25.188119: step: 960/530, loss: 7.104873475327622e-06
2023-01-23 03:11:26.390574: step: 964/530, loss: 0.021570492535829544
2023-01-23 03:11:27.592250: step: 968/530, loss: 5.8746340073412284e-05
2023-01-23 03:11:28.794763: step: 972/530, loss: 0.07768039405345917
2023-01-23 03:11:29.951786: step: 976/530, loss: 0.1064678207039833
2023-01-23 03:11:31.195500: step: 980/530, loss: 0.02261219173669815
2023-01-23 03:11:32.387282: step: 984/530, loss: 0.048804618418216705
2023-01-23 03:11:33.535805: step: 988/530, loss: 0.006248092278838158
2023-01-23 03:11:34.699162: step: 992/530, loss: 0.0010195731883868575
2023-01-23 03:11:35.874892: step: 996/530, loss: 0.07508783787488937
2023-01-23 03:11:37.018137: step: 1000/530, loss: 5.722046125811175e-07
2023-01-23 03:11:38.207679: step: 1004/530, loss: 4.091262962901965e-05
2023-01-23 03:11:39.402966: step: 1008/530, loss: 0.02834959141910076
2023-01-23 03:11:40.572633: step: 1012/530, loss: 9.307861182605848e-05
2023-01-23 03:11:41.733878: step: 1016/530, loss: 0.0012316703796386719
2023-01-23 03:11:42.887127: step: 1020/530, loss: 0.009230202995240688
2023-01-23 03:11:44.055139: step: 1024/530, loss: 0.006628227420151234
2023-01-23 03:11:45.257790: step: 1028/530, loss: 0.03822221979498863
2023-01-23 03:11:46.398142: step: 1032/530, loss: 0.0041792867705225945
2023-01-23 03:11:47.592766: step: 1036/530, loss: 0.008895493112504482
2023-01-23 03:11:48.776264: step: 1040/530, loss: 0.0030621530022472143
2023-01-23 03:11:49.938074: step: 1044/530, loss: 0.016025353223085403
2023-01-23 03:11:51.093688: step: 1048/530, loss: 0.008230209350585938
2023-01-23 03:11:52.303545: step: 1052/530, loss: 0.0006102562183514237
2023-01-23 03:11:53.438796: step: 1056/530, loss: 2.6893614631262608e-05
2023-01-23 03:11:54.607628: step: 1060/530, loss: 0.011555385775864124
2023-01-23 03:11:55.755653: step: 1064/530, loss: 9.250640869140625e-05
2023-01-23 03:11:56.913264: step: 1068/530, loss: 0.0006545067299157381
2023-01-23 03:11:58.105402: step: 1072/530, loss: 0.0007943630334921181
2023-01-23 03:11:59.242452: step: 1076/530, loss: 0.028077127411961555
2023-01-23 03:12:00.430240: step: 1080/530, loss: 0.015691090375185013
2023-01-23 03:12:01.601929: step: 1084/530, loss: 0.00042181016760878265
2023-01-23 03:12:02.765766: step: 1088/530, loss: 0.002599430037662387
2023-01-23 03:12:03.952956: step: 1092/530, loss: 0.0004177093505859375
2023-01-23 03:12:05.118035: step: 1096/530, loss: 0.0009422302828170359
2023-01-23 03:12:06.295162: step: 1100/530, loss: 0.005600595846772194
2023-01-23 03:12:07.438010: step: 1104/530, loss: 0.0012667656410485506
2023-01-23 03:12:08.606982: step: 1108/530, loss: 0.057733204215765
2023-01-23 03:12:09.788235: step: 1112/530, loss: 0.013042068108916283
2023-01-23 03:12:10.946893: step: 1116/530, loss: 0.038478996604681015
2023-01-23 03:12:12.157606: step: 1120/530, loss: 0.0031649114098399878
2023-01-23 03:12:13.366138: step: 1124/530, loss: 0.00018358232046011835
2023-01-23 03:12:14.531814: step: 1128/530, loss: 0.00019969939603470266
2023-01-23 03:12:15.733331: step: 1132/530, loss: 1.869201696536038e-05
2023-01-23 03:12:16.902703: step: 1136/530, loss: 0.04739074781537056
2023-01-23 03:12:18.108820: step: 1140/530, loss: 0.014592265710234642
2023-01-23 03:12:19.262703: step: 1144/530, loss: 0.00036449433537200093
2023-01-23 03:12:20.411538: step: 1148/530, loss: 0.0008961677667684853
2023-01-23 03:12:21.589068: step: 1152/530, loss: 0.007920980453491211
2023-01-23 03:12:22.745398: step: 1156/530, loss: 0.007328605744987726
2023-01-23 03:12:23.909667: step: 1160/530, loss: 0.0293426513671875
2023-01-23 03:12:25.094344: step: 1164/530, loss: 0.019978905096650124
2023-01-23 03:12:26.255458: step: 1168/530, loss: 0.00258979806676507
2023-01-23 03:12:27.420849: step: 1172/530, loss: 0.03161735460162163
2023-01-23 03:12:28.567673: step: 1176/530, loss: 0.004947376437485218
2023-01-23 03:12:29.708205: step: 1180/530, loss: 0.00047860146150924265
2023-01-23 03:12:30.842504: step: 1184/530, loss: 0.0007875442388467491
2023-01-23 03:12:31.991241: step: 1188/530, loss: 0.004349708557128906
2023-01-23 03:12:33.158273: step: 1192/530, loss: 0.0018177032470703125
2023-01-23 03:12:34.344364: step: 1196/530, loss: 0.0017662049503996968
2023-01-23 03:12:35.494631: step: 1200/530, loss: 0.003905773162841797
2023-01-23 03:12:36.617570: step: 1204/530, loss: 0.003988456912338734
2023-01-23 03:12:37.824379: step: 1208/530, loss: 0.0016990661388263106
2023-01-23 03:12:38.984364: step: 1212/530, loss: 0.0002038955717580393
2023-01-23 03:12:40.167506: step: 1216/530, loss: 0.0037208558060228825
2023-01-23 03:12:41.332547: step: 1220/530, loss: 0.00017161370487883687
2023-01-23 03:12:42.548578: step: 1224/530, loss: 0.0182023998349905
2023-01-23 03:12:43.705197: step: 1228/530, loss: 0.020683765411376953
2023-01-23 03:12:44.861179: step: 1232/530, loss: 0.008129501715302467
2023-01-23 03:12:46.014665: step: 1236/530, loss: 0.008852005936205387
2023-01-23 03:12:47.182182: step: 1240/530, loss: 0.02244281768798828
2023-01-23 03:12:48.313815: step: 1244/530, loss: 0.04608936235308647
2023-01-23 03:12:49.485374: step: 1248/530, loss: 0.0015254972968250513
2023-01-23 03:12:50.656792: step: 1252/530, loss: 0.007021427154541016
2023-01-23 03:12:51.868456: step: 1256/530, loss: 0.0054569244384765625
2023-01-23 03:12:53.062998: step: 1260/530, loss: 0.00021114348783157766
2023-01-23 03:12:54.227050: step: 1264/530, loss: 0.007398843765258789
2023-01-23 03:12:55.373664: step: 1268/530, loss: 0.00024337768263649195
2023-01-23 03:12:56.529273: step: 1272/530, loss: 0.00011262894258834422
2023-01-23 03:12:57.704954: step: 1276/530, loss: 0.0491454154253006
2023-01-23 03:12:58.912208: step: 1280/530, loss: 0.0002900123945437372
2023-01-23 03:13:00.041535: step: 1284/530, loss: 0.012590598315000534
2023-01-23 03:13:01.229801: step: 1288/530, loss: 0.18321160972118378
2023-01-23 03:13:02.393673: step: 1292/530, loss: 0.020140647888183594
2023-01-23 03:13:03.566302: step: 1296/530, loss: 0.03394355624914169
2023-01-23 03:13:04.732167: step: 1300/530, loss: 2.3460386728402227e-05
2023-01-23 03:13:05.889352: step: 1304/530, loss: 0.06991196423768997
2023-01-23 03:13:07.102763: step: 1308/530, loss: 0.021816732361912727
2023-01-23 03:13:08.289725: step: 1312/530, loss: 0.009323501028120518
2023-01-23 03:13:09.447527: step: 1316/530, loss: 0.022315694019198418
2023-01-23 03:13:10.608531: step: 1320/530, loss: 0.0010746002662926912
2023-01-23 03:13:11.813810: step: 1324/530, loss: 0.0009769439930096269
2023-01-23 03:13:12.922289: step: 1328/530, loss: 0.0003716468927450478
2023-01-23 03:13:14.204577: step: 1332/530, loss: 0.0005878448719158769
2023-01-23 03:13:15.379383: step: 1336/530, loss: 0.005566311068832874
2023-01-23 03:13:16.560913: step: 1340/530, loss: 0.02081451378762722
2023-01-23 03:13:17.744098: step: 1344/530, loss: 0.0004314422549214214
2023-01-23 03:13:18.907219: step: 1348/530, loss: 0.05808582156896591
2023-01-23 03:13:20.095374: step: 1352/530, loss: 7.023811485851184e-05
2023-01-23 03:13:21.272993: step: 1356/530, loss: 0.005383777432143688
2023-01-23 03:13:22.410546: step: 1360/530, loss: 0.00406837509945035
2023-01-23 03:13:23.564527: step: 1364/530, loss: 0.015238761901855469
2023-01-23 03:13:24.730265: step: 1368/530, loss: 0.10889206826686859
2023-01-23 03:13:25.894192: step: 1372/530, loss: 0.009109783917665482
2023-01-23 03:13:27.065525: step: 1376/530, loss: 0.0020843506790697575
2023-01-23 03:13:28.215928: step: 1380/530, loss: 0.013313103467226028
2023-01-23 03:13:29.387219: step: 1384/530, loss: 0.061997320502996445
2023-01-23 03:13:30.593984: step: 1388/530, loss: 0.018683088943362236
2023-01-23 03:13:31.731030: step: 1392/530, loss: 0.008904362097382545
2023-01-23 03:13:32.904453: step: 1396/530, loss: 0.01609659194946289
2023-01-23 03:13:34.109255: step: 1400/530, loss: 0.0019936561584472656
2023-01-23 03:13:35.304746: step: 1404/530, loss: 0.0008223534096032381
2023-01-23 03:13:36.477791: step: 1408/530, loss: 0.011760997585952282
2023-01-23 03:13:37.615660: step: 1412/530, loss: 0.00026607513427734375
2023-01-23 03:13:38.811140: step: 1416/530, loss: 0.017190933227539062
2023-01-23 03:13:39.975444: step: 1420/530, loss: 0.08052539825439453
2023-01-23 03:13:41.129768: step: 1424/530, loss: 0.0015691757434979081
2023-01-23 03:13:42.317033: step: 1428/530, loss: 0.01707172580063343
2023-01-23 03:13:43.482149: step: 1432/530, loss: 0.000419425981817767
2023-01-23 03:13:44.636817: step: 1436/530, loss: 0.0001367092045256868
2023-01-23 03:13:45.808226: step: 1440/530, loss: 0.008555039763450623
2023-01-23 03:13:46.995265: step: 1444/530, loss: 0.026746369898319244
2023-01-23 03:13:48.177826: step: 1448/530, loss: 0.015646720305085182
2023-01-23 03:13:49.367106: step: 1452/530, loss: 0.05076298862695694
2023-01-23 03:13:50.553290: step: 1456/530, loss: 0.4115432798862457
2023-01-23 03:13:51.702944: step: 1460/530, loss: 0.00010528565326239914
2023-01-23 03:13:52.908198: step: 1464/530, loss: 1.65043044090271
2023-01-23 03:13:54.098843: step: 1468/530, loss: 0.000682449375744909
2023-01-23 03:13:55.298238: step: 1472/530, loss: 0.0018374442588537931
2023-01-23 03:13:56.526912: step: 1476/530, loss: 0.0004932403680868447
2023-01-23 03:13:57.688960: step: 1480/530, loss: 8.60214204294607e-05
2023-01-23 03:13:58.856931: step: 1484/530, loss: 0.011019039899110794
2023-01-23 03:14:00.048867: step: 1488/530, loss: 0.06644248217344284
2023-01-23 03:14:01.208315: step: 1492/530, loss: 0.0017852783203125
2023-01-23 03:14:02.375343: step: 1496/530, loss: 0.007105064578354359
2023-01-23 03:14:03.503483: step: 1500/530, loss: 5.254745337879285e-05
2023-01-23 03:14:04.670624: step: 1504/530, loss: 0.0010986328125
2023-01-23 03:14:05.837046: step: 1508/530, loss: 0.00033750536385923624
2023-01-23 03:14:07.002186: step: 1512/530, loss: 0.005956745240837336
2023-01-23 03:14:08.174738: step: 1516/530, loss: 0.00362224574200809
2023-01-23 03:14:09.324815: step: 1520/530, loss: 9.946823411155492e-05
2023-01-23 03:14:10.502655: step: 1524/530, loss: 0.027692366391420364
2023-01-23 03:14:11.653728: step: 1528/530, loss: 0.020485782995820045
2023-01-23 03:14:12.842616: step: 1532/530, loss: 6.790161569369957e-05
2023-01-23 03:14:13.991486: step: 1536/530, loss: 0.01285934541374445
2023-01-23 03:14:15.168071: step: 1540/530, loss: 0.0024919509887695312
2023-01-23 03:14:16.337009: step: 1544/530, loss: 0.009604454040527344
2023-01-23 03:14:17.514585: step: 1548/530, loss: 0.0012637138133868575
2023-01-23 03:14:18.684830: step: 1552/530, loss: 0.006312465760856867
2023-01-23 03:14:19.847381: step: 1556/530, loss: 0.0005198002327233553
2023-01-23 03:14:21.006531: step: 1560/530, loss: 0.001466464949771762
2023-01-23 03:14:22.156794: step: 1564/530, loss: 0.05649099498987198
2023-01-23 03:14:23.289952: step: 1568/530, loss: 0.004805660340934992
2023-01-23 03:14:24.456109: step: 1572/530, loss: 0.0033572197426110506
2023-01-23 03:14:25.630283: step: 1576/530, loss: 0.019612504169344902
2023-01-23 03:14:26.766429: step: 1580/530, loss: 0.013346290215849876
2023-01-23 03:14:27.929700: step: 1584/530, loss: 0.018196679651737213
2023-01-23 03:14:29.135953: step: 1588/530, loss: 0.002219676971435547
2023-01-23 03:14:30.289322: step: 1592/530, loss: 0.06623125076293945
2023-01-23 03:14:31.450276: step: 1596/530, loss: 0.020299913361668587
2023-01-23 03:14:32.637832: step: 1600/530, loss: 0.0023983002174645662
2023-01-23 03:14:33.797284: step: 1604/530, loss: 0.0004515647888183594
2023-01-23 03:14:34.971521: step: 1608/530, loss: 0.009576797485351562
2023-01-23 03:14:36.185976: step: 1612/530, loss: 0.0004172325134277344
2023-01-23 03:14:37.393877: step: 1616/530, loss: 0.045198824256658554
2023-01-23 03:14:38.563251: step: 1620/530, loss: 0.001467204187065363
2023-01-23 03:14:39.744314: step: 1624/530, loss: 2.517700158932712e-05
2023-01-23 03:14:40.913603: step: 1628/530, loss: 0.0011226654751226306
2023-01-23 03:14:42.077426: step: 1632/530, loss: 0.0025594711769372225
2023-01-23 03:14:43.236110: step: 1636/530, loss: 0.09730224311351776
2023-01-23 03:14:44.437281: step: 1640/530, loss: 0.03456687927246094
2023-01-23 03:14:45.588651: step: 1644/530, loss: 1.4400482541532256e-05
2023-01-23 03:14:46.745740: step: 1648/530, loss: 0.005744457244873047
2023-01-23 03:14:47.907769: step: 1652/530, loss: 0.12579460442066193
2023-01-23 03:14:49.104047: step: 1656/530, loss: 0.007267761509865522
2023-01-23 03:14:50.292629: step: 1660/530, loss: 0.06963996589183807
2023-01-23 03:14:51.470127: step: 1664/530, loss: 0.022086717188358307
2023-01-23 03:14:52.631505: step: 1668/530, loss: 0.0005795002216473222
2023-01-23 03:14:53.796934: step: 1672/530, loss: 0.1747472733259201
2023-01-23 03:14:54.996289: step: 1676/530, loss: 0.10909853875637054
2023-01-23 03:14:56.218304: step: 1680/530, loss: 0.04020848125219345
2023-01-23 03:14:57.382387: step: 1684/530, loss: 0.002763891126960516
2023-01-23 03:14:58.545544: step: 1688/530, loss: 0.00013256072998046875
2023-01-23 03:14:59.702479: step: 1692/530, loss: 0.0007474899757653475
2023-01-23 03:15:00.873559: step: 1696/530, loss: 0.08283176273107529
2023-01-23 03:15:02.077750: step: 1700/530, loss: 0.02291278727352619
2023-01-23 03:15:03.289955: step: 1704/530, loss: 0.01754322089254856
2023-01-23 03:15:04.459948: step: 1708/530, loss: 0.00372142787091434
2023-01-23 03:15:05.603320: step: 1712/530, loss: 0.01638164557516575
2023-01-23 03:15:06.799473: step: 1716/530, loss: 0.020516490563750267
2023-01-23 03:15:07.958588: step: 1720/530, loss: 0.0001412391575286165
2023-01-23 03:15:09.147949: step: 1724/530, loss: 0.041799817234277725
2023-01-23 03:15:10.305845: step: 1728/530, loss: 0.005722093395888805
2023-01-23 03:15:11.505070: step: 1732/530, loss: 0.6590420007705688
2023-01-23 03:15:12.705880: step: 1736/530, loss: 0.033585548400878906
2023-01-23 03:15:13.878333: step: 1740/530, loss: 0.12217274308204651
2023-01-23 03:15:15.053664: step: 1744/530, loss: 5.2988529205322266e-05
2023-01-23 03:15:16.197192: step: 1748/530, loss: 0.035793498158454895
2023-01-23 03:15:17.381559: step: 1752/530, loss: 0.0636606216430664
2023-01-23 03:15:18.524446: step: 1756/530, loss: 0.006601619999855757
2023-01-23 03:15:19.716487: step: 1760/530, loss: 0.00021650790586136281
2023-01-23 03:15:20.883344: step: 1764/530, loss: 0.0004972219467163086
2023-01-23 03:15:22.128633: step: 1768/530, loss: 0.043898582458496094
2023-01-23 03:15:23.284577: step: 1772/530, loss: 0.06102113798260689
2023-01-23 03:15:24.409474: step: 1776/530, loss: 0.00043125153752043843
2023-01-23 03:15:25.571232: step: 1780/530, loss: 0.0008471012115478516
2023-01-23 03:15:26.729672: step: 1784/530, loss: 0.03125715255737305
2023-01-23 03:15:27.892431: step: 1788/530, loss: 0.007453442085534334
2023-01-23 03:15:29.107000: step: 1792/530, loss: 0.06212577968835831
2023-01-23 03:15:30.298581: step: 1796/530, loss: 0.001355934189632535
2023-01-23 03:15:31.457216: step: 1800/530, loss: 0.011693191714584827
2023-01-23 03:15:32.606513: step: 1804/530, loss: 0.16507187485694885
2023-01-23 03:15:33.768565: step: 1808/530, loss: 0.0025229454040527344
2023-01-23 03:15:34.968243: step: 1812/530, loss: 0.003869295120239258
2023-01-23 03:15:36.149321: step: 1816/530, loss: 0.009980487637221813
2023-01-23 03:15:37.338028: step: 1820/530, loss: 0.0013246536254882812
2023-01-23 03:15:38.525290: step: 1824/530, loss: 0.0005734444130212069
2023-01-23 03:15:39.731138: step: 1828/530, loss: 0.004064178094267845
2023-01-23 03:15:40.874198: step: 1832/530, loss: 0.05234880745410919
2023-01-23 03:15:42.049971: step: 1836/530, loss: 0.004139041993767023
2023-01-23 03:15:43.192903: step: 1840/530, loss: 0.00028662680415436625
2023-01-23 03:15:44.387653: step: 1844/530, loss: 0.16543789207935333
2023-01-23 03:15:45.565664: step: 1848/530, loss: 0.0007221221458166838
2023-01-23 03:15:46.819032: step: 1852/530, loss: 0.013888930901885033
2023-01-23 03:15:47.991366: step: 1856/530, loss: 0.007541084196418524
2023-01-23 03:15:49.205876: step: 1860/530, loss: 0.010792732238769531
2023-01-23 03:15:50.396712: step: 1864/530, loss: 0.006150341127067804
2023-01-23 03:15:51.575036: step: 1868/530, loss: 0.7755119204521179
2023-01-23 03:15:52.749168: step: 1872/530, loss: 0.008628464303910732
2023-01-23 03:15:53.889707: step: 1876/530, loss: 0.0010536194313317537
2023-01-23 03:15:55.059371: step: 1880/530, loss: 0.003494834993034601
2023-01-23 03:15:56.207949: step: 1884/530, loss: 7.61032133596018e-05
2023-01-23 03:15:57.373216: step: 1888/530, loss: 0.008405113592743874
2023-01-23 03:15:58.530255: step: 1892/530, loss: 0.00044484136742539704
2023-01-23 03:15:59.716301: step: 1896/530, loss: 0.021352767944335938
2023-01-23 03:16:00.895897: step: 1900/530, loss: 0.0013708114856854081
2023-01-23 03:16:02.054379: step: 1904/530, loss: 0.0006736755603924394
2023-01-23 03:16:03.222594: step: 1908/530, loss: 0.00013999939255882055
2023-01-23 03:16:04.346425: step: 1912/530, loss: 0.013002777472138405
2023-01-23 03:16:05.529660: step: 1916/530, loss: 0.004801368806511164
2023-01-23 03:16:06.720850: step: 1920/530, loss: 0.04571075364947319
2023-01-23 03:16:07.866359: step: 1924/530, loss: 0.00974273681640625
2023-01-23 03:16:09.054959: step: 1928/530, loss: 0.09742498397827148
2023-01-23 03:16:10.271739: step: 1932/530, loss: 0.05283212661743164
2023-01-23 03:16:11.439271: step: 1936/530, loss: 0.0009844780433923006
2023-01-23 03:16:12.615478: step: 1940/530, loss: 0.0005422591930255294
2023-01-23 03:16:13.753742: step: 1944/530, loss: 1.049041748046875e-05
2023-01-23 03:16:14.918119: step: 1948/530, loss: 0.00788955669850111
2023-01-23 03:16:16.104196: step: 1952/530, loss: 0.0006093978881835938
2023-01-23 03:16:17.288349: step: 1956/530, loss: 0.01922302320599556
2023-01-23 03:16:18.438778: step: 1960/530, loss: 0.01354312989860773
2023-01-23 03:16:19.582898: step: 1964/530, loss: 0.0006777763483114541
2023-01-23 03:16:20.729701: step: 1968/530, loss: 0.011162662878632545
2023-01-23 03:16:21.899466: step: 1972/530, loss: 0.013269996270537376
2023-01-23 03:16:23.102750: step: 1976/530, loss: 0.01797962374985218
2023-01-23 03:16:24.241864: step: 1980/530, loss: 0.020705606788396835
2023-01-23 03:16:25.431126: step: 1984/530, loss: 0.0014919281238690019
2023-01-23 03:16:26.588717: step: 1988/530, loss: 0.0012494086986407638
2023-01-23 03:16:27.781761: step: 1992/530, loss: 0.00022964477830100805
2023-01-23 03:16:28.923259: step: 1996/530, loss: 0.08007641136646271
2023-01-23 03:16:30.117365: step: 2000/530, loss: 9.603500802768394e-05
2023-01-23 03:16:31.302590: step: 2004/530, loss: 0.005882644560188055
2023-01-23 03:16:32.491383: step: 2008/530, loss: 0.001674652099609375
2023-01-23 03:16:33.698350: step: 2012/530, loss: 0.3758220672607422
2023-01-23 03:16:34.850663: step: 2016/530, loss: 0.04876318201422691
2023-01-23 03:16:36.052745: step: 2020/530, loss: 0.0038507464341819286
2023-01-23 03:16:37.208175: step: 2024/530, loss: 0.06845073401927948
2023-01-23 03:16:38.342644: step: 2028/530, loss: 0.002036666963249445
2023-01-23 03:16:39.535619: step: 2032/530, loss: 0.024755287915468216
2023-01-23 03:16:40.706998: step: 2036/530, loss: 0.0005062103155069053
2023-01-23 03:16:41.881657: step: 2040/530, loss: 0.00430984515696764
2023-01-23 03:16:43.069488: step: 2044/530, loss: 0.02907733991742134
2023-01-23 03:16:44.196100: step: 2048/530, loss: 1.754760705807712e-05
2023-01-23 03:16:45.348044: step: 2052/530, loss: 0.0004219055117573589
2023-01-23 03:16:46.541037: step: 2056/530, loss: 0.03699970245361328
2023-01-23 03:16:47.704343: step: 2060/530, loss: 0.01606121100485325
2023-01-23 03:16:48.884043: step: 2064/530, loss: 0.05028242990374565
2023-01-23 03:16:50.053580: step: 2068/530, loss: 0.006548118777573109
2023-01-23 03:16:51.211213: step: 2072/530, loss: 0.0005677699809893966
2023-01-23 03:16:52.379564: step: 2076/530, loss: 0.0325685515999794
2023-01-23 03:16:53.579094: step: 2080/530, loss: 0.004090690519660711
2023-01-23 03:16:54.733015: step: 2084/530, loss: 0.2901313900947571
2023-01-23 03:16:55.938761: step: 2088/530, loss: 0.0026451589073985815
2023-01-23 03:16:57.129625: step: 2092/530, loss: 0.00032224657479673624
2023-01-23 03:16:58.302287: step: 2096/530, loss: 1.0603395700454712
2023-01-23 03:16:59.467117: step: 2100/530, loss: 0.05462236329913139
2023-01-23 03:17:00.695807: step: 2104/530, loss: 0.0004228711186442524
2023-01-23 03:17:01.844412: step: 2108/530, loss: 0.1792866289615631
2023-01-23 03:17:03.023676: step: 2112/530, loss: 0.023072529584169388
2023-01-23 03:17:04.158708: step: 2116/530, loss: 0.00445899972692132
2023-01-23 03:17:05.326066: step: 2120/530, loss: 0.00666046142578125
==================================================
Loss: 0.029
--------------------
Dev: {'event': {'p': 0.576271186440678, 'r': 0.7696404793608522, 'f1': 0.6590649942987458}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 20}
Test: {'event': {'p': 0.6543778801843319, 'r': 0.816561242093157, 'f1': 0.7265285239191609}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 20}
Chinese: {'event': {'p': 0.5652173913043478, 'r': 0.9629629629629629, 'f1': 0.7123287671232876}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 20}
Korean: {'event': {'p': 0.576271186440678, 'r': 0.5396825396825397, 'f1': 0.5573770491803278}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 20}
Russian: {'event': {'p': 0.32, 'r': 0.4444444444444444, 'f1': 0.37209302325581395}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 20}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6065057712486883, 'r': 0.7696404793608522, 'f1': 0.6784037558685445}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
Eng Test for Chinese: {'event': {'p': 0.6643026004728132, 'r': 0.8079355951696378, 'f1': 0.7291126102750389}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
Sample Chinese: {'event': {'p': 0.6024096385542169, 'r': 0.9259259259259259, 'f1': 0.7299270072992702}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5733990147783251, 'r': 0.7749667110519307, 'f1': 0.6591166477916196}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Eng Test for Korean: {'event': {'p': 0.6218005295675199, 'r': 0.8102357676825762, 'f1': 0.7036204744069912}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Sample Korean: {'event': {'p': 0.6417910447761194, 'r': 0.6825396825396826, 'f1': 0.6615384615384614}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5951882845188284, 'r': 0.7576564580559254, 'f1': 0.6666666666666666}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6663405088062623, 'r': 0.7832087406555491, 'f1': 0.7200634417129264}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5, 'r': 0.6666666666666666, 'f1': 0.5714285714285715}, '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 03:17:48.267568: step: 4/530, loss: 0.00022544861712958664
2023-01-23 03:17:49.463780: step: 8/530, loss: 0.00010385513451183215
2023-01-23 03:17:50.602546: step: 12/530, loss: 0.004794311709702015
2023-01-23 03:17:51.798264: step: 16/530, loss: 0.03369102254509926
2023-01-23 03:17:52.948978: step: 20/530, loss: 0.0003787994501180947
2023-01-23 03:17:54.113258: step: 24/530, loss: 0.0006971359252929688
2023-01-23 03:17:55.268003: step: 28/530, loss: 0.015932369977235794
2023-01-23 03:17:56.466324: step: 32/530, loss: 0.00010662078420864418
2023-01-23 03:17:57.658229: step: 36/530, loss: 0.00012683868408203125
2023-01-23 03:17:58.836923: step: 40/530, loss: 0.00041790009709075093
2023-01-23 03:17:59.997827: step: 44/530, loss: 0.002053546952083707
2023-01-23 03:18:01.180894: step: 48/530, loss: 0.03153686597943306
2023-01-23 03:18:02.367636: step: 52/530, loss: 0.00965042132884264
2023-01-23 03:18:03.537853: step: 56/530, loss: 0.0003934860578738153
2023-01-23 03:18:04.736993: step: 60/530, loss: 0.0003167152754031122
2023-01-23 03:18:05.919184: step: 64/530, loss: 0.0008425712585449219
2023-01-23 03:18:07.120387: step: 68/530, loss: 0.0015649795532226562
2023-01-23 03:18:08.281944: step: 72/530, loss: 0.00030832289485260844
2023-01-23 03:18:09.438026: step: 76/530, loss: 0.001506805419921875
2023-01-23 03:18:10.637895: step: 80/530, loss: 0.00019693374633789062
2023-01-23 03:18:11.819034: step: 84/530, loss: 0.00872650183737278
2023-01-23 03:18:12.968560: step: 88/530, loss: 0.032575178891420364
2023-01-23 03:18:14.115238: step: 92/530, loss: 0.00780487060546875
2023-01-23 03:18:15.290687: step: 96/530, loss: 7.290840585483238e-05
2023-01-23 03:18:16.438094: step: 100/530, loss: -1.9073486328125e-06
2023-01-23 03:18:17.564392: step: 104/530, loss: 0.0010035515297204256
2023-01-23 03:18:18.736009: step: 108/530, loss: 0.41664770245552063
2023-01-23 03:18:19.918931: step: 112/530, loss: 0.021617509424686432
2023-01-23 03:18:21.094394: step: 116/530, loss: 0.008367538452148438
2023-01-23 03:18:22.276032: step: 120/530, loss: 0.04301929473876953
2023-01-23 03:18:23.438708: step: 124/530, loss: 0.0036594390403479338
2023-01-23 03:18:24.619610: step: 128/530, loss: 0.002813148545101285
2023-01-23 03:18:25.770914: step: 132/530, loss: 0.07530871033668518
2023-01-23 03:18:26.925462: step: 136/530, loss: 0.2991907000541687
2023-01-23 03:18:28.138851: step: 140/530, loss: 0.0011005401611328125
2023-01-23 03:18:29.306026: step: 144/530, loss: 0.00027327536372467875
2023-01-23 03:18:30.467697: step: 148/530, loss: 0.0002777099725790322
2023-01-23 03:18:31.630392: step: 152/530, loss: 0.0033702850341796875
2023-01-23 03:18:32.787594: step: 156/530, loss: 0.00286960625089705
2023-01-23 03:18:33.997826: step: 160/530, loss: 0.004630756564438343
2023-01-23 03:18:35.139657: step: 164/530, loss: 0.006375408265739679
2023-01-23 03:18:36.302980: step: 168/530, loss: 0.0008205414051190019
2023-01-23 03:18:37.476874: step: 172/530, loss: 0.010860252194106579
2023-01-23 03:18:38.637410: step: 176/530, loss: 0.0017423630924895406
2023-01-23 03:18:39.847338: step: 180/530, loss: 0.06566419452428818
2023-01-23 03:18:41.029110: step: 184/530, loss: 0.004422569647431374
2023-01-23 03:18:42.166560: step: 188/530, loss: 0.0034994124434888363
2023-01-23 03:18:43.359481: step: 192/530, loss: 0.017185211181640625
2023-01-23 03:18:44.536950: step: 196/530, loss: 0.013257408514618874
2023-01-23 03:18:45.664409: step: 200/530, loss: 0.0019195557106286287
2023-01-23 03:18:46.817245: step: 204/530, loss: 0.025051262229681015
2023-01-23 03:18:47.980244: step: 208/530, loss: 0.010174370370805264
2023-01-23 03:18:49.150136: step: 212/530, loss: 0.0030391693580895662
2023-01-23 03:18:50.313183: step: 216/530, loss: 0.005788612179458141
2023-01-23 03:18:51.481982: step: 220/530, loss: 0.025357436388731003
2023-01-23 03:18:52.667954: step: 224/530, loss: 0.02130146138370037
2023-01-23 03:18:53.818255: step: 228/530, loss: 0.0031027316581457853
2023-01-23 03:18:54.986944: step: 232/530, loss: 0.0005702972412109375
2023-01-23 03:18:56.164855: step: 236/530, loss: 0.002884006593376398
2023-01-23 03:18:57.340789: step: 240/530, loss: 0.0018054962856695056
2023-01-23 03:18:58.518959: step: 244/530, loss: 0.0008661747560836375
2023-01-23 03:18:59.715312: step: 248/530, loss: 0.0006205082172527909
2023-01-23 03:19:00.901643: step: 252/530, loss: 0.00012426376633811742
2023-01-23 03:19:02.061977: step: 256/530, loss: 0.01732473447918892
2023-01-23 03:19:03.207714: step: 260/530, loss: 0.00013537406630348414
2023-01-23 03:19:04.390155: step: 264/530, loss: 0.0021300793159753084
2023-01-23 03:19:05.533210: step: 268/530, loss: 0.0003980636829510331
2023-01-23 03:19:06.700086: step: 272/530, loss: 0.0020854950416833162
2023-01-23 03:19:07.897627: step: 276/530, loss: 0.006554889492690563
2023-01-23 03:19:09.039988: step: 280/530, loss: 0.002033805940300226
2023-01-23 03:19:10.215550: step: 284/530, loss: 0.012477397918701172
2023-01-23 03:19:11.389684: step: 288/530, loss: 0.0038387300446629524
2023-01-23 03:19:12.562368: step: 292/530, loss: 0.00016641616821289062
2023-01-23 03:19:13.700649: step: 296/530, loss: 0.026497460901737213
2023-01-23 03:19:14.873726: step: 300/530, loss: 0.03892707824707031
2023-01-23 03:19:16.046434: step: 304/530, loss: 0.06496113538742065
2023-01-23 03:19:17.179328: step: 308/530, loss: 2.47955313170678e-06
2023-01-23 03:19:18.342074: step: 312/530, loss: 0.07023658603429794
2023-01-23 03:19:19.529431: step: 316/530, loss: 0.30156898498535156
2023-01-23 03:19:20.681452: step: 320/530, loss: 0.017316604033112526
2023-01-23 03:19:21.867652: step: 324/530, loss: 0.0011844635009765625
2023-01-23 03:19:23.067139: step: 328/530, loss: 0.0005579948774538934
2023-01-23 03:19:24.212728: step: 332/530, loss: 0.00010375976853538305
2023-01-23 03:19:25.385501: step: 336/530, loss: 0.008565330877900124
2023-01-23 03:19:26.553539: step: 340/530, loss: 0.000873184239026159
2023-01-23 03:19:27.695061: step: 344/530, loss: 0.03654494509100914
2023-01-23 03:19:28.858496: step: 348/530, loss: 0.005431937985122204
2023-01-23 03:19:30.044058: step: 352/530, loss: 0.5572018623352051
2023-01-23 03:19:31.211395: step: 356/530, loss: 0.011644936166703701
2023-01-23 03:19:32.383979: step: 360/530, loss: 0.015163802541792393
2023-01-23 03:19:33.559917: step: 364/530, loss: 0.0002283096400788054
2023-01-23 03:19:34.722203: step: 368/530, loss: 0.00139789585955441
2023-01-23 03:19:35.935866: step: 372/530, loss: 0.006923676002770662
2023-01-23 03:19:37.144631: step: 376/530, loss: 0.002502632327377796
2023-01-23 03:19:38.294570: step: 380/530, loss: 0.0006104469066485763
2023-01-23 03:19:39.460278: step: 384/530, loss: 0.023661326617002487
2023-01-23 03:19:40.628508: step: 388/530, loss: 0.0037982941139489412
2023-01-23 03:19:41.817901: step: 392/530, loss: 0.017516423016786575
2023-01-23 03:19:43.005831: step: 396/530, loss: 0.0073608397506177425
2023-01-23 03:19:44.202821: step: 400/530, loss: 0.01524648629128933
2023-01-23 03:19:45.373669: step: 404/530, loss: 0.0013905524974688888
2023-01-23 03:19:46.527523: step: 408/530, loss: 0.0073544979095458984
2023-01-23 03:19:47.706103: step: 412/530, loss: 5.226135181146674e-05
2023-01-23 03:19:48.863726: step: 416/530, loss: 0.008092212490737438
2023-01-23 03:19:50.025444: step: 420/530, loss: 0.06045146286487579
2023-01-23 03:19:51.195821: step: 424/530, loss: 0.02800917811691761
2023-01-23 03:19:52.396247: step: 428/530, loss: 0.005451393313705921
2023-01-23 03:19:53.596110: step: 432/530, loss: 0.0014471054309979081
2023-01-23 03:19:54.768319: step: 436/530, loss: 0.11318083107471466
2023-01-23 03:19:55.919990: step: 440/530, loss: 0.0011535645462572575
2023-01-23 03:19:57.094087: step: 444/530, loss: 0.0001038074551615864
2023-01-23 03:19:58.235506: step: 448/530, loss: 0.000736713467631489
2023-01-23 03:19:59.411431: step: 452/530, loss: 0.0007370948442257941
2023-01-23 03:20:00.588716: step: 456/530, loss: 0.018181132152676582
2023-01-23 03:20:01.781440: step: 460/530, loss: 4.3487551010912284e-05
2023-01-23 03:20:02.985896: step: 464/530, loss: 0.000263214111328125
2023-01-23 03:20:04.127811: step: 468/530, loss: 0.0003094673156738281
2023-01-23 03:20:05.266509: step: 472/530, loss: 7.677078247070312e-05
2023-01-23 03:20:06.433630: step: 476/530, loss: 0.00023751257685944438
2023-01-23 03:20:07.584431: step: 480/530, loss: 0.029003430157899857
2023-01-23 03:20:08.760110: step: 484/530, loss: 0.01321487408131361
2023-01-23 03:20:09.938315: step: 488/530, loss: 0.0027103424072265625
2023-01-23 03:20:11.120461: step: 492/530, loss: 0.0086402902379632
2023-01-23 03:20:12.302843: step: 496/530, loss: 0.0009473800892010331
2023-01-23 03:20:13.438531: step: 500/530, loss: 0.29113462567329407
2023-01-23 03:20:14.626602: step: 504/530, loss: 0.01332998275756836
2023-01-23 03:20:15.772106: step: 508/530, loss: 9.317397780250758e-05
2023-01-23 03:20:16.915108: step: 512/530, loss: 1.1873245966853574e-05
2023-01-23 03:20:18.054357: step: 516/530, loss: 4.4631960918195546e-05
2023-01-23 03:20:19.210830: step: 520/530, loss: 0.005668449681252241
2023-01-23 03:20:20.355359: step: 524/530, loss: 0.005369758699089289
2023-01-23 03:20:21.541202: step: 528/530, loss: 0.00043358802213333547
2023-01-23 03:20:22.801964: step: 532/530, loss: 0.012942886911332607
2023-01-23 03:20:23.973929: step: 536/530, loss: 0.019423531368374825
2023-01-23 03:20:25.123837: step: 540/530, loss: 0.009538078680634499
2023-01-23 03:20:26.312658: step: 544/530, loss: 0.0006220817449502647
2023-01-23 03:20:27.520172: step: 548/530, loss: 0.033678580075502396
2023-01-23 03:20:28.686684: step: 552/530, loss: 0.0038746357895433903
2023-01-23 03:20:29.852500: step: 556/530, loss: 0.03186088055372238
2023-01-23 03:20:30.974832: step: 560/530, loss: 0.00124359130859375
2023-01-23 03:20:32.204170: step: 564/530, loss: 0.017687320709228516
2023-01-23 03:20:33.371621: step: 568/530, loss: 0.03152046352624893
2023-01-23 03:20:34.486584: step: 572/530, loss: 0.0008993148803710938
2023-01-23 03:20:35.661648: step: 576/530, loss: 0.00567283621057868
2023-01-23 03:20:36.822653: step: 580/530, loss: 0.0018933296669274569
2023-01-23 03:20:37.973883: step: 584/530, loss: 0.0005732536665163934
2023-01-23 03:20:39.130180: step: 588/530, loss: 0.0028955459129065275
2023-01-23 03:20:40.299980: step: 592/530, loss: 0.00383510603569448
2023-01-23 03:20:41.431413: step: 596/530, loss: 0.0005003213882446289
2023-01-23 03:20:42.605316: step: 600/530, loss: 0.038018230348825455
2023-01-23 03:20:43.807032: step: 604/530, loss: 0.06990861892700195
2023-01-23 03:20:44.986291: step: 608/530, loss: 0.05002880096435547
2023-01-23 03:20:46.116248: step: 612/530, loss: 0.02055969275534153
2023-01-23 03:20:47.277150: step: 616/530, loss: 0.01705198548734188
2023-01-23 03:20:48.400523: step: 620/530, loss: 0.0005360603099688888
2023-01-23 03:20:49.576079: step: 624/530, loss: 0.3124147355556488
2023-01-23 03:20:50.740823: step: 628/530, loss: 0.0058685303665697575
2023-01-23 03:20:51.928430: step: 632/530, loss: 0.015434646978974342
2023-01-23 03:20:53.141775: step: 636/530, loss: 0.01999836042523384
2023-01-23 03:20:54.280682: step: 640/530, loss: 0.02104015462100506
2023-01-23 03:20:55.423202: step: 644/530, loss: 0.009812641888856888
2023-01-23 03:20:56.585217: step: 648/530, loss: 0.0021873475052416325
2023-01-23 03:20:57.790201: step: 652/530, loss: 0.00022878649178892374
2023-01-23 03:20:58.938392: step: 656/530, loss: 0.00044288637582212687
2023-01-23 03:21:00.074716: step: 660/530, loss: 0.0016105652321130037
2023-01-23 03:21:01.280338: step: 664/530, loss: 0.014573002234101295
2023-01-23 03:21:02.443681: step: 668/530, loss: 4.77790817967616e-05
2023-01-23 03:21:03.601532: step: 672/530, loss: 0.00555000314489007
2023-01-23 03:21:04.770350: step: 676/530, loss: 0.0013641357654705644
2023-01-23 03:21:05.941923: step: 680/530, loss: 0.051749229431152344
2023-01-23 03:21:07.135670: step: 684/530, loss: 0.0006423949962481856
2023-01-23 03:21:08.347339: step: 688/530, loss: 0.08304862678050995
2023-01-23 03:21:09.526388: step: 692/530, loss: 0.0011313437717035413
2023-01-23 03:21:10.699286: step: 696/530, loss: 0.04104633256793022
2023-01-23 03:21:11.906270: step: 700/530, loss: 0.04244270548224449
2023-01-23 03:21:13.052449: step: 704/530, loss: 0.01815938949584961
2023-01-23 03:21:14.242099: step: 708/530, loss: 0.016731834039092064
2023-01-23 03:21:15.453957: step: 712/530, loss: 0.030443955212831497
2023-01-23 03:21:16.646856: step: 716/530, loss: 0.040987778455019
2023-01-23 03:21:17.829917: step: 720/530, loss: 0.08112120628356934
2023-01-23 03:21:18.938217: step: 724/530, loss: 0.009659003466367722
2023-01-23 03:21:20.119840: step: 728/530, loss: 0.0007363319164142013
2023-01-23 03:21:21.290817: step: 732/530, loss: 0.0635766014456749
2023-01-23 03:21:22.465345: step: 736/530, loss: 0.004429626744240522
2023-01-23 03:21:23.623527: step: 740/530, loss: 0.01755695417523384
2023-01-23 03:21:24.803437: step: 744/530, loss: 0.030556773766875267
2023-01-23 03:21:25.973683: step: 748/530, loss: 0.005811882205307484
2023-01-23 03:21:27.133383: step: 752/530, loss: -2.765655517578125e-05
2023-01-23 03:21:28.307626: step: 756/530, loss: 0.008227873593568802
2023-01-23 03:21:29.433012: step: 760/530, loss: 0.0046897889114916325
2023-01-23 03:21:30.620549: step: 764/530, loss: 0.0001104354887502268
2023-01-23 03:21:31.783364: step: 768/530, loss: 0.0017789840931072831
2023-01-23 03:21:32.962386: step: 772/530, loss: 0.0018478394486010075
2023-01-23 03:21:34.124287: step: 776/530, loss: 0.03618679195642471
2023-01-23 03:21:35.315405: step: 780/530, loss: 0.018131066113710403
2023-01-23 03:21:36.515406: step: 784/530, loss: 0.034902192652225494
2023-01-23 03:21:37.686004: step: 788/530, loss: 0.0006243705865927041
2023-01-23 03:21:38.886381: step: 792/530, loss: 0.0643729642033577
2023-01-23 03:21:40.073121: step: 796/530, loss: 0.03406066820025444
2023-01-23 03:21:41.280159: step: 800/530, loss: 0.026997948065400124
2023-01-23 03:21:42.432414: step: 804/530, loss: 0.005030632484704256
2023-01-23 03:21:43.594811: step: 808/530, loss: 0.003253269474953413
2023-01-23 03:21:44.735397: step: 812/530, loss: 0.020756054669618607
2023-01-23 03:21:45.889730: step: 816/530, loss: 0.0016414641868323088
2023-01-23 03:21:47.026162: step: 820/530, loss: 0.04311408847570419
2023-01-23 03:21:48.222104: step: 824/530, loss: 4.4822695599577855e-06
2023-01-23 03:21:49.422387: step: 828/530, loss: 0.0008703708299435675
2023-01-23 03:21:50.692708: step: 832/530, loss: 0.0015067100757732987
2023-01-23 03:21:51.815604: step: 836/530, loss: 0.00022792816162109375
2023-01-23 03:21:52.995021: step: 840/530, loss: 0.014737176708877087
2023-01-23 03:21:54.163793: step: 844/530, loss: 0.001051950384862721
2023-01-23 03:21:55.317479: step: 848/530, loss: 0.0041065216064453125
2023-01-23 03:21:56.507551: step: 852/530, loss: 0.04677295684814453
2023-01-23 03:21:57.694441: step: 856/530, loss: 0.0018159865867346525
2023-01-23 03:21:58.879967: step: 860/530, loss: 0.007681942544877529
2023-01-23 03:22:00.039024: step: 864/530, loss: 8.316040475619957e-05
2023-01-23 03:22:01.192382: step: 868/530, loss: 0.0026844025123864412
2023-01-23 03:22:02.376583: step: 872/530, loss: 0.0024504661560058594
2023-01-23 03:22:03.534098: step: 876/530, loss: 0.00020074844360351562
2023-01-23 03:22:04.733677: step: 880/530, loss: 0.0007545471307821572
2023-01-23 03:22:05.892235: step: 884/530, loss: 0.005092716310173273
2023-01-23 03:22:07.091822: step: 888/530, loss: 0.0020111084450036287
2023-01-23 03:22:08.260807: step: 892/530, loss: 0.002813720842823386
2023-01-23 03:22:09.412464: step: 896/530, loss: 0.003751564072445035
2023-01-23 03:22:10.575706: step: 900/530, loss: 0.0003544807550497353
2023-01-23 03:22:11.812877: step: 904/530, loss: 0.005286312196403742
2023-01-23 03:22:13.025326: step: 908/530, loss: 0.03681468963623047
2023-01-23 03:22:14.217332: step: 912/530, loss: 0.014543152414262295
2023-01-23 03:22:15.356133: step: 916/530, loss: 0.026371479034423828
2023-01-23 03:22:16.553470: step: 920/530, loss: 0.0037866593338549137
2023-01-23 03:22:17.742861: step: 924/530, loss: 0.001305580255575478
2023-01-23 03:22:18.931289: step: 928/530, loss: 0.007343864534050226
2023-01-23 03:22:20.150011: step: 932/530, loss: 0.0003808975452557206
2023-01-23 03:22:21.368374: step: 936/530, loss: 8.630752563476562e-05
2023-01-23 03:22:22.593281: step: 940/530, loss: 0.005280685611069202
2023-01-23 03:22:23.744276: step: 944/530, loss: 0.03523607552051544
2023-01-23 03:22:24.907357: step: 948/530, loss: 0.007588863838464022
2023-01-23 03:22:26.086936: step: 952/530, loss: 0.024454500526189804
2023-01-23 03:22:27.276901: step: 956/530, loss: 0.00014591217041015625
2023-01-23 03:22:28.442942: step: 960/530, loss: 0.0022132874000817537
2023-01-23 03:22:29.592978: step: 964/530, loss: 0.0037399292923510075
2023-01-23 03:22:30.757405: step: 968/530, loss: 0.002145147416740656
2023-01-23 03:22:31.919968: step: 972/530, loss: 0.019171716645359993
2023-01-23 03:22:33.152592: step: 976/530, loss: 0.00036525726318359375
2023-01-23 03:22:34.337645: step: 980/530, loss: 6.442069570766762e-05
2023-01-23 03:22:35.503791: step: 984/530, loss: 0.0010175704956054688
2023-01-23 03:22:36.752502: step: 988/530, loss: 0.003712558886036277
2023-01-23 03:22:37.917082: step: 992/530, loss: 0.006087112706154585
2023-01-23 03:22:39.122662: step: 996/530, loss: -3.6716460272145923e-06
2023-01-23 03:22:40.302037: step: 1000/530, loss: 0.02530221827328205
2023-01-23 03:22:41.475889: step: 1004/530, loss: 0.0005221366882324219
2023-01-23 03:22:42.637454: step: 1008/530, loss: 9.51766996877268e-05
2023-01-23 03:22:43.810041: step: 1012/530, loss: 0.022327804937958717
2023-01-23 03:22:44.959976: step: 1016/530, loss: 0.0017938613891601562
2023-01-23 03:22:46.118378: step: 1020/530, loss: 0.0002803802490234375
2023-01-23 03:22:47.269616: step: 1024/530, loss: 0.0038398741744458675
2023-01-23 03:22:48.434028: step: 1028/530, loss: 0.0003364562871865928
2023-01-23 03:22:49.610209: step: 1032/530, loss: 0.002929878421127796
2023-01-23 03:22:50.754395: step: 1036/530, loss: 0.00024881362332962453
2023-01-23 03:22:51.964576: step: 1040/530, loss: 0.00012168884859420359
2023-01-23 03:22:53.102583: step: 1044/530, loss: 0.00022702215937897563
2023-01-23 03:22:54.278421: step: 1048/530, loss: 0.025398733094334602
2023-01-23 03:22:55.448950: step: 1052/530, loss: 0.16058588027954102
2023-01-23 03:22:56.581196: step: 1056/530, loss: 1.735687328618951e-05
2023-01-23 03:22:57.732369: step: 1060/530, loss: 0.009137011133134365
2023-01-23 03:22:58.917241: step: 1064/530, loss: 0.002721595810726285
2023-01-23 03:23:00.100070: step: 1068/530, loss: 0.020731544122099876
2023-01-23 03:23:01.288670: step: 1072/530, loss: 0.002322292421013117
2023-01-23 03:23:02.471385: step: 1076/530, loss: 0.0025777816772460938
2023-01-23 03:23:03.664752: step: 1080/530, loss: 0.00026159288245253265
2023-01-23 03:23:04.825870: step: 1084/530, loss: 3.1948089599609375e-05
2023-01-23 03:23:06.009555: step: 1088/530, loss: 0.021294020116329193
2023-01-23 03:23:07.189815: step: 1092/530, loss: 0.04923572763800621
2023-01-23 03:23:08.407121: step: 1096/530, loss: 0.004612350836396217
2023-01-23 03:23:09.653155: step: 1100/530, loss: 9.498596045887098e-05
2023-01-23 03:23:10.812850: step: 1104/530, loss: 0.004296588711440563
2023-01-23 03:23:12.026410: step: 1108/530, loss: 0.0004343986511230469
2023-01-23 03:23:13.185950: step: 1112/530, loss: 0.00036277773324400187
2023-01-23 03:23:14.356888: step: 1116/530, loss: 0.20355768501758575
2023-01-23 03:23:15.516920: step: 1120/530, loss: 0.0001848220854299143
2023-01-23 03:23:16.681782: step: 1124/530, loss: 0.0007444382063113153
2023-01-23 03:23:17.895460: step: 1128/530, loss: 0.00036296845064498484
2023-01-23 03:23:19.087352: step: 1132/530, loss: 2.0885467165498994e-05
2023-01-23 03:23:20.283163: step: 1136/530, loss: 0.0006978035089559853
2023-01-23 03:23:21.469912: step: 1140/530, loss: 0.00013573169417213649
2023-01-23 03:23:22.631415: step: 1144/530, loss: 0.012542152777314186
2023-01-23 03:23:23.777246: step: 1148/530, loss: 0.00011076927330577746
2023-01-23 03:23:24.931538: step: 1152/530, loss: 0.008348274044692516
2023-01-23 03:23:26.122365: step: 1156/530, loss: 0.0007147789583541453
2023-01-23 03:23:27.307865: step: 1160/530, loss: 0.011353492736816406
2023-01-23 03:23:28.490261: step: 1164/530, loss: 0.021475983783602715
2023-01-23 03:23:29.650183: step: 1168/530, loss: 7.009506225585938e-05
2023-01-23 03:23:30.803813: step: 1172/530, loss: 0.0011430740123614669
2023-01-23 03:23:31.980250: step: 1176/530, loss: 0.028866050764918327
2023-01-23 03:23:33.180766: step: 1180/530, loss: 8.516311936546117e-05
2023-01-23 03:23:34.332508: step: 1184/530, loss: 0.0003108978271484375
2023-01-23 03:23:35.472112: step: 1188/530, loss: 5.860329110873863e-05
2023-01-23 03:23:36.639572: step: 1192/530, loss: 0.00028548241243697703
2023-01-23 03:23:37.769187: step: 1196/530, loss: 0.006782818119972944
2023-01-23 03:23:38.909473: step: 1200/530, loss: 0.0011333465809002519
2023-01-23 03:23:40.095752: step: 1204/530, loss: 0.023638440296053886
2023-01-23 03:23:41.240318: step: 1208/530, loss: 4.901886131847277e-05
2023-01-23 03:23:42.490534: step: 1212/530, loss: 0.008943939581513405
2023-01-23 03:23:43.631827: step: 1216/530, loss: 0.021670913323760033
2023-01-23 03:23:44.767524: step: 1220/530, loss: 0.007708454504609108
2023-01-23 03:23:45.993203: step: 1224/530, loss: 0.004290103912353516
2023-01-23 03:23:47.178359: step: 1228/530, loss: 0.05924654006958008
2023-01-23 03:23:48.358198: step: 1232/530, loss: 0.0024260522332042456
2023-01-23 03:23:49.493847: step: 1236/530, loss: 0.00013074875460006297
2023-01-23 03:23:50.687410: step: 1240/530, loss: 0.011115646921098232
2023-01-23 03:23:51.913057: step: 1244/530, loss: 0.01061868667602539
2023-01-23 03:23:53.138599: step: 1248/530, loss: 0.0015537738800048828
2023-01-23 03:23:54.321325: step: 1252/530, loss: 0.0038841248024255037
2023-01-23 03:23:55.465481: step: 1256/530, loss: 0.10177478939294815
2023-01-23 03:23:56.641862: step: 1260/530, loss: 0.0012756347423419356
2023-01-23 03:23:57.795852: step: 1264/530, loss: 0.0008525848388671875
2023-01-23 03:23:58.994423: step: 1268/530, loss: 0.028227806091308594
2023-01-23 03:24:00.181465: step: 1272/530, loss: 0.0022107125259935856
2023-01-23 03:24:01.359679: step: 1276/530, loss: 0.002467632293701172
2023-01-23 03:24:02.513937: step: 1280/530, loss: 0.04509372636675835
2023-01-23 03:24:03.706166: step: 1284/530, loss: 0.0008831977611407638
2023-01-23 03:24:04.890212: step: 1288/530, loss: 0.00166149134747684
2023-01-23 03:24:06.058307: step: 1292/530, loss: 0.029405975714325905
2023-01-23 03:24:07.220873: step: 1296/530, loss: 0.0039193155243992805
2023-01-23 03:24:08.411648: step: 1300/530, loss: 0.014392471872270107
2023-01-23 03:24:09.579644: step: 1304/530, loss: 0.001334381173364818
2023-01-23 03:24:10.769581: step: 1308/530, loss: 0.03337745741009712
2023-01-23 03:24:11.941674: step: 1312/530, loss: 6.341934204101562e-05
2023-01-23 03:24:13.092945: step: 1316/530, loss: 0.27916595339775085
2023-01-23 03:24:14.273568: step: 1320/530, loss: 0.00081806187517941
2023-01-23 03:24:15.444985: step: 1324/530, loss: 0.008203888311982155
2023-01-23 03:24:16.607438: step: 1328/530, loss: 0.0007153988117352128
2023-01-23 03:24:17.780180: step: 1332/530, loss: 0.003934287931770086
2023-01-23 03:24:18.942534: step: 1336/530, loss: 0.009502124972641468
2023-01-23 03:24:20.103891: step: 1340/530, loss: 8.106231689453125e-05
2023-01-23 03:24:21.303065: step: 1344/530, loss: 0.19960841536521912
2023-01-23 03:24:22.569137: step: 1348/530, loss: 0.01688537746667862
2023-01-23 03:24:23.737561: step: 1352/530, loss: 0.0016566276317462325
2023-01-23 03:24:24.889778: step: 1356/530, loss: 0.06125936657190323
2023-01-23 03:24:26.101328: step: 1360/530, loss: 0.011808013543486595
2023-01-23 03:24:27.271058: step: 1364/530, loss: 0.0034175217151641846
2023-01-23 03:24:28.433189: step: 1368/530, loss: 0.0020648958161473274
2023-01-23 03:24:29.600824: step: 1372/530, loss: 0.0003074645937886089
2023-01-23 03:24:30.753555: step: 1376/530, loss: 0.1559613198041916
2023-01-23 03:24:31.936027: step: 1380/530, loss: 0.0005715370061807334
2023-01-23 03:24:33.083339: step: 1384/530, loss: 1.5544890629826114e-05
2023-01-23 03:24:34.266459: step: 1388/530, loss: 7.820130122127011e-06
2023-01-23 03:24:35.434443: step: 1392/530, loss: 0.001327133271843195
2023-01-23 03:24:36.598738: step: 1396/530, loss: 0.003715706057846546
2023-01-23 03:24:37.758820: step: 1400/530, loss: 5.054473876953125e-05
2023-01-23 03:24:38.957684: step: 1404/530, loss: 0.012380409985780716
2023-01-23 03:24:40.087927: step: 1408/530, loss: 0.006866169162094593
2023-01-23 03:24:41.241795: step: 1412/530, loss: 0.03629784658551216
2023-01-23 03:24:42.427514: step: 1416/530, loss: 0.0019253729842603207
2023-01-23 03:24:43.603255: step: 1420/530, loss: 0.00010805130295921117
2023-01-23 03:24:44.791934: step: 1424/530, loss: 0.06991958618164062
2023-01-23 03:24:45.957682: step: 1428/530, loss: 0.0049078939482569695
2023-01-23 03:24:47.105743: step: 1432/530, loss: 0.07744617015123367
2023-01-23 03:24:48.263978: step: 1436/530, loss: 0.00035533905611373484
2023-01-23 03:24:49.475850: step: 1440/530, loss: 0.04077615961432457
2023-01-23 03:24:50.649671: step: 1444/530, loss: 0.00399284390732646
2023-01-23 03:24:51.828021: step: 1448/530, loss: 0.0034280777908861637
2023-01-23 03:24:52.994617: step: 1452/530, loss: 0.008730793371796608
2023-01-23 03:24:54.143229: step: 1456/530, loss: 0.0009521484607830644
2023-01-23 03:24:55.327581: step: 1460/530, loss: 0.018700361251831055
2023-01-23 03:24:56.528791: step: 1464/530, loss: 0.004648399073630571
2023-01-23 03:24:57.699979: step: 1468/530, loss: 0.004745769780129194
2023-01-23 03:24:58.837969: step: 1472/530, loss: 0.023762892931699753
2023-01-23 03:25:00.037586: step: 1476/530, loss: 2.28881845032447e-06
2023-01-23 03:25:01.170675: step: 1480/530, loss: 0.0011127472389489412
2023-01-23 03:25:02.373801: step: 1484/530, loss: 0.007662534713745117
2023-01-23 03:25:03.596108: step: 1488/530, loss: 0.0008435249328613281
2023-01-23 03:25:04.731926: step: 1492/530, loss: 0.00045281497295945883
2023-01-23 03:25:05.866488: step: 1496/530, loss: 0.017081070691347122
2023-01-23 03:25:07.062417: step: 1500/530, loss: 0.007808685302734375
2023-01-23 03:25:08.192310: step: 1504/530, loss: 0.0007936477777548134
2023-01-23 03:25:09.389620: step: 1508/530, loss: 0.04832973703742027
2023-01-23 03:25:10.576317: step: 1512/530, loss: 0.08074036240577698
2023-01-23 03:25:11.748800: step: 1516/530, loss: 0.00397148123010993
2023-01-23 03:25:12.902434: step: 1520/530, loss: 0.012388801202178001
2023-01-23 03:25:14.084789: step: 1524/530, loss: 0.03733024746179581
2023-01-23 03:25:15.244794: step: 1528/530, loss: 0.05975513160228729
2023-01-23 03:25:16.457836: step: 1532/530, loss: 4.1651728679426014e-05
2023-01-23 03:25:17.625948: step: 1536/530, loss: 0.011095809750258923
2023-01-23 03:25:18.836107: step: 1540/530, loss: 0.0012161254417151213
2023-01-23 03:25:20.072427: step: 1544/530, loss: 0.0009416580433025956
2023-01-23 03:25:21.220583: step: 1548/530, loss: 0.001074504922144115
2023-01-23 03:25:22.394411: step: 1552/530, loss: 0.009495258331298828
2023-01-23 03:25:23.542288: step: 1556/530, loss: 0.004488920792937279
2023-01-23 03:25:24.733114: step: 1560/530, loss: 0.00022668838209938258
2023-01-23 03:25:25.917651: step: 1564/530, loss: 0.005683327093720436
2023-01-23 03:25:27.071206: step: 1568/530, loss: 0.02956237830221653
2023-01-23 03:25:28.244585: step: 1572/530, loss: 3.929138256353326e-05
2023-01-23 03:25:29.421518: step: 1576/530, loss: 0.0024566650390625
2023-01-23 03:25:30.570736: step: 1580/530, loss: 0.00012607575627043843
2023-01-23 03:25:31.825181: step: 1584/530, loss: 0.0028226852882653475
2023-01-23 03:25:32.997857: step: 1588/530, loss: 0.005423259921371937
2023-01-23 03:25:34.188500: step: 1592/530, loss: 0.0004559516964945942
2023-01-23 03:25:35.347686: step: 1596/530, loss: 0.00016479492478538305
2023-01-23 03:25:36.532886: step: 1600/530, loss: 0.0024972916580736637
2023-01-23 03:25:37.695004: step: 1604/530, loss: 0.0044796462170779705
2023-01-23 03:25:38.853994: step: 1608/530, loss: 0.003361702198162675
2023-01-23 03:25:40.023904: step: 1612/530, loss: 1.964569128176663e-05
2023-01-23 03:25:41.181934: step: 1616/530, loss: 0.02086505852639675
2023-01-23 03:25:42.391287: step: 1620/530, loss: 0.0014811038272455335
2023-01-23 03:25:43.548805: step: 1624/530, loss: 4.692077709478326e-05
2023-01-23 03:25:44.703731: step: 1628/530, loss: 0.001530551933683455
2023-01-23 03:25:45.902269: step: 1632/530, loss: 5.4645537602482364e-05
2023-01-23 03:25:47.067762: step: 1636/530, loss: 0.028560448437929153
2023-01-23 03:25:48.215729: step: 1640/530, loss: 0.000335884076775983
2023-01-23 03:25:49.377869: step: 1644/530, loss: 0.0003836631658487022
2023-01-23 03:25:50.512761: step: 1648/530, loss: 5.722045557376987e-07
2023-01-23 03:25:51.708846: step: 1652/530, loss: 0.03167577460408211
2023-01-23 03:25:52.850463: step: 1656/530, loss: 0.011873818002641201
2023-01-23 03:25:54.008690: step: 1660/530, loss: 0.0022684098221361637
2023-01-23 03:25:55.220299: step: 1664/530, loss: 3.6716461181640625e-05
2023-01-23 03:25:56.424862: step: 1668/530, loss: 0.007731437683105469
2023-01-23 03:25:57.590542: step: 1672/530, loss: 0.0006959915044717491
2023-01-23 03:25:58.732586: step: 1676/530, loss: 0.0001160621686722152
2023-01-23 03:25:59.913305: step: 1680/530, loss: 0.003297233721241355
2023-01-23 03:26:01.132061: step: 1684/530, loss: 0.07754363864660263
2023-01-23 03:26:02.305097: step: 1688/530, loss: 0.01988682709634304
2023-01-23 03:26:03.465827: step: 1692/530, loss: 0.6587401628494263
2023-01-23 03:26:04.629610: step: 1696/530, loss: 2.4890900022001006e-05
2023-01-23 03:26:05.786908: step: 1700/530, loss: 0.07908801734447479
2023-01-23 03:26:07.014858: step: 1704/530, loss: 0.00016698836407158524
2023-01-23 03:26:08.192472: step: 1708/530, loss: 0.010745239444077015
2023-01-23 03:26:09.387180: step: 1712/530, loss: 0.0034881592728197575
2023-01-23 03:26:10.559302: step: 1716/530, loss: 0.006335449405014515
2023-01-23 03:26:11.799255: step: 1720/530, loss: 1.087188684323337e-05
2023-01-23 03:26:12.980808: step: 1724/530, loss: 0.0004985809209756553
2023-01-23 03:26:14.117863: step: 1728/530, loss: 0.0007890701526775956
2023-01-23 03:26:15.280150: step: 1732/530, loss: 0.00017390251741744578
2023-01-23 03:26:16.470506: step: 1736/530, loss: 0.004042911808937788
2023-01-23 03:26:17.656496: step: 1740/530, loss: 0.010141182690858841
2023-01-23 03:26:18.818595: step: 1744/530, loss: 2.398491051280871e-05
2023-01-23 03:26:20.027584: step: 1748/530, loss: 0.0002347946137888357
2023-01-23 03:26:21.209194: step: 1752/530, loss: 0.010663891211152077
2023-01-23 03:26:22.359375: step: 1756/530, loss: 0.007246876135468483
2023-01-23 03:26:23.599710: step: 1760/530, loss: 0.18355527520179749
2023-01-23 03:26:24.765815: step: 1764/530, loss: 0.0003510475507937372
2023-01-23 03:26:25.932927: step: 1768/530, loss: 0.00040884019108489156
2023-01-23 03:26:27.125425: step: 1772/530, loss: 0.002647495362907648
2023-01-23 03:26:28.309814: step: 1776/530, loss: 0.01062865275889635
2023-01-23 03:26:29.464725: step: 1780/530, loss: 0.0031936645973473787
2023-01-23 03:26:30.654009: step: 1784/530, loss: 0.0019193649059161544
2023-01-23 03:26:31.847592: step: 1788/530, loss: -4.196167537884321e-06
2023-01-23 03:26:33.018926: step: 1792/530, loss: 0.00018072128295898438
2023-01-23 03:26:34.187829: step: 1796/530, loss: 0.010405254550278187
2023-01-23 03:26:35.372174: step: 1800/530, loss: 0.0006045341724529862
2023-01-23 03:26:36.529303: step: 1804/530, loss: 0.0001813888520700857
2023-01-23 03:26:37.764140: step: 1808/530, loss: 0.0020097733940929174
2023-01-23 03:26:38.944174: step: 1812/530, loss: 0.0071659088134765625
2023-01-23 03:26:40.171219: step: 1816/530, loss: 0.08185024559497833
2023-01-23 03:26:41.336203: step: 1820/530, loss: 0.00233039865270257
2023-01-23 03:26:42.523796: step: 1824/530, loss: 0.0022067308891564608
2023-01-23 03:26:43.710001: step: 1828/530, loss: 0.015968896448612213
2023-01-23 03:26:44.893794: step: 1832/530, loss: 6.546974327648059e-05
2023-01-23 03:26:46.030344: step: 1836/530, loss: 0.00022449492826126516
2023-01-23 03:26:47.223116: step: 1840/530, loss: -6.9141387939453125e-06
2023-01-23 03:26:48.404432: step: 1844/530, loss: 0.0005926132434979081
2023-01-23 03:26:49.568716: step: 1848/530, loss: 0.0011260986793786287
2023-01-23 03:26:50.715401: step: 1852/530, loss: 0.0034766674507409334
2023-01-23 03:26:51.855309: step: 1856/530, loss: 0.011931801214814186
2023-01-23 03:26:53.002576: step: 1860/530, loss: 0.017504312098026276
2023-01-23 03:26:54.171244: step: 1864/530, loss: 0.00032329559326171875
2023-01-23 03:26:55.329230: step: 1868/530, loss: 3.63349899998866e-05
2023-01-23 03:26:56.499121: step: 1872/530, loss: 0.017606163397431374
2023-01-23 03:26:57.680526: step: 1876/530, loss: 0.0029344558715820312
2023-01-23 03:26:58.860659: step: 1880/530, loss: 2.6607514882925898e-05
2023-01-23 03:27:00.056276: step: 1884/530, loss: 0.00019378663273528218
2023-01-23 03:27:01.249142: step: 1888/530, loss: 0.00064849853515625
2023-01-23 03:27:02.441103: step: 1892/530, loss: 0.10974311828613281
2023-01-23 03:27:03.582447: step: 1896/530, loss: 0.0019610405433923006
2023-01-23 03:27:04.764357: step: 1900/530, loss: 0.0015119552845135331
2023-01-23 03:27:05.934269: step: 1904/530, loss: 0.00703353900462389
2023-01-23 03:27:07.093643: step: 1908/530, loss: 0.002143478486686945
2023-01-23 03:27:08.313891: step: 1912/530, loss: 0.03368987888097763
2023-01-23 03:27:09.458552: step: 1916/530, loss: 0.0006131172413006425
2023-01-23 03:27:10.638761: step: 1920/530, loss: 0.0030071258079260588
2023-01-23 03:27:11.820882: step: 1924/530, loss: 0.02026844024658203
2023-01-23 03:27:12.987217: step: 1928/530, loss: 0.0004669189511332661
2023-01-23 03:27:14.165372: step: 1932/530, loss: 0.06076173856854439
2023-01-23 03:27:15.339863: step: 1936/530, loss: 0.006413459777832031
2023-01-23 03:27:16.528193: step: 1940/530, loss: 0.0016765595646575093
2023-01-23 03:27:17.735421: step: 1944/530, loss: 0.3521394729614258
2023-01-23 03:27:18.860390: step: 1948/530, loss: 0.025275137275457382
2023-01-23 03:27:20.035110: step: 1952/530, loss: 0.0017601012950763106
2023-01-23 03:27:21.196581: step: 1956/530, loss: 0.001084995223209262
2023-01-23 03:27:22.375768: step: 1960/530, loss: 0.0307159423828125
2023-01-23 03:27:23.521227: step: 1964/530, loss: 0.03825478255748749
2023-01-23 03:27:24.696903: step: 1968/530, loss: 0.01157302875071764
2023-01-23 03:27:25.822038: step: 1972/530, loss: 0.37308740615844727
2023-01-23 03:27:26.990688: step: 1976/530, loss: 0.00114269251935184
2023-01-23 03:27:28.180846: step: 1980/530, loss: 0.0013395309215411544
2023-01-23 03:27:29.352167: step: 1984/530, loss: 2.1457672119140625e-06
2023-01-23 03:27:30.508167: step: 1988/530, loss: 0.0010505676036700606
2023-01-23 03:27:31.685830: step: 1992/530, loss: 0.00013828279043082148
2023-01-23 03:27:32.845098: step: 1996/530, loss: 4.196166628389619e-06
2023-01-23 03:27:34.010117: step: 2000/530, loss: 0.0009437561384402215
2023-01-23 03:27:35.187326: step: 2004/530, loss: 0.016751958057284355
2023-01-23 03:27:36.374345: step: 2008/530, loss: 0.0018543243641033769
2023-01-23 03:27:37.500216: step: 2012/530, loss: 0.001955318497493863
2023-01-23 03:27:38.698458: step: 2016/530, loss: 0.0036637308076024055
2023-01-23 03:27:39.889645: step: 2020/530, loss: 0.007431983947753906
2023-01-23 03:27:41.053833: step: 2024/530, loss: 0.0022258758544921875
2023-01-23 03:27:42.202615: step: 2028/530, loss: 0.004039120860397816
2023-01-23 03:27:43.378732: step: 2032/530, loss: 0.08428115397691727
2023-01-23 03:27:44.569528: step: 2036/530, loss: 0.013484669849276543
2023-01-23 03:27:45.733763: step: 2040/530, loss: 0.06308307498693466
2023-01-23 03:27:46.944439: step: 2044/530, loss: 0.6312940716743469
2023-01-23 03:27:48.080753: step: 2048/530, loss: 4.100799742445815e-06
2023-01-23 03:27:49.274445: step: 2052/530, loss: 0.00032596586970612407
2023-01-23 03:27:50.435865: step: 2056/530, loss: 0.0023956298828125
2023-01-23 03:27:51.614576: step: 2060/530, loss: 0.005625915713608265
2023-01-23 03:27:52.768651: step: 2064/530, loss: 8.935928053688258e-05
2023-01-23 03:27:53.905345: step: 2068/530, loss: 0.283809095621109
2023-01-23 03:27:55.108174: step: 2072/530, loss: 0.006003189366310835
2023-01-23 03:27:56.265133: step: 2076/530, loss: 0.007678413763642311
2023-01-23 03:27:57.410653: step: 2080/530, loss: 0.0034894943237304688
2023-01-23 03:27:58.594286: step: 2084/530, loss: 0.0008052826160565019
2023-01-23 03:27:59.765316: step: 2088/530, loss: 0.01092443522065878
2023-01-23 03:28:00.954591: step: 2092/530, loss: 0.001795959542505443
2023-01-23 03:28:02.146249: step: 2096/530, loss: 0.007378959562629461
2023-01-23 03:28:03.334779: step: 2100/530, loss: 0.007089043036103249
2023-01-23 03:28:04.531424: step: 2104/530, loss: 0.023382043465971947
2023-01-23 03:28:05.712035: step: 2108/530, loss: 0.0007674216758459806
2023-01-23 03:28:06.929448: step: 2112/530, loss: 0.020740794017910957
2023-01-23 03:28:08.118934: step: 2116/530, loss: 0.0013728141784667969
2023-01-23 03:28:09.283621: step: 2120/530, loss: 0.00037031175452284515
==================================================
Loss: 0.021
--------------------
Dev: {'event': {'p': 0.5765765765765766, 'r': 0.7669773635153129, 'f1': 0.6582857142857143}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
Test: {'event': {'p': 0.6460622710622711, 'r': 0.8113858539390454, 'f1': 0.7193474381850625}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
Chinese: {'event': {'p': 0.5494505494505495, 'r': 0.9259259259259259, 'f1': 0.6896551724137931}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
Korean: {'event': {'p': 0.5454545454545454, 'r': 0.5714285714285714, 'f1': 0.5581395348837208}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
Russian: {'event': {'p': 0.41818181818181815, 'r': 0.6388888888888888, 'f1': 0.5054945054945054}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6065057712486883, 'r': 0.7696404793608522, 'f1': 0.6784037558685445}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
Eng Test for Chinese: {'event': {'p': 0.6643026004728132, 'r': 0.8079355951696378, 'f1': 0.7291126102750389}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
Sample Chinese: {'event': {'p': 0.6024096385542169, 'r': 0.9259259259259259, 'f1': 0.7299270072992702}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5733990147783251, 'r': 0.7749667110519307, 'f1': 0.6591166477916196}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Eng Test for Korean: {'event': {'p': 0.6218005295675199, 'r': 0.8102357676825762, 'f1': 0.7036204744069912}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Sample Korean: {'event': {'p': 0.6417910447761194, 'r': 0.6825396825396826, 'f1': 0.6615384615384614}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5951882845188284, 'r': 0.7576564580559254, 'f1': 0.6666666666666666}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Eng Test for Russian: {'event': {'p': 0.6663405088062623, 'r': 0.7832087406555491, 'f1': 0.7200634417129264}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Sample Russian: {'event': {'p': 0.5, 'r': 0.6666666666666666, 'f1': 0.5714285714285715}, '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 03:28:52.140355: step: 4/530, loss: 0.0014701844193041325
2023-01-23 03:28:53.317615: step: 8/530, loss: 1.0967254638671875e-05
2023-01-23 03:28:54.473622: step: 12/530, loss: 8.916854858398438e-05
2023-01-23 03:28:55.674836: step: 16/530, loss: 9.040832810569555e-05
2023-01-23 03:28:56.836100: step: 20/530, loss: 0.004154628608375788
2023-01-23 03:28:58.004464: step: 24/530, loss: 5.235671778791584e-05
2023-01-23 03:28:59.171746: step: 28/530, loss: 0.0028720854315906763
2023-01-23 03:29:00.340522: step: 32/530, loss: 0.0003357887326274067
2023-01-23 03:29:01.525403: step: 36/530, loss: 0.009093094617128372
2023-01-23 03:29:02.666928: step: 40/530, loss: 0.003338289214298129
2023-01-23 03:29:03.837291: step: 44/530, loss: 0.0037233352195471525
2023-01-23 03:29:05.008525: step: 48/530, loss: 1.5449522834387608e-05
2023-01-23 03:29:06.169832: step: 52/530, loss: 7.095337059581652e-05
2023-01-23 03:29:07.329546: step: 56/530, loss: 0.004692649934440851
2023-01-23 03:29:08.511835: step: 60/530, loss: 0.0011865616543218493
2023-01-23 03:29:09.649155: step: 64/530, loss: 0.023685075342655182
2023-01-23 03:29:10.836599: step: 68/530, loss: 0.008388710208237171
2023-01-23 03:29:12.037231: step: 72/530, loss: 0.014268017373979092
2023-01-23 03:29:13.213910: step: 76/530, loss: 0.0016756057739257812
2023-01-23 03:29:14.370981: step: 80/530, loss: 4.29630272265058e-05
2023-01-23 03:29:15.528257: step: 84/530, loss: 0.0005746841197833419
2023-01-23 03:29:16.669036: step: 88/530, loss: 0.5348788499832153
2023-01-23 03:29:17.845679: step: 92/530, loss: 0.03282108157873154
2023-01-23 03:29:19.022049: step: 96/530, loss: 3.509521411615424e-05
2023-01-23 03:29:20.187539: step: 100/530, loss: 0.005488014314323664
2023-01-23 03:29:21.341333: step: 104/530, loss: 0.00036916733370162547
2023-01-23 03:29:22.575414: step: 108/530, loss: 0.03900289535522461
2023-01-23 03:29:23.750976: step: 112/530, loss: 0.010463238693773746
2023-01-23 03:29:24.932469: step: 116/530, loss: 0.010022545233368874
2023-01-23 03:29:26.062906: step: 120/530, loss: 1.6880036127986386e-05
2023-01-23 03:29:27.228779: step: 124/530, loss: 0.0005819320795126259
2023-01-23 03:29:28.379308: step: 128/530, loss: 0.013443994335830212
2023-01-23 03:29:29.516124: step: 132/530, loss: 0.014048386365175247
2023-01-23 03:29:30.695952: step: 136/530, loss: 0.009867859072983265
2023-01-23 03:29:31.844750: step: 140/530, loss: 0.005676746368408203
2023-01-23 03:29:32.997600: step: 144/530, loss: 0.02029280550777912
2023-01-23 03:29:34.146828: step: 148/530, loss: 3.4761429560603574e-05
2023-01-23 03:29:35.341715: step: 152/530, loss: 0.009539413265883923
2023-01-23 03:29:36.532156: step: 156/530, loss: 0.049428846687078476
2023-01-23 03:29:37.694404: step: 160/530, loss: 0.00010929108248092234
2023-01-23 03:29:38.902806: step: 164/530, loss: 0.011634635739028454
2023-01-23 03:29:40.081288: step: 168/530, loss: 0.005303573794662952
2023-01-23 03:29:41.273921: step: 172/530, loss: 0.0002442359982524067
2023-01-23 03:29:42.514107: step: 176/530, loss: 0.004111289978027344
2023-01-23 03:29:43.694353: step: 180/530, loss: 0.033786870539188385
2023-01-23 03:29:44.838724: step: 184/530, loss: 0.0001243591250386089
2023-01-23 03:29:45.966636: step: 188/530, loss: 0.00015544891357421875
2023-01-23 03:29:47.128674: step: 192/530, loss: 0.03639201819896698
2023-01-23 03:29:48.312579: step: 196/530, loss: 0.0003463744942564517
2023-01-23 03:29:49.530359: step: 200/530, loss: 0.05901079252362251
2023-01-23 03:29:50.697155: step: 204/530, loss: 1.672506368777249e-05
2023-01-23 03:29:51.849509: step: 208/530, loss: 0.0016666412120684981
2023-01-23 03:29:53.031145: step: 212/530, loss: 0.002579975174739957
2023-01-23 03:29:54.199973: step: 216/530, loss: 2.7322768801241182e-05
2023-01-23 03:29:55.352828: step: 220/530, loss: 3.418922642595135e-05
2023-01-23 03:29:56.555060: step: 224/530, loss: 0.12445631623268127
2023-01-23 03:29:57.701154: step: 228/530, loss: 2.1839143300894648e-05
2023-01-23 03:29:58.923027: step: 232/530, loss: 0.033011723309755325
2023-01-23 03:30:00.109789: step: 236/530, loss: 8.97407517186366e-05
2023-01-23 03:30:01.297933: step: 240/530, loss: 0.003277301788330078
2023-01-23 03:30:02.455693: step: 244/530, loss: 0.0028509378898888826
2023-01-23 03:30:03.640138: step: 248/530, loss: 0.033632662147283554
2023-01-23 03:30:04.805271: step: 252/530, loss: 0.053069114685058594
2023-01-23 03:30:05.956677: step: 256/530, loss: 0.0007869720575399697
2023-01-23 03:30:07.131881: step: 260/530, loss: 0.0009078025468625128
2023-01-23 03:30:08.346982: step: 264/530, loss: 0.0075768474489450455
2023-01-23 03:30:09.515561: step: 268/530, loss: 0.0003010749933309853
2023-01-23 03:30:10.672732: step: 272/530, loss: 0.0003259658988099545
2023-01-23 03:30:11.843336: step: 276/530, loss: 0.004863929934799671
2023-01-23 03:30:13.008492: step: 280/530, loss: 0.06417150050401688
2023-01-23 03:30:14.244469: step: 284/530, loss: 0.007483053021132946
2023-01-23 03:30:15.390931: step: 288/530, loss: 0.0030393600463867188
2023-01-23 03:30:16.578070: step: 292/530, loss: 0.005133247934281826
2023-01-23 03:30:17.750701: step: 296/530, loss: 0.017632102593779564
2023-01-23 03:30:18.915668: step: 300/530, loss: 0.04000253975391388
2023-01-23 03:30:20.077550: step: 304/530, loss: 0.0014787673717364669
2023-01-23 03:30:21.265180: step: 308/530, loss: 0.0016761779552325606
2023-01-23 03:30:22.408268: step: 312/530, loss: 0.0029859542846679688
2023-01-23 03:30:23.606661: step: 316/530, loss: 7.343292054429185e-06
2023-01-23 03:30:24.789661: step: 320/530, loss: 0.00011539459228515625
2023-01-23 03:30:25.971905: step: 324/530, loss: 0.0003215789911337197
2023-01-23 03:30:27.138753: step: 328/530, loss: 0.0032497404608875513
2023-01-23 03:30:28.296170: step: 332/530, loss: 0.00034971238346770406
2023-01-23 03:30:29.509129: step: 336/530, loss: 0.0008471489418298006
2023-01-23 03:30:30.670674: step: 340/530, loss: 0.0012094498379155993
2023-01-23 03:30:31.846942: step: 344/530, loss: 0.0029775621369481087
2023-01-23 03:30:33.015223: step: 348/530, loss: 0.000530242919921875
2023-01-23 03:30:34.167773: step: 352/530, loss: 0.0820433646440506
2023-01-23 03:30:35.341817: step: 356/530, loss: 0.007937431335449219
2023-01-23 03:30:36.507509: step: 360/530, loss: 0.006622695829719305
2023-01-23 03:30:37.695358: step: 364/530, loss: 0.007391166873276234
2023-01-23 03:30:38.851933: step: 368/530, loss: 0.0011903762351721525
2023-01-23 03:30:39.983625: step: 372/530, loss: 0.00038013458834029734
2023-01-23 03:30:41.141230: step: 376/530, loss: 0.0021543502807617188
2023-01-23 03:30:42.311819: step: 380/530, loss: 0.005744743626564741
2023-01-23 03:30:43.485791: step: 384/530, loss: 0.07745113223791122
2023-01-23 03:30:44.628158: step: 388/530, loss: 0.0005623817560262978
2023-01-23 03:30:45.834590: step: 392/530, loss: 0.035173892974853516
2023-01-23 03:30:47.000957: step: 396/530, loss: 0.0489748977124691
2023-01-23 03:30:48.192376: step: 400/530, loss: 0.001634359359741211
2023-01-23 03:30:49.359432: step: 404/530, loss: 0.006951427552849054
2023-01-23 03:30:50.523988: step: 408/530, loss: 0.0011802196968346834
2023-01-23 03:30:51.694968: step: 412/530, loss: 0.012400436215102673
2023-01-23 03:30:52.932465: step: 416/530, loss: 0.03774872049689293
2023-01-23 03:30:54.111557: step: 420/530, loss: 0.01274251937866211
2023-01-23 03:30:55.278010: step: 424/530, loss: 0.006424236577004194
2023-01-23 03:30:56.448017: step: 428/530, loss: 0.0006192207220010459
2023-01-23 03:30:57.623599: step: 432/530, loss: 0.003768539521843195
2023-01-23 03:30:58.786463: step: 436/530, loss: 0.0005600929143838584
2023-01-23 03:30:59.976349: step: 440/530, loss: 9.918212890625e-05
2023-01-23 03:31:01.122805: step: 444/530, loss: 0.003454923629760742
2023-01-23 03:31:02.265647: step: 448/530, loss: 0.004976654425263405
2023-01-23 03:31:03.439590: step: 452/530, loss: 0.0025743485894054174
2023-01-23 03:31:04.575233: step: 456/530, loss: 0.0011004448169842362
2023-01-23 03:31:05.721750: step: 460/530, loss: 0.0015920639270916581
2023-01-23 03:31:06.855334: step: 464/530, loss: 0.004820060916244984
2023-01-23 03:31:08.007087: step: 468/530, loss: 0.0027841210830956697
2023-01-23 03:31:09.182409: step: 472/530, loss: 0.0010772228706628084
2023-01-23 03:31:10.353566: step: 476/530, loss: 0.10511579364538193
2023-01-23 03:31:11.539242: step: 480/530, loss: 0.009735107421875
2023-01-23 03:31:12.671084: step: 484/530, loss: 0.001150417374446988
2023-01-23 03:31:13.818338: step: 488/530, loss: 0.47361665964126587
2023-01-23 03:31:14.972741: step: 492/530, loss: 1.659393274167087e-05
2023-01-23 03:31:16.133021: step: 496/530, loss: 0.020464323461055756
2023-01-23 03:31:17.335505: step: 500/530, loss: 0.01638164557516575
2023-01-23 03:31:18.481849: step: 504/530, loss: 0.0013010979164391756
2023-01-23 03:31:19.655450: step: 508/530, loss: 0.005679654888808727
2023-01-23 03:31:20.846648: step: 512/530, loss: 0.00033941271249204874
2023-01-23 03:31:22.006062: step: 516/530, loss: 0.00011940002877963707
2023-01-23 03:31:23.164199: step: 520/530, loss: 9.632110959501006e-06
2023-01-23 03:31:24.321687: step: 524/530, loss: 0.005273151211440563
2023-01-23 03:31:25.537544: step: 528/530, loss: 0.023619651794433594
2023-01-23 03:31:26.651335: step: 532/530, loss: 0.0018474578391760588
2023-01-23 03:31:27.857399: step: 536/530, loss: 0.012527274899184704
2023-01-23 03:31:29.034422: step: 540/530, loss: 0.047043945640325546
2023-01-23 03:31:30.251296: step: 544/530, loss: 0.013675117865204811
2023-01-23 03:31:31.381078: step: 548/530, loss: 0.0006269455188885331
2023-01-23 03:31:32.533007: step: 552/530, loss: 0.0001562118559377268
2023-01-23 03:31:33.675235: step: 556/530, loss: 0.000125885009765625
2023-01-23 03:31:34.851465: step: 560/530, loss: 0.054869841784238815
2023-01-23 03:31:36.006700: step: 564/530, loss: 0.0012381552951410413
2023-01-23 03:31:37.159074: step: 568/530, loss: 0.0024313449393957853
2023-01-23 03:31:38.307291: step: 572/530, loss: 0.0017583846347406507
2023-01-23 03:31:39.505005: step: 576/530, loss: 1.7261505490751006e-05
2023-01-23 03:31:40.638998: step: 580/530, loss: 0.031575966626405716
2023-01-23 03:31:41.862964: step: 584/530, loss: 1.392364538332913e-05
2023-01-23 03:31:43.035616: step: 588/530, loss: 0.004573631100356579
2023-01-23 03:31:44.216408: step: 592/530, loss: 0.0180511474609375
2023-01-23 03:31:45.391807: step: 596/530, loss: 0.006071948911994696
2023-01-23 03:31:46.546136: step: 600/530, loss: 0.030272865667939186
2023-01-23 03:31:47.677161: step: 604/530, loss: 0.0009492874378338456
2023-01-23 03:31:48.832875: step: 608/530, loss: 9.946823411155492e-05
2023-01-23 03:31:50.006179: step: 612/530, loss: 0.009868240915238857
2023-01-23 03:31:51.196897: step: 616/530, loss: 0.05019426718354225
2023-01-23 03:31:52.377790: step: 620/530, loss: 0.0007445336086675525
2023-01-23 03:31:53.553224: step: 624/530, loss: 0.03754863515496254
2023-01-23 03:31:54.706248: step: 628/530, loss: 0.0002620696905069053
2023-01-23 03:31:55.910009: step: 632/530, loss: 4.39643845311366e-05
2023-01-23 03:31:57.097607: step: 636/530, loss: 0.0051344153471291065
2023-01-23 03:31:58.246690: step: 640/530, loss: 0.0004296302795410156
2023-01-23 03:31:59.412877: step: 644/530, loss: 7.877349707996473e-05
2023-01-23 03:32:00.590049: step: 648/530, loss: 0.010566520504653454
2023-01-23 03:32:01.771797: step: 652/530, loss: 0.0008101463317871094
2023-01-23 03:32:02.910583: step: 656/530, loss: 9.709596633911133e-05
2023-01-23 03:32:04.120224: step: 660/530, loss: 0.024234723299741745
2023-01-23 03:32:05.375791: step: 664/530, loss: 0.014329529367387295
2023-01-23 03:32:06.529012: step: 668/530, loss: 0.00010221004777122289
2023-01-23 03:32:07.660498: step: 672/530, loss: 0.00029020311194472015
2023-01-23 03:32:08.803176: step: 676/530, loss: 0.0035304068587720394
2023-01-23 03:32:10.022598: step: 680/530, loss: 0.00017032623873092234
2023-01-23 03:32:11.242832: step: 684/530, loss: 0.039608001708984375
2023-01-23 03:32:12.441027: step: 688/530, loss: 0.08978991210460663
2023-01-23 03:32:13.608833: step: 692/530, loss: 0.009096909314393997
2023-01-23 03:32:14.773909: step: 696/530, loss: 0.004308891016989946
2023-01-23 03:32:15.983392: step: 700/530, loss: 0.010627173818647861
2023-01-23 03:32:17.186763: step: 704/530, loss: 0.0014354706509038806
2023-01-23 03:32:18.341252: step: 708/530, loss: 0.0012062073219567537
2023-01-23 03:32:19.520010: step: 712/530, loss: -3.46153956343187e-06
2023-01-23 03:32:20.655692: step: 716/530, loss: 0.000312614458380267
2023-01-23 03:32:21.840264: step: 720/530, loss: 0.013672161847352982
2023-01-23 03:32:23.003915: step: 724/530, loss: 0.0004307747003622353
2023-01-23 03:32:24.177943: step: 728/530, loss: 0.0114281065762043
2023-01-23 03:32:25.328139: step: 732/530, loss: 0.0009140968322753906
2023-01-23 03:32:26.479179: step: 736/530, loss: 0.008310128003358841
2023-01-23 03:32:27.695208: step: 740/530, loss: 0.004988241475075483
2023-01-23 03:32:28.857723: step: 744/530, loss: 8.907317533157766e-05
2023-01-23 03:32:30.029512: step: 748/530, loss: 0.00041608812171034515
2023-01-23 03:32:31.169370: step: 752/530, loss: 0.04133319854736328
2023-01-23 03:32:32.352868: step: 756/530, loss: 0.0003288269217591733
2023-01-23 03:32:33.511398: step: 760/530, loss: 0.005394697189331055
2023-01-23 03:32:34.654253: step: 764/530, loss: 0.0019208908779546618
2023-01-23 03:32:35.881318: step: 768/530, loss: 0.00014419556828215718
2023-01-23 03:32:37.054037: step: 772/530, loss: 0.010583209805190563
2023-01-23 03:32:38.237152: step: 776/530, loss: 0.0008448601001873612
2023-01-23 03:32:39.386812: step: 780/530, loss: 8.144378807628527e-05
2023-01-23 03:32:40.560811: step: 784/530, loss: 0.0014475345378741622
2023-01-23 03:32:41.723372: step: 788/530, loss: 7.62939453125e-06
2023-01-23 03:32:42.928878: step: 792/530, loss: 0.05154099315404892
2023-01-23 03:32:44.113696: step: 796/530, loss: 0.021154213696718216
2023-01-23 03:32:45.274201: step: 800/530, loss: 0.0024848938919603825
2023-01-23 03:32:46.427455: step: 804/530, loss: 0.0038153647910803556
2023-01-23 03:32:47.586272: step: 808/530, loss: 0.06039123982191086
2023-01-23 03:32:48.816182: step: 812/530, loss: 0.007724094670265913
2023-01-23 03:32:50.008869: step: 816/530, loss: 0.0030528069473803043
2023-01-23 03:32:51.167570: step: 820/530, loss: 0.009526634588837624
2023-01-23 03:32:52.340639: step: 824/530, loss: 4.806518700206652e-05
2023-01-23 03:32:53.507368: step: 828/530, loss: 0.00848617684096098
2023-01-23 03:32:54.626269: step: 832/530, loss: 0.012754536233842373
2023-01-23 03:32:55.897027: step: 836/530, loss: 0.0004299163701944053
2023-01-23 03:32:57.016331: step: 840/530, loss: 0.0015683174133300781
2023-01-23 03:32:58.166981: step: 844/530, loss: 0.0032050609588623047
2023-01-23 03:32:59.299441: step: 848/530, loss: 0.005408573430031538
2023-01-23 03:33:00.480971: step: 852/530, loss: 3.700256274896674e-05
2023-01-23 03:33:01.648283: step: 856/530, loss: 0.011404801160097122
2023-01-23 03:33:02.816450: step: 860/530, loss: 0.007604170124977827
2023-01-23 03:33:04.073378: step: 864/530, loss: 0.0003216743643861264
2023-01-23 03:33:05.251670: step: 868/530, loss: 0.0001183509812108241
2023-01-23 03:33:06.437818: step: 872/530, loss: 0.01935749128460884
2023-01-23 03:33:07.618447: step: 876/530, loss: 0.0028211595490574837
2023-01-23 03:33:08.811370: step: 880/530, loss: 0.00755805941298604
2023-01-23 03:33:09.954553: step: 884/530, loss: 0.003159427549690008
2023-01-23 03:33:11.130080: step: 888/530, loss: 0.037175893783569336
2023-01-23 03:33:12.366878: step: 892/530, loss: 0.015821266919374466
2023-01-23 03:33:13.576674: step: 896/530, loss: 0.0014829635620117188
2023-01-23 03:33:14.787548: step: 900/530, loss: 0.00900039728730917
2023-01-23 03:33:16.002077: step: 904/530, loss: 9.262561798095703e-05
2023-01-23 03:33:17.156107: step: 908/530, loss: 0.001655149506404996
2023-01-23 03:33:18.306978: step: 912/530, loss: 0.015964603051543236
2023-01-23 03:33:19.460347: step: 916/530, loss: 0.00024623872013762593
2023-01-23 03:33:20.572485: step: 920/530, loss: 2.1266936528263614e-05
2023-01-23 03:33:21.733433: step: 924/530, loss: 7.762909081066027e-05
2023-01-23 03:33:22.882982: step: 928/530, loss: 2.5749209271452855e-06
2023-01-23 03:33:24.088146: step: 932/530, loss: 0.009514904581010342
2023-01-23 03:33:25.259573: step: 936/530, loss: 0.019620705395936966
2023-01-23 03:33:26.471950: step: 940/530, loss: 0.0007677078247070312
2023-01-23 03:33:27.630718: step: 944/530, loss: 1.697540210443549e-05
2023-01-23 03:33:28.814126: step: 948/530, loss: 0.05004329979419708
2023-01-23 03:33:29.982814: step: 952/530, loss: 0.020263671875
2023-01-23 03:33:31.136849: step: 956/530, loss: 0.022067641839385033
2023-01-23 03:33:32.315283: step: 960/530, loss: 0.006657171528786421
2023-01-23 03:33:33.491728: step: 964/530, loss: 0.006328964605927467
2023-01-23 03:33:34.646499: step: 968/530, loss: 0.0002513885556254536
2023-01-23 03:33:35.813544: step: 972/530, loss: 0.009434843435883522
2023-01-23 03:33:36.996245: step: 976/530, loss: 0.06498666107654572
2023-01-23 03:33:38.161076: step: 980/530, loss: 0.0012529372470453382
2023-01-23 03:33:39.357182: step: 984/530, loss: 0.012515640817582607
2023-01-23 03:33:40.539319: step: 988/530, loss: 1.6307831174344756e-05
2023-01-23 03:33:41.731202: step: 992/530, loss: 0.0017027854919433594
2023-01-23 03:33:42.877959: step: 996/530, loss: 0.002058005426079035
2023-01-23 03:33:44.073239: step: 1000/530, loss: 0.011433720588684082
2023-01-23 03:33:45.235648: step: 1004/530, loss: 0.000885009765625
2023-01-23 03:33:46.427725: step: 1008/530, loss: 0.001210021902807057
2023-01-23 03:33:47.597557: step: 1012/530, loss: 1.392364538332913e-05
2023-01-23 03:33:48.780179: step: 1016/530, loss: 3.62396240234375e-05
2023-01-23 03:33:49.921740: step: 1020/530, loss: 0.007728290744125843
2023-01-23 03:33:51.089052: step: 1024/530, loss: 0.05792379379272461
2023-01-23 03:33:52.262276: step: 1028/530, loss: 0.00032062531681731343
2023-01-23 03:33:53.467683: step: 1032/530, loss: 0.006886482238769531
2023-01-23 03:33:54.660274: step: 1036/530, loss: 0.014691448770463467
2023-01-23 03:33:55.864146: step: 1040/530, loss: 0.005779266357421875
2023-01-23 03:33:57.058725: step: 1044/530, loss: 0.00018901826115325093
2023-01-23 03:33:58.283239: step: 1048/530, loss: 0.0035127641167491674
2023-01-23 03:33:59.442974: step: 1052/530, loss: 0.014005947858095169
2023-01-23 03:34:00.574282: step: 1056/530, loss: 9.555817086948082e-05
2023-01-23 03:34:01.823638: step: 1060/530, loss: -8.77380352903856e-06
2023-01-23 03:34:02.994343: step: 1064/530, loss: 0.001686143921688199
2023-01-23 03:34:04.154894: step: 1068/530, loss: 0.02495570294559002
2023-01-23 03:34:05.330454: step: 1072/530, loss: 0.0002761840878520161
2023-01-23 03:34:06.513868: step: 1076/530, loss: 0.0030611041001975536
2023-01-23 03:34:07.681120: step: 1080/530, loss: 0.0011238097213208675
2023-01-23 03:34:08.830691: step: 1084/530, loss: 0.0015411378117278218
2023-01-23 03:34:09.999289: step: 1088/530, loss: 0.0008461237302981317
2023-01-23 03:34:11.163446: step: 1092/530, loss: 0.0164521224796772
2023-01-23 03:34:12.342976: step: 1096/530, loss: 0.00014743805513717234
2023-01-23 03:34:13.472126: step: 1100/530, loss: 4.301071385270916e-05
2023-01-23 03:34:14.671839: step: 1104/530, loss: 0.0015448570484295487
2023-01-23 03:34:15.870781: step: 1108/530, loss: 0.010260599665343761
2023-01-23 03:34:17.022472: step: 1112/530, loss: 0.009003067389130592
2023-01-23 03:34:18.171608: step: 1116/530, loss: 0.08434911072254181
2023-01-23 03:34:19.342215: step: 1120/530, loss: 0.007406425662338734
2023-01-23 03:34:20.509102: step: 1124/530, loss: 0.004745578393340111
2023-01-23 03:34:21.703057: step: 1128/530, loss: 0.03506889566779137
2023-01-23 03:34:22.858882: step: 1132/530, loss: 0.5541387796401978
2023-01-23 03:34:24.056450: step: 1136/530, loss: 0.0067115784622728825
2023-01-23 03:34:25.207099: step: 1140/530, loss: 0.0021336558274924755
2023-01-23 03:34:26.368672: step: 1144/530, loss: 0.0051889424212276936
2023-01-23 03:34:27.502922: step: 1148/530, loss: 0.05879192799329758
2023-01-23 03:34:28.689896: step: 1152/530, loss: 0.011456489562988281
2023-01-23 03:34:29.858491: step: 1156/530, loss: 4.730224463855848e-05
2023-01-23 03:34:31.023233: step: 1160/530, loss: 0.008330726064741611
2023-01-23 03:34:32.175239: step: 1164/530, loss: 0.00033226015511900187
2023-01-23 03:34:33.311175: step: 1168/530, loss: 0.05797901377081871
2023-01-23 03:34:34.492439: step: 1172/530, loss: 0.019885780289769173
2023-01-23 03:34:35.635381: step: 1176/530, loss: 0.0030896186362951994
2023-01-23 03:34:36.818112: step: 1180/530, loss: 0.0006618499755859375
2023-01-23 03:34:37.992212: step: 1184/530, loss: 2.2602082026423886e-05
2023-01-23 03:34:39.163553: step: 1188/530, loss: 0.0017972945934161544
2023-01-23 03:34:40.335675: step: 1192/530, loss: 0.006542601156979799
2023-01-23 03:34:41.555545: step: 1196/530, loss: 0.014737558551132679
2023-01-23 03:34:42.737392: step: 1200/530, loss: 0.0018316268688067794
2023-01-23 03:34:43.914837: step: 1204/530, loss: 0.028890609741210938
2023-01-23 03:34:45.067976: step: 1208/530, loss: 0.00779228238388896
2023-01-23 03:34:46.232143: step: 1212/530, loss: 0.004622649867087603
2023-01-23 03:34:47.415388: step: 1216/530, loss: 0.06822347640991211
2023-01-23 03:34:48.620266: step: 1220/530, loss: 3.337860107421875e-05
2023-01-23 03:34:49.763953: step: 1224/530, loss: 0.022996138781309128
2023-01-23 03:34:50.914864: step: 1228/530, loss: 0.020897196605801582
2023-01-23 03:34:52.068007: step: 1232/530, loss: 0.0004893302684649825
2023-01-23 03:34:53.238940: step: 1236/530, loss: 0.007553481962531805
2023-01-23 03:34:54.415967: step: 1240/530, loss: 0.014276409521698952
2023-01-23 03:34:55.595890: step: 1244/530, loss: 0.004218960180878639
2023-01-23 03:34:56.749133: step: 1248/530, loss: 0.029697038233280182
2023-01-23 03:34:57.941054: step: 1252/530, loss: 7.524490501964465e-05
2023-01-23 03:34:59.108256: step: 1256/530, loss: 0.08282909542322159
2023-01-23 03:35:00.246151: step: 1260/530, loss: 0.008394146338105202
2023-01-23 03:35:01.416474: step: 1264/530, loss: 0.0020895004272460938
2023-01-23 03:35:02.594134: step: 1268/530, loss: 0.0007704735035076737
2023-01-23 03:35:03.790844: step: 1272/530, loss: 0.00031147003755904734
2023-01-23 03:35:05.023348: step: 1276/530, loss: 0.001314449356868863
2023-01-23 03:35:06.180361: step: 1280/530, loss: 0.00013256072998046875
2023-01-23 03:35:07.394851: step: 1284/530, loss: 3.44276413670741e-05
2023-01-23 03:35:08.604933: step: 1288/530, loss: 0.0028358460403978825
2023-01-23 03:35:09.755660: step: 1292/530, loss: 0.0018567085498943925
2023-01-23 03:35:10.976393: step: 1296/530, loss: 0.0002290725678903982
2023-01-23 03:35:12.119675: step: 1300/530, loss: 0.00034055710420943797
2023-01-23 03:35:13.317461: step: 1304/530, loss: 0.00014047622971702367
2023-01-23 03:35:14.449621: step: 1308/530, loss: 0.0190140251070261
2023-01-23 03:35:15.590116: step: 1312/530, loss: 0.0007493019220419228
2023-01-23 03:35:16.733757: step: 1316/530, loss: 0.021253205835819244
2023-01-23 03:35:17.890439: step: 1320/530, loss: 0.0007530212169513106
2023-01-23 03:35:19.023584: step: 1324/530, loss: 0.004752159118652344
2023-01-23 03:35:20.215312: step: 1328/530, loss: 0.0007967948913574219
2023-01-23 03:35:21.406408: step: 1332/530, loss: 0.043637800961732864
2023-01-23 03:35:22.594150: step: 1336/530, loss: 0.009446716867387295
2023-01-23 03:35:23.806404: step: 1340/530, loss: 0.006819725502282381
2023-01-23 03:35:25.000275: step: 1344/530, loss: 0.0009269714937545359
2023-01-23 03:35:26.161863: step: 1348/530, loss: 0.005797004792839289
2023-01-23 03:35:27.342717: step: 1352/530, loss: 0.008511209860444069
2023-01-23 03:35:28.508252: step: 1356/530, loss: 0.0006796836969442666
2023-01-23 03:35:29.675404: step: 1360/530, loss: 0.0008857726934365928
2023-01-23 03:35:30.899436: step: 1364/530, loss: 0.009960937313735485
2023-01-23 03:35:32.056426: step: 1368/530, loss: 0.0021012306679040194
2023-01-23 03:35:33.209155: step: 1372/530, loss: 0.00013246537127997726
2023-01-23 03:35:34.398258: step: 1376/530, loss: 5.2070619858568534e-05
2023-01-23 03:35:35.548444: step: 1380/530, loss: 0.06548728793859482
2023-01-23 03:35:36.753743: step: 1384/530, loss: 2.155303991457913e-05
2023-01-23 03:35:37.923662: step: 1388/530, loss: 0.004328870680183172
2023-01-23 03:35:39.104787: step: 1392/530, loss: 0.0002286911039846018
2023-01-23 03:35:40.249755: step: 1396/530, loss: -1.7642976217757678e-06
2023-01-23 03:35:41.434286: step: 1400/530, loss: 0.0009002685546875
2023-01-23 03:35:42.648320: step: 1404/530, loss: 0.013399315066635609
2023-01-23 03:35:43.819256: step: 1408/530, loss: 0.017896080389618874
2023-01-23 03:35:45.039986: step: 1412/530, loss: 0.034514620900154114
2023-01-23 03:35:46.254795: step: 1416/530, loss: 0.003491687821224332
2023-01-23 03:35:47.449928: step: 1420/530, loss: 0.004248619079589844
2023-01-23 03:35:48.625684: step: 1424/530, loss: 0.00629157992079854
2023-01-23 03:35:49.771492: step: 1428/530, loss: 0.05060386657714844
2023-01-23 03:35:50.990221: step: 1432/530, loss: 0.0019865036010742188
2023-01-23 03:35:52.114995: step: 1436/530, loss: 0.0010718345874920487
2023-01-23 03:35:53.312255: step: 1440/530, loss: 0.00940332468599081
2023-01-23 03:35:54.535726: step: 1444/530, loss: 4.158019874012098e-05
2023-01-23 03:35:55.677244: step: 1448/530, loss: 0.018683433532714844
2023-01-23 03:35:56.839991: step: 1452/530, loss: 0.01313552912324667
2023-01-23 03:35:57.985656: step: 1456/530, loss: 0.0004421710909809917
2023-01-23 03:35:59.178017: step: 1460/530, loss: 0.0009889602661132812
2023-01-23 03:36:00.364540: step: 1464/530, loss: 0.024580860510468483
2023-01-23 03:36:01.525403: step: 1468/530, loss: 0.0045175557024776936
2023-01-23 03:36:02.680678: step: 1472/530, loss: 0.28092309832572937
2023-01-23 03:36:03.839827: step: 1476/530, loss: 0.00019836427236441523
2023-01-23 03:36:05.005285: step: 1480/530, loss: -4.7683897719252855e-08
2023-01-23 03:36:06.193107: step: 1484/530, loss: 0.0009140014881268144
2023-01-23 03:36:07.369765: step: 1488/530, loss: 0.0036263468209654093
2023-01-23 03:36:08.556400: step: 1492/530, loss: 0.004390430171042681
2023-01-23 03:36:09.751438: step: 1496/530, loss: 0.08982839435338974
2023-01-23 03:36:10.912757: step: 1500/530, loss: 0.022475814446806908
2023-01-23 03:36:12.106483: step: 1504/530, loss: 0.0007926941034384072
2023-01-23 03:36:13.282738: step: 1508/530, loss: 0.005611419677734375
2023-01-23 03:36:14.440427: step: 1512/530, loss: 0.043725013732910156
2023-01-23 03:36:15.587317: step: 1516/530, loss: 0.00036373137845657766
2023-01-23 03:36:16.756040: step: 1520/530, loss: 0.0011141776340082288
2023-01-23 03:36:17.917539: step: 1524/530, loss: 2.7275083994027227e-05
2023-01-23 03:36:19.092945: step: 1528/530, loss: 0.004909897223114967
2023-01-23 03:36:20.273008: step: 1532/530, loss: 0.02686906047165394
2023-01-23 03:36:21.423921: step: 1536/530, loss: 0.03424873575568199
2023-01-23 03:36:22.589617: step: 1540/530, loss: 0.0008774757734499872
2023-01-23 03:36:23.770410: step: 1544/530, loss: 0.0003266334533691406
2023-01-23 03:36:24.924430: step: 1548/530, loss: 1.0013580322265625e-05
2023-01-23 03:36:26.121795: step: 1552/530, loss: 0.0026200294960290194
2023-01-23 03:36:27.287205: step: 1556/530, loss: 0.0070549012161791325
2023-01-23 03:36:28.437367: step: 1560/530, loss: 0.01136865559965372
2023-01-23 03:36:29.629011: step: 1564/530, loss: 9.822845458984375e-05
2023-01-23 03:36:30.775799: step: 1568/530, loss: 0.02331266552209854
2023-01-23 03:36:31.960059: step: 1572/530, loss: 1.1444089977885596e-06
2023-01-23 03:36:33.101616: step: 1576/530, loss: 0.0058283330872654915
2023-01-23 03:36:34.231468: step: 1580/530, loss: 0.03490380942821503
2023-01-23 03:36:35.396816: step: 1584/530, loss: 0.004513788037002087
2023-01-23 03:36:36.548585: step: 1588/530, loss: 0.0018037796253338456
2023-01-23 03:36:37.690412: step: 1592/530, loss: 0.005067348480224609
2023-01-23 03:36:38.883679: step: 1596/530, loss: 1.068115216185106e-05
2023-01-23 03:36:40.044472: step: 1600/530, loss: 0.00022296904353424907
2023-01-23 03:36:41.224725: step: 1604/530, loss: 2.117157055181451e-05
2023-01-23 03:36:42.428041: step: 1608/530, loss: 0.015858221799135208
2023-01-23 03:36:43.562412: step: 1612/530, loss: 1.4019013178767636e-05
2023-01-23 03:36:44.721131: step: 1616/530, loss: 0.0002799034118652344
2023-01-23 03:36:45.916783: step: 1620/530, loss: 0.0002558708074502647
2023-01-23 03:36:47.094714: step: 1624/530, loss: 0.00590591412037611
2023-01-23 03:36:48.248676: step: 1628/530, loss: 0.005512046627700329
2023-01-23 03:36:49.461802: step: 1632/530, loss: 0.07719950377941132
2023-01-23 03:36:50.626869: step: 1636/530, loss: 0.013679122552275658
2023-01-23 03:36:51.753114: step: 1640/530, loss: 0.05072479322552681
2023-01-23 03:36:52.949501: step: 1644/530, loss: 0.022053956985473633
2023-01-23 03:36:54.118553: step: 1648/530, loss: 0.0007184505229815841
2023-01-23 03:36:55.344522: step: 1652/530, loss: 0.000417795788962394
2023-01-23 03:36:56.589059: step: 1656/530, loss: 0.009464453905820847
2023-01-23 03:36:57.865642: step: 1660/530, loss: 0.04511604458093643
2023-01-23 03:36:59.051430: step: 1664/530, loss: 0.03674044832587242
2023-01-23 03:37:00.212820: step: 1668/530, loss: 0.00019321442232467234
2023-01-23 03:37:01.395386: step: 1672/530, loss: 0.0008433341863565147
2023-01-23 03:37:02.561062: step: 1676/530, loss: 0.008237838745117188
2023-01-23 03:37:03.750286: step: 1680/530, loss: 0.057820796966552734
2023-01-23 03:37:04.972922: step: 1684/530, loss: 0.015452957712113857
2023-01-23 03:37:06.152984: step: 1688/530, loss: 0.002544879913330078
2023-01-23 03:37:07.327373: step: 1692/530, loss: 0.013648772612214088
2023-01-23 03:37:08.493262: step: 1696/530, loss: 0.194017231464386
2023-01-23 03:37:09.687222: step: 1700/530, loss: 0.00018358230590820312
2023-01-23 03:37:10.823280: step: 1704/530, loss: 0.001372528146021068
2023-01-23 03:37:11.965098: step: 1708/530, loss: 0.020580768585205078
2023-01-23 03:37:13.100457: step: 1712/530, loss: 0.000981235527433455
2023-01-23 03:37:14.253083: step: 1716/530, loss: 0.004852390848100185
2023-01-23 03:37:15.402415: step: 1720/530, loss: 0.015310479328036308
2023-01-23 03:37:16.619057: step: 1724/530, loss: 0.023380279541015625
2023-01-23 03:37:17.821316: step: 1728/530, loss: 0.00010576248314464465
2023-01-23 03:37:18.965107: step: 1732/530, loss: 0.0026194097008556128
2023-01-23 03:37:20.150558: step: 1736/530, loss: 0.0059715271927416325
2023-01-23 03:37:21.303474: step: 1740/530, loss: 0.0016260147094726562
2023-01-23 03:37:22.466650: step: 1744/530, loss: 0.003533935407176614
2023-01-23 03:37:23.639325: step: 1748/530, loss: 0.0035459520295262337
2023-01-23 03:37:24.868144: step: 1752/530, loss: 0.04165840148925781
2023-01-23 03:37:26.016557: step: 1756/530, loss: 0.01239700336009264
2023-01-23 03:37:27.190081: step: 1760/530, loss: 0.00011367798288119957
2023-01-23 03:37:28.385418: step: 1764/530, loss: 0.00020933151245117188
2023-01-23 03:37:29.561745: step: 1768/530, loss: 0.01231927890330553
2023-01-23 03:37:30.753766: step: 1772/530, loss: 0.0012462616432458162
2023-01-23 03:37:31.980622: step: 1776/530, loss: 0.021958064287900925
2023-01-23 03:37:33.080432: step: 1780/530, loss: 0.0005257606972008944
2023-01-23 03:37:34.232828: step: 1784/530, loss: 0.0007620811811648309
2023-01-23 03:37:35.391291: step: 1788/530, loss: 9.822846186580136e-05
2023-01-23 03:37:36.562495: step: 1792/530, loss: 0.01444787997752428
2023-01-23 03:37:37.740620: step: 1796/530, loss: 0.011604023166000843
2023-01-23 03:37:38.937383: step: 1800/530, loss: 0.0021286250557750463
2023-01-23 03:37:40.118760: step: 1804/530, loss: 0.02203369140625
2023-01-23 03:37:41.280994: step: 1808/530, loss: 0.09160070866346359
2023-01-23 03:37:42.429668: step: 1812/530, loss: 0.0006944656488485634
2023-01-23 03:37:43.591197: step: 1816/530, loss: 0.0673886314034462
2023-01-23 03:37:44.743629: step: 1820/530, loss: 0.002995395567268133
2023-01-23 03:37:45.911094: step: 1824/530, loss: 0.003184699919074774
2023-01-23 03:37:47.057686: step: 1828/530, loss: 0.004975604824721813
2023-01-23 03:37:48.224444: step: 1832/530, loss: 0.0010208130115643144
2023-01-23 03:37:49.404546: step: 1836/530, loss: 0.004937982652336359
2023-01-23 03:37:50.600215: step: 1840/530, loss: 0.000186920166015625
2023-01-23 03:37:51.785244: step: 1844/530, loss: 0.004055976867675781
2023-01-23 03:37:52.961968: step: 1848/530, loss: 0.0027333260513842106
2023-01-23 03:37:54.128514: step: 1852/530, loss: 0.0010071754222735763
2023-01-23 03:37:55.309366: step: 1856/530, loss: 0.0011112213833257556
2023-01-23 03:37:56.447993: step: 1860/530, loss: 0.026075219735503197
2023-01-23 03:37:57.552355: step: 1864/530, loss: 0.003545474959537387
2023-01-23 03:37:58.709805: step: 1868/530, loss: 0.0871007964015007
2023-01-23 03:37:59.846486: step: 1872/530, loss: 4.37736525782384e-05
2023-01-23 03:38:01.035283: step: 1876/530, loss: 0.03094806708395481
2023-01-23 03:38:02.181629: step: 1880/530, loss: 0.004812241066247225
2023-01-23 03:38:03.396282: step: 1884/530, loss: 0.004081630613654852
2023-01-23 03:38:04.582833: step: 1888/530, loss: 0.03372840955853462
2023-01-23 03:38:05.755620: step: 1892/530, loss: 0.0009820937411859632
2023-01-23 03:38:06.952745: step: 1896/530, loss: 0.05806773900985718
2023-01-23 03:38:08.090641: step: 1900/530, loss: 0.0023453712929040194
2023-01-23 03:38:09.297582: step: 1904/530, loss: 0.014659976586699486
2023-01-23 03:38:10.488838: step: 1908/530, loss: 0.0034152986481785774
2023-01-23 03:38:11.646720: step: 1912/530, loss: 0.0011112213833257556
2023-01-23 03:38:12.825668: step: 1916/530, loss: 0.010769081301987171
2023-01-23 03:38:13.982602: step: 1920/530, loss: 0.050217293202877045
2023-01-23 03:38:15.196458: step: 1924/530, loss: 0.0021835328079760075
2023-01-23 03:38:16.382499: step: 1928/530, loss: 0.0014083862770348787
2023-01-23 03:38:17.516939: step: 1932/530, loss: 0.0004518509085755795
2023-01-23 03:38:18.718235: step: 1936/530, loss: 0.0013151168823242188
2023-01-23 03:38:19.908178: step: 1940/530, loss: 0.0003743171691894531
2023-01-23 03:38:21.084721: step: 1944/530, loss: 0.0037317750975489616
2023-01-23 03:38:22.289330: step: 1948/530, loss: 0.0014743804931640625
2023-01-23 03:38:23.428170: step: 1952/530, loss: 7.400512549793348e-05
2023-01-23 03:38:24.607914: step: 1956/530, loss: 0.00670623779296875
2023-01-23 03:38:25.760784: step: 1960/530, loss: 0.01037659589201212
2023-01-23 03:38:26.951337: step: 1964/530, loss: 0.08839912712574005
2023-01-23 03:38:28.161127: step: 1968/530, loss: 0.0008859634399414062
2023-01-23 03:38:29.336135: step: 1972/530, loss: 0.002801323076710105
2023-01-23 03:38:30.470698: step: 1976/530, loss: 0.0005109787452965975
2023-01-23 03:38:31.649319: step: 1980/530, loss: 0.41833528876304626
2023-01-23 03:38:32.777619: step: 1984/530, loss: 0.0005877971998415887
2023-01-23 03:38:33.938052: step: 1988/530, loss: 0.044048406183719635
2023-01-23 03:38:35.074858: step: 1992/530, loss: 0.0008211136446334422
2023-01-23 03:38:36.233666: step: 1996/530, loss: 0.0005893707275390625
2023-01-23 03:38:37.405544: step: 2000/530, loss: 0.04506273195147514
2023-01-23 03:38:38.560271: step: 2004/530, loss: 0.016488265246152878
2023-01-23 03:38:39.705390: step: 2008/530, loss: 0.06820683181285858
2023-01-23 03:38:40.839301: step: 2012/530, loss: 0.2930595278739929
2023-01-23 03:38:42.067983: step: 2016/530, loss: 0.08129578083753586
2023-01-23 03:38:43.220827: step: 2020/530, loss: 0.0015571117401123047
2023-01-23 03:38:44.395894: step: 2024/530, loss: 0.004266262520104647
2023-01-23 03:38:45.608869: step: 2028/530, loss: 0.023415755480527878
2023-01-23 03:38:46.786872: step: 2032/530, loss: 0.00029535291832871735
2023-01-23 03:38:48.022994: step: 2036/530, loss: 0.002544593997299671
2023-01-23 03:38:49.214753: step: 2040/530, loss: 0.01532745361328125
2023-01-23 03:38:50.371453: step: 2044/530, loss: 0.02802753448486328
2023-01-23 03:38:51.555706: step: 2048/530, loss: 0.09281416237354279
2023-01-23 03:38:52.720225: step: 2052/530, loss: 0.0054483418352901936
2023-01-23 03:38:53.883954: step: 2056/530, loss: 0.006575680337846279
2023-01-23 03:38:55.068827: step: 2060/530, loss: 0.0006768226739950478
2023-01-23 03:38:56.231193: step: 2064/530, loss: 0.00012712478928733617
2023-01-23 03:38:57.399484: step: 2068/530, loss: 0.0015028000343590975
2023-01-23 03:38:58.610293: step: 2072/530, loss: 1.3160706657799892e-05
2023-01-23 03:38:59.785855: step: 2076/530, loss: 0.00200996408239007
2023-01-23 03:39:00.925820: step: 2080/530, loss: 0.0028454780112951994
2023-01-23 03:39:02.089264: step: 2084/530, loss: 0.001373386476188898
2023-01-23 03:39:03.286684: step: 2088/530, loss: 0.0005094528314657509
2023-01-23 03:39:04.497444: step: 2092/530, loss: 0.01798381842672825
2023-01-23 03:39:05.730005: step: 2096/530, loss: 0.01404180470854044
2023-01-23 03:39:06.886549: step: 2100/530, loss: 0.006818962283432484
2023-01-23 03:39:08.051972: step: 2104/530, loss: 0.0044081686064600945
2023-01-23 03:39:09.178381: step: 2108/530, loss: 0.004641341976821423
2023-01-23 03:39:10.395853: step: 2112/530, loss: 0.0015964508056640625
2023-01-23 03:39:11.560315: step: 2116/530, loss: 0.011506086215376854
2023-01-23 03:39:12.740685: step: 2120/530, loss: 0.001605945872142911
==================================================
Loss: 0.016
--------------------
Dev: {'event': {'p': 0.6284796573875803, 'r': 0.7816245006657789, 'f1': 0.6967359050445103}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Test: {'event': {'p': 0.6768263183357524, 'r': 0.80448533640023, 'f1': 0.7351550183920126}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Chinese: {'event': {'p': 0.5975609756097561, 'r': 0.9074074074074074, 'f1': 0.7205882352941176}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
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': 22}
Russian: {'event': {'p': 0.4791666666666667, 'r': 0.6388888888888888, 'f1': 0.5476190476190476}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
New best chinese model...
New best russian model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6284796573875803, 'r': 0.7816245006657789, 'f1': 0.6967359050445103}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Eng Test for Chinese: {'event': {'p': 0.6768263183357524, 'r': 0.80448533640023, 'f1': 0.7351550183920126}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Sample Chinese: {'event': {'p': 0.5975609756097561, 'r': 0.9074074074074074, 'f1': 0.7205882352941176}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5733990147783251, 'r': 0.7749667110519307, 'f1': 0.6591166477916196}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Eng Test for Korean: {'event': {'p': 0.6218005295675199, 'r': 0.8102357676825762, 'f1': 0.7036204744069912}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Sample Korean: {'event': {'p': 0.6417910447761194, 'r': 0.6825396825396826, 'f1': 0.6615384615384614}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6284796573875803, 'r': 0.7816245006657789, 'f1': 0.6967359050445103}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Eng Test for Russian: {'event': {'p': 0.6768263183357524, 'r': 0.80448533640023, 'f1': 0.7351550183920126}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Sample Russian: {'event': {'p': 0.4791666666666667, 'r': 0.6388888888888888, 'f1': 0.5476190476190476}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
******************************
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 03:40:12.426633: step: 4/530, loss: 0.003424739930778742
2023-01-23 03:40:13.605193: step: 8/530, loss: 0.004018020816147327
2023-01-23 03:40:14.743858: step: 12/530, loss: 0.004458618350327015
2023-01-23 03:40:15.918977: step: 16/530, loss: 5.340576171875e-05
2023-01-23 03:40:17.085801: step: 20/530, loss: 0.012980175204575062
2023-01-23 03:40:18.235754: step: 24/530, loss: 0.0033050538040697575
2023-01-23 03:40:19.441434: step: 28/530, loss: 0.00045351980952546
2023-01-23 03:40:20.577345: step: 32/530, loss: 1.0538101378188003e-05
2023-01-23 03:40:21.728724: step: 36/530, loss: 9.527207294013351e-05
2023-01-23 03:40:22.861592: step: 40/530, loss: 3.6525725590763614e-05
2023-01-23 03:40:24.029160: step: 44/530, loss: 0.012993239797651768
2023-01-23 03:40:25.193127: step: 48/530, loss: 0.010903931222856045
2023-01-23 03:40:26.350332: step: 52/530, loss: 0.00037097930908203125
2023-01-23 03:40:27.513844: step: 56/530, loss: 0.0013163567055016756
2023-01-23 03:40:28.696763: step: 60/530, loss: 0.02053070068359375
2023-01-23 03:40:29.871370: step: 64/530, loss: 0.00100116734392941
2023-01-23 03:40:31.005373: step: 68/530, loss: 0.00011148452904308215
2023-01-23 03:40:32.143858: step: 72/530, loss: 0.008852195926010609
2023-01-23 03:40:33.306291: step: 76/530, loss: 0.013536644168198109
2023-01-23 03:40:34.449169: step: 80/530, loss: 8.239746239269152e-05
2023-01-23 03:40:35.603282: step: 84/530, loss: 7.22885160939768e-05
2023-01-23 03:40:36.785460: step: 88/530, loss: 0.011665153317153454
2023-01-23 03:40:37.991412: step: 92/530, loss: 0.007336711976677179
2023-01-23 03:40:39.134496: step: 96/530, loss: 7.23838820704259e-05
2023-01-23 03:40:40.324673: step: 100/530, loss: 4.272460864740424e-05
2023-01-23 03:40:41.514225: step: 104/530, loss: 3.137588646495715e-05
2023-01-23 03:40:42.696147: step: 108/530, loss: 0.00027918818523176014
2023-01-23 03:40:43.845001: step: 112/530, loss: 9.136199514614418e-05
2023-01-23 03:40:45.024723: step: 116/530, loss: -1.5258788153005298e-06
2023-01-23 03:40:46.235976: step: 120/530, loss: 5.378723290050402e-05
2023-01-23 03:40:47.397578: step: 124/530, loss: 0.00127239222638309
2023-01-23 03:40:48.581720: step: 128/530, loss: 0.012261008843779564
2023-01-23 03:40:49.735656: step: 132/530, loss: 0.038495443761348724
2023-01-23 03:40:50.909251: step: 136/530, loss: 0.008259868249297142
2023-01-23 03:40:52.066009: step: 140/530, loss: 0.0006150722620077431
2023-01-23 03:40:53.219051: step: 144/530, loss: 0.0029197693802416325
2023-01-23 03:40:54.368903: step: 148/530, loss: 0.00023794174194335938
2023-01-23 03:40:55.556144: step: 152/530, loss: 0.02695331536233425
2023-01-23 03:40:56.745667: step: 156/530, loss: 0.07549522817134857
2023-01-23 03:40:57.858686: step: 160/530, loss: 0.0029567719902843237
2023-01-23 03:40:58.991387: step: 164/530, loss: 2.059936559817288e-05
2023-01-23 03:41:00.174330: step: 168/530, loss: 0.001317787216976285
2023-01-23 03:41:01.317852: step: 172/530, loss: 0.0003772735653910786
2023-01-23 03:41:02.497530: step: 176/530, loss: 9.34600830078125e-05
2023-01-23 03:41:03.661748: step: 180/530, loss: 0.0011773108271881938
2023-01-23 03:41:04.831354: step: 184/530, loss: 0.002960681915283203
2023-01-23 03:41:06.001186: step: 188/530, loss: 0.034941960126161575
2023-01-23 03:41:07.165473: step: 192/530, loss: 0.00020637513080146164
2023-01-23 03:41:08.356873: step: 196/530, loss: 0.0005014419439248741
2023-01-23 03:41:09.539686: step: 200/530, loss: 0.04156685248017311
2023-01-23 03:41:10.692586: step: 204/530, loss: 2.8085709345759824e-05
2023-01-23 03:41:11.873170: step: 208/530, loss: 0.0003295898495707661
2023-01-23 03:41:13.025704: step: 212/530, loss: 0.0008407592540606856
2023-01-23 03:41:14.201232: step: 216/530, loss: 0.018683435395359993
2023-01-23 03:41:15.302592: step: 220/530, loss: 7.123946852516383e-05
2023-01-23 03:41:16.504034: step: 224/530, loss: 0.00022833794355392456
2023-01-23 03:41:17.655457: step: 228/530, loss: 0.0008405685075558722
2023-01-23 03:41:18.786198: step: 232/530, loss: 0.0003780364932026714
2023-01-23 03:41:19.927249: step: 236/530, loss: 0.0002020835963776335
2023-01-23 03:41:21.050572: step: 240/530, loss: 0.0025697709061205387
2023-01-23 03:41:22.225433: step: 244/530, loss: 0.06228943169116974
2023-01-23 03:41:23.445639: step: 248/530, loss: 0.005413437262177467
2023-01-23 03:41:24.642640: step: 252/530, loss: 0.00015182494826149195
2023-01-23 03:41:25.806552: step: 256/530, loss: 0.0018491744995117188
2023-01-23 03:41:26.952633: step: 260/530, loss: 3.0517578125e-05
2023-01-23 03:41:28.180436: step: 264/530, loss: 0.004176139831542969
2023-01-23 03:41:29.354127: step: 268/530, loss: 0.029385756701231003
2023-01-23 03:41:30.509793: step: 272/530, loss: 0.00019865036301780492
2023-01-23 03:41:31.690466: step: 276/530, loss: 0.010694503784179688
2023-01-23 03:41:32.878644: step: 280/530, loss: 0.04029655456542969
2023-01-23 03:41:34.014845: step: 284/530, loss: 0.0018493651878088713
2023-01-23 03:41:35.166765: step: 288/530, loss: 0.003316688584163785
2023-01-23 03:41:36.340999: step: 292/530, loss: 0.012442111037671566
2023-01-23 03:41:37.519356: step: 296/530, loss: 0.000630283378995955
2023-01-23 03:41:38.678054: step: 300/530, loss: 0.0062122349627316
2023-01-23 03:41:39.851681: step: 304/530, loss: 0.042719174176454544
2023-01-23 03:41:41.068845: step: 308/530, loss: -3.051757857974735e-06
2023-01-23 03:41:42.320502: step: 312/530, loss: 0.0012497903080657125
2023-01-23 03:41:43.518441: step: 316/530, loss: 0.03459300845861435
2023-01-23 03:41:44.734899: step: 320/530, loss: 0.04709320142865181
2023-01-23 03:41:45.913999: step: 324/530, loss: 0.016632556915283203
2023-01-23 03:41:47.101844: step: 328/530, loss: 0.000469207763671875
2023-01-23 03:41:48.252615: step: 332/530, loss: 0.028017044067382812
2023-01-23 03:41:49.452018: step: 336/530, loss: 0.0040229796431958675
2023-01-23 03:41:50.573144: step: 340/530, loss: 0.0012210846180096269
2023-01-23 03:41:51.741452: step: 344/530, loss: 0.10255460441112518
2023-01-23 03:41:52.893988: step: 348/530, loss: -2.1934511096333154e-06
2023-01-23 03:41:54.042418: step: 352/530, loss: 7.190705218818039e-05
2023-01-23 03:41:55.197710: step: 356/530, loss: 0.00010929108248092234
2023-01-23 03:41:56.353042: step: 360/530, loss: 0.020425032824277878
2023-01-23 03:41:57.540194: step: 364/530, loss: 0.004412079229950905
2023-01-23 03:41:58.721755: step: 368/530, loss: 0.05528130754828453
2023-01-23 03:41:59.901578: step: 372/530, loss: 5.445480201160535e-05
2023-01-23 03:42:01.082694: step: 376/530, loss: 0.0001678466796875
2023-01-23 03:42:02.254641: step: 380/530, loss: 0.006081533618271351
2023-01-23 03:42:03.431244: step: 384/530, loss: 0.005450630094856024
2023-01-23 03:42:04.588857: step: 388/530, loss: 0.004245090764015913
2023-01-23 03:42:05.789111: step: 392/530, loss: 0.02884502336382866
2023-01-23 03:42:06.992662: step: 396/530, loss: 0.1141141876578331
2023-01-23 03:42:08.142386: step: 400/530, loss: 0.009141446091234684
2023-01-23 03:42:09.282399: step: 404/530, loss: 1.9073479506914737e-07
2023-01-23 03:42:10.440149: step: 408/530, loss: 0.14864583313465118
2023-01-23 03:42:11.586440: step: 412/530, loss: 0.013268853537738323
2023-01-23 03:42:12.806371: step: 416/530, loss: 0.003097248263657093
2023-01-23 03:42:13.973046: step: 420/530, loss: 0.00128345494158566
2023-01-23 03:42:15.149191: step: 424/530, loss: 1.220703143189894e-05
2023-01-23 03:42:16.333461: step: 428/530, loss: 0.0031614303588867188
2023-01-23 03:42:17.506852: step: 432/530, loss: 0.0001514911709818989
2023-01-23 03:42:18.689267: step: 436/530, loss: 0.02956867218017578
2023-01-23 03:42:19.859507: step: 440/530, loss: 2.2602082026423886e-05
2023-01-23 03:42:21.035031: step: 444/530, loss: 9.403228614246473e-05
2023-01-23 03:42:22.200481: step: 448/530, loss: 0.018086815252900124
2023-01-23 03:42:23.322551: step: 452/530, loss: 6.28471389063634e-05
2023-01-23 03:42:24.469732: step: 456/530, loss: 0.014873409643769264
2023-01-23 03:42:25.636193: step: 460/530, loss: 8.0108642578125e-05
2023-01-23 03:42:26.819760: step: 464/530, loss: 0.018649864941835403
2023-01-23 03:42:27.971521: step: 468/530, loss: 6.11305222264491e-05
2023-01-23 03:42:29.167971: step: 472/530, loss: 0.010495376773178577
2023-01-23 03:42:30.339107: step: 476/530, loss: 0.0023288726806640625
2023-01-23 03:42:31.518382: step: 480/530, loss: 0.01381759624928236
2023-01-23 03:42:32.684841: step: 484/530, loss: 0.004343274515122175
2023-01-23 03:42:33.860835: step: 488/530, loss: 0.2963119447231293
2023-01-23 03:42:35.013577: step: 492/530, loss: 0.016789723187685013
2023-01-23 03:42:36.191771: step: 496/530, loss: 0.005762734916061163
2023-01-23 03:42:37.372486: step: 500/530, loss: 0.019247055053710938
2023-01-23 03:42:38.547599: step: 504/530, loss: 0.11031127721071243
2023-01-23 03:42:39.758828: step: 508/530, loss: 0.002789497608318925
2023-01-23 03:42:40.906595: step: 512/530, loss: 0.04680890962481499
2023-01-23 03:42:42.087246: step: 516/530, loss: 0.00012893676466774195
2023-01-23 03:42:43.301411: step: 520/530, loss: 0.005897474475204945
2023-01-23 03:42:44.452270: step: 524/530, loss: 0.0003764152352232486
2023-01-23 03:42:45.648217: step: 528/530, loss: 0.01007699966430664
2023-01-23 03:42:46.822196: step: 532/530, loss: 0.006680965423583984
2023-01-23 03:42:48.003887: step: 536/530, loss: 0.00040912628173828125
2023-01-23 03:42:49.194907: step: 540/530, loss: 4.978180004400201e-05
2023-01-23 03:42:50.384253: step: 544/530, loss: 0.0003132820420432836
2023-01-23 03:42:51.561075: step: 548/530, loss: 0.004288482945412397
2023-01-23 03:42:52.722632: step: 552/530, loss: 0.0003602028009481728
2023-01-23 03:42:53.918754: step: 556/530, loss: 0.007989502511918545
2023-01-23 03:42:55.069293: step: 560/530, loss: 0.0012689590221270919
2023-01-23 03:42:56.229668: step: 564/530, loss: 0.005208635702729225
2023-01-23 03:42:57.394825: step: 568/530, loss: 0.0009551048278808594
2023-01-23 03:42:58.573732: step: 572/530, loss: 0.005188846495002508
2023-01-23 03:42:59.749686: step: 576/530, loss: 0.02417469210922718
2023-01-23 03:43:00.942984: step: 580/530, loss: 4.9400332500226796e-05
2023-01-23 03:43:02.124949: step: 584/530, loss: 0.00015773772611282766
2023-01-23 03:43:03.314365: step: 588/530, loss: 0.0002110004425048828
2023-01-23 03:43:04.472727: step: 592/530, loss: 0.0015655518509447575
2023-01-23 03:43:05.612864: step: 596/530, loss: 1.850128137448337e-05
2023-01-23 03:43:06.888870: step: 600/530, loss: 0.0031991959549486637
2023-01-23 03:43:08.065606: step: 604/530, loss: 0.0034526826348155737
2023-01-23 03:43:09.200779: step: 608/530, loss: 0.018709946423768997
2023-01-23 03:43:10.395788: step: 612/530, loss: 0.010827064514160156
2023-01-23 03:43:11.577560: step: 616/530, loss: 0.0048656463623046875
2023-01-23 03:43:12.760695: step: 620/530, loss: 0.005568885710090399
2023-01-23 03:43:13.964975: step: 624/530, loss: 0.00010585784912109375
2023-01-23 03:43:15.146149: step: 628/530, loss: 0.0006314277998171747
2023-01-23 03:43:16.322393: step: 632/530, loss: 0.054948996752500534
2023-01-23 03:43:17.524388: step: 636/530, loss: 0.0015434265369549394
2023-01-23 03:43:18.686363: step: 640/530, loss: 0.023142529651522636
2023-01-23 03:43:19.893716: step: 644/530, loss: 0.018304824829101562
2023-01-23 03:43:21.074894: step: 648/530, loss: 0.0011981964344158769
2023-01-23 03:43:22.255216: step: 652/530, loss: 0.007338809780776501
2023-01-23 03:43:23.407708: step: 656/530, loss: 0.0020253180991858244
2023-01-23 03:43:24.559704: step: 660/530, loss: -7.629394644936838e-07
2023-01-23 03:43:25.748209: step: 664/530, loss: 0.0057255979627370834
2023-01-23 03:43:26.906829: step: 668/530, loss: 0.0007538318750448525
2023-01-23 03:43:28.094361: step: 672/530, loss: 0.00047397613525390625
2023-01-23 03:43:29.273596: step: 676/530, loss: 0.0005088806501589715
2023-01-23 03:43:30.441341: step: 680/530, loss: 0.0016721725696697831
2023-01-23 03:43:31.619198: step: 684/530, loss: 3.967285010730848e-05
2023-01-23 03:43:32.812104: step: 688/530, loss: 0.00017299651517532766
2023-01-23 03:43:34.011403: step: 692/530, loss: 0.025927353650331497
2023-01-23 03:43:35.157012: step: 696/530, loss: 0.01835918426513672
2023-01-23 03:43:36.322404: step: 700/530, loss: 0.03897666931152344
2023-01-23 03:43:37.499538: step: 704/530, loss: 0.02163524553179741
2023-01-23 03:43:38.696860: step: 708/530, loss: 0.0012620926136150956
2023-01-23 03:43:39.849174: step: 712/530, loss: 0.00028858185396529734
2023-01-23 03:43:41.060439: step: 716/530, loss: 0.015540754422545433
2023-01-23 03:43:42.200114: step: 720/530, loss: 3.069639205932617e-06
2023-01-23 03:43:43.425135: step: 724/530, loss: 0.0012387275928631425
2023-01-23 03:43:44.579885: step: 728/530, loss: 0.00011291504051769152
2023-01-23 03:43:45.731104: step: 732/530, loss: 5.9150161177967675e-06
2023-01-23 03:43:46.917853: step: 736/530, loss: 0.00010328293137717992
2023-01-23 03:43:48.076231: step: 740/530, loss: 0.0010553359752520919
2023-01-23 03:43:49.250324: step: 744/530, loss: 0.005288219545036554
2023-01-23 03:43:50.455270: step: 748/530, loss: 1.4495850336970761e-05
2023-01-23 03:43:51.589839: step: 752/530, loss: 3.14712519866589e-06
2023-01-23 03:43:52.718699: step: 756/530, loss: 0.0045181275345385075
2023-01-23 03:43:53.923650: step: 760/530, loss: 0.013479471206665039
2023-01-23 03:43:55.116446: step: 764/530, loss: 0.060167886316776276
2023-01-23 03:43:56.256654: step: 768/530, loss: 0.02922964096069336
2023-01-23 03:43:57.409475: step: 772/530, loss: 0.0001808166562113911
2023-01-23 03:43:58.577713: step: 776/530, loss: 0.0025566101539880037
2023-01-23 03:43:59.723425: step: 780/530, loss: 6.179809861350805e-05
2023-01-23 03:44:00.905032: step: 784/530, loss: 2.9039383662166074e-05
2023-01-23 03:44:02.118500: step: 788/530, loss: 0.0418337844312191
2023-01-23 03:44:03.279290: step: 792/530, loss: 0.09356942027807236
2023-01-23 03:44:04.480673: step: 796/530, loss: 0.018194295465946198
2023-01-23 03:44:05.607883: step: 800/530, loss: 0.0008517265086993575
2023-01-23 03:44:06.787543: step: 804/530, loss: 1.6880036127986386e-05
2023-01-23 03:44:07.950823: step: 808/530, loss: 0.021120835095643997
2023-01-23 03:44:09.121658: step: 812/530, loss: 0.15958061814308167
2023-01-23 03:44:10.268263: step: 816/530, loss: 0.00013704299635719508
2023-01-23 03:44:11.420128: step: 820/530, loss: 0.00041797160520218313
2023-01-23 03:44:12.586083: step: 824/530, loss: 0.003691387362778187
2023-01-23 03:44:13.774373: step: 828/530, loss: 0.012251567095518112
2023-01-23 03:44:14.935145: step: 832/530, loss: 9.632110959501006e-06
2023-01-23 03:44:16.205651: step: 836/530, loss: 0.001038551446981728
2023-01-23 03:44:17.355187: step: 840/530, loss: 0.0001832962007028982
2023-01-23 03:44:18.552019: step: 844/530, loss: 0.017710590735077858
2023-01-23 03:44:19.775568: step: 848/530, loss: 0.014767074026167393
2023-01-23 03:44:20.919098: step: 852/530, loss: 0.0002273559512104839
2023-01-23 03:44:22.080015: step: 856/530, loss: 6.046295311534777e-05
2023-01-23 03:44:23.290700: step: 860/530, loss: 8.010865713004023e-06
2023-01-23 03:44:24.448404: step: 864/530, loss: 0.001394128892570734
2023-01-23 03:44:25.604097: step: 868/530, loss: 1.4400481632037554e-05
2023-01-23 03:44:26.767495: step: 872/530, loss: 2.002715973503655e-06
2023-01-23 03:44:27.927695: step: 876/530, loss: 0.00047912599984556437
2023-01-23 03:44:29.088305: step: 880/530, loss: 0.07759761810302734
2023-01-23 03:44:30.258410: step: 884/530, loss: 3.547668529790826e-05
2023-01-23 03:44:31.432709: step: 888/530, loss: 0.0688687339425087
2023-01-23 03:44:32.590521: step: 892/530, loss: 0.026904869824647903
2023-01-23 03:44:33.778409: step: 896/530, loss: -3.6621091567212716e-05
2023-01-23 03:44:34.978698: step: 900/530, loss: 0.00119609828107059
2023-01-23 03:44:36.119194: step: 904/530, loss: 0.0021844864822924137
2023-01-23 03:44:37.246341: step: 908/530, loss: 8.387566049350426e-05
2023-01-23 03:44:38.411299: step: 912/530, loss: 0.00261192349717021
2023-01-23 03:44:39.544694: step: 916/530, loss: 0.005834389012306929
2023-01-23 03:44:40.734905: step: 920/530, loss: -2.098083541568485e-06
2023-01-23 03:44:41.938543: step: 924/530, loss: 0.0010517120826989412
2023-01-23 03:44:43.102461: step: 928/530, loss: 0.0006122589111328125
2023-01-23 03:44:44.282505: step: 932/530, loss: 0.006759834475815296
2023-01-23 03:44:45.435594: step: 936/530, loss: 0.0006929397350177169
2023-01-23 03:44:46.643088: step: 940/530, loss: 0.002057981677353382
2023-01-23 03:44:47.782300: step: 944/530, loss: 0.0024179460015147924
2023-01-23 03:44:48.939869: step: 948/530, loss: 0.00021333694166969508
2023-01-23 03:44:50.092936: step: 952/530, loss: 0.000305539375403896
2023-01-23 03:44:51.238596: step: 956/530, loss: 0.004509163089096546
2023-01-23 03:44:52.400683: step: 960/530, loss: 0.01748066022992134
2023-01-23 03:44:53.656791: step: 964/530, loss: 0.0003255844349041581
2023-01-23 03:44:54.829186: step: 968/530, loss: 0.00025391578674316406
2023-01-23 03:44:55.974539: step: 972/530, loss: 0.0030090808868408203
2023-01-23 03:44:57.183181: step: 976/530, loss: 0.005576896481215954
2023-01-23 03:44:58.368998: step: 980/530, loss: 3.719329833984375e-05
2023-01-23 03:44:59.633083: step: 984/530, loss: 0.009737014770507812
2023-01-23 03:45:00.786603: step: 988/530, loss: 0.00018544196791481227
2023-01-23 03:45:01.954350: step: 992/530, loss: 0.0004286766052246094
2023-01-23 03:45:03.152322: step: 996/530, loss: 1.8692018784349784e-05
2023-01-23 03:45:04.294985: step: 1000/530, loss: 0.025798607617616653
2023-01-23 03:45:05.461545: step: 1004/530, loss: 0.01819467544555664
2023-01-23 03:45:06.633234: step: 1008/530, loss: 0.004063606262207031
2023-01-23 03:45:07.799045: step: 1012/530, loss: 0.0146621223539114
2023-01-23 03:45:08.980179: step: 1016/530, loss: 0.005760956089943647
2023-01-23 03:45:10.157588: step: 1020/530, loss: 0.0004344940243754536
2023-01-23 03:45:11.268545: step: 1024/530, loss: 0.0017871379386633635
2023-01-23 03:45:12.460283: step: 1028/530, loss: 0.00201835623010993
2023-01-23 03:45:13.630907: step: 1032/530, loss: 0.00036077501135878265
2023-01-23 03:45:14.794174: step: 1036/530, loss: 0.0021250725258141756
2023-01-23 03:45:15.946623: step: 1040/530, loss: 7.152557827794226e-06
2023-01-23 03:45:17.103234: step: 1044/530, loss: -1.068115216185106e-05
2023-01-23 03:45:18.285742: step: 1048/530, loss: 0.004632544703781605
2023-01-23 03:45:19.473210: step: 1052/530, loss: 0.032651904970407486
2023-01-23 03:45:20.684643: step: 1056/530, loss: 9.231566946255043e-05
2023-01-23 03:45:21.860885: step: 1060/530, loss: 0.00125293736346066
2023-01-23 03:45:23.096816: step: 1064/530, loss: 0.007747459691017866
2023-01-23 03:45:24.252209: step: 1068/530, loss: 0.0006618500337935984
2023-01-23 03:45:25.390959: step: 1072/530, loss: 0.011079597286880016
2023-01-23 03:45:26.550949: step: 1076/530, loss: 5.4073334467830136e-05
2023-01-23 03:45:27.712310: step: 1080/530, loss: 2.250671423098538e-05
2023-01-23 03:45:28.880897: step: 1084/530, loss: 0.0020433426834642887
2023-01-23 03:45:30.058512: step: 1088/530, loss: 4.100799560546875e-05
2023-01-23 03:45:31.286593: step: 1092/530, loss: 1.640319896978326e-05
2023-01-23 03:45:32.440929: step: 1096/530, loss: 0.00039358140202239156
2023-01-23 03:45:33.599781: step: 1100/530, loss: 0.00023345947556663305
2023-01-23 03:45:34.745689: step: 1104/530, loss: 0.022386642172932625
2023-01-23 03:45:35.942155: step: 1108/530, loss: 0.005397797096520662
2023-01-23 03:45:37.121998: step: 1112/530, loss: 0.05992889776825905
2023-01-23 03:45:38.281397: step: 1116/530, loss: 0.00010395050048828125
2023-01-23 03:45:39.430737: step: 1120/530, loss: 0.0007589340093545616
2023-01-23 03:45:40.637482: step: 1124/530, loss: 1.9931794668082148e-05
2023-01-23 03:45:41.820261: step: 1128/530, loss: 2.8610227218450746e-06
2023-01-23 03:45:43.006497: step: 1132/530, loss: 0.021286966279149055
2023-01-23 03:45:44.240594: step: 1136/530, loss: 0.00011281967454124242
2023-01-23 03:45:45.382400: step: 1140/530, loss: -1.9073486328125e-06
2023-01-23 03:45:46.612214: step: 1144/530, loss: 2.4318694613612024e-06
2023-01-23 03:45:47.800698: step: 1148/530, loss: 0.0006731033208779991
2023-01-23 03:45:48.956532: step: 1152/530, loss: 0.025429202243685722
2023-01-23 03:45:50.082254: step: 1156/530, loss: 0.0006122589111328125
2023-01-23 03:45:51.253199: step: 1160/530, loss: 5.4645537602482364e-05
2023-01-23 03:45:52.446235: step: 1164/530, loss: 0.046225644648075104
2023-01-23 03:45:53.630527: step: 1168/530, loss: 0.004306030459702015
2023-01-23 03:45:54.761195: step: 1172/530, loss: 0.0003841400030069053
2023-01-23 03:45:55.947100: step: 1176/530, loss: 0.12259978801012039
2023-01-23 03:45:57.113509: step: 1180/530, loss: 2.727508581301663e-05
2023-01-23 03:45:58.303298: step: 1184/530, loss: 0.0022701264824718237
2023-01-23 03:45:59.514521: step: 1188/530, loss: 4.405975414556451e-05
2023-01-23 03:46:00.686819: step: 1192/530, loss: 0.010464095510542393
2023-01-23 03:46:01.858138: step: 1196/530, loss: 0.02464168146252632
2023-01-23 03:46:02.999947: step: 1200/530, loss: 0.003505229949951172
2023-01-23 03:46:04.149322: step: 1204/530, loss: 0.012092113494873047
2023-01-23 03:46:05.341709: step: 1208/530, loss: 0.0017627477645874023
2023-01-23 03:46:06.528945: step: 1212/530, loss: 0.08307018876075745
2023-01-23 03:46:07.717779: step: 1216/530, loss: 0.029086114838719368
2023-01-23 03:46:08.884576: step: 1220/530, loss: 0.00015144348435569555
2023-01-23 03:46:10.023740: step: 1224/530, loss: 0.019352149218320847
2023-01-23 03:46:11.221495: step: 1228/530, loss: 0.0001125335693359375
2023-01-23 03:46:12.329283: step: 1232/530, loss: 0.007159900851547718
2023-01-23 03:46:13.501252: step: 1236/530, loss: 0.017534637823700905
2023-01-23 03:46:14.701471: step: 1240/530, loss: 0.0006711006280966103
2023-01-23 03:46:15.815990: step: 1244/530, loss: 0.0016992568271234632
2023-01-23 03:46:17.002998: step: 1248/530, loss: 0.00010290146747138351
2023-01-23 03:46:18.179951: step: 1252/530, loss: 0.013883877545595169
2023-01-23 03:46:19.402811: step: 1256/530, loss: 0.002599811414256692
2023-01-23 03:46:20.560115: step: 1260/530, loss: 2.040863000729587e-05
2023-01-23 03:46:21.739282: step: 1264/530, loss: 2.079009937006049e-05
2023-01-23 03:46:22.864393: step: 1268/530, loss: 0.00031408070935867727
2023-01-23 03:46:23.998873: step: 1272/530, loss: 0.05851106718182564
2023-01-23 03:46:25.207588: step: 1276/530, loss: 0.01069183461368084
2023-01-23 03:46:26.355128: step: 1280/530, loss: 0.001836681505665183
2023-01-23 03:46:27.527333: step: 1284/530, loss: 0.0003002166922669858
2023-01-23 03:46:28.672805: step: 1288/530, loss: 0.02693486213684082
2023-01-23 03:46:29.847882: step: 1292/530, loss: 0.00148267752956599
2023-01-23 03:46:31.007357: step: 1296/530, loss: 3.3855437777674524e-06
2023-01-23 03:46:32.182284: step: 1300/530, loss: 0.00547714252024889
2023-01-23 03:46:33.380787: step: 1304/530, loss: 0.022827625274658203
2023-01-23 03:46:34.543236: step: 1308/530, loss: 0.0025603293906897306
2023-01-23 03:46:35.690890: step: 1312/530, loss: 1.9669532775878906e-05
2023-01-23 03:46:36.830421: step: 1316/530, loss: 0.05727529525756836
2023-01-23 03:46:37.983494: step: 1320/530, loss: 0.0001794815034372732
2023-01-23 03:46:39.155102: step: 1324/530, loss: 0.0029422759544104338
2023-01-23 03:46:40.338669: step: 1328/530, loss: 0.007952690124511719
2023-01-23 03:46:41.507642: step: 1332/530, loss: 0.006788825616240501
2023-01-23 03:46:42.689152: step: 1336/530, loss: 0.0005025863647460938
2023-01-23 03:46:43.885464: step: 1340/530, loss: 0.001758575439453125
2023-01-23 03:46:45.104480: step: 1344/530, loss: 0.003667640732601285
2023-01-23 03:46:46.286220: step: 1348/530, loss: 0.0007131577003747225
2023-01-23 03:46:47.469250: step: 1352/530, loss: 0.02998518943786621
2023-01-23 03:46:48.645360: step: 1356/530, loss: 0.008506203070282936
2023-01-23 03:46:49.803049: step: 1360/530, loss: 3.4809113458322827e-06
2023-01-23 03:46:51.002533: step: 1364/530, loss: 0.0016820906894281507
2023-01-23 03:46:52.178677: step: 1368/530, loss: 0.0035636902321130037
2023-01-23 03:46:53.328205: step: 1372/530, loss: 6.217956251930445e-05
2023-01-23 03:46:54.542796: step: 1376/530, loss: 0.03614712134003639
2023-01-23 03:46:55.734376: step: 1380/530, loss: 0.00024657248286530375
2023-01-23 03:46:56.895300: step: 1384/530, loss: 0.00037784577580168843
2023-01-23 03:46:58.079823: step: 1388/530, loss: 0.04331236332654953
2023-01-23 03:46:59.239893: step: 1392/530, loss: 5.817413693876006e-06
2023-01-23 03:47:00.441166: step: 1396/530, loss: 0.0016355514526367188
2023-01-23 03:47:01.614324: step: 1400/530, loss: 8.120536949718371e-05
2023-01-23 03:47:02.787608: step: 1404/530, loss: 0.0002738833427429199
2023-01-23 03:47:03.981983: step: 1408/530, loss: 2.822876012942288e-05
2023-01-23 03:47:05.126203: step: 1412/530, loss: 0.0004620552354026586
2023-01-23 03:47:06.272200: step: 1416/530, loss: 4.322528911870904e-05
2023-01-23 03:47:07.434280: step: 1420/530, loss: 1.3256072634248994e-05
2023-01-23 03:47:08.586761: step: 1424/530, loss: 5.53131121705519e-06
2023-01-23 03:47:09.774819: step: 1428/530, loss: 0.0005479812389239669
2023-01-23 03:47:10.974575: step: 1432/530, loss: 0.0001502990780863911
2023-01-23 03:47:12.132247: step: 1436/530, loss: 0.04714584723114967
2023-01-23 03:47:13.344099: step: 1440/530, loss: 0.021670151501893997
2023-01-23 03:47:14.534572: step: 1444/530, loss: 0.000869536364916712
2023-01-23 03:47:15.692892: step: 1448/530, loss: 0.46847161650657654
2023-01-23 03:47:16.851653: step: 1452/530, loss: 0.035117149353027344
2023-01-23 03:47:18.004146: step: 1456/530, loss: 0.02888631820678711
2023-01-23 03:47:19.143214: step: 1460/530, loss: 0.0011163711315020919
2023-01-23 03:47:20.312300: step: 1464/530, loss: 3.547668529790826e-05
2023-01-23 03:47:21.475980: step: 1468/530, loss: 0.01249632891267538
2023-01-23 03:47:22.685163: step: 1472/530, loss: 8.668899681651965e-05
2023-01-23 03:47:23.839051: step: 1476/530, loss: 0.0004951477167196572
2023-01-23 03:47:24.989228: step: 1480/530, loss: 0.0003058433358091861
2023-01-23 03:47:26.172292: step: 1484/530, loss: 0.0032613754738122225
2023-01-23 03:47:27.403837: step: 1488/530, loss: 5.53131121705519e-06
2023-01-23 03:47:28.587651: step: 1492/530, loss: 0.012811660766601562
2023-01-23 03:47:29.763125: step: 1496/530, loss: 0.00046129230759106576
2023-01-23 03:47:30.944949: step: 1500/530, loss: 0.008317947387695312
2023-01-23 03:47:32.106922: step: 1504/530, loss: 0.0001320362207479775
2023-01-23 03:47:33.291619: step: 1508/530, loss: 0.0006953239790163934
2023-01-23 03:47:34.462192: step: 1512/530, loss: 6.10351571594947e-06
2023-01-23 03:47:35.614253: step: 1516/530, loss: 0.005542946048080921
2023-01-23 03:47:36.780110: step: 1520/530, loss: 0.009789466857910156
2023-01-23 03:47:37.948175: step: 1524/530, loss: 4.978180368198082e-05
2023-01-23 03:47:39.146689: step: 1528/530, loss: 0.0003383636649232358
2023-01-23 03:47:40.302766: step: 1532/530, loss: 0.00104522705078125
2023-01-23 03:47:41.493205: step: 1536/530, loss: 0.0003890037478413433
2023-01-23 03:47:42.715486: step: 1540/530, loss: 0.10388441383838654
2023-01-23 03:47:43.889471: step: 1544/530, loss: 0.0036623000632971525
2023-01-23 03:47:45.083954: step: 1548/530, loss: 0.026074599474668503
2023-01-23 03:47:46.298791: step: 1552/530, loss: 0.0011375427711755037
2023-01-23 03:47:47.451698: step: 1556/530, loss: 0.0007243156433105469
2023-01-23 03:47:48.584283: step: 1560/530, loss: 0.03665218502283096
2023-01-23 03:47:49.768152: step: 1564/530, loss: 0.0010131836170330644
2023-01-23 03:47:50.925205: step: 1568/530, loss: 0.06963463127613068
2023-01-23 03:47:52.076495: step: 1572/530, loss: 0.006336784455925226
2023-01-23 03:47:53.262215: step: 1576/530, loss: 8.535384949936997e-06
2023-01-23 03:47:54.464681: step: 1580/530, loss: 0.0002690315304789692
2023-01-23 03:47:55.670073: step: 1584/530, loss: 0.059790898114442825
2023-01-23 03:47:56.823723: step: 1588/530, loss: 0.009599113836884499
2023-01-23 03:47:57.978239: step: 1592/530, loss: 0.004770755767822266
2023-01-23 03:47:59.157478: step: 1596/530, loss: 0.006071853917092085
2023-01-23 03:48:00.302693: step: 1600/530, loss: 0.0009387970203533769
2023-01-23 03:48:01.495843: step: 1604/530, loss: 0.011533546261489391
2023-01-23 03:48:02.672318: step: 1608/530, loss: 0.0001070022553903982
2023-01-23 03:48:03.851443: step: 1612/530, loss: 0.004736470989882946
2023-01-23 03:48:05.034809: step: 1616/530, loss: 0.017360592260956764
2023-01-23 03:48:06.213555: step: 1620/530, loss: 0.03340759500861168
2023-01-23 03:48:07.342450: step: 1624/530, loss: 1.2969970157428179e-05
2023-01-23 03:48:08.501070: step: 1628/530, loss: 0.02504558488726616
2023-01-23 03:48:09.639349: step: 1632/530, loss: 0.01328191813081503
2023-01-23 03:48:10.798856: step: 1636/530, loss: 0.00024662018404342234
2023-01-23 03:48:11.971304: step: 1640/530, loss: 0.0028443338815122843
2023-01-23 03:48:13.130928: step: 1644/530, loss: 0.00019845963106490672
2023-01-23 03:48:14.273857: step: 1648/530, loss: 0.005619239993393421
2023-01-23 03:48:15.452657: step: 1652/530, loss: 0.010685157962143421
2023-01-23 03:48:16.611387: step: 1656/530, loss: 0.007655525114387274
2023-01-23 03:48:17.771433: step: 1660/530, loss: 0.01723175123333931
2023-01-23 03:48:18.960704: step: 1664/530, loss: 0.0029481889214366674
2023-01-23 03:48:20.143916: step: 1668/530, loss: 0.0009908676147460938
2023-01-23 03:48:21.297199: step: 1672/530, loss: 0.004089737311005592
2023-01-23 03:48:22.457405: step: 1676/530, loss: 0.01135864295065403
2023-01-23 03:48:23.629086: step: 1680/530, loss: 0.0005916595691815019
2023-01-23 03:48:24.822100: step: 1684/530, loss: 0.006215095520019531
2023-01-23 03:48:26.010218: step: 1688/530, loss: 0.03696784749627113
2023-01-23 03:48:27.178171: step: 1692/530, loss: 0.04552946239709854
2023-01-23 03:48:28.352133: step: 1696/530, loss: 0.011257028207182884
2023-01-23 03:48:29.541450: step: 1700/530, loss: 0.003250312991440296
2023-01-23 03:48:30.744612: step: 1704/530, loss: 0.02100525051355362
2023-01-23 03:48:31.872193: step: 1708/530, loss: 0.01047439593821764
2023-01-23 03:48:33.011573: step: 1712/530, loss: 0.0016035079024732113
2023-01-23 03:48:34.172609: step: 1716/530, loss: 0.0007534027099609375
2023-01-23 03:48:35.423225: step: 1720/530, loss: 0.005093193147331476
2023-01-23 03:48:36.602734: step: 1724/530, loss: 0.0381532683968544
2023-01-23 03:48:37.749179: step: 1728/530, loss: 0.007084846496582031
2023-01-23 03:48:38.907937: step: 1732/530, loss: 3.0136110581224784e-05
2023-01-23 03:48:40.144290: step: 1736/530, loss: 3.056526111322455e-05
2023-01-23 03:48:41.342850: step: 1740/530, loss: 0.012841987423598766
2023-01-23 03:48:42.512055: step: 1744/530, loss: 2.0122528439969756e-05
2023-01-23 03:48:43.700323: step: 1748/530, loss: 4.38690176451928e-06
2023-01-23 03:48:44.901285: step: 1752/530, loss: 0.010372733697295189
2023-01-23 03:48:46.073698: step: 1756/530, loss: 0.0001239776611328125
2023-01-23 03:48:47.281467: step: 1760/530, loss: 0.00013790131197310984
2023-01-23 03:48:48.450776: step: 1764/530, loss: 0.017101097851991653
2023-01-23 03:48:49.622472: step: 1768/530, loss: 0.01523437537252903
2023-01-23 03:48:50.804348: step: 1772/530, loss: 0.0005068779573775828
2023-01-23 03:48:52.031853: step: 1776/530, loss: 0.041847798973321915
2023-01-23 03:48:53.167266: step: 1780/530, loss: 0.003219032194465399
2023-01-23 03:48:54.363355: step: 1784/530, loss: 0.009685707278549671
2023-01-23 03:48:55.538811: step: 1788/530, loss: 0.06047554314136505
2023-01-23 03:48:56.707522: step: 1792/530, loss: 0.002909088274464011
2023-01-23 03:48:57.876189: step: 1796/530, loss: 0.00017547607421875
2023-01-23 03:48:59.090008: step: 1800/530, loss: 0.0016261100536212325
2023-01-23 03:49:00.286246: step: 1804/530, loss: 0.0014720142353326082
2023-01-23 03:49:01.477566: step: 1808/530, loss: 0.004967927932739258
2023-01-23 03:49:02.608676: step: 1812/530, loss: 0.022266961634159088
2023-01-23 03:49:03.773582: step: 1816/530, loss: 0.0004787445068359375
2023-01-23 03:49:04.964304: step: 1820/530, loss: 0.021136663854122162
2023-01-23 03:49:06.144686: step: 1824/530, loss: 4.5490265620173886e-05
2023-01-23 03:49:07.305305: step: 1828/530, loss: 0.015691757202148438
2023-01-23 03:49:08.451366: step: 1832/530, loss: 0.0002340316859772429
2023-01-23 03:49:09.594791: step: 1836/530, loss: 3.204345557605848e-05
2023-01-23 03:49:10.729027: step: 1840/530, loss: 0.0004479408380575478
2023-01-23 03:49:11.928449: step: 1844/530, loss: 1.6689300537109375e-05
2023-01-23 03:49:13.099920: step: 1848/530, loss: 0.00197104224935174
2023-01-23 03:49:14.267851: step: 1852/530, loss: 1.754760705807712e-05
2023-01-23 03:49:15.449549: step: 1856/530, loss: 0.0062202452681958675
2023-01-23 03:49:16.619011: step: 1860/530, loss: 0.1797536015510559
2023-01-23 03:49:17.774429: step: 1864/530, loss: 0.01392068900167942
2023-01-23 03:49:18.976134: step: 1868/530, loss: 0.0005453109624795616
2023-01-23 03:49:20.167310: step: 1872/530, loss: 5.149840944795869e-06
2023-01-23 03:49:21.346972: step: 1876/530, loss: 0.0009885788895189762
2023-01-23 03:49:22.518192: step: 1880/530, loss: 0.021121788769960403
2023-01-23 03:49:23.709967: step: 1884/530, loss: 0.00025844573974609375
2023-01-23 03:49:24.842885: step: 1888/530, loss: 0.012636709958314896
2023-01-23 03:49:26.048150: step: 1892/530, loss: 0.0004238128603901714
2023-01-23 03:49:27.189135: step: 1896/530, loss: 0.0006933212280273438
2023-01-23 03:49:28.363854: step: 1900/530, loss: 0.36515775322914124
2023-01-23 03:49:29.540742: step: 1904/530, loss: 0.004790115635842085
2023-01-23 03:49:30.680875: step: 1908/530, loss: 0.007931709289550781
2023-01-23 03:49:31.835854: step: 1912/530, loss: 2.6416777473059483e-05
2023-01-23 03:49:33.009791: step: 1916/530, loss: -5.14984139954322e-06
2023-01-23 03:49:34.218773: step: 1920/530, loss: 0.0028755187522619963
2023-01-23 03:49:35.361514: step: 1924/530, loss: 0.00011577606346691027
2023-01-23 03:49:36.519533: step: 1928/530, loss: 0.0026265145279467106
2023-01-23 03:49:37.705109: step: 1932/530, loss: 0.026862526312470436
2023-01-23 03:49:38.865541: step: 1936/530, loss: 0.00019812583923339844
2023-01-23 03:49:40.075232: step: 1940/530, loss: 0.002017402555793524
2023-01-23 03:49:41.249283: step: 1944/530, loss: 0.019564246758818626
2023-01-23 03:49:42.421203: step: 1948/530, loss: 2.717971983656753e-05
2023-01-23 03:49:43.575136: step: 1952/530, loss: 3.623962356869015e-06
2023-01-23 03:49:44.711626: step: 1956/530, loss: 6.895065598655492e-05
2023-01-23 03:49:45.865249: step: 1960/530, loss: 0.0003321647527627647
2023-01-23 03:49:47.004975: step: 1964/530, loss: 0.0006653785821981728
2023-01-23 03:49:48.194728: step: 1968/530, loss: 0.009163380600512028
2023-01-23 03:49:49.365635: step: 1972/530, loss: 0.012134457007050514
2023-01-23 03:49:50.503999: step: 1976/530, loss: 0.0007505416870117188
2023-01-23 03:49:51.671027: step: 1980/530, loss: 0.0051285745576024055
2023-01-23 03:49:52.815066: step: 1984/530, loss: 0.05881378799676895
2023-01-23 03:49:53.982948: step: 1988/530, loss: 0.005851173307746649
2023-01-23 03:49:55.143563: step: 1992/530, loss: 5.092620995128527e-05
2023-01-23 03:49:56.286108: step: 1996/530, loss: 0.02148609235882759
2023-01-23 03:49:57.423992: step: 2000/530, loss: 1.544952465337701e-05
2023-01-23 03:49:58.561907: step: 2004/530, loss: 0.002046298934146762
2023-01-23 03:49:59.697479: step: 2008/530, loss: 0.00047178269596770406
2023-01-23 03:50:00.845577: step: 2012/530, loss: 0.003085231874138117
2023-01-23 03:50:02.024756: step: 2016/530, loss: 0.0004485130193643272
2023-01-23 03:50:03.195835: step: 2020/530, loss: 0.00022335053654387593
2023-01-23 03:50:04.377371: step: 2024/530, loss: 0.0019073486328125
2023-01-23 03:50:05.554029: step: 2028/530, loss: 0.018143033608794212
2023-01-23 03:50:06.752906: step: 2032/530, loss: 0.04486484453082085
2023-01-23 03:50:07.973095: step: 2036/530, loss: 0.10240411758422852
2023-01-23 03:50:09.120690: step: 2040/530, loss: 0.0013899803161621094
2023-01-23 03:50:10.317839: step: 2044/530, loss: 0.008051108568906784
2023-01-23 03:50:11.526730: step: 2048/530, loss: 9.70840483205393e-05
2023-01-23 03:50:12.699193: step: 2052/530, loss: 0.01144037302583456
2023-01-23 03:50:13.869927: step: 2056/530, loss: 0.0005726814270019531
2023-01-23 03:50:15.008857: step: 2060/530, loss: 0.00018634795560501516
2023-01-23 03:50:16.171532: step: 2064/530, loss: 0.17143535614013672
2023-01-23 03:50:17.386324: step: 2068/530, loss: 0.0010038375621661544
2023-01-23 03:50:18.582290: step: 2072/530, loss: 0.029504967853426933
2023-01-23 03:50:19.782788: step: 2076/530, loss: 0.002227306365966797
2023-01-23 03:50:20.934500: step: 2080/530, loss: 0.03633098676800728
2023-01-23 03:50:22.136157: step: 2084/530, loss: 0.008029365912079811
2023-01-23 03:50:23.295901: step: 2088/530, loss: 0.0002578735293354839
2023-01-23 03:50:24.513383: step: 2092/530, loss: 0.0011538505787029862
2023-01-23 03:50:25.692911: step: 2096/530, loss: 0.0033519745338708162
2023-01-23 03:50:26.884213: step: 2100/530, loss: 2.536773718020413e-05
2023-01-23 03:50:28.067394: step: 2104/530, loss: 0.009519577026367188
2023-01-23 03:50:29.239152: step: 2108/530, loss: 0.0391053669154644
2023-01-23 03:50:30.384523: step: 2112/530, loss: 0.0018769741291180253
2023-01-23 03:50:31.566643: step: 2116/530, loss: 0.0025014877319335938
2023-01-23 03:50:32.696538: step: 2120/530, loss: 0.0002906799491029233
==================================================
Loss: 0.013
--------------------
Dev: {'event': {'p': 0.603537981269511, 'r': 0.7723035952063915, 'f1': 0.677570093457944}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Test: {'event': {'p': 0.6663560111835974, 'r': 0.8223116733755031, 'f1': 0.7361647361647363}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Chinese: {'event': {'p': 0.611764705882353, 'r': 0.9629629629629629, 'f1': 0.748201438848921}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Korean: {'event': {'p': 0.5740740740740741, 'r': 0.49206349206349204, 'f1': 0.5299145299145299}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Russian: {'event': {'p': 0.4583333333333333, 'r': 0.6111111111111112, 'f1': 0.5238095238095238}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
New best chinese model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.603537981269511, 'r': 0.7723035952063915, 'f1': 0.677570093457944}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Eng Test for Chinese: {'event': {'p': 0.6663560111835974, 'r': 0.8223116733755031, 'f1': 0.7361647361647363}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Sample Chinese: {'event': {'p': 0.611764705882353, 'r': 0.9629629629629629, 'f1': 0.748201438848921}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5733990147783251, 'r': 0.7749667110519307, 'f1': 0.6591166477916196}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Eng Test for Korean: {'event': {'p': 0.6218005295675199, 'r': 0.8102357676825762, 'f1': 0.7036204744069912}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Sample Korean: {'event': {'p': 0.6417910447761194, 'r': 0.6825396825396826, 'f1': 0.6615384615384614}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6284796573875803, 'r': 0.7816245006657789, 'f1': 0.6967359050445103}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Eng Test for Russian: {'event': {'p': 0.6768263183357524, 'r': 0.80448533640023, 'f1': 0.7351550183920126}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Sample Russian: {'event': {'p': 0.4791666666666667, 'r': 0.6388888888888888, 'f1': 0.5476190476190476}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
******************************
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 03:51:22.836175: step: 4/530, loss: 0.0006740569951944053
2023-01-23 03:51:24.058946: step: 8/530, loss: 7.295608520507812e-05
2023-01-23 03:51:25.218036: step: 12/530, loss: 2.002715973503655e-06
2023-01-23 03:51:26.406513: step: 16/530, loss: 0.46518364548683167
2023-01-23 03:51:27.566671: step: 20/530, loss: 0.012784719467163086
2023-01-23 03:51:28.725171: step: 24/530, loss: 2.288818359375e-05
2023-01-23 03:51:29.930313: step: 28/530, loss: 0.0009852409129962325
2023-01-23 03:51:31.099882: step: 32/530, loss: 0.005530357360839844
2023-01-23 03:51:32.324959: step: 36/530, loss: 0.0014236450660973787
2023-01-23 03:51:33.504358: step: 40/530, loss: 0.0001847267267294228
2023-01-23 03:51:34.658184: step: 44/530, loss: 0.0018189430702477694
2023-01-23 03:51:35.833538: step: 48/530, loss: 0.0001865387021098286
2023-01-23 03:51:36.991078: step: 52/530, loss: 0.008963692933321
2023-01-23 03:51:38.151903: step: 56/530, loss: 0.019423676654696465
2023-01-23 03:51:39.336381: step: 60/530, loss: 0.009451580233871937
2023-01-23 03:51:40.501853: step: 64/530, loss: 1.964569128176663e-05
2023-01-23 03:51:41.667100: step: 68/530, loss: 0.043291185051202774
2023-01-23 03:51:42.866610: step: 72/530, loss: 0.003860521363094449
2023-01-23 03:51:44.005821: step: 76/530, loss: 2.3651124138268642e-05
2023-01-23 03:51:45.130761: step: 80/530, loss: 4.634857032215223e-05
2023-01-23 03:51:46.332952: step: 84/530, loss: 0.0029699327424168587
2023-01-23 03:51:47.497707: step: 88/530, loss: 3.185272362316027e-05
2023-01-23 03:51:48.697514: step: 92/530, loss: 3.051757857974735e-06
2023-01-23 03:51:49.833170: step: 96/530, loss: 0.0005241394392214715
2023-01-23 03:51:51.019166: step: 100/530, loss: 0.015805864706635475
2023-01-23 03:51:52.175546: step: 104/530, loss: 0.0055706980638206005
2023-01-23 03:51:53.352476: step: 108/530, loss: 6.160735938465223e-05
2023-01-23 03:51:54.488254: step: 112/530, loss: 0.0009018898708745837
2023-01-23 03:51:55.656631: step: 116/530, loss: 0.05310382694005966
2023-01-23 03:51:56.835571: step: 120/530, loss: 0.013140535913407803
2023-01-23 03:51:58.008123: step: 124/530, loss: 0.0003645896795205772
2023-01-23 03:51:59.189582: step: 128/530, loss: 0.0032705306075513363
2023-01-23 03:52:00.362939: step: 132/530, loss: 0.00047168732271529734
2023-01-23 03:52:01.507341: step: 136/530, loss: 0.008203315548598766
2023-01-23 03:52:02.663776: step: 140/530, loss: 0.00031948089599609375
2023-01-23 03:52:03.848305: step: 144/530, loss: 0.0029963492415845394
2023-01-23 03:52:05.007774: step: 148/530, loss: 0.0009487151983194053
2023-01-23 03:52:06.169608: step: 152/530, loss: 5.817413239128655e-06
2023-01-23 03:52:07.388236: step: 156/530, loss: 7.600784010719508e-05
2023-01-23 03:52:08.551183: step: 160/530, loss: 0.0006208419799804688
2023-01-23 03:52:09.748210: step: 164/530, loss: 0.012035656720399857
2023-01-23 03:52:10.922430: step: 168/530, loss: 0.007426643744111061
2023-01-23 03:52:12.133351: step: 172/530, loss: 1.201629675051663e-05
2023-01-23 03:52:13.300918: step: 176/530, loss: 0.011675453744828701
2023-01-23 03:52:14.451088: step: 180/530, loss: 0.010170172899961472
2023-01-23 03:52:15.613516: step: 184/530, loss: 0.0017167091136798263
2023-01-23 03:52:16.816427: step: 188/530, loss: 0.004544639959931374
2023-01-23 03:52:17.980165: step: 192/530, loss: 0.06287956237792969
2023-01-23 03:52:19.133309: step: 196/530, loss: 0.04869117960333824
2023-01-23 03:52:20.295933: step: 200/530, loss: 0.0006194591405801475
2023-01-23 03:52:21.497673: step: 204/530, loss: 0.0009937286376953125
2023-01-23 03:52:22.649485: step: 208/530, loss: 0.006678664591163397
2023-01-23 03:52:23.826747: step: 212/530, loss: 0.0019138335483148694
2023-01-23 03:52:25.006076: step: 216/530, loss: 0.04346428066492081
2023-01-23 03:52:26.183463: step: 220/530, loss: 0.006625556852668524
2023-01-23 03:52:27.375844: step: 224/530, loss: 0.027075672522187233
2023-01-23 03:52:28.560476: step: 228/530, loss: 1.583099401614163e-05
2023-01-23 03:52:29.786910: step: 232/530, loss: 0.02287750132381916
2023-01-23 03:52:30.993118: step: 236/530, loss: 0.013226223178207874
2023-01-23 03:52:32.136335: step: 240/530, loss: 0.0020423890091478825
2023-01-23 03:52:33.297183: step: 244/530, loss: 0.006968498695641756
2023-01-23 03:52:34.464916: step: 248/530, loss: 0.00022125244140625
2023-01-23 03:52:35.619782: step: 252/530, loss: 1.7166139514301904e-06
2023-01-23 03:52:36.805530: step: 256/530, loss: 0.0290051456540823
2023-01-23 03:52:37.939547: step: 260/530, loss: 0.009728336706757545
2023-01-23 03:52:39.085133: step: 264/530, loss: 0.0008256912115029991
2023-01-23 03:52:40.218815: step: 268/530, loss: 0.004562854766845703
2023-01-23 03:52:41.435506: step: 272/530, loss: 0.002161407610401511
2023-01-23 03:52:42.612838: step: 276/530, loss: 0.00025234222994185984
2023-01-23 03:52:43.811893: step: 280/530, loss: 0.0039386749267578125
2023-01-23 03:52:44.984070: step: 284/530, loss: 0.0054306029342114925
2023-01-23 03:52:46.152236: step: 288/530, loss: 0.00012674331082962453
2023-01-23 03:52:47.366502: step: 292/530, loss: 4.00543212890625e-05
2023-01-23 03:52:48.522020: step: 296/530, loss: 0.0003856658877339214
2023-01-23 03:52:49.694214: step: 300/530, loss: 0.0019322395091876388
2023-01-23 03:52:50.851788: step: 304/530, loss: 0.0006701469537802041
2023-01-23 03:52:52.034147: step: 308/530, loss: 0.008366823196411133
2023-01-23 03:52:53.192793: step: 312/530, loss: 0.0012504577171057463
2023-01-23 03:52:54.349776: step: 316/530, loss: 0.018553685396909714
2023-01-23 03:52:55.522453: step: 320/530, loss: 0.0001993656187551096
2023-01-23 03:52:56.655833: step: 324/530, loss: 0.0007571220630779862
2023-01-23 03:52:57.853018: step: 328/530, loss: -3.4809111184586072e-06
2023-01-23 03:52:59.005884: step: 332/530, loss: 0.0003067016659770161
2023-01-23 03:53:00.147819: step: 336/530, loss: 0.013459968380630016
2023-01-23 03:53:01.325628: step: 340/530, loss: 0.00576672563329339
2023-01-23 03:53:02.514704: step: 344/530, loss: 0.0013429642422124743
2023-01-23 03:53:03.706647: step: 348/530, loss: 0.0196272861212492
2023-01-23 03:53:04.877111: step: 352/530, loss: 0.00039253238355740905
2023-01-23 03:53:06.028837: step: 356/530, loss: 0.006956195924431086
2023-01-23 03:53:07.243126: step: 360/530, loss: 0.011643314734101295
2023-01-23 03:53:08.427889: step: 364/530, loss: 0.00018749237642623484
2023-01-23 03:53:09.558632: step: 368/530, loss: 0.030957603827118874
2023-01-23 03:53:10.737223: step: 372/530, loss: 0.008719539269804955
2023-01-23 03:53:11.960892: step: 376/530, loss: 0.2043663114309311
2023-01-23 03:53:13.162535: step: 380/530, loss: 0.010303784161806107
2023-01-23 03:53:14.355003: step: 384/530, loss: 0.0002574920654296875
2023-01-23 03:53:15.550392: step: 388/530, loss: 0.00010809898958541453
2023-01-23 03:53:16.681106: step: 392/530, loss: 0.03522491827607155
2023-01-23 03:53:17.858011: step: 396/530, loss: 0.0021526338532567024
2023-01-23 03:53:19.035645: step: 400/530, loss: 0.00030069350032135844
2023-01-23 03:53:20.193116: step: 404/530, loss: 0.0008027076837606728
2023-01-23 03:53:21.342869: step: 408/530, loss: 6.4849853515625e-05
2023-01-23 03:53:22.517307: step: 412/530, loss: 0.00031785963801667094
2023-01-23 03:53:23.699707: step: 416/530, loss: 1.850128137448337e-05
2023-01-23 03:53:24.875370: step: 420/530, loss: 0.011610651388764381
2023-01-23 03:53:26.023885: step: 424/530, loss: 0.0002832413010764867
2023-01-23 03:53:27.186155: step: 428/530, loss: 0.009240913204848766
2023-01-23 03:53:28.369541: step: 432/530, loss: 0.021496916189789772
2023-01-23 03:53:29.501849: step: 436/530, loss: 1.1539459592313506e-05
2023-01-23 03:53:30.676533: step: 440/530, loss: 0.023509692400693893
2023-01-23 03:53:31.869429: step: 444/530, loss: 8.583068620282575e-07
2023-01-23 03:53:33.087192: step: 448/530, loss: 0.0003246307314839214
2023-01-23 03:53:34.259325: step: 452/530, loss: 0.00047140123206190765
2023-01-23 03:53:35.436945: step: 456/530, loss: 0.02174091339111328
2023-01-23 03:53:36.620551: step: 460/530, loss: 0.05800876393914223
2023-01-23 03:53:37.781219: step: 464/530, loss: 1.8775463104248047e-05
2023-01-23 03:53:39.044611: step: 468/530, loss: 0.0005529404152184725
2023-01-23 03:53:40.176593: step: 472/530, loss: -5.722046125811175e-07
2023-01-23 03:53:41.345071: step: 476/530, loss: 0.0008450031746178865
2023-01-23 03:53:42.512597: step: 480/530, loss: 0.040723226964473724
2023-01-23 03:53:43.690648: step: 484/530, loss: 0.025408267974853516
2023-01-23 03:53:44.857793: step: 488/530, loss: 0.0025696754455566406
2023-01-23 03:53:46.050270: step: 492/530, loss: 0.0008945465087890625
2023-01-23 03:53:47.206055: step: 496/530, loss: 0.00018768310837913305
2023-01-23 03:53:48.332528: step: 500/530, loss: 0.00019459723262116313
2023-01-23 03:53:49.524876: step: 504/530, loss: 0.0008348465198650956
2023-01-23 03:53:50.693858: step: 508/530, loss: 0.002517747925594449
2023-01-23 03:53:51.826705: step: 512/530, loss: 0.026071738451719284
2023-01-23 03:53:52.971273: step: 516/530, loss: 0.00955886859446764
2023-01-23 03:53:54.150949: step: 520/530, loss: 0.0028583526145666838
2023-01-23 03:53:55.310949: step: 524/530, loss: 0.045081425458192825
2023-01-23 03:53:56.508791: step: 528/530, loss: 0.028779126703739166
2023-01-23 03:53:57.675916: step: 532/530, loss: 0.0012316703796386719
2023-01-23 03:53:58.801091: step: 536/530, loss: 0.009562588296830654
2023-01-23 03:54:00.002127: step: 540/530, loss: 4.8255922592943534e-05
2023-01-23 03:54:01.177238: step: 544/530, loss: 0.0045378683134913445
2023-01-23 03:54:02.357240: step: 548/530, loss: 0.008693314157426357
2023-01-23 03:54:03.517558: step: 552/530, loss: 0.001110076904296875
2023-01-23 03:54:04.669695: step: 556/530, loss: 0.038436368107795715
2023-01-23 03:54:05.820067: step: 560/530, loss: 0.001132714794948697
2023-01-23 03:54:06.974002: step: 564/530, loss: 0.00012683868408203125
2023-01-23 03:54:08.151309: step: 568/530, loss: 0.010332107543945312
2023-01-23 03:54:09.296067: step: 572/530, loss: 0.00013303756713867188
2023-01-23 03:54:10.461077: step: 576/530, loss: 0.08344526588916779
2023-01-23 03:54:11.649611: step: 580/530, loss: 0.000332736992277205
2023-01-23 03:54:12.809184: step: 584/530, loss: 0.005936527159065008
2023-01-23 03:54:13.978759: step: 588/530, loss: 0.005217742640525103
2023-01-23 03:54:15.156510: step: 592/530, loss: 0.03415513038635254
2023-01-23 03:54:16.302443: step: 596/530, loss: 0.0014522552955895662
2023-01-23 03:54:17.441198: step: 600/530, loss: 0.0443662628531456
2023-01-23 03:54:18.589534: step: 604/530, loss: 0.003227138426154852
2023-01-23 03:54:19.736530: step: 608/530, loss: 0.0006905555492267013
2023-01-23 03:54:20.907242: step: 612/530, loss: 0.00015659333439543843
2023-01-23 03:54:22.071850: step: 616/530, loss: 0.0003570556582417339
2023-01-23 03:54:23.233735: step: 620/530, loss: 0.027857590466737747
2023-01-23 03:54:24.413481: step: 624/530, loss: 0.014815999194979668
2023-01-23 03:54:25.582189: step: 628/530, loss: 0.00278224959038198
2023-01-23 03:54:26.762227: step: 632/530, loss: 3.623962811616366e-06
2023-01-23 03:54:27.907124: step: 636/530, loss: 0.0005414963234215975
2023-01-23 03:54:29.079673: step: 640/530, loss: 0.00013637544179800898
2023-01-23 03:54:30.235882: step: 644/530, loss: 7.45773286325857e-05
2023-01-23 03:54:31.405333: step: 648/530, loss: 0.00028553008451126516
2023-01-23 03:54:32.612615: step: 652/530, loss: 0.005470085423439741
2023-01-23 03:54:33.813111: step: 656/530, loss: 0.0020800591446459293
2023-01-23 03:54:34.966498: step: 660/530, loss: 0.018434524536132812
2023-01-23 03:54:36.162754: step: 664/530, loss: 0.0002639770682435483
2023-01-23 03:54:37.326884: step: 668/530, loss: 5.197524842515122e-06
2023-01-23 03:54:38.544454: step: 672/530, loss: 0.00237197894603014
2023-01-23 03:54:39.681190: step: 676/530, loss: 0.00010032654245151207
2023-01-23 03:54:40.783591: step: 680/530, loss: 0.0005856514326296747
2023-01-23 03:54:41.972946: step: 684/530, loss: 0.003860855009406805
2023-01-23 03:54:43.171622: step: 688/530, loss: 0.007921313866972923
2023-01-23 03:54:44.299007: step: 692/530, loss: 0.02006354369223118
2023-01-23 03:54:45.489484: step: 696/530, loss: 0.08081436157226562
2023-01-23 03:54:46.716650: step: 700/530, loss: 0.0035410881973803043
2023-01-23 03:54:47.859342: step: 704/530, loss: 0.009917736053466797
2023-01-23 03:54:49.100062: step: 708/530, loss: 0.00015592575073242188
2023-01-23 03:54:50.279173: step: 712/530, loss: 0.10614929348230362
2023-01-23 03:54:51.470112: step: 716/530, loss: 1.6641617548884824e-05
2023-01-23 03:54:52.658677: step: 720/530, loss: 0.05105409398674965
2023-01-23 03:54:53.796854: step: 724/530, loss: 0.00033216478186659515
2023-01-23 03:54:55.004251: step: 728/530, loss: 0.009569644927978516
2023-01-23 03:54:56.173026: step: 732/530, loss: 0.00016813278489280492
2023-01-23 03:54:57.315575: step: 736/530, loss: 0.00020885467529296875
2023-01-23 03:54:58.475797: step: 740/530, loss: 0.024511337280273438
2023-01-23 03:54:59.626004: step: 744/530, loss: 0.03788242116570473
2023-01-23 03:55:00.807121: step: 748/530, loss: 0.0008025169372558594
2023-01-23 03:55:01.965393: step: 752/530, loss: 0.004583549685776234
2023-01-23 03:55:03.125815: step: 756/530, loss: 0.014370251446962357
2023-01-23 03:55:04.305291: step: 760/530, loss: 0.007969665341079235
2023-01-23 03:55:05.518897: step: 764/530, loss: 0.001255798269994557
2023-01-23 03:55:06.682105: step: 768/530, loss: 6.246567500056699e-05
2023-01-23 03:55:07.833804: step: 772/530, loss: 0.010210228152573109
2023-01-23 03:55:09.008065: step: 776/530, loss: 3.075599670410156e-05
2023-01-23 03:55:10.234884: step: 780/530, loss: 0.0077866557985544205
2023-01-23 03:55:11.413590: step: 784/530, loss: 8.435249037574977e-05
2023-01-23 03:55:12.613434: step: 788/530, loss: 0.00010852813284145668
2023-01-23 03:55:13.810435: step: 792/530, loss: 0.00587120046839118
2023-01-23 03:55:14.985336: step: 796/530, loss: 0.006425237748771906
2023-01-23 03:55:16.120465: step: 800/530, loss: 0.029317380860447884
2023-01-23 03:55:17.279614: step: 804/530, loss: 0.44524702429771423
2023-01-23 03:55:18.440993: step: 808/530, loss: 9.829997725319117e-05
2023-01-23 03:55:19.622978: step: 812/530, loss: 0.0011178969871252775
2023-01-23 03:55:20.849843: step: 816/530, loss: 2.9325485229492188e-05
2023-01-23 03:55:22.004500: step: 820/530, loss: 0.007728386204689741
2023-01-23 03:55:23.186767: step: 824/530, loss: 8.42094377730973e-05
2023-01-23 03:55:24.386112: step: 828/530, loss: 0.007036400027573109
2023-01-23 03:55:25.598998: step: 832/530, loss: 0.0013431073166429996
2023-01-23 03:55:26.782438: step: 836/530, loss: 0.0010127543937414885
2023-01-23 03:55:27.922230: step: 840/530, loss: 0.0026439668145030737
2023-01-23 03:55:29.114526: step: 844/530, loss: 0.01310262642800808
2023-01-23 03:55:30.237948: step: 848/530, loss: 4.7445296331716236e-06
2023-01-23 03:55:31.408199: step: 852/530, loss: 0.002571487333625555
2023-01-23 03:55:32.572574: step: 856/530, loss: 0.005652046296745539
2023-01-23 03:55:33.771118: step: 860/530, loss: 0.0010980606311932206
2023-01-23 03:55:34.968912: step: 864/530, loss: 0.0022942544892430305
2023-01-23 03:55:36.135105: step: 868/530, loss: 0.025679968297481537
2023-01-23 03:55:37.343664: step: 872/530, loss: 0.014879417605698109
2023-01-23 03:55:38.514013: step: 876/530, loss: 0.0015710832085460424
2023-01-23 03:55:39.675813: step: 880/530, loss: 3.24249276673072e-06
2023-01-23 03:55:40.837990: step: 884/530, loss: 0.006766891106963158
2023-01-23 03:55:42.040033: step: 888/530, loss: 0.0001432418794138357
2023-01-23 03:55:43.252452: step: 892/530, loss: 5.550384594243951e-05
2023-01-23 03:55:44.425554: step: 896/530, loss: 0.003029441926628351
2023-01-23 03:55:45.608500: step: 900/530, loss: 1.792907642084174e-05
2023-01-23 03:55:46.753562: step: 904/530, loss: 0.019577981904149055
2023-01-23 03:55:47.911160: step: 908/530, loss: 0.011146735399961472
2023-01-23 03:55:49.062290: step: 912/530, loss: 2.231597864010837e-05
2023-01-23 03:55:50.222330: step: 916/530, loss: 5.53131121705519e-06
2023-01-23 03:55:51.398901: step: 920/530, loss: 0.03512993082404137
2023-01-23 03:55:52.543820: step: 924/530, loss: 0.04661102220416069
2023-01-23 03:55:53.706566: step: 928/530, loss: 0.04242458567023277
2023-01-23 03:55:54.845443: step: 932/530, loss: -1.277923547604587e-05
2023-01-23 03:55:56.018417: step: 936/530, loss: 0.0012426376342773438
2023-01-23 03:55:57.161734: step: 940/530, loss: 0.0002252578706247732
2023-01-23 03:55:58.292960: step: 944/530, loss: 0.00174627301748842
2023-01-23 03:55:59.431463: step: 948/530, loss: 0.0011163236340507865
2023-01-23 03:56:00.630000: step: 952/530, loss: 0.0080099580809474
2023-01-23 03:56:01.799322: step: 956/530, loss: 0.00010657311213435605
2023-01-23 03:56:02.936221: step: 960/530, loss: 0.0003981590270996094
2023-01-23 03:56:04.096045: step: 964/530, loss: 4.39643845311366e-05
2023-01-23 03:56:05.264048: step: 968/530, loss: 9.355843212688342e-05
2023-01-23 03:56:06.433650: step: 972/530, loss: 0.00485153216868639
2023-01-23 03:56:07.608402: step: 976/530, loss: 0.00027189255342818797
2023-01-23 03:56:08.787364: step: 980/530, loss: 0.035962868481874466
2023-01-23 03:56:09.989362: step: 984/530, loss: 0.046094752848148346
2023-01-23 03:56:11.197761: step: 988/530, loss: 0.001702976180240512
2023-01-23 03:56:12.406487: step: 992/530, loss: 0.006884765811264515
2023-01-23 03:56:13.537745: step: 996/530, loss: 0.07497740536928177
2023-01-23 03:56:14.727525: step: 1000/530, loss: 0.007089042570441961
2023-01-23 03:56:15.889128: step: 1004/530, loss: 9.33647170313634e-05
2023-01-23 03:56:17.084876: step: 1008/530, loss: 0.00031538010807707906
2023-01-23 03:56:18.283433: step: 1012/530, loss: 7.915497008070815e-06
2023-01-23 03:56:19.460187: step: 1016/530, loss: 0.012768586166203022
2023-01-23 03:56:20.639055: step: 1020/530, loss: 0.00975713785737753
2023-01-23 03:56:21.817459: step: 1024/530, loss: 0.00567894009873271
2023-01-23 03:56:22.989962: step: 1028/530, loss: 0.00019588469876907766
2023-01-23 03:56:24.180570: step: 1032/530, loss: 0.050194643437862396
2023-01-23 03:56:25.371618: step: 1036/530, loss: 0.03354144096374512
2023-01-23 03:56:26.544667: step: 1040/530, loss: 0.024974346160888672
2023-01-23 03:56:27.677289: step: 1044/530, loss: 9.450912330066785e-05
2023-01-23 03:56:28.933331: step: 1048/530, loss: 0.13647671043872833
2023-01-23 03:56:30.085816: step: 1052/530, loss: 0.03473663330078125
2023-01-23 03:56:31.279467: step: 1056/530, loss: 2.9182432626839727e-05
2023-01-23 03:56:32.477531: step: 1060/530, loss: 0.008570862002670765
2023-01-23 03:56:33.642512: step: 1064/530, loss: 0.00018696785264182836
2023-01-23 03:56:34.814247: step: 1068/530, loss: 0.0032999992836266756
2023-01-23 03:56:35.969910: step: 1072/530, loss: 0.0005920410039834678
2023-01-23 03:56:37.119614: step: 1076/530, loss: 0.0022314072120934725
2023-01-23 03:56:38.319725: step: 1080/530, loss: 0.020543480291962624
2023-01-23 03:56:39.477104: step: 1084/530, loss: 0.029347991570830345
2023-01-23 03:56:40.676963: step: 1088/530, loss: 0.04615059122443199
2023-01-23 03:56:41.891138: step: 1092/530, loss: 0.0012877463595941663
2023-01-23 03:56:43.063388: step: 1096/530, loss: 0.0014866829151287675
2023-01-23 03:56:44.246513: step: 1100/530, loss: 0.0016661644913256168
2023-01-23 03:56:45.467066: step: 1104/530, loss: 0.0003555297735147178
2023-01-23 03:56:46.637670: step: 1108/530, loss: 0.00023202896409202367
2023-01-23 03:56:47.827380: step: 1112/530, loss: 0.009560585021972656
2023-01-23 03:56:48.981114: step: 1116/530, loss: 0.01760578155517578
2023-01-23 03:56:50.130534: step: 1120/530, loss: 0.000244140625
2023-01-23 03:56:51.288560: step: 1124/530, loss: 0.03168916702270508
2023-01-23 03:56:52.458243: step: 1128/530, loss: 3.3092499506892636e-05
2023-01-23 03:56:53.623725: step: 1132/530, loss: 0.0003772735653910786
2023-01-23 03:56:54.787634: step: 1136/530, loss: 6.008148375258315e-06
2023-01-23 03:56:55.955449: step: 1140/530, loss: 0.00023326874361373484
2023-01-23 03:56:57.124169: step: 1144/530, loss: 0.00015196800814010203
2023-01-23 03:56:58.292697: step: 1148/530, loss: 7.152557373046875e-07
2023-01-23 03:56:59.522782: step: 1152/530, loss: 0.05049953609704971
2023-01-23 03:57:00.707313: step: 1156/530, loss: 0.0037563324440270662
2023-01-23 03:57:01.902024: step: 1160/530, loss: 0.028315259143710136
2023-01-23 03:57:03.094803: step: 1164/530, loss: 2.4795533590804553e-06
2023-01-23 03:57:04.229207: step: 1168/530, loss: 0.008877134881913662
2023-01-23 03:57:05.430605: step: 1172/530, loss: 0.00611801166087389
2023-01-23 03:57:06.588070: step: 1176/530, loss: 0.0030728341080248356
2023-01-23 03:57:07.727738: step: 1180/530, loss: 0.023630525916814804
2023-01-23 03:57:08.882626: step: 1184/530, loss: 0.012866735458374023
2023-01-23 03:57:10.042333: step: 1188/530, loss: 0.016594409942626953
2023-01-23 03:57:11.210688: step: 1192/530, loss: 0.7331809997558594
2023-01-23 03:57:12.393031: step: 1196/530, loss: 0.023678209632635117
2023-01-23 03:57:13.552540: step: 1200/530, loss: 0.00012874603271484375
2023-01-23 03:57:14.736552: step: 1204/530, loss: 0.06244392320513725
2023-01-23 03:57:15.924026: step: 1208/530, loss: 0.001530295587144792
2023-01-23 03:57:17.119270: step: 1212/530, loss: 0.0306854248046875
2023-01-23 03:57:18.298452: step: 1216/530, loss: 0.009037780575454235
2023-01-23 03:57:19.474032: step: 1220/530, loss: 0.0001447677641408518
2023-01-23 03:57:20.641281: step: 1224/530, loss: 2.1266936528263614e-05
2023-01-23 03:57:21.791796: step: 1228/530, loss: 0.0014192580711096525
2023-01-23 03:57:22.936867: step: 1232/530, loss: 0.0001623153657419607
2023-01-23 03:57:24.098036: step: 1236/530, loss: 6.10351571594947e-06
2023-01-23 03:57:25.277543: step: 1240/530, loss: 0.009286880493164062
2023-01-23 03:57:26.444810: step: 1244/530, loss: 0.00759048480540514
2023-01-23 03:57:27.586656: step: 1248/530, loss: 0.2149791717529297
2023-01-23 03:57:28.731817: step: 1252/530, loss: 0.004594040103256702
2023-01-23 03:57:29.873172: step: 1256/530, loss: 0.010485362261533737
2023-01-23 03:57:31.070515: step: 1260/530, loss: 0.00025777818518690765
2023-01-23 03:57:32.221633: step: 1264/530, loss: 3.108978125965223e-05
2023-01-23 03:57:33.359767: step: 1268/530, loss: 3.724098496604711e-05
2023-01-23 03:57:34.544864: step: 1272/530, loss: 0.02824382856488228
2023-01-23 03:57:35.711811: step: 1276/530, loss: 0.0008536339155398309
2023-01-23 03:57:36.865313: step: 1280/530, loss: 0.021918296813964844
2023-01-23 03:57:38.054692: step: 1284/530, loss: 2.8896331059513614e-05
2023-01-23 03:57:39.216874: step: 1288/530, loss: 0.002739048097282648
2023-01-23 03:57:40.354648: step: 1292/530, loss: 0.0001479625643696636
2023-01-23 03:57:41.535173: step: 1296/530, loss: 0.006362724583595991
2023-01-23 03:57:42.655013: step: 1300/530, loss: 6.618500628974289e-05
2023-01-23 03:57:43.839800: step: 1304/530, loss: 0.00021419525728560984
2023-01-23 03:57:45.022144: step: 1308/530, loss: 6.29425039733178e-06
2023-01-23 03:57:46.215890: step: 1312/530, loss: 0.08460979163646698
2023-01-23 03:57:47.412530: step: 1316/530, loss: 7.562637620139867e-05
2023-01-23 03:57:48.551973: step: 1320/530, loss: 0.014352512545883656
2023-01-23 03:57:49.725766: step: 1324/530, loss: 0.02317953109741211
2023-01-23 03:57:50.895229: step: 1328/530, loss: 0.0035579681862145662
2023-01-23 03:57:52.087807: step: 1332/530, loss: 0.07616596668958664
2023-01-23 03:57:53.277497: step: 1336/530, loss: 0.03576679527759552
2023-01-23 03:57:54.416349: step: 1340/530, loss: 0.012133312411606312
2023-01-23 03:57:55.535583: step: 1344/530, loss: 1.5258789289873675e-06
2023-01-23 03:57:56.720720: step: 1348/530, loss: 0.00012559890456032008
2023-01-23 03:57:57.910229: step: 1352/530, loss: 5.292892819852568e-05
2023-01-23 03:57:59.085447: step: 1356/530, loss: 0.0052702901884913445
2023-01-23 03:58:00.289370: step: 1360/530, loss: 0.029619980603456497
2023-01-23 03:58:01.454807: step: 1364/530, loss: 0.01212606392800808
2023-01-23 03:58:02.663434: step: 1368/530, loss: 0.0018018722767010331
2023-01-23 03:58:03.818855: step: 1372/530, loss: 0.0028234960045665503
2023-01-23 03:58:04.981811: step: 1376/530, loss: 0.00011181831359863281
2023-01-23 03:58:06.113601: step: 1380/530, loss: 0.0032169341575354338
2023-01-23 03:58:07.256579: step: 1384/530, loss: 0.03360586240887642
2023-01-23 03:58:08.467991: step: 1388/530, loss: 3.032684253412299e-05
2023-01-23 03:58:09.618455: step: 1392/530, loss: 0.0016109467251226306
2023-01-23 03:58:10.790645: step: 1396/530, loss: 0.0010810851817950606
2023-01-23 03:58:11.986957: step: 1400/530, loss: 0.006634521298110485
2023-01-23 03:58:13.142009: step: 1404/530, loss: 0.0003199577331542969
2023-01-23 03:58:14.346299: step: 1408/530, loss: 0.0006072759279049933
2023-01-23 03:58:15.486760: step: 1412/530, loss: 0.06238015368580818
2023-01-23 03:58:16.713756: step: 1416/530, loss: 0.0003296852228231728
2023-01-23 03:58:17.898803: step: 1420/530, loss: 0.0027104378677904606
2023-01-23 03:58:19.099374: step: 1424/530, loss: 0.006822013761848211
2023-01-23 03:58:20.284922: step: 1428/530, loss: 1.3828277587890625e-05
2023-01-23 03:58:21.419958: step: 1432/530, loss: 0.010188483633100986
2023-01-23 03:58:22.594807: step: 1436/530, loss: 0.004301690962165594
2023-01-23 03:58:23.796610: step: 1440/530, loss: 0.001052045845426619
2023-01-23 03:58:24.955332: step: 1444/530, loss: 0.003041595220565796
2023-01-23 03:58:26.130882: step: 1448/530, loss: 0.0009585380903445184
2023-01-23 03:58:27.309407: step: 1452/530, loss: 0.00013246537127997726
2023-01-23 03:58:28.520462: step: 1456/530, loss: 6.246566954359878e-06
2023-01-23 03:58:29.676464: step: 1460/530, loss: 0.0012956619029864669
2023-01-23 03:58:30.852507: step: 1464/530, loss: 0.0021375655196607113
2023-01-23 03:58:32.031464: step: 1468/530, loss: 8.783341036178172e-05
2023-01-23 03:58:33.203320: step: 1472/530, loss: 0.023109912872314453
2023-01-23 03:58:34.313475: step: 1476/530, loss: 0.001922702882438898
2023-01-23 03:58:35.511483: step: 1480/530, loss: 0.0004650116025004536
2023-01-23 03:58:36.687145: step: 1484/530, loss: 6.85691848048009e-05
2023-01-23 03:58:37.835014: step: 1488/530, loss: 8.277893357444555e-05
2023-01-23 03:58:38.989810: step: 1492/530, loss: 0.011076449416577816
2023-01-23 03:58:40.138136: step: 1496/530, loss: 3.1471245165448636e-06
2023-01-23 03:58:41.322049: step: 1500/530, loss: 0.03397378697991371
2023-01-23 03:58:42.505096: step: 1504/530, loss: 0.0004516601620707661
2023-01-23 03:58:43.710400: step: 1508/530, loss: 0.0021149637177586555
2023-01-23 03:58:44.857949: step: 1512/530, loss: 0.002013301942497492
2023-01-23 03:58:46.022696: step: 1516/530, loss: 9.803772263694555e-05
2023-01-23 03:58:47.187191: step: 1520/530, loss: 0.025347614660859108
2023-01-23 03:58:48.332564: step: 1524/530, loss: 0.0056841373443603516
2023-01-23 03:58:49.510822: step: 1528/530, loss: 0.0022999763023108244
2023-01-23 03:58:50.660059: step: 1532/530, loss: 1.544952465337701e-05
2023-01-23 03:58:51.810261: step: 1536/530, loss: 0.0358307845890522
2023-01-23 03:58:52.993921: step: 1540/530, loss: 0.00011887550499523059
2023-01-23 03:58:54.169573: step: 1544/530, loss: 0.006964207161217928
2023-01-23 03:58:55.336874: step: 1548/530, loss: 0.03176441043615341
2023-01-23 03:58:56.519871: step: 1552/530, loss: 0.002363491104915738
2023-01-23 03:58:57.656430: step: 1556/530, loss: 0.004384422674775124
2023-01-23 03:58:58.816239: step: 1560/530, loss: 0.001578474068082869
2023-01-23 03:59:00.008145: step: 1564/530, loss: 0.0002208709775004536
2023-01-23 03:59:01.193133: step: 1568/530, loss: 0.0006872176891192794
2023-01-23 03:59:02.381088: step: 1572/530, loss: 8.735656592762098e-05
2023-01-23 03:59:03.527390: step: 1576/530, loss: 0.012870502658188343
2023-01-23 03:59:04.709645: step: 1580/530, loss: 1.2111663636460435e-05
2023-01-23 03:59:05.905421: step: 1584/530, loss: 0.00031700136605650187
2023-01-23 03:59:07.099440: step: 1588/530, loss: 0.00013303756713867188
2023-01-23 03:59:08.279314: step: 1592/530, loss: 0.01388464029878378
2023-01-23 03:59:09.465376: step: 1596/530, loss: 0.002241134876385331
2023-01-23 03:59:10.628567: step: 1600/530, loss: 0.005175304599106312
2023-01-23 03:59:11.822136: step: 1604/530, loss: 0.0003341674746479839
2023-01-23 03:59:12.958617: step: 1608/530, loss: 0.0003044128534384072
2023-01-23 03:59:14.139289: step: 1612/530, loss: 0.030898094177246094
2023-01-23 03:59:15.330392: step: 1616/530, loss: 0.05405378341674805
2023-01-23 03:59:16.470191: step: 1620/530, loss: 0.00025281906710006297
2023-01-23 03:59:17.664364: step: 1624/530, loss: 0.012464333325624466
2023-01-23 03:59:18.855306: step: 1628/530, loss: 0.005871963687241077
2023-01-23 03:59:19.999005: step: 1632/530, loss: 0.0002311706484761089
2023-01-23 03:59:21.176735: step: 1636/530, loss: 0.0046561239287257195
2023-01-23 03:59:22.327071: step: 1640/530, loss: 0.0007787704234942794
2023-01-23 03:59:23.504748: step: 1644/530, loss: 0.05828724056482315
2023-01-23 03:59:24.678638: step: 1648/530, loss: 0.005613517947494984
2023-01-23 03:59:25.859683: step: 1652/530, loss: 8.859634544933215e-05
2023-01-23 03:59:27.006112: step: 1656/530, loss: 0.014995479956269264
2023-01-23 03:59:28.186973: step: 1660/530, loss: 0.0005239486927166581
2023-01-23 03:59:29.342551: step: 1664/530, loss: 0.0035930632147938013
2023-01-23 03:59:30.522578: step: 1668/530, loss: 0.0002971649228129536
2023-01-23 03:59:31.650127: step: 1672/530, loss: 0.008928203955292702
2023-01-23 03:59:32.815961: step: 1676/530, loss: 0.026163674890995026
2023-01-23 03:59:33.944143: step: 1680/530, loss: 0.0001846313534770161
2023-01-23 03:59:35.097345: step: 1684/530, loss: 0.001850128173828125
2023-01-23 03:59:36.229649: step: 1688/530, loss: 0.01158752478659153
2023-01-23 03:59:37.392035: step: 1692/530, loss: 0.00013198853412177414
2023-01-23 03:59:38.559067: step: 1696/530, loss: 7.629394644936838e-07
2023-01-23 03:59:39.752766: step: 1700/530, loss: 0.06135311350226402
2023-01-23 03:59:40.959499: step: 1704/530, loss: 0.00010347366333007812
2023-01-23 03:59:42.122453: step: 1708/530, loss: 0.010078048333525658
2023-01-23 03:59:43.350722: step: 1712/530, loss: -2.0694733393611386e-05
2023-01-23 03:59:44.526674: step: 1716/530, loss: 0.03971848264336586
2023-01-23 03:59:45.721249: step: 1720/530, loss: 0.005565356928855181
2023-01-23 03:59:46.895797: step: 1724/530, loss: 0.00013256072998046875
2023-01-23 03:59:48.042999: step: 1728/530, loss: 0.0007171630859375
2023-01-23 03:59:49.209977: step: 1732/530, loss: 0.011522389017045498
2023-01-23 03:59:50.346151: step: 1736/530, loss: 0.0003811836359091103
2023-01-23 03:59:51.508780: step: 1740/530, loss: 9.117127046920359e-05
2023-01-23 03:59:52.682055: step: 1744/530, loss: 0.04341239854693413
2023-01-23 03:59:53.850238: step: 1748/530, loss: 0.00011978149996139109
2023-01-23 03:59:55.018703: step: 1752/530, loss: 0.0016124247340485454
2023-01-23 03:59:56.159309: step: 1756/530, loss: 0.026941873133182526
2023-01-23 03:59:57.318298: step: 1760/530, loss: 0.0016798973083496094
2023-01-23 03:59:58.491570: step: 1764/530, loss: 0.0005294799921102822
2023-01-23 03:59:59.677808: step: 1768/530, loss: 0.0002500057453289628
2023-01-23 04:00:00.852470: step: 1772/530, loss: 0.0006555557483807206
2023-01-23 04:00:02.014124: step: 1776/530, loss: 0.0005375385517254472
2023-01-23 04:00:03.189062: step: 1780/530, loss: 0.00018386841111350805
2023-01-23 04:00:04.354563: step: 1784/530, loss: 0.006489753723144531
2023-01-23 04:00:05.549134: step: 1788/530, loss: 0.00165138253942132
2023-01-23 04:00:06.709935: step: 1792/530, loss: 0.020051386207342148
2023-01-23 04:00:07.888186: step: 1796/530, loss: 0.0018508911598473787
2023-01-23 04:00:09.031088: step: 1800/530, loss: 2.384185791015625e-05
2023-01-23 04:00:10.194982: step: 1804/530, loss: 0.022998999804258347
2023-01-23 04:00:11.329855: step: 1808/530, loss: 0.07964038848876953
2023-01-23 04:00:12.470575: step: 1812/530, loss: 0.00139369978569448
2023-01-23 04:00:13.651839: step: 1816/530, loss: 0.0007360458257608116
2023-01-23 04:00:14.818887: step: 1820/530, loss: 0.010867023840546608
2023-01-23 04:00:15.951448: step: 1824/530, loss: 7.62939453125e-06
2023-01-23 04:00:17.103478: step: 1828/530, loss: 0.0028465271461755037
2023-01-23 04:00:18.252196: step: 1832/530, loss: 0.0019508362747728825
2023-01-23 04:00:19.463961: step: 1836/530, loss: 0.0008322715875692666
2023-01-23 04:00:20.614559: step: 1840/530, loss: -1.697540210443549e-05
2023-01-23 04:00:21.745745: step: 1844/530, loss: 0.03522701561450958
2023-01-23 04:00:22.908644: step: 1848/530, loss: 0.045407772064208984
2023-01-23 04:00:24.066311: step: 1852/530, loss: 0.0006903648609295487
2023-01-23 04:00:25.261374: step: 1856/530, loss: 0.00048170090303756297
2023-01-23 04:00:26.428209: step: 1860/530, loss: 0.0032573698554188013
2023-01-23 04:00:27.614313: step: 1864/530, loss: 0.00097570416983217
2023-01-23 04:00:28.749938: step: 1868/530, loss: 1.4352799553307705e-05
2023-01-23 04:00:29.926031: step: 1872/530, loss: 7.324219041038305e-05
2023-01-23 04:00:31.095651: step: 1876/530, loss: 0.0012922286987304688
2023-01-23 04:00:32.272892: step: 1880/530, loss: 0.06396484375
2023-01-23 04:00:33.442761: step: 1884/530, loss: 9.684562974143773e-05
2023-01-23 04:00:34.649916: step: 1888/530, loss: 0.00028438569279387593
2023-01-23 04:00:35.828215: step: 1892/530, loss: 0.0044876099564135075
2023-01-23 04:00:37.019817: step: 1896/530, loss: 0.00038166047306731343
2023-01-23 04:00:38.194918: step: 1900/530, loss: 0.011277103796601295
2023-01-23 04:00:39.391120: step: 1904/530, loss: 0.0171876922249794
2023-01-23 04:00:40.562153: step: 1908/530, loss: 0.008937835693359375
2023-01-23 04:00:41.724621: step: 1912/530, loss: 0.001917076064273715
2023-01-23 04:00:42.904201: step: 1916/530, loss: 0.044335268437862396
2023-01-23 04:00:44.026625: step: 1920/530, loss: 0.0001510620058979839
2023-01-23 04:00:45.233025: step: 1924/530, loss: 0.022577762603759766
2023-01-23 04:00:46.421288: step: 1928/530, loss: 0.0007621765835210681
2023-01-23 04:00:47.590810: step: 1932/530, loss: 0.00020885468984488398
2023-01-23 04:00:48.767643: step: 1936/530, loss: 0.6109886169433594
2023-01-23 04:00:49.965819: step: 1940/530, loss: 1.4972687495173886e-05
2023-01-23 04:00:51.102310: step: 1944/530, loss: 5.53131121705519e-06
2023-01-23 04:00:52.270213: step: 1948/530, loss: 0.004287147428840399
2023-01-23 04:00:53.446475: step: 1952/530, loss: 0.004920387174934149
2023-01-23 04:00:54.614388: step: 1956/530, loss: 0.00034208298893645406
2023-01-23 04:00:55.778318: step: 1960/530, loss: 0.015040588565170765
2023-01-23 04:00:56.953440: step: 1964/530, loss: 7.820130122127011e-06
2023-01-23 04:00:58.109911: step: 1968/530, loss: 9.012222290039062e-05
2023-01-23 04:00:59.322935: step: 1972/530, loss: 0.0004574775812216103
2023-01-23 04:01:00.483146: step: 1976/530, loss: 0.0016291618812829256
2023-01-23 04:01:01.656579: step: 1980/530, loss: 0.0843442901968956
2023-01-23 04:01:02.807073: step: 1984/530, loss: 8.306503877975047e-05
2023-01-23 04:01:03.974057: step: 1988/530, loss: 0.02689075469970703
2023-01-23 04:01:05.135536: step: 1992/530, loss: 1.430511474609375e-05
2023-01-23 04:01:06.305644: step: 1996/530, loss: 0.012757301330566406
2023-01-23 04:01:07.450471: step: 2000/530, loss: 3.519058373058215e-05
2023-01-23 04:01:08.604143: step: 2004/530, loss: 0.0058303833939135075
2023-01-23 04:01:09.741498: step: 2008/530, loss: 0.001104641007259488
2023-01-23 04:01:10.918547: step: 2012/530, loss: 3.399848719709553e-05
2023-01-23 04:01:12.146952: step: 2016/530, loss: 4.2629242670955136e-05
2023-01-23 04:01:13.331320: step: 2020/530, loss: 0.01100218202918768
2023-01-23 04:01:14.479364: step: 2024/530, loss: 0.13027158379554749
2023-01-23 04:01:15.672791: step: 2028/530, loss: 0.0009748458978720009
2023-01-23 04:01:16.873354: step: 2032/530, loss: 0.05574851110577583
2023-01-23 04:01:18.034551: step: 2036/530, loss: 0.009688759222626686
2023-01-23 04:01:19.274057: step: 2040/530, loss: 0.00873866118490696
2023-01-23 04:01:20.437476: step: 2044/530, loss: 3.24249276673072e-06
2023-01-23 04:01:21.571629: step: 2048/530, loss: 0.00049676897469908
2023-01-23 04:01:22.754803: step: 2052/530, loss: 0.008192062377929688
2023-01-23 04:01:23.954959: step: 2056/530, loss: 0.00023956299992278218
2023-01-23 04:01:25.152741: step: 2060/530, loss: 0.019434548914432526
2023-01-23 04:01:26.342711: step: 2064/530, loss: 0.007743454072624445
2023-01-23 04:01:27.608219: step: 2068/530, loss: 0.0006824017036706209
2023-01-23 04:01:28.781312: step: 2072/530, loss: 0.013895797543227673
2023-01-23 04:01:29.991180: step: 2076/530, loss: 0.0012094498379155993
2023-01-23 04:01:31.179713: step: 2080/530, loss: 0.010045862756669521
2023-01-23 04:01:32.330459: step: 2084/530, loss: 0.014191294088959694
2023-01-23 04:01:33.489634: step: 2088/530, loss: 0.020464038476347923
2023-01-23 04:01:34.690055: step: 2092/530, loss: 0.026391983032226562
2023-01-23 04:01:35.861135: step: 2096/530, loss: 0.03534698486328125
2023-01-23 04:01:37.090782: step: 2100/530, loss: 0.00110797886736691
2023-01-23 04:01:38.253205: step: 2104/530, loss: 0.26089000701904297
2023-01-23 04:01:39.384205: step: 2108/530, loss: 1.602172778802924e-05
2023-01-23 04:01:40.558344: step: 2112/530, loss: 8.296966552734375e-05
2023-01-23 04:01:41.812035: step: 2116/530, loss: 0.004843521397560835
2023-01-23 04:01:42.927284: step: 2120/530, loss: 0.00043315888615325093
==================================================
Loss: 0.015
--------------------
Dev: {'event': {'p': 0.5966562173458725, 'r': 0.7603195739014648, 'f1': 0.6686182669789228}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 24}
Test: {'event': {'p': 0.660672030288689, 'r': 0.8027602070155262, 'f1': 0.7248182762201454}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 24}
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': 24}
Korean: {'event': {'p': 0.5681818181818182, 'r': 0.3968253968253968, 'f1': 0.4672897196261682}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 24}
Russian: {'event': {'p': 0.5116279069767442, 'r': 0.6111111111111112, 'f1': 0.5569620253164557}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 24}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.603537981269511, 'r': 0.7723035952063915, 'f1': 0.677570093457944}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Eng Test for Chinese: {'event': {'p': 0.6663560111835974, 'r': 0.8223116733755031, 'f1': 0.7361647361647363}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Sample Chinese: {'event': {'p': 0.611764705882353, 'r': 0.9629629629629629, 'f1': 0.748201438848921}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5733990147783251, 'r': 0.7749667110519307, 'f1': 0.6591166477916196}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Eng Test for Korean: {'event': {'p': 0.6218005295675199, 'r': 0.8102357676825762, 'f1': 0.7036204744069912}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Sample Korean: {'event': {'p': 0.6417910447761194, 'r': 0.6825396825396826, 'f1': 0.6615384615384614}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6284796573875803, 'r': 0.7816245006657789, 'f1': 0.6967359050445103}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Eng Test for Russian: {'event': {'p': 0.6768263183357524, 'r': 0.80448533640023, 'f1': 0.7351550183920126}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Sample Russian: {'event': {'p': 0.4791666666666667, 'r': 0.6388888888888888, 'f1': 0.5476190476190476}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
******************************
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 04:02:25.463581: step: 4/530, loss: 2.8610231311176904e-05
2023-01-23 04:02:26.617239: step: 8/530, loss: 0.00030112266540527344
2023-01-23 04:02:27.847134: step: 12/530, loss: 4.920959327137098e-05
2023-01-23 04:02:28.976050: step: 16/530, loss: 0.0013895034790039062
2023-01-23 04:02:30.134162: step: 20/530, loss: 2.4700164431123994e-05
2023-01-23 04:02:31.308547: step: 24/530, loss: 0.002346229739487171
2023-01-23 04:02:32.435962: step: 28/530, loss: 4.501342846197076e-05
2023-01-23 04:02:33.590511: step: 32/530, loss: 0.0016015053261071444
2023-01-23 04:02:34.741425: step: 36/530, loss: 1.735687328618951e-05
2023-01-23 04:02:35.945384: step: 40/530, loss: 0.003616523928940296
2023-01-23 04:02:37.096996: step: 44/530, loss: 0.0013772010570392013
2023-01-23 04:02:38.245855: step: 48/530, loss: 0.0013776780106127262
2023-01-23 04:02:39.452724: step: 52/530, loss: 0.0005647659418173134
2023-01-23 04:02:40.586471: step: 56/530, loss: 0.017456578090786934
2023-01-23 04:02:41.739324: step: 60/530, loss: 0.3524666428565979
2023-01-23 04:02:42.893011: step: 64/530, loss: 0.03489341586828232
2023-01-23 04:02:44.098238: step: 68/530, loss: 0.008141708560287952
2023-01-23 04:02:45.287783: step: 72/530, loss: 9.059906005859375e-06
2023-01-23 04:02:46.451046: step: 76/530, loss: 0.0006840705755166709
2023-01-23 04:02:47.598907: step: 80/530, loss: 4.410744077176787e-05
2023-01-23 04:02:48.768228: step: 84/530, loss: 0.0004075646575074643
2023-01-23 04:02:49.918189: step: 88/530, loss: 0.00022687914315611124
2023-01-23 04:02:51.081502: step: 92/530, loss: 0.00473442068323493
2023-01-23 04:02:52.291632: step: 96/530, loss: 0.00018739700317382812
2023-01-23 04:02:53.446364: step: 100/530, loss: 0.020488977432250977
2023-01-23 04:02:54.568593: step: 104/530, loss: 0.00012311936006881297
2023-01-23 04:02:55.721943: step: 108/530, loss: 0.00228118896484375
2023-01-23 04:02:56.879774: step: 112/530, loss: 5.14984139954322e-06
2023-01-23 04:02:58.009796: step: 116/530, loss: 0.042673587799072266
2023-01-23 04:02:59.212928: step: 120/530, loss: 0.004301262088119984
2023-01-23 04:03:00.392369: step: 124/530, loss: 0.005278730299323797
2023-01-23 04:03:01.519836: step: 128/530, loss: 0.00015459061251021922
2023-01-23 04:03:02.715201: step: 132/530, loss: 0.0064051151275634766
2023-01-23 04:03:03.866399: step: 136/530, loss: 0.00020074844360351562
2023-01-23 04:03:05.024432: step: 140/530, loss: 0.00320091238245368
2023-01-23 04:03:06.176940: step: 144/530, loss: 0.0005567550542764366
2023-01-23 04:03:07.355694: step: 148/530, loss: 0.005089759360998869
2023-01-23 04:03:08.547181: step: 152/530, loss: 0.0013366222847253084
2023-01-23 04:03:09.690698: step: 156/530, loss: 0.0005156517145223916
2023-01-23 04:03:10.899890: step: 160/530, loss: 0.07894507050514221
2023-01-23 04:03:12.060669: step: 164/530, loss: 0.002525425050407648
2023-01-23 04:03:13.195524: step: 168/530, loss: 8.153916132869199e-05
2023-01-23 04:03:14.395705: step: 172/530, loss: 0.005180740263313055
2023-01-23 04:03:15.569302: step: 176/530, loss: 3.137588646495715e-05
2023-01-23 04:03:16.768243: step: 180/530, loss: 0.00013055802264716476
2023-01-23 04:03:17.950481: step: 184/530, loss: 0.007346916012465954
2023-01-23 04:03:19.106217: step: 188/530, loss: 1.831054760259576e-05
2023-01-23 04:03:20.271216: step: 192/530, loss: 0.0013288498157635331
2023-01-23 04:03:21.424398: step: 196/530, loss: 9.74655122263357e-05
2023-01-23 04:03:22.572699: step: 200/530, loss: 0.002631122013553977
2023-01-23 04:03:23.756877: step: 204/530, loss: 0.0023022652603685856
2023-01-23 04:03:24.964746: step: 208/530, loss: 0.028542518615722656
2023-01-23 04:03:26.127787: step: 212/530, loss: 0.0020797729957848787
2023-01-23 04:03:27.312088: step: 216/530, loss: 0.01642742194235325
2023-01-23 04:03:28.586667: step: 220/530, loss: 7.41004987503402e-05
2023-01-23 04:03:29.785126: step: 224/530, loss: 0.0009593010181561112
2023-01-23 04:03:30.939525: step: 228/530, loss: 6.48498553346144e-06
2023-01-23 04:03:32.116608: step: 232/530, loss: 7.476806786144152e-05
2023-01-23 04:03:33.356719: step: 236/530, loss: 0.010511589236557484
2023-01-23 04:03:34.509298: step: 240/530, loss: 0.0020109207835048437
2023-01-23 04:03:35.677294: step: 244/530, loss: 0.016209030523896217
2023-01-23 04:03:36.852122: step: 248/530, loss: 0.0001601219264557585
2023-01-23 04:03:38.004038: step: 252/530, loss: 0.0037382126320153475
2023-01-23 04:03:39.169660: step: 256/530, loss: 0.04468689113855362
2023-01-23 04:03:40.359827: step: 260/530, loss: 7.333754911087453e-05
2023-01-23 04:03:41.517480: step: 264/530, loss: 0.0015219688648357987
2023-01-23 04:03:42.678188: step: 268/530, loss: 0.002352809999138117
2023-01-23 04:03:43.854541: step: 272/530, loss: 0.007522773928940296
2023-01-23 04:03:45.033520: step: 276/530, loss: 0.00037469863309524953
2023-01-23 04:03:46.184630: step: 280/530, loss: 0.0010393142001703382
2023-01-23 04:03:47.373321: step: 284/530, loss: 0.0002165794576285407
2023-01-23 04:03:48.535826: step: 288/530, loss: 0.0004205704026389867
2023-01-23 04:03:49.705738: step: 292/530, loss: 0.009319496341049671
2023-01-23 04:03:50.856203: step: 296/530, loss: 0.0013811112148687243
2023-01-23 04:03:52.048061: step: 300/530, loss: 0.004154205322265625
2023-01-23 04:03:53.242098: step: 304/530, loss: 0.0006717205396853387
2023-01-23 04:03:54.391772: step: 308/530, loss: 0.025911331176757812
2023-01-23 04:03:55.552346: step: 312/530, loss: 0.011598111130297184
2023-01-23 04:03:56.702948: step: 316/530, loss: 0.00010623932030284777
2023-01-23 04:03:57.885704: step: 320/530, loss: 0.0020164488814771175
2023-01-23 04:03:59.049106: step: 324/530, loss: 8.39233416627394e-06
2023-01-23 04:04:00.255447: step: 328/530, loss: 0.0016307830810546875
2023-01-23 04:04:01.484723: step: 332/530, loss: 0.005638694856315851
2023-01-23 04:04:02.615844: step: 336/530, loss: 5.455017162603326e-05
2023-01-23 04:04:03.807271: step: 340/530, loss: 7.915496826171875e-05
2023-01-23 04:04:04.942497: step: 344/530, loss: 0.00010924339585471898
2023-01-23 04:04:06.142775: step: 348/530, loss: 0.001330900238826871
2023-01-23 04:04:07.302724: step: 352/530, loss: 0.03559169918298721
2023-01-23 04:04:08.456851: step: 356/530, loss: 0.0019571303855627775
2023-01-23 04:04:09.654586: step: 360/530, loss: 0.004663276951760054
2023-01-23 04:04:10.827098: step: 364/530, loss: 0.01383962668478489
2023-01-23 04:04:11.975663: step: 368/530, loss: 0.02313375473022461
2023-01-23 04:04:13.099331: step: 372/530, loss: 0.0007349014631472528
2023-01-23 04:04:14.262104: step: 376/530, loss: 0.0002777099434752017
2023-01-23 04:04:15.449902: step: 380/530, loss: 0.005493354983627796
2023-01-23 04:04:16.612068: step: 384/530, loss: 0.011819315142929554
2023-01-23 04:04:17.759798: step: 388/530, loss: 0.00010414123244117945
2023-01-23 04:04:18.934892: step: 392/530, loss: 0.017976760864257812
2023-01-23 04:04:20.080549: step: 396/530, loss: 0.028553390875458717
2023-01-23 04:04:21.241982: step: 400/530, loss: 0.009997558780014515
2023-01-23 04:04:22.389382: step: 404/530, loss: 0.0003131866396870464
2023-01-23 04:04:23.566397: step: 408/530, loss: 0.0001901626674225554
2023-01-23 04:04:24.747013: step: 412/530, loss: 0.013402557000517845
2023-01-23 04:04:25.920005: step: 416/530, loss: 0.011005974374711514
2023-01-23 04:04:27.136285: step: 420/530, loss: 0.017657851800322533
2023-01-23 04:04:28.296334: step: 424/530, loss: 3.8787944316864014
2023-01-23 04:04:29.480893: step: 428/530, loss: 0.0010305405594408512
2023-01-23 04:04:30.651907: step: 432/530, loss: 1.811981201171875e-05
2023-01-23 04:04:31.819817: step: 436/530, loss: 0.002593135926872492
2023-01-23 04:04:32.977368: step: 440/530, loss: 0.0010244370205327868
2023-01-23 04:04:34.168801: step: 444/530, loss: 0.006948661990463734
2023-01-23 04:04:35.351877: step: 448/530, loss: 0.0049953460693359375
2023-01-23 04:04:36.540206: step: 452/530, loss: 0.00032596586970612407
2023-01-23 04:04:37.739224: step: 456/530, loss: 4.625320343620842e-06
2023-01-23 04:04:38.909371: step: 460/530, loss: 1.3780593690171372e-05
2023-01-23 04:04:40.089335: step: 464/530, loss: 0.004208659753203392
2023-01-23 04:04:41.224263: step: 468/530, loss: 9.703636169433594e-05
2023-01-23 04:04:42.438096: step: 472/530, loss: 0.0031389237847179174
2023-01-23 04:04:43.601353: step: 476/530, loss: 0.00023431777663063258
2023-01-23 04:04:44.736494: step: 480/530, loss: 0.006004285998642445
2023-01-23 04:04:45.917019: step: 484/530, loss: 0.0002674102724995464
2023-01-23 04:04:47.042999: step: 488/530, loss: -1.144409225162235e-06
2023-01-23 04:04:48.212188: step: 492/530, loss: 0.002213001251220703
2023-01-23 04:04:49.360135: step: 496/530, loss: 0.10098133236169815
2023-01-23 04:04:50.523771: step: 500/530, loss: 0.001959896180778742
2023-01-23 04:04:51.711845: step: 504/530, loss: 0.12911739945411682
2023-01-23 04:04:52.836098: step: 508/530, loss: 0.000282096880255267
2023-01-23 04:04:54.033950: step: 512/530, loss: 0.013754653744399548
2023-01-23 04:04:55.169914: step: 516/530, loss: 0.00013847350783180445
2023-01-23 04:04:56.316017: step: 520/530, loss: 0.0002933502255473286
2023-01-23 04:04:57.460993: step: 524/530, loss: 0.002707862760871649
2023-01-23 04:04:58.643226: step: 528/530, loss: 0.06650009006261826
2023-01-23 04:04:59.818215: step: 532/530, loss: 0.018381405621767044
2023-01-23 04:05:00.991022: step: 536/530, loss: 0.0006687164423055947
2023-01-23 04:05:02.137505: step: 540/530, loss: 0.0001873016299214214
2023-01-23 04:05:03.336732: step: 544/530, loss: 0.0003247261338401586
2023-01-23 04:05:04.548098: step: 548/530, loss: 0.021899795159697533
2023-01-23 04:05:05.730538: step: 552/530, loss: 0.00013939141354057938
2023-01-23 04:05:06.893278: step: 556/530, loss: 0.07399959117174149
2023-01-23 04:05:08.054612: step: 560/530, loss: 8.254051499534398e-05
2023-01-23 04:05:09.192143: step: 564/530, loss: 5.316734313964844e-05
2023-01-23 04:05:10.352945: step: 568/530, loss: 0.0491674430668354
2023-01-23 04:05:11.529297: step: 572/530, loss: 0.00020227432833053172
2023-01-23 04:05:12.703272: step: 576/530, loss: 0.016153907403349876
2023-01-23 04:05:13.872903: step: 580/530, loss: 0.037256333976984024
2023-01-23 04:05:15.048318: step: 584/530, loss: 5.626678102998994e-06
2023-01-23 04:05:16.173565: step: 588/530, loss: 0.0015472412342205644
2023-01-23 04:05:17.350119: step: 592/530, loss: 0.00028896331787109375
2023-01-23 04:05:18.512395: step: 596/530, loss: 0.0006258010980673134
2023-01-23 04:05:19.693853: step: 600/530, loss: 0.00015382767014671117
2023-01-23 04:05:20.887344: step: 604/530, loss: 0.0009347915765829384
2023-01-23 04:05:22.017751: step: 608/530, loss: 0.0010693550575524569
2023-01-23 04:05:23.172843: step: 612/530, loss: 4.3487551010912284e-05
2023-01-23 04:05:24.369915: step: 616/530, loss: 0.004958534613251686
2023-01-23 04:05:25.564140: step: 620/530, loss: 0.0035626410972326994
2023-01-23 04:05:26.692890: step: 624/530, loss: 5.170107033336535e-05
2023-01-23 04:05:27.866250: step: 628/530, loss: 0.0010870933765545487
2023-01-23 04:05:29.051727: step: 632/530, loss: 0.01930713653564453
2023-01-23 04:05:30.237890: step: 636/530, loss: 0.0350315123796463
2023-01-23 04:05:31.386356: step: 640/530, loss: 2.431869688734878e-06
2023-01-23 04:05:32.525980: step: 644/530, loss: 2.86102294921875e-06
2023-01-23 04:05:33.697722: step: 648/530, loss: 0.005962944123893976
2023-01-23 04:05:34.880081: step: 652/530, loss: 0.03679676353931427
2023-01-23 04:05:36.047320: step: 656/530, loss: 0.0029224397148936987
2023-01-23 04:05:37.205715: step: 660/530, loss: 0.0005386352422647178
2023-01-23 04:05:38.409975: step: 664/530, loss: 0.0001626968296477571
2023-01-23 04:05:39.560272: step: 668/530, loss: 0.0038320065941661596
2023-01-23 04:05:40.769264: step: 672/530, loss: 3.5953522456111386e-05
2023-01-23 04:05:41.941226: step: 676/530, loss: 0.03695201873779297
2023-01-23 04:05:43.115122: step: 680/530, loss: 0.0002428054722258821
2023-01-23 04:05:44.328574: step: 684/530, loss: 0.0013056278694421053
2023-01-23 04:05:45.478279: step: 688/530, loss: 2.7990341550321318e-05
2023-01-23 04:05:46.690869: step: 692/530, loss: 0.00013294219388626516
2023-01-23 04:05:47.895432: step: 696/530, loss: 0.006185817997902632
2023-01-23 04:05:49.057875: step: 700/530, loss: 0.01731119118630886
2023-01-23 04:05:50.231827: step: 704/530, loss: 0.001958179520443082
2023-01-23 04:05:51.377156: step: 708/530, loss: 0.0034168243873864412
2023-01-23 04:05:52.528636: step: 712/530, loss: 0.013438224792480469
2023-01-23 04:05:53.695453: step: 716/530, loss: 3.80516066798009e-05
2023-01-23 04:05:54.889175: step: 720/530, loss: 0.0004945755354128778
2023-01-23 04:05:56.078637: step: 724/530, loss: 0.00011692046973621473
2023-01-23 04:05:57.223697: step: 728/530, loss: 0.00026569367037154734
2023-01-23 04:05:58.370054: step: 732/530, loss: 0.0017206192715093493
2023-01-23 04:05:59.569551: step: 736/530, loss: 0.06024417653679848
2023-01-23 04:06:00.748883: step: 740/530, loss: 9.193420555675402e-05
2023-01-23 04:06:01.875190: step: 744/530, loss: 0.004082441329956055
2023-01-23 04:06:03.094424: step: 748/530, loss: 3.128051685052924e-05
2023-01-23 04:06:04.240189: step: 752/530, loss: 0.00048484804574400187
2023-01-23 04:06:05.404042: step: 756/530, loss: 0.0011425971752032638
2023-01-23 04:06:06.567636: step: 760/530, loss: 0.0004642009735107422
2023-01-23 04:06:07.786349: step: 764/530, loss: 2.1076202756376006e-05
2023-01-23 04:06:08.923647: step: 768/530, loss: 1.258850079466356e-05
2023-01-23 04:06:10.077066: step: 772/530, loss: 3.7860871088923886e-05
2023-01-23 04:06:11.282234: step: 776/530, loss: 0.04156646877527237
2023-01-23 04:06:12.498604: step: 780/530, loss: 7.200241088867188e-05
2023-01-23 04:06:13.682315: step: 784/530, loss: 3.2711028325138614e-05
2023-01-23 04:06:14.863777: step: 788/530, loss: 0.0013545990223065019
2023-01-23 04:06:16.044093: step: 792/530, loss: 0.348680317401886
2023-01-23 04:06:17.199589: step: 796/530, loss: 0.00010690689668990672
2023-01-23 04:06:18.391266: step: 800/530, loss: 0.010894298553466797
2023-01-23 04:06:19.545534: step: 804/530, loss: 0.0027828216552734375
2023-01-23 04:06:20.732024: step: 808/530, loss: 1.0328563451766968
2023-01-23 04:06:21.880446: step: 812/530, loss: 0.04568615183234215
2023-01-23 04:06:23.031592: step: 816/530, loss: 1.9931792849092744e-05
2023-01-23 04:06:24.186232: step: 820/530, loss: 0.005255031865090132
2023-01-23 04:06:25.362201: step: 824/530, loss: 1.2874604180979077e-05
2023-01-23 04:06:26.486212: step: 828/530, loss: 3.80516066798009e-05
2023-01-23 04:06:27.641430: step: 832/530, loss: 8.106232598947827e-06
2023-01-23 04:06:28.821186: step: 836/530, loss: 0.0001008987455861643
2023-01-23 04:06:29.952015: step: 840/530, loss: 0.003927039913833141
2023-01-23 04:06:31.105587: step: 844/530, loss: 0.014068317599594593
2023-01-23 04:06:32.297625: step: 848/530, loss: 7.51018596929498e-05
2023-01-23 04:06:33.445804: step: 852/530, loss: 2.0980837689421605e-06
2023-01-23 04:06:34.612136: step: 856/530, loss: 7.06017017364502e-05
2023-01-23 04:06:35.784198: step: 860/530, loss: 0.01698770374059677
2023-01-23 04:06:36.950020: step: 864/530, loss: 3.3855438232421875e-05
2023-01-23 04:06:38.165297: step: 868/530, loss: 2.679825047380291e-05
2023-01-23 04:06:39.358955: step: 872/530, loss: 0.057471469044685364
2023-01-23 04:06:40.524423: step: 876/530, loss: 0.0015130043029785156
2023-01-23 04:06:41.695190: step: 880/530, loss: 6.237030174816027e-05
2023-01-23 04:06:42.860984: step: 884/530, loss: 0.012771129608154297
2023-01-23 04:06:44.029877: step: 888/530, loss: 5.702972339349799e-05
2023-01-23 04:06:45.175939: step: 892/530, loss: 0.004717064090073109
2023-01-23 04:06:46.337682: step: 896/530, loss: 0.08671274781227112
2023-01-23 04:06:47.541390: step: 900/530, loss: 2.689361645025201e-05
2023-01-23 04:06:48.713517: step: 904/530, loss: 0.0001701354922261089
2023-01-23 04:06:49.896561: step: 908/530, loss: 0.00448651285842061
2023-01-23 04:06:51.106071: step: 912/530, loss: 0.005318641662597656
2023-01-23 04:06:52.354232: step: 916/530, loss: 0.04563131555914879
2023-01-23 04:06:53.544051: step: 920/530, loss: 0.0001272201625397429
2023-01-23 04:06:54.705271: step: 924/530, loss: 8.811950829112902e-05
2023-01-23 04:06:55.881412: step: 928/530, loss: 0.00016098022751975805
2023-01-23 04:06:57.048483: step: 932/530, loss: 0.03024015575647354
2023-01-23 04:06:58.323452: step: 936/530, loss: -1.0490418844710803e-06
2023-01-23 04:06:59.460020: step: 940/530, loss: 0.03760671615600586
2023-01-23 04:07:00.609638: step: 944/530, loss: 7.915497008070815e-06
2023-01-23 04:07:01.769265: step: 948/530, loss: 0.010150527581572533
2023-01-23 04:07:02.962339: step: 952/530, loss: -2.6226043701171875e-06
2023-01-23 04:07:04.160640: step: 956/530, loss: 0.031029893085360527
2023-01-23 04:07:05.386144: step: 960/530, loss: 1.9454957509879023e-05
2023-01-23 04:07:06.590609: step: 964/530, loss: 0.00800857599824667
2023-01-23 04:07:07.764321: step: 968/530, loss: 0.0007581710815429688
2023-01-23 04:07:08.954278: step: 972/530, loss: 0.0022471428383141756
2023-01-23 04:07:10.122920: step: 976/530, loss: 5.2261355449445546e-05
2023-01-23 04:07:11.334008: step: 980/530, loss: 3.652572922874242e-05
2023-01-23 04:07:12.480482: step: 984/530, loss: 6.618499901378527e-05
2023-01-23 04:07:13.659856: step: 988/530, loss: 0.0010714532108977437
2023-01-23 04:07:14.804537: step: 992/530, loss: 0.0011800766224041581
2023-01-23 04:07:15.955332: step: 996/530, loss: 0.009926033206284046
2023-01-23 04:07:17.111417: step: 1000/530, loss: 0.0003354072687216103
2023-01-23 04:07:18.289040: step: 1004/530, loss: 0.004562282469123602
2023-01-23 04:07:19.468034: step: 1008/530, loss: 4.482269105210435e-06
2023-01-23 04:07:20.639329: step: 1012/530, loss: 0.017740631476044655
2023-01-23 04:07:21.771953: step: 1016/530, loss: 0.00041332244290970266
2023-01-23 04:07:22.961530: step: 1020/530, loss: 0.013396358117461205
2023-01-23 04:07:24.116640: step: 1024/530, loss: 2.3174286980065517e-05
2023-01-23 04:07:25.317777: step: 1028/530, loss: 9.5367431640625e-06
2023-01-23 04:07:26.480541: step: 1032/530, loss: 0.0002525329764466733
2023-01-23 04:07:27.646391: step: 1036/530, loss: 0.0011200904846191406
2023-01-23 04:07:28.833742: step: 1040/530, loss: 0.0007210731273517013
2023-01-23 04:07:30.001143: step: 1044/530, loss: 0.024316787719726562
2023-01-23 04:07:31.116640: step: 1048/530, loss: 0.0033081055153161287
2023-01-23 04:07:32.274306: step: 1052/530, loss: 0.023715544492006302
2023-01-23 04:07:33.516834: step: 1056/530, loss: 0.0011663436889648438
2023-01-23 04:07:34.691079: step: 1060/530, loss: 9.059906005859375e-06
2023-01-23 04:07:35.883734: step: 1064/530, loss: 0.003678607987239957
2023-01-23 04:07:37.059689: step: 1068/530, loss: 3.5095217754133046e-05
2023-01-23 04:07:38.220902: step: 1072/530, loss: 0.000904083251953125
2023-01-23 04:07:39.409039: step: 1076/530, loss: 0.00022010803513694555
2023-01-23 04:07:40.600436: step: 1080/530, loss: 0.0051860809326171875
2023-01-23 04:07:41.756815: step: 1084/530, loss: 5.645752025884576e-05
2023-01-23 04:07:42.943571: step: 1088/530, loss: 0.005726623814553022
2023-01-23 04:07:44.123063: step: 1092/530, loss: 0.0002117156982421875
2023-01-23 04:07:45.286977: step: 1096/530, loss: 0.003433704376220703
2023-01-23 04:07:46.437843: step: 1100/530, loss: 8.17298932815902e-05
2023-01-23 04:07:47.624718: step: 1104/530, loss: 0.002113819122314453
2023-01-23 04:07:48.791448: step: 1108/530, loss: 0.010368680581450462
2023-01-23 04:07:49.981432: step: 1112/530, loss: 0.00024094581021927297
2023-01-23 04:07:51.167121: step: 1116/530, loss: 0.007313537411391735
2023-01-23 04:07:52.422320: step: 1120/530, loss: 0.014876746572554111
2023-01-23 04:07:53.597980: step: 1124/530, loss: 0.017028523609042168
2023-01-23 04:07:54.764114: step: 1128/530, loss: 0.004668808076530695
2023-01-23 04:07:55.914046: step: 1132/530, loss: 0.06572303920984268
2023-01-23 04:07:57.072944: step: 1136/530, loss: 0.0008529662736691535
2023-01-23 04:07:58.281786: step: 1140/530, loss: 0.032503318041563034
2023-01-23 04:07:59.458532: step: 1144/530, loss: 0.0007240295526571572
2023-01-23 04:08:00.657779: step: 1148/530, loss: -2.241135007352568e-06
2023-01-23 04:08:01.869218: step: 1152/530, loss: 0.008105326443910599
2023-01-23 04:08:03.011737: step: 1156/530, loss: 0.0008573532104492188
2023-01-23 04:08:04.167971: step: 1160/530, loss: 0.03178920969367027
2023-01-23 04:08:05.329767: step: 1164/530, loss: 0.005588531494140625
2023-01-23 04:08:06.494317: step: 1168/530, loss: 0.0027174949645996094
2023-01-23 04:08:07.703423: step: 1172/530, loss: 3.986358569818549e-05
2023-01-23 04:08:08.867722: step: 1176/530, loss: 0.00017042159743141383
2023-01-23 04:08:10.008719: step: 1180/530, loss: 1.62124638336536e-06
2023-01-23 04:08:11.203669: step: 1184/530, loss: 7.114410982467234e-05
2023-01-23 04:08:12.376674: step: 1188/530, loss: 0.00031423717155121267
2023-01-23 04:08:13.494164: step: 1192/530, loss: 4.997253563487902e-05
2023-01-23 04:08:14.651562: step: 1196/530, loss: 0.015460587106645107
2023-01-23 04:08:15.802809: step: 1200/530, loss: 0.0008395195472985506
2023-01-23 04:08:16.953609: step: 1204/530, loss: 0.2750614285469055
2023-01-23 04:08:18.130995: step: 1208/530, loss: 0.01067962683737278
2023-01-23 04:08:19.276005: step: 1212/530, loss: 0.0009273529285565019
2023-01-23 04:08:20.497014: step: 1216/530, loss: 0.0005411148304119706
2023-01-23 04:08:21.650194: step: 1220/530, loss: 0.0001255035458598286
2023-01-23 04:08:22.798170: step: 1224/530, loss: 0.013475227169692516
2023-01-23 04:08:23.940915: step: 1228/530, loss: 0.10015039891004562
2023-01-23 04:08:25.068807: step: 1232/530, loss: 0.00964660756289959
2023-01-23 04:08:26.227891: step: 1236/530, loss: 0.008114432916045189
2023-01-23 04:08:27.381426: step: 1240/530, loss: 0.0003173828299622983
2023-01-23 04:08:28.514787: step: 1244/530, loss: 1.9836426872643642e-05
2023-01-23 04:08:29.719712: step: 1248/530, loss: 0.0001046180768753402
2023-01-23 04:08:30.954277: step: 1252/530, loss: 0.0021859167609363794
2023-01-23 04:08:32.126499: step: 1256/530, loss: 0.007715749554336071
2023-01-23 04:08:33.289593: step: 1260/530, loss: 0.009414386935532093
2023-01-23 04:08:34.453902: step: 1264/530, loss: 0.03513622283935547
2023-01-23 04:08:35.676059: step: 1268/530, loss: 0.0027791978791356087
2023-01-23 04:08:36.868739: step: 1272/530, loss: 0.0009056091075763106
2023-01-23 04:08:38.049215: step: 1276/530, loss: 0.0024213790893554688
2023-01-23 04:08:39.183745: step: 1280/530, loss: 0.0014198303688317537
2023-01-23 04:08:40.338984: step: 1284/530, loss: 0.004444694146513939
2023-01-23 04:08:41.542642: step: 1288/530, loss: 0.003329944796860218
2023-01-23 04:08:42.687180: step: 1292/530, loss: 0.0009348869207315147
2023-01-23 04:08:43.856158: step: 1296/530, loss: 0.00026702880859375
2023-01-23 04:08:45.019052: step: 1300/530, loss: 0.00299835205078125
2023-01-23 04:08:46.162479: step: 1304/530, loss: 0.00018482207087799907
2023-01-23 04:08:47.384028: step: 1308/530, loss: 0.0005199432489462197
2023-01-23 04:08:48.534577: step: 1312/530, loss: 0.012120533734560013
2023-01-23 04:08:49.689566: step: 1316/530, loss: 0.05013008415699005
2023-01-23 04:08:50.825354: step: 1320/530, loss: 0.002054882235825062
2023-01-23 04:08:51.987402: step: 1324/530, loss: 0.0003935813729185611
2023-01-23 04:08:53.152158: step: 1328/530, loss: 4.863738922722405e-06
2023-01-23 04:08:54.300006: step: 1332/530, loss: 0.016919897869229317
2023-01-23 04:08:55.482213: step: 1336/530, loss: 0.024862386286258698
2023-01-23 04:08:56.686118: step: 1340/530, loss: 0.00015563966007903218
2023-01-23 04:08:57.818623: step: 1344/530, loss: 0.00042514799861237407
2023-01-23 04:08:58.994059: step: 1348/530, loss: 0.01694164238870144
2023-01-23 04:09:00.157344: step: 1352/530, loss: 0.0005329131963662803
2023-01-23 04:09:01.324037: step: 1356/530, loss: 0.0009568214300088584
2023-01-23 04:09:02.471232: step: 1360/530, loss: 0.022759154438972473
2023-01-23 04:09:03.618542: step: 1364/530, loss: 0.020641708746552467
2023-01-23 04:09:04.814998: step: 1368/530, loss: 6.370544724632055e-05
2023-01-23 04:09:05.956409: step: 1372/530, loss: 0.05861835554242134
2023-01-23 04:09:07.142510: step: 1376/530, loss: 0.003581809811294079
2023-01-23 04:09:08.354000: step: 1380/530, loss: 0.0006729125743731856
2023-01-23 04:09:09.567843: step: 1384/530, loss: 0.01955127902328968
2023-01-23 04:09:10.734887: step: 1388/530, loss: 0.0031902315095067024
2023-01-23 04:09:11.914298: step: 1392/530, loss: 0.12280026078224182
2023-01-23 04:09:13.069844: step: 1396/530, loss: 0.0033663748763501644
2023-01-23 04:09:14.231403: step: 1400/530, loss: 0.0012676238548010588
2023-01-23 04:09:15.488223: step: 1404/530, loss: 0.001957464264705777
2023-01-23 04:09:16.632151: step: 1408/530, loss: 0.0006841659778729081
2023-01-23 04:09:17.827303: step: 1412/530, loss: 0.003468799637630582
2023-01-23 04:09:18.987505: step: 1416/530, loss: 5.683898780262098e-05
2023-01-23 04:09:20.132543: step: 1420/530, loss: 0.0003314971982035786
2023-01-23 04:09:21.285587: step: 1424/530, loss: 1.1825562978629023e-05
2023-01-23 04:09:22.461072: step: 1428/530, loss: 0.0072282785549759865
2023-01-23 04:09:23.614012: step: 1432/530, loss: 2.117157055181451e-05
2023-01-23 04:09:24.801666: step: 1436/530, loss: 1.392364538332913e-05
2023-01-23 04:09:25.970141: step: 1440/530, loss: 0.00032300950260832906
2023-01-23 04:09:27.146211: step: 1444/530, loss: 0.029506873339414597
2023-01-23 04:09:28.333785: step: 1448/530, loss: 0.00043296816875226796
2023-01-23 04:09:29.517532: step: 1452/530, loss: 0.002433300018310547
2023-01-23 04:09:30.696072: step: 1456/530, loss: 2.2411345526052173e-06
2023-01-23 04:09:31.878010: step: 1460/530, loss: 0.002944088075309992
2023-01-23 04:09:33.007127: step: 1464/530, loss: 0.005879783537238836
2023-01-23 04:09:34.172240: step: 1468/530, loss: 0.01812162436544895
2023-01-23 04:09:35.336217: step: 1472/530, loss: 0.0010649681789800525
2023-01-23 04:09:36.489235: step: 1476/530, loss: 6.198883056640625e-06
2023-01-23 04:09:37.692202: step: 1480/530, loss: 0.0006489753723144531
2023-01-23 04:09:38.878975: step: 1484/530, loss: 1.4305115314527939e-07
2023-01-23 04:09:40.042626: step: 1488/530, loss: 0.1085321381688118
2023-01-23 04:09:41.206615: step: 1492/530, loss: 0.0005033492925576866
2023-01-23 04:09:42.431280: step: 1496/530, loss: 4.0054324017546605e-06
2023-01-23 04:09:43.572144: step: 1500/530, loss: 0.00018973351689055562
2023-01-23 04:09:44.695650: step: 1504/530, loss: 0.0008160591241903603
2023-01-23 04:09:45.892518: step: 1508/530, loss: 0.04935717210173607
2023-01-23 04:09:47.061227: step: 1512/530, loss: 0.024823378771543503
2023-01-23 04:09:48.215191: step: 1516/530, loss: 0.009255743585526943
2023-01-23 04:09:49.381204: step: 1520/530, loss: 8.106231689453125e-05
2023-01-23 04:09:50.537326: step: 1524/530, loss: 2.6798248654813506e-05
2023-01-23 04:09:51.703809: step: 1528/530, loss: 0.00024538038996979594
2023-01-23 04:09:52.887853: step: 1532/530, loss: 0.0011971474159508944
2023-01-23 04:09:54.045625: step: 1536/530, loss: 7.629396350239404e-07
2023-01-23 04:09:55.232173: step: 1540/530, loss: 0.0003688812139444053
2023-01-23 04:09:56.402244: step: 1544/530, loss: 0.001695919083431363
2023-01-23 04:09:57.568577: step: 1548/530, loss: 0.0007320403819903731
2023-01-23 04:09:58.698058: step: 1552/530, loss: 0.0021512031089514494
2023-01-23 04:09:59.876136: step: 1556/530, loss: 0.0037168501876294613
2023-01-23 04:10:01.082582: step: 1560/530, loss: 0.13877636194229126
2023-01-23 04:10:02.276826: step: 1564/530, loss: 0.0021050453651696444
2023-01-23 04:10:03.477348: step: 1568/530, loss: 0.00802688580006361
2023-01-23 04:10:04.668062: step: 1572/530, loss: 0.00025815964909270406
2023-01-23 04:10:05.850233: step: 1576/530, loss: 0.0014194488758221269
2023-01-23 04:10:06.992269: step: 1580/530, loss: -1.258850079466356e-05
2023-01-23 04:10:08.147676: step: 1584/530, loss: 0.0004368782101664692
2023-01-23 04:10:09.334669: step: 1588/530, loss: 0.039253998547792435
2023-01-23 04:10:10.478710: step: 1592/530, loss: 0.00030221938504837453
2023-01-23 04:10:11.680372: step: 1596/530, loss: 0.0011402129894122481
2023-01-23 04:10:12.870254: step: 1600/530, loss: 3.4999848139705136e-05
2023-01-23 04:10:14.020275: step: 1604/530, loss: 8.58306884765625e-06
2023-01-23 04:10:15.213449: step: 1608/530, loss: 0.007841110229492188
2023-01-23 04:10:16.395415: step: 1612/530, loss: 0.0008140564314089715
2023-01-23 04:10:17.557334: step: 1616/530, loss: 0.0003173828008584678
2023-01-23 04:10:18.729610: step: 1620/530, loss: 0.00022583008103538305
2023-01-23 04:10:19.951978: step: 1624/530, loss: 0.0006501197931356728
2023-01-23 04:10:21.138125: step: 1628/530, loss: 0.017969703301787376
2023-01-23 04:10:22.334303: step: 1632/530, loss: 0.0007604599231854081
2023-01-23 04:10:23.485926: step: 1636/530, loss: 3.347396705066785e-05
2023-01-23 04:10:24.682448: step: 1640/530, loss: 0.09605789929628372
2023-01-23 04:10:25.846709: step: 1644/530, loss: 6.8664553509734105e-06
2023-01-23 04:10:27.025553: step: 1648/530, loss: 0.008725167252123356
2023-01-23 04:10:28.210346: step: 1652/530, loss: 3.280639793956652e-05
2023-01-23 04:10:29.337803: step: 1656/530, loss: 0.0008182525634765625
2023-01-23 04:10:30.501410: step: 1660/530, loss: 0.0010366917122155428
2023-01-23 04:10:31.702413: step: 1664/530, loss: 0.00048828125
2023-01-23 04:10:32.905909: step: 1668/530, loss: 0.0008810996660031378
2023-01-23 04:10:34.083416: step: 1672/530, loss: 1.716613724056515e-06
2023-01-23 04:10:35.267874: step: 1676/530, loss: 0.0028417587745934725
2023-01-23 04:10:36.425346: step: 1680/530, loss: 0.032867431640625
2023-01-23 04:10:37.597474: step: 1684/530, loss: 0.00012092589895473793
2023-01-23 04:10:38.764195: step: 1688/530, loss: 0.0030490877106785774
2023-01-23 04:10:39.921908: step: 1692/530, loss: -6.389617738022935e-06
2023-01-23 04:10:41.089101: step: 1696/530, loss: -8.01086389401462e-06
2023-01-23 04:10:42.350168: step: 1700/530, loss: 0.005925178527832031
2023-01-23 04:10:43.527524: step: 1704/530, loss: 0.02528972551226616
2023-01-23 04:10:44.737660: step: 1708/530, loss: 0.01662302017211914
2023-01-23 04:10:45.894239: step: 1712/530, loss: 0.005824279971420765
2023-01-23 04:10:47.085207: step: 1716/530, loss: 0.002816915512084961
2023-01-23 04:10:48.261837: step: 1720/530, loss: 0.0006657720077782869
2023-01-23 04:10:49.451546: step: 1724/530, loss: 0.0036499022971838713
2023-01-23 04:10:50.624302: step: 1728/530, loss: 2.1457672119140625e-05
2023-01-23 04:10:51.832165: step: 1732/530, loss: 9.32693510549143e-05
2023-01-23 04:10:53.074969: step: 1736/530, loss: 0.021967792883515358
2023-01-23 04:10:54.251294: step: 1740/530, loss: 0.016535663977265358
2023-01-23 04:10:55.444109: step: 1744/530, loss: 0.02796478383243084
2023-01-23 04:10:56.631107: step: 1748/530, loss: 1.2063980648235884e-05
2023-01-23 04:10:57.834777: step: 1752/530, loss: 0.01540374755859375
2023-01-23 04:10:59.019949: step: 1756/530, loss: 5.168914867681451e-05
2023-01-23 04:11:00.193000: step: 1760/530, loss: 0.004541588015854359
2023-01-23 04:11:01.338743: step: 1764/530, loss: 6.906985800014809e-05
2023-01-23 04:11:02.544840: step: 1768/530, loss: 0.018044328317046165
2023-01-23 04:11:03.760147: step: 1772/530, loss: 2.8610230629055877e-07
2023-01-23 04:11:04.951868: step: 1776/530, loss: 0.0005989075289107859
2023-01-23 04:11:06.114524: step: 1780/530, loss: 1.983642505365424e-05
2023-01-23 04:11:07.390839: step: 1784/530, loss: 0.002282810164615512
2023-01-23 04:11:08.560380: step: 1788/530, loss: 5.626678466796875e-05
2023-01-23 04:11:09.705885: step: 1792/530, loss: 0.0004341125604696572
2023-01-23 04:11:10.905222: step: 1796/530, loss: 0.0007532119634561241
2023-01-23 04:11:12.163519: step: 1800/530, loss: 0.07870350033044815
2023-01-23 04:11:13.338599: step: 1804/530, loss: 0.0013563156826421618
2023-01-23 04:11:14.487759: step: 1808/530, loss: 0.00024003982252907008
2023-01-23 04:11:15.692716: step: 1812/530, loss: 4.968643406755291e-05
2023-01-23 04:11:16.829402: step: 1816/530, loss: 0.0013772487873211503
2023-01-23 04:11:17.964301: step: 1820/530, loss: 0.00015192032151389867
2023-01-23 04:11:19.123174: step: 1824/530, loss: 0.03337249904870987
2023-01-23 04:11:20.312701: step: 1828/530, loss: 5.2261355449445546e-05
2023-01-23 04:11:21.498700: step: 1832/530, loss: 0.0005826950073242188
2023-01-23 04:11:22.713835: step: 1836/530, loss: 0.01380131859332323
2023-01-23 04:11:23.885265: step: 1840/530, loss: 0.00044078828068450093
2023-01-23 04:11:25.075761: step: 1844/530, loss: 0.0010494232410565019
2023-01-23 04:11:26.267399: step: 1848/530, loss: 0.0054892064072191715
2023-01-23 04:11:27.398503: step: 1852/530, loss: 5.14984130859375e-05
2023-01-23 04:11:28.556647: step: 1856/530, loss: 0.00040121079655364156
2023-01-23 04:11:29.689952: step: 1860/530, loss: 0.0018254281021654606
2023-01-23 04:11:30.841531: step: 1864/530, loss: 0.1102914810180664
2023-01-23 04:11:32.051075: step: 1868/530, loss: 0.0018491744995117188
2023-01-23 04:11:33.209862: step: 1872/530, loss: 0.06604178249835968
2023-01-23 04:11:34.371125: step: 1876/530, loss: 0.0002149581996491179
2023-01-23 04:11:35.513498: step: 1880/530, loss: 2.5272369384765625e-05
2023-01-23 04:11:36.663887: step: 1884/530, loss: 0.010656642727553844
2023-01-23 04:11:37.802681: step: 1888/530, loss: 2.708435022213962e-05
2023-01-23 04:11:38.950073: step: 1892/530, loss: 0.0021576881408691406
2023-01-23 04:11:40.127545: step: 1896/530, loss: 0.0027456283569335938
2023-01-23 04:11:41.288938: step: 1900/530, loss: 0.0024428367614746094
2023-01-23 04:11:42.417402: step: 1904/530, loss: 9.72747784544481e-06
2023-01-23 04:11:43.627162: step: 1908/530, loss: 0.000358390825567767
2023-01-23 04:11:44.863429: step: 1912/530, loss: 0.0005353927845135331
2023-01-23 04:11:46.021717: step: 1916/530, loss: 0.08630505204200745
2023-01-23 04:11:47.191214: step: 1920/530, loss: 0.00055017473641783
2023-01-23 04:11:48.389741: step: 1924/530, loss: 0.0001198768659378402
2023-01-23 04:11:49.576917: step: 1928/530, loss: 0.0011196136474609375
2023-01-23 04:11:50.731838: step: 1932/530, loss: 0.01929626613855362
2023-01-23 04:11:51.946824: step: 1936/530, loss: 0.00058999058092013
2023-01-23 04:11:53.096142: step: 1940/530, loss: 0.0008335113525390625
2023-01-23 04:11:54.234860: step: 1944/530, loss: 0.00021028520131949335
2023-01-23 04:11:55.460922: step: 1948/530, loss: 0.013557148166000843
2023-01-23 04:11:56.658520: step: 1952/530, loss: 0.009141159243881702
2023-01-23 04:11:57.852896: step: 1956/530, loss: 0.001148223876953125
2023-01-23 04:11:59.032957: step: 1960/530, loss: 0.17177735269069672
2023-01-23 04:12:00.212609: step: 1964/530, loss: 0.005257606506347656
2023-01-23 04:12:01.380205: step: 1968/530, loss: 0.018319321796298027
2023-01-23 04:12:02.644857: step: 1972/530, loss: 0.0002735138114076108
2023-01-23 04:12:03.854018: step: 1976/530, loss: 0.009503745473921299
2023-01-23 04:12:04.989564: step: 1980/530, loss: 0.0019828795921057463
2023-01-23 04:12:06.177372: step: 1984/530, loss: 0.0013078689808025956
2023-01-23 04:12:07.342735: step: 1988/530, loss: 0.011764240451157093
2023-01-23 04:12:08.540551: step: 1992/530, loss: 2.9230119253043085e-05
2023-01-23 04:12:09.711324: step: 1996/530, loss: 4.825591895496473e-05
2023-01-23 04:12:10.896110: step: 2000/530, loss: 0.004332542419433594
2023-01-23 04:12:12.073322: step: 2004/530, loss: 0.006155204493552446
2023-01-23 04:12:13.219731: step: 2008/530, loss: 0.00040073395939543843
2023-01-23 04:12:14.408959: step: 2012/530, loss: 4.38690185546875e-05
2023-01-23 04:12:15.557917: step: 2016/530, loss: 0.00033674240694381297
2023-01-23 04:12:16.718757: step: 2020/530, loss: 0.0028434754349291325
2023-01-23 04:12:17.885363: step: 2024/530, loss: 0.0004271507204975933
2023-01-23 04:12:19.060763: step: 2028/530, loss: 0.005650329403579235
2023-01-23 04:12:20.184871: step: 2032/530, loss: 0.004430484492331743
2023-01-23 04:12:21.335645: step: 2036/530, loss: 0.00422325124964118
2023-01-23 04:12:22.501055: step: 2040/530, loss: 0.059149935841560364
2023-01-23 04:12:23.653431: step: 2044/530, loss: 0.0010932922596111894
2023-01-23 04:12:24.823415: step: 2048/530, loss: 0.031925298273563385
2023-01-23 04:12:26.034138: step: 2052/530, loss: 0.00017223358736373484
2023-01-23 04:12:27.187352: step: 2056/530, loss: 0.007066082675009966
2023-01-23 04:12:28.371428: step: 2060/530, loss: 0.00026264190091751516
2023-01-23 04:12:29.535929: step: 2064/530, loss: 0.5322442650794983
2023-01-23 04:12:30.718485: step: 2068/530, loss: 0.0003354072687216103
2023-01-23 04:12:31.907287: step: 2072/530, loss: 0.0006837844848632812
2023-01-23 04:12:33.062591: step: 2076/530, loss: 9.059906005859375e-06
2023-01-23 04:12:34.201919: step: 2080/530, loss: 1.6689300537109375e-06
2023-01-23 04:12:35.367467: step: 2084/530, loss: 0.02824115753173828
2023-01-23 04:12:36.520213: step: 2088/530, loss: 0.016320228576660156
2023-01-23 04:12:37.715570: step: 2092/530, loss: 0.00010118485079146922
2023-01-23 04:12:38.888425: step: 2096/530, loss: 1.106262243411038e-05
2023-01-23 04:12:40.060033: step: 2100/530, loss: 0.004332924261689186
2023-01-23 04:12:41.257364: step: 2104/530, loss: 0.0001888275146484375
2023-01-23 04:12:42.422165: step: 2108/530, loss: 0.005513286683708429
2023-01-23 04:12:43.568235: step: 2112/530, loss: 8.726119995117188e-05
2023-01-23 04:12:44.729069: step: 2116/530, loss: -2.8610230629055877e-07
2023-01-23 04:12:45.852328: step: 2120/530, loss: 0.0013326645130291581
==================================================
Loss: 0.021
--------------------
Dev: {'event': {'p': 0.5603864734299517, 'r': 0.7723035952063915, 'f1': 0.6494960806270997}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 25}
Test: {'event': {'p': 0.6428893905191874, 'r': 0.8188614146060954, 'f1': 0.7202832574607991}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 25}
Chinese: {'event': {'p': 0.5319148936170213, 'r': 0.9259259259259259, 'f1': 0.6756756756756757}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 25}
Korean: {'event': {'p': 0.6181818181818182, 'r': 0.5396825396825397, 'f1': 0.576271186440678}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 25}
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': 25}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.603537981269511, 'r': 0.7723035952063915, 'f1': 0.677570093457944}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Eng Test for Chinese: {'event': {'p': 0.6663560111835974, 'r': 0.8223116733755031, 'f1': 0.7361647361647363}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Sample Chinese: {'event': {'p': 0.611764705882353, 'r': 0.9629629629629629, 'f1': 0.748201438848921}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5733990147783251, 'r': 0.7749667110519307, 'f1': 0.6591166477916196}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Eng Test for Korean: {'event': {'p': 0.6218005295675199, 'r': 0.8102357676825762, 'f1': 0.7036204744069912}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Sample Korean: {'event': {'p': 0.6417910447761194, 'r': 0.6825396825396826, 'f1': 0.6615384615384614}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6284796573875803, 'r': 0.7816245006657789, 'f1': 0.6967359050445103}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Eng Test for Russian: {'event': {'p': 0.6768263183357524, 'r': 0.80448533640023, 'f1': 0.7351550183920126}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Sample Russian: {'event': {'p': 0.4791666666666667, 'r': 0.6388888888888888, 'f1': 0.5476190476190476}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
******************************
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 04:13:28.927744: step: 4/530, loss: 0.0007568359724245965
2023-01-23 04:13:30.080923: step: 8/530, loss: 0.000789642333984375
2023-01-23 04:13:31.277568: step: 12/530, loss: 0.007081222720444202
2023-01-23 04:13:32.450029: step: 16/530, loss: 0.02008648030459881
2023-01-23 04:13:33.615703: step: 20/530, loss: 1.5640260244254023e-05
2023-01-23 04:13:34.798520: step: 24/530, loss: 0.0005744934314861894
2023-01-23 04:13:35.961185: step: 28/530, loss: 0.00030517578125
2023-01-23 04:13:37.142416: step: 32/530, loss: 0.0013067246181890368
2023-01-23 04:13:38.286410: step: 36/530, loss: 2.8514861696748994e-05
2023-01-23 04:13:39.412451: step: 40/530, loss: 0.013948059640824795
2023-01-23 04:13:40.643351: step: 44/530, loss: 0.0015874862438067794
2023-01-23 04:13:41.753990: step: 48/530, loss: 9.384155418956652e-05
2023-01-23 04:13:42.960248: step: 52/530, loss: 0.004475307650864124
2023-01-23 04:13:44.121455: step: 56/530, loss: 0.005197715945541859
2023-01-23 04:13:45.295890: step: 60/530, loss: 0.0002473831409588456
2023-01-23 04:13:46.453259: step: 64/530, loss: 0.017169570550322533
2023-01-23 04:13:47.612823: step: 68/530, loss: 0.0059562684036791325
2023-01-23 04:13:48.765055: step: 72/530, loss: 1.9168854123563506e-05
2023-01-23 04:13:49.940474: step: 76/530, loss: 0.03314227983355522
2023-01-23 04:13:51.106245: step: 80/530, loss: 0.003228855086490512
2023-01-23 04:13:52.324867: step: 84/530, loss: 0.014593602158129215
2023-01-23 04:13:53.483342: step: 88/530, loss: 0.0008642196771688759
2023-01-23 04:13:54.640668: step: 92/530, loss: 0.028277970850467682
2023-01-23 04:13:55.816185: step: 96/530, loss: 0.013110924512147903
2023-01-23 04:13:57.003327: step: 100/530, loss: -7.629394076502649e-06
2023-01-23 04:13:58.216318: step: 104/530, loss: -2.47955313170678e-06
2023-01-23 04:13:59.399836: step: 108/530, loss: 0.00126142508815974
2023-01-23 04:14:00.539062: step: 112/530, loss: 1.5258792700478807e-06
2023-01-23 04:14:01.709010: step: 116/530, loss: 0.0017021179664880037
2023-01-23 04:14:02.830395: step: 120/530, loss: 0.001508426619693637
2023-01-23 04:14:03.999302: step: 124/530, loss: 0.002375364303588867
2023-01-23 04:14:05.176317: step: 128/530, loss: 0.0025171281304210424
2023-01-23 04:14:06.346874: step: 132/530, loss: 0.0010322571033611894
2023-01-23 04:14:07.489778: step: 136/530, loss: 0.007959938608109951
2023-01-23 04:14:08.629768: step: 140/530, loss: 0.003632068634033203
2023-01-23 04:14:09.788435: step: 144/530, loss: 0.16893978416919708
2023-01-23 04:14:10.975935: step: 148/530, loss: 0.003363037249073386
2023-01-23 04:14:12.153678: step: 152/530, loss: 0.0062608723528683186
2023-01-23 04:14:13.302721: step: 156/530, loss: 0.012283516116440296
2023-01-23 04:14:14.459739: step: 160/530, loss: -4.911422365694307e-06
2023-01-23 04:14:15.636659: step: 164/530, loss: 0.024712370708584785
2023-01-23 04:14:16.828313: step: 168/530, loss: 0.00021839141845703125
2023-01-23 04:14:18.006601: step: 172/530, loss: 0.02800884284079075
2023-01-23 04:14:19.144997: step: 176/530, loss: 0.0009626864921301603
2023-01-23 04:14:20.337949: step: 180/530, loss: 0.0008506655576638877
2023-01-23 04:14:21.499793: step: 184/530, loss: 0.0005820274236612022
2023-01-23 04:14:22.652328: step: 188/530, loss: 0.02467288449406624
2023-01-23 04:14:23.795476: step: 192/530, loss: 5.855560448253527e-05
2023-01-23 04:14:24.942109: step: 196/530, loss: 0.0018627167446538806
2023-01-23 04:14:26.132323: step: 200/530, loss: 0.0003234863397665322
2023-01-23 04:14:27.356292: step: 204/530, loss: 0.03568696975708008
2023-01-23 04:14:28.580610: step: 208/530, loss: 0.009022235870361328
2023-01-23 04:14:29.740241: step: 212/530, loss: 0.00020465851412154734
2023-01-23 04:14:30.870065: step: 216/530, loss: 0.0031142234802246094
2023-01-23 04:14:32.015587: step: 220/530, loss: 0.00057306292001158
2023-01-23 04:14:33.203469: step: 224/530, loss: 1.659393274167087e-05
2023-01-23 04:14:34.392104: step: 228/530, loss: 0.00822978001087904
2023-01-23 04:14:35.538139: step: 232/530, loss: 0.06761913001537323
2023-01-23 04:14:36.735683: step: 236/530, loss: 0.00013666153245139867
2023-01-23 04:14:37.853727: step: 240/530, loss: 0.00016946792311500758
2023-01-23 04:14:39.033133: step: 244/530, loss: 0.0008533478248864412
2023-01-23 04:14:40.194950: step: 248/530, loss: 0.005192756652832031
2023-01-23 04:14:41.363756: step: 252/530, loss: 0.00134449009783566
2023-01-23 04:14:42.560626: step: 256/530, loss: 0.003793763928115368
2023-01-23 04:14:43.724611: step: 260/530, loss: 1.640319896978326e-05
2023-01-23 04:14:44.876173: step: 264/530, loss: 7.972717139637098e-05
2023-01-23 04:14:46.035804: step: 268/530, loss: 0.011298180557787418
2023-01-23 04:14:47.171638: step: 272/530, loss: 8.64267349243164e-05
2023-01-23 04:14:48.314539: step: 276/530, loss: 0.0003021717129740864
2023-01-23 04:14:49.430991: step: 280/530, loss: 0.003907394595444202
2023-01-23 04:14:50.625793: step: 284/530, loss: 0.000901556049939245
2023-01-23 04:14:51.736254: step: 288/530, loss: 0.000935459160245955
2023-01-23 04:14:52.911868: step: 292/530, loss: 0.006976318545639515
2023-01-23 04:14:54.092195: step: 296/530, loss: 0.002673340030014515
2023-01-23 04:14:55.250344: step: 300/530, loss: 0.0051259989850223064
2023-01-23 04:14:56.425968: step: 304/530, loss: 4.4441225327318534e-05
2023-01-23 04:14:57.573794: step: 308/530, loss: 3.070831371587701e-05
2023-01-23 04:14:58.753378: step: 312/530, loss: 0.042662426829338074
2023-01-23 04:14:59.973396: step: 316/530, loss: 3.61442580469884e-05
2023-01-23 04:15:01.117366: step: 320/530, loss: 2.0122528439969756e-05
2023-01-23 04:15:02.305948: step: 324/530, loss: 0.0007370948442257941
2023-01-23 04:15:03.477522: step: 328/530, loss: 0.003315162844955921
2023-01-23 04:15:04.642048: step: 332/530, loss: 0.2565120458602905
2023-01-23 04:15:05.845712: step: 336/530, loss: 0.00016322211013175547
2023-01-23 04:15:07.003596: step: 340/530, loss: 0.0003981590270996094
2023-01-23 04:15:08.176694: step: 344/530, loss: 4.043579247081652e-05
2023-01-23 04:15:09.327122: step: 348/530, loss: 0.012861061841249466
2023-01-23 04:15:10.526473: step: 352/530, loss: 0.021822737529873848
2023-01-23 04:15:11.735881: step: 356/530, loss: 0.004702186677604914
2023-01-23 04:15:12.883701: step: 360/530, loss: 8.621215965831652e-05
2023-01-23 04:15:14.106272: step: 364/530, loss: 0.0001369476376567036
2023-01-23 04:15:15.261903: step: 368/530, loss: 8.77380352903856e-06
2023-01-23 04:15:16.436407: step: 372/530, loss: 0.0008996963733807206
2023-01-23 04:15:17.600122: step: 376/530, loss: 0.000244590628426522
2023-01-23 04:15:18.735846: step: 380/530, loss: 0.0032007216941565275
2023-01-23 04:15:19.920018: step: 384/530, loss: 0.000171661376953125
2023-01-23 04:15:21.098192: step: 388/530, loss: 0.0002132415829692036
2023-01-23 04:15:22.289060: step: 392/530, loss: 6.999969627941027e-05
2023-01-23 04:15:23.449499: step: 396/530, loss: 7.343292054429185e-06
2023-01-23 04:15:24.612097: step: 400/530, loss: 0.02237539365887642
2023-01-23 04:15:25.785719: step: 404/530, loss: 0.025648878887295723
2023-01-23 04:15:26.992630: step: 408/530, loss: 0.09307050704956055
2023-01-23 04:15:28.164647: step: 412/530, loss: 0.016724204644560814
2023-01-23 04:15:29.323223: step: 416/530, loss: 0.00046606065006926656
2023-01-23 04:15:30.450370: step: 420/530, loss: 0.002266311552375555
2023-01-23 04:15:31.604218: step: 424/530, loss: 0.0010375023121014237
2023-01-23 04:15:32.797020: step: 428/530, loss: 0.0015836716629564762
2023-01-23 04:15:33.955438: step: 432/530, loss: 0.001078271889127791
2023-01-23 04:15:35.125650: step: 436/530, loss: 0.0008712768321856856
2023-01-23 04:15:36.289124: step: 440/530, loss: 1.3732910701946821e-05
2023-01-23 04:15:37.453225: step: 444/530, loss: 7.24792471373803e-06
2023-01-23 04:15:38.627672: step: 448/530, loss: 0.012126159854233265
2023-01-23 04:15:39.810208: step: 452/530, loss: 0.007420015055686235
2023-01-23 04:15:41.009866: step: 456/530, loss: 0.004495430272072554
2023-01-23 04:15:42.191947: step: 460/530, loss: 0.0011464118724688888
2023-01-23 04:15:43.349698: step: 464/530, loss: 0.039704132825136185
2023-01-23 04:15:44.511172: step: 468/530, loss: 0.001136398408561945
2023-01-23 04:15:45.669826: step: 472/530, loss: 0.00037107468233443797
2023-01-23 04:15:46.866732: step: 476/530, loss: 0.33526134490966797
2023-01-23 04:15:48.010432: step: 480/530, loss: 0.0004972458118572831
2023-01-23 04:15:49.195988: step: 484/530, loss: -1.52587890625e-05
2023-01-23 04:15:50.350332: step: 488/530, loss: 0.03555698320269585
2023-01-23 04:15:51.487730: step: 492/530, loss: 1.4305115655588452e-05
2023-01-23 04:15:52.681560: step: 496/530, loss: 0.026581954210996628
2023-01-23 04:15:53.846991: step: 500/530, loss: 4.00543194700731e-06
2023-01-23 04:15:55.013018: step: 504/530, loss: 0.03551435470581055
2023-01-23 04:15:56.190854: step: 508/530, loss: 0.032139018177986145
2023-01-23 04:15:57.364571: step: 512/530, loss: 0.00390892056748271
2023-01-23 04:15:58.556074: step: 516/530, loss: 1.71661376953125e-05
2023-01-23 04:15:59.707774: step: 520/530, loss: 0.00043010711669921875
2023-01-23 04:16:00.885004: step: 524/530, loss: 0.04823443293571472
2023-01-23 04:16:02.068402: step: 528/530, loss: 0.00024199485778808594
2023-01-23 04:16:03.196846: step: 532/530, loss: 0.003749799681827426
2023-01-23 04:16:04.371679: step: 536/530, loss: 0.003295517060905695
2023-01-23 04:16:05.534289: step: 540/530, loss: 0.0003692627069540322
2023-01-23 04:16:06.721630: step: 544/530, loss: 2.6607514882925898e-05
2023-01-23 04:16:07.879124: step: 548/530, loss: 8.525848534191027e-05
2023-01-23 04:16:09.102217: step: 552/530, loss: 0.01848583295941353
2023-01-23 04:16:10.282378: step: 556/530, loss: 6.904602196300402e-05
2023-01-23 04:16:11.439808: step: 560/530, loss: 2.288818359375e-05
2023-01-23 04:16:12.639729: step: 564/530, loss: 0.004246520809829235
2023-01-23 04:16:13.828729: step: 568/530, loss: 0.011366653256118298
2023-01-23 04:16:14.975888: step: 572/530, loss: 0.021131135523319244
2023-01-23 04:16:16.162402: step: 576/530, loss: 0.06805382668972015
2023-01-23 04:16:17.358433: step: 580/530, loss: 0.00032863617525435984
2023-01-23 04:16:18.527306: step: 584/530, loss: 0.01811981201171875
2023-01-23 04:16:19.691321: step: 588/530, loss: 6.68525681248866e-05
2023-01-23 04:16:20.846567: step: 592/530, loss: 9.32693510549143e-05
2023-01-23 04:16:22.003037: step: 596/530, loss: 0.00023641585721634328
2023-01-23 04:16:23.132990: step: 600/530, loss: 4.100799742445815e-06
2023-01-23 04:16:24.267628: step: 604/530, loss: 0.0018379210960119963
2023-01-23 04:16:25.405677: step: 608/530, loss: 0.0013702393043786287
2023-01-23 04:16:26.603100: step: 612/530, loss: 0.0008249283418990672
2023-01-23 04:16:27.795169: step: 616/530, loss: 0.000719261122867465
2023-01-23 04:16:28.966083: step: 620/530, loss: 0.000911331211682409
2023-01-23 04:16:30.182496: step: 624/530, loss: 0.04983940348029137
2023-01-23 04:16:31.321307: step: 628/530, loss: 8.96453821042087e-06
2023-01-23 04:16:32.517427: step: 632/530, loss: 0.0003658771456684917
2023-01-23 04:16:33.732256: step: 636/530, loss: 0.0015933990944176912
2023-01-23 04:16:34.950026: step: 640/530, loss: 0.0035876273177564144
2023-01-23 04:16:36.163380: step: 644/530, loss: 0.0003837585391011089
2023-01-23 04:16:37.324143: step: 648/530, loss: 4.959107172908261e-06
2023-01-23 04:16:38.492972: step: 652/530, loss: 0.00549659738317132
2023-01-23 04:16:39.675751: step: 656/530, loss: 0.0005027293809689581
2023-01-23 04:16:40.824156: step: 660/530, loss: 0.0028153895400464535
2023-01-23 04:16:42.043770: step: 664/530, loss: 0.00101137172896415
2023-01-23 04:16:43.213221: step: 668/530, loss: 0.0016317367553710938
2023-01-23 04:16:44.354582: step: 672/530, loss: 0.00011301040649414062
2023-01-23 04:16:45.515698: step: 676/530, loss: 0.0020776749588549137
2023-01-23 04:16:46.665680: step: 680/530, loss: 0.00027637480525299907
2023-01-23 04:16:47.881029: step: 684/530, loss: 1.087188684323337e-05
2023-01-23 04:16:49.044041: step: 688/530, loss: 0.032381821423769
2023-01-23 04:16:50.194049: step: 692/530, loss: 5.53131121705519e-06
2023-01-23 04:16:51.365381: step: 696/530, loss: 0.02615508995950222
2023-01-23 04:16:52.578629: step: 700/530, loss: 0.00012254714965820312
2023-01-23 04:16:53.715895: step: 704/530, loss: 0.04984540864825249
2023-01-23 04:16:54.895411: step: 708/530, loss: 0.0004677772521972656
2023-01-23 04:16:56.063576: step: 712/530, loss: 0.00036115647526457906
2023-01-23 04:16:57.221391: step: 716/530, loss: 0.0002439498930471018
2023-01-23 04:16:58.357598: step: 720/530, loss: 0.0007411956903524697
2023-01-23 04:16:59.524595: step: 724/530, loss: 0.04214467853307724
2023-01-23 04:17:00.686825: step: 728/530, loss: 0.01281723938882351
2023-01-23 04:17:01.820230: step: 732/530, loss: 0.0002998351992573589
2023-01-23 04:17:03.020348: step: 736/530, loss: 5.999803397571668e-05
2023-01-23 04:17:04.182677: step: 740/530, loss: 0.0005027771112509072
2023-01-23 04:17:05.347503: step: 744/530, loss: 0.0597267672419548
2023-01-23 04:17:06.522571: step: 748/530, loss: 2.28881845032447e-06
2023-01-23 04:17:07.689682: step: 752/530, loss: 0.0033818245865404606
2023-01-23 04:17:08.881194: step: 756/530, loss: 0.0004976272466592491
2023-01-23 04:17:10.032273: step: 760/530, loss: 0.0044303894974291325
2023-01-23 04:17:11.199122: step: 764/530, loss: 0.5494731664657593
2023-01-23 04:17:12.364716: step: 768/530, loss: 0.00227012624964118
2023-01-23 04:17:13.537739: step: 772/530, loss: 0.001123714493587613
2023-01-23 04:17:14.711430: step: 776/530, loss: 0.010221481323242188
2023-01-23 04:17:15.910363: step: 780/530, loss: 7.843971616239287e-06
2023-01-23 04:17:17.072396: step: 784/530, loss: 0.005095290951430798
2023-01-23 04:17:18.230241: step: 788/530, loss: 0.026606272906064987
2023-01-23 04:17:19.381396: step: 792/530, loss: 9.870528447208926e-05
2023-01-23 04:17:20.546363: step: 796/530, loss: 0.03448162227869034
2023-01-23 04:17:21.713419: step: 800/530, loss: 8.678435733600054e-06
2023-01-23 04:17:22.870329: step: 804/530, loss: 0.001176905701868236
2023-01-23 04:17:24.012303: step: 808/530, loss: -4.57763690064894e-06
2023-01-23 04:17:25.196890: step: 812/530, loss: 0.00015993117995094508
2023-01-23 04:17:26.374304: step: 816/530, loss: 0.04126386716961861
2023-01-23 04:17:27.565145: step: 820/530, loss: 0.0003602981742005795
2023-01-23 04:17:28.725987: step: 824/530, loss: 0.0006037711864337325
2023-01-23 04:17:29.904168: step: 828/530, loss: 0.003129387041553855
2023-01-23 04:17:31.102494: step: 832/530, loss: 0.04142417758703232
2023-01-23 04:17:32.266734: step: 836/530, loss: 0.003353309817612171
2023-01-23 04:17:33.457884: step: 840/530, loss: 0.022490119561553
2023-01-23 04:17:34.617597: step: 844/530, loss: 0.00012054444232489914
2023-01-23 04:17:35.803880: step: 848/530, loss: 0.0005702018970623612
2023-01-23 04:17:36.992288: step: 852/530, loss: 0.003967476077377796
2023-01-23 04:17:38.220216: step: 856/530, loss: -2.574920654296875e-05
2023-01-23 04:17:39.428441: step: 860/530, loss: 0.6077167391777039
2023-01-23 04:17:40.593393: step: 864/530, loss: -1.602172778802924e-05
2023-01-23 04:17:41.753094: step: 868/530, loss: 3.337860050578456e-07
2023-01-23 04:17:42.916520: step: 872/530, loss: 9.72747784544481e-06
2023-01-23 04:17:44.063354: step: 876/530, loss: 0.0011521339183673263
2023-01-23 04:17:45.253794: step: 880/530, loss: 0.0014534472720697522
2023-01-23 04:17:46.431791: step: 884/530, loss: 0.0003037452697753906
2023-01-23 04:17:47.609471: step: 888/530, loss: 1.811981201171875e-05
2023-01-23 04:17:48.766017: step: 892/530, loss: 0.060346126556396484
2023-01-23 04:17:49.953874: step: 896/530, loss: 0.017130661755800247
2023-01-23 04:17:51.107856: step: 900/530, loss: 0.006789970677345991
2023-01-23 04:17:52.260871: step: 904/530, loss: 0.006602096371352673
2023-01-23 04:17:53.454329: step: 908/530, loss: 0.0019224167335778475
2023-01-23 04:17:54.606307: step: 912/530, loss: 0.002901363419368863
2023-01-23 04:17:55.776728: step: 916/530, loss: 0.0003399848937988281
2023-01-23 04:17:56.995216: step: 920/530, loss: 0.008092307485640049
2023-01-23 04:17:58.146431: step: 924/530, loss: 0.00016107558622024953
2023-01-23 04:17:59.316721: step: 928/530, loss: 0.0010921478969976306
2023-01-23 04:18:00.449634: step: 932/530, loss: 0.006289577577263117
2023-01-23 04:18:01.653634: step: 936/530, loss: 0.011955118738114834
2023-01-23 04:18:02.816914: step: 940/530, loss: 0.02442169189453125
2023-01-23 04:18:03.998143: step: 944/530, loss: 0.00762100238353014
2023-01-23 04:18:05.251045: step: 948/530, loss: 0.0023729323875159025
2023-01-23 04:18:06.419828: step: 952/530, loss: 0.002636528108268976
2023-01-23 04:18:07.606106: step: 956/530, loss: 0.00024480820866301656
2023-01-23 04:18:08.783140: step: 960/530, loss: 5.445480201160535e-05
2023-01-23 04:18:09.924049: step: 964/530, loss: 0.006041908171027899
2023-01-23 04:18:11.090681: step: 968/530, loss: 0.00015468598576262593
2023-01-23 04:18:12.251032: step: 972/530, loss: 0.000392913818359375
2023-01-23 04:18:13.457223: step: 976/530, loss: 0.04430718347430229
2023-01-23 04:18:14.684818: step: 980/530, loss: 0.0004947215784341097
2023-01-23 04:18:15.852930: step: 984/530, loss: 0.0018101693131029606
2023-01-23 04:18:17.027069: step: 988/530, loss: 0.0009911536471918225
2023-01-23 04:18:18.176298: step: 992/530, loss: 0.00022783280292060226
2023-01-23 04:18:19.383944: step: 996/530, loss: 0.0017267226940020919
2023-01-23 04:18:20.601953: step: 1000/530, loss: 0.0005803108215332031
2023-01-23 04:18:21.746806: step: 1004/530, loss: 2.403259350103326e-05
2023-01-23 04:18:22.977303: step: 1008/530, loss: 0.0022466660011559725
2023-01-23 04:18:24.164782: step: 1012/530, loss: 0.0019380568992346525
2023-01-23 04:18:25.327770: step: 1016/530, loss: 0.0002027511509368196
2023-01-23 04:18:26.509365: step: 1020/530, loss: 0.015423774719238281
2023-01-23 04:18:27.656469: step: 1024/530, loss: 1.1825562069134321e-05
2023-01-23 04:18:28.821187: step: 1028/530, loss: 0.005142593290656805
2023-01-23 04:18:30.008718: step: 1032/530, loss: 0.06525135040283203
2023-01-23 04:18:31.193418: step: 1036/530, loss: 0.08869529515504837
2023-01-23 04:18:32.364964: step: 1040/530, loss: 0.008227539248764515
2023-01-23 04:18:33.545410: step: 1044/530, loss: 0.10853490233421326
2023-01-23 04:18:34.767071: step: 1048/530, loss: 0.0004175186331849545
2023-01-23 04:18:35.915699: step: 1052/530, loss: 0.006182861514389515
2023-01-23 04:18:37.053914: step: 1056/530, loss: 0.022937975823879242
2023-01-23 04:18:38.223531: step: 1060/530, loss: 2.689361645025201e-05
2023-01-23 04:18:39.399403: step: 1064/530, loss: 0.00026302336482331157
2023-01-23 04:18:40.578023: step: 1068/530, loss: 2.6798248654813506e-05
2023-01-23 04:18:41.824575: step: 1072/530, loss: 3.814697265625e-05
2023-01-23 04:18:42.945068: step: 1076/530, loss: 1.029968279908644e-05
2023-01-23 04:18:44.109231: step: 1080/530, loss: 0.03255882114171982
2023-01-23 04:18:45.300844: step: 1084/530, loss: 1.6689300537109375e-05
2023-01-23 04:18:46.531678: step: 1088/530, loss: -5.626678557746345e-06
2023-01-23 04:18:47.703687: step: 1092/530, loss: 0.001160097192041576
2023-01-23 04:18:48.877956: step: 1096/530, loss: 0.0005065918085165322
2023-01-23 04:18:50.111621: step: 1100/530, loss: 0.03304634243249893
2023-01-23 04:18:51.316154: step: 1104/530, loss: 0.013874339871108532
2023-01-23 04:18:52.483633: step: 1108/530, loss: 0.0012496948475018144
2023-01-23 04:18:53.685311: step: 1112/530, loss: 0.010713387280702591
2023-01-23 04:18:54.859187: step: 1116/530, loss: 2.2077560061006807e-05
2023-01-23 04:18:56.025127: step: 1120/530, loss: 0.0011201859451830387
2023-01-23 04:18:57.208368: step: 1124/530, loss: 0.0011579514248296618
2023-01-23 04:18:58.330731: step: 1128/530, loss: 9.269714064430445e-05
2023-01-23 04:18:59.499999: step: 1132/530, loss: 0.014981555752456188
2023-01-23 04:19:00.685128: step: 1136/530, loss: 0.012707042507827282
2023-01-23 04:19:01.866341: step: 1140/530, loss: 0.00010375976853538305
2023-01-23 04:19:03.011659: step: 1144/530, loss: 0.004528141114860773
2023-01-23 04:19:04.222199: step: 1148/530, loss: 0.028721999377012253
2023-01-23 04:19:05.381025: step: 1152/530, loss: 6.4849850787140895e-06
2023-01-23 04:19:06.564628: step: 1156/530, loss: 0.00014867782010696828
2023-01-23 04:19:07.754373: step: 1160/530, loss: 0.00014743805513717234
2023-01-23 04:19:08.928274: step: 1164/530, loss: 0.24661773443222046
2023-01-23 04:19:10.132376: step: 1168/530, loss: 0.029487991705536842
2023-01-23 04:19:11.321432: step: 1172/530, loss: 8.296966370835435e-06
2023-01-23 04:19:12.547474: step: 1176/530, loss: 5.5122378398664296e-05
2023-01-23 04:19:13.750701: step: 1180/530, loss: -1.9073513612966053e-07
2023-01-23 04:19:14.938851: step: 1184/530, loss: 5.664825584972277e-05
2023-01-23 04:19:16.107440: step: 1188/530, loss: 3.8719179428881034e-05
2023-01-23 04:19:17.287169: step: 1192/530, loss: 0.005318927578628063
2023-01-23 04:19:18.462505: step: 1196/530, loss: 0.0010579109657555819
2023-01-23 04:19:19.673308: step: 1200/530, loss: 5.0020218623103574e-05
2023-01-23 04:19:20.816929: step: 1204/530, loss: 0.006645965855568647
2023-01-23 04:19:22.014888: step: 1208/530, loss: 0.0002490997430868447
2023-01-23 04:19:23.166762: step: 1212/530, loss: 1.3351441339182202e-06
2023-01-23 04:19:24.360722: step: 1216/530, loss: 0.10840167850255966
2023-01-23 04:19:25.618105: step: 1220/530, loss: 0.009071588516235352
2023-01-23 04:19:26.784447: step: 1224/530, loss: 0.009002208709716797
2023-01-23 04:19:27.939220: step: 1228/530, loss: -1.430511474609375e-06
2023-01-23 04:19:29.095410: step: 1232/530, loss: 1.9550323486328125e-05
2023-01-23 04:19:30.330831: step: 1236/530, loss: 2.86102294921875e-06
2023-01-23 04:19:31.525281: step: 1240/530, loss: 7.734299288131297e-05
2023-01-23 04:19:32.666457: step: 1244/530, loss: 0.017638398334383965
2023-01-23 04:19:33.841911: step: 1248/530, loss: 0.001321983290836215
2023-01-23 04:19:35.032695: step: 1252/530, loss: 0.0007258415571413934
2023-01-23 04:19:36.187903: step: 1256/530, loss: 0.07361221313476562
2023-01-23 04:19:37.323314: step: 1260/530, loss: 0.0014802933437749743
2023-01-23 04:19:38.520730: step: 1264/530, loss: 0.03154754638671875
2023-01-23 04:19:39.682250: step: 1268/530, loss: 2.517700158932712e-05
2023-01-23 04:19:40.851218: step: 1272/530, loss: 0.020094681531190872
2023-01-23 04:19:42.044502: step: 1276/530, loss: 0.015736008062958717
2023-01-23 04:19:43.207976: step: 1280/530, loss: 0.000560760498046875
2023-01-23 04:19:44.405625: step: 1284/530, loss: 0.004497718531638384
2023-01-23 04:19:45.633065: step: 1288/530, loss: 0.03965797647833824
2023-01-23 04:19:46.810911: step: 1292/530, loss: 0.00014240741438698024
2023-01-23 04:19:47.969483: step: 1296/530, loss: 0.0038696289993822575
2023-01-23 04:19:49.108028: step: 1300/530, loss: -5.722046125811175e-07
2023-01-23 04:19:50.287236: step: 1304/530, loss: 0.02644939348101616
2023-01-23 04:19:51.474917: step: 1308/530, loss: 0.0005460738902911544
2023-01-23 04:19:52.616607: step: 1312/530, loss: 0.005497550591826439
2023-01-23 04:19:53.799353: step: 1316/530, loss: 0.00822525005787611
2023-01-23 04:19:54.969490: step: 1320/530, loss: 0.0001352310209767893
2023-01-23 04:19:56.121907: step: 1324/530, loss: 0.00020141602726653218
2023-01-23 04:19:57.262550: step: 1328/530, loss: 0.0007658004178665578
2023-01-23 04:19:58.422953: step: 1332/530, loss: 0.0002704620419535786
2023-01-23 04:19:59.574900: step: 1336/530, loss: 0.02989816665649414
2023-01-23 04:20:00.785653: step: 1340/530, loss: 0.00987462978810072
2023-01-23 04:20:01.951148: step: 1344/530, loss: 7.629394076502649e-07
2023-01-23 04:20:03.108222: step: 1348/530, loss: 4.062652442371473e-05
2023-01-23 04:20:04.261689: step: 1352/530, loss: 0.030718136578798294
2023-01-23 04:20:05.399918: step: 1356/530, loss: 0.005306530278176069
2023-01-23 04:20:06.568450: step: 1360/530, loss: 4.95910626341356e-06
2023-01-23 04:20:07.757565: step: 1364/530, loss: 0.00403175363317132
2023-01-23 04:20:08.958843: step: 1368/530, loss: 0.03531799092888832
2023-01-23 04:20:10.110245: step: 1372/530, loss: 0.18708762526512146
2023-01-23 04:20:11.260171: step: 1376/530, loss: 1.0871887752728071e-05
2023-01-23 04:20:12.441430: step: 1380/530, loss: 0.005984306335449219
2023-01-23 04:20:13.636270: step: 1384/530, loss: 0.04849529266357422
2023-01-23 04:20:14.857907: step: 1388/530, loss: -1.2016295841021929e-05
2023-01-23 04:20:16.021319: step: 1392/530, loss: 0.012498856522142887
2023-01-23 04:20:17.258460: step: 1396/530, loss: 0.02756214141845703
2023-01-23 04:20:18.428190: step: 1400/530, loss: 0.002640151884406805
2023-01-23 04:20:19.614666: step: 1404/530, loss: 0.0022094727028161287
2023-01-23 04:20:20.745727: step: 1408/530, loss: 0.0017432213062420487
2023-01-23 04:20:21.889141: step: 1412/530, loss: 2.4795533590804553e-06
2023-01-23 04:20:23.021967: step: 1416/530, loss: 0.0006325722206383944
2023-01-23 04:20:24.232022: step: 1420/530, loss: 0.006892586126923561
2023-01-23 04:20:25.391208: step: 1424/530, loss: 1.5926361811580136e-05
2023-01-23 04:20:26.539050: step: 1428/530, loss: 2.2983551389188506e-05
2023-01-23 04:20:27.727857: step: 1432/530, loss: 9.303689148509875e-05
2023-01-23 04:20:28.900368: step: 1436/530, loss: 0.005741882603615522
2023-01-23 04:20:30.069968: step: 1440/530, loss: 0.6808220148086548
2023-01-23 04:20:31.220814: step: 1444/530, loss: 1.964569128176663e-05
2023-01-23 04:20:32.378460: step: 1448/530, loss: 2.5177003408316523e-05
2023-01-23 04:20:33.551907: step: 1452/530, loss: 0.008117723278701305
2023-01-23 04:20:34.695214: step: 1456/530, loss: -2.47955313170678e-06
2023-01-23 04:20:35.873567: step: 1460/530, loss: 0.007694053463637829
2023-01-23 04:20:37.013146: step: 1464/530, loss: 7.953643944347277e-05
2023-01-23 04:20:38.220387: step: 1468/530, loss: 0.0006851673242636025
2023-01-23 04:20:39.384552: step: 1472/530, loss: 0.27452126145362854
2023-01-23 04:20:40.520188: step: 1476/530, loss: 0.0002521514834370464
2023-01-23 04:20:41.667487: step: 1480/530, loss: 0.0004478454648051411
2023-01-23 04:20:42.855341: step: 1484/530, loss: 6.380080594681203e-05
2023-01-23 04:20:44.012455: step: 1488/530, loss: 1.3208389646024443e-05
2023-01-23 04:20:45.217175: step: 1492/530, loss: 0.008752251043915749
2023-01-23 04:20:46.410072: step: 1496/530, loss: 4.7290326619986445e-05
2023-01-23 04:20:47.591205: step: 1500/530, loss: 0.00012643336958717555
2023-01-23 04:20:48.778642: step: 1504/530, loss: 0.06284723430871964
2023-01-23 04:20:49.963238: step: 1508/530, loss: 0.009980965405702591
2023-01-23 04:20:51.145896: step: 1512/530, loss: 0.00010881424532271922
2023-01-23 04:20:52.309939: step: 1516/530, loss: 0.00030765534029342234
2023-01-23 04:20:53.516541: step: 1520/530, loss: 9.441375732421875e-05
2023-01-23 04:20:54.739633: step: 1524/530, loss: 0.0007264137384481728
2023-01-23 04:20:55.886047: step: 1528/530, loss: 2.403259350103326e-05
2023-01-23 04:20:57.128697: step: 1532/530, loss: 0.0004508972051553428
2023-01-23 04:20:58.329042: step: 1536/530, loss: 0.00015439986600540578
2023-01-23 04:20:59.556565: step: 1540/530, loss: 0.26156723499298096
2023-01-23 04:21:00.733911: step: 1544/530, loss: 0.008775139227509499
2023-01-23 04:21:01.867814: step: 1548/530, loss: 5.9604644775390625e-05
2023-01-23 04:21:03.008173: step: 1552/530, loss: 0.0002475738583598286
2023-01-23 04:21:04.135139: step: 1556/530, loss: -7.24792471373803e-06
2023-01-23 04:21:05.294984: step: 1560/530, loss: 0.0008518219110555947
2023-01-23 04:21:06.456958: step: 1564/530, loss: 0.0015647888649255037
2023-01-23 04:21:07.657317: step: 1568/530, loss: 0.01835193671286106
2023-01-23 04:21:08.798419: step: 1572/530, loss: 0.0004593849298544228
2023-01-23 04:21:09.974402: step: 1576/530, loss: 0.013573646545410156
2023-01-23 04:21:11.132300: step: 1580/530, loss: 0.03272509574890137
2023-01-23 04:21:12.330483: step: 1584/530, loss: 3.1089784897631034e-05
2023-01-23 04:21:13.468237: step: 1588/530, loss: 0.017539408057928085
2023-01-23 04:21:14.617276: step: 1592/530, loss: 2.9706954592256807e-05
2023-01-23 04:21:15.787487: step: 1596/530, loss: 0.10423310846090317
2023-01-23 04:21:16.971956: step: 1600/530, loss: 1.068115216185106e-05
2023-01-23 04:21:18.134803: step: 1604/530, loss: 0.00011692046973621473
2023-01-23 04:21:19.296856: step: 1608/530, loss: 0.001994896214455366
2023-01-23 04:21:20.551092: step: 1612/530, loss: 0.010228920727968216
2023-01-23 04:21:21.722775: step: 1616/530, loss: 0.0009129524114541709
2023-01-23 04:21:22.918858: step: 1620/530, loss: 0.00224552140571177
2023-01-23 04:21:24.104471: step: 1624/530, loss: 0.01322717685252428
2023-01-23 04:21:25.301743: step: 1628/530, loss: 0.0002165317564504221
2023-01-23 04:21:26.484831: step: 1632/530, loss: 4.19616708313697e-06
2023-01-23 04:21:27.703392: step: 1636/530, loss: 0.0011947632301598787
2023-01-23 04:21:28.884430: step: 1640/530, loss: 5.187988426769152e-05
2023-01-23 04:21:30.024582: step: 1644/530, loss: 7.04765334376134e-05
2023-01-23 04:21:31.193884: step: 1648/530, loss: 0.015824509784579277
2023-01-23 04:21:32.367618: step: 1652/530, loss: 0.005257987882941961
2023-01-23 04:21:33.593663: step: 1656/530, loss: 0.00292720808647573
2023-01-23 04:21:34.735991: step: 1660/530, loss: 0.0020580291748046875
2023-01-23 04:21:35.903877: step: 1664/530, loss: 6.27517729299143e-05
2023-01-23 04:21:37.078676: step: 1668/530, loss: 4.692077709478326e-05
2023-01-23 04:21:38.194754: step: 1672/530, loss: 0.00011215210543014109
2023-01-23 04:21:39.379894: step: 1676/530, loss: 0.00032701491727493703
2023-01-23 04:21:40.526012: step: 1680/530, loss: 6.151199340820312e-05
2023-01-23 04:21:41.682481: step: 1684/530, loss: 0.0881689041852951
2023-01-23 04:21:42.916665: step: 1688/530, loss: 1.955032530531753e-06
2023-01-23 04:21:44.067255: step: 1692/530, loss: 7.119178189896047e-05
2023-01-23 04:21:45.308038: step: 1696/530, loss: 0.001602554228156805
2023-01-23 04:21:46.474583: step: 1700/530, loss: 9.74655122263357e-05
2023-01-23 04:21:47.675042: step: 1704/530, loss: 2.002716064453125e-05
2023-01-23 04:21:48.834933: step: 1708/530, loss: 4.367828296381049e-05
2023-01-23 04:21:49.990171: step: 1712/530, loss: 0.012990475632250309
2023-01-23 04:21:51.135405: step: 1716/530, loss: 0.011924361810088158
2023-01-23 04:21:52.299710: step: 1720/530, loss: 8.01086389401462e-06
2023-01-23 04:21:53.512546: step: 1724/530, loss: 0.00032167433528229594
2023-01-23 04:21:54.678972: step: 1728/530, loss: 0.0011802673107013106
2023-01-23 04:21:55.858200: step: 1732/530, loss: 0.0004791259707417339
2023-01-23 04:21:57.021125: step: 1736/530, loss: 0.00028867722721770406
2023-01-23 04:21:58.161569: step: 1740/530, loss: 0.008658124133944511
2023-01-23 04:21:59.321711: step: 1744/530, loss: 0.2613298296928406
2023-01-23 04:22:00.484949: step: 1748/530, loss: 0.004587268922477961
2023-01-23 04:22:01.687104: step: 1752/530, loss: 0.0003921508905477822
2023-01-23 04:22:02.902061: step: 1756/530, loss: 0.06064901500940323
2023-01-23 04:22:04.108322: step: 1760/530, loss: 0.002286243485286832
2023-01-23 04:22:05.248624: step: 1764/530, loss: 0.00023480058007407933
2023-01-23 04:22:06.410520: step: 1768/530, loss: 0.010594654828310013
2023-01-23 04:22:07.563202: step: 1772/530, loss: 0.0012146950466558337
2023-01-23 04:22:08.729212: step: 1776/530, loss: 2.393722752458416e-05
2023-01-23 04:22:09.849183: step: 1780/530, loss: 2.880096508306451e-05
2023-01-23 04:22:11.036845: step: 1784/530, loss: 6.10351571594947e-06
2023-01-23 04:22:12.219537: step: 1788/530, loss: 0.0014347076648846269
2023-01-23 04:22:13.357288: step: 1792/530, loss: 0.0022736547980457544
2023-01-23 04:22:14.520302: step: 1796/530, loss: 0.0001733779936330393
2023-01-23 04:22:15.699486: step: 1800/530, loss: 7.05718994140625e-05
2023-01-23 04:22:16.871949: step: 1804/530, loss: 0.00040340423583984375
2023-01-23 04:22:18.012528: step: 1808/530, loss: 4.215240551275201e-05
2023-01-23 04:22:19.167788: step: 1812/530, loss: 0.004420280456542969
2023-01-23 04:22:20.342150: step: 1816/530, loss: 0.00019912720017600805
2023-01-23 04:22:21.541251: step: 1820/530, loss: 0.002767372177913785
2023-01-23 04:22:22.729655: step: 1824/530, loss: 0.0004207611200399697
2023-01-23 04:22:23.921332: step: 1828/530, loss: 1.7833710444392636e-05
2023-01-23 04:22:25.061573: step: 1832/530, loss: 0.0003097057342529297
2023-01-23 04:22:26.237568: step: 1836/530, loss: 5.817413693876006e-06
2023-01-23 04:22:27.450304: step: 1840/530, loss: 3.0994415283203125e-06
2023-01-23 04:22:28.613899: step: 1844/530, loss: 0.020272446796298027
2023-01-23 04:22:29.800820: step: 1848/530, loss: 0.00018959045701194555
2023-01-23 04:22:30.991891: step: 1852/530, loss: -4.100799742445815e-06
2023-01-23 04:22:32.163672: step: 1856/530, loss: 1.5258789289873675e-06
2023-01-23 04:22:33.346060: step: 1860/530, loss: 0.00044155120849609375
2023-01-23 04:22:34.508396: step: 1864/530, loss: 1.4257431757869199e-05
2023-01-23 04:22:35.616728: step: 1868/530, loss: 0.0008022308466024697
2023-01-23 04:22:36.803575: step: 1872/530, loss: 3.61442580469884e-05
2023-01-23 04:22:37.969559: step: 1876/530, loss: 0.0013172150356695056
2023-01-23 04:22:39.146700: step: 1880/530, loss: 0.031190158799290657
2023-01-23 04:22:40.272719: step: 1884/530, loss: -1.9073486328125e-06
2023-01-23 04:22:41.462474: step: 1888/530, loss: 0.012263918295502663
2023-01-23 04:22:42.624706: step: 1892/530, loss: 0.005146598909050226
2023-01-23 04:22:43.815706: step: 1896/530, loss: 0.030160902068018913
2023-01-23 04:22:44.959551: step: 1900/530, loss: 0.019657708704471588
2023-01-23 04:22:46.131797: step: 1904/530, loss: 0.005186653230339289
2023-01-23 04:22:47.302907: step: 1908/530, loss: 0.00033636094303801656
2023-01-23 04:22:48.477390: step: 1912/530, loss: 0.0002037048398051411
2023-01-23 04:22:49.629903: step: 1916/530, loss: 3.814697265625e-05
2023-01-23 04:22:50.812462: step: 1920/530, loss: 0.00023794174194335938
2023-01-23 04:22:51.965702: step: 1924/530, loss: 2.4414064682787284e-05
2023-01-23 04:22:53.194101: step: 1928/530, loss: 0.0017952442867681384
2023-01-23 04:22:54.320455: step: 1932/530, loss: 0.017080020159482956
2023-01-23 04:22:55.478429: step: 1936/530, loss: 0.01831073872745037
2023-01-23 04:22:56.635843: step: 1940/530, loss: 0.03422556072473526
2023-01-23 04:22:57.803251: step: 1944/530, loss: 0.007584571838378906
2023-01-23 04:22:58.950837: step: 1948/530, loss: 5.1212311518611386e-05
2023-01-23 04:23:00.124655: step: 1952/530, loss: 0.00025196076603606343
2023-01-23 04:23:01.294411: step: 1956/530, loss: 3.0326844353112392e-05
2023-01-23 04:23:02.544034: step: 1960/530, loss: 0.013930893503129482
2023-01-23 04:23:03.702957: step: 1964/530, loss: 0.0002763748343568295
2023-01-23 04:23:04.852568: step: 1968/530, loss: 7.152557373046875e-05
2023-01-23 04:23:06.018838: step: 1972/530, loss: 0.0011129379272460938
2023-01-23 04:23:07.161248: step: 1976/530, loss: 0.00010190009925281629
2023-01-23 04:23:08.314665: step: 1980/530, loss: 0.00531616248190403
2023-01-23 04:23:09.478553: step: 1984/530, loss: 6.448030035244301e-05
2023-01-23 04:23:10.635023: step: 1988/530, loss: 0.0011472703190520406
2023-01-23 04:23:11.817396: step: 1992/530, loss: 0.0029087066650390625
2023-01-23 04:23:13.022025: step: 1996/530, loss: 0.013268089853227139
2023-01-23 04:23:14.219564: step: 2000/530, loss: 0.06974449008703232
2023-01-23 04:23:15.352023: step: 2004/530, loss: 0.00023012161545921117
2023-01-23 04:23:16.570877: step: 2008/530, loss: 0.0004161834658589214
2023-01-23 04:23:17.699862: step: 2012/530, loss: 0.04718197509646416
2023-01-23 04:23:18.812662: step: 2016/530, loss: 4.76837158203125e-07
2023-01-23 04:23:19.965176: step: 2020/530, loss: 0.015970278531312943
2023-01-23 04:23:21.118441: step: 2024/530, loss: 0.024612711742520332
2023-01-23 04:23:22.266610: step: 2028/530, loss: 7.891654968261719e-05
2023-01-23 04:23:23.393171: step: 2032/530, loss: 0.00558891287073493
2023-01-23 04:23:24.578660: step: 2036/530, loss: 0.0020313262939453125
2023-01-23 04:23:25.768945: step: 2040/530, loss: 0.013216019608080387
2023-01-23 04:23:26.943134: step: 2044/530, loss: 3.4618376957951114e-05
2023-01-23 04:23:28.091245: step: 2048/530, loss: 5.9556961787166074e-05
2023-01-23 04:23:29.231298: step: 2052/530, loss: 0.00029430389986373484
2023-01-23 04:23:30.388916: step: 2056/530, loss: 3.24249276673072e-06
2023-01-23 04:23:31.555517: step: 2060/530, loss: 0.0004739254654850811
2023-01-23 04:23:32.739555: step: 2064/530, loss: 0.02978820726275444
2023-01-23 04:23:33.891777: step: 2068/530, loss: 0.000949859619140625
2023-01-23 04:23:35.073311: step: 2072/530, loss: 0.16993635892868042
2023-01-23 04:23:36.229697: step: 2076/530, loss: 0.005030251108109951
2023-01-23 04:23:37.406219: step: 2080/530, loss: 0.0006069183582440019
2023-01-23 04:23:38.609037: step: 2084/530, loss: 0.0015707015991210938
2023-01-23 04:23:39.791983: step: 2088/530, loss: 1.52587890625e-05
2023-01-23 04:23:40.935433: step: 2092/530, loss: 7.190704491222277e-05
2023-01-23 04:23:42.151114: step: 2096/530, loss: 0.009448433294892311
2023-01-23 04:23:43.348234: step: 2100/530, loss: 0.02007303200662136
2023-01-23 04:23:44.550099: step: 2104/530, loss: 3.957748776883818e-05
2023-01-23 04:23:45.665923: step: 2108/530, loss: 0.00011758804612327367
2023-01-23 04:23:46.824878: step: 2112/530, loss: 0.0006860733265057206
2023-01-23 04:23:47.982068: step: 2116/530, loss: 3.14712519866589e-06
2023-01-23 04:23:49.124011: step: 2120/530, loss: 0.0009111881372518837
==================================================
Loss: 0.015
--------------------
Dev: {'event': {'p': 0.5703048180924287, 'r': 0.7723035952063915, 'f1': 0.6561085972850678}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
Test: {'event': {'p': 0.6487471526195899, 'r': 0.8188614146060954, 'f1': 0.7239450940518556}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
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': 26}
Korean: {'event': {'p': 0.6071428571428571, 'r': 0.5396825396825397, 'f1': 0.5714285714285714}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
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': 26}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.603537981269511, 'r': 0.7723035952063915, 'f1': 0.677570093457944}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Eng Test for Chinese: {'event': {'p': 0.6663560111835974, 'r': 0.8223116733755031, 'f1': 0.7361647361647363}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Sample Chinese: {'event': {'p': 0.611764705882353, 'r': 0.9629629629629629, 'f1': 0.748201438848921}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5733990147783251, 'r': 0.7749667110519307, 'f1': 0.6591166477916196}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Eng Test for Korean: {'event': {'p': 0.6218005295675199, 'r': 0.8102357676825762, 'f1': 0.7036204744069912}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Sample Korean: {'event': {'p': 0.6417910447761194, 'r': 0.6825396825396826, 'f1': 0.6615384615384614}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6284796573875803, 'r': 0.7816245006657789, 'f1': 0.6967359050445103}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Eng Test for Russian: {'event': {'p': 0.6768263183357524, 'r': 0.80448533640023, 'f1': 0.7351550183920126}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Sample Russian: {'event': {'p': 0.4791666666666667, 'r': 0.6388888888888888, 'f1': 0.5476190476190476}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
******************************
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 04:24:31.896690: step: 4/530, loss: 0.000652313232421875
2023-01-23 04:24:33.060948: step: 8/530, loss: 0.04241752624511719
2023-01-23 04:24:34.180687: step: 12/530, loss: 0.00018243789963889867
2023-01-23 04:24:35.365608: step: 16/530, loss: 0.0008916854858398438
2023-01-23 04:24:36.517816: step: 20/530, loss: 0.0002452850458212197
2023-01-23 04:24:37.685494: step: 24/530, loss: 0.0049461605958640575
2023-01-23 04:24:38.848447: step: 28/530, loss: 0.007714462466537952
2023-01-23 04:24:40.003214: step: 32/530, loss: 0.0009332657209597528
2023-01-23 04:24:41.170542: step: 36/530, loss: 0.0002077102690236643
2023-01-23 04:24:42.299173: step: 40/530, loss: 7.82012921263231e-06
2023-01-23 04:24:43.470397: step: 44/530, loss: 0.021197892725467682
2023-01-23 04:24:44.637377: step: 48/530, loss: 0.0004343986511230469
2023-01-23 04:24:45.788110: step: 52/530, loss: 0.027161406353116035
2023-01-23 04:24:46.960750: step: 56/530, loss: 2.09808349609375e-05
2023-01-23 04:24:48.148907: step: 60/530, loss: 0.6663224101066589
2023-01-23 04:24:49.314863: step: 64/530, loss: 0.0018278599018231034
2023-01-23 04:24:50.512684: step: 68/530, loss: 0.00020141601271461695
2023-01-23 04:24:51.648374: step: 72/530, loss: 0.0012106895446777344
2023-01-23 04:24:52.831994: step: 76/530, loss: 0.0032207490876317024
2023-01-23 04:24:54.024651: step: 80/530, loss: 0.0019592284224927425
2023-01-23 04:24:55.208193: step: 84/530, loss: 0.3091375529766083
2023-01-23 04:24:56.374853: step: 88/530, loss: 0.0045620440505445
2023-01-23 04:24:57.530952: step: 92/530, loss: 0.001122856279835105
2023-01-23 04:24:58.713521: step: 96/530, loss: 0.000551801931578666
2023-01-23 04:24:59.880073: step: 100/530, loss: 0.00569992046803236
2023-01-23 04:25:01.012835: step: 104/530, loss: 0.003243064973503351
2023-01-23 04:25:02.148256: step: 108/530, loss: 0.0007908821571618319
2023-01-23 04:25:03.316355: step: 112/530, loss: 0.04158763960003853
2023-01-23 04:25:04.499042: step: 116/530, loss: -2.6416777473059483e-05
2023-01-23 04:25:05.657307: step: 120/530, loss: 0.00010452271089889109
2023-01-23 04:25:06.808708: step: 124/530, loss: 0.00032429693965241313
2023-01-23 04:25:07.969268: step: 128/530, loss: 0.005371475592255592
2023-01-23 04:25:09.107865: step: 132/530, loss: 0.0002779960632324219
2023-01-23 04:25:10.253999: step: 136/530, loss: 0.0015871048672124743
2023-01-23 04:25:11.422314: step: 140/530, loss: 0.000629043614026159
2023-01-23 04:25:12.617892: step: 144/530, loss: 0.00011520386033225805
2023-01-23 04:25:13.787252: step: 148/530, loss: 0.0076586720533668995
2023-01-23 04:25:14.961553: step: 152/530, loss: 0.006493282504379749
2023-01-23 04:25:16.139714: step: 156/530, loss: 0.00032024382380768657
2023-01-23 04:25:17.250046: step: 160/530, loss: 0.00016860962205100805
2023-01-23 04:25:18.416024: step: 164/530, loss: 0.0026494027115404606
2023-01-23 04:25:19.574945: step: 168/530, loss: 3.1280520488508046e-05
2023-01-23 04:25:20.729929: step: 172/530, loss: 0.024794865399599075
2023-01-23 04:25:21.916234: step: 176/530, loss: 0.0024705887772142887
2023-01-23 04:25:23.089659: step: 180/530, loss: 0.0002193450927734375
2023-01-23 04:25:24.207528: step: 184/530, loss: 1.2874603271484375e-05
2023-01-23 04:25:25.392189: step: 188/530, loss: 6.608963303733617e-05
2023-01-23 04:25:26.530797: step: 192/530, loss: 0.00037822723970748484
2023-01-23 04:25:27.686653: step: 196/530, loss: -1.1539459592313506e-05
2023-01-23 04:25:28.955146: step: 200/530, loss: 0.06555958092212677
2023-01-23 04:25:30.126076: step: 204/530, loss: 3.4809112548828125e-05
2023-01-23 04:25:31.301268: step: 208/530, loss: 0.022398566827178
2023-01-23 04:25:32.464028: step: 212/530, loss: 7.07626313669607e-05
2023-01-23 04:25:33.629149: step: 216/530, loss: 0.0002288818359375
2023-01-23 04:25:34.823098: step: 220/530, loss: -1.9073486328125e-06
2023-01-23 04:25:36.036402: step: 224/530, loss: 0.00019006729417014867
2023-01-23 04:25:37.233394: step: 228/530, loss: 0.00888590794056654
2023-01-23 04:25:38.416242: step: 232/530, loss: 3.1280520488508046e-05
2023-01-23 04:25:39.575949: step: 236/530, loss: 0.0013383865589275956
2023-01-23 04:25:40.767288: step: 240/530, loss: 0.0020571709610521793
2023-01-23 04:25:41.930211: step: 244/530, loss: 0.0011640548473224044
2023-01-23 04:25:43.092132: step: 248/530, loss: 0.0001386642543366179
2023-01-23 04:25:44.242727: step: 252/530, loss: 0.0011583329178392887
2023-01-23 04:25:45.430226: step: 256/530, loss: 0.005512142553925514
2023-01-23 04:25:46.619950: step: 260/530, loss: 0.00018596649169921875
2023-01-23 04:25:47.831987: step: 264/530, loss: 0.00275421142578125
2023-01-23 04:25:48.984529: step: 268/530, loss: 0.0002172470121877268
2023-01-23 04:25:50.143342: step: 272/530, loss: 3.814697265625e-06
2023-01-23 04:25:51.308965: step: 276/530, loss: 0.05360012128949165
2023-01-23 04:25:52.500178: step: 280/530, loss: 0.0003742217959370464
2023-01-23 04:25:53.654530: step: 284/530, loss: 0.0005376815679483116
2023-01-23 04:25:54.821180: step: 288/530, loss: 0.0009409904014319181
2023-01-23 04:25:55.991202: step: 292/530, loss: 0.1426229476928711
2023-01-23 04:25:57.140707: step: 296/530, loss: 0.00012464524479582906
2023-01-23 04:25:58.279835: step: 300/530, loss: 0.003947449382394552
2023-01-23 04:25:59.484809: step: 304/530, loss: 0.020606566220521927
2023-01-23 04:26:00.687612: step: 308/530, loss: 0.11624108254909515
2023-01-23 04:26:01.861737: step: 312/530, loss: 0.005692481994628906
2023-01-23 04:26:03.009845: step: 316/530, loss: 0.008369731716811657
2023-01-23 04:26:04.201793: step: 320/530, loss: 0.7331158518791199
2023-01-23 04:26:05.403546: step: 324/530, loss: 3.6716462545882678e-06
2023-01-23 04:26:06.612117: step: 328/530, loss: 0.0017117501702159643
2023-01-23 04:26:07.791898: step: 332/530, loss: 4.863739013671875e-05
2023-01-23 04:26:08.947347: step: 336/530, loss: 0.0005509853363037109
2023-01-23 04:26:10.098934: step: 340/530, loss: 4.024505687993951e-05
2023-01-23 04:26:11.237404: step: 344/530, loss: 0.0009725571144372225
2023-01-23 04:26:12.426619: step: 348/530, loss: 0.0049304962158203125
2023-01-23 04:26:13.647678: step: 352/530, loss: 0.01746549643576145
2023-01-23 04:26:14.835830: step: 356/530, loss: 0.00017108916654251516
2023-01-23 04:26:16.043978: step: 360/530, loss: 0.0007452011341229081
2023-01-23 04:26:17.192883: step: 364/530, loss: 0.1918550431728363
2023-01-23 04:26:18.357290: step: 368/530, loss: 0.0003002166631631553
2023-01-23 04:26:19.540441: step: 372/530, loss: 0.0014599800342693925
2023-01-23 04:26:20.701851: step: 376/530, loss: 0.00024375914654228836
2023-01-23 04:26:21.858166: step: 380/530, loss: 0.0032867430709302425
2023-01-23 04:26:23.015650: step: 384/530, loss: 0.00017766952805686742
2023-01-23 04:26:24.208434: step: 388/530, loss: 0.0005496978992596269
2023-01-23 04:26:25.397098: step: 392/530, loss: 0.0015678406925871968
2023-01-23 04:26:26.603204: step: 396/530, loss: 0.0015939712757244706
2023-01-23 04:26:27.791806: step: 400/530, loss: 0.0054035186767578125
2023-01-23 04:26:28.958353: step: 404/530, loss: 0.0004133224720135331
2023-01-23 04:26:30.129385: step: 408/530, loss: 0.0001386642543366179
2023-01-23 04:26:31.300983: step: 412/530, loss: 0.025389863178133965
2023-01-23 04:26:32.454881: step: 416/530, loss: 6.10351571594947e-06
2023-01-23 04:26:33.619176: step: 420/530, loss: 0.0011966705787926912
2023-01-23 04:26:34.771965: step: 424/530, loss: 0.0023927688598632812
2023-01-23 04:26:35.917252: step: 428/530, loss: 0.001926422119140625
2023-01-23 04:26:37.068125: step: 432/530, loss: 0.00010261536226607859
2023-01-23 04:26:38.222812: step: 436/530, loss: 0.02662210538983345
2023-01-23 04:26:39.381072: step: 440/530, loss: 2.6607513063936494e-05
2023-01-23 04:26:40.544435: step: 444/530, loss: 0.00012855531531386077
2023-01-23 04:26:41.711727: step: 448/530, loss: 0.003286266466602683
2023-01-23 04:26:42.899451: step: 452/530, loss: 0.00022544861712958664
2023-01-23 04:26:44.057098: step: 456/530, loss: 0.00159282679669559
2023-01-23 04:26:45.219760: step: 460/530, loss: 0.00022296904353424907
2023-01-23 04:26:46.392848: step: 464/530, loss: 0.0004608154413290322
2023-01-23 04:26:47.580352: step: 468/530, loss: 0.0009136199951171875
2023-01-23 04:26:48.758555: step: 472/530, loss: 0.00028371813823468983
2023-01-23 04:26:49.915869: step: 476/530, loss: 0.00032901763916015625
2023-01-23 04:26:51.100914: step: 480/530, loss: 0.03972644731402397
2023-01-23 04:26:52.276265: step: 484/530, loss: 0.0004926681285724044
2023-01-23 04:26:53.435104: step: 488/530, loss: 0.01566906087100506
2023-01-23 04:26:54.594734: step: 492/530, loss: 3.814697322468419e-07
2023-01-23 04:26:55.760483: step: 496/530, loss: 0.00011901855759788305
2023-01-23 04:26:56.918248: step: 500/530, loss: 2.5367738999193534e-05
2023-01-23 04:26:58.093391: step: 504/530, loss: 0.026016617193818092
2023-01-23 04:26:59.268873: step: 508/530, loss: 1.0871887752728071e-05
2023-01-23 04:27:00.445221: step: 512/530, loss: 0.004142093472182751
2023-01-23 04:27:01.603715: step: 516/530, loss: 0.0015645980602130294
2023-01-23 04:27:02.804516: step: 520/530, loss: 0.005073929205536842
2023-01-23 04:27:03.987806: step: 524/530, loss: 0.00011363029625499621
2023-01-23 04:27:05.135725: step: 528/530, loss: 1.1396407899155747e-05
2023-01-23 04:27:06.347908: step: 532/530, loss: 0.00016498565673828125
2023-01-23 04:27:07.532436: step: 536/530, loss: 0.0005448341253213584
2023-01-23 04:27:08.707618: step: 540/530, loss: 0.0011166572803631425
2023-01-23 04:27:09.862315: step: 544/530, loss: 0.06685008853673935
2023-01-23 04:27:11.051746: step: 548/530, loss: 0.015690326690673828
2023-01-23 04:27:12.239735: step: 552/530, loss: 0.004598522558808327
2023-01-23 04:27:13.421109: step: 556/530, loss: 0.00011863708641612902
2023-01-23 04:27:14.616270: step: 560/530, loss: 0.0001617431698832661
2023-01-23 04:27:15.830976: step: 564/530, loss: 0.011500931344926357
2023-01-23 04:27:17.001724: step: 568/530, loss: 0.012121009640395641
2023-01-23 04:27:18.208098: step: 572/530, loss: 0.0027837753295898438
2023-01-23 04:27:19.410320: step: 576/530, loss: 0.03747894614934921
2023-01-23 04:27:20.584419: step: 580/530, loss: 0.004900932312011719
2023-01-23 04:27:21.742858: step: 584/530, loss: 0.021369457244873047
2023-01-23 04:27:22.908509: step: 588/530, loss: 0.0007748603820800781
2023-01-23 04:27:24.080733: step: 592/530, loss: 8.306503150379285e-05
2023-01-23 04:27:25.341556: step: 596/530, loss: 0.0034616473130881786
2023-01-23 04:27:26.499766: step: 600/530, loss: -1.716613724056515e-06
2023-01-23 04:27:27.639711: step: 604/530, loss: 0.00012016297114314511
2023-01-23 04:27:28.759662: step: 608/530, loss: 0.0003517151053529233
2023-01-23 04:27:29.934347: step: 612/530, loss: 0.0009232521406374872
2023-01-23 04:27:31.143823: step: 616/530, loss: 0.1094297543168068
2023-01-23 04:27:32.308179: step: 620/530, loss: 0.0047598364762961864
2023-01-23 04:27:33.510725: step: 624/530, loss: 0.00019631386385299265
2023-01-23 04:27:34.703708: step: 628/530, loss: 4.6396256948355585e-05
2023-01-23 04:27:35.910004: step: 632/530, loss: 0.0024840356782078743
2023-01-23 04:27:37.091795: step: 636/530, loss: 5.645752025884576e-05
2023-01-23 04:27:38.262429: step: 640/530, loss: 0.005050182808190584
2023-01-23 04:27:39.419418: step: 644/530, loss: 0.03261242061853409
2023-01-23 04:27:40.585431: step: 648/530, loss: 0.007231330499053001
2023-01-23 04:27:41.733094: step: 652/530, loss: 0.013742828741669655
2023-01-23 04:27:42.932493: step: 656/530, loss: -3.814697720372351e-06
2023-01-23 04:27:44.075890: step: 660/530, loss: 0.0019468307727947831
2023-01-23 04:27:45.256306: step: 664/530, loss: 2.956390289909905e-06
2023-01-23 04:27:46.452472: step: 668/530, loss: 3.662109520519152e-05
2023-01-23 04:27:47.579067: step: 672/530, loss: 0.0012308121658861637
2023-01-23 04:27:48.784174: step: 676/530, loss: 0.014968300238251686
2023-01-23 04:27:49.947318: step: 680/530, loss: 0.022825241088867188
2023-01-23 04:27:51.113988: step: 684/530, loss: 5.9700014389818534e-05
2023-01-23 04:27:52.299541: step: 688/530, loss: 2.746581958490424e-05
2023-01-23 04:27:53.441407: step: 692/530, loss: 0.0004076957702636719
2023-01-23 04:27:54.661640: step: 696/530, loss: 5.493163916980848e-05
2023-01-23 04:27:55.830096: step: 700/530, loss: 0.0104224206879735
2023-01-23 04:27:57.019948: step: 704/530, loss: 0.0008493423811160028
2023-01-23 04:27:58.208782: step: 708/530, loss: 0.00011444091796875
2023-01-23 04:27:59.355631: step: 712/530, loss: 9.508132643532008e-05
2023-01-23 04:28:00.549751: step: 716/530, loss: 0.0005712509155273438
2023-01-23 04:28:01.784429: step: 720/530, loss: 0.00039472582284361124
2023-01-23 04:28:02.934896: step: 724/530, loss: 0.0003915310080628842
2023-01-23 04:28:04.073349: step: 728/530, loss: 0.0009037494892254472
2023-01-23 04:28:05.246335: step: 732/530, loss: 0.0009094238630495965
2023-01-23 04:28:06.362925: step: 736/530, loss: 1.7166138377433526e-06
2023-01-23 04:28:07.561340: step: 740/530, loss: 0.0009223938104696572
2023-01-23 04:28:08.749767: step: 744/530, loss: 1.735687328618951e-05
2023-01-23 04:28:09.906127: step: 748/530, loss: 0.0017135620582848787
2023-01-23 04:28:11.050374: step: 752/530, loss: 0.00047740936861373484
2023-01-23 04:28:12.215577: step: 756/530, loss: 0.0002415657218080014
2023-01-23 04:28:13.366262: step: 760/530, loss: 7.314681715797633e-05
2023-01-23 04:28:14.517742: step: 764/530, loss: 6.0653688706224784e-05
2023-01-23 04:28:15.679661: step: 768/530, loss: 6.771087646484375e-05
2023-01-23 04:28:16.856568: step: 772/530, loss: 7.62939453125e-05
2023-01-23 04:28:18.016666: step: 776/530, loss: 0.0002066135493805632
2023-01-23 04:28:19.218956: step: 780/530, loss: 4.291534423828125e-06
2023-01-23 04:28:20.391904: step: 784/530, loss: 0.0063911438919603825
2023-01-23 04:28:21.541938: step: 788/530, loss: 0.009363556280732155
2023-01-23 04:28:22.688278: step: 792/530, loss: 0.00013513564772438258
2023-01-23 04:28:23.861114: step: 796/530, loss: 0.02267284318804741
2023-01-23 04:28:25.019891: step: 800/530, loss: 0.005314063746482134
2023-01-23 04:28:26.161639: step: 804/530, loss: 3.719329833984375e-05
2023-01-23 04:28:27.314787: step: 808/530, loss: 6.12258882028982e-05
2023-01-23 04:28:28.491686: step: 812/530, loss: 7.820128666935489e-05
2023-01-23 04:28:29.672671: step: 816/530, loss: -1.3065337043371983e-05
2023-01-23 04:28:30.841638: step: 820/530, loss: 0.0003643035888671875
2023-01-23 04:28:31.962073: step: 824/530, loss: 2.040863000729587e-05
2023-01-23 04:28:33.153880: step: 828/530, loss: 0.00294666294939816
2023-01-23 04:28:34.314613: step: 832/530, loss: -4.57763690064894e-06
2023-01-23 04:28:35.487153: step: 836/530, loss: 0.00037555693415924907
2023-01-23 04:28:36.656247: step: 840/530, loss: 0.0009501457680016756
2023-01-23 04:28:37.846998: step: 844/530, loss: 0.02007884904742241
2023-01-23 04:28:38.981691: step: 848/530, loss: 0.1260012686252594
2023-01-23 04:28:40.149626: step: 852/530, loss: 2.8514861696748994e-05
2023-01-23 04:28:41.310343: step: 856/530, loss: 0.054146863520145416
2023-01-23 04:28:42.446792: step: 860/530, loss: 8.96453821042087e-06
2023-01-23 04:28:43.605736: step: 864/530, loss: 1.0937668085098267
2023-01-23 04:28:44.749624: step: 868/530, loss: 9.5367431640625e-06
2023-01-23 04:28:45.952966: step: 872/530, loss: 0.020180320367217064
2023-01-23 04:28:47.122320: step: 876/530, loss: 6.008148193359375e-05
2023-01-23 04:28:48.277302: step: 880/530, loss: 2.0980833141948096e-06
2023-01-23 04:28:49.452773: step: 884/530, loss: 0.00044384002103470266
2023-01-23 04:28:50.640151: step: 888/530, loss: 6.27517729299143e-05
2023-01-23 04:28:51.839194: step: 892/530, loss: 0.2867233157157898
2023-01-23 04:28:53.050754: step: 896/530, loss: 0.04669523239135742
2023-01-23 04:28:54.195006: step: 900/530, loss: 0.004283714573830366
2023-01-23 04:28:55.368033: step: 904/530, loss: 2.86102294921875e-06
2023-01-23 04:28:56.518310: step: 908/530, loss: 2.09808349609375e-05
2023-01-23 04:28:57.699762: step: 912/530, loss: 0.0654270127415657
2023-01-23 04:28:58.868353: step: 916/530, loss: 0.0008623883477412164
2023-01-23 04:28:59.990839: step: 920/530, loss: 0.0012042999733239412
2023-01-23 04:29:01.154432: step: 924/530, loss: 2.536773718020413e-05
2023-01-23 04:29:02.360799: step: 928/530, loss: 0.009328269399702549
2023-01-23 04:29:03.504180: step: 932/530, loss: 0.00010900497727561742
2023-01-23 04:29:04.653947: step: 936/530, loss: 0.018418503925204277
2023-01-23 04:29:05.815325: step: 940/530, loss: 0.0004088401619810611
2023-01-23 04:29:06.966292: step: 944/530, loss: 2.19345088225964e-06
2023-01-23 04:29:08.128980: step: 948/530, loss: 0.05818052217364311
2023-01-23 04:29:09.293979: step: 952/530, loss: 0.0006552219274453819
2023-01-23 04:29:10.514557: step: 956/530, loss: 0.022797392681241035
2023-01-23 04:29:11.698838: step: 960/530, loss: 6.809234764659777e-05
2023-01-23 04:29:12.838897: step: 964/530, loss: 0.0003148078976664692
2023-01-23 04:29:14.051921: step: 968/530, loss: 0.005818271543830633
2023-01-23 04:29:15.278463: step: 972/530, loss: 0.0008106231689453125
2023-01-23 04:29:16.469708: step: 976/530, loss: 0.02296772040426731
2023-01-23 04:29:17.672715: step: 980/530, loss: 0.0008661270258016884
2023-01-23 04:29:18.832864: step: 984/530, loss: 0.014449119567871094
2023-01-23 04:29:20.018604: step: 988/530, loss: 0.0003707885625772178
2023-01-23 04:29:21.246456: step: 992/530, loss: 0.06511564552783966
2023-01-23 04:29:22.402669: step: 996/530, loss: 0.0417327880859375
2023-01-23 04:29:23.555816: step: 1000/530, loss: 2.574920654296875e-05
2023-01-23 04:29:24.734853: step: 1004/530, loss: 0.00013999939255882055
2023-01-23 04:29:25.920875: step: 1008/530, loss: 0.0027029039338231087
2023-01-23 04:29:27.079197: step: 1012/530, loss: 1.564025842526462e-05
2023-01-23 04:29:28.199321: step: 1016/530, loss: 0.03310136869549751
2023-01-23 04:29:29.329991: step: 1020/530, loss: 0.0008900642278604209
2023-01-23 04:29:30.509600: step: 1024/530, loss: 0.00037167072878219187
2023-01-23 04:29:31.713003: step: 1028/530, loss: 0.005944252014160156
2023-01-23 04:29:32.911172: step: 1032/530, loss: 0.0632532611489296
2023-01-23 04:29:34.081658: step: 1036/530, loss: 2.1648407710017636e-05
2023-01-23 04:29:35.255274: step: 1040/530, loss: 0.012198258191347122
2023-01-23 04:29:36.433992: step: 1044/530, loss: 3.9863589336164296e-05
2023-01-23 04:29:37.574198: step: 1048/530, loss: 2.4032591682043858e-05
2023-01-23 04:29:38.738281: step: 1052/530, loss: 1.9168854123563506e-05
2023-01-23 04:29:39.907407: step: 1056/530, loss: 0.001992607256397605
2023-01-23 04:29:41.074019: step: 1060/530, loss: 0.04386749118566513
2023-01-23 04:29:42.329359: step: 1064/530, loss: 0.0008985519525595009
2023-01-23 04:29:43.522501: step: 1068/530, loss: 0.0007492065196856856
2023-01-23 04:29:44.693554: step: 1072/530, loss: 2.7561189199332148e-05
2023-01-23 04:29:45.890310: step: 1076/530, loss: 9.994507126975805e-05
2023-01-23 04:29:47.047378: step: 1080/530, loss: 0.0005281448247842491
2023-01-23 04:29:48.251234: step: 1084/530, loss: 0.009174728766083717
2023-01-23 04:29:49.444130: step: 1088/530, loss: 0.0003482818719930947
2023-01-23 04:29:50.601563: step: 1092/530, loss: 0.024530887603759766
2023-01-23 04:29:51.769653: step: 1096/530, loss: 0.0004904747474938631
2023-01-23 04:29:52.982294: step: 1100/530, loss: 0.021392822265625
2023-01-23 04:29:54.149552: step: 1104/530, loss: 0.12941399216651917
2023-01-23 04:29:55.363954: step: 1108/530, loss: 0.0005178452120162547
2023-01-23 04:29:56.536197: step: 1112/530, loss: 0.01640205644071102
2023-01-23 04:29:57.757902: step: 1116/530, loss: 0.0015214920276775956
2023-01-23 04:29:58.969015: step: 1120/530, loss: 0.03469962999224663
2023-01-23 04:30:00.151076: step: 1124/530, loss: 9.465218317927793e-05
2023-01-23 04:30:01.334668: step: 1128/530, loss: 0.02155141718685627
2023-01-23 04:30:02.542904: step: 1132/530, loss: 0.0699758529663086
2023-01-23 04:30:03.729274: step: 1136/530, loss: 0.0002003193076234311
2023-01-23 04:30:04.921208: step: 1140/530, loss: 0.0001405716029694304
2023-01-23 04:30:06.084488: step: 1144/530, loss: 0.00013895034499000758
2023-01-23 04:30:07.239063: step: 1148/530, loss: 0.0009246826521120965
2023-01-23 04:30:08.412951: step: 1152/530, loss: 0.0033431528136134148
2023-01-23 04:30:09.584043: step: 1156/530, loss: 0.005737495142966509
2023-01-23 04:30:10.723526: step: 1160/530, loss: 0.0003601074276957661
2023-01-23 04:30:11.910750: step: 1164/530, loss: 8.568763587391004e-05
2023-01-23 04:30:13.090819: step: 1168/530, loss: 0.04725942760705948
2023-01-23 04:30:14.248208: step: 1172/530, loss: 0.041841890662908554
2023-01-23 04:30:15.459811: step: 1176/530, loss: 1.8024444216280244e-05
2023-01-23 04:30:16.638431: step: 1180/530, loss: 0.0011386871337890625
2023-01-23 04:30:17.791407: step: 1184/530, loss: 9.737015352584422e-05
2023-01-23 04:30:18.995038: step: 1188/530, loss: 0.024085618555545807
2023-01-23 04:30:20.169355: step: 1192/530, loss: 0.021039199084043503
2023-01-23 04:30:21.321610: step: 1196/530, loss: 0.00024835168733261526
2023-01-23 04:30:22.496500: step: 1200/530, loss: 0.0002582550223451108
2023-01-23 04:30:23.709518: step: 1204/530, loss: 0.0008246421930380166
2023-01-23 04:30:24.856711: step: 1208/530, loss: 0.0001012802094919607
2023-01-23 04:30:26.024414: step: 1212/530, loss: 5.3882598876953125e-05
2023-01-23 04:30:27.248148: step: 1216/530, loss: 0.0017414093017578125
2023-01-23 04:30:28.438069: step: 1220/530, loss: 0.04070444032549858
2023-01-23 04:30:29.601263: step: 1224/530, loss: 0.00042743684025481343
2023-01-23 04:30:30.770530: step: 1228/530, loss: 8.525848534191027e-05
2023-01-23 04:30:31.903420: step: 1232/530, loss: 0.011065292172133923
2023-01-23 04:30:33.111416: step: 1236/530, loss: 0.0008114814991131425
2023-01-23 04:30:34.266793: step: 1240/530, loss: 0.0041748047806322575
2023-01-23 04:30:35.445861: step: 1244/530, loss: 0.4805641174316406
2023-01-23 04:30:36.609934: step: 1248/530, loss: 0.0022430419921875
2023-01-23 04:30:37.771502: step: 1252/530, loss: 0.008849906735122204
2023-01-23 04:30:38.885401: step: 1256/530, loss: 6.914139521541074e-05
2023-01-23 04:30:40.033147: step: 1260/530, loss: 7.576942880405113e-05
2023-01-23 04:30:41.178811: step: 1264/530, loss: 0.0035113333724439144
2023-01-23 04:30:42.428389: step: 1268/530, loss: 0.003048515412956476
2023-01-23 04:30:43.604926: step: 1272/530, loss: 0.04379329830408096
2023-01-23 04:30:44.746145: step: 1276/530, loss: 0.0038431170396506786
2023-01-23 04:30:45.879228: step: 1280/530, loss: 0.00012903212336823344
2023-01-23 04:30:47.055185: step: 1284/530, loss: 0.023546408861875534
2023-01-23 04:30:48.256444: step: 1288/530, loss: 4.1580202378099784e-05
2023-01-23 04:30:49.435048: step: 1292/530, loss: 0.0004962921375408769
2023-01-23 04:30:50.579132: step: 1296/530, loss: 0.0007173537742346525
2023-01-23 04:30:51.757753: step: 1300/530, loss: 0.06420421600341797
2023-01-23 04:30:52.926224: step: 1304/530, loss: 0.0006399154663085938
2023-01-23 04:30:54.046803: step: 1308/530, loss: 0.0009020805009640753
2023-01-23 04:30:55.222861: step: 1312/530, loss: 0.0006678581121377647
2023-01-23 04:30:56.360337: step: 1316/530, loss: 8.468628220725805e-05
2023-01-23 04:30:57.537617: step: 1320/530, loss: -4.425048973644152e-05
2023-01-23 04:30:58.748860: step: 1324/530, loss: 0.013179397210478783
2023-01-23 04:30:59.896827: step: 1328/530, loss: 0.16914503276348114
2023-01-23 04:31:01.039302: step: 1332/530, loss: 0.00017867088899947703
2023-01-23 04:31:02.216660: step: 1336/530, loss: 1.773834264895413e-05
2023-01-23 04:31:03.392740: step: 1340/530, loss: 0.004110908601433039
2023-01-23 04:31:04.577909: step: 1344/530, loss: 0.009069251827895641
2023-01-23 04:31:05.776106: step: 1348/530, loss: 5.53131121705519e-06
2023-01-23 04:31:06.978891: step: 1352/530, loss: 0.0009420394781045616
2023-01-23 04:31:08.152147: step: 1356/530, loss: -2.6702878130890895e-06
2023-01-23 04:31:09.332055: step: 1360/530, loss: 0.0013238906394690275
2023-01-23 04:31:10.539262: step: 1364/530, loss: 0.0012136459117755294
2023-01-23 04:31:11.690069: step: 1368/530, loss: 4.110336158191785e-05
2023-01-23 04:31:12.891670: step: 1372/530, loss: 2.4795533590804553e-06
2023-01-23 04:31:14.043808: step: 1376/530, loss: 0.10059070587158203
2023-01-23 04:31:15.184293: step: 1380/530, loss: 0.00042552949162200093
2023-01-23 04:31:16.326266: step: 1384/530, loss: 0.006117343902587891
2023-01-23 04:31:17.489983: step: 1388/530, loss: 0.05645294114947319
2023-01-23 04:31:18.647482: step: 1392/530, loss: 0.00015325547428801656
2023-01-23 04:31:19.838519: step: 1396/530, loss: 1.049041748046875e-05
2023-01-23 04:31:20.994314: step: 1400/530, loss: 1.430511474609375e-06
2023-01-23 04:31:22.166004: step: 1404/530, loss: 0.0007281303405761719
2023-01-23 04:31:23.324191: step: 1408/530, loss: 1.1444092706369702e-05
2023-01-23 04:31:24.532180: step: 1412/530, loss: 0.0068569183349609375
2023-01-23 04:31:25.723606: step: 1416/530, loss: 0.023429013788700104
2023-01-23 04:31:26.913345: step: 1420/530, loss: 0.020067404955625534
2023-01-23 04:31:28.088739: step: 1424/530, loss: 0.00022239686222746968
2023-01-23 04:31:29.271602: step: 1428/530, loss: 0.01184997521340847
2023-01-23 04:31:30.476425: step: 1432/530, loss: 0.0011535644298419356
2023-01-23 04:31:31.647256: step: 1436/530, loss: 0.031447697430849075
2023-01-23 04:31:32.832016: step: 1440/530, loss: 1.945495569088962e-05
2023-01-23 04:31:34.004689: step: 1444/530, loss: 0.00011568070476641878
2023-01-23 04:31:35.186595: step: 1448/530, loss: 9.34600848268019e-06
2023-01-23 04:31:36.393735: step: 1452/530, loss: 8.41140717966482e-05
2023-01-23 04:31:37.556896: step: 1456/530, loss: 0.0009826660389080644
2023-01-23 04:31:38.737905: step: 1460/530, loss: 0.09364718943834305
2023-01-23 04:31:39.878481: step: 1464/530, loss: 0.3904864192008972
2023-01-23 04:31:41.022887: step: 1468/530, loss: 0.021575165912508965
2023-01-23 04:31:42.200141: step: 1472/530, loss: 0.0010513304732739925
2023-01-23 04:31:43.355918: step: 1476/530, loss: 0.020025253295898438
2023-01-23 04:31:44.508526: step: 1480/530, loss: 0.0161909107118845
2023-01-23 04:31:45.690982: step: 1484/530, loss: 1.4972686585679185e-05
2023-01-23 04:31:46.881112: step: 1488/530, loss: 0.04743757098913193
2023-01-23 04:31:48.059376: step: 1492/530, loss: 0.0004596233193296939
2023-01-23 04:31:49.220966: step: 1496/530, loss: 9.5367431640625e-06
2023-01-23 04:31:50.397748: step: 1500/530, loss: 5.2261355449445546e-05
2023-01-23 04:31:51.549394: step: 1504/530, loss: 0.04272441938519478
2023-01-23 04:31:52.726239: step: 1508/530, loss: 0.0622737891972065
2023-01-23 04:31:53.938100: step: 1512/530, loss: 0.04793167486786842
2023-01-23 04:31:55.107390: step: 1516/530, loss: 0.001499176025390625
2023-01-23 04:31:56.278598: step: 1520/530, loss: 0.001739072846248746
2023-01-23 04:31:57.432921: step: 1524/530, loss: 0.03913154453039169
2023-01-23 04:31:58.633978: step: 1528/530, loss: 0.00031528473482467234
2023-01-23 04:31:59.794315: step: 1532/530, loss: 0.008660029619932175
2023-01-23 04:32:00.969451: step: 1536/530, loss: 0.0001298904389841482
2023-01-23 04:32:02.155464: step: 1540/530, loss: 0.7714803814888
2023-01-23 04:32:03.283653: step: 1544/530, loss: 2.861023403966101e-06
2023-01-23 04:32:04.463161: step: 1548/530, loss: 0.017801284790039062
2023-01-23 04:32:05.646113: step: 1552/530, loss: 0.5545670390129089
2023-01-23 04:32:06.784886: step: 1556/530, loss: -5.340575626178179e-06
2023-01-23 04:32:07.968239: step: 1560/530, loss: 0.012270832434296608
2023-01-23 04:32:09.151608: step: 1564/530, loss: 2.3508071535616182e-05
2023-01-23 04:32:10.292824: step: 1568/530, loss: 8.678435733600054e-06
2023-01-23 04:32:11.453431: step: 1572/530, loss: 4.119873119634576e-05
2023-01-23 04:32:12.617358: step: 1576/530, loss: 0.514556884765625
2023-01-23 04:32:13.778263: step: 1580/530, loss: 0.0011501312255859375
2023-01-23 04:32:14.988279: step: 1584/530, loss: 0.05809364467859268
2023-01-23 04:32:16.119565: step: 1588/530, loss: 0.06097240746021271
2023-01-23 04:32:17.318366: step: 1592/530, loss: 0.00040950774564407766
2023-01-23 04:32:18.484251: step: 1596/530, loss: 0.0023648261558264494
2023-01-23 04:32:19.698228: step: 1600/530, loss: 0.0027667998801916838
2023-01-23 04:32:20.874619: step: 1604/530, loss: 0.0003456115664448589
2023-01-23 04:32:22.054239: step: 1608/530, loss: 0.003501415252685547
2023-01-23 04:32:23.222541: step: 1612/530, loss: 0.002284145448356867
2023-01-23 04:32:24.406365: step: 1616/530, loss: 0.02496662177145481
2023-01-23 04:32:25.584573: step: 1620/530, loss: 7.43865984986769e-06
2023-01-23 04:32:26.756228: step: 1624/530, loss: 0.0054302215576171875
2023-01-23 04:32:27.902108: step: 1628/530, loss: 0.00013294219388626516
2023-01-23 04:32:29.064747: step: 1632/530, loss: 0.00744781456887722
2023-01-23 04:32:30.240439: step: 1636/530, loss: 5.34057608092553e-06
2023-01-23 04:32:31.421062: step: 1640/530, loss: 1.583099401614163e-05
2023-01-23 04:32:32.589832: step: 1644/530, loss: 9.212493750965223e-05
2023-01-23 04:32:33.741516: step: 1648/530, loss: 0.003195476485416293
2023-01-23 04:32:34.922072: step: 1652/530, loss: 0.007518577389419079
2023-01-23 04:32:36.051269: step: 1656/530, loss: 0.02119617536664009
2023-01-23 04:32:37.202799: step: 1660/530, loss: 8.869171870173886e-05
2023-01-23 04:32:38.369767: step: 1664/530, loss: 3.528595334501006e-05
2023-01-23 04:32:39.583321: step: 1668/530, loss: 8.58306884765625e-06
2023-01-23 04:32:40.736862: step: 1672/530, loss: 0.0006631851429119706
2023-01-23 04:32:41.875494: step: 1676/530, loss: 8.7738037109375e-05
2023-01-23 04:32:43.025095: step: 1680/530, loss: 0.05201740562915802
2023-01-23 04:32:44.240471: step: 1684/530, loss: 0.3211304545402527
2023-01-23 04:32:45.407323: step: 1688/530, loss: 2.746581958490424e-05
2023-01-23 04:32:46.620689: step: 1692/530, loss: 0.6078338623046875
2023-01-23 04:32:47.737634: step: 1696/530, loss: 3.719329924933845e-06
2023-01-23 04:32:48.900605: step: 1700/530, loss: 0.008941460400819778
2023-01-23 04:32:50.113968: step: 1704/530, loss: 0.011018562130630016
2023-01-23 04:32:51.265942: step: 1708/530, loss: 4.529952639131807e-05
2023-01-23 04:32:52.432035: step: 1712/530, loss: 0.034650806337594986
2023-01-23 04:32:53.608419: step: 1716/530, loss: 3.337860107421875e-06
2023-01-23 04:32:54.787803: step: 1720/530, loss: 0.0003250122244935483
2023-01-23 04:32:56.001605: step: 1724/530, loss: 0.004837989807128906
2023-01-23 04:32:57.200466: step: 1728/530, loss: 0.004127121064811945
2023-01-23 04:32:58.337386: step: 1732/530, loss: 0.00225830078125
2023-01-23 04:32:59.533812: step: 1736/530, loss: 0.01828174665570259
2023-01-23 04:33:00.707234: step: 1740/530, loss: 1.71661376953125e-05
2023-01-23 04:33:01.869330: step: 1744/530, loss: 0.004638671875
2023-01-23 04:33:03.048256: step: 1748/530, loss: 0.4977077543735504
2023-01-23 04:33:04.250029: step: 1752/530, loss: 0.1226491928100586
2023-01-23 04:33:05.442268: step: 1756/530, loss: 6.84738188283518e-05
2023-01-23 04:33:06.616719: step: 1760/530, loss: 0.007302188780158758
2023-01-23 04:33:07.812729: step: 1764/530, loss: 0.004945182707160711
2023-01-23 04:33:08.977221: step: 1768/530, loss: 0.0008996963733807206
2023-01-23 04:33:10.135654: step: 1772/530, loss: 0.00038013458834029734
2023-01-23 04:33:11.295069: step: 1776/530, loss: 0.420545756816864
2023-01-23 04:33:12.466537: step: 1780/530, loss: 0.0004016876046080142
2023-01-23 04:33:13.626083: step: 1784/530, loss: 0.08477678894996643
2023-01-23 04:33:14.827884: step: 1788/530, loss: 0.03332257270812988
2023-01-23 04:33:15.994232: step: 1792/530, loss: 0.03261518478393555
2023-01-23 04:33:17.141646: step: 1796/530, loss: 3.3092499506892636e-05
2023-01-23 04:33:18.281282: step: 1800/530, loss: 7.43865984986769e-06
2023-01-23 04:33:19.478082: step: 1804/530, loss: 0.01912212371826172
2023-01-23 04:33:20.749875: step: 1808/530, loss: 0.03701825439929962
2023-01-23 04:33:21.915762: step: 1812/530, loss: 0.028536034747958183
2023-01-23 04:33:23.062568: step: 1816/530, loss: 0.010234450921416283
2023-01-23 04:33:24.245810: step: 1820/530, loss: 0.0033693313598632812
2023-01-23 04:33:25.432988: step: 1824/530, loss: 0.017996788024902344
2023-01-23 04:33:26.640785: step: 1828/530, loss: 6.256103370105848e-05
2023-01-23 04:33:27.793427: step: 1832/530, loss: 0.00023679735022597015
2023-01-23 04:33:28.977125: step: 1836/530, loss: 0.0003586769162211567
2023-01-23 04:33:30.165782: step: 1840/530, loss: 0.0008254767162725329
2023-01-23 04:33:31.320940: step: 1844/530, loss: 0.027808047831058502
2023-01-23 04:33:32.510920: step: 1848/530, loss: 0.0001522064267192036
2023-01-23 04:33:33.677823: step: 1852/530, loss: 0.009389973245561123
2023-01-23 04:33:34.890572: step: 1856/530, loss: 0.00022439956956077367
2023-01-23 04:33:36.051375: step: 1860/530, loss: 0.007344245910644531
2023-01-23 04:33:37.226829: step: 1864/530, loss: 0.0031612396705895662
2023-01-23 04:33:38.411465: step: 1868/530, loss: 0.011002159677445889
2023-01-23 04:33:39.591700: step: 1872/530, loss: 0.20148134231567383
2023-01-23 04:33:40.769475: step: 1876/530, loss: 0.008301354013383389
2023-01-23 04:33:41.964833: step: 1880/530, loss: 0.00038938524085097015
2023-01-23 04:33:43.106159: step: 1884/530, loss: 0.00013890267291571945
2023-01-23 04:33:44.270246: step: 1888/530, loss: 0.005334234796464443
2023-01-23 04:33:45.432098: step: 1892/530, loss: 0.006791305728256702
2023-01-23 04:33:46.580466: step: 1896/530, loss: 0.00507245073094964
2023-01-23 04:33:47.762015: step: 1900/530, loss: 0.001680231187492609
2023-01-23 04:33:48.935942: step: 1904/530, loss: 5.9556961787166074e-05
2023-01-23 04:33:50.102980: step: 1908/530, loss: 0.019367694854736328
2023-01-23 04:33:51.267926: step: 1912/530, loss: 0.0010700225830078125
2023-01-23 04:33:52.444615: step: 1916/530, loss: 0.00015869141498114914
2023-01-23 04:33:53.582087: step: 1920/530, loss: -6.008148375258315e-06
2023-01-23 04:33:54.755744: step: 1924/530, loss: 0.06260509788990021
2023-01-23 04:33:55.931420: step: 1928/530, loss: 0.007757091429084539
2023-01-23 04:33:57.116853: step: 1932/530, loss: 0.004966640379279852
2023-01-23 04:33:58.308535: step: 1936/530, loss: 0.00013999939255882055
2023-01-23 04:33:59.507142: step: 1940/530, loss: 8.726119631319307e-06
2023-01-23 04:34:00.693801: step: 1944/530, loss: 0.03010082244873047
2023-01-23 04:34:01.865016: step: 1948/530, loss: 6.599425978492945e-05
2023-01-23 04:34:03.056535: step: 1952/530, loss: 0.04095101356506348
2023-01-23 04:34:04.219824: step: 1956/530, loss: 0.0036619186867028475
2023-01-23 04:34:05.389937: step: 1960/530, loss: 3.623962811616366e-06
2023-01-23 04:34:06.543481: step: 1964/530, loss: 9.689330909168348e-05
2023-01-23 04:34:07.695453: step: 1968/530, loss: 0.004737568087875843
2023-01-23 04:34:08.858160: step: 1972/530, loss: 0.0053186421282589436
2023-01-23 04:34:10.076523: step: 1976/530, loss: 0.0003681182861328125
2023-01-23 04:34:11.260236: step: 1980/530, loss: 0.008392333984375
2023-01-23 04:34:12.428537: step: 1984/530, loss: 0.0004643261490855366
2023-01-23 04:34:13.595907: step: 1988/530, loss: 0.0018993377452716231
2023-01-23 04:34:14.742743: step: 1992/530, loss: 0.00027289389981888235
2023-01-23 04:34:15.892260: step: 1996/530, loss: 0.00516433734446764
2023-01-23 04:34:17.111989: step: 2000/530, loss: 7.43865984986769e-06
2023-01-23 04:34:18.304840: step: 2004/530, loss: 1.71661376953125e-05
2023-01-23 04:34:19.489494: step: 2008/530, loss: 8.668899681651965e-05
2023-01-23 04:34:20.711286: step: 2012/530, loss: 0.00010356902930652723
2023-01-23 04:34:21.890950: step: 2016/530, loss: 0.004231262486428022
2023-01-23 04:34:23.038833: step: 2020/530, loss: 0.010181237012147903
2023-01-23 04:34:24.192368: step: 2024/530, loss: 6.532669067382812e-05
2023-01-23 04:34:25.392435: step: 2028/530, loss: 0.009036826901137829
2023-01-23 04:34:26.585409: step: 2032/530, loss: 0.028632165864109993
2023-01-23 04:34:27.736443: step: 2036/530, loss: 0.00042476653470657766
2023-01-23 04:34:28.912900: step: 2040/530, loss: 0.030996322631835938
2023-01-23 04:34:30.059841: step: 2044/530, loss: 0.00026035308837890625
2023-01-23 04:34:31.258740: step: 2048/530, loss: 0.00032420159550383687
2023-01-23 04:34:32.435875: step: 2052/530, loss: 0.09732723236083984
2023-01-23 04:34:33.578599: step: 2056/530, loss: 3.948211815441027e-05
2023-01-23 04:34:34.777927: step: 2060/530, loss: 0.0001239776611328125
2023-01-23 04:34:35.952775: step: 2064/530, loss: 0.013938712887465954
2023-01-23 04:34:37.134254: step: 2068/530, loss: 0.0001979827939067036
2023-01-23 04:34:38.319985: step: 2072/530, loss: 7.629394644936838e-07
2023-01-23 04:34:39.462668: step: 2076/530, loss: 0.01680145226418972
2023-01-23 04:34:40.617997: step: 2080/530, loss: 0.011154365725815296
2023-01-23 04:34:41.808871: step: 2084/530, loss: 0.013043785467743874
2023-01-23 04:34:42.959056: step: 2088/530, loss: 0.0038467408157885075
2023-01-23 04:34:44.117748: step: 2092/530, loss: 0.0002492904895916581
2023-01-23 04:34:45.269627: step: 2096/530, loss: 0.3864928185939789
2023-01-23 04:34:46.528874: step: 2100/530, loss: 0.00013008118548896164
2023-01-23 04:34:47.713516: step: 2104/530, loss: 5.717277599615045e-05
2023-01-23 04:34:48.866463: step: 2108/530, loss: 0.0015916824340820312
2023-01-23 04:34:50.039387: step: 2112/530, loss: 0.005071067716926336
2023-01-23 04:34:51.196904: step: 2116/530, loss: 0.022485733032226562
2023-01-23 04:34:52.354114: step: 2120/530, loss: 0.0004511833540163934
==================================================
Loss: 0.025
--------------------
Dev: {'event': {'p': 0.5920651068158698, 'r': 0.7749667110519307, 'f1': 0.671280276816609}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
Test: {'event': {'p': 0.6632510479739171, 'r': 0.8188614146060954, 'f1': 0.7328872876994339}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
Chinese: {'event': {'p': 0.5384615384615384, 'r': 0.9074074074074074, 'f1': 0.6758620689655174}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
Korean: {'event': {'p': 0.5636363636363636, 'r': 0.49206349206349204, 'f1': 0.5254237288135594}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
Russian: {'event': {'p': 0.44680851063829785, 'r': 0.5833333333333334, 'f1': 0.5060240963855422}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.603537981269511, 'r': 0.7723035952063915, 'f1': 0.677570093457944}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Eng Test for Chinese: {'event': {'p': 0.6663560111835974, 'r': 0.8223116733755031, 'f1': 0.7361647361647363}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Sample Chinese: {'event': {'p': 0.611764705882353, 'r': 0.9629629629629629, 'f1': 0.748201438848921}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5733990147783251, 'r': 0.7749667110519307, 'f1': 0.6591166477916196}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Eng Test for Korean: {'event': {'p': 0.6218005295675199, 'r': 0.8102357676825762, 'f1': 0.7036204744069912}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Sample Korean: {'event': {'p': 0.6417910447761194, 'r': 0.6825396825396826, 'f1': 0.6615384615384614}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6284796573875803, 'r': 0.7816245006657789, 'f1': 0.6967359050445103}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Eng Test for Russian: {'event': {'p': 0.6768263183357524, 'r': 0.80448533640023, 'f1': 0.7351550183920126}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Sample Russian: {'event': {'p': 0.4791666666666667, 'r': 0.6388888888888888, 'f1': 0.5476190476190476}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
******************************
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 04:35:35.249367: step: 4/530, loss: -1.411438006471144e-05
2023-01-23 04:35:36.439296: step: 8/530, loss: 0.005829238798469305
2023-01-23 04:35:37.632339: step: 12/530, loss: 0.0022008896339684725
2023-01-23 04:35:38.824186: step: 16/530, loss: 0.00023756027803756297
2023-01-23 04:35:40.011537: step: 20/530, loss: 6.523132469737902e-05
2023-01-23 04:35:41.184118: step: 24/530, loss: 0.0021169662941247225
2023-01-23 04:35:42.358829: step: 28/530, loss: 3.9672853745287284e-05
2023-01-23 04:35:43.506436: step: 32/530, loss: 0.0016769410576671362
2023-01-23 04:35:44.705599: step: 36/530, loss: 0.0018096923595294356
2023-01-23 04:35:45.856039: step: 40/530, loss: -1.5258788153005298e-06
2023-01-23 04:35:47.025093: step: 44/530, loss: 0.03781404346227646
2023-01-23 04:35:48.204825: step: 48/530, loss: 4.3296811782056466e-05
2023-01-23 04:35:49.385443: step: 52/530, loss: 0.011431884951889515
2023-01-23 04:35:50.554226: step: 56/530, loss: 5.283355858409777e-05
2023-01-23 04:35:51.748508: step: 60/530, loss: 8.20159948489163e-06
2023-01-23 04:35:52.907430: step: 64/530, loss: 0.05240192636847496
2023-01-23 04:35:54.083631: step: 68/530, loss: 0.015002822503447533
2023-01-23 04:35:55.200154: step: 72/530, loss: 0.003928661346435547
2023-01-23 04:35:56.376875: step: 76/530, loss: 4.4345855712890625e-05
2023-01-23 04:35:57.533628: step: 80/530, loss: 2.5272369384765625e-05
2023-01-23 04:35:58.694987: step: 84/530, loss: 5.9890749980695546e-05
2023-01-23 04:35:59.846716: step: 88/530, loss: 0.008724022656679153
2023-01-23 04:36:01.024665: step: 92/530, loss: 0.030758477747440338
2023-01-23 04:36:02.179452: step: 96/530, loss: 0.522162675857544
2023-01-23 04:36:03.370187: step: 100/530, loss: 0.0011777877807617188
2023-01-23 04:36:04.538039: step: 104/530, loss: 0.013872909359633923
2023-01-23 04:36:05.747806: step: 108/530, loss: 0.00011672973050735891
2023-01-23 04:36:06.918795: step: 112/530, loss: 0.01543350238353014
2023-01-23 04:36:08.077273: step: 116/530, loss: 0.004726219456642866
2023-01-23 04:36:09.224956: step: 120/530, loss: 0.0005173683166503906
2023-01-23 04:36:10.424120: step: 124/530, loss: 0.00018844603619072586
2023-01-23 04:36:11.577955: step: 128/530, loss: 0.012730026617646217
2023-01-23 04:36:12.757150: step: 132/530, loss: 0.0008310317643918097
2023-01-23 04:36:13.943879: step: 136/530, loss: 0.0010021210182458162
2023-01-23 04:36:15.114915: step: 140/530, loss: 0.0005702972412109375
2023-01-23 04:36:16.260761: step: 144/530, loss: 2.4795534045551904e-05
2023-01-23 04:36:17.418716: step: 148/530, loss: 0.0012784958817064762
2023-01-23 04:36:18.551252: step: 152/530, loss: 0.006991386413574219
2023-01-23 04:36:19.708158: step: 156/530, loss: 0.0006891250959597528
2023-01-23 04:36:20.898119: step: 160/530, loss: 3.4809113458322827e-06
2023-01-23 04:36:22.095621: step: 164/530, loss: 5.34057608092553e-06
2023-01-23 04:36:23.266890: step: 168/530, loss: 0.0011166095500811934
2023-01-23 04:36:24.424550: step: 172/530, loss: 0.009955216199159622
2023-01-23 04:36:25.651622: step: 176/530, loss: 0.003135299775749445
2023-01-23 04:36:26.869897: step: 180/530, loss: -0.0
2023-01-23 04:36:28.067284: step: 184/530, loss: 0.11247196793556213
2023-01-23 04:36:29.267382: step: 188/530, loss: 0.0133819580078125
2023-01-23 04:36:30.452775: step: 192/530, loss: 0.03193207085132599
2023-01-23 04:36:31.645175: step: 196/530, loss: -2.098083541568485e-06
2023-01-23 04:36:32.830153: step: 200/530, loss: 2.47955313170678e-06
2023-01-23 04:36:33.946110: step: 204/530, loss: 0.021140672266483307
2023-01-23 04:36:35.103749: step: 208/530, loss: 3.14712519866589e-06
2023-01-23 04:36:36.281440: step: 212/530, loss: 0.005852794740349054
2023-01-23 04:36:37.479342: step: 216/530, loss: 0.00011329651169944555
2023-01-23 04:36:38.671160: step: 220/530, loss: 0.012430763803422451
2023-01-23 04:36:39.901153: step: 224/530, loss: 0.0016486168606206775
2023-01-23 04:36:41.096697: step: 228/530, loss: 0.007553291507065296
2023-01-23 04:36:42.309988: step: 232/530, loss: 7.009506225585938e-05
2023-01-23 04:36:43.521845: step: 236/530, loss: 0.0026180266868323088
2023-01-23 04:36:44.689927: step: 240/530, loss: 0.000709152256604284
2023-01-23 04:36:45.858602: step: 244/530, loss: 0.0011796951293945312
2023-01-23 04:36:47.034530: step: 248/530, loss: 0.0001911163271870464
2023-01-23 04:36:48.207411: step: 252/530, loss: 6.351470801746473e-05
2023-01-23 04:36:49.420155: step: 256/530, loss: 0.00014419556828215718
2023-01-23 04:36:50.613842: step: 260/530, loss: 0.02088947221636772
2023-01-23 04:36:51.776512: step: 264/530, loss: 0.00022888182138558477
2023-01-23 04:36:52.926172: step: 268/530, loss: 0.10502319037914276
2023-01-23 04:36:54.067256: step: 272/530, loss: 5.7220458984375e-06
2023-01-23 04:36:55.203665: step: 276/530, loss: 0.002025604248046875
2023-01-23 04:36:56.405214: step: 280/530, loss: 0.0003971099795307964
2023-01-23 04:36:57.594956: step: 284/530, loss: 0.0021179199684411287
2023-01-23 04:36:58.721912: step: 288/530, loss: 3.929138256353326e-05
2023-01-23 04:36:59.881465: step: 292/530, loss: 0.00011672973778331652
2023-01-23 04:37:01.052458: step: 296/530, loss: 0.011717605404555798
2023-01-23 04:37:02.282361: step: 300/530, loss: 0.0038456919137388468
2023-01-23 04:37:03.491785: step: 304/530, loss: 0.0001558303920319304
2023-01-23 04:37:04.643417: step: 308/530, loss: 0.9889169931411743
2023-01-23 04:37:05.816900: step: 312/530, loss: 2.86102294921875e-05
2023-01-23 04:37:06.968378: step: 316/530, loss: 0.000629043614026159
2023-01-23 04:37:08.146707: step: 320/530, loss: 0.0002006530703511089
2023-01-23 04:37:09.340756: step: 324/530, loss: 9.546280489303172e-05
2023-01-23 04:37:10.530072: step: 328/530, loss: 0.004076194949448109
2023-01-23 04:37:11.757706: step: 332/530, loss: 0.009505748748779297
2023-01-23 04:37:12.971354: step: 336/530, loss: 0.00015592575073242188
2023-01-23 04:37:14.131973: step: 340/530, loss: 2.5558472771081142e-05
2023-01-23 04:37:15.310149: step: 344/530, loss: 0.10532741993665695
2023-01-23 04:37:16.489458: step: 348/530, loss: 0.0023677826393395662
2023-01-23 04:37:17.656775: step: 352/530, loss: 2.9277802241267636e-05
2023-01-23 04:37:18.806391: step: 356/530, loss: 0.0007671356434002519
2023-01-23 04:37:19.998382: step: 360/530, loss: 7.340907905017957e-05
2023-01-23 04:37:21.180031: step: 364/530, loss: 0.01973876915872097
2023-01-23 04:37:22.314358: step: 368/530, loss: 0.0006958008161745965
2023-01-23 04:37:23.513045: step: 372/530, loss: 5.5885317124193534e-05
2023-01-23 04:37:24.700734: step: 376/530, loss: 0.0007942199590615928
2023-01-23 04:37:25.936243: step: 380/530, loss: 0.0001218795805471018
2023-01-23 04:37:27.133809: step: 384/530, loss: 0.0007528782007284462
2023-01-23 04:37:28.326989: step: 388/530, loss: 0.008753967471420765
2023-01-23 04:37:29.525494: step: 392/530, loss: 0.011868476867675781
2023-01-23 04:37:30.731546: step: 396/530, loss: -3.051757857974735e-06
2023-01-23 04:37:31.882004: step: 400/530, loss: 8.058547973632812e-05
2023-01-23 04:37:33.057120: step: 404/530, loss: 0.001388931181281805
2023-01-23 04:37:34.289503: step: 408/530, loss: 0.002764415927231312
2023-01-23 04:37:35.469491: step: 412/530, loss: 0.12310740351676941
2023-01-23 04:37:36.594494: step: 416/530, loss: 1.6403197150793858e-05
2023-01-23 04:37:37.758868: step: 420/530, loss: 1.468658410885837e-05
2023-01-23 04:37:38.893867: step: 424/530, loss: 1.1634829206741415e-05
2023-01-23 04:37:40.052934: step: 428/530, loss: 0.0002911567862611264
2023-01-23 04:37:41.192340: step: 432/530, loss: 0.0027927877381443977
2023-01-23 04:37:42.361299: step: 436/530, loss: 0.013282060623168945
2023-01-23 04:37:43.529756: step: 440/530, loss: 0.00015926361083984375
2023-01-23 04:37:44.677685: step: 444/530, loss: 3.166198803228326e-05
2023-01-23 04:37:45.871605: step: 448/530, loss: 4.38690185546875e-05
2023-01-23 04:37:47.128725: step: 452/530, loss: 0.00017023086547851562
2023-01-23 04:37:48.306451: step: 456/530, loss: 0.02713337168097496
2023-01-23 04:37:49.490690: step: 460/530, loss: 0.0024721145164221525
2023-01-23 04:37:50.656564: step: 464/530, loss: 0.008486270904541016
2023-01-23 04:37:51.846232: step: 468/530, loss: 0.00018768310837913305
2023-01-23 04:37:53.012696: step: 472/530, loss: 0.0006136894226074219
2023-01-23 04:37:54.172036: step: 476/530, loss: 0.0005424499977380037
2023-01-23 04:37:55.309763: step: 480/530, loss: 5.259514000499621e-05
2023-01-23 04:37:56.464450: step: 484/530, loss: 4.119873119634576e-05
2023-01-23 04:37:57.659816: step: 488/530, loss: 0.011005019769072533
2023-01-23 04:37:58.825910: step: 492/530, loss: 4.043579247081652e-05
2023-01-23 04:37:59.992685: step: 496/530, loss: 0.024452686309814453
2023-01-23 04:38:01.156011: step: 500/530, loss: -1.5258789289873675e-06
2023-01-23 04:38:02.362449: step: 504/530, loss: 0.09538283199071884
2023-01-23 04:38:03.546268: step: 508/530, loss: -9.5367431640625e-07
2023-01-23 04:38:04.730677: step: 512/530, loss: 0.05043812096118927
2023-01-23 04:38:05.897805: step: 516/530, loss: 0.009728622622787952
2023-01-23 04:38:07.107042: step: 520/530, loss: 0.0059486390091478825
2023-01-23 04:38:08.278613: step: 524/530, loss: 0.0002765655517578125
2023-01-23 04:38:09.433113: step: 528/530, loss: 0.00093841552734375
2023-01-23 04:38:10.603956: step: 532/530, loss: 0.007543755229562521
2023-01-23 04:38:11.816941: step: 536/530, loss: 0.00015363693819381297
2023-01-23 04:38:12.992918: step: 540/530, loss: 0.006043815519660711
2023-01-23 04:38:14.182759: step: 544/530, loss: 0.02072477526962757
2023-01-23 04:38:15.343624: step: 548/530, loss: 0.004043388180434704
2023-01-23 04:38:16.514535: step: 552/530, loss: 0.00010719299461925402
2023-01-23 04:38:17.669614: step: 556/530, loss: 5.817413330078125e-05
2023-01-23 04:38:18.833870: step: 560/530, loss: 4.100799560546875e-05
2023-01-23 04:38:20.008961: step: 564/530, loss: 0.020451830700039864
2023-01-23 04:38:21.198285: step: 568/530, loss: 0.00010986328561557457
2023-01-23 04:38:22.364407: step: 572/530, loss: 0.0011040688259527087
2023-01-23 04:38:23.502952: step: 576/530, loss: 2.86102294921875e-05
2023-01-23 04:38:24.663860: step: 580/530, loss: 0.0011440276866778731
2023-01-23 04:38:25.847140: step: 584/530, loss: 0.07844734191894531
2023-01-23 04:38:27.032302: step: 588/530, loss: 3.051757857974735e-06
2023-01-23 04:38:28.224485: step: 592/530, loss: 0.018649006262421608
2023-01-23 04:38:29.421495: step: 596/530, loss: 0.025931738317012787
2023-01-23 04:38:30.580748: step: 600/530, loss: 4.091262962901965e-05
2023-01-23 04:38:31.748035: step: 604/530, loss: 0.00020704269991256297
2023-01-23 04:38:32.957725: step: 608/530, loss: 9.059906005859375e-06
2023-01-23 04:38:34.201531: step: 612/530, loss: 1.8501283193472773e-05
2023-01-23 04:38:35.409119: step: 616/530, loss: 0.021941184997558594
2023-01-23 04:38:36.637646: step: 620/530, loss: 0.022238541394472122
2023-01-23 04:38:37.815911: step: 624/530, loss: 6.484985988208791e-06
2023-01-23 04:38:38.991094: step: 628/530, loss: 0.0023048878647387028
2023-01-23 04:38:40.188743: step: 632/530, loss: 5.226135181146674e-05
2023-01-23 04:38:41.358249: step: 636/530, loss: 3.471374657237902e-05
2023-01-23 04:38:42.546668: step: 640/530, loss: 0.0001127243012888357
2023-01-23 04:38:43.745921: step: 644/530, loss: 0.00019428730593062937
2023-01-23 04:38:44.918008: step: 648/530, loss: 0.0004571914905682206
2023-01-23 04:38:46.081853: step: 652/530, loss: 0.005955314729362726
2023-01-23 04:38:47.296281: step: 656/530, loss: 7.82012921263231e-06
2023-01-23 04:38:48.467365: step: 660/530, loss: 0.00432586669921875
2023-01-23 04:38:49.659440: step: 664/530, loss: 0.00024204252986237407
2023-01-23 04:38:50.827466: step: 668/530, loss: 4.7206878662109375e-05
2023-01-23 04:38:52.010787: step: 672/530, loss: 9.269714792026207e-05
2023-01-23 04:38:53.147948: step: 676/530, loss: 0.0001852035493357107
2023-01-23 04:38:54.290587: step: 680/530, loss: 0.0034044268541038036
2023-01-23 04:38:55.482921: step: 684/530, loss: 3.814698175119702e-07
2023-01-23 04:38:56.676358: step: 688/530, loss: 0.011425400152802467
2023-01-23 04:38:57.826698: step: 692/530, loss: 3.7002566386945546e-05
2023-01-23 04:38:58.990931: step: 696/530, loss: 0.003380012698471546
2023-01-23 04:39:00.184637: step: 700/530, loss: 0.017837142571806908
2023-01-23 04:39:01.373109: step: 704/530, loss: 0.00694541959092021
2023-01-23 04:39:02.576547: step: 708/530, loss: 0.00041370390681549907
2023-01-23 04:39:03.762874: step: 712/530, loss: 0.0023647306952625513
2023-01-23 04:39:04.994266: step: 716/530, loss: 0.0005698204040527344
2023-01-23 04:39:06.192362: step: 720/530, loss: 0.00197772984392941
2023-01-23 04:39:07.457760: step: 724/530, loss: 0.019533729180693626
2023-01-23 04:39:08.615247: step: 728/530, loss: 0.00031414031400345266
2023-01-23 04:39:09.804716: step: 732/530, loss: 7.629395213371026e-07
2023-01-23 04:39:10.972142: step: 736/530, loss: 9.212494478560984e-05
2023-01-23 04:39:12.142377: step: 740/530, loss: 0.005208874121308327
2023-01-23 04:39:13.323639: step: 744/530, loss: 0.00032062531681731343
2023-01-23 04:39:14.493947: step: 748/530, loss: 0.00017604828462935984
2023-01-23 04:39:15.654448: step: 752/530, loss: 0.006326961796730757
2023-01-23 04:39:16.833514: step: 756/530, loss: 0.00015506744966842234
2023-01-23 04:39:18.011475: step: 760/530, loss: 0.0501561313867569
2023-01-23 04:39:19.172929: step: 764/530, loss: 0.0518682487308979
2023-01-23 04:39:20.364301: step: 768/530, loss: 0.00028028490487486124
2023-01-23 04:39:21.594545: step: 772/530, loss: 0.024476338177919388
2023-01-23 04:39:22.778055: step: 776/530, loss: 7.553101022494957e-05
2023-01-23 04:39:23.921690: step: 780/530, loss: 9.765625145519152e-05
2023-01-23 04:39:25.119404: step: 784/530, loss: 1.468658410885837e-05
2023-01-23 04:39:26.289113: step: 788/530, loss: 0.0009940625168383121
2023-01-23 04:39:27.420648: step: 792/530, loss: 0.0026735307183116674
2023-01-23 04:39:28.579647: step: 796/530, loss: 0.00018615722365211695
2023-01-23 04:39:29.769077: step: 800/530, loss: -2.7942656743107364e-05
2023-01-23 04:39:30.932440: step: 804/530, loss: 0.18169337511062622
2023-01-23 04:39:32.077382: step: 808/530, loss: 0.00030517578125
2023-01-23 04:39:33.283032: step: 812/530, loss: 0.0002914428769145161
2023-01-23 04:39:34.475900: step: 816/530, loss: 0.00486259488388896
2023-01-23 04:39:35.662223: step: 820/530, loss: 6.160735938465223e-05
2023-01-23 04:39:36.879207: step: 824/530, loss: 0.024407386779785156
2023-01-23 04:39:38.077938: step: 828/530, loss: 0.0040107727982103825
2023-01-23 04:39:39.212057: step: 832/530, loss: 0.000316619873046875
2023-01-23 04:39:40.385059: step: 836/530, loss: 0.0010696410899981856
2023-01-23 04:39:41.572518: step: 840/530, loss: 5.435943421616685e-06
2023-01-23 04:39:42.747978: step: 844/530, loss: 0.01974639855325222
2023-01-23 04:39:43.924862: step: 848/530, loss: 0.0012443542946130037
2023-01-23 04:39:45.074179: step: 852/530, loss: 7.266998727573082e-05
2023-01-23 04:39:46.244065: step: 856/530, loss: 0.000118255615234375
2023-01-23 04:39:47.486237: step: 860/530, loss: 0.0012861251598224044
2023-01-23 04:39:48.674532: step: 864/530, loss: 0.010896540246903896
2023-01-23 04:39:49.812413: step: 868/530, loss: 0.001472568605095148
2023-01-23 04:39:50.994407: step: 872/530, loss: 0.00396232632920146
2023-01-23 04:39:52.183245: step: 876/530, loss: 0.010645628906786442
2023-01-23 04:39:53.341422: step: 880/530, loss: 0.0005401611560955644
2023-01-23 04:39:54.497087: step: 884/530, loss: 0.00780754117295146
2023-01-23 04:39:55.723076: step: 888/530, loss: 2.751350257312879e-05
2023-01-23 04:39:56.923699: step: 892/530, loss: -7.62939453125e-06
2023-01-23 04:39:58.143059: step: 896/530, loss: 0.009859276004135609
2023-01-23 04:39:59.275468: step: 900/530, loss: 0.008296012878417969
2023-01-23 04:40:00.500211: step: 904/530, loss: -3.051757857974735e-06
2023-01-23 04:40:01.709922: step: 908/530, loss: 3.0517576306010596e-06
2023-01-23 04:40:02.878785: step: 912/530, loss: 3.4666059946175665e-05
2023-01-23 04:40:04.117003: step: 916/530, loss: 0.06484317779541016
2023-01-23 04:40:05.307308: step: 920/530, loss: 0.2999833822250366
2023-01-23 04:40:06.456740: step: 924/530, loss: -1.7166138377433526e-06
2023-01-23 04:40:07.627456: step: 928/530, loss: 0.00015506744966842234
2023-01-23 04:40:08.798519: step: 932/530, loss: 0.00039272307185456157
2023-01-23 04:40:09.983692: step: 936/530, loss: 0.00027523041353560984
2023-01-23 04:40:11.152916: step: 940/530, loss: 0.019242476671934128
2023-01-23 04:40:12.352186: step: 944/530, loss: 0.011103439144790173
2023-01-23 04:40:13.527471: step: 948/530, loss: 0.0004304886097088456
2023-01-23 04:40:14.741292: step: 952/530, loss: 0.00046329497126862407
2023-01-23 04:40:15.891280: step: 956/530, loss: 5.34057608092553e-06
2023-01-23 04:40:17.084376: step: 960/530, loss: 0.0023315430153161287
2023-01-23 04:40:18.261266: step: 964/530, loss: 0.018631935119628906
2023-01-23 04:40:19.432248: step: 968/530, loss: 4.57763671875e-05
2023-01-23 04:40:20.637073: step: 972/530, loss: 0.004718780983239412
2023-01-23 04:40:21.827495: step: 976/530, loss: 9.136199514614418e-05
2023-01-23 04:40:22.990913: step: 980/530, loss: -9.15527380129788e-06
2023-01-23 04:40:24.127553: step: 984/530, loss: 2.117157055181451e-05
2023-01-23 04:40:25.286180: step: 988/530, loss: 6.45637555862777e-05
2023-01-23 04:40:26.452365: step: 992/530, loss: 2.0027162008773303e-06
2023-01-23 04:40:27.607579: step: 996/530, loss: 0.004752159118652344
2023-01-23 04:40:28.770082: step: 1000/530, loss: 1.3351441339182202e-06
2023-01-23 04:40:29.912174: step: 1004/530, loss: 2.0503997802734375e-05
2023-01-23 04:40:31.065434: step: 1008/530, loss: 0.004763985052704811
2023-01-23 04:40:32.244725: step: 1012/530, loss: 0.0013132095336914062
2023-01-23 04:40:33.395253: step: 1016/530, loss: 4.0054324017546605e-06
2023-01-23 04:40:34.531870: step: 1020/530, loss: 6.47544875391759e-05
2023-01-23 04:40:35.701360: step: 1024/530, loss: 0.00011501312110340223
2023-01-23 04:40:36.903771: step: 1028/530, loss: 6.389617919921875e-05
2023-01-23 04:40:38.108442: step: 1032/530, loss: 0.007443428039550781
2023-01-23 04:40:39.287891: step: 1036/530, loss: 0.0003108978271484375
2023-01-23 04:40:40.449929: step: 1040/530, loss: 0.04680442810058594
2023-01-23 04:40:41.612088: step: 1044/530, loss: 0.009980392642319202
2023-01-23 04:40:42.777970: step: 1048/530, loss: 0.004717922303825617
2023-01-23 04:40:43.941921: step: 1052/530, loss: 4.768367034557741e-08
2023-01-23 04:40:45.109649: step: 1056/530, loss: 0.0005322456127032638
2023-01-23 04:40:46.277112: step: 1060/530, loss: 0.0006889343494549394
2023-01-23 04:40:47.442511: step: 1064/530, loss: 0.005567741580307484
2023-01-23 04:40:48.601309: step: 1068/530, loss: 4.730224463855848e-05
2023-01-23 04:40:49.738013: step: 1072/530, loss: 0.03714475780725479
2023-01-23 04:40:50.897737: step: 1076/530, loss: 7.629394644936838e-07
2023-01-23 04:40:52.066357: step: 1080/530, loss: 6.675722943327855e-07
2023-01-23 04:40:53.216342: step: 1084/530, loss: 5.054474058852065e-06
2023-01-23 04:40:54.397576: step: 1088/530, loss: 0.013685226440429688
2023-01-23 04:40:55.549185: step: 1092/530, loss: 6.618499901378527e-05
2023-01-23 04:40:56.733629: step: 1096/530, loss: 0.005281352903693914
2023-01-23 04:40:57.897186: step: 1100/530, loss: 0.015789033845067024
2023-01-23 04:40:59.097715: step: 1104/530, loss: 0.21039943397045135
2023-01-23 04:41:00.259657: step: 1108/530, loss: 9.264946129405871e-05
2023-01-23 04:41:01.410821: step: 1112/530, loss: 0.0021619796752929688
2023-01-23 04:41:02.532581: step: 1116/530, loss: 0.00043430327787064016
2023-01-23 04:41:03.681422: step: 1120/530, loss: 0.00020642280287574977
2023-01-23 04:41:04.813676: step: 1124/530, loss: 0.005421829409897327
2023-01-23 04:41:05.979379: step: 1128/530, loss: 0.00016880035400390625
2023-01-23 04:41:07.111683: step: 1132/530, loss: 0.03523435816168785
2023-01-23 04:41:08.284704: step: 1136/530, loss: 0.0001575946807861328
2023-01-23 04:41:09.451696: step: 1140/530, loss: 0.00011196136620128527
2023-01-23 04:41:10.628073: step: 1144/530, loss: 3.0517578125e-05
2023-01-23 04:41:11.858439: step: 1148/530, loss: 0.004398345947265625
2023-01-23 04:41:13.057767: step: 1152/530, loss: 1.9121171135338955e-05
2023-01-23 04:41:14.218985: step: 1156/530, loss: 0.00014057158841751516
2023-01-23 04:41:15.356008: step: 1160/530, loss: 3.662109884317033e-05
2023-01-23 04:41:16.499223: step: 1164/530, loss: 0.00027408599271439016
2023-01-23 04:41:17.683186: step: 1168/530, loss: 0.012848759070038795
2023-01-23 04:41:18.866862: step: 1172/530, loss: 0.03924904018640518
2023-01-23 04:41:20.010021: step: 1176/530, loss: 0.0001693725644145161
2023-01-23 04:41:21.186170: step: 1180/530, loss: 6.67572021484375e-05
2023-01-23 04:41:22.338505: step: 1184/530, loss: 3.452301098150201e-05
2023-01-23 04:41:23.547757: step: 1188/530, loss: 0.0005263328785076737
2023-01-23 04:41:24.755579: step: 1192/530, loss: 7.05719003235572e-06
2023-01-23 04:41:25.926634: step: 1196/530, loss: 0.00010337829735362902
2023-01-23 04:41:27.119161: step: 1200/530, loss: 0.00014381408982444555
2023-01-23 04:41:28.271662: step: 1204/530, loss: 5.245208740234375e-05
2023-01-23 04:41:29.433522: step: 1208/530, loss: 0.00010166168067371473
2023-01-23 04:41:30.604885: step: 1212/530, loss: 0.2588704228401184
2023-01-23 04:41:31.768934: step: 1216/530, loss: 0.0010334014659747481
2023-01-23 04:41:32.970904: step: 1220/530, loss: 0.07205124199390411
2023-01-23 04:41:34.129336: step: 1224/530, loss: 0.00019655228243209422
2023-01-23 04:41:35.300284: step: 1228/530, loss: 0.00027723313542082906
2023-01-23 04:41:36.490795: step: 1232/530, loss: 0.010649108327925205
2023-01-23 04:41:37.650548: step: 1236/530, loss: -2.8610247682081535e-07
2023-01-23 04:41:38.811282: step: 1240/530, loss: -5.149840944795869e-06
2023-01-23 04:41:39.992483: step: 1244/530, loss: 2.212524486822076e-05
2023-01-23 04:41:41.145066: step: 1248/530, loss: 0.0014511108165606856
2023-01-23 04:41:42.336667: step: 1252/530, loss: 0.000644683837890625
2023-01-23 04:41:43.472618: step: 1256/530, loss: 0.11577071994543076
2023-01-23 04:41:44.646469: step: 1260/530, loss: 0.0029537200462073088
2023-01-23 04:41:45.810503: step: 1264/530, loss: 0.0004999160883016884
2023-01-23 04:41:46.968703: step: 1268/530, loss: 0.04533729702234268
2023-01-23 04:41:48.094965: step: 1272/530, loss: 0.0013213157653808594
2023-01-23 04:41:49.276852: step: 1276/530, loss: 3.719329924933845e-06
2023-01-23 04:41:50.469816: step: 1280/530, loss: -3.7193294701864943e-06
2023-01-23 04:41:51.594906: step: 1284/530, loss: 4.501343209994957e-05
2023-01-23 04:41:52.818399: step: 1288/530, loss: 0.0007952689775265753
2023-01-23 04:41:54.039694: step: 1292/530, loss: 0.0002464294375386089
2023-01-23 04:41:55.219689: step: 1296/530, loss: 2.4795534045551904e-05
2023-01-23 04:41:56.321079: step: 1300/530, loss: 0.0003879547293763608
2023-01-23 04:41:57.498423: step: 1304/530, loss: -8.96453821042087e-06
2023-01-23 04:41:58.679207: step: 1308/530, loss: 0.000449943559942767
2023-01-23 04:41:59.805436: step: 1312/530, loss: 0.020659064874053
2023-01-23 04:42:00.947235: step: 1316/530, loss: 0.01578044891357422
2023-01-23 04:42:02.121799: step: 1320/530, loss: 0.056273460388183594
2023-01-23 04:42:03.333226: step: 1324/530, loss: 3.852844383800402e-05
2023-01-23 04:42:04.488120: step: 1328/530, loss: 0.41256943345069885
2023-01-23 04:42:05.683318: step: 1332/530, loss: 0.0485655777156353
2023-01-23 04:42:06.854399: step: 1336/530, loss: 0.0007797241560183465
2023-01-23 04:42:07.986083: step: 1340/530, loss: 0.0013965606922283769
2023-01-23 04:42:09.161550: step: 1344/530, loss: 2.956390380859375e-05
2023-01-23 04:42:10.359140: step: 1348/530, loss: 2.1839143300894648e-05
2023-01-23 04:42:11.519627: step: 1352/530, loss: 0.006017494481056929
2023-01-23 04:42:12.687371: step: 1356/530, loss: 1.068115216185106e-05
2023-01-23 04:42:13.835599: step: 1360/530, loss: -1.4495850336970761e-05
2023-01-23 04:42:15.033964: step: 1364/530, loss: 5.549192792386748e-06
2023-01-23 04:42:16.174123: step: 1368/530, loss: 0.0001067161574610509
2023-01-23 04:42:17.317883: step: 1372/530, loss: 8.296966370835435e-06
2023-01-23 04:42:18.503271: step: 1376/530, loss: 0.009438419714570045
2023-01-23 04:42:19.675845: step: 1380/530, loss: 2.2792815798311494e-05
2023-01-23 04:42:20.829556: step: 1384/530, loss: 0.012886714190244675
2023-01-23 04:42:22.005889: step: 1388/530, loss: 4.243850526108872e-06
2023-01-23 04:42:23.174147: step: 1392/530, loss: 0.0007118224748410285
2023-01-23 04:42:24.375654: step: 1396/530, loss: 0.000377464311895892
2023-01-23 04:42:25.575396: step: 1400/530, loss: 0.0002514839288778603
2023-01-23 04:42:26.765532: step: 1404/530, loss: 1.187875747680664
2023-01-23 04:42:27.982770: step: 1408/530, loss: 0.09320488572120667
2023-01-23 04:42:29.176099: step: 1412/530, loss: 2.86102294921875e-06
2023-01-23 04:42:30.305922: step: 1416/530, loss: 0.0017673491965979338
2023-01-23 04:42:31.459457: step: 1420/530, loss: 0.010086918249726295
2023-01-23 04:42:32.606678: step: 1424/530, loss: 0.0006376266828738153
2023-01-23 04:42:33.738928: step: 1428/530, loss: 0.011838329024612904
2023-01-23 04:42:34.911828: step: 1432/530, loss: 0.00014142990403342992
2023-01-23 04:42:36.155225: step: 1436/530, loss: 0.012244224548339844
2023-01-23 04:42:37.303740: step: 1440/530, loss: 4.854202416026965e-05
2023-01-23 04:42:38.484932: step: 1444/530, loss: 0.0002248764067189768
2023-01-23 04:42:39.693755: step: 1448/530, loss: 0.0015636443858966231
2023-01-23 04:42:40.892188: step: 1452/530, loss: 0.0005785942194052041
2023-01-23 04:42:42.063661: step: 1456/530, loss: 0.008548641577363014
2023-01-23 04:42:43.199863: step: 1460/530, loss: 0.06243762746453285
2023-01-23 04:42:44.355488: step: 1464/530, loss: 0.00026111601619049907
2023-01-23 04:42:45.516002: step: 1468/530, loss: 0.0014337539905682206
2023-01-23 04:42:46.644009: step: 1472/530, loss: 1.621246337890625e-05
2023-01-23 04:42:47.800140: step: 1476/530, loss: -1.583099401614163e-05
2023-01-23 04:42:48.974734: step: 1480/530, loss: 0.0001445770321879536
2023-01-23 04:42:50.156712: step: 1484/530, loss: 2.331733594473917e-05
2023-01-23 04:42:51.311155: step: 1488/530, loss: -4.482268650463084e-06
2023-01-23 04:42:52.474380: step: 1492/530, loss: 0.005095291417092085
2023-01-23 04:42:53.642594: step: 1496/530, loss: 0.0022885799407958984
2023-01-23 04:42:54.820735: step: 1500/530, loss: 0.019936610013246536
2023-01-23 04:42:55.984684: step: 1504/530, loss: 0.0018334866035729647
2023-01-23 04:42:57.112556: step: 1508/530, loss: 0.1090051680803299
2023-01-23 04:42:58.330226: step: 1512/530, loss: 0.0007868766551837325
2023-01-23 04:42:59.534417: step: 1516/530, loss: -2.28881845032447e-06
2023-01-23 04:43:00.739482: step: 1520/530, loss: 1.049041748046875e-05
2023-01-23 04:43:01.900715: step: 1524/530, loss: 0.0005147933843545616
2023-01-23 04:43:03.101006: step: 1528/530, loss: 0.00010366439528297633
2023-01-23 04:43:04.265128: step: 1532/530, loss: 0.001170849776826799
2023-01-23 04:43:05.427411: step: 1536/530, loss: 0.0039466856978833675
2023-01-23 04:43:06.576274: step: 1540/530, loss: 0.00123004917986691
2023-01-23 04:43:07.748476: step: 1544/530, loss: 0.00287132291123271
2023-01-23 04:43:08.947599: step: 1548/530, loss: 1.4591217222914565e-05
2023-01-23 04:43:10.101622: step: 1552/530, loss: 0.00010967254638671875
2023-01-23 04:43:11.314850: step: 1556/530, loss: 0.0016574859619140625
2023-01-23 04:43:12.486985: step: 1560/530, loss: 1.6212464970521978e-06
2023-01-23 04:43:13.625807: step: 1564/530, loss: 4.38690185546875e-05
2023-01-23 04:43:14.819588: step: 1568/530, loss: 6.198883056640625e-06
2023-01-23 04:43:16.001745: step: 1572/530, loss: 6.084442065912299e-05
2023-01-23 04:43:17.197682: step: 1576/530, loss: -1.201629675051663e-05
2023-01-23 04:43:18.330738: step: 1580/530, loss: 2.384185791015625e-05
2023-01-23 04:43:19.532660: step: 1584/530, loss: 4.7111509047681466e-05
2023-01-23 04:43:20.706175: step: 1588/530, loss: 0.0018552780384197831
2023-01-23 04:43:21.857783: step: 1592/530, loss: 0.00010452270362293348
2023-01-23 04:43:23.049085: step: 1596/530, loss: 0.0035234452225267887
2023-01-23 04:43:24.259871: step: 1600/530, loss: 0.00045490264892578125
2023-01-23 04:43:25.430786: step: 1604/530, loss: 0.00014319420733954757
2023-01-23 04:43:26.590916: step: 1608/530, loss: 0.0006534576532430947
2023-01-23 04:43:27.790281: step: 1612/530, loss: 8.392333984375e-05
2023-01-23 04:43:28.965897: step: 1616/530, loss: 9.72747784544481e-06
2023-01-23 04:43:30.125881: step: 1620/530, loss: 0.0004037857288494706
2023-01-23 04:43:31.282870: step: 1624/530, loss: 5.359649730962701e-05
2023-01-23 04:43:32.455338: step: 1628/530, loss: 0.0005096435779705644
2023-01-23 04:43:33.587301: step: 1632/530, loss: 0.0010642051929607987
2023-01-23 04:43:34.792062: step: 1636/530, loss: 0.00016441346087958664
2023-01-23 04:43:35.928570: step: 1640/530, loss: 1.2636184692382812e-05
2023-01-23 04:43:37.122300: step: 1644/530, loss: 0.0025866508949548006
2023-01-23 04:43:38.297258: step: 1648/530, loss: 8.58306884765625e-06
2023-01-23 04:43:39.479605: step: 1652/530, loss: 0.009610939770936966
2023-01-23 04:43:40.683401: step: 1656/530, loss: 1.9471209049224854
2023-01-23 04:43:41.861169: step: 1660/530, loss: 0.0010099411010742188
2023-01-23 04:43:43.006303: step: 1664/530, loss: 0.0005261421320028603
2023-01-23 04:43:44.161551: step: 1668/530, loss: 0.003709983779117465
2023-01-23 04:43:45.346766: step: 1672/530, loss: 0.009287643246352673
2023-01-23 04:43:46.473887: step: 1676/530, loss: -5.722045557376987e-07
2023-01-23 04:43:47.633791: step: 1680/530, loss: 0.0017478943336755037
2023-01-23 04:43:48.770435: step: 1684/530, loss: 0.026054099202156067
2023-01-23 04:43:49.956168: step: 1688/530, loss: 8.697509474586695e-05
2023-01-23 04:43:51.102941: step: 1692/530, loss: 0.00012302398681640625
2023-01-23 04:43:52.259456: step: 1696/530, loss: 0.00021066665067337453
2023-01-23 04:43:53.448355: step: 1700/530, loss: 0.0002636909484863281
2023-01-23 04:43:54.609480: step: 1704/530, loss: 0.012686824426054955
2023-01-23 04:43:55.722144: step: 1708/530, loss: 3.62396240234375e-05
2023-01-23 04:43:56.892461: step: 1712/530, loss: 0.0033990859519690275
2023-01-23 04:43:58.147076: step: 1716/530, loss: 3.0517578125e-05
2023-01-23 04:43:59.335967: step: 1720/530, loss: 9.51766996877268e-05
2023-01-23 04:44:00.523968: step: 1724/530, loss: 0.004762554541230202
2023-01-23 04:44:01.676638: step: 1728/530, loss: -2.86102294921875e-06
2023-01-23 04:44:02.828494: step: 1732/530, loss: 1.2874604180979077e-05
2023-01-23 04:44:04.005855: step: 1736/530, loss: 0.0002754211309365928
2023-01-23 04:44:05.164367: step: 1740/530, loss: -5.5313107623078395e-06
2023-01-23 04:44:06.347324: step: 1744/530, loss: 0.0009949683444574475
2023-01-23 04:44:07.498796: step: 1748/530, loss: 0.02216815948486328
2023-01-23 04:44:08.724153: step: 1752/530, loss: 0.003179454943165183
2023-01-23 04:44:09.903454: step: 1756/530, loss: 0.0002360344078624621
2023-01-23 04:44:11.075322: step: 1760/530, loss: 0.0007087707635946572
2023-01-23 04:44:12.308668: step: 1764/530, loss: 0.01787385903298855
2023-01-23 04:44:13.473823: step: 1768/530, loss: 0.0024094581604003906
2023-01-23 04:44:14.686203: step: 1772/530, loss: 0.007044506259262562
2023-01-23 04:44:15.871526: step: 1776/530, loss: 8.869171324477065e-06
2023-01-23 04:44:17.046539: step: 1780/530, loss: 1.5258789289873675e-06
2023-01-23 04:44:18.209757: step: 1784/530, loss: 0.00026226043701171875
2023-01-23 04:44:19.393958: step: 1788/530, loss: -1.716613724056515e-06
2023-01-23 04:44:20.575133: step: 1792/530, loss: 0.04228496551513672
2023-01-23 04:44:21.744404: step: 1796/530, loss: 0.00020380019850563258
2023-01-23 04:44:22.982731: step: 1800/530, loss: -3.42369094141759e-05
2023-01-23 04:44:24.156883: step: 1804/530, loss: 0.00028705596923828125
2023-01-23 04:44:25.332335: step: 1808/530, loss: 0.0005010605091229081
2023-01-23 04:44:26.538644: step: 1812/530, loss: -3.337859652674524e-06
2023-01-23 04:44:27.722530: step: 1816/530, loss: 0.00019178391085006297
2023-01-23 04:44:28.914824: step: 1820/530, loss: 0.058434486389160156
2023-01-23 04:44:30.100013: step: 1824/530, loss: 0.0049758912064135075
2023-01-23 04:44:31.282798: step: 1828/530, loss: 0.0064424993470311165
2023-01-23 04:44:32.516908: step: 1832/530, loss: 0.0012840271228924394
2023-01-23 04:44:33.732470: step: 1836/530, loss: 2.4318695068359375e-05
2023-01-23 04:44:34.936164: step: 1840/530, loss: 0.04388141632080078
2023-01-23 04:44:36.108266: step: 1844/530, loss: 0.005647850222885609
2023-01-23 04:44:37.296996: step: 1848/530, loss: 0.00037641526432707906
2023-01-23 04:44:38.453548: step: 1852/530, loss: 0.00090961460955441
2023-01-23 04:44:39.658329: step: 1856/530, loss: -7.82012921263231e-06
2023-01-23 04:44:40.818642: step: 1860/530, loss: 0.006428528111428022
2023-01-23 04:44:42.035541: step: 1864/530, loss: 0.1455366015434265
2023-01-23 04:44:43.208512: step: 1868/530, loss: 0.0027129175141453743
2023-01-23 04:44:44.383940: step: 1872/530, loss: 0.009030342102050781
2023-01-23 04:44:45.580673: step: 1876/530, loss: 0.003905868623405695
2023-01-23 04:44:46.790011: step: 1880/530, loss: 0.009376334957778454
2023-01-23 04:44:47.961003: step: 1884/530, loss: 4.7206878662109375e-05
2023-01-23 04:44:49.162925: step: 1888/530, loss: 0.00034770966158248484
2023-01-23 04:44:50.359375: step: 1892/530, loss: 0.0007037162431515753
2023-01-23 04:44:51.518179: step: 1896/530, loss: 0.0005411148304119706
2023-01-23 04:44:52.736751: step: 1900/530, loss: -1.7642974853515625e-05
2023-01-23 04:44:53.927961: step: 1904/530, loss: 2.517700158932712e-05
2023-01-23 04:44:55.134751: step: 1908/530, loss: 0.00028171538724564016
2023-01-23 04:44:56.316304: step: 1912/530, loss: 0.002069854876026511
2023-01-23 04:44:57.527189: step: 1916/530, loss: 0.0005008697626180947
2023-01-23 04:44:58.693125: step: 1920/530, loss: 0.012419892475008965
2023-01-23 04:44:59.839586: step: 1924/530, loss: 9.54627976170741e-05
2023-01-23 04:45:01.018086: step: 1928/530, loss: 0.0007087350240908563
2023-01-23 04:45:02.229076: step: 1932/530, loss: 1.239776611328125e-05
2023-01-23 04:45:03.481271: step: 1936/530, loss: 0.0006891250959597528
2023-01-23 04:45:04.706102: step: 1940/530, loss: 3.63349899998866e-05
2023-01-23 04:45:05.885798: step: 1944/530, loss: 0.0014512062771245837
2023-01-23 04:45:07.082658: step: 1948/530, loss: 0.0005121231079101562
2023-01-23 04:45:08.279724: step: 1952/530, loss: 0.0002449035819154233
2023-01-23 04:45:09.460463: step: 1956/530, loss: 0.0005399704095907509
2023-01-23 04:45:10.663377: step: 1960/530, loss: 0.013637542724609375
2023-01-23 04:45:11.860351: step: 1964/530, loss: 4.019737389171496e-05
2023-01-23 04:45:13.055663: step: 1968/530, loss: 0.007344054989516735
2023-01-23 04:45:14.199925: step: 1972/530, loss: 3.43322744811303e-06
2023-01-23 04:45:15.387818: step: 1976/530, loss: 9.021758887683973e-05
2023-01-23 04:45:16.524430: step: 1980/530, loss: 0.0034140588250011206
2023-01-23 04:45:17.716835: step: 1984/530, loss: 0.023987771943211555
2023-01-23 04:45:18.921056: step: 1988/530, loss: 0.0003339767863508314
2023-01-23 04:45:20.089652: step: 1992/530, loss: 0.007114219479262829
2023-01-23 04:45:21.260359: step: 1996/530, loss: 6.198883056640625e-06
2023-01-23 04:45:22.441430: step: 2000/530, loss: 3.528594970703125e-05
2023-01-23 04:45:23.591689: step: 2004/530, loss: 0.05183382332324982
2023-01-23 04:45:24.738729: step: 2008/530, loss: 0.00010976791963912547
2023-01-23 04:45:25.902060: step: 2012/530, loss: 0.0005473137134686112
2023-01-23 04:45:27.123688: step: 2016/530, loss: 0.00012130737013649195
2023-01-23 04:45:28.339361: step: 2020/530, loss: 0.053607940673828125
2023-01-23 04:45:29.510677: step: 2024/530, loss: 0.00015263557725120336
2023-01-23 04:45:30.677951: step: 2028/530, loss: 2.341270555916708e-05
2023-01-23 04:45:31.884458: step: 2032/530, loss: 0.0008840560913085938
2023-01-23 04:45:33.075991: step: 2036/530, loss: 0.00039920807466842234
2023-01-23 04:45:34.276075: step: 2040/530, loss: 0.0005187034839764237
2023-01-23 04:45:35.474065: step: 2044/530, loss: 0.002173256827518344
2023-01-23 04:45:36.659110: step: 2048/530, loss: 4.711151268566027e-05
2023-01-23 04:45:37.798098: step: 2052/530, loss: 0.00014344156079459935
2023-01-23 04:45:38.963100: step: 2056/530, loss: 0.004884147550910711
2023-01-23 04:45:40.152891: step: 2060/530, loss: 0.011502837762236595
2023-01-23 04:45:41.322262: step: 2064/530, loss: 0.004092359449714422
2023-01-23 04:45:42.495342: step: 2068/530, loss: 0.0008064269786700606
2023-01-23 04:45:43.650896: step: 2072/530, loss: 2.4461747671011835e-05
2023-01-23 04:45:44.830864: step: 2076/530, loss: 0.011409771628677845
2023-01-23 04:45:46.019807: step: 2080/530, loss: 0.020146608352661133
2023-01-23 04:45:47.176810: step: 2084/530, loss: 0.014391040429472923
2023-01-23 04:45:48.357520: step: 2088/530, loss: 0.00011110305786132812
2023-01-23 04:45:49.527626: step: 2092/530, loss: -3.24249276673072e-06
2023-01-23 04:45:50.706689: step: 2096/530, loss: 2.2792815798311494e-05
2023-01-23 04:45:51.901543: step: 2100/530, loss: 0.06636810302734375
2023-01-23 04:45:53.042756: step: 2104/530, loss: 0.36463260650634766
2023-01-23 04:45:54.201544: step: 2108/530, loss: 0.010037994012236595
2023-01-23 04:45:55.362561: step: 2112/530, loss: 3.128051685052924e-05
2023-01-23 04:45:56.520680: step: 2116/530, loss: -2.708435022213962e-05
2023-01-23 04:45:57.661614: step: 2120/530, loss: 0.0002667427179403603
==================================================
Loss: 0.019
--------------------
Dev: {'event': {'p': 0.608421052631579, 'r': 0.7696404793608522, 'f1': 0.6796002351557907}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 28}
Test: {'event': {'p': 0.6660377358490566, 'r': 0.81196089706728, 'f1': 0.731795802021249}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 28}
Chinese: {'event': {'p': 0.5666666666666667, 'r': 0.9444444444444444, 'f1': 0.7083333333333334}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 28}
Korean: {'event': {'p': 0.6170212765957447, 'r': 0.4603174603174603, 'f1': 0.5272727272727272}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 28}
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': 28}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.603537981269511, 'r': 0.7723035952063915, 'f1': 0.677570093457944}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Eng Test for Chinese: {'event': {'p': 0.6663560111835974, 'r': 0.8223116733755031, 'f1': 0.7361647361647363}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Sample Chinese: {'event': {'p': 0.611764705882353, 'r': 0.9629629629629629, 'f1': 0.748201438848921}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5733990147783251, 'r': 0.7749667110519307, 'f1': 0.6591166477916196}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Eng Test for Korean: {'event': {'p': 0.6218005295675199, 'r': 0.8102357676825762, 'f1': 0.7036204744069912}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Sample Korean: {'event': {'p': 0.6417910447761194, 'r': 0.6825396825396826, 'f1': 0.6615384615384614}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6284796573875803, 'r': 0.7816245006657789, 'f1': 0.6967359050445103}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Eng Test for Russian: {'event': {'p': 0.6768263183357524, 'r': 0.80448533640023, 'f1': 0.7351550183920126}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Sample Russian: {'event': {'p': 0.4791666666666667, 'r': 0.6388888888888888, 'f1': 0.5476190476190476}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
******************************
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 04:46:40.822903: step: 4/530, loss: 0.0008842467796057463
2023-01-23 04:46:41.968224: step: 8/530, loss: 3.5667417250806466e-05
2023-01-23 04:46:43.155588: step: 12/530, loss: 3.24249276673072e-06
2023-01-23 04:46:44.322734: step: 16/530, loss: 0.0023732187692075968
2023-01-23 04:46:45.473373: step: 20/530, loss: 2.86102294921875e-06
2023-01-23 04:46:46.650107: step: 24/530, loss: 4.38690176451928e-06
2023-01-23 04:46:47.837434: step: 28/530, loss: 1.0108947208209429e-05
2023-01-23 04:46:48.993894: step: 32/530, loss: 0.018539810553193092
2023-01-23 04:46:50.194160: step: 36/530, loss: 0.0005767822731286287
2023-01-23 04:46:51.357124: step: 40/530, loss: -2.6702882678364404e-06
2023-01-23 04:46:52.509553: step: 44/530, loss: 7.62939453125e-06
2023-01-23 04:46:53.701333: step: 48/530, loss: 0.0004245758173055947
2023-01-23 04:46:54.862191: step: 52/530, loss: 5.7220458984375e-06
2023-01-23 04:46:56.049515: step: 56/530, loss: 0.025035668164491653
2023-01-23 04:46:57.235199: step: 60/530, loss: 3.662109520519152e-05
2023-01-23 04:46:58.422863: step: 64/530, loss: 3.0517580853484105e-06
2023-01-23 04:46:59.562652: step: 68/530, loss: 0.0008785247919149697
2023-01-23 04:47:00.713735: step: 72/530, loss: 1.1730195183190517e-05
2023-01-23 04:47:01.981339: step: 76/530, loss: 0.11610870808362961
2023-01-23 04:47:03.171217: step: 80/530, loss: 7.915496098576114e-06
2023-01-23 04:47:04.343653: step: 84/530, loss: 0.00016508101543877274
2023-01-23 04:47:05.544726: step: 88/530, loss: -6.580352874152595e-06
2023-01-23 04:47:06.727516: step: 92/530, loss: 7.629387255292386e-07
2023-01-23 04:47:07.911247: step: 96/530, loss: 0.0005901336553506553
2023-01-23 04:47:09.060031: step: 100/530, loss: 0.024289704859256744
2023-01-23 04:47:10.231193: step: 104/530, loss: 0.0012409210903570056
2023-01-23 04:47:11.385616: step: 108/530, loss: 0.0002658844168763608
2023-01-23 04:47:12.608648: step: 112/530, loss: 9.059906005859375e-06
2023-01-23 04:47:13.777875: step: 116/530, loss: 6.885529001010582e-05
2023-01-23 04:47:14.932769: step: 120/530, loss: 3.929138256353326e-05
2023-01-23 04:47:16.089750: step: 124/530, loss: 0.000301170366583392
2023-01-23 04:47:17.257355: step: 128/530, loss: 0.0020597458351403475
2023-01-23 04:47:18.436935: step: 132/530, loss: 1.6880036127986386e-05
2023-01-23 04:47:19.626355: step: 136/530, loss: 4.9114232751890086e-06
2023-01-23 04:47:20.796256: step: 140/530, loss: 0.00022525788517668843
2023-01-23 04:47:22.007794: step: 144/530, loss: 0.00028362273587845266
2023-01-23 04:47:23.200768: step: 148/530, loss: 0.00023651123046875
2023-01-23 04:47:24.325988: step: 152/530, loss: -8.39233416627394e-06
2023-01-23 04:47:25.483046: step: 156/530, loss: 3.4809112548828125e-05
2023-01-23 04:47:26.633388: step: 160/530, loss: 0.014372444711625576
2023-01-23 04:47:27.815865: step: 164/530, loss: 0.0003044605255126953
2023-01-23 04:47:28.995079: step: 168/530, loss: 0.0006437301635742188
2023-01-23 04:47:30.165184: step: 172/530, loss: 0.012850952334702015
2023-01-23 04:47:31.340414: step: 176/530, loss: 2.8610227218450746e-06
2023-01-23 04:47:32.528816: step: 180/530, loss: 0.00577621441334486
2023-01-23 04:47:33.759490: step: 184/530, loss: 0.0009630203130654991
2023-01-23 04:47:34.928128: step: 188/530, loss: 0.0001680374116403982
2023-01-23 04:47:36.059826: step: 192/530, loss: 8.096695091808215e-05
2023-01-23 04:47:37.230265: step: 196/530, loss: 0.00010147094872081652
2023-01-23 04:47:38.414080: step: 200/530, loss: 0.0022326470352709293
2023-01-23 04:47:39.600396: step: 204/530, loss: 0.032537125051021576
2023-01-23 04:47:40.731963: step: 208/530, loss: 7.019042823230848e-05
2023-01-23 04:47:41.903040: step: 212/530, loss: 0.0013736726250499487
2023-01-23 04:47:43.060524: step: 216/530, loss: 0.0007306575425900519
2023-01-23 04:47:44.263116: step: 220/530, loss: 0.00033226015511900187
2023-01-23 04:47:45.420114: step: 224/530, loss: 5.7220458984375e-05
2023-01-23 04:47:46.593833: step: 228/530, loss: -3.24249276673072e-06
2023-01-23 04:47:47.748900: step: 232/530, loss: 0.0001653671351959929
2023-01-23 04:47:48.931815: step: 236/530, loss: 0.00037860870361328125
2023-01-23 04:47:50.152143: step: 240/530, loss: 0.0007821083418093622
2023-01-23 04:47:51.309727: step: 244/530, loss: 0.0029730796813964844
2023-01-23 04:47:52.525666: step: 248/530, loss: 6.65664701955393e-05
2023-01-23 04:47:53.683636: step: 252/530, loss: 0.009882736951112747
2023-01-23 04:47:54.859763: step: 256/530, loss: 5.2833554946118966e-05
2023-01-23 04:47:56.051507: step: 260/530, loss: 0.0005966186290606856
2023-01-23 04:47:57.172252: step: 264/530, loss: 1.6498566765221767e-05
2023-01-23 04:47:58.341169: step: 268/530, loss: 0.0024673461448401213
2023-01-23 04:47:59.501308: step: 272/530, loss: 0.005174827296286821
2023-01-23 04:48:00.667644: step: 276/530, loss: 3.089904930675402e-05
2023-01-23 04:48:01.832649: step: 280/530, loss: 0.024163484573364258
2023-01-23 04:48:02.985144: step: 284/530, loss: 0.0002408981235930696
2023-01-23 04:48:04.181467: step: 288/530, loss: 7.43865984986769e-06
2023-01-23 04:48:05.318959: step: 292/530, loss: 0.013293981552124023
2023-01-23 04:48:06.495039: step: 296/530, loss: 4.0817263652570546e-05
2023-01-23 04:48:07.627614: step: 300/530, loss: 0.0014567375183105469
2023-01-23 04:48:08.866144: step: 304/530, loss: 0.0006543159252032638
2023-01-23 04:48:09.987286: step: 308/530, loss: 8.211136446334422e-05
2023-01-23 04:48:11.141500: step: 312/530, loss: 0.004639816470444202
2023-01-23 04:48:12.364981: step: 316/530, loss: 6.628037226619199e-06
2023-01-23 04:48:13.563800: step: 320/530, loss: 0.00024890899658203125
2023-01-23 04:48:14.784377: step: 324/530, loss: 0.008576965890824795
2023-01-23 04:48:15.988500: step: 328/530, loss: 0.0008941650739870965
2023-01-23 04:48:17.155384: step: 332/530, loss: 0.009537887759506702
2023-01-23 04:48:18.361296: step: 336/530, loss: 0.0052429200150072575
2023-01-23 04:48:19.528443: step: 340/530, loss: 0.0012697218917310238
2023-01-23 04:48:20.705509: step: 344/530, loss: -3.814697322468419e-07
2023-01-23 04:48:21.865790: step: 348/530, loss: 0.00011100769916083664
2023-01-23 04:48:23.070277: step: 352/530, loss: 0.05011463165283203
2023-01-23 04:48:24.262649: step: 356/530, loss: 0.00014781951904296875
2023-01-23 04:48:25.416987: step: 360/530, loss: 7.171630568336695e-05
2023-01-23 04:48:26.573958: step: 364/530, loss: 0.014308357611298561
2023-01-23 04:48:27.757610: step: 368/530, loss: 0.0017265320057049394
2023-01-23 04:48:28.937459: step: 372/530, loss: 0.0004422187921591103
2023-01-23 04:48:30.100424: step: 376/530, loss: 0.0004518509085755795
2023-01-23 04:48:31.287040: step: 380/530, loss: 0.020642662420868874
2023-01-23 04:48:32.445570: step: 384/530, loss: 0.0028545379173010588
2023-01-23 04:48:33.624572: step: 388/530, loss: 0.048616793006658554
2023-01-23 04:48:34.845519: step: 392/530, loss: 0.06614677608013153
2023-01-23 04:48:36.009295: step: 396/530, loss: 0.04632611200213432
2023-01-23 04:48:37.209409: step: 400/530, loss: 0.0011794089805334806
2023-01-23 04:48:38.345882: step: 404/530, loss: 0.0017919540405273438
2023-01-23 04:48:39.568143: step: 408/530, loss: 0.10392151027917862
2023-01-23 04:48:40.708598: step: 412/530, loss: 0.011982726864516735
2023-01-23 04:48:41.880229: step: 416/530, loss: 6.961822691664565e-06
2023-01-23 04:48:43.032876: step: 420/530, loss: 9.16481003514491e-05
2023-01-23 04:48:44.211284: step: 424/530, loss: 0.00059933663578704
2023-01-23 04:48:45.375026: step: 428/530, loss: 1.354217511106981e-05
2023-01-23 04:48:46.510008: step: 432/530, loss: 8.96453821042087e-06
2023-01-23 04:48:47.637202: step: 436/530, loss: 0.006188583560287952
2023-01-23 04:48:48.814617: step: 440/530, loss: 1.296997106692288e-05
2023-01-23 04:48:49.961185: step: 444/530, loss: 0.00043315888615325093
2023-01-23 04:48:51.158770: step: 448/530, loss: 0.014470291323959827
2023-01-23 04:48:52.319203: step: 452/530, loss: 0.00013236999802757055
2023-01-23 04:48:53.501370: step: 456/530, loss: 0.0029067995492368937
2023-01-23 04:48:54.681748: step: 460/530, loss: 0.0010534286266192794
2023-01-23 04:48:55.852563: step: 464/530, loss: 1.9073485191256623e-06
2023-01-23 04:48:57.078191: step: 468/530, loss: 0.0004135131894145161
2023-01-23 04:48:58.339177: step: 472/530, loss: 0.0010515212779864669
2023-01-23 04:48:59.476800: step: 476/530, loss: 6.10351571594947e-06
2023-01-23 04:49:00.655974: step: 480/530, loss: 0.0002742767392192036
2023-01-23 04:49:01.806748: step: 484/530, loss: 0.005839633755385876
2023-01-23 04:49:02.971700: step: 488/530, loss: 0.0009885787731036544
2023-01-23 04:49:04.141361: step: 492/530, loss: 2.059936559817288e-05
2023-01-23 04:49:05.328904: step: 496/530, loss: -1.430511474609375e-05
2023-01-23 04:49:06.501614: step: 500/530, loss: 0.004357337951660156
2023-01-23 04:49:07.682941: step: 504/530, loss: 0.00020256043353583664
2023-01-23 04:49:08.845723: step: 508/530, loss: 0.00032167433528229594
2023-01-23 04:49:10.006709: step: 512/530, loss: 3.1948089599609375e-05
2023-01-23 04:49:11.149222: step: 516/530, loss: 0.0009796142112463713
2023-01-23 04:49:12.342943: step: 520/530, loss: 2.8371810913085938e-05
2023-01-23 04:49:13.489735: step: 524/530, loss: 0.0570131354033947
2023-01-23 04:49:14.679952: step: 528/530, loss: 4.081726001459174e-05
2023-01-23 04:49:15.872686: step: 532/530, loss: 1.8787384760798886e-05
2023-01-23 04:49:17.040734: step: 536/530, loss: 0.004150390625
2023-01-23 04:49:18.197201: step: 540/530, loss: 3.14712519866589e-06
2023-01-23 04:49:19.358841: step: 544/530, loss: 9.5367431640625e-07
2023-01-23 04:49:20.521988: step: 548/530, loss: 0.0017355919117107987
2023-01-23 04:49:21.673607: step: 552/530, loss: 0.04094123840332031
2023-01-23 04:49:22.830777: step: 556/530, loss: 3.0517585400957614e-06
2023-01-23 04:49:24.026465: step: 560/530, loss: 0.08593368530273438
2023-01-23 04:49:25.180210: step: 564/530, loss: 0.00010757445852505043
2023-01-23 04:49:26.341100: step: 568/530, loss: 6.675720101156912e-07
2023-01-23 04:49:27.491634: step: 572/530, loss: 1.0204315003647935e-05
2023-01-23 04:49:28.660092: step: 576/530, loss: 0.0035228729248046875
2023-01-23 04:49:29.842564: step: 580/530, loss: 0.24749116599559784
2023-01-23 04:49:30.992080: step: 584/530, loss: 0.003583812853321433
2023-01-23 04:49:32.148182: step: 588/530, loss: -4.2915345943583816e-07
2023-01-23 04:49:33.306451: step: 592/530, loss: 0.04141292721033096
2023-01-23 04:49:34.468949: step: 596/530, loss: 0.0002520561101846397
2023-01-23 04:49:35.599409: step: 600/530, loss: 0.0040562632493674755
2023-01-23 04:49:36.763466: step: 604/530, loss: 0.0001661300630075857
2023-01-23 04:49:37.920028: step: 608/530, loss: 1.7070769899873994e-05
2023-01-23 04:49:39.092847: step: 612/530, loss: 0.0006566047668457031
2023-01-23 04:49:40.262009: step: 616/530, loss: -1.373290979245212e-05
2023-01-23 04:49:41.422711: step: 620/530, loss: 8.754729788051918e-05
2023-01-23 04:49:42.605752: step: 624/530, loss: 0.02286529541015625
2023-01-23 04:49:43.763609: step: 628/530, loss: 0.001042366144247353
2023-01-23 04:49:44.949606: step: 632/530, loss: 0.004548836033791304
2023-01-23 04:49:46.123136: step: 636/530, loss: 6.84738188283518e-05
2023-01-23 04:49:47.261714: step: 640/530, loss: 0.0026903152465820312
2023-01-23 04:49:48.431891: step: 644/530, loss: 0.030205916613340378
2023-01-23 04:49:49.616187: step: 648/530, loss: 0.04602985456585884
2023-01-23 04:49:50.796067: step: 652/530, loss: 0.10034985095262527
2023-01-23 04:49:51.950044: step: 656/530, loss: 3.0517578125e-05
2023-01-23 04:49:53.090029: step: 660/530, loss: 0.00026607513427734375
2023-01-23 04:49:54.279871: step: 664/530, loss: 0.00036792753962799907
2023-01-23 04:49:55.426615: step: 668/530, loss: 0.06706103682518005
2023-01-23 04:49:56.559784: step: 672/530, loss: 0.006276160478591919
2023-01-23 04:49:57.735989: step: 676/530, loss: 9.346009392174892e-06
2023-01-23 04:49:58.884789: step: 680/530, loss: 8.182526653399691e-05
2023-01-23 04:50:00.095186: step: 684/530, loss: 0.00019803046598099172
2023-01-23 04:50:01.199065: step: 688/530, loss: 0.0021015643142163754
2023-01-23 04:50:02.392673: step: 692/530, loss: 0.00011692046973621473
2023-01-23 04:50:03.537792: step: 696/530, loss: 0.001840019365772605
2023-01-23 04:50:04.714190: step: 700/530, loss: 0.007706690113991499
2023-01-23 04:50:05.950234: step: 704/530, loss: 0.00015344620624091476
2023-01-23 04:50:07.125796: step: 708/530, loss: 6.065368506824598e-05
2023-01-23 04:50:08.282235: step: 712/530, loss: 0.01141433697193861
2023-01-23 04:50:09.460067: step: 716/530, loss: 0.02528552897274494
2023-01-23 04:50:10.656492: step: 720/530, loss: 0.0014438629150390625
2023-01-23 04:50:11.876697: step: 724/530, loss: 5.0830840336857364e-05
2023-01-23 04:50:13.067422: step: 728/530, loss: -2.2983551389188506e-05
2023-01-23 04:50:14.236902: step: 732/530, loss: 2.1934511096333154e-06
2023-01-23 04:50:15.408711: step: 736/530, loss: 1.5354156857938506e-05
2023-01-23 04:50:16.587096: step: 740/530, loss: 0.0019367217319086194
2023-01-23 04:50:17.735570: step: 744/530, loss: 0.04069080203771591
2023-01-23 04:50:18.912184: step: 748/530, loss: 0.0002922058047261089
2023-01-23 04:50:20.065980: step: 752/530, loss: 0.001455593155696988
2023-01-23 04:50:21.236195: step: 756/530, loss: 0.00019226073345635086
2023-01-23 04:50:22.411892: step: 760/530, loss: 0.02594890631735325
2023-01-23 04:50:23.615413: step: 764/530, loss: 0.0003811836359091103
2023-01-23 04:50:24.784718: step: 768/530, loss: 0.00017986298189498484
2023-01-23 04:50:25.941387: step: 772/530, loss: 0.0012166977394372225
2023-01-23 04:50:27.150124: step: 776/530, loss: 8.010864985408261e-05
2023-01-23 04:50:28.284322: step: 780/530, loss: 0.00016984940157271922
2023-01-23 04:50:29.459820: step: 784/530, loss: 0.0003554344002623111
2023-01-23 04:50:30.638723: step: 788/530, loss: 0.00036554335383698344
2023-01-23 04:50:31.786881: step: 792/530, loss: 0.0010256767272949219
2023-01-23 04:50:32.937866: step: 796/530, loss: 0.0005213349941186607
2023-01-23 04:50:34.081581: step: 800/530, loss: 1.602172778802924e-05
2023-01-23 04:50:35.214176: step: 804/530, loss: 1.8215179807157256e-05
2023-01-23 04:50:36.366056: step: 808/530, loss: -6.771088010282256e-06
2023-01-23 04:50:37.532675: step: 812/530, loss: 0.00036449433537200093
2023-01-23 04:50:38.680352: step: 816/530, loss: 0.0028724311850965023
2023-01-23 04:50:39.843052: step: 820/530, loss: 4.38690176451928e-06
2023-01-23 04:50:41.045253: step: 824/530, loss: 0.0005382538074627519
2023-01-23 04:50:42.270780: step: 828/530, loss: 0.006535148713737726
2023-01-23 04:50:43.414292: step: 832/530, loss: 5.722046125811175e-07
2023-01-23 04:50:44.601755: step: 836/530, loss: 2.136230432370212e-05
2023-01-23 04:50:45.774570: step: 840/530, loss: 1.9073486328125e-05
2023-01-23 04:50:46.973286: step: 844/530, loss: 0.2399924397468567
2023-01-23 04:50:48.127929: step: 848/530, loss: 0.00017642974853515625
2023-01-23 04:50:49.270776: step: 852/530, loss: 0.0009315491188317537
2023-01-23 04:50:50.420444: step: 856/530, loss: 3.814697265625e-06
2023-01-23 04:50:51.579382: step: 860/530, loss: 7.772445314913057e-06
2023-01-23 04:50:52.727906: step: 864/530, loss: 0.08931998908519745
2023-01-23 04:50:53.901958: step: 868/530, loss: 0.00010604858834994957
2023-01-23 04:50:55.091970: step: 872/530, loss: 0.06591244041919708
2023-01-23 04:50:56.274280: step: 876/530, loss: 0.00011148452904308215
2023-01-23 04:50:57.479963: step: 880/530, loss: 1.6975403923424892e-05
2023-01-23 04:50:58.670017: step: 884/530, loss: 0.013180924579501152
2023-01-23 04:50:59.848893: step: 888/530, loss: 2.4223329091910273e-05
2023-01-23 04:51:01.003938: step: 892/530, loss: 0.0005052566411904991
2023-01-23 04:51:02.206981: step: 896/530, loss: 8.068084571277723e-05
2023-01-23 04:51:03.313503: step: 900/530, loss: 0.13582110404968262
2023-01-23 04:51:04.465438: step: 904/530, loss: 0.00046348574687726796
2023-01-23 04:51:05.655369: step: 908/530, loss: 0.00021095277043059468
2023-01-23 04:51:06.811321: step: 912/530, loss: 0.00795822124928236
2023-01-23 04:51:07.933813: step: 916/530, loss: 0.16425706446170807
2023-01-23 04:51:09.088961: step: 920/530, loss: 0.21882934868335724
2023-01-23 04:51:10.268034: step: 924/530, loss: 1.7547608877066523e-05
2023-01-23 04:51:11.427710: step: 928/530, loss: 0.00507087679579854
2023-01-23 04:51:12.614990: step: 932/530, loss: 0.004935646429657936
2023-01-23 04:51:13.794401: step: 936/530, loss: 0.0003787994501180947
2023-01-23 04:51:14.979500: step: 940/530, loss: 0.0007572174072265625
2023-01-23 04:51:16.174405: step: 944/530, loss: 0.036307621747255325
2023-01-23 04:51:17.352257: step: 948/530, loss: 4.196167537884321e-06
2023-01-23 04:51:18.517676: step: 952/530, loss: 0.01940155029296875
2023-01-23 04:51:19.696909: step: 956/530, loss: 0.0023254393599927425
2023-01-23 04:51:20.900359: step: 960/530, loss: 0.00016078949556685984
2023-01-23 04:51:22.062166: step: 964/530, loss: 0.00016059876361396164
2023-01-23 04:51:23.261214: step: 968/530, loss: 0.004443454556167126
2023-01-23 04:51:24.438226: step: 972/530, loss: 0.01424484234303236
2023-01-23 04:51:25.630135: step: 976/530, loss: 0.040998175740242004
2023-01-23 04:51:26.833537: step: 980/530, loss: 0.013793183490633965
2023-01-23 04:51:28.030018: step: 984/530, loss: 3.328323509776965e-05
2023-01-23 04:51:29.182058: step: 988/530, loss: 7.028579420875758e-05
2023-01-23 04:51:30.365303: step: 992/530, loss: 0.005992317106574774
2023-01-23 04:51:31.546635: step: 996/530, loss: 1.2588501704158261e-05
2023-01-23 04:51:32.737108: step: 1000/530, loss: 0.0009240627405233681
2023-01-23 04:51:33.891262: step: 1004/530, loss: 9.5367431640625e-07
2023-01-23 04:51:35.071861: step: 1008/530, loss: 0.024341583251953125
2023-01-23 04:51:36.269519: step: 1012/530, loss: 0.05434875562787056
2023-01-23 04:51:37.480032: step: 1016/530, loss: 1.659393274167087e-05
2023-01-23 04:51:38.648739: step: 1020/530, loss: 0.001986599061638117
2023-01-23 04:51:39.814931: step: 1024/530, loss: 0.0003702164103742689
2023-01-23 04:51:40.979854: step: 1028/530, loss: -4.76837158203125e-07
2023-01-23 04:51:42.147489: step: 1032/530, loss: 0.002497005509212613
2023-01-23 04:51:43.326975: step: 1036/530, loss: 0.008041191846132278
2023-01-23 04:51:44.484036: step: 1040/530, loss: 0.0037450790405273438
2023-01-23 04:51:45.689265: step: 1044/530, loss: 3.032684253412299e-05
2023-01-23 04:51:46.840673: step: 1048/530, loss: 0.0004096984921488911
2023-01-23 04:51:48.020630: step: 1052/530, loss: 0.0015766144497320056
2023-01-23 04:51:49.193347: step: 1056/530, loss: 0.013672351837158203
2023-01-23 04:51:50.394114: step: 1060/530, loss: 0.0008726119995117188
2023-01-23 04:51:51.570262: step: 1064/530, loss: 8.778572373557836e-05
2023-01-23 04:51:52.781286: step: 1068/530, loss: 0.04264412075281143
2023-01-23 04:51:53.959759: step: 1072/530, loss: 1.7166138377433526e-06
2023-01-23 04:51:55.104577: step: 1076/530, loss: 0.03991241380572319
2023-01-23 04:51:56.251470: step: 1080/530, loss: 2.498626781743951e-05
2023-01-23 04:51:57.414800: step: 1084/530, loss: 9.5367431640625e-07
2023-01-23 04:51:58.575373: step: 1088/530, loss: 0.00010881424532271922
2023-01-23 04:51:59.736545: step: 1092/530, loss: 0.00028629304142668843
2023-01-23 04:52:00.963509: step: 1096/530, loss: 0.0003783225838560611
2023-01-23 04:52:02.163858: step: 1100/530, loss: 0.00022563934908248484
2023-01-23 04:52:03.289940: step: 1104/530, loss: 0.0025642395485192537
2023-01-23 04:52:04.444648: step: 1108/530, loss: 0.0002099990815622732
2023-01-23 04:52:05.630555: step: 1112/530, loss: 0.0004987716674804688
2023-01-23 04:52:06.825036: step: 1116/530, loss: -1.9073486328125e-06
2023-01-23 04:52:07.981035: step: 1120/530, loss: 0.003844356629997492
2023-01-23 04:52:09.158816: step: 1124/530, loss: 0.11600160598754883
2023-01-23 04:52:10.317322: step: 1128/530, loss: 0.002038288163021207
2023-01-23 04:52:11.459848: step: 1132/530, loss: 0.005327797029167414
2023-01-23 04:52:12.693950: step: 1136/530, loss: -5.722044988942798e-07
2023-01-23 04:52:13.834993: step: 1140/530, loss: 0.014038467779755592
2023-01-23 04:52:15.033623: step: 1144/530, loss: 0.017444420605897903
2023-01-23 04:52:16.192772: step: 1148/530, loss: 6.637573096668348e-05
2023-01-23 04:52:17.365365: step: 1152/530, loss: 0.00552978552877903
2023-01-23 04:52:18.545509: step: 1156/530, loss: 1.411438006471144e-05
2023-01-23 04:52:19.682511: step: 1160/530, loss: 0.0004173278866801411
2023-01-23 04:52:20.828974: step: 1164/530, loss: 0.0005161285516805947
2023-01-23 04:52:21.987597: step: 1168/530, loss: 1.831054760259576e-05
2023-01-23 04:52:23.176489: step: 1172/530, loss: 0.0017156600952148438
2023-01-23 04:52:24.394913: step: 1176/530, loss: 9.460448927711695e-05
2023-01-23 04:52:25.521064: step: 1180/530, loss: 0.0008845329284667969
2023-01-23 04:52:26.713637: step: 1184/530, loss: 7.305145118152723e-05
2023-01-23 04:52:27.919146: step: 1188/530, loss: 0.013806152157485485
2023-01-23 04:52:29.089990: step: 1192/530, loss: 0.1845572590827942
2023-01-23 04:52:30.247032: step: 1196/530, loss: 0.0011671066749840975
2023-01-23 04:52:31.446426: step: 1200/530, loss: 0.00014991761418059468
2023-01-23 04:52:32.648996: step: 1204/530, loss: 0.003384542418643832
2023-01-23 04:52:33.818995: step: 1208/530, loss: 0.00027980803861282766
2023-01-23 04:52:34.931441: step: 1212/530, loss: 0.022311020642518997
2023-01-23 04:52:36.112381: step: 1216/530, loss: 4.4822695599577855e-06
2023-01-23 04:52:37.360453: step: 1220/530, loss: 0.00020141602726653218
2023-01-23 04:52:38.564110: step: 1224/530, loss: 7.085800461936742e-05
2023-01-23 04:52:39.765858: step: 1228/530, loss: 0.001888275146484375
2023-01-23 04:52:40.971432: step: 1232/530, loss: 0.023880766704678535
2023-01-23 04:52:42.142467: step: 1236/530, loss: 0.0007135391933843493
2023-01-23 04:52:43.300277: step: 1240/530, loss: 0.00010433197167003527
2023-01-23 04:52:44.457985: step: 1244/530, loss: 6.332397606456652e-05
2023-01-23 04:52:45.640401: step: 1248/530, loss: 0.02476673200726509
2023-01-23 04:52:46.774305: step: 1252/530, loss: 0.0003673553292173892
2023-01-23 04:52:47.950259: step: 1256/530, loss: 0.0006803512806072831
2023-01-23 04:52:49.087369: step: 1260/530, loss: 0.00018367767916060984
2023-01-23 04:52:50.274826: step: 1264/530, loss: 6.294250852079131e-06
2023-01-23 04:52:51.447076: step: 1268/530, loss: 0.0031463622581213713
2023-01-23 04:52:52.603246: step: 1272/530, loss: 0.0005197525024414062
2023-01-23 04:52:53.811560: step: 1276/530, loss: 0.00027718543424271047
2023-01-23 04:52:54.966262: step: 1280/530, loss: -1.9073486612342094e-07
2023-01-23 04:52:56.096329: step: 1284/530, loss: 9.346007573185489e-06
2023-01-23 04:52:57.253988: step: 1288/530, loss: 1.1444091796875e-05
2023-01-23 04:52:58.434703: step: 1292/530, loss: 8.125304884742945e-05
2023-01-23 04:52:59.600978: step: 1296/530, loss: 0.0008970260387286544
2023-01-23 04:53:00.796219: step: 1300/530, loss: 0.0032665252219885588
2023-01-23 04:53:01.943340: step: 1304/530, loss: 0.01168289128690958
2023-01-23 04:53:03.131445: step: 1308/530, loss: 0.004407310858368874
2023-01-23 04:53:04.339217: step: 1312/530, loss: 0.005623626988381147
2023-01-23 04:53:05.539482: step: 1316/530, loss: 0.0002190590021200478
2023-01-23 04:53:06.700316: step: 1320/530, loss: 3.657341221696697e-05
2023-01-23 04:53:07.888655: step: 1324/530, loss: 0.00010948181443382055
2023-01-23 04:53:09.007816: step: 1328/530, loss: 0.007991408929228783
2023-01-23 04:53:10.150723: step: 1332/530, loss: 0.00017862320237327367
2023-01-23 04:53:11.328292: step: 1336/530, loss: 0.0006183624500408769
2023-01-23 04:53:12.558690: step: 1340/530, loss: 0.00026721955509856343
2023-01-23 04:53:13.699637: step: 1344/530, loss: 7.61032133596018e-05
2023-01-23 04:53:14.876807: step: 1348/530, loss: 0.00025501250638626516
2023-01-23 04:53:16.064714: step: 1352/530, loss: 0.02398242987692356
2023-01-23 04:53:17.251831: step: 1356/530, loss: 0.005943107884377241
2023-01-23 04:53:18.451607: step: 1360/530, loss: 0.0102081298828125
2023-01-23 04:53:19.628876: step: 1364/530, loss: 0.011873865500092506
2023-01-23 04:53:20.777517: step: 1368/530, loss: 6.29425048828125e-05
2023-01-23 04:53:21.954170: step: 1372/530, loss: 0.0014804840320721269
2023-01-23 04:53:23.142311: step: 1376/530, loss: 0.0049648284912109375
2023-01-23 04:53:24.308296: step: 1380/530, loss: 5.145073009771295e-05
2023-01-23 04:53:25.483599: step: 1384/530, loss: 3.995895167463459e-05
2023-01-23 04:53:26.633177: step: 1388/530, loss: 2.7084352041129023e-05
2023-01-23 04:53:27.791126: step: 1392/530, loss: 0.0013572692405432463
2023-01-23 04:53:28.960461: step: 1396/530, loss: 9.440183930564672e-05
2023-01-23 04:53:30.105752: step: 1400/530, loss: 0.0005758285406045616
2023-01-23 04:53:31.280220: step: 1404/530, loss: 0.0029203894082456827
2023-01-23 04:53:32.473735: step: 1408/530, loss: 0.0056747435592114925
2023-01-23 04:53:33.703534: step: 1412/530, loss: 0.0018299103248864412
2023-01-23 04:53:34.871379: step: 1416/530, loss: 0.00022201538376975805
2023-01-23 04:53:36.022369: step: 1420/530, loss: -6.532669431180693e-06
2023-01-23 04:53:37.140188: step: 1424/530, loss: 1.430511474609375e-06
2023-01-23 04:53:38.289724: step: 1428/530, loss: 0.0007806777721270919
2023-01-23 04:53:39.487717: step: 1432/530, loss: 0.0001430511474609375
2023-01-23 04:53:40.721155: step: 1436/530, loss: 0.025507165119051933
2023-01-23 04:53:41.878882: step: 1440/530, loss: 0.005219364073127508
2023-01-23 04:53:43.056468: step: 1444/530, loss: 0.003677559085190296
2023-01-23 04:53:44.232929: step: 1448/530, loss: 1.4781952813791577e-05
2023-01-23 04:53:45.371451: step: 1452/530, loss: 1.5258789289873675e-06
2023-01-23 04:53:46.557152: step: 1456/530, loss: 9.298324584960938e-05
2023-01-23 04:53:47.702805: step: 1460/530, loss: -6.675720669591101e-07
2023-01-23 04:53:48.897121: step: 1464/530, loss: -9.059906005859375e-06
2023-01-23 04:53:50.090363: step: 1468/530, loss: 0.008012866601347923
2023-01-23 04:53:51.292811: step: 1472/530, loss: 0.00022373200044967234
2023-01-23 04:53:52.479826: step: 1476/530, loss: 0.007389616686850786
2023-01-23 04:53:53.616814: step: 1480/530, loss: 0.02299499697983265
2023-01-23 04:53:54.791971: step: 1484/530, loss: 0.0001958847133209929
2023-01-23 04:53:55.993496: step: 1488/530, loss: 0.004261589143425226
2023-01-23 04:53:57.193550: step: 1492/530, loss: 0.00020780562772415578
2023-01-23 04:53:58.346226: step: 1496/530, loss: 8.139610145008191e-05
2023-01-23 04:53:59.492549: step: 1500/530, loss: 0.0020116805098950863
2023-01-23 04:54:00.707482: step: 1504/530, loss: 0.03600320965051651
2023-01-23 04:54:01.880626: step: 1508/530, loss: 0.009292221628129482
2023-01-23 04:54:03.064378: step: 1512/530, loss: 0.0004786968056578189
2023-01-23 04:54:04.237710: step: 1516/530, loss: 0.019435741007328033
2023-01-23 04:54:05.389885: step: 1520/530, loss: 0.0002419471857137978
2023-01-23 04:54:06.570573: step: 1524/530, loss: 0.004563617520034313
2023-01-23 04:54:07.773188: step: 1528/530, loss: 0.04167766496539116
2023-01-23 04:54:08.926908: step: 1532/530, loss: 9.841918654274195e-05
2023-01-23 04:54:10.049641: step: 1536/530, loss: 0.00012369155592750758
2023-01-23 04:54:11.219199: step: 1540/530, loss: 0.0001038074551615864
2023-01-23 04:54:12.390756: step: 1544/530, loss: 0.08750343322753906
2023-01-23 04:54:13.568088: step: 1548/530, loss: 0.0005702972994185984
2023-01-23 04:54:14.782664: step: 1552/530, loss: 0.00012092590623069555
2023-01-23 04:54:15.963648: step: 1556/530, loss: 0.0005222320323809981
2023-01-23 04:54:17.118396: step: 1560/530, loss: 1.7547608877066523e-05
2023-01-23 04:54:18.246248: step: 1564/530, loss: 0.0005163192981854081
2023-01-23 04:54:19.411173: step: 1568/530, loss: 3.8814549043308944e-05
2023-01-23 04:54:20.529680: step: 1572/530, loss: 0.00011787414405262098
2023-01-23 04:54:21.688504: step: 1576/530, loss: 0.015435123816132545
2023-01-23 04:54:22.836703: step: 1580/530, loss: 0.0011412620078772306
2023-01-23 04:54:24.038708: step: 1584/530, loss: 0.07253475487232208
2023-01-23 04:54:25.220756: step: 1588/530, loss: 0.0007831574184820056
2023-01-23 04:54:26.348797: step: 1592/530, loss: 0.0033389092423021793
2023-01-23 04:54:27.506464: step: 1596/530, loss: 0.0004299163992982358
2023-01-23 04:54:28.722436: step: 1600/530, loss: 0.0006494522094726562
2023-01-23 04:54:29.904992: step: 1604/530, loss: 0.0002834320184774697
2023-01-23 04:54:31.071561: step: 1608/530, loss: 0.00012321471876930445
2023-01-23 04:54:32.271341: step: 1612/530, loss: 0.04742469638586044
2023-01-23 04:54:33.459217: step: 1616/530, loss: 0.000179290771484375
2023-01-23 04:54:34.587803: step: 1620/530, loss: 1.773834264895413e-05
2023-01-23 04:54:35.741620: step: 1624/530, loss: 0.08136377483606339
2023-01-23 04:54:36.885121: step: 1628/530, loss: 0.00038900377694517374
2023-01-23 04:54:38.081926: step: 1632/530, loss: 0.030256273224949837
2023-01-23 04:54:39.237442: step: 1636/530, loss: 0.0012609482510015368
2023-01-23 04:54:40.390381: step: 1640/530, loss: 0.003018951276317239
2023-01-23 04:54:41.553820: step: 1644/530, loss: 0.0014301299815997481
2023-01-23 04:54:42.818655: step: 1648/530, loss: 0.00031490327091887593
2023-01-23 04:54:43.980610: step: 1652/530, loss: 0.0003257751523051411
2023-01-23 04:54:45.114471: step: 1656/530, loss: 7.133484177757055e-05
2023-01-23 04:54:46.287112: step: 1660/530, loss: 0.0004219055117573589
2023-01-23 04:54:47.419092: step: 1664/530, loss: 0.039891913533210754
2023-01-23 04:54:48.681389: step: 1668/530, loss: 0.0017008304130285978
2023-01-23 04:54:49.877511: step: 1672/530, loss: 0.02526683919131756
2023-01-23 04:54:51.043752: step: 1676/530, loss: 2.4271012080134824e-05
2023-01-23 04:54:52.196076: step: 1680/530, loss: 8.640289161121473e-05
2023-01-23 04:54:53.331580: step: 1684/530, loss: 0.00032749175443314016
2023-01-23 04:54:54.525997: step: 1688/530, loss: 2.326965295651462e-05
2023-01-23 04:54:55.724885: step: 1692/530, loss: 0.006415272131562233
2023-01-23 04:54:56.869634: step: 1696/530, loss: 0.0003487110079731792
2023-01-23 04:54:58.062325: step: 1700/530, loss: 2.9850007194909267e-05
2023-01-23 04:54:59.224548: step: 1704/530, loss: 0.01628255844116211
2023-01-23 04:55:00.400068: step: 1708/530, loss: 0.048612214624881744
2023-01-23 04:55:01.565355: step: 1712/530, loss: 2.3412703740177676e-05
2023-01-23 04:55:02.740529: step: 1716/530, loss: 0.00526504497975111
2023-01-23 04:55:03.921938: step: 1720/530, loss: 0.00026836394681595266
2023-01-23 04:55:05.104143: step: 1724/530, loss: 0.0010107040870934725
2023-01-23 04:55:06.260228: step: 1728/530, loss: 0.007612800691276789
2023-01-23 04:55:07.386814: step: 1732/530, loss: 2.47955322265625e-05
2023-01-23 04:55:08.568577: step: 1736/530, loss: 9.117126319324598e-05
2023-01-23 04:55:09.749594: step: 1740/530, loss: 0.0017866134876385331
2023-01-23 04:55:10.938198: step: 1744/530, loss: 0.013206672854721546
2023-01-23 04:55:12.135299: step: 1748/530, loss: 1.144409225162235e-06
2023-01-23 04:55:13.326310: step: 1752/530, loss: 1.506805438111769e-05
2023-01-23 04:55:14.478470: step: 1756/530, loss: 1.8215179807157256e-05
2023-01-23 04:55:15.658826: step: 1760/530, loss: 0.000735855137463659
2023-01-23 04:55:16.819228: step: 1764/530, loss: 5.702972339349799e-05
2023-01-23 04:55:17.996766: step: 1768/530, loss: 0.031631093472242355
2023-01-23 04:55:19.175819: step: 1772/530, loss: 0.029294490814208984
2023-01-23 04:55:20.338216: step: 1776/530, loss: 0.040686845779418945
2023-01-23 04:55:21.462408: step: 1780/530, loss: 5.6934357417048886e-05
2023-01-23 04:55:22.622520: step: 1784/530, loss: 0.022653676569461823
2023-01-23 04:55:23.827059: step: 1788/530, loss: 0.0002642631297931075
2023-01-23 04:55:24.947639: step: 1792/530, loss: 0.006672334857285023
2023-01-23 04:55:26.095175: step: 1796/530, loss: 0.041307639330625534
2023-01-23 04:55:27.277677: step: 1800/530, loss: 0.0008560181013308465
2023-01-23 04:55:28.422303: step: 1804/530, loss: 4.911423093290068e-05
2023-01-23 04:55:29.615081: step: 1808/530, loss: 4.0531158447265625e-06
2023-01-23 04:55:30.792573: step: 1812/530, loss: 0.002923965686932206
2023-01-23 04:55:31.972552: step: 1816/530, loss: 0.00022010803513694555
2023-01-23 04:55:33.115000: step: 1820/530, loss: 0.052977368235588074
2023-01-23 04:55:34.266182: step: 1824/530, loss: 6.29425048828125e-05
2023-01-23 04:55:35.432608: step: 1828/530, loss: 0.04450187832117081
2023-01-23 04:55:36.609648: step: 1832/530, loss: 0.0009071350796148181
2023-01-23 04:55:37.790399: step: 1836/530, loss: 0.005719495005905628
2023-01-23 04:55:38.965845: step: 1840/530, loss: 0.0035389901604503393
2023-01-23 04:55:40.129318: step: 1844/530, loss: 0.00225582136772573
2023-01-23 04:55:41.302073: step: 1848/530, loss: 0.00020542144193314016
2023-01-23 04:55:42.487094: step: 1852/530, loss: 0.0027408599853515625
2023-01-23 04:55:43.662989: step: 1856/530, loss: -0.0
2023-01-23 04:55:44.868853: step: 1860/530, loss: 0.0010612488258630037
2023-01-23 04:55:46.034552: step: 1864/530, loss: 0.0031875609420239925
2023-01-23 04:55:47.299888: step: 1868/530, loss: 0.024716569110751152
2023-01-23 04:55:48.459374: step: 1872/530, loss: 0.003655815264210105
2023-01-23 04:55:49.647236: step: 1876/530, loss: 0.0016331672668457031
2023-01-23 04:55:50.808529: step: 1880/530, loss: 0.0018974303966388106
2023-01-23 04:55:51.974943: step: 1884/530, loss: 0.0013987065758556128
2023-01-23 04:55:53.159932: step: 1888/530, loss: 0.0005106925964355469
2023-01-23 04:55:54.371147: step: 1892/530, loss: -1.392364538332913e-05
2023-01-23 04:55:55.509441: step: 1896/530, loss: 0.00018005371384788305
2023-01-23 04:55:56.700911: step: 1900/530, loss: 0.01983346976339817
2023-01-23 04:55:57.927262: step: 1904/530, loss: 5.8460234868107364e-05
2023-01-23 04:55:59.153563: step: 1908/530, loss: -2.708435022213962e-05
2023-01-23 04:56:00.324885: step: 1912/530, loss: 0.0031436921562999487
2023-01-23 04:56:01.508191: step: 1916/530, loss: 0.03290868178009987
2023-01-23 04:56:02.720581: step: 1920/530, loss: 0.03983325883746147
2023-01-23 04:56:03.873890: step: 1924/530, loss: 0.010126017965376377
2023-01-23 04:56:05.034682: step: 1928/530, loss: 0.01784348487854004
2023-01-23 04:56:06.228975: step: 1932/530, loss: 0.012363815680146217
2023-01-23 04:56:07.391286: step: 1936/530, loss: 0.0004967689164914191
2023-01-23 04:56:08.552953: step: 1940/530, loss: 0.0001873016299214214
2023-01-23 04:56:09.740183: step: 1944/530, loss: 0.0019415856804698706
2023-01-23 04:56:10.897323: step: 1948/530, loss: 9.298324584960938e-05
2023-01-23 04:56:12.078567: step: 1952/530, loss: 5.683898780262098e-05
2023-01-23 04:56:13.222589: step: 1956/530, loss: 0.00019340515427757055
2023-01-23 04:56:14.350268: step: 1960/530, loss: 0.030147897079586983
2023-01-23 04:56:15.546436: step: 1964/530, loss: 0.07901906967163086
2023-01-23 04:56:16.717044: step: 1968/530, loss: 0.0003911018429789692
2023-01-23 04:56:17.911862: step: 1972/530, loss: 0.00030362606048583984
2023-01-23 04:56:19.070619: step: 1976/530, loss: 0.04544582590460777
2023-01-23 04:56:20.214200: step: 1980/530, loss: 0.0032825469970703125
2023-01-23 04:56:21.351399: step: 1984/530, loss: 0.043270111083984375
2023-01-23 04:56:22.549204: step: 1988/530, loss: 7.801055471645668e-05
2023-01-23 04:56:23.737348: step: 1992/530, loss: 0.03510646894574165
2023-01-23 04:56:24.900500: step: 1996/530, loss: 0.0034122467041015625
2023-01-23 04:56:26.072403: step: 2000/530, loss: 0.0005594253307208419
2023-01-23 04:56:27.231885: step: 2004/530, loss: 5.493163916980848e-05
2023-01-23 04:56:28.400364: step: 2008/530, loss: 2.1457672119140625e-06
2023-01-23 04:56:29.573508: step: 2012/530, loss: 0.047719959169626236
2023-01-23 04:56:30.697929: step: 2016/530, loss: 0.00013847350783180445
2023-01-23 04:56:31.839780: step: 2020/530, loss: 7.762909081066027e-05
2023-01-23 04:56:32.972248: step: 2024/530, loss: 0.00016536712064407766
2023-01-23 04:56:34.144411: step: 2028/530, loss: 0.00013652147026732564
2023-01-23 04:56:35.308975: step: 2032/530, loss: 0.000762939453125
2023-01-23 04:56:36.491747: step: 2036/530, loss: -1.811981746868696e-06
2023-01-23 04:56:37.658520: step: 2040/530, loss: 9.241103543899953e-05
2023-01-23 04:56:38.848990: step: 2044/530, loss: 0.005942249670624733
2023-01-23 04:56:39.994409: step: 2048/530, loss: 0.0001508712739450857
2023-01-23 04:56:41.205995: step: 2052/530, loss: 0.04231433942914009
2023-01-23 04:56:42.380157: step: 2056/530, loss: 0.0025626658461987972
2023-01-23 04:56:43.581504: step: 2060/530, loss: 0.017107581719756126
2023-01-23 04:56:44.760893: step: 2064/530, loss: 0.0030672072898596525
2023-01-23 04:56:45.907714: step: 2068/530, loss: 0.4188602566719055
2023-01-23 04:56:47.067056: step: 2072/530, loss: -9.536742595628311e-08
2023-01-23 04:56:48.270794: step: 2076/530, loss: 5.302429053699598e-05
2023-01-23 04:56:49.436888: step: 2080/530, loss: 0.5609552264213562
2023-01-23 04:56:50.609441: step: 2084/530, loss: 0.026812173426151276
2023-01-23 04:56:51.800486: step: 2088/530, loss: 0.006197548005729914
2023-01-23 04:56:52.910079: step: 2092/530, loss: 8.668899681651965e-05
2023-01-23 04:56:54.090931: step: 2096/530, loss: 0.05037679523229599
2023-01-23 04:56:55.274349: step: 2100/530, loss: 1.711845470708795e-05
2023-01-23 04:56:56.474445: step: 2104/530, loss: 7.62939453125e-06
2023-01-23 04:56:57.632406: step: 2108/530, loss: 1.287460349885805e-06
2023-01-23 04:56:58.812415: step: 2112/530, loss: -1.716613724056515e-06
2023-01-23 04:56:59.989914: step: 2116/530, loss: 0.0001663207949604839
2023-01-23 04:57:01.168562: step: 2120/530, loss: 0.02290496975183487
==================================================
Loss: 0.012
--------------------
Dev: {'event': {'p': 0.6156316916488223, 'r': 0.7656458055925432, 'f1': 0.6824925816023738}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 29}
Test: {'event': {'p': 0.6636665087636191, 'r': 0.8056354226566993, 'f1': 0.7277922077922078}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 29}
Chinese: {'event': {'p': 0.550561797752809, 'r': 0.9074074074074074, 'f1': 0.6853146853146853}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 29}
Korean: {'event': {'p': 0.6666666666666666, 'r': 0.47619047619047616, 'f1': 0.5555555555555556}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 29}
Russian: {'event': {'p': 0.37777777777777777, 'r': 0.4722222222222222, 'f1': 0.4197530864197531}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 29}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.603537981269511, 'r': 0.7723035952063915, 'f1': 0.677570093457944}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Eng Test for Chinese: {'event': {'p': 0.6663560111835974, 'r': 0.8223116733755031, 'f1': 0.7361647361647363}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Sample Chinese: {'event': {'p': 0.611764705882353, 'r': 0.9629629629629629, 'f1': 0.748201438848921}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5733990147783251, 'r': 0.7749667110519307, 'f1': 0.6591166477916196}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Eng Test for Korean: {'event': {'p': 0.6218005295675199, 'r': 0.8102357676825762, 'f1': 0.7036204744069912}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Sample Korean: {'event': {'p': 0.6417910447761194, 'r': 0.6825396825396826, 'f1': 0.6615384615384614}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6284796573875803, 'r': 0.7816245006657789, 'f1': 0.6967359050445103}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Eng Test for Russian: {'event': {'p': 0.6768263183357524, 'r': 0.80448533640023, 'f1': 0.7351550183920126}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Sample Russian: {'event': {'p': 0.4791666666666667, 'r': 0.6388888888888888, 'f1': 0.5476190476190476}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}