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 23:23:13.039655: step: 4/530, loss: 3.8247714042663574
2023-01-22 23:23:14.153403: step: 8/530, loss: 23.67460060119629
2023-01-22 23:23:15.281510: step: 12/530, loss: 7.792829990386963
2023-01-22 23:23:16.417197: step: 16/530, loss: 4.223147869110107
2023-01-22 23:23:17.506797: step: 20/530, loss: 2.8740739822387695
2023-01-22 23:23:18.598384: step: 24/530, loss: 3.734103202819824
2023-01-22 23:23:19.699688: step: 28/530, loss: 12.453813552856445
2023-01-22 23:23:20.807635: step: 32/530, loss: 14.550145149230957
2023-01-22 23:23:21.917636: step: 36/530, loss: 11.228058815002441
2023-01-22 23:23:22.999588: step: 40/530, loss: 5.496736526489258
2023-01-22 23:23:24.115482: step: 44/530, loss: 4.227232933044434
2023-01-22 23:23:25.243090: step: 48/530, loss: 16.84233283996582
2023-01-22 23:23:26.369214: step: 52/530, loss: 5.055027961730957
2023-01-22 23:23:27.465864: step: 56/530, loss: 3.682136058807373
2023-01-22 23:23:28.580687: step: 60/530, loss: 3.2572784423828125
2023-01-22 23:23:29.695097: step: 64/530, loss: 23.948823928833008
2023-01-22 23:23:30.811159: step: 68/530, loss: 20.843276977539062
2023-01-22 23:23:31.902221: step: 72/530, loss: 4.5136613845825195
2023-01-22 23:23:32.994031: step: 76/530, loss: 2.308722496032715
2023-01-22 23:23:34.096220: step: 80/530, loss: 2.8275487422943115
2023-01-22 23:23:35.224301: step: 84/530, loss: 2.968357563018799
2023-01-22 23:23:36.338298: step: 88/530, loss: 11.509078979492188
2023-01-22 23:23:37.425414: step: 92/530, loss: 3.8847250938415527
2023-01-22 23:23:38.550226: step: 96/530, loss: 9.048340797424316
2023-01-22 23:23:39.636393: step: 100/530, loss: 2.91939640045166
2023-01-22 23:23:40.749176: step: 104/530, loss: 14.225627899169922
2023-01-22 23:23:41.873190: step: 108/530, loss: 14.548890113830566
2023-01-22 23:23:42.975549: step: 112/530, loss: 3.8967552185058594
2023-01-22 23:23:44.077500: step: 116/530, loss: 3.956684112548828
2023-01-22 23:23:45.176508: step: 120/530, loss: 15.386672973632812
2023-01-22 23:23:46.319971: step: 124/530, loss: 2.935511589050293
2023-01-22 23:23:47.410161: step: 128/530, loss: 18.256500244140625
2023-01-22 23:23:48.512299: step: 132/530, loss: 17.10557746887207
2023-01-22 23:23:49.609720: step: 136/530, loss: 15.099573135375977
2023-01-22 23:23:50.723153: step: 140/530, loss: 13.445436477661133
2023-01-22 23:23:51.813037: step: 144/530, loss: 7.539018630981445
2023-01-22 23:23:52.943097: step: 148/530, loss: 4.33933162689209
2023-01-22 23:23:54.064866: step: 152/530, loss: 3.9608230590820312
2023-01-22 23:23:55.185541: step: 156/530, loss: 18.758262634277344
2023-01-22 23:23:56.292923: step: 160/530, loss: 8.985645294189453
2023-01-22 23:23:57.399299: step: 164/530, loss: 2.8852083683013916
2023-01-22 23:23:58.506533: step: 168/530, loss: 11.083765983581543
2023-01-22 23:23:59.624302: step: 172/530, loss: 43.80861282348633
2023-01-22 23:24:00.719008: step: 176/530, loss: 11.351310729980469
2023-01-22 23:24:01.825237: step: 180/530, loss: 4.1110429763793945
2023-01-22 23:24:02.941984: step: 184/530, loss: 32.73598098754883
2023-01-22 23:24:04.058078: step: 188/530, loss: 4.337249279022217
2023-01-22 23:24:05.161909: step: 192/530, loss: 3.4171199798583984
2023-01-22 23:24:06.255571: step: 196/530, loss: 2.5224828720092773
2023-01-22 23:24:07.355126: step: 200/530, loss: 20.38568878173828
2023-01-22 23:24:08.472858: step: 204/530, loss: 26.72294044494629
2023-01-22 23:24:09.588027: step: 208/530, loss: 19.891393661499023
2023-01-22 23:24:10.723737: step: 212/530, loss: 30.0582275390625
2023-01-22 23:24:11.839912: step: 216/530, loss: 19.12263298034668
2023-01-22 23:24:12.961174: step: 220/530, loss: 6.009547710418701
2023-01-22 23:24:14.079082: step: 224/530, loss: 11.162466049194336
2023-01-22 23:24:15.199173: step: 228/530, loss: 4.6891913414001465
2023-01-22 23:24:16.286591: step: 232/530, loss: 2.2201602458953857
2023-01-22 23:24:17.406309: step: 236/530, loss: 7.960633277893066
2023-01-22 23:24:18.491127: step: 240/530, loss: 11.456367492675781
2023-01-22 23:24:19.584809: step: 244/530, loss: 14.501708984375
2023-01-22 23:24:20.707823: step: 248/530, loss: 3.6611335277557373
2023-01-22 23:24:21.771716: step: 252/530, loss: 2.475947380065918
2023-01-22 23:24:22.856478: step: 256/530, loss: 3.2388885021209717
2023-01-22 23:24:23.984127: step: 260/530, loss: 27.763608932495117
2023-01-22 23:24:25.088095: step: 264/530, loss: 18.940582275390625
2023-01-22 23:24:26.192413: step: 268/530, loss: 3.1587743759155273
2023-01-22 23:24:27.331292: step: 272/530, loss: 3.3968143463134766
2023-01-22 23:24:28.437022: step: 276/530, loss: 3.409374713897705
2023-01-22 23:24:29.555135: step: 280/530, loss: 2.417004108428955
2023-01-22 23:24:30.653084: step: 284/530, loss: 16.142274856567383
2023-01-22 23:24:31.749955: step: 288/530, loss: 3.892843246459961
2023-01-22 23:24:32.863959: step: 292/530, loss: 33.742530822753906
2023-01-22 23:24:33.960764: step: 296/530, loss: 2.62148380279541
2023-01-22 23:24:35.074864: step: 300/530, loss: 3.6804006099700928
2023-01-22 23:24:36.174699: step: 304/530, loss: 15.33167839050293
2023-01-22 23:24:37.277231: step: 308/530, loss: 10.790513038635254
2023-01-22 23:24:38.390872: step: 312/530, loss: 26.385334014892578
2023-01-22 23:24:39.497871: step: 316/530, loss: 3.1453404426574707
2023-01-22 23:24:40.606991: step: 320/530, loss: 12.452153205871582
2023-01-22 23:24:41.721222: step: 324/530, loss: 7.401740074157715
2023-01-22 23:24:42.824932: step: 328/530, loss: 3.147793769836426
2023-01-22 23:24:43.938824: step: 332/530, loss: 2.480666399002075
2023-01-22 23:24:45.050231: step: 336/530, loss: 23.008018493652344
2023-01-22 23:24:46.172291: step: 340/530, loss: 3.5525450706481934
2023-01-22 23:24:47.281127: step: 344/530, loss: 7.9330573081970215
2023-01-22 23:24:48.395226: step: 348/530, loss: 16.135713577270508
2023-01-22 23:24:49.517826: step: 352/530, loss: 23.471017837524414
2023-01-22 23:24:50.611785: step: 356/530, loss: 3.0813751220703125
2023-01-22 23:24:51.715706: step: 360/530, loss: 11.863367080688477
2023-01-22 23:24:52.825952: step: 364/530, loss: 10.527448654174805
2023-01-22 23:24:53.952348: step: 368/530, loss: 3.463357925415039
2023-01-22 23:24:55.072220: step: 372/530, loss: 2.7780189514160156
2023-01-22 23:24:56.168105: step: 376/530, loss: 14.865715980529785
2023-01-22 23:24:57.283112: step: 380/530, loss: 10.684891700744629
2023-01-22 23:24:58.371497: step: 384/530, loss: 7.3157548904418945
2023-01-22 23:24:59.465401: step: 388/530, loss: 2.45033597946167
2023-01-22 23:25:00.581311: step: 392/530, loss: 11.809349060058594
2023-01-22 23:25:01.708756: step: 396/530, loss: 42.17725372314453
2023-01-22 23:25:02.864753: step: 400/530, loss: 3.670440912246704
2023-01-22 23:25:03.968778: step: 404/530, loss: 18.743728637695312
2023-01-22 23:25:05.099106: step: 408/530, loss: 10.496770858764648
2023-01-22 23:25:06.213858: step: 412/530, loss: 8.040962219238281
2023-01-22 23:25:07.319245: step: 416/530, loss: 8.307551383972168
2023-01-22 23:25:08.408708: step: 420/530, loss: 2.8908748626708984
2023-01-22 23:25:09.504493: step: 424/530, loss: 2.5674121379852295
2023-01-22 23:25:10.614365: step: 428/530, loss: 6.737289905548096
2023-01-22 23:25:11.719438: step: 432/530, loss: 3.182615280151367
2023-01-22 23:25:12.861454: step: 436/530, loss: 2.5280990600585938
2023-01-22 23:25:13.943542: step: 440/530, loss: 0.8647371530532837
2023-01-22 23:25:15.056390: step: 444/530, loss: 3.473031997680664
2023-01-22 23:25:16.163392: step: 448/530, loss: 19.18760108947754
2023-01-22 23:25:17.309043: step: 452/530, loss: 21.098207473754883
2023-01-22 23:25:18.419519: step: 456/530, loss: 8.163414001464844
2023-01-22 23:25:19.521540: step: 460/530, loss: 2.3193511962890625
2023-01-22 23:25:20.655220: step: 464/530, loss: 13.555221557617188
2023-01-22 23:25:21.748162: step: 468/530, loss: 5.614279747009277
2023-01-22 23:25:22.864686: step: 472/530, loss: 0.9741687774658203
2023-01-22 23:25:23.983611: step: 476/530, loss: 10.289423942565918
2023-01-22 23:25:25.072291: step: 480/530, loss: 2.3159141540527344
2023-01-22 23:25:26.233392: step: 484/530, loss: 22.161727905273438
2023-01-22 23:25:27.318300: step: 488/530, loss: 6.443577289581299
2023-01-22 23:25:28.425904: step: 492/530, loss: 8.419048309326172
2023-01-22 23:25:29.519181: step: 496/530, loss: 14.569345474243164
2023-01-22 23:25:30.623975: step: 500/530, loss: 4.437444686889648
2023-01-22 23:25:31.745634: step: 504/530, loss: 9.023085594177246
2023-01-22 23:25:32.838547: step: 508/530, loss: 1.7570666074752808
2023-01-22 23:25:33.958598: step: 512/530, loss: 1.242442011833191
2023-01-22 23:25:35.059090: step: 516/530, loss: 2.1309428215026855
2023-01-22 23:25:36.224374: step: 520/530, loss: 11.416577339172363
2023-01-22 23:25:37.336320: step: 524/530, loss: 1.3897480964660645
2023-01-22 23:25:38.438044: step: 528/530, loss: 0.7908315658569336
2023-01-22 23:25:39.522503: step: 532/530, loss: 5.504734992980957
2023-01-22 23:25:40.642787: step: 536/530, loss: 7.440115451812744
2023-01-22 23:25:41.719656: step: 540/530, loss: 5.421571731567383
2023-01-22 23:25:42.845618: step: 544/530, loss: 1.9857515096664429
2023-01-22 23:25:43.950161: step: 548/530, loss: 5.138154983520508
2023-01-22 23:25:45.061516: step: 552/530, loss: 7.50291109085083
2023-01-22 23:25:46.180937: step: 556/530, loss: 5.5284423828125
2023-01-22 23:25:47.284834: step: 560/530, loss: 0.5684511661529541
2023-01-22 23:25:48.421813: step: 564/530, loss: 1.676917552947998
2023-01-22 23:25:49.547801: step: 568/530, loss: 3.98514986038208
2023-01-22 23:25:50.640921: step: 572/530, loss: 3.480156183242798
2023-01-22 23:25:51.761051: step: 576/530, loss: 1.4299927949905396
2023-01-22 23:25:52.854772: step: 580/530, loss: 1.1517208814620972
2023-01-22 23:25:53.982428: step: 584/530, loss: 1.609199047088623
2023-01-22 23:25:55.100893: step: 588/530, loss: 4.33005428314209
2023-01-22 23:25:56.151802: step: 592/530, loss: 1.8189414739608765
2023-01-22 23:25:57.259856: step: 596/530, loss: 1.275876760482788
2023-01-22 23:25:58.412164: step: 600/530, loss: 1.5633254051208496
2023-01-22 23:25:59.525325: step: 604/530, loss: 1.5762386322021484
2023-01-22 23:26:00.632400: step: 608/530, loss: 1.553145170211792
2023-01-22 23:26:01.720138: step: 612/530, loss: 0.8412739038467407
2023-01-22 23:26:02.819148: step: 616/530, loss: 12.081649780273438
2023-01-22 23:26:03.940160: step: 620/530, loss: 2.5497283935546875
2023-01-22 23:26:05.047382: step: 624/530, loss: 1.0212419033050537
2023-01-22 23:26:06.155348: step: 628/530, loss: 1.2420941591262817
2023-01-22 23:26:07.273660: step: 632/530, loss: 2.6803927421569824
2023-01-22 23:26:08.369699: step: 636/530, loss: 1.0779914855957031
2023-01-22 23:26:09.444834: step: 640/530, loss: 2.8131189346313477
2023-01-22 23:26:10.560395: step: 644/530, loss: 0.6291118860244751
2023-01-22 23:26:11.648017: step: 648/530, loss: 0.5420863628387451
2023-01-22 23:26:12.758479: step: 652/530, loss: 1.374135136604309
2023-01-22 23:26:13.862787: step: 656/530, loss: 1.1891915798187256
2023-01-22 23:26:14.964595: step: 660/530, loss: 1.52848482131958
2023-01-22 23:26:16.059990: step: 664/530, loss: 0.4244338870048523
2023-01-22 23:26:17.177648: step: 668/530, loss: 2.2306554317474365
2023-01-22 23:26:18.273805: step: 672/530, loss: 1.2155712842941284
2023-01-22 23:26:19.400800: step: 676/530, loss: 5.540233612060547
2023-01-22 23:26:20.502153: step: 680/530, loss: 2.3425376415252686
2023-01-22 23:26:21.614355: step: 684/530, loss: 4.238117218017578
2023-01-22 23:26:22.706435: step: 688/530, loss: 3.1852188110351562
2023-01-22 23:26:23.796740: step: 692/530, loss: 1.182296633720398
2023-01-22 23:26:24.909673: step: 696/530, loss: 0.5667551159858704
2023-01-22 23:26:26.063900: step: 700/530, loss: 0.7019741535186768
2023-01-22 23:26:27.171275: step: 704/530, loss: 2.8834035396575928
2023-01-22 23:26:28.278804: step: 708/530, loss: 0.7900824546813965
2023-01-22 23:26:29.405954: step: 712/530, loss: 0.6206392049789429
2023-01-22 23:26:30.524219: step: 716/530, loss: 0.850639283657074
2023-01-22 23:26:31.635734: step: 720/530, loss: 1.5720481872558594
2023-01-22 23:26:32.739178: step: 724/530, loss: 1.7020812034606934
2023-01-22 23:26:33.850058: step: 728/530, loss: 2.5883989334106445
2023-01-22 23:26:34.947887: step: 732/530, loss: 0.4605291485786438
2023-01-22 23:26:36.073034: step: 736/530, loss: 2.860867500305176
2023-01-22 23:26:37.198438: step: 740/530, loss: 0.6037940979003906
2023-01-22 23:26:38.325572: step: 744/530, loss: 0.5121645331382751
2023-01-22 23:26:39.416784: step: 748/530, loss: 0.8227473497390747
2023-01-22 23:26:40.539249: step: 752/530, loss: 1.8856215476989746
2023-01-22 23:26:41.652998: step: 756/530, loss: 3.2209324836730957
2023-01-22 23:26:42.787062: step: 760/530, loss: 1.5242799520492554
2023-01-22 23:26:43.912014: step: 764/530, loss: 1.6156655550003052
2023-01-22 23:26:45.083997: step: 768/530, loss: 7.142295837402344
2023-01-22 23:26:46.188851: step: 772/530, loss: 2.956252098083496
2023-01-22 23:26:47.277732: step: 776/530, loss: 2.57435941696167
2023-01-22 23:26:48.365099: step: 780/530, loss: 2.185138702392578
2023-01-22 23:26:49.469878: step: 784/530, loss: 1.475036382675171
2023-01-22 23:26:50.573417: step: 788/530, loss: 3.275002956390381
2023-01-22 23:26:51.665009: step: 792/530, loss: 0.53302001953125
2023-01-22 23:26:52.796570: step: 796/530, loss: 1.1679275035858154
2023-01-22 23:26:53.906638: step: 800/530, loss: 1.7728608846664429
2023-01-22 23:26:55.010700: step: 804/530, loss: 1.7904905080795288
2023-01-22 23:26:56.133910: step: 808/530, loss: 0.435213565826416
2023-01-22 23:26:57.256470: step: 812/530, loss: 1.6923174858093262
2023-01-22 23:26:58.363673: step: 816/530, loss: 1.0787800550460815
2023-01-22 23:26:59.475808: step: 820/530, loss: 1.5630905628204346
2023-01-22 23:27:00.572015: step: 824/530, loss: 1.8154237270355225
2023-01-22 23:27:01.687319: step: 828/530, loss: 1.0555299520492554
2023-01-22 23:27:02.795141: step: 832/530, loss: 0.30740228295326233
2023-01-22 23:27:03.966234: step: 836/530, loss: 1.428336501121521
2023-01-22 23:27:05.071180: step: 840/530, loss: 0.840860903263092
2023-01-22 23:27:06.167395: step: 844/530, loss: 1.2396767139434814
2023-01-22 23:27:07.287082: step: 848/530, loss: 3.9791877269744873
2023-01-22 23:27:08.374945: step: 852/530, loss: 0.35215941071510315
2023-01-22 23:27:09.475728: step: 856/530, loss: 0.6679888963699341
2023-01-22 23:27:10.573309: step: 860/530, loss: 0.9668667912483215
2023-01-22 23:27:11.695956: step: 864/530, loss: 1.4698896408081055
2023-01-22 23:27:12.776731: step: 868/530, loss: 0.9979019165039062
2023-01-22 23:27:13.897985: step: 872/530, loss: 1.2002317905426025
2023-01-22 23:27:14.995606: step: 876/530, loss: 1.027078628540039
2023-01-22 23:27:16.140350: step: 880/530, loss: 0.4487758278846741
2023-01-22 23:27:17.268061: step: 884/530, loss: 0.6453434228897095
2023-01-22 23:27:18.393447: step: 888/530, loss: 2.2120256423950195
2023-01-22 23:27:19.489242: step: 892/530, loss: 0.8503849506378174
2023-01-22 23:27:20.583395: step: 896/530, loss: 0.8715493679046631
2023-01-22 23:27:21.679098: step: 900/530, loss: 1.0814640522003174
2023-01-22 23:27:22.821152: step: 904/530, loss: 1.3172224760055542
2023-01-22 23:27:23.918378: step: 908/530, loss: 1.3666542768478394
2023-01-22 23:27:25.015546: step: 912/530, loss: 0.5948504209518433
2023-01-22 23:27:26.137172: step: 916/530, loss: 0.663577675819397
2023-01-22 23:27:27.234272: step: 920/530, loss: 1.9897325038909912
2023-01-22 23:27:28.347148: step: 924/530, loss: 3.843177318572998
2023-01-22 23:27:29.463608: step: 928/530, loss: 0.59805828332901
2023-01-22 23:27:30.579167: step: 932/530, loss: 1.1364173889160156
2023-01-22 23:27:31.698075: step: 936/530, loss: 0.4614202380180359
2023-01-22 23:27:32.802354: step: 940/530, loss: 0.9006638526916504
2023-01-22 23:27:33.909429: step: 944/530, loss: 0.7295122146606445
2023-01-22 23:27:34.999018: step: 948/530, loss: 0.6285088658332825
2023-01-22 23:27:36.110230: step: 952/530, loss: 3.0079128742218018
2023-01-22 23:27:37.216814: step: 956/530, loss: 2.412795305252075
2023-01-22 23:27:38.305594: step: 960/530, loss: 1.062082052230835
2023-01-22 23:27:39.433868: step: 964/530, loss: 7.645524501800537
2023-01-22 23:27:40.527624: step: 968/530, loss: 1.0616767406463623
2023-01-22 23:27:41.650318: step: 972/530, loss: 0.529765248298645
2023-01-22 23:27:42.834278: step: 976/530, loss: 1.302058458328247
2023-01-22 23:27:43.943147: step: 980/530, loss: 0.21375632286071777
2023-01-22 23:27:45.046255: step: 984/530, loss: 0.5772824287414551
2023-01-22 23:27:46.148946: step: 988/530, loss: 1.480478286743164
2023-01-22 23:27:47.272758: step: 992/530, loss: 0.9834421873092651
2023-01-22 23:27:48.370407: step: 996/530, loss: 0.579673707485199
2023-01-22 23:27:49.460427: step: 1000/530, loss: 0.3045511841773987
2023-01-22 23:27:50.573189: step: 1004/530, loss: 0.25266918540000916
2023-01-22 23:27:51.706316: step: 1008/530, loss: 10.320324897766113
2023-01-22 23:27:52.807269: step: 1012/530, loss: 3.3231372833251953
2023-01-22 23:27:53.901580: step: 1016/530, loss: 0.40265029668807983
2023-01-22 23:27:54.985409: step: 1020/530, loss: 2.4831089973449707
2023-01-22 23:27:56.103167: step: 1024/530, loss: 1.7501744031906128
2023-01-22 23:27:57.189177: step: 1028/530, loss: 3.6602187156677246
2023-01-22 23:27:58.306281: step: 1032/530, loss: 0.7583255767822266
2023-01-22 23:27:59.431336: step: 1036/530, loss: 3.5173087120056152
2023-01-22 23:28:00.525226: step: 1040/530, loss: 0.5259652137756348
2023-01-22 23:28:01.615477: step: 1044/530, loss: 0.4828094244003296
2023-01-22 23:28:02.712875: step: 1048/530, loss: 2.1581530570983887
2023-01-22 23:28:03.831416: step: 1052/530, loss: 1.682107925415039
2023-01-22 23:28:04.959943: step: 1056/530, loss: 5.119508266448975
2023-01-22 23:28:06.080215: step: 1060/530, loss: 1.1785764694213867
2023-01-22 23:28:07.179454: step: 1064/530, loss: 3.040731906890869
2023-01-22 23:28:08.289480: step: 1068/530, loss: 1.6753065586090088
2023-01-22 23:28:09.379918: step: 1072/530, loss: 1.3754546642303467
2023-01-22 23:28:10.489095: step: 1076/530, loss: 0.8640093803405762
2023-01-22 23:28:11.648403: step: 1080/530, loss: 2.893430471420288
2023-01-22 23:28:12.737726: step: 1084/530, loss: 0.7830283045768738
2023-01-22 23:28:13.827910: step: 1088/530, loss: 2.3461999893188477
2023-01-22 23:28:14.930573: step: 1092/530, loss: 3.523620128631592
2023-01-22 23:28:16.041182: step: 1096/530, loss: 1.7385973930358887
2023-01-22 23:28:17.156755: step: 1100/530, loss: 1.2825385332107544
2023-01-22 23:28:18.329866: step: 1104/530, loss: 0.9041227698326111
2023-01-22 23:28:19.435384: step: 1108/530, loss: 1.1137878894805908
2023-01-22 23:28:20.555936: step: 1112/530, loss: 1.480239748954773
2023-01-22 23:28:21.645268: step: 1116/530, loss: 2.263979434967041
2023-01-22 23:28:22.718515: step: 1120/530, loss: 0.2563742697238922
2023-01-22 23:28:23.825717: step: 1124/530, loss: 1.25351083278656
2023-01-22 23:28:24.949701: step: 1128/530, loss: 0.672776997089386
2023-01-22 23:28:26.037574: step: 1132/530, loss: 0.7901431322097778
2023-01-22 23:28:27.145634: step: 1136/530, loss: 0.9601890444755554
2023-01-22 23:28:28.252137: step: 1140/530, loss: 0.2271064817905426
2023-01-22 23:28:29.366901: step: 1144/530, loss: 0.5148394107818604
2023-01-22 23:28:30.464376: step: 1148/530, loss: 0.6287330389022827
2023-01-22 23:28:31.590928: step: 1152/530, loss: 0.09950122982263565
2023-01-22 23:28:32.719653: step: 1156/530, loss: 1.6398297548294067
2023-01-22 23:28:33.834855: step: 1160/530, loss: 1.1630470752716064
2023-01-22 23:28:34.955825: step: 1164/530, loss: 2.411144733428955
2023-01-22 23:28:36.051862: step: 1168/530, loss: 0.42353355884552
2023-01-22 23:28:37.174253: step: 1172/530, loss: 0.9469929933547974
2023-01-22 23:28:38.297612: step: 1176/530, loss: 0.553544282913208
2023-01-22 23:28:39.426133: step: 1180/530, loss: 1.738619327545166
2023-01-22 23:28:40.525752: step: 1184/530, loss: 0.6206778883934021
2023-01-22 23:28:41.624037: step: 1188/530, loss: 0.3105440139770508
2023-01-22 23:28:42.760513: step: 1192/530, loss: 2.693908929824829
2023-01-22 23:28:43.848519: step: 1196/530, loss: 1.777593731880188
2023-01-22 23:28:44.933367: step: 1200/530, loss: 0.8583033084869385
2023-01-22 23:28:46.017842: step: 1204/530, loss: 2.3872568607330322
2023-01-22 23:28:47.113495: step: 1208/530, loss: 0.8927949666976929
2023-01-22 23:28:48.221826: step: 1212/530, loss: 3.0335655212402344
2023-01-22 23:28:49.327714: step: 1216/530, loss: 0.5857503414154053
2023-01-22 23:28:50.471744: step: 1220/530, loss: 0.6111335754394531
2023-01-22 23:28:51.541140: step: 1224/530, loss: 1.4603767395019531
2023-01-22 23:28:52.648522: step: 1228/530, loss: 1.1542656421661377
2023-01-22 23:28:53.762212: step: 1232/530, loss: 1.0547513961791992
2023-01-22 23:28:54.892253: step: 1236/530, loss: 0.9050506353378296
2023-01-22 23:28:55.998922: step: 1240/530, loss: 0.29006433486938477
2023-01-22 23:28:57.095588: step: 1244/530, loss: 0.9352859258651733
2023-01-22 23:28:58.215596: step: 1248/530, loss: 3.6817405223846436
2023-01-22 23:28:59.366064: step: 1252/530, loss: 1.9098585844039917
2023-01-22 23:29:00.466954: step: 1256/530, loss: 0.15108633041381836
2023-01-22 23:29:01.599124: step: 1260/530, loss: 0.7575054168701172
2023-01-22 23:29:02.717631: step: 1264/530, loss: 1.0700103044509888
2023-01-22 23:29:03.831506: step: 1268/530, loss: 0.9888304471969604
2023-01-22 23:29:04.954447: step: 1272/530, loss: 1.375380277633667
2023-01-22 23:29:06.057258: step: 1276/530, loss: 0.4859444499015808
2023-01-22 23:29:07.132137: step: 1280/530, loss: 1.3718180656433105
2023-01-22 23:29:08.212273: step: 1284/530, loss: 0.1925945281982422
2023-01-22 23:29:09.315092: step: 1288/530, loss: 3.917142868041992
2023-01-22 23:29:10.418759: step: 1292/530, loss: 1.2278058528900146
2023-01-22 23:29:11.510386: step: 1296/530, loss: 0.9864823222160339
2023-01-22 23:29:12.625561: step: 1300/530, loss: 1.3247333765029907
2023-01-22 23:29:13.714830: step: 1304/530, loss: 8.950865745544434
2023-01-22 23:29:14.816950: step: 1308/530, loss: 2.6282296180725098
2023-01-22 23:29:15.937394: step: 1312/530, loss: 1.0457541942596436
2023-01-22 23:29:17.026971: step: 1316/530, loss: 0.9159600734710693
2023-01-22 23:29:18.119284: step: 1320/530, loss: 0.482572078704834
2023-01-22 23:29:19.225508: step: 1324/530, loss: 0.6768025159835815
2023-01-22 23:29:20.342495: step: 1328/530, loss: 0.4802801012992859
2023-01-22 23:29:21.429649: step: 1332/530, loss: 1.5758532285690308
2023-01-22 23:29:22.527732: step: 1336/530, loss: 1.118682622909546
2023-01-22 23:29:23.613222: step: 1340/530, loss: 0.3925798237323761
2023-01-22 23:29:24.724974: step: 1344/530, loss: 0.8370621800422668
2023-01-22 23:29:25.810622: step: 1348/530, loss: 0.3212825357913971
2023-01-22 23:29:26.954916: step: 1352/530, loss: 1.6958136558532715
2023-01-22 23:29:28.076096: step: 1356/530, loss: 2.019230842590332
2023-01-22 23:29:29.212749: step: 1360/530, loss: 0.8408951163291931
2023-01-22 23:29:30.311874: step: 1364/530, loss: 0.3634986877441406
2023-01-22 23:29:31.417798: step: 1368/530, loss: 0.67097407579422
2023-01-22 23:29:32.515457: step: 1372/530, loss: 1.2005330324172974
2023-01-22 23:29:33.589176: step: 1376/530, loss: 2.2117621898651123
2023-01-22 23:29:34.671953: step: 1380/530, loss: 1.6814545392990112
2023-01-22 23:29:35.796236: step: 1384/530, loss: 1.991078495979309
2023-01-22 23:29:36.889178: step: 1388/530, loss: 0.7127151489257812
2023-01-22 23:29:38.018252: step: 1392/530, loss: 5.336414337158203
2023-01-22 23:29:39.122880: step: 1396/530, loss: 0.8501438498497009
2023-01-22 23:29:40.271198: step: 1400/530, loss: 0.3514707684516907
2023-01-22 23:29:41.404377: step: 1404/530, loss: 3.9994394779205322
2023-01-22 23:29:42.524819: step: 1408/530, loss: 1.231032371520996
2023-01-22 23:29:43.631175: step: 1412/530, loss: 0.8287548422813416
2023-01-22 23:29:44.729816: step: 1416/530, loss: 1.6837100982666016
2023-01-22 23:29:45.835874: step: 1420/530, loss: 0.3052191734313965
2023-01-22 23:29:46.925076: step: 1424/530, loss: 1.0436056852340698
2023-01-22 23:29:48.034971: step: 1428/530, loss: 2.4814023971557617
2023-01-22 23:29:49.143730: step: 1432/530, loss: 0.3525175154209137
2023-01-22 23:29:50.254716: step: 1436/530, loss: 0.3126464784145355
2023-01-22 23:29:51.340375: step: 1440/530, loss: 0.39958441257476807
2023-01-22 23:29:52.450465: step: 1444/530, loss: 1.7367284297943115
2023-01-22 23:29:53.547861: step: 1448/530, loss: 0.5831590890884399
2023-01-22 23:29:54.678157: step: 1452/530, loss: 0.615650475025177
2023-01-22 23:29:55.826615: step: 1456/530, loss: 1.6531391143798828
2023-01-22 23:29:56.929132: step: 1460/530, loss: 0.5343203544616699
2023-01-22 23:29:58.023677: step: 1464/530, loss: 0.47699472308158875
2023-01-22 23:29:59.134947: step: 1468/530, loss: 0.9981957674026489
2023-01-22 23:30:00.221194: step: 1472/530, loss: 1.7923558950424194
2023-01-22 23:30:01.327195: step: 1476/530, loss: 1.1693894863128662
2023-01-22 23:30:02.413619: step: 1480/530, loss: 0.795159101486206
2023-01-22 23:30:03.525130: step: 1484/530, loss: 0.5918500423431396
2023-01-22 23:30:04.600394: step: 1488/530, loss: 2.7539942264556885
2023-01-22 23:30:05.693654: step: 1492/530, loss: 1.7908340692520142
2023-01-22 23:30:06.831583: step: 1496/530, loss: 1.0554401874542236
2023-01-22 23:30:07.927655: step: 1500/530, loss: 0.699389636516571
2023-01-22 23:30:09.040435: step: 1504/530, loss: 0.32550257444381714
2023-01-22 23:30:10.119341: step: 1508/530, loss: 0.28601014614105225
2023-01-22 23:30:11.256173: step: 1512/530, loss: 0.612713634967804
2023-01-22 23:30:12.383485: step: 1516/530, loss: 0.392680287361145
2023-01-22 23:30:13.467171: step: 1520/530, loss: 0.40928196907043457
2023-01-22 23:30:14.563929: step: 1524/530, loss: 0.1674882024526596
2023-01-22 23:30:15.674066: step: 1528/530, loss: 3.099695920944214
2023-01-22 23:30:16.771911: step: 1532/530, loss: 1.3022334575653076
2023-01-22 23:30:17.868748: step: 1536/530, loss: 1.6655919551849365
2023-01-22 23:30:18.988557: step: 1540/530, loss: 0.5938438177108765
2023-01-22 23:30:20.085989: step: 1544/530, loss: 3.4514589309692383
2023-01-22 23:30:21.185581: step: 1548/530, loss: 0.3294870853424072
2023-01-22 23:30:22.301949: step: 1552/530, loss: 1.470881700515747
2023-01-22 23:30:23.387128: step: 1556/530, loss: 0.570382833480835
2023-01-22 23:30:24.495328: step: 1560/530, loss: 0.13573046028614044
2023-01-22 23:30:25.600217: step: 1564/530, loss: 0.5438030958175659
2023-01-22 23:30:26.696134: step: 1568/530, loss: 0.4118262231349945
2023-01-22 23:30:27.805488: step: 1572/530, loss: 0.6908621788024902
2023-01-22 23:30:28.916889: step: 1576/530, loss: 0.889116108417511
2023-01-22 23:30:30.022321: step: 1580/530, loss: 1.42928147315979
2023-01-22 23:30:31.131456: step: 1584/530, loss: 0.3483037054538727
2023-01-22 23:30:32.239285: step: 1588/530, loss: 0.8478102087974548
2023-01-22 23:30:33.353373: step: 1592/530, loss: 2.0233829021453857
2023-01-22 23:30:34.472316: step: 1596/530, loss: 0.46418219804763794
2023-01-22 23:30:35.577696: step: 1600/530, loss: 0.31813845038414
2023-01-22 23:30:36.697473: step: 1604/530, loss: 0.864906370639801
2023-01-22 23:30:37.785926: step: 1608/530, loss: 1.582698941230774
2023-01-22 23:30:38.907452: step: 1612/530, loss: 2.6298794746398926
2023-01-22 23:30:40.030029: step: 1616/530, loss: 0.48941707611083984
2023-01-22 23:30:41.143672: step: 1620/530, loss: 1.6487646102905273
2023-01-22 23:30:42.246330: step: 1624/530, loss: 0.34516072273254395
2023-01-22 23:30:43.341789: step: 1628/530, loss: 0.9980376958847046
2023-01-22 23:30:44.447591: step: 1632/530, loss: 0.4461982846260071
2023-01-22 23:30:45.536851: step: 1636/530, loss: 1.734879970550537
2023-01-22 23:30:46.631989: step: 1640/530, loss: 1.4458205699920654
2023-01-22 23:30:47.746970: step: 1644/530, loss: 0.5368051528930664
2023-01-22 23:30:48.849404: step: 1648/530, loss: 0.6995850801467896
2023-01-22 23:30:49.934398: step: 1652/530, loss: 0.2262871414422989
2023-01-22 23:30:51.040627: step: 1656/530, loss: 1.145828127861023
2023-01-22 23:30:52.126741: step: 1660/530, loss: 0.5478800535202026
2023-01-22 23:30:53.248272: step: 1664/530, loss: 0.4348495602607727
2023-01-22 23:30:54.350656: step: 1668/530, loss: 1.1593722105026245
2023-01-22 23:30:55.457468: step: 1672/530, loss: 0.17307350039482117
2023-01-22 23:30:56.572021: step: 1676/530, loss: 0.41946423053741455
2023-01-22 23:30:57.681082: step: 1680/530, loss: 0.6250231862068176
2023-01-22 23:30:58.758963: step: 1684/530, loss: 1.464827537536621
2023-01-22 23:30:59.874385: step: 1688/530, loss: 0.2861084043979645
2023-01-22 23:31:01.005854: step: 1692/530, loss: 1.3531503677368164
2023-01-22 23:31:02.113102: step: 1696/530, loss: 1.0335527658462524
2023-01-22 23:31:03.188917: step: 1700/530, loss: 0.43667900562286377
2023-01-22 23:31:04.290283: step: 1704/530, loss: 1.32804536819458
2023-01-22 23:31:05.391990: step: 1708/530, loss: 0.5761452913284302
2023-01-22 23:31:06.546416: step: 1712/530, loss: 0.6144669651985168
2023-01-22 23:31:07.663727: step: 1716/530, loss: 0.8968162536621094
2023-01-22 23:31:08.756924: step: 1720/530, loss: 0.7122179865837097
2023-01-22 23:31:09.877592: step: 1724/530, loss: 1.0318787097930908
2023-01-22 23:31:10.975436: step: 1728/530, loss: 2.2600173950195312
2023-01-22 23:31:12.061923: step: 1732/530, loss: 0.864188551902771
2023-01-22 23:31:13.147364: step: 1736/530, loss: 0.36919277906417847
2023-01-22 23:31:14.258929: step: 1740/530, loss: 4.889497756958008
2023-01-22 23:31:15.365706: step: 1744/530, loss: 1.5948606729507446
2023-01-22 23:31:16.465330: step: 1748/530, loss: 0.337212473154068
2023-01-22 23:31:17.576110: step: 1752/530, loss: 0.5207529664039612
2023-01-22 23:31:18.679076: step: 1756/530, loss: 2.303536891937256
2023-01-22 23:31:19.781002: step: 1760/530, loss: 1.9565526247024536
2023-01-22 23:31:20.888600: step: 1764/530, loss: 2.555671453475952
2023-01-22 23:31:21.969091: step: 1768/530, loss: 1.539425015449524
2023-01-22 23:31:23.081225: step: 1772/530, loss: 0.3795326352119446
2023-01-22 23:31:24.167628: step: 1776/530, loss: 1.0622613430023193
2023-01-22 23:31:25.281738: step: 1780/530, loss: 0.19718846678733826
2023-01-22 23:31:26.411035: step: 1784/530, loss: 1.8759675025939941
2023-01-22 23:31:27.501686: step: 1788/530, loss: 0.5692466497421265
2023-01-22 23:31:28.577556: step: 1792/530, loss: 0.5606082081794739
2023-01-22 23:31:29.704710: step: 1796/530, loss: 0.7490469217300415
2023-01-22 23:31:30.797129: step: 1800/530, loss: 0.2673374116420746
2023-01-22 23:31:31.923179: step: 1804/530, loss: 1.0290288925170898
2023-01-22 23:31:33.045961: step: 1808/530, loss: 0.44509202241897583
2023-01-22 23:31:34.165073: step: 1812/530, loss: 0.3291131854057312
2023-01-22 23:31:35.280183: step: 1816/530, loss: 0.6886335015296936
2023-01-22 23:31:36.375449: step: 1820/530, loss: 1.92379629611969
2023-01-22 23:31:37.497855: step: 1824/530, loss: 2.0243961811065674
2023-01-22 23:31:38.605098: step: 1828/530, loss: 0.6118788719177246
2023-01-22 23:31:39.700894: step: 1832/530, loss: 1.6476573944091797
2023-01-22 23:31:40.802475: step: 1836/530, loss: 1.144230604171753
2023-01-22 23:31:41.887062: step: 1840/530, loss: 4.090342044830322
2023-01-22 23:31:42.990058: step: 1844/530, loss: 0.3739830255508423
2023-01-22 23:31:44.077820: step: 1848/530, loss: 0.42024731636047363
2023-01-22 23:31:45.166488: step: 1852/530, loss: 0.6363363265991211
2023-01-22 23:31:46.332084: step: 1856/530, loss: 7.146363258361816
2023-01-22 23:31:47.468324: step: 1860/530, loss: 1.9021787643432617
2023-01-22 23:31:48.577072: step: 1864/530, loss: 0.2815357446670532
2023-01-22 23:31:49.687503: step: 1868/530, loss: 0.3476211428642273
2023-01-22 23:31:50.774486: step: 1872/530, loss: 1.9249788522720337
2023-01-22 23:31:51.860668: step: 1876/530, loss: 2.4019217491149902
2023-01-22 23:31:52.978974: step: 1880/530, loss: 1.1774638891220093
2023-01-22 23:31:54.091333: step: 1884/530, loss: 1.0605806112289429
2023-01-22 23:31:55.219648: step: 1888/530, loss: 1.097830057144165
2023-01-22 23:31:56.330819: step: 1892/530, loss: 0.6262301206588745
2023-01-22 23:31:57.426149: step: 1896/530, loss: 0.3009089231491089
2023-01-22 23:31:58.530900: step: 1900/530, loss: 1.0584033727645874
2023-01-22 23:31:59.671818: step: 1904/530, loss: 2.5493252277374268
2023-01-22 23:32:00.767778: step: 1908/530, loss: 0.9976029992103577
2023-01-22 23:32:01.872810: step: 1912/530, loss: 1.029822587966919
2023-01-22 23:32:02.989102: step: 1916/530, loss: 0.46277350187301636
2023-01-22 23:32:04.092718: step: 1920/530, loss: 0.2852664887905121
2023-01-22 23:32:05.190929: step: 1924/530, loss: 0.7696099281311035
2023-01-22 23:32:06.288024: step: 1928/530, loss: 3.251713514328003
2023-01-22 23:32:07.374883: step: 1932/530, loss: 0.4431355595588684
2023-01-22 23:32:08.465692: step: 1936/530, loss: 1.986539602279663
2023-01-22 23:32:09.589170: step: 1940/530, loss: 0.4960607588291168
2023-01-22 23:32:10.718409: step: 1944/530, loss: 1.300311803817749
2023-01-22 23:32:11.836600: step: 1948/530, loss: 0.26442885398864746
2023-01-22 23:32:12.951006: step: 1952/530, loss: 0.5087611079216003
2023-01-22 23:32:14.060173: step: 1956/530, loss: 1.1133818626403809
2023-01-22 23:32:15.156555: step: 1960/530, loss: 0.18851400911808014
2023-01-22 23:32:16.278117: step: 1964/530, loss: 1.8992023468017578
2023-01-22 23:32:17.357363: step: 1968/530, loss: 0.7801329493522644
2023-01-22 23:32:18.441307: step: 1972/530, loss: 0.614930272102356
2023-01-22 23:32:19.547680: step: 1976/530, loss: 0.27177974581718445
2023-01-22 23:32:20.674241: step: 1980/530, loss: 2.7597458362579346
2023-01-22 23:32:21.799399: step: 1984/530, loss: 0.20599856972694397
2023-01-22 23:32:22.920274: step: 1988/530, loss: 1.3647637367248535
2023-01-22 23:32:24.018690: step: 1992/530, loss: 0.5085301399230957
2023-01-22 23:32:25.144354: step: 1996/530, loss: 1.1464451551437378
2023-01-22 23:32:26.256026: step: 2000/530, loss: 0.3140926957130432
2023-01-22 23:32:27.366268: step: 2004/530, loss: 0.8599792122840881
2023-01-22 23:32:28.462281: step: 2008/530, loss: 0.17204852402210236
2023-01-22 23:32:29.597871: step: 2012/530, loss: 0.24362383782863617
2023-01-22 23:32:30.715317: step: 2016/530, loss: 0.7568389177322388
2023-01-22 23:32:31.817580: step: 2020/530, loss: 1.926169753074646
2023-01-22 23:32:32.934128: step: 2024/530, loss: 0.23006616532802582
2023-01-22 23:32:34.047630: step: 2028/530, loss: 0.782691478729248
2023-01-22 23:32:35.135180: step: 2032/530, loss: 2.08746075630188
2023-01-22 23:32:36.248034: step: 2036/530, loss: 0.6575571298599243
2023-01-22 23:32:37.363811: step: 2040/530, loss: 0.2450738400220871
2023-01-22 23:32:38.506743: step: 2044/530, loss: 0.31441497802734375
2023-01-22 23:32:39.610383: step: 2048/530, loss: 2.1679301261901855
2023-01-22 23:32:40.731909: step: 2052/530, loss: 1.4379644393920898
2023-01-22 23:32:41.852268: step: 2056/530, loss: 0.44014471769332886
2023-01-22 23:32:42.961121: step: 2060/530, loss: 0.10426025092601776
2023-01-22 23:32:44.094017: step: 2064/530, loss: 1.3592344522476196
2023-01-22 23:32:45.207094: step: 2068/530, loss: 0.21736669540405273
2023-01-22 23:32:46.372907: step: 2072/530, loss: 0.11242156475782394
2023-01-22 23:32:47.455049: step: 2076/530, loss: 1.2034382820129395
2023-01-22 23:32:48.546281: step: 2080/530, loss: 0.22735628485679626
2023-01-22 23:32:49.654084: step: 2084/530, loss: 1.4170310497283936
2023-01-22 23:32:50.776407: step: 2088/530, loss: 1.1202428340911865
2023-01-22 23:32:51.874794: step: 2092/530, loss: 0.4065219759941101
2023-01-22 23:32:52.989422: step: 2096/530, loss: 0.8180004358291626
2023-01-22 23:32:54.128048: step: 2100/530, loss: 1.1105661392211914
2023-01-22 23:32:55.217054: step: 2104/530, loss: 1.7270715236663818
2023-01-22 23:32:56.329527: step: 2108/530, loss: 0.36386728286743164
2023-01-22 23:32:57.451230: step: 2112/530, loss: 1.3461484909057617
2023-01-22 23:32:58.543166: step: 2116/530, loss: 1.5666639804840088
2023-01-22 23:32:59.646975: step: 2120/530, loss: 0.3403962552547455
==================================================
Loss: 3.547
--------------------
Dev: {'event': {'p': 0.5575842696629213, 'r': 0.5286284953395473, 'f1': 0.5427204374572795}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Test: {'event': {'p': 0.47513440860215056, 'r': 0.412004662004662, 'f1': 0.44132334581772786}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Chinese: {'event': {'p': 0.5428571428571428, 'r': 0.35185185185185186, 'f1': 0.42696629213483145}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Korean: {'event': {'p': 0.8571428571428571, 'r': 0.19047619047619047, 'f1': 0.31168831168831174}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Russian: {'event': {'p': 0.875, 'r': 0.19444444444444445, 'f1': 0.3181818181818182}, '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': 0.5575842696629213, 'r': 0.5286284953395473, 'f1': 0.5427204374572795}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Eng Test for Chinese: {'event': {'p': 0.47513440860215056, 'r': 0.412004662004662, 'f1': 0.44132334581772786}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Sample Chinese: {'event': {'p': 0.5428571428571428, 'r': 0.35185185185185186, 'f1': 0.42696629213483145}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5575842696629213, 'r': 0.5286284953395473, 'f1': 0.5427204374572795}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Eng Test for Korean: {'event': {'p': 0.47513440860215056, 'r': 0.412004662004662, 'f1': 0.44132334581772786}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Sample Korean: {'event': {'p': 0.8571428571428571, 'r': 0.19047619047619047, 'f1': 0.31168831168831174}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5575842696629213, 'r': 0.5286284953395473, 'f1': 0.5427204374572795}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Eng Test for Russian: {'event': {'p': 0.47513440860215056, 'r': 0.412004662004662, 'f1': 0.44132334581772786}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
Sample Russian: {'event': {'p': 0.875, 'r': 0.19444444444444445, 'f1': 0.3181818181818182}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 0}
******************************
Epoch: 1
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-22 23:33:59.555032: step: 4/530, loss: 2.200685977935791
2023-01-22 23:34:00.648992: step: 8/530, loss: 1.058659553527832
2023-01-22 23:34:01.728027: step: 12/530, loss: 0.1197165995836258
2023-01-22 23:34:02.823633: step: 16/530, loss: 1.0336403846740723
2023-01-22 23:34:03.957681: step: 20/530, loss: 1.0256123542785645
2023-01-22 23:34:05.067331: step: 24/530, loss: 0.892248272895813
2023-01-22 23:34:06.165334: step: 28/530, loss: 0.22788238525390625
2023-01-22 23:34:07.254366: step: 32/530, loss: 0.28901946544647217
2023-01-22 23:34:08.384168: step: 36/530, loss: 2.5979502201080322
2023-01-22 23:34:09.532925: step: 40/530, loss: 2.4533352851867676
2023-01-22 23:34:10.674454: step: 44/530, loss: 0.34595173597335815
2023-01-22 23:34:11.794248: step: 48/530, loss: 1.4736697673797607
2023-01-22 23:34:12.915871: step: 52/530, loss: 0.563647449016571
2023-01-22 23:34:14.035612: step: 56/530, loss: 0.9589254856109619
2023-01-22 23:34:15.172547: step: 60/530, loss: 0.5077283978462219
2023-01-22 23:34:16.263172: step: 64/530, loss: 0.26661205291748047
2023-01-22 23:34:17.365883: step: 68/530, loss: 0.2586950361728668
2023-01-22 23:34:18.483756: step: 72/530, loss: 1.91961669921875
2023-01-22 23:34:19.567330: step: 76/530, loss: 0.12271666526794434
2023-01-22 23:34:20.692598: step: 80/530, loss: 0.7731084227561951
2023-01-22 23:34:21.827981: step: 84/530, loss: 7.6644368171691895
2023-01-22 23:34:22.974884: step: 88/530, loss: 0.26792946457862854
2023-01-22 23:34:24.156950: step: 92/530, loss: 0.2669130265712738
2023-01-22 23:34:25.272641: step: 96/530, loss: 0.9699838161468506
2023-01-22 23:34:26.390940: step: 100/530, loss: 0.24093469977378845
2023-01-22 23:34:27.532643: step: 104/530, loss: 1.9498194456100464
2023-01-22 23:34:28.667543: step: 108/530, loss: 0.19898051023483276
2023-01-22 23:34:29.860347: step: 112/530, loss: 0.576029896736145
2023-01-22 23:34:30.979053: step: 116/530, loss: 0.27473029494285583
2023-01-22 23:34:32.116481: step: 120/530, loss: 0.3010798990726471
2023-01-22 23:34:33.240956: step: 124/530, loss: 0.8356246948242188
2023-01-22 23:34:34.361260: step: 128/530, loss: 1.5021779537200928
2023-01-22 23:34:35.488614: step: 132/530, loss: 0.6857924461364746
2023-01-22 23:34:36.583179: step: 136/530, loss: 0.324203222990036
2023-01-22 23:34:37.710333: step: 140/530, loss: 0.6615785360336304
2023-01-22 23:34:38.874462: step: 144/530, loss: 0.9998345375061035
2023-01-22 23:34:39.972833: step: 148/530, loss: 1.3763024806976318
2023-01-22 23:34:41.085690: step: 152/530, loss: 1.1671593189239502
2023-01-22 23:34:42.207024: step: 156/530, loss: 0.29817238450050354
2023-01-22 23:34:43.335344: step: 160/530, loss: 0.18124710023403168
2023-01-22 23:34:44.425481: step: 164/530, loss: 1.1664457321166992
2023-01-22 23:34:45.534003: step: 168/530, loss: 3.0986249446868896
2023-01-22 23:34:46.618874: step: 172/530, loss: 0.7280139327049255
2023-01-22 23:34:47.699527: step: 176/530, loss: 0.8106658458709717
2023-01-22 23:34:48.779978: step: 180/530, loss: 0.7450309991836548
2023-01-22 23:34:49.864191: step: 184/530, loss: 0.5360084772109985
2023-01-22 23:34:50.955237: step: 188/530, loss: 2.1084046363830566
2023-01-22 23:34:52.061412: step: 192/530, loss: 1.2971171140670776
2023-01-22 23:34:53.150915: step: 196/530, loss: 0.26097896695137024
2023-01-22 23:34:54.269278: step: 200/530, loss: 0.44702231884002686
2023-01-22 23:34:55.375474: step: 204/530, loss: 0.20342564582824707
2023-01-22 23:34:56.465976: step: 208/530, loss: 0.09978476166725159
2023-01-22 23:34:57.592331: step: 212/530, loss: 0.33453789353370667
2023-01-22 23:34:58.684763: step: 216/530, loss: 1.5588793754577637
2023-01-22 23:34:59.816630: step: 220/530, loss: 0.2923765182495117
2023-01-22 23:35:00.929673: step: 224/530, loss: 1.2631158828735352
2023-01-22 23:35:02.018356: step: 228/530, loss: 0.27993661165237427
2023-01-22 23:35:03.159497: step: 232/530, loss: 0.30080148577690125
2023-01-22 23:35:04.249757: step: 236/530, loss: 1.7464178800582886
2023-01-22 23:35:05.358041: step: 240/530, loss: 0.9044017791748047
2023-01-22 23:35:06.443669: step: 244/530, loss: 0.2250264585018158
2023-01-22 23:35:07.541132: step: 248/530, loss: 0.1649579107761383
2023-01-22 23:35:08.642389: step: 252/530, loss: 1.2601319551467896
2023-01-22 23:35:09.743832: step: 256/530, loss: 0.8354940414428711
2023-01-22 23:35:10.861509: step: 260/530, loss: 1.1860452890396118
2023-01-22 23:35:11.944373: step: 264/530, loss: 0.13848038017749786
2023-01-22 23:35:13.052164: step: 268/530, loss: 0.16463322937488556
2023-01-22 23:35:14.149111: step: 272/530, loss: 6.484447479248047
2023-01-22 23:35:15.224693: step: 276/530, loss: 0.7893614172935486
2023-01-22 23:35:16.290612: step: 280/530, loss: 1.489478349685669
2023-01-22 23:35:17.386181: step: 284/530, loss: 1.029711127281189
2023-01-22 23:35:18.508357: step: 288/530, loss: 0.16102752089500427
2023-01-22 23:35:19.596872: step: 292/530, loss: 1.1562092304229736
2023-01-22 23:35:20.756654: step: 296/530, loss: 0.36202916502952576
2023-01-22 23:35:21.888189: step: 300/530, loss: 0.4381279945373535
2023-01-22 23:35:23.016902: step: 304/530, loss: 0.8384024500846863
2023-01-22 23:35:24.118446: step: 308/530, loss: 0.2489282786846161
2023-01-22 23:35:25.225811: step: 312/530, loss: 0.2302195131778717
2023-01-22 23:35:26.325448: step: 316/530, loss: 0.9098072052001953
2023-01-22 23:35:27.419448: step: 320/530, loss: 0.7628673315048218
2023-01-22 23:35:28.512072: step: 324/530, loss: 0.8541550040245056
2023-01-22 23:35:29.618270: step: 328/530, loss: 10.53091812133789
2023-01-22 23:35:30.732451: step: 332/530, loss: 0.2528610825538635
2023-01-22 23:35:31.840818: step: 336/530, loss: 1.1355164051055908
2023-01-22 23:35:32.993771: step: 340/530, loss: 0.7249311208724976
2023-01-22 23:35:34.091754: step: 344/530, loss: 0.8423562049865723
2023-01-22 23:35:35.199635: step: 348/530, loss: 0.2510421872138977
2023-01-22 23:35:36.327100: step: 352/530, loss: 0.2662091851234436
2023-01-22 23:35:37.440598: step: 356/530, loss: 0.754250168800354
2023-01-22 23:35:38.572858: step: 360/530, loss: 0.9891226291656494
2023-01-22 23:35:39.683683: step: 364/530, loss: 0.43972665071487427
2023-01-22 23:35:40.775983: step: 368/530, loss: 0.6635894775390625
2023-01-22 23:35:41.870929: step: 372/530, loss: 0.795781135559082
2023-01-22 23:35:42.983593: step: 376/530, loss: 0.21503916382789612
2023-01-22 23:35:44.108173: step: 380/530, loss: 0.26122504472732544
2023-01-22 23:35:45.182907: step: 384/530, loss: 0.8479779958724976
2023-01-22 23:35:46.280414: step: 388/530, loss: 0.3621244430541992
2023-01-22 23:35:47.379772: step: 392/530, loss: 0.13838304579257965
2023-01-22 23:35:48.497687: step: 396/530, loss: 0.4224167764186859
2023-01-22 23:35:49.603469: step: 400/530, loss: 1.967092514038086
2023-01-22 23:35:50.678744: step: 404/530, loss: 6.675584316253662
2023-01-22 23:35:51.773350: step: 408/530, loss: 0.2253103405237198
2023-01-22 23:35:52.911365: step: 412/530, loss: 0.5202027559280396
2023-01-22 23:35:53.984500: step: 416/530, loss: 0.37715089321136475
2023-01-22 23:35:55.069941: step: 420/530, loss: 0.4904758334159851
2023-01-22 23:35:56.155617: step: 424/530, loss: 0.22176390886306763
2023-01-22 23:35:57.256479: step: 428/530, loss: 0.20544129610061646
2023-01-22 23:35:58.383728: step: 432/530, loss: 0.6765258312225342
2023-01-22 23:35:59.519087: step: 436/530, loss: 1.2053048610687256
2023-01-22 23:36:00.615241: step: 440/530, loss: 0.4454779624938965
2023-01-22 23:36:01.711054: step: 444/530, loss: 1.6111702919006348
2023-01-22 23:36:02.811350: step: 448/530, loss: 0.06502237170934677
2023-01-22 23:36:03.938651: step: 452/530, loss: 0.22973480820655823
2023-01-22 23:36:05.086123: step: 456/530, loss: 2.492570400238037
2023-01-22 23:36:06.197544: step: 460/530, loss: 0.14618225395679474
2023-01-22 23:36:07.330649: step: 464/530, loss: 2.185479164123535
2023-01-22 23:36:08.428271: step: 468/530, loss: 0.2644267678260803
2023-01-22 23:36:09.539751: step: 472/530, loss: 0.8231765627861023
2023-01-22 23:36:10.658681: step: 476/530, loss: 0.21066045761108398
2023-01-22 23:36:11.749260: step: 480/530, loss: 0.33683720231056213
2023-01-22 23:36:12.844295: step: 484/530, loss: 1.4127780199050903
2023-01-22 23:36:13.921446: step: 488/530, loss: 0.9362136125564575
2023-01-22 23:36:15.014353: step: 492/530, loss: 1.5947743654251099
2023-01-22 23:36:16.137446: step: 496/530, loss: 0.5059801340103149
2023-01-22 23:36:17.253056: step: 500/530, loss: 0.17963333427906036
2023-01-22 23:36:18.374187: step: 504/530, loss: 0.24877767264842987
2023-01-22 23:36:19.453429: step: 508/530, loss: 0.35003119707107544
2023-01-22 23:36:20.561000: step: 512/530, loss: 0.5445950031280518
2023-01-22 23:36:21.676535: step: 516/530, loss: 1.3959622383117676
2023-01-22 23:36:22.783867: step: 520/530, loss: 1.0506694316864014
2023-01-22 23:36:23.872367: step: 524/530, loss: 0.530386745929718
2023-01-22 23:36:24.963635: step: 528/530, loss: 0.1987399160861969
2023-01-22 23:36:26.057052: step: 532/530, loss: 0.3992048501968384
2023-01-22 23:36:27.165974: step: 536/530, loss: 0.39069196581840515
2023-01-22 23:36:28.309177: step: 540/530, loss: 0.16810913383960724
2023-01-22 23:36:29.413711: step: 544/530, loss: 0.24973583221435547
2023-01-22 23:36:30.519587: step: 548/530, loss: 0.24334926903247833
2023-01-22 23:36:31.607986: step: 552/530, loss: 0.8767409324645996
2023-01-22 23:36:32.720471: step: 556/530, loss: 0.761859655380249
2023-01-22 23:36:33.834310: step: 560/530, loss: 3.0349068641662598
2023-01-22 23:36:34.958070: step: 564/530, loss: 0.07478771358728409
2023-01-22 23:36:36.099067: step: 568/530, loss: 0.4298804998397827
2023-01-22 23:36:37.193612: step: 572/530, loss: 0.2968323230743408
2023-01-22 23:36:38.335166: step: 576/530, loss: 1.9561132192611694
2023-01-22 23:36:39.458031: step: 580/530, loss: 0.20468273758888245
2023-01-22 23:36:40.582734: step: 584/530, loss: 0.30116721987724304
2023-01-22 23:36:41.680659: step: 588/530, loss: 3.4594688415527344
2023-01-22 23:36:42.779858: step: 592/530, loss: 0.9758798480033875
2023-01-22 23:36:43.922290: step: 596/530, loss: 0.4043503701686859
2023-01-22 23:36:45.027943: step: 600/530, loss: 0.4305291175842285
2023-01-22 23:36:46.137098: step: 604/530, loss: 1.6910337209701538
2023-01-22 23:36:47.252732: step: 608/530, loss: 0.4943602681159973
2023-01-22 23:36:48.366167: step: 612/530, loss: 0.22036682069301605
2023-01-22 23:36:49.470521: step: 616/530, loss: 1.5216723680496216
2023-01-22 23:36:50.573678: step: 620/530, loss: 0.8112492561340332
2023-01-22 23:36:51.673517: step: 624/530, loss: 0.3797592222690582
2023-01-22 23:36:52.783918: step: 628/530, loss: 0.3138834238052368
2023-01-22 23:36:53.906050: step: 632/530, loss: 0.2239220142364502
2023-01-22 23:36:55.051529: step: 636/530, loss: 0.9719775319099426
2023-01-22 23:36:56.174984: step: 640/530, loss: 0.22301378846168518
2023-01-22 23:36:57.271333: step: 644/530, loss: 0.366659939289093
2023-01-22 23:36:58.360305: step: 648/530, loss: 0.2508353292942047
2023-01-22 23:36:59.480078: step: 652/530, loss: 0.15830039978027344
2023-01-22 23:37:00.575441: step: 656/530, loss: 1.149523377418518
2023-01-22 23:37:01.677496: step: 660/530, loss: 0.10059557110071182
2023-01-22 23:37:02.775072: step: 664/530, loss: 0.946194052696228
2023-01-22 23:37:03.891283: step: 668/530, loss: 0.9798312187194824
2023-01-22 23:37:04.978272: step: 672/530, loss: 0.9051358699798584
2023-01-22 23:37:06.090543: step: 676/530, loss: 0.18281203508377075
2023-01-22 23:37:07.196403: step: 680/530, loss: 0.334725558757782
2023-01-22 23:37:08.304028: step: 684/530, loss: 1.388506531715393
2023-01-22 23:37:09.409401: step: 688/530, loss: 0.34011203050613403
2023-01-22 23:37:10.547676: step: 692/530, loss: 0.28743547201156616
2023-01-22 23:37:11.635956: step: 696/530, loss: 0.19589228928089142
2023-01-22 23:37:12.765879: step: 700/530, loss: 0.5151674151420593
2023-01-22 23:37:13.850348: step: 704/530, loss: 0.22857657074928284
2023-01-22 23:37:14.957124: step: 708/530, loss: 1.3195732831954956
2023-01-22 23:37:16.063812: step: 712/530, loss: 0.34966832399368286
2023-01-22 23:37:17.151967: step: 716/530, loss: 0.255550742149353
2023-01-22 23:37:18.262607: step: 720/530, loss: 0.21411819756031036
2023-01-22 23:37:19.357202: step: 724/530, loss: 0.29211390018463135
2023-01-22 23:37:20.465205: step: 728/530, loss: 1.381205439567566
2023-01-22 23:37:21.588831: step: 732/530, loss: 3.2000765800476074
2023-01-22 23:37:22.677829: step: 736/530, loss: 0.7178811430931091
2023-01-22 23:37:23.806369: step: 740/530, loss: 1.4770170450210571
2023-01-22 23:37:24.891294: step: 744/530, loss: 0.3136110007762909
2023-01-22 23:37:25.985587: step: 748/530, loss: 0.28192827105522156
2023-01-22 23:37:27.077382: step: 752/530, loss: 0.22102923691272736
2023-01-22 23:37:28.194702: step: 756/530, loss: 0.5702583193778992
2023-01-22 23:37:29.286800: step: 760/530, loss: 0.35236233472824097
2023-01-22 23:37:30.402612: step: 764/530, loss: 7.44382381439209
2023-01-22 23:37:31.488684: step: 768/530, loss: 0.8546481132507324
2023-01-22 23:37:32.612150: step: 772/530, loss: 0.9909370541572571
2023-01-22 23:37:33.723842: step: 776/530, loss: 1.0059850215911865
2023-01-22 23:37:34.826409: step: 780/530, loss: 0.5271921753883362
2023-01-22 23:37:35.938600: step: 784/530, loss: 0.17919960618019104
2023-01-22 23:37:37.020267: step: 788/530, loss: 0.5968723297119141
2023-01-22 23:37:38.114526: step: 792/530, loss: 0.5476526618003845
2023-01-22 23:37:39.216640: step: 796/530, loss: 0.32966527342796326
2023-01-22 23:37:40.296421: step: 800/530, loss: 0.9981452226638794
2023-01-22 23:37:41.408337: step: 804/530, loss: 1.527134656906128
2023-01-22 23:37:42.517207: step: 808/530, loss: 0.31798163056373596
2023-01-22 23:37:43.653492: step: 812/530, loss: 0.3976700007915497
2023-01-22 23:37:44.752179: step: 816/530, loss: 1.3337130546569824
2023-01-22 23:37:45.900497: step: 820/530, loss: 0.4176862835884094
2023-01-22 23:37:47.013478: step: 824/530, loss: 1.2289540767669678
2023-01-22 23:37:48.156733: step: 828/530, loss: 0.7914347648620605
2023-01-22 23:37:49.246571: step: 832/530, loss: 2.5298385620117188
2023-01-22 23:37:50.353331: step: 836/530, loss: 0.19650602340698242
2023-01-22 23:37:51.461020: step: 840/530, loss: 0.39637166261672974
2023-01-22 23:37:52.561752: step: 844/530, loss: 0.13046441972255707
2023-01-22 23:37:53.646588: step: 848/530, loss: 0.42809364199638367
2023-01-22 23:37:54.748641: step: 852/530, loss: 0.08593922108411789
2023-01-22 23:37:55.902994: step: 856/530, loss: 0.8894029855728149
2023-01-22 23:37:57.015045: step: 860/530, loss: 0.8561725616455078
2023-01-22 23:37:58.119829: step: 864/530, loss: 0.1408546417951584
2023-01-22 23:37:59.221457: step: 868/530, loss: 0.8385001420974731
2023-01-22 23:38:00.353869: step: 872/530, loss: 0.3299209475517273
2023-01-22 23:38:01.445138: step: 876/530, loss: 0.06449031829833984
2023-01-22 23:38:02.571161: step: 880/530, loss: 0.5882061719894409
2023-01-22 23:38:03.693355: step: 884/530, loss: 1.0153770446777344
2023-01-22 23:38:04.829361: step: 888/530, loss: 0.9610913991928101
2023-01-22 23:38:05.959096: step: 892/530, loss: 0.3587445616722107
2023-01-22 23:38:07.071278: step: 896/530, loss: 0.4174576699733734
2023-01-22 23:38:08.152948: step: 900/530, loss: 6.706972599029541
2023-01-22 23:38:09.267281: step: 904/530, loss: 0.683864951133728
2023-01-22 23:38:10.367932: step: 908/530, loss: 0.4716065227985382
2023-01-22 23:38:11.509962: step: 912/530, loss: 0.254197359085083
2023-01-22 23:38:12.637131: step: 916/530, loss: 0.17095708847045898
2023-01-22 23:38:13.761854: step: 920/530, loss: 0.5439212322235107
2023-01-22 23:38:14.868254: step: 924/530, loss: 0.08776841312646866
2023-01-22 23:38:15.959057: step: 928/530, loss: 0.3539993464946747
2023-01-22 23:38:17.034889: step: 932/530, loss: 0.1430431306362152
2023-01-22 23:38:18.154644: step: 936/530, loss: 0.22902193665504456
2023-01-22 23:38:19.272290: step: 940/530, loss: 0.5222132205963135
2023-01-22 23:38:20.369902: step: 944/530, loss: 0.1301381140947342
2023-01-22 23:38:21.490544: step: 948/530, loss: 1.1966793537139893
2023-01-22 23:38:22.577514: step: 952/530, loss: 0.471148282289505
2023-01-22 23:38:23.647291: step: 956/530, loss: 0.22538577020168304
2023-01-22 23:38:24.765382: step: 960/530, loss: 0.05984830856323242
2023-01-22 23:38:25.877332: step: 964/530, loss: 0.22298157215118408
2023-01-22 23:38:26.998245: step: 968/530, loss: 3.1551895141601562
2023-01-22 23:38:28.117626: step: 972/530, loss: 0.3010341227054596
2023-01-22 23:38:29.214845: step: 976/530, loss: 0.1772564947605133
2023-01-22 23:38:30.331971: step: 980/530, loss: 2.4243040084838867
2023-01-22 23:38:31.456886: step: 984/530, loss: 1.9680969715118408
2023-01-22 23:38:32.546620: step: 988/530, loss: 0.5540863871574402
2023-01-22 23:38:33.685210: step: 992/530, loss: 0.48715218901634216
2023-01-22 23:38:34.788751: step: 996/530, loss: 0.6629146337509155
2023-01-22 23:38:35.881267: step: 1000/530, loss: 0.7571136951446533
2023-01-22 23:38:36.990648: step: 1004/530, loss: 0.20634795725345612
2023-01-22 23:38:38.072577: step: 1008/530, loss: 0.25444328784942627
2023-01-22 23:38:39.160925: step: 1012/530, loss: 0.29206714034080505
2023-01-22 23:38:40.266032: step: 1016/530, loss: 0.13060179352760315
2023-01-22 23:38:41.373851: step: 1020/530, loss: 0.1235198974609375
2023-01-22 23:38:42.499689: step: 1024/530, loss: 1.6179931163787842
2023-01-22 23:38:43.578341: step: 1028/530, loss: 0.3424397110939026
2023-01-22 23:38:44.693048: step: 1032/530, loss: 1.0380901098251343
2023-01-22 23:38:45.791402: step: 1036/530, loss: 1.6306990385055542
2023-01-22 23:38:46.912725: step: 1040/530, loss: 0.3984840214252472
2023-01-22 23:38:47.998469: step: 1044/530, loss: 2.4112985134124756
2023-01-22 23:38:49.106968: step: 1048/530, loss: 0.07761536538600922
2023-01-22 23:38:50.226542: step: 1052/530, loss: 0.23065900802612305
2023-01-22 23:38:51.354770: step: 1056/530, loss: 0.559539794921875
2023-01-22 23:38:52.471343: step: 1060/530, loss: 7.068521976470947
2023-01-22 23:38:53.577425: step: 1064/530, loss: 1.8452435731887817
2023-01-22 23:38:54.691838: step: 1068/530, loss: 0.28903770446777344
2023-01-22 23:38:55.794906: step: 1072/530, loss: 0.4422036409378052
2023-01-22 23:38:56.903411: step: 1076/530, loss: 1.5652391910552979
2023-01-22 23:38:58.042288: step: 1080/530, loss: 0.7198148965835571
2023-01-22 23:38:59.159091: step: 1084/530, loss: 0.543188214302063
2023-01-22 23:39:00.276981: step: 1088/530, loss: 0.17771998047828674
2023-01-22 23:39:01.438378: step: 1092/530, loss: 0.172528937458992
2023-01-22 23:39:02.511116: step: 1096/530, loss: 0.9231682419776917
2023-01-22 23:39:03.583125: step: 1100/530, loss: 0.11629854142665863
2023-01-22 23:39:04.661034: step: 1104/530, loss: 1.3081920146942139
2023-01-22 23:39:05.739210: step: 1108/530, loss: 2.267946243286133
2023-01-22 23:39:06.873437: step: 1112/530, loss: 0.2682268023490906
2023-01-22 23:39:07.960373: step: 1116/530, loss: 0.6809921264648438
2023-01-22 23:39:09.068549: step: 1120/530, loss: 0.25974375009536743
2023-01-22 23:39:10.162011: step: 1124/530, loss: 2.283151149749756
2023-01-22 23:39:11.270749: step: 1128/530, loss: 0.9658295512199402
2023-01-22 23:39:12.385623: step: 1132/530, loss: 1.4376046657562256
2023-01-22 23:39:13.478767: step: 1136/530, loss: 0.1428484469652176
2023-01-22 23:39:14.604589: step: 1140/530, loss: 0.24889430403709412
2023-01-22 23:39:15.718826: step: 1144/530, loss: 0.5231178402900696
2023-01-22 23:39:16.825070: step: 1148/530, loss: 0.7936610579490662
2023-01-22 23:39:17.935024: step: 1152/530, loss: 0.2305418848991394
2023-01-22 23:39:19.036711: step: 1156/530, loss: 0.2333575338125229
2023-01-22 23:39:20.137090: step: 1160/530, loss: 0.589411199092865
2023-01-22 23:39:21.270991: step: 1164/530, loss: 1.415989637374878
2023-01-22 23:39:22.372329: step: 1168/530, loss: 0.8055539727210999
2023-01-22 23:39:23.491594: step: 1172/530, loss: 0.18290147185325623
2023-01-22 23:39:24.589500: step: 1176/530, loss: 0.10870780795812607
2023-01-22 23:39:25.684032: step: 1180/530, loss: 1.1774333715438843
2023-01-22 23:39:26.768299: step: 1184/530, loss: 0.2196376770734787
2023-01-22 23:39:27.879221: step: 1188/530, loss: 0.7387223243713379
2023-01-22 23:39:29.009975: step: 1192/530, loss: 0.24026966094970703
2023-01-22 23:39:30.109043: step: 1196/530, loss: 0.32315802574157715
2023-01-22 23:39:31.200615: step: 1200/530, loss: 0.27900105714797974
2023-01-22 23:39:32.315697: step: 1204/530, loss: 0.3503550887107849
2023-01-22 23:39:33.435170: step: 1208/530, loss: 0.46504974365234375
2023-01-22 23:39:34.548960: step: 1212/530, loss: 0.9156852960586548
2023-01-22 23:39:35.631919: step: 1216/530, loss: 0.28622308373451233
2023-01-22 23:39:36.754425: step: 1220/530, loss: 0.5559775233268738
2023-01-22 23:39:37.867920: step: 1224/530, loss: 0.37156346440315247
2023-01-22 23:39:38.983048: step: 1228/530, loss: 0.2069849967956543
2023-01-22 23:39:40.090691: step: 1232/530, loss: 0.11998063325881958
2023-01-22 23:39:41.252719: step: 1236/530, loss: 0.6977161169052124
2023-01-22 23:39:42.343662: step: 1240/530, loss: 0.15370111167430878
2023-01-22 23:39:43.454826: step: 1244/530, loss: 0.7312580347061157
2023-01-22 23:39:44.580406: step: 1248/530, loss: 0.3679896593093872
2023-01-22 23:39:45.680572: step: 1252/530, loss: 1.4025382995605469
2023-01-22 23:39:46.803142: step: 1256/530, loss: 1.2641417980194092
2023-01-22 23:39:47.898317: step: 1260/530, loss: 0.5815926194190979
2023-01-22 23:39:48.989421: step: 1264/530, loss: 0.5595970153808594
2023-01-22 23:39:50.112810: step: 1268/530, loss: 1.2447837591171265
2023-01-22 23:39:51.222531: step: 1272/530, loss: 0.8371374011039734
2023-01-22 23:39:52.315765: step: 1276/530, loss: 0.3096882700920105
2023-01-22 23:39:53.433506: step: 1280/530, loss: 0.9768273830413818
2023-01-22 23:39:54.551578: step: 1284/530, loss: 0.2760496735572815
2023-01-22 23:39:55.654731: step: 1288/530, loss: 0.6941208243370056
2023-01-22 23:39:56.757383: step: 1292/530, loss: 0.27443069219589233
2023-01-22 23:39:57.844408: step: 1296/530, loss: 0.6266626119613647
2023-01-22 23:39:58.947926: step: 1300/530, loss: 0.1924697458744049
2023-01-22 23:40:00.089524: step: 1304/530, loss: 0.7267837524414062
2023-01-22 23:40:01.208773: step: 1308/530, loss: 0.3956131041049957
2023-01-22 23:40:02.338494: step: 1312/530, loss: 0.8520927429199219
2023-01-22 23:40:03.437436: step: 1316/530, loss: 0.8948471546173096
2023-01-22 23:40:04.558343: step: 1320/530, loss: 1.0180714130401611
2023-01-22 23:40:05.665071: step: 1324/530, loss: 0.3404025137424469
2023-01-22 23:40:06.764964: step: 1328/530, loss: 0.4013948440551758
2023-01-22 23:40:07.876827: step: 1332/530, loss: 0.8326259851455688
2023-01-22 23:40:08.969485: step: 1336/530, loss: 0.5155757665634155
2023-01-22 23:40:10.070653: step: 1340/530, loss: 0.9842905402183533
2023-01-22 23:40:11.172148: step: 1344/530, loss: 1.397153377532959
2023-01-22 23:40:12.266825: step: 1348/530, loss: 1.6116747856140137
2023-01-22 23:40:13.374674: step: 1352/530, loss: 0.9735078811645508
2023-01-22 23:40:14.465159: step: 1356/530, loss: 0.3553386628627777
2023-01-22 23:40:15.573635: step: 1360/530, loss: 0.2220364660024643
2023-01-22 23:40:16.670004: step: 1364/530, loss: 0.37782537937164307
2023-01-22 23:40:17.783377: step: 1368/530, loss: 0.1812712550163269
2023-01-22 23:40:18.879411: step: 1372/530, loss: 0.5432860851287842
2023-01-22 23:40:20.002687: step: 1376/530, loss: 0.25794145464897156
2023-01-22 23:40:21.117769: step: 1380/530, loss: 0.22914743423461914
2023-01-22 23:40:22.225279: step: 1384/530, loss: 0.10989566147327423
2023-01-22 23:40:23.301061: step: 1388/530, loss: 0.3832426965236664
2023-01-22 23:40:24.414880: step: 1392/530, loss: 0.23594056069850922
2023-01-22 23:40:25.511529: step: 1396/530, loss: 6.348154067993164
2023-01-22 23:40:26.599238: step: 1400/530, loss: 0.5787858963012695
2023-01-22 23:40:27.722374: step: 1404/530, loss: 0.6329714059829712
2023-01-22 23:40:28.836669: step: 1408/530, loss: 6.840663909912109
2023-01-22 23:40:29.946447: step: 1412/530, loss: 0.29743510484695435
2023-01-22 23:40:31.057543: step: 1416/530, loss: 0.4690084457397461
2023-01-22 23:40:32.155101: step: 1420/530, loss: 0.3014492988586426
2023-01-22 23:40:33.246933: step: 1424/530, loss: 0.887120246887207
2023-01-22 23:40:34.376457: step: 1428/530, loss: 0.6102879643440247
2023-01-22 23:40:35.477150: step: 1432/530, loss: 0.22859859466552734
2023-01-22 23:40:36.581300: step: 1436/530, loss: 0.18292587995529175
2023-01-22 23:40:37.684510: step: 1440/530, loss: 0.1110515147447586
2023-01-22 23:40:38.804297: step: 1444/530, loss: 0.2376570701599121
2023-01-22 23:40:39.910127: step: 1448/530, loss: 0.800528883934021
2023-01-22 23:40:41.047853: step: 1452/530, loss: 0.6649103760719299
2023-01-22 23:40:42.156954: step: 1456/530, loss: 0.6304930448532104
2023-01-22 23:40:43.291275: step: 1460/530, loss: 1.6297876834869385
2023-01-22 23:40:44.402873: step: 1464/530, loss: 3.6106503009796143
2023-01-22 23:40:45.505487: step: 1468/530, loss: 0.8605820536613464
2023-01-22 23:40:46.615488: step: 1472/530, loss: 0.6748793721199036
2023-01-22 23:40:47.721446: step: 1476/530, loss: 0.967780351638794
2023-01-22 23:40:48.823304: step: 1480/530, loss: 1.4351000785827637
2023-01-22 23:40:49.935340: step: 1484/530, loss: 0.603656530380249
2023-01-22 23:40:51.042152: step: 1488/530, loss: 7.496251583099365
2023-01-22 23:40:52.130044: step: 1492/530, loss: 1.1967928409576416
2023-01-22 23:40:53.246354: step: 1496/530, loss: 0.3948216438293457
2023-01-22 23:40:54.334757: step: 1500/530, loss: 0.34825554490089417
2023-01-22 23:40:55.431522: step: 1504/530, loss: 0.5797415375709534
2023-01-22 23:40:56.539601: step: 1508/530, loss: 0.40484657883644104
2023-01-22 23:40:57.607219: step: 1512/530, loss: 0.18350154161453247
2023-01-22 23:40:58.698011: step: 1516/530, loss: 0.1745496243238449
2023-01-22 23:40:59.862498: step: 1520/530, loss: 2.0335772037506104
2023-01-22 23:41:00.984586: step: 1524/530, loss: 0.583419144153595
2023-01-22 23:41:02.080711: step: 1528/530, loss: 0.5432870984077454
2023-01-22 23:41:03.190054: step: 1532/530, loss: 0.2994877099990845
2023-01-22 23:41:04.281379: step: 1536/530, loss: 1.1855978965759277
2023-01-22 23:41:05.370014: step: 1540/530, loss: 0.017529677599668503
2023-01-22 23:41:06.469361: step: 1544/530, loss: 0.15532922744750977
2023-01-22 23:41:07.595978: step: 1548/530, loss: 0.14575806260108948
2023-01-22 23:41:08.739412: step: 1552/530, loss: 0.6545190811157227
2023-01-22 23:41:09.841973: step: 1556/530, loss: 2.1368188858032227
2023-01-22 23:41:10.957234: step: 1560/530, loss: 0.34058934450149536
2023-01-22 23:41:12.051053: step: 1564/530, loss: 0.2849229574203491
2023-01-22 23:41:13.150878: step: 1568/530, loss: 0.7994819283485413
2023-01-22 23:41:14.265731: step: 1572/530, loss: 0.11903336644172668
2023-01-22 23:41:15.384117: step: 1576/530, loss: 0.2817000448703766
2023-01-22 23:41:16.501995: step: 1580/530, loss: 0.449527770280838
2023-01-22 23:41:17.607107: step: 1584/530, loss: 0.6340710520744324
2023-01-22 23:41:18.710171: step: 1588/530, loss: 2.8808865547180176
2023-01-22 23:41:19.795470: step: 1592/530, loss: 0.2109864056110382
2023-01-22 23:41:20.883537: step: 1596/530, loss: 1.0190500020980835
2023-01-22 23:41:21.991143: step: 1600/530, loss: 0.3280106484889984
2023-01-22 23:41:23.120267: step: 1604/530, loss: 0.5436847805976868
2023-01-22 23:41:24.206161: step: 1608/530, loss: 1.1243443489074707
2023-01-22 23:41:25.308581: step: 1612/530, loss: 2.0383827686309814
2023-01-22 23:41:26.413617: step: 1616/530, loss: 0.33474865555763245
2023-01-22 23:41:27.545208: step: 1620/530, loss: 1.7503913640975952
2023-01-22 23:41:28.685520: step: 1624/530, loss: 0.26492491364479065
2023-01-22 23:41:29.818756: step: 1628/530, loss: 6.1829023361206055
2023-01-22 23:41:30.938151: step: 1632/530, loss: 0.1590873897075653
2023-01-22 23:41:32.025039: step: 1636/530, loss: 0.1909516453742981
2023-01-22 23:41:33.129522: step: 1640/530, loss: 6.731661319732666
2023-01-22 23:41:34.221670: step: 1644/530, loss: 0.19422298669815063
2023-01-22 23:41:35.330872: step: 1648/530, loss: 1.962960124015808
2023-01-22 23:41:36.478396: step: 1652/530, loss: 0.10533075034618378
2023-01-22 23:41:37.563110: step: 1656/530, loss: 0.6906180381774902
2023-01-22 23:41:38.660827: step: 1660/530, loss: 0.8270504474639893
2023-01-22 23:41:39.741362: step: 1664/530, loss: 0.13559304177761078
2023-01-22 23:41:40.844251: step: 1668/530, loss: 0.1347503662109375
2023-01-22 23:41:41.961232: step: 1672/530, loss: 0.575066328048706
2023-01-22 23:41:43.063002: step: 1676/530, loss: 0.14067545533180237
2023-01-22 23:41:44.166361: step: 1680/530, loss: 0.7516908049583435
2023-01-22 23:41:45.254243: step: 1684/530, loss: 6.5101637840271
2023-01-22 23:41:46.360792: step: 1688/530, loss: 1.2372459173202515
2023-01-22 23:41:47.488928: step: 1692/530, loss: 0.3302198350429535
2023-01-22 23:41:48.582613: step: 1696/530, loss: 0.22318939864635468
2023-01-22 23:41:49.686493: step: 1700/530, loss: 0.09426946938037872
2023-01-22 23:41:50.768341: step: 1704/530, loss: 0.27652445435523987
2023-01-22 23:41:51.871329: step: 1708/530, loss: 2.6318087577819824
2023-01-22 23:41:52.959407: step: 1712/530, loss: 0.11620178818702698
2023-01-22 23:41:54.077761: step: 1716/530, loss: 0.1317480206489563
2023-01-22 23:41:55.214956: step: 1720/530, loss: 1.7940690517425537
2023-01-22 23:41:56.308400: step: 1724/530, loss: 1.6589747667312622
2023-01-22 23:41:57.383047: step: 1728/530, loss: 0.8428720235824585
2023-01-22 23:41:58.511279: step: 1732/530, loss: 0.5653031468391418
2023-01-22 23:41:59.630259: step: 1736/530, loss: 0.4600246548652649
2023-01-22 23:42:00.774339: step: 1740/530, loss: 0.794142484664917
2023-01-22 23:42:01.858237: step: 1744/530, loss: 0.1945888102054596
2023-01-22 23:42:02.942175: step: 1748/530, loss: 0.3469984829425812
2023-01-22 23:42:04.034989: step: 1752/530, loss: 0.4326963424682617
2023-01-22 23:42:05.148748: step: 1756/530, loss: 0.4124979078769684
2023-01-22 23:42:06.268960: step: 1760/530, loss: 0.47238463163375854
2023-01-22 23:42:07.372421: step: 1764/530, loss: 0.14860983192920685
2023-01-22 23:42:08.489793: step: 1768/530, loss: 0.09306001663208008
2023-01-22 23:42:09.600888: step: 1772/530, loss: 0.22691026329994202
2023-01-22 23:42:10.702287: step: 1776/530, loss: 0.9747693538665771
2023-01-22 23:42:11.805979: step: 1780/530, loss: 0.20004530251026154
2023-01-22 23:42:12.894248: step: 1784/530, loss: 0.494042307138443
2023-01-22 23:42:14.044840: step: 1788/530, loss: 1.4173266887664795
2023-01-22 23:42:15.154103: step: 1792/530, loss: 0.1959010660648346
2023-01-22 23:42:16.259372: step: 1796/530, loss: 0.04304571449756622
2023-01-22 23:42:17.371746: step: 1800/530, loss: 0.23430344462394714
2023-01-22 23:42:18.448523: step: 1804/530, loss: 0.44915252923965454
2023-01-22 23:42:19.582740: step: 1808/530, loss: 0.4876177906990051
2023-01-22 23:42:20.694009: step: 1812/530, loss: 0.5615189671516418
2023-01-22 23:42:21.815825: step: 1816/530, loss: 0.5588340759277344
2023-01-22 23:42:22.936402: step: 1820/530, loss: 0.8740360140800476
2023-01-22 23:42:24.070999: step: 1824/530, loss: 0.19792518019676208
2023-01-22 23:42:25.210536: step: 1828/530, loss: 0.8894966244697571
2023-01-22 23:42:26.319940: step: 1832/530, loss: 0.7123299241065979
2023-01-22 23:42:27.462120: step: 1836/530, loss: 7.956293106079102
2023-01-22 23:42:28.551938: step: 1840/530, loss: 0.6290836334228516
2023-01-22 23:42:29.636697: step: 1844/530, loss: 0.13174043595790863
2023-01-22 23:42:30.741014: step: 1848/530, loss: 0.05672721937298775
2023-01-22 23:42:31.833868: step: 1852/530, loss: 0.2497064620256424
2023-01-22 23:42:32.975579: step: 1856/530, loss: 1.2424890995025635
2023-01-22 23:42:34.089034: step: 1860/530, loss: 2.1453628540039062
2023-01-22 23:42:35.198017: step: 1864/530, loss: 0.2790115475654602
2023-01-22 23:42:36.344678: step: 1868/530, loss: 1.2661535739898682
2023-01-22 23:42:37.459755: step: 1872/530, loss: 0.19563522934913635
2023-01-22 23:42:38.593222: step: 1876/530, loss: 0.22174735367298126
2023-01-22 23:42:39.720532: step: 1880/530, loss: 0.46822452545166016
2023-01-22 23:42:40.820346: step: 1884/530, loss: 0.29099929332733154
2023-01-22 23:42:41.937062: step: 1888/530, loss: 0.22542151808738708
2023-01-22 23:42:43.049252: step: 1892/530, loss: 0.1695103645324707
2023-01-22 23:42:44.153579: step: 1896/530, loss: 0.9925119876861572
2023-01-22 23:42:45.250737: step: 1900/530, loss: 0.7793893814086914
2023-01-22 23:42:46.364248: step: 1904/530, loss: 0.2987210154533386
2023-01-22 23:42:47.482758: step: 1908/530, loss: 0.19492071866989136
2023-01-22 23:42:48.603424: step: 1912/530, loss: 0.7757922410964966
2023-01-22 23:42:49.706270: step: 1916/530, loss: 0.6475934982299805
2023-01-22 23:42:50.829585: step: 1920/530, loss: 0.14425954222679138
2023-01-22 23:42:51.909499: step: 1924/530, loss: 8.044897079467773
2023-01-22 23:42:53.012086: step: 1928/530, loss: 0.16726180911064148
2023-01-22 23:42:54.114335: step: 1932/530, loss: 3.476111650466919
2023-01-22 23:42:55.243637: step: 1936/530, loss: 0.3560600280761719
2023-01-22 23:42:56.337127: step: 1940/530, loss: 0.385974645614624
2023-01-22 23:42:57.458396: step: 1944/530, loss: 0.18302546441555023
2023-01-22 23:42:58.550114: step: 1948/530, loss: 1.3148813247680664
2023-01-22 23:42:59.668383: step: 1952/530, loss: 1.1450821161270142
2023-01-22 23:43:00.789904: step: 1956/530, loss: 0.276010662317276
2023-01-22 23:43:01.921718: step: 1960/530, loss: 0.46828946471214294
2023-01-22 23:43:03.028056: step: 1964/530, loss: 0.10745782405138016
2023-01-22 23:43:04.129912: step: 1968/530, loss: 0.2576693296432495
2023-01-22 23:43:05.250804: step: 1972/530, loss: 0.27766895294189453
2023-01-22 23:43:06.356779: step: 1976/530, loss: 0.5240230560302734
2023-01-22 23:43:07.440303: step: 1980/530, loss: 0.3402024507522583
2023-01-22 23:43:08.535277: step: 1984/530, loss: 0.24026700854301453
2023-01-22 23:43:09.634693: step: 1988/530, loss: 0.15107068419456482
2023-01-22 23:43:10.758330: step: 1992/530, loss: 0.3911333978176117
2023-01-22 23:43:11.856006: step: 1996/530, loss: 1.0349074602127075
2023-01-22 23:43:12.969243: step: 2000/530, loss: 0.5420598983764648
2023-01-22 23:43:14.048522: step: 2004/530, loss: 0.16595658659934998
2023-01-22 23:43:15.173852: step: 2008/530, loss: 0.30934134125709534
2023-01-22 23:43:16.276004: step: 2012/530, loss: 0.844071090221405
2023-01-22 23:43:17.390499: step: 2016/530, loss: 0.5643080472946167
2023-01-22 23:43:18.507188: step: 2020/530, loss: 0.19648417830467224
2023-01-22 23:43:19.641091: step: 2024/530, loss: 0.8921326398849487
2023-01-22 23:43:20.737569: step: 2028/530, loss: 0.2289905697107315
2023-01-22 23:43:21.854780: step: 2032/530, loss: 0.4843575954437256
2023-01-22 23:43:22.970525: step: 2036/530, loss: 0.09185238182544708
2023-01-22 23:43:24.075136: step: 2040/530, loss: 0.11409693211317062
2023-01-22 23:43:25.225305: step: 2044/530, loss: 1.2405942678451538
2023-01-22 23:43:26.357168: step: 2048/530, loss: 0.7801334261894226
2023-01-22 23:43:27.454913: step: 2052/530, loss: 0.2562309503555298
2023-01-22 23:43:28.564525: step: 2056/530, loss: 0.11504669487476349
2023-01-22 23:43:29.671832: step: 2060/530, loss: 0.12310314178466797
2023-01-22 23:43:30.744114: step: 2064/530, loss: 0.24266549944877625
2023-01-22 23:43:31.837642: step: 2068/530, loss: 0.3099118769168854
2023-01-22 23:43:32.994025: step: 2072/530, loss: 1.113924264907837
2023-01-22 23:43:34.080943: step: 2076/530, loss: 0.1543026864528656
2023-01-22 23:43:35.235904: step: 2080/530, loss: 0.3281656503677368
2023-01-22 23:43:36.342022: step: 2084/530, loss: 0.145040363073349
2023-01-22 23:43:37.448442: step: 2088/530, loss: 0.20680847764015198
2023-01-22 23:43:38.544242: step: 2092/530, loss: 0.41933003067970276
2023-01-22 23:43:39.680043: step: 2096/530, loss: 0.24388772249221802
2023-01-22 23:43:40.788713: step: 2100/530, loss: 0.12686343491077423
2023-01-22 23:43:41.887371: step: 2104/530, loss: 0.1317652463912964
2023-01-22 23:43:43.000368: step: 2108/530, loss: 0.3071400821208954
2023-01-22 23:43:44.104950: step: 2112/530, loss: 0.847781777381897
2023-01-22 23:43:45.221196: step: 2116/530, loss: 0.5406198501586914
2023-01-22 23:43:46.352683: step: 2120/530, loss: 2.2067911624908447
==================================================
Loss: 0.853
--------------------
Dev: {'event': {'p': 0.5862457722660653, 'r': 0.6924101198402131, 'f1': 0.634920634920635}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Test: {'event': {'p': 0.5994652406417113, 'r': 0.6532634032634033, 'f1': 0.6252091466815394}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Chinese: {'event': {'p': 0.5303030303030303, 'r': 0.6481481481481481, 'f1': 0.5833333333333333}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Korean: {'event': {'p': 0.6190476190476191, 'r': 0.4126984126984127, 'f1': 0.49523809523809526}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Russian: {'event': {'p': 0.625, 'r': 0.4166666666666667, 'f1': 0.5}, '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': 0.5862457722660653, 'r': 0.6924101198402131, 'f1': 0.634920634920635}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Eng Test for Chinese: {'event': {'p': 0.5994652406417113, 'r': 0.6532634032634033, 'f1': 0.6252091466815394}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Sample Chinese: {'event': {'p': 0.5303030303030303, 'r': 0.6481481481481481, 'f1': 0.5833333333333333}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5862457722660653, 'r': 0.6924101198402131, 'f1': 0.634920634920635}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Eng Test for Korean: {'event': {'p': 0.5994652406417113, 'r': 0.6532634032634033, 'f1': 0.6252091466815394}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Sample Korean: {'event': {'p': 0.6190476190476191, 'r': 0.4126984126984127, 'f1': 0.49523809523809526}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5862457722660653, 'r': 0.6924101198402131, 'f1': 0.634920634920635}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Eng Test for Russian: {'event': {'p': 0.5994652406417113, 'r': 0.6532634032634033, 'f1': 0.6252091466815394}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Sample Russian: {'event': {'p': 0.625, 'r': 0.4166666666666667, 'f1': 0.5}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
******************************
Epoch: 2
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-22 23:44:45.545547: step: 4/530, loss: 0.6198540925979614
2023-01-22 23:44:46.659400: step: 8/530, loss: 1.0048609972000122
2023-01-22 23:44:47.768773: step: 12/530, loss: 0.10401640087366104
2023-01-22 23:44:48.879003: step: 16/530, loss: 0.438334196805954
2023-01-22 23:44:49.953702: step: 20/530, loss: 0.11243266612291336
2023-01-22 23:44:51.058452: step: 24/530, loss: 0.09344482421875
2023-01-22 23:44:52.149511: step: 28/530, loss: 0.0319981575012207
2023-01-22 23:44:53.278576: step: 32/530, loss: 0.8867971301078796
2023-01-22 23:44:54.398324: step: 36/530, loss: 0.07208891212940216
2023-01-22 23:44:55.502821: step: 40/530, loss: 2.2601394653320312
2023-01-22 23:44:56.599852: step: 44/530, loss: 0.2554208040237427
2023-01-22 23:44:57.701717: step: 48/530, loss: 0.5622318983078003
2023-01-22 23:44:58.841189: step: 52/530, loss: 1.9114444255828857
2023-01-22 23:44:59.958882: step: 56/530, loss: 0.22458219528198242
2023-01-22 23:45:01.083187: step: 60/530, loss: 0.376301109790802
2023-01-22 23:45:02.189806: step: 64/530, loss: 0.41722679138183594
2023-01-22 23:45:03.276412: step: 68/530, loss: 0.6288596391677856
2023-01-22 23:45:04.380574: step: 72/530, loss: 0.28783828020095825
2023-01-22 23:45:05.499168: step: 76/530, loss: 0.38284817337989807
2023-01-22 23:45:06.584176: step: 80/530, loss: 1.1731423139572144
2023-01-22 23:45:07.685528: step: 84/530, loss: 0.19999781250953674
2023-01-22 23:45:08.756154: step: 88/530, loss: 0.08881092071533203
2023-01-22 23:45:09.865179: step: 92/530, loss: 0.4845197796821594
2023-01-22 23:45:10.954895: step: 96/530, loss: 0.7929043173789978
2023-01-22 23:45:12.053580: step: 100/530, loss: 0.7115422487258911
2023-01-22 23:45:13.147628: step: 104/530, loss: 0.03243611007928848
2023-01-22 23:45:14.250806: step: 108/530, loss: 0.26674890518188477
2023-01-22 23:45:15.337855: step: 112/530, loss: 1.51459801197052
2023-01-22 23:45:16.439880: step: 116/530, loss: 0.126674085855484
2023-01-22 23:45:17.620434: step: 120/530, loss: 0.30515193939208984
2023-01-22 23:45:18.717842: step: 124/530, loss: 0.8636605143547058
2023-01-22 23:45:19.813405: step: 128/530, loss: 0.3570449650287628
2023-01-22 23:45:20.939398: step: 132/530, loss: 0.19358369708061218
2023-01-22 23:45:22.018157: step: 136/530, loss: 0.8373862504959106
2023-01-22 23:45:23.122092: step: 140/530, loss: 0.6789923906326294
2023-01-22 23:45:24.256301: step: 144/530, loss: 2.21024751663208
2023-01-22 23:45:25.364163: step: 148/530, loss: 0.19918937981128693
2023-01-22 23:45:26.502371: step: 152/530, loss: 0.24911203980445862
2023-01-22 23:45:27.596978: step: 156/530, loss: 0.6159843802452087
2023-01-22 23:45:28.725216: step: 160/530, loss: 0.15210619568824768
2023-01-22 23:45:29.822403: step: 164/530, loss: 1.9229626655578613
2023-01-22 23:45:30.915069: step: 168/530, loss: 0.4069795608520508
2023-01-22 23:45:32.030080: step: 172/530, loss: 0.6554365158081055
2023-01-22 23:45:33.176491: step: 176/530, loss: 1.0374741554260254
2023-01-22 23:45:34.271857: step: 180/530, loss: 0.44456160068511963
2023-01-22 23:45:35.410895: step: 184/530, loss: 0.44057178497314453
2023-01-22 23:45:36.496466: step: 188/530, loss: 0.07241783291101456
2023-01-22 23:45:37.601131: step: 192/530, loss: 0.0739767998456955
2023-01-22 23:45:38.717384: step: 196/530, loss: 0.17059560120105743
2023-01-22 23:45:39.828275: step: 200/530, loss: 0.10765685886144638
2023-01-22 23:45:40.936200: step: 204/530, loss: 0.3262357711791992
2023-01-22 23:45:42.041258: step: 208/530, loss: 0.20020842552185059
2023-01-22 23:45:43.154210: step: 212/530, loss: 0.5621374845504761
2023-01-22 23:45:44.284767: step: 216/530, loss: 0.3833032548427582
2023-01-22 23:45:45.363863: step: 220/530, loss: 0.2669598460197449
2023-01-22 23:45:46.503655: step: 224/530, loss: 0.38778916001319885
2023-01-22 23:45:47.624299: step: 228/530, loss: 0.19167184829711914
2023-01-22 23:45:48.752293: step: 232/530, loss: 0.7273862957954407
2023-01-22 23:45:49.861532: step: 236/530, loss: 0.18002071976661682
2023-01-22 23:45:50.967395: step: 240/530, loss: 0.3420677185058594
2023-01-22 23:45:52.092623: step: 244/530, loss: 0.6326888799667358
2023-01-22 23:45:53.248533: step: 248/530, loss: 0.1943381279706955
2023-01-22 23:45:54.370006: step: 252/530, loss: 0.7952607274055481
2023-01-22 23:45:55.470989: step: 256/530, loss: 0.204506978392601
2023-01-22 23:45:56.607658: step: 260/530, loss: 0.44783174991607666
2023-01-22 23:45:57.711346: step: 264/530, loss: 0.3366151452064514
2023-01-22 23:45:58.842396: step: 268/530, loss: 6.446836948394775
2023-01-22 23:45:59.980641: step: 272/530, loss: 1.0232226848602295
2023-01-22 23:46:01.085710: step: 276/530, loss: 0.7964997291564941
2023-01-22 23:46:02.204291: step: 280/530, loss: 0.5236971974372864
2023-01-22 23:46:03.332841: step: 284/530, loss: 0.3770301938056946
2023-01-22 23:46:04.454762: step: 288/530, loss: 0.404171347618103
2023-01-22 23:46:05.567461: step: 292/530, loss: 0.32622891664505005
2023-01-22 23:46:06.689426: step: 296/530, loss: 1.228914499282837
2023-01-22 23:46:07.795991: step: 300/530, loss: 0.21097077429294586
2023-01-22 23:46:08.914962: step: 304/530, loss: 0.5476157069206238
2023-01-22 23:46:10.036378: step: 308/530, loss: 0.7025691866874695
2023-01-22 23:46:11.132071: step: 312/530, loss: 0.459287166595459
2023-01-22 23:46:12.275743: step: 316/530, loss: 0.1931048035621643
2023-01-22 23:46:13.417795: step: 320/530, loss: 0.1928127259016037
2023-01-22 23:46:14.528919: step: 324/530, loss: 0.41293030977249146
2023-01-22 23:46:15.614281: step: 328/530, loss: 0.7993488311767578
2023-01-22 23:46:16.707399: step: 332/530, loss: 0.219730943441391
2023-01-22 23:46:17.779102: step: 336/530, loss: 0.2729508578777313
2023-01-22 23:46:18.918519: step: 340/530, loss: 0.968357503414154
2023-01-22 23:46:20.023521: step: 344/530, loss: 1.211496353149414
2023-01-22 23:46:21.117079: step: 348/530, loss: 0.1360091269016266
2023-01-22 23:46:22.203300: step: 352/530, loss: 0.1271168738603592
2023-01-22 23:46:23.328487: step: 356/530, loss: 0.21786938607692719
2023-01-22 23:46:24.464719: step: 360/530, loss: 0.758103609085083
2023-01-22 23:46:25.592382: step: 364/530, loss: 0.35645848512649536
2023-01-22 23:46:26.737613: step: 368/530, loss: 0.12861737608909607
2023-01-22 23:46:27.812454: step: 372/530, loss: 0.15587054193019867
2023-01-22 23:46:28.912665: step: 376/530, loss: 0.21404004096984863
2023-01-22 23:46:30.008761: step: 380/530, loss: 0.1603788584470749
2023-01-22 23:46:31.116097: step: 384/530, loss: 0.852162778377533
2023-01-22 23:46:32.259564: step: 388/530, loss: 0.14658966660499573
2023-01-22 23:46:33.370516: step: 392/530, loss: 0.07474938035011292
2023-01-22 23:46:34.480052: step: 396/530, loss: 0.17949095368385315
2023-01-22 23:46:35.578772: step: 400/530, loss: 0.3295811712741852
2023-01-22 23:46:36.672257: step: 404/530, loss: 0.041338253766298294
2023-01-22 23:46:37.766141: step: 408/530, loss: 0.0775061622262001
2023-01-22 23:46:38.863032: step: 412/530, loss: 0.8199677467346191
2023-01-22 23:46:39.965125: step: 416/530, loss: 0.2995205819606781
2023-01-22 23:46:41.056073: step: 420/530, loss: 0.07244706153869629
2023-01-22 23:46:42.150021: step: 424/530, loss: 0.2044380158185959
2023-01-22 23:46:43.262138: step: 428/530, loss: 0.15572519600391388
2023-01-22 23:46:44.368343: step: 432/530, loss: 0.1981772929430008
2023-01-22 23:46:45.481001: step: 436/530, loss: 0.7305552363395691
2023-01-22 23:46:46.619494: step: 440/530, loss: 0.3490244150161743
2023-01-22 23:46:47.718767: step: 444/530, loss: 0.12870512902736664
2023-01-22 23:46:48.808453: step: 448/530, loss: 0.5862518548965454
2023-01-22 23:46:49.951585: step: 452/530, loss: 1.2806965112686157
2023-01-22 23:46:51.059792: step: 456/530, loss: 0.7453708052635193
2023-01-22 23:46:52.170577: step: 460/530, loss: 2.356369972229004
2023-01-22 23:46:53.256311: step: 464/530, loss: 0.37028247117996216
2023-01-22 23:46:54.354761: step: 468/530, loss: 0.1040465384721756
2023-01-22 23:46:55.455571: step: 472/530, loss: 0.2980291247367859
2023-01-22 23:46:56.574786: step: 476/530, loss: 0.4111400842666626
2023-01-22 23:46:57.689162: step: 480/530, loss: 1.046571969985962
2023-01-22 23:46:58.804924: step: 484/530, loss: 0.12694759666919708
2023-01-22 23:46:59.949417: step: 488/530, loss: 0.4188306927680969
2023-01-22 23:47:01.061707: step: 492/530, loss: 0.16274185478687286
2023-01-22 23:47:02.148884: step: 496/530, loss: 1.4421719312667847
2023-01-22 23:47:03.254646: step: 500/530, loss: 0.5529559254646301
2023-01-22 23:47:04.399204: step: 504/530, loss: 1.087599515914917
2023-01-22 23:47:05.486477: step: 508/530, loss: 0.8141428828239441
2023-01-22 23:47:06.604506: step: 512/530, loss: 0.15626506507396698
2023-01-22 23:47:07.690866: step: 516/530, loss: 0.463449090719223
2023-01-22 23:47:08.787976: step: 520/530, loss: 0.17906340956687927
2023-01-22 23:47:09.896423: step: 524/530, loss: 0.18124504387378693
2023-01-22 23:47:11.004289: step: 528/530, loss: 0.8169660568237305
2023-01-22 23:47:12.137572: step: 532/530, loss: 0.08687052875757217
2023-01-22 23:47:13.262007: step: 536/530, loss: 0.34089356660842896
2023-01-22 23:47:14.406946: step: 540/530, loss: 6.535667419433594
2023-01-22 23:47:15.480570: step: 544/530, loss: 0.13303260505199432
2023-01-22 23:47:16.566268: step: 548/530, loss: 0.8227423429489136
2023-01-22 23:47:17.694410: step: 552/530, loss: 2.0486085414886475
2023-01-22 23:47:18.789992: step: 556/530, loss: 1.2675211429595947
2023-01-22 23:47:19.904623: step: 560/530, loss: 0.12148484587669373
2023-01-22 23:47:21.032161: step: 564/530, loss: 0.1736951768398285
2023-01-22 23:47:22.170677: step: 568/530, loss: 0.22327347099781036
2023-01-22 23:47:23.280236: step: 572/530, loss: 0.3861965835094452
2023-01-22 23:47:24.371838: step: 576/530, loss: 0.5449054837226868
2023-01-22 23:47:25.488279: step: 580/530, loss: 0.7828955054283142
2023-01-22 23:47:26.589255: step: 584/530, loss: 0.18622727692127228
2023-01-22 23:47:27.716928: step: 588/530, loss: 0.4909900724887848
2023-01-22 23:47:28.813497: step: 592/530, loss: 0.12133082747459412
2023-01-22 23:47:29.946937: step: 596/530, loss: 0.5887743234634399
2023-01-22 23:47:31.056426: step: 600/530, loss: 0.718548059463501
2023-01-22 23:47:32.147242: step: 604/530, loss: 0.6871337890625
2023-01-22 23:47:33.254803: step: 608/530, loss: 1.932072639465332
2023-01-22 23:47:34.334468: step: 612/530, loss: 0.09411783516407013
2023-01-22 23:47:35.428140: step: 616/530, loss: 6.547301769256592
2023-01-22 23:47:36.564448: step: 620/530, loss: 0.11248989403247833
2023-01-22 23:47:37.660755: step: 624/530, loss: 0.65790855884552
2023-01-22 23:47:38.776248: step: 628/530, loss: 0.42045754194259644
2023-01-22 23:47:39.876065: step: 632/530, loss: 0.235052689909935
2023-01-22 23:47:40.987634: step: 636/530, loss: 1.0346062183380127
2023-01-22 23:47:42.097409: step: 640/530, loss: 0.34569817781448364
2023-01-22 23:47:43.198389: step: 644/530, loss: 0.1865081787109375
2023-01-22 23:47:44.301397: step: 648/530, loss: 1.367523431777954
2023-01-22 23:47:45.431634: step: 652/530, loss: 1.7905677556991577
2023-01-22 23:47:46.536457: step: 656/530, loss: 0.26142510771751404
2023-01-22 23:47:47.657258: step: 660/530, loss: 0.1052650511264801
2023-01-22 23:47:48.741204: step: 664/530, loss: 0.06505956500768661
2023-01-22 23:47:49.861879: step: 668/530, loss: 0.3729133605957031
2023-01-22 23:47:50.965685: step: 672/530, loss: 1.1665695905685425
2023-01-22 23:47:52.062681: step: 676/530, loss: 6.638486862182617
2023-01-22 23:47:53.151468: step: 680/530, loss: 0.2751946449279785
2023-01-22 23:47:54.262972: step: 684/530, loss: 1.2329219579696655
2023-01-22 23:47:55.394161: step: 688/530, loss: 1.2752113342285156
2023-01-22 23:47:56.492254: step: 692/530, loss: 0.14408570528030396
2023-01-22 23:47:57.588434: step: 696/530, loss: 0.1870080530643463
2023-01-22 23:47:58.718119: step: 700/530, loss: 0.10327625274658203
2023-01-22 23:47:59.826460: step: 704/530, loss: 0.08513936400413513
2023-01-22 23:48:00.932408: step: 708/530, loss: 0.13387763500213623
2023-01-22 23:48:02.055571: step: 712/530, loss: 0.20930396020412445
2023-01-22 23:48:03.180164: step: 716/530, loss: 0.0390867218375206
2023-01-22 23:48:04.274061: step: 720/530, loss: 0.1083621084690094
2023-01-22 23:48:05.401534: step: 724/530, loss: 0.21164169907569885
2023-01-22 23:48:06.517145: step: 728/530, loss: 1.0349600315093994
2023-01-22 23:48:07.640318: step: 732/530, loss: 0.7430177330970764
2023-01-22 23:48:08.753062: step: 736/530, loss: 0.9095494747161865
2023-01-22 23:48:09.828291: step: 740/530, loss: 0.17585691809654236
2023-01-22 23:48:10.912740: step: 744/530, loss: 0.1105884537100792
2023-01-22 23:48:12.040962: step: 748/530, loss: 0.3017406165599823
2023-01-22 23:48:13.172840: step: 752/530, loss: 1.8819596767425537
2023-01-22 23:48:14.298296: step: 756/530, loss: 0.08317108452320099
2023-01-22 23:48:15.392373: step: 760/530, loss: 0.11746960133314133
2023-01-22 23:48:16.485691: step: 764/530, loss: 0.3329296112060547
2023-01-22 23:48:17.603174: step: 768/530, loss: 0.7258298993110657
2023-01-22 23:48:18.707246: step: 772/530, loss: 0.6615149974822998
2023-01-22 23:48:19.782243: step: 776/530, loss: 0.42301470041275024
2023-01-22 23:48:20.876966: step: 780/530, loss: 0.7776275873184204
2023-01-22 23:48:21.975245: step: 784/530, loss: 0.277630478143692
2023-01-22 23:48:23.076407: step: 788/530, loss: 0.11778479069471359
2023-01-22 23:48:24.168702: step: 792/530, loss: 0.546926736831665
2023-01-22 23:48:25.260523: step: 796/530, loss: 0.187687486410141
2023-01-22 23:48:26.353964: step: 800/530, loss: 1.0700546503067017
2023-01-22 23:48:27.448998: step: 804/530, loss: 0.16792288422584534
2023-01-22 23:48:28.573571: step: 808/530, loss: 0.4400085508823395
2023-01-22 23:48:29.715204: step: 812/530, loss: 0.4263395369052887
2023-01-22 23:48:30.843270: step: 816/530, loss: 0.8427593111991882
2023-01-22 23:48:31.925969: step: 820/530, loss: 0.18162737786769867
2023-01-22 23:48:33.044234: step: 824/530, loss: 0.17045126855373383
2023-01-22 23:48:34.141677: step: 828/530, loss: 0.21789920330047607
2023-01-22 23:48:35.289304: step: 832/530, loss: 0.33441415429115295
2023-01-22 23:48:36.396173: step: 836/530, loss: 0.4782443046569824
2023-01-22 23:48:37.484401: step: 840/530, loss: 0.2746063768863678
2023-01-22 23:48:38.613751: step: 844/530, loss: 0.10232143849134445
2023-01-22 23:48:39.731619: step: 848/530, loss: 0.3500874638557434
2023-01-22 23:48:40.836769: step: 852/530, loss: 0.46785441040992737
2023-01-22 23:48:41.949963: step: 856/530, loss: 1.894441843032837
2023-01-22 23:48:43.076484: step: 860/530, loss: 1.593152403831482
2023-01-22 23:48:44.187061: step: 864/530, loss: 1.164519190788269
2023-01-22 23:48:45.323831: step: 868/530, loss: 1.2089849710464478
2023-01-22 23:48:46.410628: step: 872/530, loss: 1.041414499282837
2023-01-22 23:48:47.500103: step: 876/530, loss: 0.07045307010412216
2023-01-22 23:48:48.610318: step: 880/530, loss: 0.17739133536815643
2023-01-22 23:48:49.705452: step: 884/530, loss: 0.12095470726490021
2023-01-22 23:48:50.849112: step: 888/530, loss: 0.18453478813171387
2023-01-22 23:48:51.975564: step: 892/530, loss: 0.18750068545341492
2023-01-22 23:48:53.075459: step: 896/530, loss: 0.6000241041183472
2023-01-22 23:48:54.173207: step: 900/530, loss: 0.7636511325836182
2023-01-22 23:48:55.293380: step: 904/530, loss: 0.4843316078186035
2023-01-22 23:48:56.384671: step: 908/530, loss: 2.582265853881836
2023-01-22 23:48:57.493258: step: 912/530, loss: 0.12574473023414612
2023-01-22 23:48:58.609891: step: 916/530, loss: 0.8842158913612366
2023-01-22 23:48:59.728396: step: 920/530, loss: 1.2186427116394043
2023-01-22 23:49:00.824403: step: 924/530, loss: 0.3755435347557068
2023-01-22 23:49:01.954920: step: 928/530, loss: 1.015951156616211
2023-01-22 23:49:03.059809: step: 932/530, loss: 0.3734275698661804
2023-01-22 23:49:04.181371: step: 936/530, loss: 0.12297917157411575
2023-01-22 23:49:05.310301: step: 940/530, loss: 0.3472760319709778
2023-01-22 23:49:06.432412: step: 944/530, loss: 0.11199600994586945
2023-01-22 23:49:07.548983: step: 948/530, loss: 0.27879610657691956
2023-01-22 23:49:08.646182: step: 952/530, loss: 0.4406503438949585
2023-01-22 23:49:09.741019: step: 956/530, loss: 0.6585742831230164
2023-01-22 23:49:10.840649: step: 960/530, loss: 0.34480369091033936
2023-01-22 23:49:11.936948: step: 964/530, loss: 0.23266686499118805
2023-01-22 23:49:13.090941: step: 968/530, loss: 1.4316868782043457
2023-01-22 23:49:14.190394: step: 972/530, loss: 0.6266285181045532
2023-01-22 23:49:15.276298: step: 976/530, loss: 0.6873924732208252
2023-01-22 23:49:16.393740: step: 980/530, loss: 0.1926651895046234
2023-01-22 23:49:17.476068: step: 984/530, loss: 0.36933737993240356
2023-01-22 23:49:18.568671: step: 988/530, loss: 1.355558156967163
2023-01-22 23:49:19.687083: step: 992/530, loss: 0.18986168503761292
2023-01-22 23:49:20.763638: step: 996/530, loss: 0.2724820375442505
2023-01-22 23:49:21.849836: step: 1000/530, loss: 0.7138489484786987
2023-01-22 23:49:22.971048: step: 1004/530, loss: 0.908253014087677
2023-01-22 23:49:24.062314: step: 1008/530, loss: 0.3453788757324219
2023-01-22 23:49:25.160094: step: 1012/530, loss: 0.26265090703964233
2023-01-22 23:49:26.282518: step: 1016/530, loss: 0.36064577102661133
2023-01-22 23:49:27.418176: step: 1020/530, loss: 1.2133195400238037
2023-01-22 23:49:28.510778: step: 1024/530, loss: 0.3026450276374817
2023-01-22 23:49:29.625144: step: 1028/530, loss: 0.5732296109199524
2023-01-22 23:49:30.740977: step: 1032/530, loss: 0.2008655071258545
2023-01-22 23:49:31.847630: step: 1036/530, loss: 0.2666444778442383
2023-01-22 23:49:32.980421: step: 1040/530, loss: 0.18301087617874146
2023-01-22 23:49:34.095908: step: 1044/530, loss: 0.371789813041687
2023-01-22 23:49:35.206193: step: 1048/530, loss: 0.2604500353336334
2023-01-22 23:49:36.295871: step: 1052/530, loss: 1.2724806070327759
2023-01-22 23:49:37.426130: step: 1056/530, loss: 0.2205449640750885
2023-01-22 23:49:38.518125: step: 1060/530, loss: 0.7035865783691406
2023-01-22 23:49:39.622759: step: 1064/530, loss: 0.3009626269340515
2023-01-22 23:49:40.719425: step: 1068/530, loss: 0.12284322082996368
2023-01-22 23:49:41.802081: step: 1072/530, loss: 0.025849152356386185
2023-01-22 23:49:42.948100: step: 1076/530, loss: 0.20307540893554688
2023-01-22 23:49:44.059814: step: 1080/530, loss: 0.15127727389335632
2023-01-22 23:49:45.165142: step: 1084/530, loss: 0.8298312425613403
2023-01-22 23:49:46.289977: step: 1088/530, loss: 0.3243715465068817
2023-01-22 23:49:47.386414: step: 1092/530, loss: 0.13563761115074158
2023-01-22 23:49:48.535208: step: 1096/530, loss: 0.39865627884864807
2023-01-22 23:49:49.655869: step: 1100/530, loss: 2.1657986640930176
2023-01-22 23:49:50.789365: step: 1104/530, loss: 0.6220483779907227
2023-01-22 23:49:51.884715: step: 1108/530, loss: 0.15092018246650696
2023-01-22 23:49:53.007444: step: 1112/530, loss: 0.14293909072875977
2023-01-22 23:49:54.109980: step: 1116/530, loss: 0.08171799778938293
2023-01-22 23:49:55.247879: step: 1120/530, loss: 0.8029688596725464
2023-01-22 23:49:56.363013: step: 1124/530, loss: 0.6350871920585632
2023-01-22 23:49:57.448771: step: 1128/530, loss: 1.74811589717865
2023-01-22 23:49:58.543566: step: 1132/530, loss: 0.8058034777641296
2023-01-22 23:49:59.612621: step: 1136/530, loss: 0.08519790321588516
2023-01-22 23:50:00.726798: step: 1140/530, loss: 0.15289148688316345
2023-01-22 23:50:01.865075: step: 1144/530, loss: 3.25345516204834
2023-01-22 23:50:02.950507: step: 1148/530, loss: 0.06894493103027344
2023-01-22 23:50:04.066238: step: 1152/530, loss: 0.19806723296642303
2023-01-22 23:50:05.187220: step: 1156/530, loss: 0.7688921093940735
2023-01-22 23:50:06.315207: step: 1160/530, loss: 1.1888424158096313
2023-01-22 23:50:07.427783: step: 1164/530, loss: 0.7915208339691162
2023-01-22 23:50:08.499677: step: 1168/530, loss: 0.1744750291109085
2023-01-22 23:50:09.580275: step: 1172/530, loss: 0.31733790040016174
2023-01-22 23:50:10.687263: step: 1176/530, loss: 0.17006739974021912
2023-01-22 23:50:11.800781: step: 1180/530, loss: 0.1752881109714508
2023-01-22 23:50:12.893985: step: 1184/530, loss: 0.10659889876842499
2023-01-22 23:50:13.993471: step: 1188/530, loss: 0.16496124863624573
2023-01-22 23:50:15.098832: step: 1192/530, loss: 0.08374490588903427
2023-01-22 23:50:16.237736: step: 1196/530, loss: 0.48457127809524536
2023-01-22 23:50:17.354133: step: 1200/530, loss: 0.86629718542099
2023-01-22 23:50:18.476529: step: 1204/530, loss: 1.7148301601409912
2023-01-22 23:50:19.575276: step: 1208/530, loss: 0.310912549495697
2023-01-22 23:50:20.701779: step: 1212/530, loss: 1.1179625988006592
2023-01-22 23:50:21.809040: step: 1216/530, loss: 0.2113800048828125
2023-01-22 23:50:22.922644: step: 1220/530, loss: 0.8314051628112793
2023-01-22 23:50:24.080067: step: 1224/530, loss: 1.0424354076385498
2023-01-22 23:50:25.210012: step: 1228/530, loss: 0.26289093494415283
2023-01-22 23:50:26.331527: step: 1232/530, loss: 0.13936421275138855
2023-01-22 23:50:27.414973: step: 1236/530, loss: 0.033315420150756836
2023-01-22 23:50:28.537062: step: 1240/530, loss: 0.191107839345932
2023-01-22 23:50:29.640435: step: 1244/530, loss: 0.13199162483215332
2023-01-22 23:50:30.774217: step: 1248/530, loss: 0.6805388927459717
2023-01-22 23:50:31.885178: step: 1252/530, loss: 0.5157516598701477
2023-01-22 23:50:32.997957: step: 1256/530, loss: 0.05537543445825577
2023-01-22 23:50:34.116095: step: 1260/530, loss: 0.2065807282924652
2023-01-22 23:50:35.252055: step: 1264/530, loss: 0.1371023952960968
2023-01-22 23:50:36.383286: step: 1268/530, loss: 0.20539751648902893
2023-01-22 23:50:37.467418: step: 1272/530, loss: 0.9061517119407654
2023-01-22 23:50:38.579907: step: 1276/530, loss: 0.16917529702186584
2023-01-22 23:50:39.651130: step: 1280/530, loss: 1.4723564386367798
2023-01-22 23:50:40.776791: step: 1284/530, loss: 3.0508389472961426
2023-01-22 23:50:41.912137: step: 1288/530, loss: 0.44625329971313477
2023-01-22 23:50:43.020392: step: 1292/530, loss: 0.799186646938324
2023-01-22 23:50:44.126811: step: 1296/530, loss: 0.31967276334762573
2023-01-22 23:50:45.264037: step: 1300/530, loss: 7.707324028015137
2023-01-22 23:50:46.382153: step: 1304/530, loss: 1.2140929698944092
2023-01-22 23:50:47.506818: step: 1308/530, loss: 0.9212249517440796
2023-01-22 23:50:48.617658: step: 1312/530, loss: 0.13182592391967773
2023-01-22 23:50:49.732617: step: 1316/530, loss: 0.1441677212715149
2023-01-22 23:50:50.828020: step: 1320/530, loss: 0.13301211595535278
2023-01-22 23:50:51.935820: step: 1324/530, loss: 0.7749804854393005
2023-01-22 23:50:53.025728: step: 1328/530, loss: 0.22777405381202698
2023-01-22 23:50:54.144474: step: 1332/530, loss: 0.6694890856742859
2023-01-22 23:50:55.234032: step: 1336/530, loss: 0.7204827666282654
2023-01-22 23:50:56.362584: step: 1340/530, loss: 0.5952070951461792
2023-01-22 23:50:57.443057: step: 1344/530, loss: 1.0272674560546875
2023-01-22 23:50:58.532283: step: 1348/530, loss: 0.13400086760520935
2023-01-22 23:50:59.637285: step: 1352/530, loss: 0.05876760929822922
2023-01-22 23:51:00.779877: step: 1356/530, loss: 0.14156198501586914
2023-01-22 23:51:01.898586: step: 1360/530, loss: 0.27535486221313477
2023-01-22 23:51:02.995012: step: 1364/530, loss: 0.7866953611373901
2023-01-22 23:51:04.103137: step: 1368/530, loss: 0.7986108660697937
2023-01-22 23:51:05.196839: step: 1372/530, loss: 0.12173084914684296
2023-01-22 23:51:06.313019: step: 1376/530, loss: 3.3247289657592773
2023-01-22 23:51:07.453298: step: 1380/530, loss: 0.1582363098859787
2023-01-22 23:51:08.555691: step: 1384/530, loss: 0.32090091705322266
2023-01-22 23:51:09.697375: step: 1388/530, loss: 0.31660154461860657
2023-01-22 23:51:10.781728: step: 1392/530, loss: 0.11389555782079697
2023-01-22 23:51:11.873423: step: 1396/530, loss: 6.792057037353516
2023-01-22 23:51:12.976547: step: 1400/530, loss: 0.3331029415130615
2023-01-22 23:51:14.074219: step: 1404/530, loss: 0.13430070877075195
2023-01-22 23:51:15.200991: step: 1408/530, loss: 0.7255303263664246
2023-01-22 23:51:16.340619: step: 1412/530, loss: 0.17140713334083557
2023-01-22 23:51:17.426507: step: 1416/530, loss: 0.24750347435474396
2023-01-22 23:51:18.525807: step: 1420/530, loss: 0.01286692637950182
2023-01-22 23:51:19.649359: step: 1424/530, loss: 0.2532024383544922
2023-01-22 23:51:20.775540: step: 1428/530, loss: 0.36322012543678284
2023-01-22 23:51:21.891298: step: 1432/530, loss: 0.33569908142089844
2023-01-22 23:51:22.997273: step: 1436/530, loss: 0.47951623797416687
2023-01-22 23:51:24.063955: step: 1440/530, loss: 0.025391483679413795
2023-01-22 23:51:25.186928: step: 1444/530, loss: 0.43312615156173706
2023-01-22 23:51:26.270200: step: 1448/530, loss: 0.4438081979751587
2023-01-22 23:51:27.376960: step: 1452/530, loss: 0.5172765851020813
2023-01-22 23:51:28.464006: step: 1456/530, loss: 0.8032631278038025
2023-01-22 23:51:29.569152: step: 1460/530, loss: 0.18786612153053284
2023-01-22 23:51:30.684207: step: 1464/530, loss: 0.29978665709495544
2023-01-22 23:51:31.804695: step: 1468/530, loss: 0.10103187710046768
2023-01-22 23:51:32.943658: step: 1472/530, loss: 0.5985674858093262
2023-01-22 23:51:34.046018: step: 1476/530, loss: 1.6050618886947632
2023-01-22 23:51:35.145588: step: 1480/530, loss: 0.43668365478515625
2023-01-22 23:51:36.245849: step: 1484/530, loss: 0.3208683133125305
2023-01-22 23:51:37.336267: step: 1488/530, loss: 0.21678543090820312
2023-01-22 23:51:38.448609: step: 1492/530, loss: 0.2097928524017334
2023-01-22 23:51:39.568016: step: 1496/530, loss: 0.09417438507080078
2023-01-22 23:51:40.660903: step: 1500/530, loss: 0.3144418001174927
2023-01-22 23:51:41.760826: step: 1504/530, loss: 0.4504164159297943
2023-01-22 23:51:42.873150: step: 1508/530, loss: 0.1631878912448883
2023-01-22 23:51:43.955902: step: 1512/530, loss: 0.20983830094337463
2023-01-22 23:51:45.048916: step: 1516/530, loss: 0.8044927716255188
2023-01-22 23:51:46.143179: step: 1520/530, loss: 0.8216346502304077
2023-01-22 23:51:47.243571: step: 1524/530, loss: 1.2991403341293335
2023-01-22 23:51:48.385380: step: 1528/530, loss: 0.4122229814529419
2023-01-22 23:51:49.500926: step: 1532/530, loss: 0.12231931835412979
2023-01-22 23:51:50.595917: step: 1536/530, loss: 6.115550518035889
2023-01-22 23:51:51.724499: step: 1540/530, loss: 0.26710453629493713
2023-01-22 23:51:52.833392: step: 1544/530, loss: 0.8378282785415649
2023-01-22 23:51:53.952046: step: 1548/530, loss: 0.5501583814620972
2023-01-22 23:51:55.074139: step: 1552/530, loss: 0.4130508303642273
2023-01-22 23:51:56.173208: step: 1556/530, loss: 0.21987763047218323
2023-01-22 23:51:57.273276: step: 1560/530, loss: 0.11682038754224777
2023-01-22 23:51:58.384886: step: 1564/530, loss: 0.09674187004566193
2023-01-22 23:51:59.484220: step: 1568/530, loss: 1.7349060773849487
2023-01-22 23:52:00.578288: step: 1572/530, loss: 0.3750064969062805
2023-01-22 23:52:01.664023: step: 1576/530, loss: 0.4631040692329407
2023-01-22 23:52:02.784361: step: 1580/530, loss: 0.16033217310905457
2023-01-22 23:52:03.924684: step: 1584/530, loss: 0.8398206830024719
2023-01-22 23:52:05.036309: step: 1588/530, loss: 0.20990324020385742
2023-01-22 23:52:06.156544: step: 1592/530, loss: 0.06987433135509491
2023-01-22 23:52:07.263866: step: 1596/530, loss: 0.09451308846473694
2023-01-22 23:52:08.369665: step: 1600/530, loss: 1.1601035594940186
2023-01-22 23:52:09.454475: step: 1604/530, loss: 0.7201159596443176
2023-01-22 23:52:10.553057: step: 1608/530, loss: 0.22964802384376526
2023-01-22 23:52:11.637607: step: 1612/530, loss: 0.9415991306304932
2023-01-22 23:52:12.756647: step: 1616/530, loss: 0.1375083029270172
2023-01-22 23:52:13.867537: step: 1620/530, loss: 1.0645108222961426
2023-01-22 23:52:14.988141: step: 1624/530, loss: 0.07066698372364044
2023-01-22 23:52:16.099506: step: 1628/530, loss: 0.26522818207740784
2023-01-22 23:52:17.188886: step: 1632/530, loss: 0.15551725029945374
2023-01-22 23:52:18.289738: step: 1636/530, loss: 6.2453484535217285
2023-01-22 23:52:19.393716: step: 1640/530, loss: 1.4349058866500854
2023-01-22 23:52:20.535073: step: 1644/530, loss: 0.38430824875831604
2023-01-22 23:52:21.680479: step: 1648/530, loss: 0.0386800542473793
2023-01-22 23:52:22.778059: step: 1652/530, loss: 0.9878458976745605
2023-01-22 23:52:23.924408: step: 1656/530, loss: 0.4824739396572113
2023-01-22 23:52:25.030130: step: 1660/530, loss: 0.21563193202018738
2023-01-22 23:52:26.147057: step: 1664/530, loss: 0.652431070804596
2023-01-22 23:52:27.236515: step: 1668/530, loss: 0.1932518035173416
2023-01-22 23:52:28.353797: step: 1672/530, loss: 1.0132458209991455
2023-01-22 23:52:29.463270: step: 1676/530, loss: 1.3405945301055908
2023-01-22 23:52:30.573826: step: 1680/530, loss: 1.7321339845657349
2023-01-22 23:52:31.696230: step: 1684/530, loss: 0.21302028000354767
2023-01-22 23:52:32.806152: step: 1688/530, loss: 0.17731493711471558
2023-01-22 23:52:33.944271: step: 1692/530, loss: 0.787173867225647
2023-01-22 23:52:35.047036: step: 1696/530, loss: 0.06732568144798279
2023-01-22 23:52:36.152571: step: 1700/530, loss: 1.5915964841842651
2023-01-22 23:52:37.237592: step: 1704/530, loss: 0.15503031015396118
2023-01-22 23:52:38.310261: step: 1708/530, loss: 0.39534908533096313
2023-01-22 23:52:39.412832: step: 1712/530, loss: 0.7797166705131531
2023-01-22 23:52:40.520073: step: 1716/530, loss: 0.302786648273468
2023-01-22 23:52:41.628556: step: 1720/530, loss: 0.14499126374721527
2023-01-22 23:52:42.748674: step: 1724/530, loss: 0.20327195525169373
2023-01-22 23:52:43.853267: step: 1728/530, loss: 0.19121117889881134
2023-01-22 23:52:44.952719: step: 1732/530, loss: 0.07347283512353897
2023-01-22 23:52:46.082074: step: 1736/530, loss: 0.2325085550546646
2023-01-22 23:52:47.189465: step: 1740/530, loss: 0.33194389939308167
2023-01-22 23:52:48.305049: step: 1744/530, loss: 0.4896666705608368
2023-01-22 23:52:49.452138: step: 1748/530, loss: 2.7166733741760254
2023-01-22 23:52:50.571990: step: 1752/530, loss: 0.2241843342781067
2023-01-22 23:52:51.644429: step: 1756/530, loss: 0.0913543701171875
2023-01-22 23:52:52.762631: step: 1760/530, loss: 0.18727102875709534
2023-01-22 23:52:53.869701: step: 1764/530, loss: 0.12417125701904297
2023-01-22 23:52:54.972906: step: 1768/530, loss: 1.0505057573318481
2023-01-22 23:52:56.092109: step: 1772/530, loss: 0.22307834029197693
2023-01-22 23:52:57.178380: step: 1776/530, loss: 0.7313587665557861
2023-01-22 23:52:58.310174: step: 1780/530, loss: 0.34805068373680115
2023-01-22 23:52:59.416762: step: 1784/530, loss: 0.3424035906791687
2023-01-22 23:53:00.538545: step: 1788/530, loss: 0.2975238859653473
2023-01-22 23:53:01.631268: step: 1792/530, loss: 0.12273558974266052
2023-01-22 23:53:02.729183: step: 1796/530, loss: 0.24811871349811554
2023-01-22 23:53:03.820282: step: 1800/530, loss: 0.1386135071516037
2023-01-22 23:53:04.925132: step: 1804/530, loss: 0.6006054878234863
2023-01-22 23:53:06.066349: step: 1808/530, loss: 1.1441017389297485
2023-01-22 23:53:07.203563: step: 1812/530, loss: 0.364539235830307
2023-01-22 23:53:08.296950: step: 1816/530, loss: 0.11590547859668732
2023-01-22 23:53:09.399135: step: 1820/530, loss: 0.08323030173778534
2023-01-22 23:53:10.483077: step: 1824/530, loss: 0.09578351676464081
2023-01-22 23:53:11.623174: step: 1828/530, loss: 0.3374289572238922
2023-01-22 23:53:12.741687: step: 1832/530, loss: 0.7044450640678406
2023-01-22 23:53:13.886199: step: 1836/530, loss: 0.18089938163757324
2023-01-22 23:53:14.994054: step: 1840/530, loss: 0.1571328192949295
2023-01-22 23:53:16.111806: step: 1844/530, loss: 0.21182399988174438
2023-01-22 23:53:17.220269: step: 1848/530, loss: 6.119668960571289
2023-01-22 23:53:18.308271: step: 1852/530, loss: 1.066497802734375
2023-01-22 23:53:19.434186: step: 1856/530, loss: 0.10223408043384552
2023-01-22 23:53:20.555985: step: 1860/530, loss: 0.8984768390655518
2023-01-22 23:53:21.667667: step: 1864/530, loss: 0.39403578639030457
2023-01-22 23:53:22.823511: step: 1868/530, loss: 1.492438554763794
2023-01-22 23:53:23.928609: step: 1872/530, loss: 0.1259802281856537
2023-01-22 23:53:25.017596: step: 1876/530, loss: 0.792575478553772
2023-01-22 23:53:26.113767: step: 1880/530, loss: 0.123436838388443
2023-01-22 23:53:27.253275: step: 1884/530, loss: 0.9703875780105591
2023-01-22 23:53:28.396096: step: 1888/530, loss: 0.18645372986793518
2023-01-22 23:53:29.498761: step: 1892/530, loss: 0.22802600264549255
2023-01-22 23:53:30.581371: step: 1896/530, loss: 0.3240196406841278
2023-01-22 23:53:31.719252: step: 1900/530, loss: 1.000592827796936
2023-01-22 23:53:32.804390: step: 1904/530, loss: 1.102270483970642
2023-01-22 23:53:33.931094: step: 1908/530, loss: 0.19817887246608734
2023-01-22 23:53:35.040606: step: 1912/530, loss: 0.23716698586940765
2023-01-22 23:53:36.149427: step: 1916/530, loss: 0.3357241749763489
2023-01-22 23:53:37.237803: step: 1920/530, loss: 0.7043208479881287
2023-01-22 23:53:38.357127: step: 1924/530, loss: 1.646287202835083
2023-01-22 23:53:39.457018: step: 1928/530, loss: 0.12129730731248856
2023-01-22 23:53:40.576461: step: 1932/530, loss: 0.46441662311553955
2023-01-22 23:53:41.682980: step: 1936/530, loss: 0.7005584836006165
2023-01-22 23:53:42.780925: step: 1940/530, loss: 0.7100865244865417
2023-01-22 23:53:43.906292: step: 1944/530, loss: 0.9885145425796509
2023-01-22 23:53:45.031210: step: 1948/530, loss: 3.2612500190734863
2023-01-22 23:53:46.122503: step: 1952/530, loss: 0.6922026872634888
2023-01-22 23:53:47.236183: step: 1956/530, loss: 0.49742573499679565
2023-01-22 23:53:48.322712: step: 1960/530, loss: 0.08750258386135101
2023-01-22 23:53:49.422521: step: 1964/530, loss: 0.2963157594203949
2023-01-22 23:53:50.500040: step: 1968/530, loss: 0.1316436231136322
2023-01-22 23:53:51.621297: step: 1972/530, loss: 0.36876344680786133
2023-01-22 23:53:52.729868: step: 1976/530, loss: 0.1679573953151703
2023-01-22 23:53:53.847449: step: 1980/530, loss: 0.12748432159423828
2023-01-22 23:53:54.958330: step: 1984/530, loss: 0.11131172627210617
2023-01-22 23:53:56.037215: step: 1988/530, loss: 0.22851115465164185
2023-01-22 23:53:57.138631: step: 1992/530, loss: 0.24699802696704865
2023-01-22 23:53:58.228072: step: 1996/530, loss: 0.15700551867485046
2023-01-22 23:53:59.341038: step: 2000/530, loss: 0.5740467309951782
2023-01-22 23:54:00.462980: step: 2004/530, loss: 6.835981369018555
2023-01-22 23:54:01.559771: step: 2008/530, loss: 0.3552057147026062
2023-01-22 23:54:02.672675: step: 2012/530, loss: 0.526369571685791
2023-01-22 23:54:03.781522: step: 2016/530, loss: 0.4025844633579254
2023-01-22 23:54:04.893899: step: 2020/530, loss: 0.3946210741996765
2023-01-22 23:54:06.000063: step: 2024/530, loss: 1.455757737159729
2023-01-22 23:54:07.137778: step: 2028/530, loss: 0.4541950225830078
2023-01-22 23:54:08.226098: step: 2032/530, loss: 0.08556075394153595
2023-01-22 23:54:09.345410: step: 2036/530, loss: 0.4059714078903198
2023-01-22 23:54:10.444687: step: 2040/530, loss: 1.0014783143997192
2023-01-22 23:54:11.555559: step: 2044/530, loss: 1.0441620349884033
2023-01-22 23:54:12.660857: step: 2048/530, loss: 0.434211790561676
2023-01-22 23:54:13.751980: step: 2052/530, loss: 0.08645358681678772
2023-01-22 23:54:14.864903: step: 2056/530, loss: 0.4502546489238739
2023-01-22 23:54:15.974527: step: 2060/530, loss: 0.28457754850387573
2023-01-22 23:54:17.086676: step: 2064/530, loss: 0.1551433503627777
2023-01-22 23:54:18.229711: step: 2068/530, loss: 0.12458033859729767
2023-01-22 23:54:19.399759: step: 2072/530, loss: 0.6769781112670898
2023-01-22 23:54:20.522709: step: 2076/530, loss: 0.22615547478199005
2023-01-22 23:54:21.630262: step: 2080/530, loss: 0.14603291451931
2023-01-22 23:54:22.730335: step: 2084/530, loss: 0.43144819140434265
2023-01-22 23:54:23.825966: step: 2088/530, loss: 0.39299678802490234
2023-01-22 23:54:24.936462: step: 2092/530, loss: 1.0879460573196411
2023-01-22 23:54:26.056867: step: 2096/530, loss: 0.3912164866924286
2023-01-22 23:54:27.167958: step: 2100/530, loss: 0.18495550751686096
2023-01-22 23:54:28.301939: step: 2104/530, loss: 1.7121546268463135
2023-01-22 23:54:29.391750: step: 2108/530, loss: 0.03103170543909073
2023-01-22 23:54:30.515900: step: 2112/530, loss: 0.6823851466178894
2023-01-22 23:54:31.616047: step: 2116/530, loss: 0.42215004563331604
2023-01-22 23:54:32.731459: step: 2120/530, loss: 0.8754414916038513
==================================================
Loss: 0.635
--------------------
Dev: {'event': {'p': 0.6218961625282167, 'r': 0.7336884154460719, 'f1': 0.6731826511912034}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Test: {'event': {'p': 0.6148681055155876, 'r': 0.747086247086247, 'f1': 0.6745593264930282}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Chinese: {'event': {'p': 0.5970149253731343, 'r': 0.7407407407407407, 'f1': 0.6611570247933883}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Korean: {'event': {'p': 0.7631578947368421, 'r': 0.4603174603174603, 'f1': 0.5742574257425742}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Russian: {'event': {'p': 0.4482758620689655, 'r': 0.3611111111111111, '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': 0.6218961625282167, 'r': 0.7336884154460719, 'f1': 0.6731826511912034}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Eng Test for Chinese: {'event': {'p': 0.6148681055155876, 'r': 0.747086247086247, 'f1': 0.6745593264930282}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Sample Chinese: {'event': {'p': 0.5970149253731343, 'r': 0.7407407407407407, 'f1': 0.6611570247933883}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6218961625282167, 'r': 0.7336884154460719, 'f1': 0.6731826511912034}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Eng Test for Korean: {'event': {'p': 0.6148681055155876, 'r': 0.747086247086247, 'f1': 0.6745593264930282}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Sample Korean: {'event': {'p': 0.7631578947368421, 'r': 0.4603174603174603, 'f1': 0.5742574257425742}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5862457722660653, 'r': 0.6924101198402131, 'f1': 0.634920634920635}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Eng Test for Russian: {'event': {'p': 0.5994652406417113, 'r': 0.6532634032634033, 'f1': 0.6252091466815394}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Sample Russian: {'event': {'p': 0.625, 'r': 0.4166666666666667, 'f1': 0.5}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
******************************
Epoch: 3
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-22 23:55:26.209326: step: 4/530, loss: 0.08670216053724289
2023-01-22 23:55:27.321470: step: 8/530, loss: 0.7425211071968079
2023-01-22 23:55:28.471546: step: 12/530, loss: 0.3656993508338928
2023-01-22 23:55:29.585795: step: 16/530, loss: 0.3146924078464508
2023-01-22 23:55:30.688616: step: 20/530, loss: 1.0017139911651611
2023-01-22 23:55:31.826260: step: 24/530, loss: 0.12959051132202148
2023-01-22 23:55:32.940494: step: 28/530, loss: 0.75166916847229
2023-01-22 23:55:34.050895: step: 32/530, loss: 0.21938994526863098
2023-01-22 23:55:35.124732: step: 36/530, loss: 0.6343160271644592
2023-01-22 23:55:36.229090: step: 40/530, loss: 0.8723506927490234
2023-01-22 23:55:37.315343: step: 44/530, loss: 0.44709905982017517
2023-01-22 23:55:38.450266: step: 48/530, loss: 0.31424370408058167
2023-01-22 23:55:39.582864: step: 52/530, loss: 0.1382661908864975
2023-01-22 23:55:40.712993: step: 56/530, loss: 6.676466941833496
2023-01-22 23:55:41.837753: step: 60/530, loss: 0.1759033203125
2023-01-22 23:55:42.940641: step: 64/530, loss: 0.31374847888946533
2023-01-22 23:55:44.046618: step: 68/530, loss: 1.4226709604263306
2023-01-22 23:55:45.154606: step: 72/530, loss: 0.8591247797012329
2023-01-22 23:55:46.278243: step: 76/530, loss: 0.3196790814399719
2023-01-22 23:55:47.387349: step: 80/530, loss: 0.16473107039928436
2023-01-22 23:55:48.531564: step: 84/530, loss: 0.70409095287323
2023-01-22 23:55:49.648832: step: 88/530, loss: 0.14920148253440857
2023-01-22 23:55:50.764907: step: 92/530, loss: 0.20997552573680878
2023-01-22 23:55:51.847491: step: 96/530, loss: 0.272161602973938
2023-01-22 23:55:52.960772: step: 100/530, loss: 0.8385303020477295
2023-01-22 23:55:54.054104: step: 104/530, loss: 6.085962295532227
2023-01-22 23:55:55.169761: step: 108/530, loss: 0.0804353728890419
2023-01-22 23:55:56.264588: step: 112/530, loss: 0.09981179982423782
2023-01-22 23:55:57.357500: step: 116/530, loss: 0.20557069778442383
2023-01-22 23:55:58.490866: step: 120/530, loss: 0.2691030502319336
2023-01-22 23:55:59.615533: step: 124/530, loss: 0.7972768545150757
2023-01-22 23:56:00.738867: step: 128/530, loss: 0.13556356728076935
2023-01-22 23:56:01.878640: step: 132/530, loss: 0.13424137234687805
2023-01-22 23:56:02.992975: step: 136/530, loss: 0.35784590244293213
2023-01-22 23:56:04.110672: step: 140/530, loss: 0.5922499895095825
2023-01-22 23:56:05.243283: step: 144/530, loss: 0.4132048189640045
2023-01-22 23:56:06.374574: step: 148/530, loss: 0.7321273684501648
2023-01-22 23:56:07.474866: step: 152/530, loss: 0.12386198341846466
2023-01-22 23:56:08.594640: step: 156/530, loss: 1.3878066539764404
2023-01-22 23:56:09.691537: step: 160/530, loss: 0.3810931146144867
2023-01-22 23:56:10.792393: step: 164/530, loss: 0.6954941749572754
2023-01-22 23:56:11.892969: step: 168/530, loss: 0.15395422279834747
2023-01-22 23:56:12.999465: step: 172/530, loss: 0.9973186254501343
2023-01-22 23:56:14.093179: step: 176/530, loss: 0.04411964491009712
2023-01-22 23:56:15.192259: step: 180/530, loss: 0.7023789882659912
2023-01-22 23:56:16.324570: step: 184/530, loss: 0.8713164329528809
2023-01-22 23:56:17.419376: step: 188/530, loss: 0.9401844143867493
2023-01-22 23:56:18.534540: step: 192/530, loss: 0.8185009956359863
2023-01-22 23:56:19.626064: step: 196/530, loss: 0.436969518661499
2023-01-22 23:56:20.737402: step: 200/530, loss: 0.7091817855834961
2023-01-22 23:56:21.847244: step: 204/530, loss: 0.1409766674041748
2023-01-22 23:56:22.933762: step: 208/530, loss: 0.1094006597995758
2023-01-22 23:56:24.007176: step: 212/530, loss: 0.12965813279151917
2023-01-22 23:56:25.108949: step: 216/530, loss: 0.9139938354492188
2023-01-22 23:56:26.203877: step: 220/530, loss: 0.09306040406227112
2023-01-22 23:56:27.298413: step: 224/530, loss: 0.15616711974143982
2023-01-22 23:56:28.427471: step: 228/530, loss: 0.021274946630001068
2023-01-22 23:56:29.572105: step: 232/530, loss: 0.18702411651611328
2023-01-22 23:56:30.689148: step: 236/530, loss: 0.17139950394630432
2023-01-22 23:56:31.778607: step: 240/530, loss: 0.10915222018957138
2023-01-22 23:56:32.940954: step: 244/530, loss: 1.5015275478363037
2023-01-22 23:56:34.049094: step: 248/530, loss: 0.9698035717010498
2023-01-22 23:56:35.159431: step: 252/530, loss: 0.35986635088920593
2023-01-22 23:56:36.275149: step: 256/530, loss: 0.510299801826477
2023-01-22 23:56:37.389562: step: 260/530, loss: 0.8220648169517517
2023-01-22 23:56:38.522034: step: 264/530, loss: 0.2708669900894165
2023-01-22 23:56:39.618725: step: 268/530, loss: 0.4881170988082886
2023-01-22 23:56:40.737088: step: 272/530, loss: 0.17152844369411469
2023-01-22 23:56:41.834070: step: 276/530, loss: 0.7094521522521973
2023-01-22 23:56:42.953395: step: 280/530, loss: 0.10604625195264816
2023-01-22 23:56:44.045267: step: 284/530, loss: 0.10316543281078339
2023-01-22 23:56:45.160250: step: 288/530, loss: 0.1440233290195465
2023-01-22 23:56:46.273348: step: 292/530, loss: 0.36348748207092285
2023-01-22 23:56:47.379264: step: 296/530, loss: 0.3383450508117676
2023-01-22 23:56:48.493817: step: 300/530, loss: 0.31017225980758667
2023-01-22 23:56:49.601800: step: 304/530, loss: 1.6978881359100342
2023-01-22 23:56:50.722074: step: 308/530, loss: 0.06570472568273544
2023-01-22 23:56:51.816173: step: 312/530, loss: 0.7695239782333374
2023-01-22 23:56:52.933080: step: 316/530, loss: 0.3221122622489929
2023-01-22 23:56:54.046473: step: 320/530, loss: 0.5657342076301575
2023-01-22 23:56:55.171363: step: 324/530, loss: 0.23307481408119202
2023-01-22 23:56:56.255722: step: 328/530, loss: 0.06699734181165695
2023-01-22 23:56:57.357770: step: 332/530, loss: 0.1255694329738617
2023-01-22 23:56:58.479848: step: 336/530, loss: 0.16757884621620178
2023-01-22 23:56:59.585496: step: 340/530, loss: 0.8738388419151306
2023-01-22 23:57:00.685142: step: 344/530, loss: 2.2099697589874268
2023-01-22 23:57:01.828947: step: 348/530, loss: 0.505162239074707
2023-01-22 23:57:02.954413: step: 352/530, loss: 0.10831813514232635
2023-01-22 23:57:04.074051: step: 356/530, loss: 0.1627213954925537
2023-01-22 23:57:05.183187: step: 360/530, loss: 0.09698152542114258
2023-01-22 23:57:06.324778: step: 364/530, loss: 1.482469081878662
2023-01-22 23:57:07.440315: step: 368/530, loss: 0.1507079005241394
2023-01-22 23:57:08.566780: step: 372/530, loss: 0.7500780820846558
2023-01-22 23:57:09.651485: step: 376/530, loss: 1.529564380645752
2023-01-22 23:57:10.779308: step: 380/530, loss: 0.1849079728126526
2023-01-22 23:57:11.888743: step: 384/530, loss: 1.5442430973052979
2023-01-22 23:57:13.006450: step: 388/530, loss: 0.40095075964927673
2023-01-22 23:57:14.114129: step: 392/530, loss: 0.15654778480529785
2023-01-22 23:57:15.233389: step: 396/530, loss: 0.2123951017856598
2023-01-22 23:57:16.300530: step: 400/530, loss: 0.29726600646972656
2023-01-22 23:57:17.412476: step: 404/530, loss: 0.22025828063488007
2023-01-22 23:57:18.533880: step: 408/530, loss: 0.29780083894729614
2023-01-22 23:57:19.655713: step: 412/530, loss: 0.21444548666477203
2023-01-22 23:57:20.763933: step: 416/530, loss: 0.3012157082557678
2023-01-22 23:57:21.886390: step: 420/530, loss: 2.1054866313934326
2023-01-22 23:57:23.001514: step: 424/530, loss: 0.17260809242725372
2023-01-22 23:57:24.112773: step: 428/530, loss: 0.9646400809288025
2023-01-22 23:57:25.253128: step: 432/530, loss: 0.22282180190086365
2023-01-22 23:57:26.398160: step: 436/530, loss: 0.15118694305419922
2023-01-22 23:57:27.525988: step: 440/530, loss: 0.04808444902300835
2023-01-22 23:57:28.661799: step: 444/530, loss: 0.3841272294521332
2023-01-22 23:57:29.824325: step: 448/530, loss: 0.4097677171230316
2023-01-22 23:57:30.950116: step: 452/530, loss: 0.0768706351518631
2023-01-22 23:57:32.057174: step: 456/530, loss: 0.2223808318376541
2023-01-22 23:57:33.188253: step: 460/530, loss: 0.14105224609375
2023-01-22 23:57:34.307330: step: 464/530, loss: 0.16852979362010956
2023-01-22 23:57:35.409769: step: 468/530, loss: 0.4800230860710144
2023-01-22 23:57:36.527229: step: 472/530, loss: 0.09110622107982635
2023-01-22 23:57:37.663790: step: 476/530, loss: 0.12302207946777344
2023-01-22 23:57:38.774330: step: 480/530, loss: 0.2196028232574463
2023-01-22 23:57:39.875194: step: 484/530, loss: 0.41382282972335815
2023-01-22 23:57:41.017273: step: 488/530, loss: 0.8743951320648193
2023-01-22 23:57:42.121743: step: 492/530, loss: 0.15086722373962402
2023-01-22 23:57:43.238264: step: 496/530, loss: 0.48656120896339417
2023-01-22 23:57:44.388021: step: 500/530, loss: 0.22239823639392853
2023-01-22 23:57:45.481535: step: 504/530, loss: 0.25987881422042847
2023-01-22 23:57:46.592457: step: 508/530, loss: 1.6225955486297607
2023-01-22 23:57:47.707941: step: 512/530, loss: 0.4051980972290039
2023-01-22 23:57:48.799753: step: 516/530, loss: 0.048266030848026276
2023-01-22 23:57:49.923896: step: 520/530, loss: 0.8777795433998108
2023-01-22 23:57:51.029395: step: 524/530, loss: 2.379406690597534
2023-01-22 23:57:52.175667: step: 528/530, loss: 6.20833158493042
2023-01-22 23:57:53.248968: step: 532/530, loss: 0.30463963747024536
2023-01-22 23:57:54.350104: step: 536/530, loss: 0.6157921552658081
2023-01-22 23:57:55.487830: step: 540/530, loss: 0.695269763469696
2023-01-22 23:57:56.591981: step: 544/530, loss: 0.039891719818115234
2023-01-22 23:57:57.702487: step: 548/530, loss: 0.16700954735279083
2023-01-22 23:57:58.818079: step: 552/530, loss: 0.20300647616386414
2023-01-22 23:57:59.922279: step: 556/530, loss: 1.4089555740356445
2023-01-22 23:58:01.018633: step: 560/530, loss: 0.15812574326992035
2023-01-22 23:58:02.107505: step: 564/530, loss: 0.09034595638513565
2023-01-22 23:58:03.252678: step: 568/530, loss: 0.04844699054956436
2023-01-22 23:58:04.342620: step: 572/530, loss: 0.7393420934677124
2023-01-22 23:58:05.461914: step: 576/530, loss: 0.17693018913269043
2023-01-22 23:58:06.566786: step: 580/530, loss: 0.1086801066994667
2023-01-22 23:58:07.657253: step: 584/530, loss: 0.6915250420570374
2023-01-22 23:58:08.755746: step: 588/530, loss: 0.048184920102357864
2023-01-22 23:58:09.859485: step: 592/530, loss: 0.09208717942237854
2023-01-22 23:58:10.953607: step: 596/530, loss: 0.29375720024108887
2023-01-22 23:58:12.065677: step: 600/530, loss: 0.06822118908166885
2023-01-22 23:58:13.199878: step: 604/530, loss: 0.09719639271497726
2023-01-22 23:58:14.306905: step: 608/530, loss: 0.29469040036201477
2023-01-22 23:58:15.414628: step: 612/530, loss: 0.08552694320678711
2023-01-22 23:58:16.526373: step: 616/530, loss: 0.3067701458930969
2023-01-22 23:58:17.615747: step: 620/530, loss: 0.31503018736839294
2023-01-22 23:58:18.732681: step: 624/530, loss: 0.42888134717941284
2023-01-22 23:58:19.842851: step: 628/530, loss: 0.38048458099365234
2023-01-22 23:58:20.962932: step: 632/530, loss: 0.07893228530883789
2023-01-22 23:58:22.031928: step: 636/530, loss: 0.05241525173187256
2023-01-22 23:58:23.162509: step: 640/530, loss: 0.04816789925098419
2023-01-22 23:58:24.254912: step: 644/530, loss: 0.12628765404224396
2023-01-22 23:58:25.366231: step: 648/530, loss: 0.18118058145046234
2023-01-22 23:58:26.503787: step: 652/530, loss: 0.07704129815101624
2023-01-22 23:58:27.590958: step: 656/530, loss: 0.285206139087677
2023-01-22 23:58:28.671431: step: 660/530, loss: 0.26229792833328247
2023-01-22 23:58:29.806865: step: 664/530, loss: 0.32291170954704285
2023-01-22 23:58:30.906278: step: 668/530, loss: 0.7378031611442566
2023-01-22 23:58:32.039275: step: 672/530, loss: 0.2469298392534256
2023-01-22 23:58:33.166238: step: 676/530, loss: 0.1913870871067047
2023-01-22 23:58:34.282870: step: 680/530, loss: 0.08320832252502441
2023-01-22 23:58:35.391012: step: 684/530, loss: 0.12690076231956482
2023-01-22 23:58:36.509696: step: 688/530, loss: 0.05353193357586861
2023-01-22 23:58:37.624334: step: 692/530, loss: 0.16691379249095917
2023-01-22 23:58:38.729369: step: 696/530, loss: 0.4470704197883606
2023-01-22 23:58:39.836948: step: 700/530, loss: 0.05875048413872719
2023-01-22 23:58:40.986570: step: 704/530, loss: 0.39918625354766846
2023-01-22 23:58:42.071979: step: 708/530, loss: 1.0729751586914062
2023-01-22 23:58:43.172250: step: 712/530, loss: 0.1060362383723259
2023-01-22 23:58:44.262073: step: 716/530, loss: 0.33943358063697815
2023-01-22 23:58:45.369340: step: 720/530, loss: 0.13942795991897583
2023-01-22 23:58:46.457532: step: 724/530, loss: 0.12517929077148438
2023-01-22 23:58:47.549104: step: 728/530, loss: 1.0905100107192993
2023-01-22 23:58:48.684787: step: 732/530, loss: 0.15050753951072693
2023-01-22 23:58:49.806846: step: 736/530, loss: 0.7042437791824341
2023-01-22 23:58:50.910209: step: 740/530, loss: 0.06839676201343536
2023-01-22 23:58:52.024426: step: 744/530, loss: 1.2980988025665283
2023-01-22 23:58:53.149757: step: 748/530, loss: 0.25233206152915955
2023-01-22 23:58:54.242773: step: 752/530, loss: 0.27263110876083374
2023-01-22 23:58:55.338972: step: 756/530, loss: 0.8508257269859314
2023-01-22 23:58:56.437830: step: 760/530, loss: 0.4084666669368744
2023-01-22 23:58:57.565606: step: 764/530, loss: 0.3968985676765442
2023-01-22 23:58:58.695495: step: 768/530, loss: 0.15251168608665466
2023-01-22 23:58:59.786539: step: 772/530, loss: 0.43838825821876526
2023-01-22 23:59:00.890198: step: 776/530, loss: 0.031958725303411484
2023-01-22 23:59:01.987595: step: 780/530, loss: 0.7524548768997192
2023-01-22 23:59:03.081499: step: 784/530, loss: 0.6981293559074402
2023-01-22 23:59:04.192571: step: 788/530, loss: 0.4371768534183502
2023-01-22 23:59:05.306118: step: 792/530, loss: 0.11718375980854034
2023-01-22 23:59:06.429750: step: 796/530, loss: 0.10837727040052414
2023-01-22 23:59:07.544547: step: 800/530, loss: 0.17525647580623627
2023-01-22 23:59:08.645401: step: 804/530, loss: 0.09127626568078995
2023-01-22 23:59:09.735715: step: 808/530, loss: 0.6791750192642212
2023-01-22 23:59:10.866416: step: 812/530, loss: 0.207861989736557
2023-01-22 23:59:11.990057: step: 816/530, loss: 0.6816747784614563
2023-01-22 23:59:13.103235: step: 820/530, loss: 0.3126440942287445
2023-01-22 23:59:14.186105: step: 824/530, loss: 0.0521392859518528
2023-01-22 23:59:15.281586: step: 828/530, loss: 0.22106227278709412
2023-01-22 23:59:16.427041: step: 832/530, loss: 1.3859901428222656
2023-01-22 23:59:17.523994: step: 836/530, loss: 0.19412536919116974
2023-01-22 23:59:18.632153: step: 840/530, loss: 0.2482614517211914
2023-01-22 23:59:19.755998: step: 844/530, loss: 0.7644062042236328
2023-01-22 23:59:20.831826: step: 848/530, loss: 0.15085983276367188
2023-01-22 23:59:21.926143: step: 852/530, loss: 0.06524792313575745
2023-01-22 23:59:23.070734: step: 856/530, loss: 0.1701214760541916
2023-01-22 23:59:24.221521: step: 860/530, loss: 0.1320631057024002
2023-01-22 23:59:25.285808: step: 864/530, loss: 0.03023524209856987
2023-01-22 23:59:26.427694: step: 868/530, loss: 0.28986629843711853
2023-01-22 23:59:27.527418: step: 872/530, loss: 0.07692985981702805
2023-01-22 23:59:28.626954: step: 876/530, loss: 0.13957038521766663
2023-01-22 23:59:29.766335: step: 880/530, loss: 0.23064078390598297
2023-01-22 23:59:30.854021: step: 884/530, loss: 0.15076637268066406
2023-01-22 23:59:31.974507: step: 888/530, loss: 0.3444465696811676
2023-01-22 23:59:33.112326: step: 892/530, loss: 0.33475741744041443
2023-01-22 23:59:34.197521: step: 896/530, loss: 6.4810099601745605
2023-01-22 23:59:35.321845: step: 900/530, loss: 0.18743714690208435
2023-01-22 23:59:36.423072: step: 904/530, loss: 0.7146020531654358
2023-01-22 23:59:37.536009: step: 908/530, loss: 0.190684512257576
2023-01-22 23:59:38.648964: step: 912/530, loss: 0.6810562014579773
2023-01-22 23:59:39.752860: step: 916/530, loss: 0.5636365413665771
2023-01-22 23:59:40.835115: step: 920/530, loss: 0.19980698823928833
2023-01-22 23:59:41.958247: step: 924/530, loss: 0.16233186423778534
2023-01-22 23:59:43.056560: step: 928/530, loss: 0.14314156770706177
2023-01-22 23:59:44.157425: step: 932/530, loss: 0.17189884185791016
2023-01-22 23:59:45.272819: step: 936/530, loss: 0.3483818769454956
2023-01-22 23:59:46.383441: step: 940/530, loss: 0.1581161618232727
2023-01-22 23:59:47.491754: step: 944/530, loss: 0.09267788380384445
2023-01-22 23:59:48.576383: step: 948/530, loss: 0.32012274861335754
2023-01-22 23:59:49.678955: step: 952/530, loss: 0.17555943131446838
2023-01-22 23:59:50.754654: step: 956/530, loss: 0.19807392358779907
2023-01-22 23:59:51.864297: step: 960/530, loss: 0.10608863830566406
2023-01-22 23:59:53.000560: step: 964/530, loss: 0.2038031667470932
2023-01-22 23:59:54.114902: step: 968/530, loss: 0.046420954167842865
2023-01-22 23:59:55.212783: step: 972/530, loss: 0.12392480671405792
2023-01-22 23:59:56.328350: step: 976/530, loss: 0.369844913482666
2023-01-22 23:59:57.444003: step: 980/530, loss: 0.5682188868522644
2023-01-22 23:59:58.555631: step: 984/530, loss: 0.14702053368091583
2023-01-22 23:59:59.639932: step: 988/530, loss: 0.5968596935272217
2023-01-23 00:00:00.739845: step: 992/530, loss: 0.050177861005067825
2023-01-23 00:00:01.853243: step: 996/530, loss: 0.15501317381858826
2023-01-23 00:00:02.943767: step: 1000/530, loss: 0.15395088493824005
2023-01-23 00:00:04.030165: step: 1004/530, loss: 0.0687994509935379
2023-01-23 00:00:05.173124: step: 1008/530, loss: 0.24949073791503906
2023-01-23 00:00:06.283624: step: 1012/530, loss: 0.14284944534301758
2023-01-23 00:00:07.432787: step: 1016/530, loss: 0.3091421127319336
2023-01-23 00:00:08.527614: step: 1020/530, loss: 0.7753722071647644
2023-01-23 00:00:09.627545: step: 1024/530, loss: 0.8655267953872681
2023-01-23 00:00:10.751421: step: 1028/530, loss: 0.9411481618881226
2023-01-23 00:00:11.855295: step: 1032/530, loss: 0.11449714004993439
2023-01-23 00:00:12.943376: step: 1036/530, loss: 1.0017517805099487
2023-01-23 00:00:14.053846: step: 1040/530, loss: 0.07056598365306854
2023-01-23 00:00:15.144319: step: 1044/530, loss: 0.11513514816761017
2023-01-23 00:00:16.243701: step: 1048/530, loss: 0.7276437282562256
2023-01-23 00:00:17.334223: step: 1052/530, loss: 0.02608940564095974
2023-01-23 00:00:18.449409: step: 1056/530, loss: 0.24173566699028015
2023-01-23 00:00:19.560225: step: 1060/530, loss: 0.19794926047325134
2023-01-23 00:00:20.657711: step: 1064/530, loss: 0.1670002043247223
2023-01-23 00:00:21.743569: step: 1068/530, loss: 0.029402829706668854
2023-01-23 00:00:22.889852: step: 1072/530, loss: 0.22314368188381195
2023-01-23 00:00:23.998079: step: 1076/530, loss: 0.1544853150844574
2023-01-23 00:00:25.128047: step: 1080/530, loss: 0.10663509368896484
2023-01-23 00:00:26.221571: step: 1084/530, loss: 0.3987272381782532
2023-01-23 00:00:27.338107: step: 1088/530, loss: 0.23635907471179962
2023-01-23 00:00:28.481392: step: 1092/530, loss: 0.4140813946723938
2023-01-23 00:00:29.629344: step: 1096/530, loss: 0.22514677047729492
2023-01-23 00:00:30.724602: step: 1100/530, loss: 0.23145970702171326
2023-01-23 00:00:31.848419: step: 1104/530, loss: 0.2770175039768219
2023-01-23 00:00:32.974243: step: 1108/530, loss: 0.8043496012687683
2023-01-23 00:00:34.059506: step: 1112/530, loss: 0.19974027574062347
2023-01-23 00:00:35.144130: step: 1116/530, loss: 0.7044044137001038
2023-01-23 00:00:36.261831: step: 1120/530, loss: 0.6138517260551453
2023-01-23 00:00:37.352654: step: 1124/530, loss: 0.10854730755090714
2023-01-23 00:00:38.431295: step: 1128/530, loss: 0.24727901816368103
2023-01-23 00:00:39.564165: step: 1132/530, loss: 0.5921028852462769
2023-01-23 00:00:40.659068: step: 1136/530, loss: 0.06702842563390732
2023-01-23 00:00:41.746356: step: 1140/530, loss: 0.8548246622085571
2023-01-23 00:00:42.857170: step: 1144/530, loss: 0.029693983495235443
2023-01-23 00:00:43.973704: step: 1148/530, loss: 0.5369237661361694
2023-01-23 00:00:45.099996: step: 1152/530, loss: 0.368988037109375
2023-01-23 00:00:46.230158: step: 1156/530, loss: 0.8940134048461914
2023-01-23 00:00:47.338703: step: 1160/530, loss: 0.09035807102918625
2023-01-23 00:00:48.424132: step: 1164/530, loss: 0.498096227645874
2023-01-23 00:00:49.508894: step: 1168/530, loss: 0.17247219383716583
2023-01-23 00:00:50.628931: step: 1172/530, loss: 0.3165737986564636
2023-01-23 00:00:51.704433: step: 1176/530, loss: 0.09919185936450958
2023-01-23 00:00:52.819526: step: 1180/530, loss: 0.38924649357795715
2023-01-23 00:00:53.908004: step: 1184/530, loss: 0.08071485161781311
2023-01-23 00:00:55.007537: step: 1188/530, loss: 0.3586675226688385
2023-01-23 00:00:56.116074: step: 1192/530, loss: 0.13473773002624512
2023-01-23 00:00:57.228467: step: 1196/530, loss: 0.18251752853393555
2023-01-23 00:00:58.335198: step: 1200/530, loss: 0.21075686812400818
2023-01-23 00:00:59.422173: step: 1204/530, loss: 0.2585081458091736
2023-01-23 00:01:00.548651: step: 1208/530, loss: 6.483245372772217
2023-01-23 00:01:01.645940: step: 1212/530, loss: 0.09810562431812286
2023-01-23 00:01:02.755785: step: 1216/530, loss: 0.6704650521278381
2023-01-23 00:01:03.869227: step: 1220/530, loss: 0.2988787293434143
2023-01-23 00:01:05.037907: step: 1224/530, loss: 2.280733346939087
2023-01-23 00:01:06.193318: step: 1228/530, loss: 0.7969030141830444
2023-01-23 00:01:07.327881: step: 1232/530, loss: 0.7011225819587708
2023-01-23 00:01:08.451723: step: 1236/530, loss: 0.09697170555591583
2023-01-23 00:01:09.575828: step: 1240/530, loss: 0.17139454185962677
2023-01-23 00:01:10.709617: step: 1244/530, loss: 0.6216720342636108
2023-01-23 00:01:11.810869: step: 1248/530, loss: 0.11119508743286133
2023-01-23 00:01:12.920136: step: 1252/530, loss: 0.7147852182388306
2023-01-23 00:01:14.013637: step: 1256/530, loss: 0.7016855478286743
2023-01-23 00:01:15.140279: step: 1260/530, loss: 0.16261878609657288
2023-01-23 00:01:16.259227: step: 1264/530, loss: 0.3030509948730469
2023-01-23 00:01:17.334690: step: 1268/530, loss: 0.14998197555541992
2023-01-23 00:01:18.422970: step: 1272/530, loss: 0.4762714207172394
2023-01-23 00:01:19.493871: step: 1276/530, loss: 0.05845193937420845
2023-01-23 00:01:20.588221: step: 1280/530, loss: 0.06526260823011398
2023-01-23 00:01:21.656335: step: 1284/530, loss: 0.6663269400596619
2023-01-23 00:01:22.756802: step: 1288/530, loss: 0.11761841922998428
2023-01-23 00:01:23.869401: step: 1292/530, loss: 0.8493305444717407
2023-01-23 00:01:24.997963: step: 1296/530, loss: 0.30929630994796753
2023-01-23 00:01:26.117575: step: 1300/530, loss: 0.16514426469802856
2023-01-23 00:01:27.225440: step: 1304/530, loss: 0.2481299638748169
2023-01-23 00:01:28.354154: step: 1308/530, loss: 0.21487656235694885
2023-01-23 00:01:29.477611: step: 1312/530, loss: 0.15511319041252136
2023-01-23 00:01:30.588699: step: 1316/530, loss: 0.34609389305114746
2023-01-23 00:01:31.682788: step: 1320/530, loss: 0.05653705447912216
2023-01-23 00:01:32.772015: step: 1324/530, loss: 0.16819362342357635
2023-01-23 00:01:33.879494: step: 1328/530, loss: 0.06947198510169983
2023-01-23 00:01:34.988936: step: 1332/530, loss: 0.17193670570850372
2023-01-23 00:01:36.109740: step: 1336/530, loss: 0.6116697788238525
2023-01-23 00:01:37.204052: step: 1340/530, loss: 0.26307305693626404
2023-01-23 00:01:38.308828: step: 1344/530, loss: 0.17689037322998047
2023-01-23 00:01:39.411555: step: 1348/530, loss: 0.06488504260778427
2023-01-23 00:01:40.517748: step: 1352/530, loss: 0.0031575204338878393
2023-01-23 00:01:41.639147: step: 1356/530, loss: 0.14478006958961487
2023-01-23 00:01:42.732832: step: 1360/530, loss: 0.328853040933609
2023-01-23 00:01:43.863983: step: 1364/530, loss: 0.12356052547693253
2023-01-23 00:01:44.974110: step: 1368/530, loss: 0.16449356079101562
2023-01-23 00:01:46.073843: step: 1372/530, loss: 0.13608606159687042
2023-01-23 00:01:47.186311: step: 1376/530, loss: 0.20090952515602112
2023-01-23 00:01:48.334810: step: 1380/530, loss: 0.811094343662262
2023-01-23 00:01:49.443173: step: 1384/530, loss: 0.18214932084083557
2023-01-23 00:01:50.543938: step: 1388/530, loss: 0.20756787061691284
2023-01-23 00:01:51.674891: step: 1392/530, loss: 3.0630927085876465
2023-01-23 00:01:52.778955: step: 1396/530, loss: 0.30200138688087463
2023-01-23 00:01:53.904243: step: 1400/530, loss: 0.36907511949539185
2023-01-23 00:01:55.015262: step: 1404/530, loss: 0.1349874585866928
2023-01-23 00:01:56.112681: step: 1408/530, loss: 0.13987398147583008
2023-01-23 00:01:57.222586: step: 1412/530, loss: 0.6564210653305054
2023-01-23 00:01:58.328843: step: 1416/530, loss: 0.2468002289533615
2023-01-23 00:01:59.419674: step: 1420/530, loss: 0.7673401832580566
2023-01-23 00:02:00.548688: step: 1424/530, loss: 0.16532397270202637
2023-01-23 00:02:01.663842: step: 1428/530, loss: 0.488692969083786
2023-01-23 00:02:02.776414: step: 1432/530, loss: 0.7249547243118286
2023-01-23 00:02:03.919701: step: 1436/530, loss: 0.25163841247558594
2023-01-23 00:02:05.006019: step: 1440/530, loss: 0.14037880301475525
2023-01-23 00:02:06.102179: step: 1444/530, loss: 0.10882120579481125
2023-01-23 00:02:07.187726: step: 1448/530, loss: 0.09499195218086243
2023-01-23 00:02:08.288985: step: 1452/530, loss: 0.47806328535079956
2023-01-23 00:02:09.417247: step: 1456/530, loss: 0.6608163714408875
2023-01-23 00:02:10.533739: step: 1460/530, loss: 1.335606575012207
2023-01-23 00:02:11.638237: step: 1464/530, loss: 0.082666777074337
2023-01-23 00:02:12.746587: step: 1468/530, loss: 0.1971803605556488
2023-01-23 00:02:13.844580: step: 1472/530, loss: 0.42231154441833496
2023-01-23 00:02:14.962257: step: 1476/530, loss: 0.37188807129859924
2023-01-23 00:02:16.058079: step: 1480/530, loss: 0.16070471704006195
2023-01-23 00:02:17.151736: step: 1484/530, loss: 0.3102894723415375
2023-01-23 00:02:18.239110: step: 1488/530, loss: 0.6405572891235352
2023-01-23 00:02:19.331623: step: 1492/530, loss: 0.6251281499862671
2023-01-23 00:02:20.440660: step: 1496/530, loss: 0.10793576389551163
2023-01-23 00:02:21.544959: step: 1500/530, loss: 0.060509875416755676
2023-01-23 00:02:22.687788: step: 1504/530, loss: 0.28500452637672424
2023-01-23 00:02:23.798272: step: 1508/530, loss: 0.14901180565357208
2023-01-23 00:02:24.876772: step: 1512/530, loss: 0.18699979782104492
2023-01-23 00:02:25.970506: step: 1516/530, loss: 0.15403318405151367
2023-01-23 00:02:27.094005: step: 1520/530, loss: 0.2750725746154785
2023-01-23 00:02:28.190501: step: 1524/530, loss: 0.7165981531143188
2023-01-23 00:02:29.316245: step: 1528/530, loss: 0.20892955362796783
2023-01-23 00:02:30.402414: step: 1532/530, loss: 0.794428288936615
2023-01-23 00:02:31.517699: step: 1536/530, loss: 0.7577297687530518
2023-01-23 00:02:32.634910: step: 1540/530, loss: 0.2666401267051697
2023-01-23 00:02:33.723321: step: 1544/530, loss: 0.12612737715244293
2023-01-23 00:02:34.831927: step: 1548/530, loss: 0.11761835217475891
2023-01-23 00:02:35.924166: step: 1552/530, loss: 1.6039170026779175
2023-01-23 00:02:37.014606: step: 1556/530, loss: 0.13649287819862366
2023-01-23 00:02:38.143256: step: 1560/530, loss: 0.2975988984107971
2023-01-23 00:02:39.253844: step: 1564/530, loss: 0.14498673379421234
2023-01-23 00:02:40.357139: step: 1568/530, loss: 0.16661281883716583
2023-01-23 00:02:41.470765: step: 1572/530, loss: 0.20801010727882385
2023-01-23 00:02:42.580757: step: 1576/530, loss: 1.2460899353027344
2023-01-23 00:02:43.702081: step: 1580/530, loss: 0.18675652146339417
2023-01-23 00:02:44.826646: step: 1584/530, loss: 0.8845086693763733
2023-01-23 00:02:45.953794: step: 1588/530, loss: 0.21355904638767242
2023-01-23 00:02:47.051470: step: 1592/530, loss: 0.5205184817314148
2023-01-23 00:02:48.139632: step: 1596/530, loss: 0.33425962924957275
2023-01-23 00:02:49.262204: step: 1600/530, loss: 0.14664211869239807
2023-01-23 00:02:50.369310: step: 1604/530, loss: 0.15042009949684143
2023-01-23 00:02:51.461465: step: 1608/530, loss: 0.25238358974456787
2023-01-23 00:02:52.547925: step: 1612/530, loss: 0.6788644790649414
2023-01-23 00:02:53.651612: step: 1616/530, loss: 0.7578309774398804
2023-01-23 00:02:54.765937: step: 1620/530, loss: 0.3974772095680237
2023-01-23 00:02:55.853198: step: 1624/530, loss: 0.06993112713098526
2023-01-23 00:02:56.963718: step: 1628/530, loss: 0.17946434020996094
2023-01-23 00:02:58.064247: step: 1632/530, loss: 0.7522901892662048
2023-01-23 00:02:59.158750: step: 1636/530, loss: 0.1679244041442871
2023-01-23 00:03:00.293529: step: 1640/530, loss: 0.14097467064857483
2023-01-23 00:03:01.406668: step: 1644/530, loss: 0.35110291838645935
2023-01-23 00:03:02.517739: step: 1648/530, loss: 0.10240183770656586
2023-01-23 00:03:03.643077: step: 1652/530, loss: 0.7020695805549622
2023-01-23 00:03:04.750140: step: 1656/530, loss: 0.7162157297134399
2023-01-23 00:03:05.848484: step: 1660/530, loss: 1.0253666639328003
2023-01-23 00:03:06.981494: step: 1664/530, loss: 0.15080061554908752
2023-01-23 00:03:08.089137: step: 1668/530, loss: 0.11613388359546661
2023-01-23 00:03:09.206934: step: 1672/530, loss: 0.8429597020149231
2023-01-23 00:03:10.315159: step: 1676/530, loss: 0.46606865525245667
2023-01-23 00:03:11.408833: step: 1680/530, loss: 0.16241370141506195
2023-01-23 00:03:12.525378: step: 1684/530, loss: 0.40332090854644775
2023-01-23 00:03:13.610270: step: 1688/530, loss: 0.401131272315979
2023-01-23 00:03:14.719540: step: 1692/530, loss: 0.6422019600868225
2023-01-23 00:03:15.817954: step: 1696/530, loss: 0.20374079048633575
2023-01-23 00:03:16.931393: step: 1700/530, loss: 0.11263875663280487
2023-01-23 00:03:18.041541: step: 1704/530, loss: 0.09507761150598526
2023-01-23 00:03:19.143152: step: 1708/530, loss: 1.0796654224395752
2023-01-23 00:03:20.256661: step: 1712/530, loss: 0.1146307960152626
2023-01-23 00:03:21.333588: step: 1716/530, loss: 0.635841429233551
2023-01-23 00:03:22.429220: step: 1720/530, loss: 0.17098593711853027
2023-01-23 00:03:23.548193: step: 1724/530, loss: 0.26894569396972656
2023-01-23 00:03:24.663218: step: 1728/530, loss: 0.2519933581352234
2023-01-23 00:03:25.758971: step: 1732/530, loss: 0.08846788108348846
2023-01-23 00:03:26.907147: step: 1736/530, loss: 1.0635778903961182
2023-01-23 00:03:27.967388: step: 1740/530, loss: 0.19321660697460175
2023-01-23 00:03:29.048377: step: 1744/530, loss: 1.8589887619018555
2023-01-23 00:03:30.150398: step: 1748/530, loss: 0.28469669818878174
2023-01-23 00:03:31.268905: step: 1752/530, loss: 0.12295150756835938
2023-01-23 00:03:32.362343: step: 1756/530, loss: 0.10439954698085785
2023-01-23 00:03:33.475181: step: 1760/530, loss: 1.2381031513214111
2023-01-23 00:03:34.584173: step: 1764/530, loss: 0.6346668004989624
2023-01-23 00:03:35.701894: step: 1768/530, loss: 0.30067309737205505
2023-01-23 00:03:36.803701: step: 1772/530, loss: 0.7033620476722717
2023-01-23 00:03:37.901119: step: 1776/530, loss: 0.17614135146141052
2023-01-23 00:03:38.997083: step: 1780/530, loss: 0.1508616954088211
2023-01-23 00:03:40.079914: step: 1784/530, loss: 0.1192924976348877
2023-01-23 00:03:41.204907: step: 1788/530, loss: 0.13729210197925568
2023-01-23 00:03:42.297669: step: 1792/530, loss: 0.07399387657642365
2023-01-23 00:03:43.386307: step: 1796/530, loss: 0.16635599732398987
2023-01-23 00:03:44.460115: step: 1800/530, loss: 0.7485564351081848
2023-01-23 00:03:45.559459: step: 1804/530, loss: 0.905587911605835
2023-01-23 00:03:46.692621: step: 1808/530, loss: 0.7672727704048157
2023-01-23 00:03:47.797503: step: 1812/530, loss: 0.6557892560958862
2023-01-23 00:03:48.880252: step: 1816/530, loss: 0.18514873087406158
2023-01-23 00:03:49.997491: step: 1820/530, loss: 0.12211170047521591
2023-01-23 00:03:51.098438: step: 1824/530, loss: 0.21593904495239258
2023-01-23 00:03:52.206864: step: 1828/530, loss: 0.21972951292991638
2023-01-23 00:03:53.298951: step: 1832/530, loss: 0.05491485446691513
2023-01-23 00:03:54.402101: step: 1836/530, loss: 0.4267908036708832
2023-01-23 00:03:55.520205: step: 1840/530, loss: 0.08494883030653
2023-01-23 00:03:56.617447: step: 1844/530, loss: 0.6058789491653442
2023-01-23 00:03:57.716120: step: 1848/530, loss: 0.23098888993263245
2023-01-23 00:03:58.840224: step: 1852/530, loss: 0.09253339469432831
2023-01-23 00:03:59.948695: step: 1856/530, loss: 0.8830114006996155
2023-01-23 00:04:01.053068: step: 1860/530, loss: 0.5928334593772888
2023-01-23 00:04:02.145696: step: 1864/530, loss: 0.3347776532173157
2023-01-23 00:04:03.298425: step: 1868/530, loss: 0.21104544401168823
2023-01-23 00:04:04.365039: step: 1872/530, loss: 0.4050540328025818
2023-01-23 00:04:05.481706: step: 1876/530, loss: 0.3125300407409668
2023-01-23 00:04:06.572838: step: 1880/530, loss: 0.1035439521074295
2023-01-23 00:04:07.659248: step: 1884/530, loss: 0.9132490158081055
2023-01-23 00:04:08.784916: step: 1888/530, loss: 0.9309858083724976
2023-01-23 00:04:09.894809: step: 1892/530, loss: 0.22997914254665375
2023-01-23 00:04:11.054170: step: 1896/530, loss: 0.6879859566688538
2023-01-23 00:04:12.139255: step: 1900/530, loss: 0.0967191755771637
2023-01-23 00:04:13.224398: step: 1904/530, loss: 0.1181757003068924
2023-01-23 00:04:14.346895: step: 1908/530, loss: 0.6646278500556946
2023-01-23 00:04:15.436092: step: 1912/530, loss: 0.2726823687553406
2023-01-23 00:04:16.540570: step: 1916/530, loss: 0.021289754658937454
2023-01-23 00:04:17.632268: step: 1920/530, loss: 0.700293779373169
2023-01-23 00:04:18.699307: step: 1924/530, loss: 0.5711280107498169
2023-01-23 00:04:19.796535: step: 1928/530, loss: 0.054721929132938385
2023-01-23 00:04:20.878236: step: 1932/530, loss: 0.26529660820961
2023-01-23 00:04:21.961414: step: 1936/530, loss: 0.31876295804977417
2023-01-23 00:04:23.090332: step: 1940/530, loss: 0.4228634536266327
2023-01-23 00:04:24.204291: step: 1944/530, loss: 0.48816490173339844
2023-01-23 00:04:25.314949: step: 1948/530, loss: 0.8233122825622559
2023-01-23 00:04:26.401244: step: 1952/530, loss: 0.8538753986358643
2023-01-23 00:04:27.512406: step: 1956/530, loss: 0.2578861117362976
2023-01-23 00:04:28.662692: step: 1960/530, loss: 0.6171329617500305
2023-01-23 00:04:29.739761: step: 1964/530, loss: 0.07076912373304367
2023-01-23 00:04:30.841307: step: 1968/530, loss: 0.14071793854236603
2023-01-23 00:04:31.955012: step: 1972/530, loss: 0.1859898567199707
2023-01-23 00:04:33.058641: step: 1976/530, loss: 0.17195367813110352
2023-01-23 00:04:34.149233: step: 1980/530, loss: 7.5247111320495605
2023-01-23 00:04:35.251838: step: 1984/530, loss: 0.1225653663277626
2023-01-23 00:04:36.387711: step: 1988/530, loss: 0.2066626250743866
2023-01-23 00:04:37.513575: step: 1992/530, loss: 0.18610382080078125
2023-01-23 00:04:38.634906: step: 1996/530, loss: 0.1112181693315506
2023-01-23 00:04:39.763804: step: 2000/530, loss: 0.10484237968921661
2023-01-23 00:04:40.890979: step: 2004/530, loss: 0.09429559856653214
2023-01-23 00:04:41.969049: step: 2008/530, loss: 0.04843835532665253
2023-01-23 00:04:43.063437: step: 2012/530, loss: 0.02923755720257759
2023-01-23 00:04:44.186884: step: 2016/530, loss: 0.27962738275527954
2023-01-23 00:04:45.311701: step: 2020/530, loss: 0.874119758605957
2023-01-23 00:04:46.411772: step: 2024/530, loss: 0.09276409447193146
2023-01-23 00:04:47.514437: step: 2028/530, loss: 0.5249509811401367
2023-01-23 00:04:48.626188: step: 2032/530, loss: 0.17505702376365662
2023-01-23 00:04:49.738921: step: 2036/530, loss: 0.6410484910011292
2023-01-23 00:04:50.838387: step: 2040/530, loss: 0.18552275002002716
2023-01-23 00:04:51.932149: step: 2044/530, loss: 0.599799633026123
2023-01-23 00:04:53.025268: step: 2048/530, loss: 0.10962982475757599
2023-01-23 00:04:54.118053: step: 2052/530, loss: 0.20413756370544434
2023-01-23 00:04:55.207238: step: 2056/530, loss: 0.17080727219581604
2023-01-23 00:04:56.319283: step: 2060/530, loss: 0.3450661599636078
2023-01-23 00:04:57.402047: step: 2064/530, loss: 0.08914312720298767
2023-01-23 00:04:58.520884: step: 2068/530, loss: 0.3270234167575836
2023-01-23 00:04:59.606162: step: 2072/530, loss: 1.773456335067749
2023-01-23 00:05:00.732599: step: 2076/530, loss: 0.45344531536102295
2023-01-23 00:05:01.843602: step: 2080/530, loss: 0.7403789758682251
2023-01-23 00:05:02.942853: step: 2084/530, loss: 0.14244294166564941
2023-01-23 00:05:04.030700: step: 2088/530, loss: 0.08439214527606964
2023-01-23 00:05:05.157566: step: 2092/530, loss: 0.6644097566604614
2023-01-23 00:05:06.255459: step: 2096/530, loss: 0.037229396402835846
2023-01-23 00:05:07.374834: step: 2100/530, loss: 0.16258402168750763
2023-01-23 00:05:08.456188: step: 2104/530, loss: 0.20126695930957794
2023-01-23 00:05:09.558330: step: 2108/530, loss: 0.3019723892211914
2023-01-23 00:05:10.668704: step: 2112/530, loss: 0.13762417435646057
2023-01-23 00:05:11.772453: step: 2116/530, loss: 0.15680614113807678
2023-01-23 00:05:12.895178: step: 2120/530, loss: 0.8581370711326599
==================================================
Loss: 0.457
--------------------
Dev: {'event': {'p': 0.5368007850834151, 'r': 0.7283621837549934, 'f1': 0.6180790960451978}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Test: {'event': {'p': 0.5938209904588824, 'r': 0.7616550116550117, 'f1': 0.6673474597906561}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Chinese: {'event': {'p': 0.5507246376811594, 'r': 0.7037037037037037, 'f1': 0.6178861788617886}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Korean: {'event': {'p': 0.5892857142857143, 'r': 0.5238095238095238, 'f1': 0.5546218487394958}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
Russian: {'event': {'p': 0.391304347826087, 'r': 0.5, 'f1': 0.4390243902439025}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 3}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6218961625282167, 'r': 0.7336884154460719, 'f1': 0.6731826511912034}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Eng Test for Chinese: {'event': {'p': 0.6148681055155876, 'r': 0.747086247086247, 'f1': 0.6745593264930282}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Sample Chinese: {'event': {'p': 0.5970149253731343, 'r': 0.7407407407407407, 'f1': 0.6611570247933883}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6218961625282167, 'r': 0.7336884154460719, 'f1': 0.6731826511912034}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Eng Test for Korean: {'event': {'p': 0.6148681055155876, 'r': 0.747086247086247, 'f1': 0.6745593264930282}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Sample Korean: {'event': {'p': 0.7631578947368421, 'r': 0.4603174603174603, 'f1': 0.5742574257425742}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5862457722660653, 'r': 0.6924101198402131, 'f1': 0.634920634920635}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Eng Test for Russian: {'event': {'p': 0.5994652406417113, 'r': 0.6532634032634033, 'f1': 0.6252091466815394}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Sample Russian: {'event': {'p': 0.625, 'r': 0.4166666666666667, 'f1': 0.5}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
******************************
Epoch: 4
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 00:05:52.577941: step: 4/530, loss: 0.04388447105884552
2023-01-23 00:05:53.686193: step: 8/530, loss: 0.11198602616786957
2023-01-23 00:05:54.816048: step: 12/530, loss: 0.17019163072109222
2023-01-23 00:05:55.911603: step: 16/530, loss: 0.07312774658203125
2023-01-23 00:05:57.016475: step: 20/530, loss: 0.14284630119800568
2023-01-23 00:05:58.112988: step: 24/530, loss: 6.983399868011475
2023-01-23 00:05:59.226512: step: 28/530, loss: 0.08075971156358719
2023-01-23 00:06:00.329357: step: 32/530, loss: 0.16543205082416534
2023-01-23 00:06:01.468964: step: 36/530, loss: 0.08619938045740128
2023-01-23 00:06:02.618743: step: 40/530, loss: 0.2631988525390625
2023-01-23 00:06:03.723933: step: 44/530, loss: 0.03482332453131676
2023-01-23 00:06:04.853280: step: 48/530, loss: 0.10708332061767578
2023-01-23 00:06:05.951816: step: 52/530, loss: 0.16978469491004944
2023-01-23 00:06:07.060546: step: 56/530, loss: 0.5531366467475891
2023-01-23 00:06:08.143107: step: 60/530, loss: 0.12346000969409943
2023-01-23 00:06:09.264749: step: 64/530, loss: 0.15774431824684143
2023-01-23 00:06:10.361776: step: 68/530, loss: 0.12009501457214355
2023-01-23 00:06:11.459584: step: 72/530, loss: 0.12849397957324982
2023-01-23 00:06:12.560036: step: 76/530, loss: 0.09989356994628906
2023-01-23 00:06:13.668092: step: 80/530, loss: 0.10430637001991272
2023-01-23 00:06:14.779784: step: 84/530, loss: 0.6266195178031921
2023-01-23 00:06:15.892569: step: 88/530, loss: 0.8400307893753052
2023-01-23 00:06:17.011223: step: 92/530, loss: 0.9327991604804993
2023-01-23 00:06:18.120335: step: 96/530, loss: 0.08378791809082031
2023-01-23 00:06:19.225862: step: 100/530, loss: 0.14061537384986877
2023-01-23 00:06:20.324049: step: 104/530, loss: 0.420955091714859
2023-01-23 00:06:21.433770: step: 108/530, loss: 0.10666060447692871
2023-01-23 00:06:22.545789: step: 112/530, loss: 0.7087104916572571
2023-01-23 00:06:23.633188: step: 116/530, loss: 0.04850292205810547
2023-01-23 00:06:24.721870: step: 120/530, loss: 0.324055552482605
2023-01-23 00:06:25.822334: step: 124/530, loss: 0.19033299386501312
2023-01-23 00:06:26.933796: step: 128/530, loss: 6.236368179321289
2023-01-23 00:06:28.011133: step: 132/530, loss: 0.03798713535070419
2023-01-23 00:06:29.111226: step: 136/530, loss: 1.053020715713501
2023-01-23 00:06:30.212305: step: 140/530, loss: 0.0592251755297184
2023-01-23 00:06:31.314967: step: 144/530, loss: 0.042023397982120514
2023-01-23 00:06:32.403203: step: 148/530, loss: 0.21973906457424164
2023-01-23 00:06:33.504216: step: 152/530, loss: 0.8609983325004578
2023-01-23 00:06:34.630180: step: 156/530, loss: 0.3036176860332489
2023-01-23 00:06:35.747800: step: 160/530, loss: 0.085118867456913
2023-01-23 00:06:36.870121: step: 164/530, loss: 0.24596424400806427
2023-01-23 00:06:37.970173: step: 168/530, loss: 0.7658373117446899
2023-01-23 00:06:39.081475: step: 172/530, loss: 0.07617044448852539
2023-01-23 00:06:40.208918: step: 176/530, loss: 0.27061253786087036
2023-01-23 00:06:41.305419: step: 180/530, loss: 0.17514467239379883
2023-01-23 00:06:42.403127: step: 184/530, loss: 0.06347942352294922
2023-01-23 00:06:43.491940: step: 188/530, loss: 0.18137702345848083
2023-01-23 00:06:44.598093: step: 192/530, loss: 0.30927228927612305
2023-01-23 00:06:45.714957: step: 196/530, loss: 0.227268785238266
2023-01-23 00:06:46.823032: step: 200/530, loss: 0.07520995289087296
2023-01-23 00:06:47.927532: step: 204/530, loss: 0.7358288764953613
2023-01-23 00:06:49.036777: step: 208/530, loss: 0.6291963458061218
2023-01-23 00:06:50.177767: step: 212/530, loss: 1.3192707300186157
2023-01-23 00:06:51.281730: step: 216/530, loss: 0.9732673764228821
2023-01-23 00:06:52.407054: step: 220/530, loss: 0.19368776679039001
2023-01-23 00:06:53.481816: step: 224/530, loss: 0.19504660367965698
2023-01-23 00:06:54.573884: step: 228/530, loss: 0.4285208284854889
2023-01-23 00:06:55.669934: step: 232/530, loss: 0.16410227119922638
2023-01-23 00:06:56.780530: step: 236/530, loss: 0.09562702476978302
2023-01-23 00:06:57.900632: step: 240/530, loss: 0.28383591771125793
2023-01-23 00:06:59.004933: step: 244/530, loss: 0.06947479397058487
2023-01-23 00:07:00.138143: step: 248/530, loss: 0.1785689890384674
2023-01-23 00:07:01.244623: step: 252/530, loss: 0.11491565406322479
2023-01-23 00:07:02.338287: step: 256/530, loss: 0.16028264164924622
2023-01-23 00:07:03.452652: step: 260/530, loss: 0.4230189323425293
2023-01-23 00:07:04.522753: step: 264/530, loss: 0.002495241118595004
2023-01-23 00:07:05.621186: step: 268/530, loss: 0.2585994601249695
2023-01-23 00:07:06.755127: step: 272/530, loss: 0.7062785029411316
2023-01-23 00:07:07.886829: step: 276/530, loss: 0.18858233094215393
2023-01-23 00:07:09.007320: step: 280/530, loss: 0.07366481423377991
2023-01-23 00:07:10.110424: step: 284/530, loss: 0.7119276523590088
2023-01-23 00:07:11.224800: step: 288/530, loss: 0.2859219014644623
2023-01-23 00:07:12.328742: step: 292/530, loss: 0.08244998753070831
2023-01-23 00:07:13.466901: step: 296/530, loss: 0.5451288223266602
2023-01-23 00:07:14.572782: step: 300/530, loss: 0.35724082589149475
2023-01-23 00:07:15.684923: step: 304/530, loss: 0.09315011650323868
2023-01-23 00:07:16.774394: step: 308/530, loss: 0.6905643343925476
2023-01-23 00:07:17.872371: step: 312/530, loss: 0.036550235003232956
2023-01-23 00:07:19.050472: step: 316/530, loss: 0.12791705131530762
2023-01-23 00:07:20.157362: step: 320/530, loss: 0.32567092776298523
2023-01-23 00:07:21.264787: step: 324/530, loss: 1.0341269969940186
2023-01-23 00:07:22.425157: step: 328/530, loss: 0.25899046659469604
2023-01-23 00:07:23.526863: step: 332/530, loss: 0.16461749374866486
2023-01-23 00:07:24.647185: step: 336/530, loss: 0.2790655195713043
2023-01-23 00:07:25.790388: step: 340/530, loss: 1.8996248245239258
2023-01-23 00:07:26.926888: step: 344/530, loss: 0.05808250978589058
2023-01-23 00:07:28.053445: step: 348/530, loss: 0.09442539513111115
2023-01-23 00:07:29.194701: step: 352/530, loss: 0.10469003021717072
2023-01-23 00:07:30.312160: step: 356/530, loss: 0.05758700519800186
2023-01-23 00:07:31.440238: step: 360/530, loss: 0.15223579108715057
2023-01-23 00:07:32.551970: step: 364/530, loss: 0.032969094812870026
2023-01-23 00:07:33.697157: step: 368/530, loss: 0.2311607301235199
2023-01-23 00:07:34.795241: step: 372/530, loss: 0.06469903141260147
2023-01-23 00:07:35.895963: step: 376/530, loss: 0.12867331504821777
2023-01-23 00:07:37.012472: step: 380/530, loss: 0.2977760434150696
2023-01-23 00:07:38.118688: step: 384/530, loss: 0.5782980918884277
2023-01-23 00:07:39.220085: step: 388/530, loss: 0.06419911980628967
2023-01-23 00:07:40.310392: step: 392/530, loss: 0.17603835463523865
2023-01-23 00:07:41.409106: step: 396/530, loss: 1.5889110565185547
2023-01-23 00:07:42.550602: step: 400/530, loss: 0.31012162566185
2023-01-23 00:07:43.660813: step: 404/530, loss: 0.6036617159843445
2023-01-23 00:07:44.807692: step: 408/530, loss: 0.04255819320678711
2023-01-23 00:07:45.908200: step: 412/530, loss: 0.07757425308227539
2023-01-23 00:07:47.011005: step: 416/530, loss: 0.1258796751499176
2023-01-23 00:07:48.095502: step: 420/530, loss: 0.17497166991233826
2023-01-23 00:07:49.204396: step: 424/530, loss: 0.2888738811016083
2023-01-23 00:07:50.300717: step: 428/530, loss: 0.6359089016914368
2023-01-23 00:07:51.392911: step: 432/530, loss: 0.04290004074573517
2023-01-23 00:07:52.485509: step: 436/530, loss: 0.8973314762115479
2023-01-23 00:07:53.581671: step: 440/530, loss: 0.6251528263092041
2023-01-23 00:07:54.711138: step: 444/530, loss: 0.10061698406934738
2023-01-23 00:07:55.830512: step: 448/530, loss: 0.6745343804359436
2023-01-23 00:07:56.941074: step: 452/530, loss: 0.22200122475624084
2023-01-23 00:07:58.061800: step: 456/530, loss: 0.1470044106245041
2023-01-23 00:07:59.162781: step: 460/530, loss: 0.22180795669555664
2023-01-23 00:08:00.270347: step: 464/530, loss: 0.11039237678050995
2023-01-23 00:08:01.395535: step: 468/530, loss: 0.3090516924858093
2023-01-23 00:08:02.511975: step: 472/530, loss: 0.8329148292541504
2023-01-23 00:08:03.613228: step: 476/530, loss: 0.2510644495487213
2023-01-23 00:08:04.706339: step: 480/530, loss: 0.11411610245704651
2023-01-23 00:08:05.822570: step: 484/530, loss: 0.1300908625125885
2023-01-23 00:08:06.952779: step: 488/530, loss: 0.2146996557712555
2023-01-23 00:08:08.060028: step: 492/530, loss: 0.41510438919067383
2023-01-23 00:08:09.163108: step: 496/530, loss: 0.6639122366905212
2023-01-23 00:08:10.276761: step: 500/530, loss: 0.2435392439365387
2023-01-23 00:08:11.381396: step: 504/530, loss: 0.2363567352294922
2023-01-23 00:08:12.510868: step: 508/530, loss: 0.7916234731674194
2023-01-23 00:08:13.635600: step: 512/530, loss: 0.08931379020214081
2023-01-23 00:08:14.763624: step: 516/530, loss: 0.14269299805164337
2023-01-23 00:08:15.863749: step: 520/530, loss: 0.6551990509033203
2023-01-23 00:08:16.983977: step: 524/530, loss: 0.10445032268762589
2023-01-23 00:08:18.114439: step: 528/530, loss: 0.1474807858467102
2023-01-23 00:08:19.254860: step: 532/530, loss: 0.13611894845962524
2023-01-23 00:08:20.373241: step: 536/530, loss: 0.13604116439819336
2023-01-23 00:08:21.489139: step: 540/530, loss: 0.18705740571022034
2023-01-23 00:08:22.599662: step: 544/530, loss: 1.0120625495910645
2023-01-23 00:08:23.755237: step: 548/530, loss: 0.05053301155567169
2023-01-23 00:08:24.895474: step: 552/530, loss: 0.2768556773662567
2023-01-23 00:08:26.023853: step: 556/530, loss: 0.3678132891654968
2023-01-23 00:08:27.132200: step: 560/530, loss: 0.0971141904592514
2023-01-23 00:08:28.250949: step: 564/530, loss: 0.16282042860984802
2023-01-23 00:08:29.401772: step: 568/530, loss: 0.13722917437553406
2023-01-23 00:08:30.551384: step: 572/530, loss: 0.14696092903614044
2023-01-23 00:08:31.732275: step: 576/530, loss: 0.6849290728569031
2023-01-23 00:08:32.830138: step: 580/530, loss: 0.4501667022705078
2023-01-23 00:08:33.957236: step: 584/530, loss: 0.06188564747571945
2023-01-23 00:08:35.041427: step: 588/530, loss: 0.1651732474565506
2023-01-23 00:08:36.138619: step: 592/530, loss: 0.5529107451438904
2023-01-23 00:08:37.269528: step: 596/530, loss: 0.07896395027637482
2023-01-23 00:08:38.366123: step: 600/530, loss: 0.7041786909103394
2023-01-23 00:08:39.482768: step: 604/530, loss: 1.0781370401382446
2023-01-23 00:08:40.563415: step: 608/530, loss: 0.07620349526405334
2023-01-23 00:08:41.641106: step: 612/530, loss: 0.11507193744182587
2023-01-23 00:08:42.735574: step: 616/530, loss: 0.12602777779102325
2023-01-23 00:08:43.838745: step: 620/530, loss: 0.7953168153762817
2023-01-23 00:08:44.978520: step: 624/530, loss: 0.095440573990345
2023-01-23 00:08:46.058114: step: 628/530, loss: 1.2022781372070312
2023-01-23 00:08:47.162300: step: 632/530, loss: 0.1201867163181305
2023-01-23 00:08:48.294683: step: 636/530, loss: 0.014252830296754837
2023-01-23 00:08:49.434120: step: 640/530, loss: 0.6441764831542969
2023-01-23 00:08:50.552905: step: 644/530, loss: 0.24249336123466492
2023-01-23 00:08:51.689264: step: 648/530, loss: 1.9413731098175049
2023-01-23 00:08:52.776505: step: 652/530, loss: 0.08212690055370331
2023-01-23 00:08:53.891001: step: 656/530, loss: 0.10359683632850647
2023-01-23 00:08:55.007520: step: 660/530, loss: 0.37283411622047424
2023-01-23 00:08:56.114109: step: 664/530, loss: 0.10111179947853088
2023-01-23 00:08:57.229838: step: 668/530, loss: 0.24938397109508514
2023-01-23 00:08:58.341417: step: 672/530, loss: 0.17855310440063477
2023-01-23 00:08:59.435400: step: 676/530, loss: 0.1608729362487793
2023-01-23 00:09:00.572161: step: 680/530, loss: 0.1649789810180664
2023-01-23 00:09:01.672305: step: 684/530, loss: 0.5319286584854126
2023-01-23 00:09:02.811456: step: 688/530, loss: 0.12849551439285278
2023-01-23 00:09:03.946105: step: 692/530, loss: 0.28484708070755005
2023-01-23 00:09:05.075125: step: 696/530, loss: 0.09623485058546066
2023-01-23 00:09:06.193823: step: 700/530, loss: 0.21513105928897858
2023-01-23 00:09:07.300607: step: 704/530, loss: 0.3709196150302887
2023-01-23 00:09:08.391351: step: 708/530, loss: 0.16567936539649963
2023-01-23 00:09:09.503036: step: 712/530, loss: 0.37518346309661865
2023-01-23 00:09:10.648201: step: 716/530, loss: 0.14251261949539185
2023-01-23 00:09:11.726084: step: 720/530, loss: 0.12498798966407776
2023-01-23 00:09:12.878793: step: 724/530, loss: 0.6333795785903931
2023-01-23 00:09:13.972817: step: 728/530, loss: 0.17226925492286682
2023-01-23 00:09:15.111333: step: 732/530, loss: 0.12304191291332245
2023-01-23 00:09:16.223196: step: 736/530, loss: 0.17060184478759766
2023-01-23 00:09:17.339645: step: 740/530, loss: 0.43817099928855896
2023-01-23 00:09:18.455575: step: 744/530, loss: 0.07978034019470215
2023-01-23 00:09:19.530064: step: 748/530, loss: 0.6017361283302307
2023-01-23 00:09:20.689441: step: 752/530, loss: 0.36384162306785583
2023-01-23 00:09:21.784281: step: 756/530, loss: 1.220491647720337
2023-01-23 00:09:22.893146: step: 760/530, loss: 0.12230122089385986
2023-01-23 00:09:23.993993: step: 764/530, loss: 0.10451364517211914
2023-01-23 00:09:25.122559: step: 768/530, loss: 0.1675034612417221
2023-01-23 00:09:26.244822: step: 772/530, loss: 0.8957836627960205
2023-01-23 00:09:27.385167: step: 776/530, loss: 0.6963475942611694
2023-01-23 00:09:28.464998: step: 780/530, loss: 0.44131603837013245
2023-01-23 00:09:29.564158: step: 784/530, loss: 0.018154477700591087
2023-01-23 00:09:30.670184: step: 788/530, loss: 0.21204958856105804
2023-01-23 00:09:31.787929: step: 792/530, loss: 0.06024010479450226
2023-01-23 00:09:32.938830: step: 796/530, loss: 0.33726751804351807
2023-01-23 00:09:34.004941: step: 800/530, loss: 0.826570987701416
2023-01-23 00:09:35.119426: step: 804/530, loss: 0.26918625831604004
2023-01-23 00:09:36.230064: step: 808/530, loss: 0.2869883179664612
2023-01-23 00:09:37.333896: step: 812/530, loss: 0.013664627447724342
2023-01-23 00:09:38.437010: step: 816/530, loss: 0.0860753059387207
2023-01-23 00:09:39.584490: step: 820/530, loss: 0.15949583053588867
2023-01-23 00:09:40.692107: step: 824/530, loss: 0.6544192433357239
2023-01-23 00:09:41.824099: step: 828/530, loss: 0.1548047959804535
2023-01-23 00:09:42.930031: step: 832/530, loss: 0.1979069709777832
2023-01-23 00:09:44.030233: step: 836/530, loss: 0.07228050380945206
2023-01-23 00:09:45.142731: step: 840/530, loss: 6.875444412231445
2023-01-23 00:09:46.229102: step: 844/530, loss: 0.2356734275817871
2023-01-23 00:09:47.339803: step: 848/530, loss: 0.6459554433822632
2023-01-23 00:09:48.424277: step: 852/530, loss: 0.6395864486694336
2023-01-23 00:09:49.512179: step: 856/530, loss: 0.20317701995372772
2023-01-23 00:09:50.647595: step: 860/530, loss: 0.25498420000076294
2023-01-23 00:09:51.748991: step: 864/530, loss: 0.11433000862598419
2023-01-23 00:09:52.835056: step: 868/530, loss: 0.06698932498693466
2023-01-23 00:09:53.916214: step: 872/530, loss: 0.1255389153957367
2023-01-23 00:09:55.024383: step: 876/530, loss: 0.11043587327003479
2023-01-23 00:09:56.123356: step: 880/530, loss: 0.2697485089302063
2023-01-23 00:09:57.214571: step: 884/530, loss: 0.05824575573205948
2023-01-23 00:09:58.311999: step: 888/530, loss: 0.11491690576076508
2023-01-23 00:09:59.443808: step: 892/530, loss: 0.2918885350227356
2023-01-23 00:10:00.554753: step: 896/530, loss: 0.029052354395389557
2023-01-23 00:10:01.678372: step: 900/530, loss: 0.12050414085388184
2023-01-23 00:10:02.770337: step: 904/530, loss: 0.06294369697570801
2023-01-23 00:10:03.870849: step: 908/530, loss: 0.18864402174949646
2023-01-23 00:10:04.992092: step: 912/530, loss: 0.19394803047180176
2023-01-23 00:10:06.079796: step: 916/530, loss: 0.7425259351730347
2023-01-23 00:10:07.195963: step: 920/530, loss: 0.9460757970809937
2023-01-23 00:10:08.303756: step: 924/530, loss: 0.12582997977733612
2023-01-23 00:10:09.410238: step: 928/530, loss: 1.155656099319458
2023-01-23 00:10:10.512037: step: 932/530, loss: 0.09659481793642044
2023-01-23 00:10:11.644029: step: 936/530, loss: 1.087873935699463
2023-01-23 00:10:12.767506: step: 940/530, loss: 0.23143865168094635
2023-01-23 00:10:13.847590: step: 944/530, loss: 0.0830029547214508
2023-01-23 00:10:14.948480: step: 948/530, loss: 0.33842581510543823
2023-01-23 00:10:16.083144: step: 952/530, loss: 0.1852489411830902
2023-01-23 00:10:17.197440: step: 956/530, loss: 0.28379565477371216
2023-01-23 00:10:18.297684: step: 960/530, loss: 0.2216116040945053
2023-01-23 00:10:19.391497: step: 964/530, loss: 0.04554443061351776
2023-01-23 00:10:20.488679: step: 968/530, loss: 0.15739575028419495
2023-01-23 00:10:21.560545: step: 972/530, loss: 0.3060400187969208
2023-01-23 00:10:22.673686: step: 976/530, loss: 0.040933992713689804
2023-01-23 00:10:23.771349: step: 980/530, loss: 0.1738167107105255
2023-01-23 00:10:24.853170: step: 984/530, loss: 0.5579696297645569
2023-01-23 00:10:25.996800: step: 988/530, loss: 0.8865674734115601
2023-01-23 00:10:27.124773: step: 992/530, loss: 0.0962413102388382
2023-01-23 00:10:28.264918: step: 996/530, loss: 0.6861871480941772
2023-01-23 00:10:29.374770: step: 1000/530, loss: 0.10171470791101456
2023-01-23 00:10:30.502901: step: 1004/530, loss: 0.8661898970603943
2023-01-23 00:10:31.604847: step: 1008/530, loss: 0.5977591872215271
2023-01-23 00:10:32.707371: step: 1012/530, loss: 0.6103788018226624
2023-01-23 00:10:33.827625: step: 1016/530, loss: 0.2674272656440735
2023-01-23 00:10:34.901710: step: 1020/530, loss: 0.41799864172935486
2023-01-23 00:10:35.996042: step: 1024/530, loss: 0.07545948028564453
2023-01-23 00:10:37.094239: step: 1028/530, loss: 0.2168571949005127
2023-01-23 00:10:38.185632: step: 1032/530, loss: 0.06912942230701447
2023-01-23 00:10:39.290918: step: 1036/530, loss: 0.23729991912841797
2023-01-23 00:10:40.422637: step: 1040/530, loss: 0.8589423894882202
2023-01-23 00:10:41.503783: step: 1044/530, loss: 0.8682339787483215
2023-01-23 00:10:42.587671: step: 1048/530, loss: 0.2830013036727905
2023-01-23 00:10:43.691932: step: 1052/530, loss: 0.9885578155517578
2023-01-23 00:10:44.832993: step: 1056/530, loss: 0.08677569031715393
2023-01-23 00:10:45.952937: step: 1060/530, loss: 0.2631365656852722
2023-01-23 00:10:47.050161: step: 1064/530, loss: 0.1325186789035797
2023-01-23 00:10:48.163396: step: 1068/530, loss: 0.22418874502182007
2023-01-23 00:10:49.257336: step: 1072/530, loss: 1.3695142269134521
2023-01-23 00:10:50.356787: step: 1076/530, loss: 0.8808327317237854
2023-01-23 00:10:51.470615: step: 1080/530, loss: 0.04392242804169655
2023-01-23 00:10:52.586823: step: 1084/530, loss: 0.7642565965652466
2023-01-23 00:10:53.674765: step: 1088/530, loss: 0.025134852156043053
2023-01-23 00:10:54.770183: step: 1092/530, loss: 0.10414576530456543
2023-01-23 00:10:55.865246: step: 1096/530, loss: 0.7188560962677002
2023-01-23 00:10:56.969836: step: 1100/530, loss: 0.17085619270801544
2023-01-23 00:10:58.061232: step: 1104/530, loss: 0.20244550704956055
2023-01-23 00:10:59.156408: step: 1108/530, loss: 0.03152339532971382
2023-01-23 00:11:00.271296: step: 1112/530, loss: 0.17336583137512207
2023-01-23 00:11:01.391649: step: 1116/530, loss: 0.7545679211616516
2023-01-23 00:11:02.501288: step: 1120/530, loss: 0.27101603150367737
2023-01-23 00:11:03.600020: step: 1124/530, loss: 0.09907560050487518
2023-01-23 00:11:04.744941: step: 1128/530, loss: 0.1450391709804535
2023-01-23 00:11:05.836493: step: 1132/530, loss: 0.053304340690374374
2023-01-23 00:11:06.967775: step: 1136/530, loss: 1.410706639289856
2023-01-23 00:11:08.074239: step: 1140/530, loss: 0.7419158816337585
2023-01-23 00:11:09.187768: step: 1144/530, loss: 0.21401935815811157
2023-01-23 00:11:10.324583: step: 1148/530, loss: 0.46108514070510864
2023-01-23 00:11:11.456376: step: 1152/530, loss: 0.7044141292572021
2023-01-23 00:11:12.581143: step: 1156/530, loss: 0.06029639393091202
2023-01-23 00:11:13.709776: step: 1160/530, loss: 0.06458232551813126
2023-01-23 00:11:14.804579: step: 1164/530, loss: 0.4040374755859375
2023-01-23 00:11:15.905587: step: 1168/530, loss: 0.09229516983032227
2023-01-23 00:11:17.003768: step: 1172/530, loss: 0.12368221580982208
2023-01-23 00:11:18.081834: step: 1176/530, loss: 0.3297635018825531
2023-01-23 00:11:19.209923: step: 1180/530, loss: 0.1534641683101654
2023-01-23 00:11:20.315868: step: 1184/530, loss: 0.10368862748146057
2023-01-23 00:11:21.430326: step: 1188/530, loss: 0.09948396682739258
2023-01-23 00:11:22.553697: step: 1192/530, loss: 0.6797982454299927
2023-01-23 00:11:23.670822: step: 1196/530, loss: 0.20515289902687073
2023-01-23 00:11:24.834996: step: 1200/530, loss: 0.7703980803489685
2023-01-23 00:11:25.968812: step: 1204/530, loss: 0.16547727584838867
2023-01-23 00:11:27.077464: step: 1208/530, loss: 0.14820536971092224
2023-01-23 00:11:28.196861: step: 1212/530, loss: 0.4443378448486328
2023-01-23 00:11:29.301044: step: 1216/530, loss: 0.12664613127708435
2023-01-23 00:11:30.416927: step: 1220/530, loss: 0.23765869438648224
2023-01-23 00:11:31.529278: step: 1224/530, loss: 0.06319089233875275
2023-01-23 00:11:32.623867: step: 1228/530, loss: 0.08023710548877716
2023-01-23 00:11:33.784525: step: 1232/530, loss: 0.22510838508605957
2023-01-23 00:11:34.871923: step: 1236/530, loss: 0.05953836441040039
2023-01-23 00:11:35.978944: step: 1240/530, loss: 0.09235696494579315
2023-01-23 00:11:37.077065: step: 1244/530, loss: 0.20956096053123474
2023-01-23 00:11:38.204304: step: 1248/530, loss: 0.28998222947120667
2023-01-23 00:11:39.346935: step: 1252/530, loss: 0.2580730617046356
2023-01-23 00:11:40.490899: step: 1256/530, loss: 0.10675134509801865
2023-01-23 00:11:41.605893: step: 1260/530, loss: 0.6177328824996948
2023-01-23 00:11:42.694176: step: 1264/530, loss: 0.7704175710678101
2023-01-23 00:11:43.808388: step: 1268/530, loss: 0.6815082430839539
2023-01-23 00:11:44.880198: step: 1272/530, loss: 0.13198518753051758
2023-01-23 00:11:45.967428: step: 1276/530, loss: 0.13034024834632874
2023-01-23 00:11:47.074770: step: 1280/530, loss: 0.5580323934555054
2023-01-23 00:11:48.243531: step: 1284/530, loss: 0.269948810338974
2023-01-23 00:11:49.368970: step: 1288/530, loss: 0.26116713881492615
2023-01-23 00:11:50.468990: step: 1292/530, loss: 0.3074115812778473
2023-01-23 00:11:51.572290: step: 1296/530, loss: 0.6316810250282288
2023-01-23 00:11:52.650009: step: 1300/530, loss: 0.07565269619226456
2023-01-23 00:11:53.758280: step: 1304/530, loss: 0.05846991389989853
2023-01-23 00:11:54.863078: step: 1308/530, loss: 0.7852305173873901
2023-01-23 00:11:55.968244: step: 1312/530, loss: 2.439734935760498
2023-01-23 00:11:57.080397: step: 1316/530, loss: 0.021925831213593483
2023-01-23 00:11:58.197862: step: 1320/530, loss: 0.3048337996006012
2023-01-23 00:11:59.293598: step: 1324/530, loss: 0.45132145285606384
2023-01-23 00:12:00.371943: step: 1328/530, loss: 0.9666004776954651
2023-01-23 00:12:01.514289: step: 1332/530, loss: 0.10889368504285812
2023-01-23 00:12:02.624374: step: 1336/530, loss: 0.0897543877363205
2023-01-23 00:12:03.779573: step: 1340/530, loss: 0.999549388885498
2023-01-23 00:12:04.892291: step: 1344/530, loss: 0.19912907481193542
2023-01-23 00:12:06.004023: step: 1348/530, loss: 0.1133183017373085
2023-01-23 00:12:07.129837: step: 1352/530, loss: 0.0887356773018837
2023-01-23 00:12:08.224759: step: 1356/530, loss: 0.19019556045532227
2023-01-23 00:12:09.334572: step: 1360/530, loss: 0.2434220314025879
2023-01-23 00:12:10.449785: step: 1364/530, loss: 0.15951910614967346
2023-01-23 00:12:11.562830: step: 1368/530, loss: 0.12713909149169922
2023-01-23 00:12:12.707949: step: 1372/530, loss: 0.16986556351184845
2023-01-23 00:12:13.803392: step: 1376/530, loss: 0.1644512265920639
2023-01-23 00:12:14.900561: step: 1380/530, loss: 0.03011941909790039
2023-01-23 00:12:15.983340: step: 1384/530, loss: 0.05201082304120064
2023-01-23 00:12:17.109499: step: 1388/530, loss: 0.779977560043335
2023-01-23 00:12:18.216865: step: 1392/530, loss: 0.1605144441127777
2023-01-23 00:12:19.347754: step: 1396/530, loss: 0.11674337089061737
2023-01-23 00:12:20.468004: step: 1400/530, loss: 0.4920404553413391
2023-01-23 00:12:21.545575: step: 1404/530, loss: 0.30350393056869507
2023-01-23 00:12:22.626899: step: 1408/530, loss: 0.11145148426294327
2023-01-23 00:12:23.691438: step: 1412/530, loss: 0.1137409657239914
2023-01-23 00:12:24.805488: step: 1416/530, loss: 0.6228853464126587
2023-01-23 00:12:25.915399: step: 1420/530, loss: 0.5316762924194336
2023-01-23 00:12:27.019071: step: 1424/530, loss: 0.0711304172873497
2023-01-23 00:12:28.093668: step: 1428/530, loss: 4.4109673500061035
2023-01-23 00:12:29.189817: step: 1432/530, loss: 0.16078682243824005
2023-01-23 00:12:30.273513: step: 1436/530, loss: 0.044262077659368515
2023-01-23 00:12:31.362059: step: 1440/530, loss: 0.23200149834156036
2023-01-23 00:12:32.489010: step: 1444/530, loss: 0.39855605363845825
2023-01-23 00:12:33.620732: step: 1448/530, loss: 0.3024076521396637
2023-01-23 00:12:34.724900: step: 1452/530, loss: 0.8743209838867188
2023-01-23 00:12:35.832795: step: 1456/530, loss: 0.3770274221897125
2023-01-23 00:12:36.936325: step: 1460/530, loss: 0.21051377058029175
2023-01-23 00:12:38.045250: step: 1464/530, loss: 0.1844814270734787
2023-01-23 00:12:39.200331: step: 1468/530, loss: 0.13277478516101837
2023-01-23 00:12:40.292263: step: 1472/530, loss: 0.3739944100379944
2023-01-23 00:12:41.379447: step: 1476/530, loss: 0.17986154556274414
2023-01-23 00:12:42.459028: step: 1480/530, loss: 0.16679593920707703
2023-01-23 00:12:43.585899: step: 1484/530, loss: 0.04356050491333008
2023-01-23 00:12:44.683522: step: 1488/530, loss: 0.03346309810876846
2023-01-23 00:12:45.775304: step: 1492/530, loss: 0.08938150852918625
2023-01-23 00:12:46.849789: step: 1496/530, loss: 0.3364669680595398
2023-01-23 00:12:47.935211: step: 1500/530, loss: 0.10517878830432892
2023-01-23 00:12:49.045968: step: 1504/530, loss: 0.2583724856376648
2023-01-23 00:12:50.155595: step: 1508/530, loss: 0.15668517351150513
2023-01-23 00:12:51.258794: step: 1512/530, loss: 0.5459786653518677
2023-01-23 00:12:52.369193: step: 1516/530, loss: 0.20449119806289673
2023-01-23 00:12:53.457377: step: 1520/530, loss: 0.20493429899215698
2023-01-23 00:12:54.580464: step: 1524/530, loss: 0.9568063616752625
2023-01-23 00:12:55.689057: step: 1528/530, loss: 0.17917633056640625
2023-01-23 00:12:56.797400: step: 1532/530, loss: 0.0346684455871582
2023-01-23 00:12:57.900166: step: 1536/530, loss: 0.2769407331943512
2023-01-23 00:12:59.002433: step: 1540/530, loss: 0.0798131451010704
2023-01-23 00:13:00.130423: step: 1544/530, loss: 0.48302823305130005
2023-01-23 00:13:01.239820: step: 1548/530, loss: 0.39195314049720764
2023-01-23 00:13:02.337263: step: 1552/530, loss: 0.6648123264312744
2023-01-23 00:13:03.481558: step: 1556/530, loss: 0.1350722461938858
2023-01-23 00:13:04.594763: step: 1560/530, loss: 0.11914177238941193
2023-01-23 00:13:05.694073: step: 1564/530, loss: 0.17729921638965607
2023-01-23 00:13:06.817905: step: 1568/530, loss: 1.0627611875534058
2023-01-23 00:13:07.942215: step: 1572/530, loss: 0.17662353813648224
2023-01-23 00:13:09.035044: step: 1576/530, loss: 0.21470819413661957
2023-01-23 00:13:10.143165: step: 1580/530, loss: 0.12393327057361603
2023-01-23 00:13:11.250539: step: 1584/530, loss: 0.41027840971946716
2023-01-23 00:13:12.357900: step: 1588/530, loss: 0.1743198037147522
2023-01-23 00:13:13.500995: step: 1592/530, loss: 0.08025846630334854
2023-01-23 00:13:14.618135: step: 1596/530, loss: 0.5930920839309692
2023-01-23 00:13:15.749531: step: 1600/530, loss: 0.25289660692214966
2023-01-23 00:13:16.864407: step: 1604/530, loss: 0.3779110014438629
2023-01-23 00:13:17.972357: step: 1608/530, loss: 0.14294977486133575
2023-01-23 00:13:19.122560: step: 1612/530, loss: 0.09378716349601746
2023-01-23 00:13:20.261866: step: 1616/530, loss: 0.3885635435581207
2023-01-23 00:13:21.383448: step: 1620/530, loss: 0.09046244621276855
2023-01-23 00:13:22.491533: step: 1624/530, loss: 0.06720075756311417
2023-01-23 00:13:23.595810: step: 1628/530, loss: 0.20623335242271423
2023-01-23 00:13:24.761714: step: 1632/530, loss: 0.17597731947898865
2023-01-23 00:13:25.867831: step: 1636/530, loss: 0.15388832986354828
2023-01-23 00:13:26.983383: step: 1640/530, loss: 0.03708148002624512
2023-01-23 00:13:28.098151: step: 1644/530, loss: 0.06569299846887589
2023-01-23 00:13:29.181318: step: 1648/530, loss: 0.7898924946784973
2023-01-23 00:13:30.279234: step: 1652/530, loss: 0.4141145646572113
2023-01-23 00:13:31.412877: step: 1656/530, loss: 0.11449708789587021
2023-01-23 00:13:32.522173: step: 1660/530, loss: 0.1139567419886589
2023-01-23 00:13:33.632968: step: 1664/530, loss: 0.4521687626838684
2023-01-23 00:13:34.734744: step: 1668/530, loss: 0.32162562012672424
2023-01-23 00:13:35.846933: step: 1672/530, loss: 0.0649513229727745
2023-01-23 00:13:36.939385: step: 1676/530, loss: 0.13818113505840302
2023-01-23 00:13:38.057054: step: 1680/530, loss: 0.18604105710983276
2023-01-23 00:13:39.212439: step: 1684/530, loss: 0.5167818069458008
2023-01-23 00:13:40.349274: step: 1688/530, loss: 0.09290018677711487
2023-01-23 00:13:41.450603: step: 1692/530, loss: 0.19726505875587463
2023-01-23 00:13:42.552501: step: 1696/530, loss: 0.14751777052879333
2023-01-23 00:13:43.686558: step: 1700/530, loss: 0.12635822594165802
2023-01-23 00:13:44.788565: step: 1704/530, loss: 0.258309543132782
2023-01-23 00:13:45.860514: step: 1708/530, loss: 0.22176837921142578
2023-01-23 00:13:46.947899: step: 1712/530, loss: 0.1805877685546875
2023-01-23 00:13:48.039661: step: 1716/530, loss: 4.1694865226745605
2023-01-23 00:13:49.145277: step: 1720/530, loss: 0.5522695779800415
2023-01-23 00:13:50.242441: step: 1724/530, loss: 0.28466200828552246
2023-01-23 00:13:51.322310: step: 1728/530, loss: 0.6798132658004761
2023-01-23 00:13:52.448332: step: 1732/530, loss: 0.13943806290626526
2023-01-23 00:13:53.570176: step: 1736/530, loss: 0.4698498845100403
2023-01-23 00:13:54.671221: step: 1740/530, loss: 0.06127600744366646
2023-01-23 00:13:55.756502: step: 1744/530, loss: 0.07682600617408752
2023-01-23 00:13:56.863182: step: 1748/530, loss: 0.25692853331565857
2023-01-23 00:13:57.974740: step: 1752/530, loss: 0.013651752844452858
2023-01-23 00:13:59.088030: step: 1756/530, loss: 0.06762795150279999
2023-01-23 00:14:00.219529: step: 1760/530, loss: 0.36070966720581055
2023-01-23 00:14:01.333121: step: 1764/530, loss: 0.5432117581367493
2023-01-23 00:14:02.410633: step: 1768/530, loss: 0.03974132239818573
2023-01-23 00:14:03.521008: step: 1772/530, loss: 0.145559161901474
2023-01-23 00:14:04.645612: step: 1776/530, loss: 0.25911301374435425
2023-01-23 00:14:05.745492: step: 1780/530, loss: 0.14911337196826935
2023-01-23 00:14:06.851942: step: 1784/530, loss: 0.6018800139427185
2023-01-23 00:14:07.954644: step: 1788/530, loss: 0.2114981710910797
2023-01-23 00:14:09.045712: step: 1792/530, loss: 0.06311145424842834
2023-01-23 00:14:10.143513: step: 1796/530, loss: 0.06796560436487198
2023-01-23 00:14:11.254613: step: 1800/530, loss: 0.1299586296081543
2023-01-23 00:14:12.344831: step: 1804/530, loss: 0.30312222242355347
2023-01-23 00:14:13.429663: step: 1808/530, loss: 1.1231557130813599
2023-01-23 00:14:14.527398: step: 1812/530, loss: 0.6786888241767883
2023-01-23 00:14:15.616689: step: 1816/530, loss: 0.6103639602661133
2023-01-23 00:14:16.728433: step: 1820/530, loss: 0.22400322556495667
2023-01-23 00:14:17.834854: step: 1824/530, loss: 0.36156922578811646
2023-01-23 00:14:18.959670: step: 1828/530, loss: 0.8919402360916138
2023-01-23 00:14:20.068631: step: 1832/530, loss: 0.23228321969509125
2023-01-23 00:14:21.178607: step: 1836/530, loss: 0.6111003756523132
2023-01-23 00:14:22.271377: step: 1840/530, loss: 0.12799987196922302
2023-01-23 00:14:23.412349: step: 1844/530, loss: 0.06422419846057892
2023-01-23 00:14:24.519918: step: 1848/530, loss: 0.3487345576286316
2023-01-23 00:14:25.621272: step: 1852/530, loss: 0.4020829200744629
2023-01-23 00:14:26.753930: step: 1856/530, loss: 0.3677646517753601
2023-01-23 00:14:27.838758: step: 1860/530, loss: 0.13299906253814697
2023-01-23 00:14:28.957588: step: 1864/530, loss: 4.291902542114258
2023-01-23 00:14:30.049357: step: 1868/530, loss: 0.12012176960706711
2023-01-23 00:14:31.142219: step: 1872/530, loss: 0.14619025588035583
2023-01-23 00:14:32.262504: step: 1876/530, loss: 0.4764387309551239
2023-01-23 00:14:33.405437: step: 1880/530, loss: 0.9240580797195435
2023-01-23 00:14:34.531277: step: 1884/530, loss: 0.3990843892097473
2023-01-23 00:14:35.640770: step: 1888/530, loss: 0.6117464303970337
2023-01-23 00:14:36.748570: step: 1892/530, loss: 0.20829543471336365
2023-01-23 00:14:37.877962: step: 1896/530, loss: 0.5275556445121765
2023-01-23 00:14:39.005132: step: 1900/530, loss: 0.39034757018089294
2023-01-23 00:14:40.067064: step: 1904/530, loss: 0.7279199361801147
2023-01-23 00:14:41.155711: step: 1908/530, loss: 0.04306039959192276
2023-01-23 00:14:42.285475: step: 1912/530, loss: 0.8557937741279602
2023-01-23 00:14:43.388006: step: 1916/530, loss: 0.6540085673332214
2023-01-23 00:14:44.459956: step: 1920/530, loss: 0.1145077720284462
2023-01-23 00:14:45.564289: step: 1924/530, loss: 0.2529016435146332
2023-01-23 00:14:46.685799: step: 1928/530, loss: 0.14663295447826385
2023-01-23 00:14:47.759603: step: 1932/530, loss: 0.07276878505945206
2023-01-23 00:14:48.863292: step: 1936/530, loss: 0.8042235970497131
2023-01-23 00:14:49.972616: step: 1940/530, loss: 0.11825352162122726
2023-01-23 00:14:51.092636: step: 1944/530, loss: 0.08867798745632172
2023-01-23 00:14:52.205906: step: 1948/530, loss: 0.1077207624912262
2023-01-23 00:14:53.353646: step: 1952/530, loss: 0.3472803235054016
2023-01-23 00:14:54.473099: step: 1956/530, loss: 0.8304993510246277
2023-01-23 00:14:55.558151: step: 1960/530, loss: 0.48092469573020935
2023-01-23 00:14:56.632651: step: 1964/530, loss: 0.15356428921222687
2023-01-23 00:14:57.724135: step: 1968/530, loss: 0.7775717973709106
2023-01-23 00:14:58.811290: step: 1972/530, loss: 0.18315431475639343
2023-01-23 00:14:59.908932: step: 1976/530, loss: 0.36433085799217224
2023-01-23 00:15:01.019518: step: 1980/530, loss: 0.12672452628612518
2023-01-23 00:15:02.135752: step: 1984/530, loss: 0.32066115736961365
2023-01-23 00:15:03.284853: step: 1988/530, loss: 0.15512457489967346
2023-01-23 00:15:04.402138: step: 1992/530, loss: 0.09265957027673721
2023-01-23 00:15:05.511345: step: 1996/530, loss: 0.06471529603004456
2023-01-23 00:15:06.656371: step: 2000/530, loss: 0.20603902637958527
2023-01-23 00:15:07.752174: step: 2004/530, loss: 0.12524700164794922
2023-01-23 00:15:08.882530: step: 2008/530, loss: 0.051560115069150925
2023-01-23 00:15:09.995486: step: 2012/530, loss: 0.0667935386300087
2023-01-23 00:15:11.078603: step: 2016/530, loss: 0.3049278259277344
2023-01-23 00:15:12.177680: step: 2020/530, loss: 0.14669866859912872
2023-01-23 00:15:13.293931: step: 2024/530, loss: 0.13566313683986664
2023-01-23 00:15:14.408078: step: 2028/530, loss: 0.6377245783805847
2023-01-23 00:15:15.492277: step: 2032/530, loss: 0.1285000890493393
2023-01-23 00:15:16.608504: step: 2036/530, loss: 0.10911282896995544
2023-01-23 00:15:17.716862: step: 2040/530, loss: 0.6941738724708557
2023-01-23 00:15:18.833885: step: 2044/530, loss: 0.33101046085357666
2023-01-23 00:15:19.969622: step: 2048/530, loss: 0.6142401099205017
2023-01-23 00:15:21.073430: step: 2052/530, loss: 0.41217711567878723
2023-01-23 00:15:22.186759: step: 2056/530, loss: 0.09512200951576233
2023-01-23 00:15:23.288358: step: 2060/530, loss: 0.11377761512994766
2023-01-23 00:15:24.393565: step: 2064/530, loss: 0.19775763154029846
2023-01-23 00:15:25.499032: step: 2068/530, loss: 0.07653675228357315
2023-01-23 00:15:26.592396: step: 2072/530, loss: 0.32089900970458984
2023-01-23 00:15:27.677463: step: 2076/530, loss: 0.0761415958404541
2023-01-23 00:15:28.796928: step: 2080/530, loss: 0.2697104811668396
2023-01-23 00:15:29.929066: step: 2084/530, loss: 0.05600576475262642
2023-01-23 00:15:31.024048: step: 2088/530, loss: 0.11992950737476349
2023-01-23 00:15:32.120497: step: 2092/530, loss: 0.0929257944226265
2023-01-23 00:15:33.263639: step: 2096/530, loss: 0.27150383591651917
2023-01-23 00:15:34.386938: step: 2100/530, loss: 0.1220850944519043
2023-01-23 00:15:35.501772: step: 2104/530, loss: 1.0428532361984253
2023-01-23 00:15:36.629878: step: 2108/530, loss: 0.15821132063865662
2023-01-23 00:15:37.730162: step: 2112/530, loss: 0.5825380682945251
2023-01-23 00:15:38.849341: step: 2116/530, loss: 0.7651004791259766
2023-01-23 00:15:39.966729: step: 2120/530, loss: 0.7224260568618774
==================================================
Loss: 0.376
--------------------
Dev: {'event': {'p': 0.5357852882703777, 'r': 0.7177097203728362, 'f1': 0.6135458167330677}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Test: {'event': {'p': 0.5814155449413808, 'r': 0.7803030303030303, 'f1': 0.6663349091813884}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Chinese: {'event': {'p': 0.5316455696202531, 'r': 0.7777777777777778, 'f1': 0.6315789473684209}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Korean: {'event': {'p': 0.6037735849056604, 'r': 0.5079365079365079, 'f1': 0.5517241379310345}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
Russian: {'event': {'p': 0.391304347826087, 'r': 0.5, 'f1': 0.4390243902439025}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 4}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6218961625282167, 'r': 0.7336884154460719, 'f1': 0.6731826511912034}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Eng Test for Chinese: {'event': {'p': 0.6148681055155876, 'r': 0.747086247086247, 'f1': 0.6745593264930282}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Sample Chinese: {'event': {'p': 0.5970149253731343, 'r': 0.7407407407407407, 'f1': 0.6611570247933883}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6218961625282167, 'r': 0.7336884154460719, 'f1': 0.6731826511912034}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Eng Test for Korean: {'event': {'p': 0.6148681055155876, 'r': 0.747086247086247, 'f1': 0.6745593264930282}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Sample Korean: {'event': {'p': 0.7631578947368421, 'r': 0.4603174603174603, 'f1': 0.5742574257425742}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5862457722660653, 'r': 0.6924101198402131, 'f1': 0.634920634920635}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Eng Test for Russian: {'event': {'p': 0.5994652406417113, 'r': 0.6532634032634033, 'f1': 0.6252091466815394}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Sample Russian: {'event': {'p': 0.625, 'r': 0.4166666666666667, 'f1': 0.5}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
******************************
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 00:16:19.691239: step: 4/530, loss: 0.1551334410905838
2023-01-23 00:16:20.813026: step: 8/530, loss: 0.15506239235401154
2023-01-23 00:16:21.912910: step: 12/530, loss: 0.09207554161548615
2023-01-23 00:16:23.009602: step: 16/530, loss: 0.27854424715042114
2023-01-23 00:16:24.110606: step: 20/530, loss: 0.06261630356311798
2023-01-23 00:16:25.220509: step: 24/530, loss: 0.07133197784423828
2023-01-23 00:16:26.315888: step: 28/530, loss: 0.18068867921829224
2023-01-23 00:16:27.456252: step: 32/530, loss: 0.20504236221313477
2023-01-23 00:16:28.554480: step: 36/530, loss: 0.15022096037864685
2023-01-23 00:16:29.663243: step: 40/530, loss: 0.07955169677734375
2023-01-23 00:16:30.774657: step: 44/530, loss: 0.16164475679397583
2023-01-23 00:16:31.873500: step: 48/530, loss: 0.43493157625198364
2023-01-23 00:16:32.994080: step: 52/530, loss: 0.08911388367414474
2023-01-23 00:16:34.097707: step: 56/530, loss: 0.3782656490802765
2023-01-23 00:16:35.204747: step: 60/530, loss: 0.13911986351013184
2023-01-23 00:16:36.310427: step: 64/530, loss: 0.21054372191429138
2023-01-23 00:16:37.421216: step: 68/530, loss: 0.17701081931591034
2023-01-23 00:16:38.532759: step: 72/530, loss: 0.06115255504846573
2023-01-23 00:16:39.641203: step: 76/530, loss: 0.06634383648633957
2023-01-23 00:16:40.709241: step: 80/530, loss: 0.07450045645236969
2023-01-23 00:16:41.813645: step: 84/530, loss: 0.2603018879890442
2023-01-23 00:16:42.925070: step: 88/530, loss: 0.14794005453586578
2023-01-23 00:16:44.031317: step: 92/530, loss: 0.04748525843024254
2023-01-23 00:16:45.119738: step: 96/530, loss: 0.18634852766990662
2023-01-23 00:16:46.230748: step: 100/530, loss: 0.2666800618171692
2023-01-23 00:16:47.339433: step: 104/530, loss: 0.14606314897537231
2023-01-23 00:16:48.444015: step: 108/530, loss: 0.053810931742191315
2023-01-23 00:16:49.545528: step: 112/530, loss: 0.056484125554561615
2023-01-23 00:16:50.671715: step: 116/530, loss: 0.02945990487933159
2023-01-23 00:16:51.762848: step: 120/530, loss: 0.08317270129919052
2023-01-23 00:16:52.843112: step: 124/530, loss: 0.08401679992675781
2023-01-23 00:16:53.970024: step: 128/530, loss: 0.21548672020435333
2023-01-23 00:16:55.061437: step: 132/530, loss: 0.2645147144794464
2023-01-23 00:16:56.139686: step: 136/530, loss: 0.05896034091711044
2023-01-23 00:16:57.238762: step: 140/530, loss: 0.1117984801530838
2023-01-23 00:16:58.347808: step: 144/530, loss: 0.1106325164437294
2023-01-23 00:16:59.480690: step: 148/530, loss: 0.06767185032367706
2023-01-23 00:17:00.572490: step: 152/530, loss: 0.14967116713523865
2023-01-23 00:17:01.676212: step: 156/530, loss: 0.19012156128883362
2023-01-23 00:17:02.791903: step: 160/530, loss: 0.03276777267456055
2023-01-23 00:17:03.912686: step: 164/530, loss: 0.31172531843185425
2023-01-23 00:17:05.001845: step: 168/530, loss: 0.114691823720932
2023-01-23 00:17:06.103215: step: 172/530, loss: 0.18882575631141663
2023-01-23 00:17:07.236991: step: 176/530, loss: 0.11627378314733505
2023-01-23 00:17:08.334265: step: 180/530, loss: 0.10448499023914337
2023-01-23 00:17:09.427608: step: 184/530, loss: 0.14155977964401245
2023-01-23 00:17:10.535326: step: 188/530, loss: 0.8063328266143799
2023-01-23 00:17:11.623376: step: 192/530, loss: 0.0875302329659462
2023-01-23 00:17:12.717746: step: 196/530, loss: 0.5578939318656921
2023-01-23 00:17:13.829944: step: 200/530, loss: 0.10926227271556854
2023-01-23 00:17:14.931424: step: 204/530, loss: 0.7452509999275208
2023-01-23 00:17:16.040078: step: 208/530, loss: 0.03836231306195259
2023-01-23 00:17:17.151569: step: 212/530, loss: 0.09682293236255646
2023-01-23 00:17:18.273072: step: 216/530, loss: 0.15231674909591675
2023-01-23 00:17:19.375110: step: 220/530, loss: 0.117932990193367
2023-01-23 00:17:20.472583: step: 224/530, loss: 0.6837148666381836
2023-01-23 00:17:21.586669: step: 228/530, loss: 0.2826762795448303
2023-01-23 00:17:22.732525: step: 232/530, loss: 0.5543189644813538
2023-01-23 00:17:23.831058: step: 236/530, loss: 0.15985733270645142
2023-01-23 00:17:24.931007: step: 240/530, loss: 0.24577981233596802
2023-01-23 00:17:26.070333: step: 244/530, loss: 0.9133776426315308
2023-01-23 00:17:27.178320: step: 248/530, loss: 0.6930559277534485
2023-01-23 00:17:28.298528: step: 252/530, loss: 0.09299831092357635
2023-01-23 00:17:29.396364: step: 256/530, loss: 0.2885358929634094
2023-01-23 00:17:30.525117: step: 260/530, loss: 0.1749928593635559
2023-01-23 00:17:31.615560: step: 264/530, loss: 0.10827026516199112
2023-01-23 00:17:32.712759: step: 268/530, loss: 0.02184920385479927
2023-01-23 00:17:33.826211: step: 272/530, loss: 0.3510655462741852
2023-01-23 00:17:34.933893: step: 276/530, loss: 0.1348002851009369
2023-01-23 00:17:36.033986: step: 280/530, loss: 0.11623439192771912
2023-01-23 00:17:37.144979: step: 284/530, loss: 0.09722137451171875
2023-01-23 00:17:38.277457: step: 288/530, loss: 0.11461953818798065
2023-01-23 00:17:39.374213: step: 292/530, loss: 0.04510857164859772
2023-01-23 00:17:40.520961: step: 296/530, loss: 0.2510346472263336
2023-01-23 00:17:41.616489: step: 300/530, loss: 0.10553913563489914
2023-01-23 00:17:42.713297: step: 304/530, loss: 0.19953250885009766
2023-01-23 00:17:43.839657: step: 308/530, loss: 0.25582802295684814
2023-01-23 00:17:44.930885: step: 312/530, loss: 0.20102459192276
2023-01-23 00:17:46.029725: step: 316/530, loss: 0.24607200920581818
2023-01-23 00:17:47.138381: step: 320/530, loss: 0.8732153177261353
2023-01-23 00:17:48.257242: step: 324/530, loss: 2.055403709411621
2023-01-23 00:17:49.362589: step: 328/530, loss: 0.03215141221880913
2023-01-23 00:17:50.436622: step: 332/530, loss: 0.32044148445129395
2023-01-23 00:17:51.543783: step: 336/530, loss: 0.34932661056518555
2023-01-23 00:17:52.655801: step: 340/530, loss: 0.12172860652208328
2023-01-23 00:17:53.754110: step: 344/530, loss: 0.24385175108909607
2023-01-23 00:17:54.865278: step: 348/530, loss: 0.4071502685546875
2023-01-23 00:17:55.963650: step: 352/530, loss: 0.683687150478363
2023-01-23 00:17:57.083610: step: 356/530, loss: 0.6186181306838989
2023-01-23 00:17:58.179725: step: 360/530, loss: 0.1526637077331543
2023-01-23 00:17:59.295217: step: 364/530, loss: 0.5194263458251953
2023-01-23 00:18:00.451047: step: 368/530, loss: 0.1720869243144989
2023-01-23 00:18:01.546078: step: 372/530, loss: 0.11544866859912872
2023-01-23 00:18:02.623197: step: 376/530, loss: 0.19601230323314667
2023-01-23 00:18:03.727247: step: 380/530, loss: 0.18928222358226776
2023-01-23 00:18:04.833044: step: 384/530, loss: 0.035704806447029114
2023-01-23 00:18:05.929717: step: 388/530, loss: 0.3087407052516937
2023-01-23 00:18:07.035762: step: 392/530, loss: 0.1764741986989975
2023-01-23 00:18:08.148604: step: 396/530, loss: 0.12920570373535156
2023-01-23 00:18:09.257062: step: 400/530, loss: 0.19927386939525604
2023-01-23 00:18:10.352352: step: 404/530, loss: 0.13349667191505432
2023-01-23 00:18:11.479219: step: 408/530, loss: 0.4260912835597992
2023-01-23 00:18:12.598025: step: 412/530, loss: 0.1230802983045578
2023-01-23 00:18:13.702153: step: 416/530, loss: 0.05097360908985138
2023-01-23 00:18:14.789209: step: 420/530, loss: 0.4008246660232544
2023-01-23 00:18:15.875168: step: 424/530, loss: 0.0753335952758789
2023-01-23 00:18:17.008952: step: 428/530, loss: 0.1770675629377365
2023-01-23 00:18:18.093203: step: 432/530, loss: 0.18485641479492188
2023-01-23 00:18:19.198855: step: 436/530, loss: 0.09987812489271164
2023-01-23 00:18:20.358083: step: 440/530, loss: 0.4275304079055786
2023-01-23 00:18:21.439549: step: 444/530, loss: 0.24299153685569763
2023-01-23 00:18:22.567526: step: 448/530, loss: 0.5446224212646484
2023-01-23 00:18:23.659756: step: 452/530, loss: 0.4821932315826416
2023-01-23 00:18:24.748458: step: 456/530, loss: 0.1085105910897255
2023-01-23 00:18:25.864630: step: 460/530, loss: 0.0808354914188385
2023-01-23 00:18:26.982696: step: 464/530, loss: 0.27912312746047974
2023-01-23 00:18:28.082743: step: 468/530, loss: 0.03377389907836914
2023-01-23 00:18:29.199927: step: 472/530, loss: 0.49941492080688477
2023-01-23 00:18:30.323563: step: 476/530, loss: 0.528192937374115
2023-01-23 00:18:31.406445: step: 480/530, loss: 0.08554622530937195
2023-01-23 00:18:32.552720: step: 484/530, loss: 0.11619433760643005
2023-01-23 00:18:33.681025: step: 488/530, loss: 0.08876297622919083
2023-01-23 00:18:34.806259: step: 492/530, loss: 0.050025273114442825
2023-01-23 00:18:35.907083: step: 496/530, loss: 0.16717156767845154
2023-01-23 00:18:37.018075: step: 500/530, loss: 0.11093826591968536
2023-01-23 00:18:38.153486: step: 504/530, loss: 0.5166789889335632
2023-01-23 00:18:39.238814: step: 508/530, loss: 0.21503543853759766
2023-01-23 00:18:40.329921: step: 512/530, loss: 0.13059958815574646
2023-01-23 00:18:41.472934: step: 516/530, loss: 0.05246753618121147
2023-01-23 00:18:42.555684: step: 520/530, loss: 0.08229523152112961
2023-01-23 00:18:43.682717: step: 524/530, loss: 0.28197503089904785
2023-01-23 00:18:44.810173: step: 528/530, loss: 0.027631474658846855
2023-01-23 00:18:45.891684: step: 532/530, loss: 0.06330624222755432
2023-01-23 00:18:46.976373: step: 536/530, loss: 0.1302996575832367
2023-01-23 00:18:48.099295: step: 540/530, loss: 0.571711540222168
2023-01-23 00:18:49.199539: step: 544/530, loss: 0.6873383522033691
2023-01-23 00:18:50.291859: step: 548/530, loss: 0.0732763335108757
2023-01-23 00:18:51.364787: step: 552/530, loss: 0.507550835609436
2023-01-23 00:18:52.487478: step: 556/530, loss: 0.2017727792263031
2023-01-23 00:18:53.617472: step: 560/530, loss: 0.19548659026622772
2023-01-23 00:18:54.725725: step: 564/530, loss: 0.11503373086452484
2023-01-23 00:18:55.821284: step: 568/530, loss: 0.10834093391895294
2023-01-23 00:18:56.948498: step: 572/530, loss: 0.31352147459983826
2023-01-23 00:18:58.070972: step: 576/530, loss: 0.3023146092891693
2023-01-23 00:18:59.162859: step: 580/530, loss: 0.10832566767930984
2023-01-23 00:19:00.277009: step: 584/530, loss: 0.16336631774902344
2023-01-23 00:19:01.380749: step: 588/530, loss: 0.2481825053691864
2023-01-23 00:19:02.470491: step: 592/530, loss: 0.19358697533607483
2023-01-23 00:19:03.589815: step: 596/530, loss: 0.09596281498670578
2023-01-23 00:19:04.708619: step: 600/530, loss: 0.1801118403673172
2023-01-23 00:19:05.781109: step: 604/530, loss: 0.035079386085271835
2023-01-23 00:19:06.856504: step: 608/530, loss: 0.2649992108345032
2023-01-23 00:19:07.976740: step: 612/530, loss: 0.4586508870124817
2023-01-23 00:19:09.106715: step: 616/530, loss: 0.10550659894943237
2023-01-23 00:19:10.229463: step: 620/530, loss: 0.2990129590034485
2023-01-23 00:19:11.323279: step: 624/530, loss: 0.12080173939466476
2023-01-23 00:19:12.411865: step: 628/530, loss: 0.8232208490371704
2023-01-23 00:19:13.546481: step: 632/530, loss: 0.08620691299438477
2023-01-23 00:19:14.663178: step: 636/530, loss: 0.09553317725658417
2023-01-23 00:19:15.799985: step: 640/530, loss: 0.11280690133571625
2023-01-23 00:19:16.925111: step: 644/530, loss: 0.1648930460214615
2023-01-23 00:19:18.024782: step: 648/530, loss: 0.08147326111793518
2023-01-23 00:19:19.122030: step: 652/530, loss: 0.07111148536205292
2023-01-23 00:19:20.212426: step: 656/530, loss: 0.06882968544960022
2023-01-23 00:19:21.311902: step: 660/530, loss: 0.07458258420228958
2023-01-23 00:19:22.407622: step: 664/530, loss: 0.06435642391443253
2023-01-23 00:19:23.508974: step: 668/530, loss: 0.03547873720526695
2023-01-23 00:19:24.609183: step: 672/530, loss: 0.3290373980998993
2023-01-23 00:19:25.704761: step: 676/530, loss: 0.12128964066505432
2023-01-23 00:19:26.797523: step: 680/530, loss: 0.022686099633574486
2023-01-23 00:19:27.864870: step: 684/530, loss: 0.05937033146619797
2023-01-23 00:19:28.959196: step: 688/530, loss: 0.15541739761829376
2023-01-23 00:19:30.063526: step: 692/530, loss: 0.5816463232040405
2023-01-23 00:19:31.146450: step: 696/530, loss: 0.16766855120658875
2023-01-23 00:19:32.245507: step: 700/530, loss: 0.8123835325241089
2023-01-23 00:19:33.358964: step: 704/530, loss: 0.06023269146680832
2023-01-23 00:19:34.428815: step: 708/530, loss: 0.23824810981750488
2023-01-23 00:19:35.511245: step: 712/530, loss: 0.14797411859035492
2023-01-23 00:19:36.623026: step: 716/530, loss: 0.4418337941169739
2023-01-23 00:19:37.719161: step: 720/530, loss: 0.11328492313623428
2023-01-23 00:19:38.852213: step: 724/530, loss: 0.5148612856864929
2023-01-23 00:19:39.964085: step: 728/530, loss: 0.1719207763671875
2023-01-23 00:19:41.053022: step: 732/530, loss: 0.08941535651683807
2023-01-23 00:19:42.137174: step: 736/530, loss: 0.4617215394973755
2023-01-23 00:19:43.249779: step: 740/530, loss: 0.24298229813575745
2023-01-23 00:19:44.361378: step: 744/530, loss: 0.1684858351945877
2023-01-23 00:19:45.464485: step: 748/530, loss: 0.13890667259693146
2023-01-23 00:19:46.580620: step: 752/530, loss: 0.0818004161119461
2023-01-23 00:19:47.668424: step: 756/530, loss: 0.3300046920776367
2023-01-23 00:19:48.767288: step: 760/530, loss: 0.049156855791807175
2023-01-23 00:19:49.904208: step: 764/530, loss: 0.6946603655815125
2023-01-23 00:19:51.002123: step: 768/530, loss: 0.1192299872636795
2023-01-23 00:19:52.137541: step: 772/530, loss: 0.5141354203224182
2023-01-23 00:19:53.255224: step: 776/530, loss: 0.18026676774024963
2023-01-23 00:19:54.359851: step: 780/530, loss: 0.05397465452551842
2023-01-23 00:19:55.518356: step: 784/530, loss: 0.1251480132341385
2023-01-23 00:19:56.615202: step: 788/530, loss: 0.7057846188545227
2023-01-23 00:19:57.699027: step: 792/530, loss: 0.4519307613372803
2023-01-23 00:19:58.790165: step: 796/530, loss: 0.14722080528736115
2023-01-23 00:19:59.875453: step: 800/530, loss: 0.09747543931007385
2023-01-23 00:20:00.999298: step: 804/530, loss: 0.077850341796875
2023-01-23 00:20:02.085295: step: 808/530, loss: 0.10528307408094406
2023-01-23 00:20:03.201276: step: 812/530, loss: 0.09825949370861053
2023-01-23 00:20:04.308637: step: 816/530, loss: 0.06850776821374893
2023-01-23 00:20:05.411707: step: 820/530, loss: 0.30127421021461487
2023-01-23 00:20:06.533415: step: 824/530, loss: 0.14816370606422424
2023-01-23 00:20:07.652577: step: 828/530, loss: 0.14640340209007263
2023-01-23 00:20:08.764300: step: 832/530, loss: 2.4464852809906006
2023-01-23 00:20:09.871562: step: 836/530, loss: 0.06996269524097443
2023-01-23 00:20:11.009797: step: 840/530, loss: 0.14491620659828186
2023-01-23 00:20:12.113214: step: 844/530, loss: 0.06943173706531525
2023-01-23 00:20:13.226800: step: 848/530, loss: 0.1271343231201172
2023-01-23 00:20:14.341954: step: 852/530, loss: 0.11489133536815643
2023-01-23 00:20:15.472126: step: 856/530, loss: 0.15254774689674377
2023-01-23 00:20:16.565667: step: 860/530, loss: 0.18742027878761292
2023-01-23 00:20:17.669387: step: 864/530, loss: 0.3837968707084656
2023-01-23 00:20:18.792616: step: 868/530, loss: 0.1033800020813942
2023-01-23 00:20:19.937090: step: 872/530, loss: 0.03995781019330025
2023-01-23 00:20:21.082582: step: 876/530, loss: 0.13536810874938965
2023-01-23 00:20:22.201534: step: 880/530, loss: 0.28823918104171753
2023-01-23 00:20:23.292003: step: 884/530, loss: 0.024879170581698418
2023-01-23 00:20:24.417300: step: 888/530, loss: 0.10541597008705139
2023-01-23 00:20:25.571433: step: 892/530, loss: 0.024629544466733932
2023-01-23 00:20:26.678554: step: 896/530, loss: 0.1403234601020813
2023-01-23 00:20:27.801185: step: 900/530, loss: 0.02727055549621582
2023-01-23 00:20:28.912668: step: 904/530, loss: 0.31268197298049927
2023-01-23 00:20:30.065171: step: 908/530, loss: 0.09237900376319885
2023-01-23 00:20:31.165368: step: 912/530, loss: 0.13170138001441956
2023-01-23 00:20:32.287247: step: 916/530, loss: 0.1602492332458496
2023-01-23 00:20:33.425608: step: 920/530, loss: 0.08932428807020187
2023-01-23 00:20:34.523015: step: 924/530, loss: 0.05107317119836807
2023-01-23 00:20:35.618457: step: 928/530, loss: 0.08118797093629837
2023-01-23 00:20:36.716264: step: 932/530, loss: 0.7868897318840027
2023-01-23 00:20:37.825168: step: 936/530, loss: 0.48330992460250854
2023-01-23 00:20:38.918419: step: 940/530, loss: 0.2798249423503876
2023-01-23 00:20:40.016157: step: 944/530, loss: 0.18205463886260986
2023-01-23 00:20:41.093636: step: 948/530, loss: 0.07632866501808167
2023-01-23 00:20:42.206980: step: 952/530, loss: 0.14600276947021484
2023-01-23 00:20:43.308781: step: 956/530, loss: 0.12420116364955902
2023-01-23 00:20:44.424939: step: 960/530, loss: 0.17914581298828125
2023-01-23 00:20:45.524082: step: 964/530, loss: 0.07404899597167969
2023-01-23 00:20:46.659915: step: 968/530, loss: 0.07964115589857101
2023-01-23 00:20:47.750807: step: 972/530, loss: 0.681236743927002
2023-01-23 00:20:48.870437: step: 976/530, loss: 0.07720178365707397
2023-01-23 00:20:49.975680: step: 980/530, loss: 0.0829225480556488
2023-01-23 00:20:51.078767: step: 984/530, loss: 0.3658096492290497
2023-01-23 00:20:52.154111: step: 988/530, loss: 0.06196928024291992
2023-01-23 00:20:53.288469: step: 992/530, loss: 0.10722789913415909
2023-01-23 00:20:54.395934: step: 996/530, loss: 0.4925207495689392
2023-01-23 00:20:55.479725: step: 1000/530, loss: 0.3912269175052643
2023-01-23 00:20:56.582449: step: 1004/530, loss: 0.2373783141374588
2023-01-23 00:20:57.676699: step: 1008/530, loss: 0.1158268004655838
2023-01-23 00:20:58.793328: step: 1012/530, loss: 0.27045750617980957
2023-01-23 00:20:59.880915: step: 1016/530, loss: 0.25494688749313354
2023-01-23 00:21:00.982073: step: 1020/530, loss: 0.08006344735622406
2023-01-23 00:21:02.119098: step: 1024/530, loss: 0.1371137797832489
2023-01-23 00:21:03.221016: step: 1028/530, loss: 0.1419234722852707
2023-01-23 00:21:04.327413: step: 1032/530, loss: 0.5381125211715698
2023-01-23 00:21:05.458184: step: 1036/530, loss: 0.3982507884502411
2023-01-23 00:21:06.569818: step: 1040/530, loss: 0.0492701530456543
2023-01-23 00:21:07.670920: step: 1044/530, loss: 0.9635698795318604
2023-01-23 00:21:08.761172: step: 1048/530, loss: 0.3938000798225403
2023-01-23 00:21:09.867644: step: 1052/530, loss: 0.1287788301706314
2023-01-23 00:21:10.972759: step: 1056/530, loss: 0.17013044655323029
2023-01-23 00:21:12.056001: step: 1060/530, loss: 0.25862035155296326
2023-01-23 00:21:13.202278: step: 1064/530, loss: 0.11327219009399414
2023-01-23 00:21:14.293780: step: 1068/530, loss: 0.1711740493774414
2023-01-23 00:21:15.391435: step: 1072/530, loss: 0.08898964524269104
2023-01-23 00:21:16.518991: step: 1076/530, loss: 0.015608405694365501
2023-01-23 00:21:17.650564: step: 1080/530, loss: 0.1789204627275467
2023-01-23 00:21:18.771902: step: 1084/530, loss: 0.44742846488952637
2023-01-23 00:21:19.901469: step: 1088/530, loss: 0.18467745184898376
2023-01-23 00:21:21.031149: step: 1092/530, loss: 0.570391058921814
2023-01-23 00:21:22.118251: step: 1096/530, loss: 0.046108148992061615
2023-01-23 00:21:23.224781: step: 1100/530, loss: 0.36170142889022827
2023-01-23 00:21:24.347047: step: 1104/530, loss: 0.22364887595176697
2023-01-23 00:21:25.475887: step: 1108/530, loss: 0.1683967560529709
2023-01-23 00:21:26.567083: step: 1112/530, loss: 0.19797784090042114
2023-01-23 00:21:27.674478: step: 1116/530, loss: 0.4206046164035797
2023-01-23 00:21:28.774629: step: 1120/530, loss: 0.14374756813049316
2023-01-23 00:21:29.901252: step: 1124/530, loss: 0.19197100400924683
2023-01-23 00:21:30.984382: step: 1128/530, loss: 0.13220463693141937
2023-01-23 00:21:32.102883: step: 1132/530, loss: 0.13229341804981232
2023-01-23 00:21:33.196363: step: 1136/530, loss: 0.11121062934398651
2023-01-23 00:21:34.305295: step: 1140/530, loss: 0.25190994143486023
2023-01-23 00:21:35.433938: step: 1144/530, loss: 0.1703149825334549
2023-01-23 00:21:36.530961: step: 1148/530, loss: 0.22351226210594177
2023-01-23 00:21:37.601582: step: 1152/530, loss: 0.14180825650691986
2023-01-23 00:21:38.729055: step: 1156/530, loss: 0.30212706327438354
2023-01-23 00:21:39.834303: step: 1160/530, loss: 0.24663162231445312
2023-01-23 00:21:40.926588: step: 1164/530, loss: 0.07623492926359177
2023-01-23 00:21:42.061932: step: 1168/530, loss: 0.16749143600463867
2023-01-23 00:21:43.147950: step: 1172/530, loss: 0.10929059982299805
2023-01-23 00:21:44.272674: step: 1176/530, loss: 0.11108779907226562
2023-01-23 00:21:45.370056: step: 1180/530, loss: 0.23363837599754333
2023-01-23 00:21:46.488455: step: 1184/530, loss: 0.11246080696582794
2023-01-23 00:21:47.591532: step: 1188/530, loss: 0.1567060351371765
2023-01-23 00:21:48.696266: step: 1192/530, loss: 0.316013902425766
2023-01-23 00:21:49.825415: step: 1196/530, loss: 0.2026081085205078
2023-01-23 00:21:50.932198: step: 1200/530, loss: 0.09864607453346252
2023-01-23 00:21:52.028330: step: 1204/530, loss: 0.07972478866577148
2023-01-23 00:21:53.159756: step: 1208/530, loss: 0.3105006217956543
2023-01-23 00:21:54.270031: step: 1212/530, loss: 0.10917239636182785
2023-01-23 00:21:55.379671: step: 1216/530, loss: 0.5183642506599426
2023-01-23 00:21:56.475973: step: 1220/530, loss: 0.04536862298846245
2023-01-23 00:21:57.576957: step: 1224/530, loss: 0.11565761268138885
2023-01-23 00:21:58.693983: step: 1228/530, loss: 0.09205341339111328
2023-01-23 00:21:59.819806: step: 1232/530, loss: 0.06267061084508896
2023-01-23 00:22:00.906257: step: 1236/530, loss: 2.686462879180908
2023-01-23 00:22:02.032800: step: 1240/530, loss: 0.3050172030925751
2023-01-23 00:22:03.157301: step: 1244/530, loss: 0.06304530799388885
2023-01-23 00:22:04.238381: step: 1248/530, loss: 0.1627376675605774
2023-01-23 00:22:05.338369: step: 1252/530, loss: 0.46814003586769104
2023-01-23 00:22:06.431771: step: 1256/530, loss: 0.06027372553944588
2023-01-23 00:22:07.533613: step: 1260/530, loss: 0.2399989515542984
2023-01-23 00:22:08.634176: step: 1264/530, loss: 0.14789867401123047
2023-01-23 00:22:09.741307: step: 1268/530, loss: 0.22475624084472656
2023-01-23 00:22:10.843918: step: 1272/530, loss: 0.7256162762641907
2023-01-23 00:22:11.990273: step: 1276/530, loss: 0.05831442028284073
2023-01-23 00:22:13.072016: step: 1280/530, loss: 0.07535219192504883
2023-01-23 00:22:14.185049: step: 1284/530, loss: 0.21973657608032227
2023-01-23 00:22:15.279562: step: 1288/530, loss: 0.041379548609256744
2023-01-23 00:22:16.373325: step: 1292/530, loss: 0.5651895999908447
2023-01-23 00:22:17.463727: step: 1296/530, loss: 0.22133028507232666
2023-01-23 00:22:18.556729: step: 1300/530, loss: 0.12573829293251038
2023-01-23 00:22:19.656181: step: 1304/530, loss: 0.11169777810573578
2023-01-23 00:22:20.786345: step: 1308/530, loss: 0.1427953690290451
2023-01-23 00:22:21.899949: step: 1312/530, loss: 1.0593838691711426
2023-01-23 00:22:23.031118: step: 1316/530, loss: 0.11087790131568909
2023-01-23 00:22:24.149591: step: 1320/530, loss: 0.17237910628318787
2023-01-23 00:22:25.246922: step: 1324/530, loss: 0.053063295781612396
2023-01-23 00:22:26.362836: step: 1328/530, loss: 0.13668623566627502
2023-01-23 00:22:27.472020: step: 1332/530, loss: 0.18629369139671326
2023-01-23 00:22:28.590406: step: 1336/530, loss: 0.04998207092285156
2023-01-23 00:22:29.685390: step: 1340/530, loss: 0.20288018882274628
2023-01-23 00:22:30.779829: step: 1344/530, loss: 0.42380857467651367
2023-01-23 00:22:31.860129: step: 1348/530, loss: 0.07907561957836151
2023-01-23 00:22:32.994075: step: 1352/530, loss: 0.32152289152145386
2023-01-23 00:22:34.114798: step: 1356/530, loss: 0.28608816862106323
2023-01-23 00:22:35.237117: step: 1360/530, loss: 0.1774696409702301
2023-01-23 00:22:36.383883: step: 1364/530, loss: 0.06905193626880646
2023-01-23 00:22:37.537297: step: 1368/530, loss: 0.08710689097642899
2023-01-23 00:22:38.657748: step: 1372/530, loss: 0.10201006382703781
2023-01-23 00:22:39.775113: step: 1376/530, loss: 0.23266802728176117
2023-01-23 00:22:40.915408: step: 1380/530, loss: 0.1315208375453949
2023-01-23 00:22:42.026997: step: 1384/530, loss: 0.1771114468574524
2023-01-23 00:22:43.146542: step: 1388/530, loss: 0.07756300270557404
2023-01-23 00:22:44.250714: step: 1392/530, loss: 0.12887659668922424
2023-01-23 00:22:45.338215: step: 1396/530, loss: 0.008038520812988281
2023-01-23 00:22:46.453118: step: 1400/530, loss: 0.4961051046848297
2023-01-23 00:22:47.554193: step: 1404/530, loss: 0.03946692869067192
2023-01-23 00:22:48.668255: step: 1408/530, loss: 0.15088291466236115
2023-01-23 00:22:49.787962: step: 1412/530, loss: 0.16244849562644958
2023-01-23 00:22:50.924876: step: 1416/530, loss: 0.2840825915336609
2023-01-23 00:22:52.009061: step: 1420/530, loss: 0.4773137867450714
2023-01-23 00:22:53.095999: step: 1424/530, loss: 0.3524189889431
2023-01-23 00:22:54.205895: step: 1428/530, loss: 0.1570848524570465
2023-01-23 00:22:55.340829: step: 1432/530, loss: 0.21168726682662964
2023-01-23 00:22:56.431341: step: 1436/530, loss: 0.8024312853813171
2023-01-23 00:22:57.511231: step: 1440/530, loss: 0.2134825736284256
2023-01-23 00:22:58.599576: step: 1444/530, loss: 0.36764150857925415
2023-01-23 00:22:59.686718: step: 1448/530, loss: 0.22510509192943573
2023-01-23 00:23:00.799081: step: 1452/530, loss: 0.8723359107971191
2023-01-23 00:23:01.886789: step: 1456/530, loss: 0.133440300822258
2023-01-23 00:23:02.999880: step: 1460/530, loss: 0.05185108631849289
2023-01-23 00:23:04.147704: step: 1464/530, loss: 0.6737065315246582
2023-01-23 00:23:05.258885: step: 1468/530, loss: 0.4873160123825073
2023-01-23 00:23:06.350064: step: 1472/530, loss: 0.11334848403930664
2023-01-23 00:23:07.458994: step: 1476/530, loss: 0.11058960855007172
2023-01-23 00:23:08.565718: step: 1480/530, loss: 0.16094177961349487
2023-01-23 00:23:09.664866: step: 1484/530, loss: 0.5077104568481445
2023-01-23 00:23:10.769306: step: 1488/530, loss: 0.09440350532531738
2023-01-23 00:23:11.830290: step: 1492/530, loss: 0.18258939683437347
2023-01-23 00:23:12.938233: step: 1496/530, loss: 0.7942599058151245
2023-01-23 00:23:14.068699: step: 1500/530, loss: 0.4238957464694977
2023-01-23 00:23:15.170995: step: 1504/530, loss: 0.0418948158621788
2023-01-23 00:23:16.278121: step: 1508/530, loss: 0.27362021803855896
2023-01-23 00:23:17.365740: step: 1512/530, loss: 0.0397065170109272
2023-01-23 00:23:18.480227: step: 1516/530, loss: 0.6666883230209351
2023-01-23 00:23:19.577560: step: 1520/530, loss: 1.1499556303024292
2023-01-23 00:23:20.703753: step: 1524/530, loss: 0.15800829231739044
2023-01-23 00:23:21.818136: step: 1528/530, loss: 0.09731989353895187
2023-01-23 00:23:22.925234: step: 1532/530, loss: 0.10863862186670303
2023-01-23 00:23:24.041344: step: 1536/530, loss: 0.08315277099609375
2023-01-23 00:23:25.166228: step: 1540/530, loss: 0.05565300211310387
2023-01-23 00:23:26.258366: step: 1544/530, loss: 0.03651104122400284
2023-01-23 00:23:27.336245: step: 1548/530, loss: 0.038918305188417435
2023-01-23 00:23:28.452952: step: 1552/530, loss: 0.08883686363697052
2023-01-23 00:23:29.563996: step: 1556/530, loss: 0.7900556325912476
2023-01-23 00:23:30.668687: step: 1560/530, loss: 0.0810883566737175
2023-01-23 00:23:31.785121: step: 1564/530, loss: 0.27109137177467346
2023-01-23 00:23:32.887516: step: 1568/530, loss: 0.22881156206130981
2023-01-23 00:23:33.972198: step: 1572/530, loss: 0.1351308375597
2023-01-23 00:23:35.074562: step: 1576/530, loss: 0.13519592583179474
2023-01-23 00:23:36.169913: step: 1580/530, loss: 0.8639758229255676
2023-01-23 00:23:37.301817: step: 1584/530, loss: 0.22835516929626465
2023-01-23 00:23:38.428350: step: 1588/530, loss: 0.07148914039134979
2023-01-23 00:23:39.517351: step: 1592/530, loss: 0.027689125388860703
2023-01-23 00:23:40.631168: step: 1596/530, loss: 0.04994068294763565
2023-01-23 00:23:41.727916: step: 1600/530, loss: 0.321359246969223
2023-01-23 00:23:42.837516: step: 1604/530, loss: 0.10063913464546204
2023-01-23 00:23:43.952332: step: 1608/530, loss: 0.6468959450721741
2023-01-23 00:23:45.056639: step: 1612/530, loss: 0.1955525279045105
2023-01-23 00:23:46.188907: step: 1616/530, loss: 0.38106268644332886
2023-01-23 00:23:47.302374: step: 1620/530, loss: 0.20295333862304688
2023-01-23 00:23:48.413505: step: 1624/530, loss: 0.4059176445007324
2023-01-23 00:23:49.524117: step: 1628/530, loss: 0.4171333312988281
2023-01-23 00:23:50.623522: step: 1632/530, loss: 0.14496035873889923
2023-01-23 00:23:51.751442: step: 1636/530, loss: 0.30505600571632385
2023-01-23 00:23:52.863201: step: 1640/530, loss: 0.6908669471740723
2023-01-23 00:23:53.957106: step: 1644/530, loss: 0.25509196519851685
2023-01-23 00:23:55.045477: step: 1648/530, loss: 0.17221689224243164
2023-01-23 00:23:56.136914: step: 1652/530, loss: 0.06633615493774414
2023-01-23 00:23:57.237619: step: 1656/530, loss: 0.2502712309360504
2023-01-23 00:23:58.315676: step: 1660/530, loss: 0.8248711824417114
2023-01-23 00:23:59.410582: step: 1664/530, loss: 0.3465215265750885
2023-01-23 00:24:00.516447: step: 1668/530, loss: 0.08193397521972656
2023-01-23 00:24:01.625242: step: 1672/530, loss: 0.12040877342224121
2023-01-23 00:24:02.745496: step: 1676/530, loss: 0.35047677159309387
2023-01-23 00:24:03.869664: step: 1680/530, loss: 0.049019861966371536
2023-01-23 00:24:04.971589: step: 1684/530, loss: 0.05154692009091377
2023-01-23 00:24:06.091545: step: 1688/530, loss: 0.282259464263916
2023-01-23 00:24:07.199750: step: 1692/530, loss: 0.2670758366584778
2023-01-23 00:24:08.295370: step: 1696/530, loss: 0.0017387866973876953
2023-01-23 00:24:09.388679: step: 1700/530, loss: 0.011727381497621536
2023-01-23 00:24:10.493514: step: 1704/530, loss: 0.10878276824951172
2023-01-23 00:24:11.598425: step: 1708/530, loss: 0.2516377568244934
2023-01-23 00:24:12.712314: step: 1712/530, loss: 0.10581941902637482
2023-01-23 00:24:13.833930: step: 1716/530, loss: 0.9195899963378906
2023-01-23 00:24:14.972064: step: 1720/530, loss: 0.16059979796409607
2023-01-23 00:24:16.080510: step: 1724/530, loss: 0.09508000314235687
2023-01-23 00:24:17.190559: step: 1728/530, loss: 0.21087685227394104
2023-01-23 00:24:18.290266: step: 1732/530, loss: 0.055779457092285156
2023-01-23 00:24:19.413776: step: 1736/530, loss: 0.2426820695400238
2023-01-23 00:24:20.593821: step: 1740/530, loss: 0.1860208511352539
2023-01-23 00:24:21.692573: step: 1744/530, loss: 0.05705900490283966
2023-01-23 00:24:22.815261: step: 1748/530, loss: 0.36168450117111206
2023-01-23 00:24:23.931954: step: 1752/530, loss: 0.1211925595998764
2023-01-23 00:24:25.032021: step: 1756/530, loss: 0.03216152265667915
2023-01-23 00:24:26.150391: step: 1760/530, loss: 0.23562975227832794
2023-01-23 00:24:27.224095: step: 1764/530, loss: 1.104426622390747
2023-01-23 00:24:28.337819: step: 1768/530, loss: 0.25021687150001526
2023-01-23 00:24:29.447430: step: 1772/530, loss: 0.058877088129520416
2023-01-23 00:24:30.571360: step: 1776/530, loss: 0.4066980481147766
2023-01-23 00:24:31.644518: step: 1780/530, loss: 0.06185188516974449
2023-01-23 00:24:32.724895: step: 1784/530, loss: 0.08910875022411346
2023-01-23 00:24:33.859953: step: 1788/530, loss: 0.5735712051391602
2023-01-23 00:24:34.964937: step: 1792/530, loss: 0.18641769886016846
2023-01-23 00:24:36.080629: step: 1796/530, loss: 0.15713229775428772
2023-01-23 00:24:37.152464: step: 1800/530, loss: 0.049398139119148254
2023-01-23 00:24:38.259506: step: 1804/530, loss: 0.049103450030088425
2023-01-23 00:24:39.337287: step: 1808/530, loss: 0.15710654854774475
2023-01-23 00:24:40.434196: step: 1812/530, loss: 0.10331745445728302
2023-01-23 00:24:41.517082: step: 1816/530, loss: 0.21179240942001343
2023-01-23 00:24:42.637945: step: 1820/530, loss: 0.09028349071741104
2023-01-23 00:24:43.725789: step: 1824/530, loss: 0.21850453317165375
2023-01-23 00:24:44.858082: step: 1828/530, loss: 0.20966672897338867
2023-01-23 00:24:45.981815: step: 1832/530, loss: 0.7462459802627563
2023-01-23 00:24:47.077375: step: 1836/530, loss: 0.211009219288826
2023-01-23 00:24:48.200304: step: 1840/530, loss: 0.09029360115528107
2023-01-23 00:24:49.326896: step: 1844/530, loss: 0.1499272882938385
2023-01-23 00:24:50.444711: step: 1848/530, loss: 0.4164814054965973
2023-01-23 00:24:51.551262: step: 1852/530, loss: 0.10152693092823029
2023-01-23 00:24:52.654699: step: 1856/530, loss: 0.1695001721382141
2023-01-23 00:24:53.779710: step: 1860/530, loss: 0.1668999195098877
2023-01-23 00:24:54.891581: step: 1864/530, loss: 0.12263212352991104
2023-01-23 00:24:56.006536: step: 1868/530, loss: 0.07730965316295624
2023-01-23 00:24:57.108277: step: 1872/530, loss: 0.12123580276966095
2023-01-23 00:24:58.253670: step: 1876/530, loss: 0.1081201583147049
2023-01-23 00:24:59.377825: step: 1880/530, loss: 0.13940171897411346
2023-01-23 00:25:00.469255: step: 1884/530, loss: 0.4191620647907257
2023-01-23 00:25:01.549089: step: 1888/530, loss: 0.12703362107276917
2023-01-23 00:25:02.693864: step: 1892/530, loss: 0.4371488690376282
2023-01-23 00:25:03.790738: step: 1896/530, loss: 0.4159420132637024
2023-01-23 00:25:04.921118: step: 1900/530, loss: 0.2792503535747528
2023-01-23 00:25:06.038346: step: 1904/530, loss: 0.11866598576307297
2023-01-23 00:25:07.144693: step: 1908/530, loss: 0.19562062621116638
2023-01-23 00:25:08.256199: step: 1912/530, loss: 0.1899430751800537
2023-01-23 00:25:09.400741: step: 1916/530, loss: 0.043691232800483704
2023-01-23 00:25:10.494262: step: 1920/530, loss: 0.6341274976730347
2023-01-23 00:25:11.579208: step: 1924/530, loss: 0.6405299305915833
2023-01-23 00:25:12.685101: step: 1928/530, loss: 0.13126060366630554
2023-01-23 00:25:13.793623: step: 1932/530, loss: 0.19063836336135864
2023-01-23 00:25:14.894698: step: 1936/530, loss: 0.06951484829187393
2023-01-23 00:25:16.009337: step: 1940/530, loss: 0.08657412230968475
2023-01-23 00:25:17.121536: step: 1944/530, loss: 0.30267333984375
2023-01-23 00:25:18.234557: step: 1948/530, loss: 0.24932155013084412
2023-01-23 00:25:19.326985: step: 1952/530, loss: 0.09713473170995712
2023-01-23 00:25:20.433530: step: 1956/530, loss: 0.13251018524169922
2023-01-23 00:25:21.543644: step: 1960/530, loss: 0.13206633925437927
2023-01-23 00:25:22.622327: step: 1964/530, loss: 0.15397652983665466
2023-01-23 00:25:23.762966: step: 1968/530, loss: 0.04049701616168022
2023-01-23 00:25:24.868786: step: 1972/530, loss: 0.19873452186584473
2023-01-23 00:25:25.981408: step: 1976/530, loss: 0.14456096291542053
2023-01-23 00:25:27.046003: step: 1980/530, loss: 0.8957277536392212
2023-01-23 00:25:28.150469: step: 1984/530, loss: 0.06741056591272354
2023-01-23 00:25:29.288170: step: 1988/530, loss: 0.27179330587387085
2023-01-23 00:25:30.401250: step: 1992/530, loss: 0.9821248054504395
2023-01-23 00:25:31.513295: step: 1996/530, loss: 0.1198514923453331
2023-01-23 00:25:32.611934: step: 2000/530, loss: 0.3271741271018982
2023-01-23 00:25:33.728220: step: 2004/530, loss: 0.09060096740722656
2023-01-23 00:25:34.844453: step: 2008/530, loss: 0.08290982246398926
2023-01-23 00:25:35.933535: step: 2012/530, loss: 0.09377145767211914
2023-01-23 00:25:37.024095: step: 2016/530, loss: 0.4499048590660095
2023-01-23 00:25:38.132438: step: 2020/530, loss: 1.5151746273040771
2023-01-23 00:25:39.284884: step: 2024/530, loss: 0.35462790727615356
2023-01-23 00:25:40.394759: step: 2028/530, loss: 0.2617608904838562
2023-01-23 00:25:41.508093: step: 2032/530, loss: 0.1583174765110016
2023-01-23 00:25:42.645516: step: 2036/530, loss: 0.22380900382995605
2023-01-23 00:25:43.783823: step: 2040/530, loss: 0.15170994400978088
2023-01-23 00:25:44.906957: step: 2044/530, loss: 0.432948499917984
2023-01-23 00:25:46.028383: step: 2048/530, loss: 0.11401405930519104
2023-01-23 00:25:47.144808: step: 2052/530, loss: 0.08476801216602325
2023-01-23 00:25:48.240665: step: 2056/530, loss: 0.3172012269496918
2023-01-23 00:25:49.372330: step: 2060/530, loss: 0.11792431771755219
2023-01-23 00:25:50.474073: step: 2064/530, loss: 0.28767237067222595
2023-01-23 00:25:51.587679: step: 2068/530, loss: 0.06708383560180664
2023-01-23 00:25:52.705165: step: 2072/530, loss: 7.337092399597168
2023-01-23 00:25:53.838198: step: 2076/530, loss: 0.1366681158542633
2023-01-23 00:25:54.929954: step: 2080/530, loss: 0.10032234340906143
2023-01-23 00:25:56.075583: step: 2084/530, loss: 0.09884100407361984
2023-01-23 00:25:57.203348: step: 2088/530, loss: 0.1326029747724533
2023-01-23 00:25:58.327761: step: 2092/530, loss: 0.24804915487766266
2023-01-23 00:25:59.453806: step: 2096/530, loss: 0.10813150554895401
2023-01-23 00:26:00.558660: step: 2100/530, loss: 0.13777141273021698
2023-01-23 00:26:01.704222: step: 2104/530, loss: 0.08997378498315811
2023-01-23 00:26:02.822306: step: 2108/530, loss: 0.09419694542884827
2023-01-23 00:26:03.944218: step: 2112/530, loss: 0.5178403258323669
2023-01-23 00:26:05.043844: step: 2116/530, loss: 0.3488030433654785
2023-01-23 00:26:06.126377: step: 2120/530, loss: 0.10376934707164764
==================================================
Loss: 0.253
--------------------
Dev: {'event': {'p': 0.5708622398414271, 'r': 0.7669773635153129, 'f1': 0.6545454545454545}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Test: {'event': {'p': 0.6044052863436123, 'r': 0.7995337995337995, 'f1': 0.6884094330155545}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Chinese: {'event': {'p': 0.6578947368421053, 'r': 0.9259259259259259, 'f1': 0.7692307692307692}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Korean: {'event': {'p': 0.6470588235294118, 'r': 0.5238095238095238, 'f1': 0.5789473684210527}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Russian: {'event': {'p': 0.391304347826087, 'r': 0.5, 'f1': 0.4390243902439025}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
New best chinese model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.5708622398414271, 'r': 0.7669773635153129, 'f1': 0.6545454545454545}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Eng Test for Chinese: {'event': {'p': 0.6044052863436123, 'r': 0.7995337995337995, 'f1': 0.6884094330155545}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Sample Chinese: {'event': {'p': 0.6578947368421053, 'r': 0.9259259259259259, 'f1': 0.7692307692307692}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6218961625282167, 'r': 0.7336884154460719, 'f1': 0.6731826511912034}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Eng Test for Korean: {'event': {'p': 0.6148681055155876, 'r': 0.747086247086247, 'f1': 0.6745593264930282}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Sample Korean: {'event': {'p': 0.7631578947368421, 'r': 0.4603174603174603, 'f1': 0.5742574257425742}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5862457722660653, 'r': 0.6924101198402131, 'f1': 0.634920634920635}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Eng Test for Russian: {'event': {'p': 0.5994652406417113, 'r': 0.6532634032634033, 'f1': 0.6252091466815394}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Sample Russian: {'event': {'p': 0.625, 'r': 0.4166666666666667, 'f1': 0.5}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
******************************
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 00:26:51.590593: step: 4/530, loss: 0.1412806510925293
2023-01-23 00:26:52.689980: step: 8/530, loss: 0.06201524659991264
2023-01-23 00:26:53.782167: step: 12/530, loss: 0.06677856296300888
2023-01-23 00:26:54.881442: step: 16/530, loss: 0.16642045974731445
2023-01-23 00:26:55.970156: step: 20/530, loss: 0.0463135726749897
2023-01-23 00:26:57.052008: step: 24/530, loss: 0.12257456034421921
2023-01-23 00:26:58.163191: step: 28/530, loss: 0.05361614376306534
2023-01-23 00:26:59.250272: step: 32/530, loss: 0.10993947833776474
2023-01-23 00:27:00.359850: step: 36/530, loss: 0.05338134616613388
2023-01-23 00:27:01.443295: step: 40/530, loss: 0.05153698846697807
2023-01-23 00:27:02.548984: step: 44/530, loss: 0.154712975025177
2023-01-23 00:27:03.656725: step: 48/530, loss: 0.498554527759552
2023-01-23 00:27:04.759018: step: 52/530, loss: 1.0199856758117676
2023-01-23 00:27:05.870130: step: 56/530, loss: 0.0324769988656044
2023-01-23 00:27:06.963192: step: 60/530, loss: 0.0748293399810791
2023-01-23 00:27:08.082371: step: 64/530, loss: 0.21995745599269867
2023-01-23 00:27:09.217121: step: 68/530, loss: 0.1282590925693512
2023-01-23 00:27:10.328386: step: 72/530, loss: 0.10734911262989044
2023-01-23 00:27:11.433204: step: 76/530, loss: 0.22396288812160492
2023-01-23 00:27:12.546618: step: 80/530, loss: 0.07477708160877228
2023-01-23 00:27:13.620008: step: 84/530, loss: 0.03555621951818466
2023-01-23 00:27:14.714470: step: 88/530, loss: 0.23825010657310486
2023-01-23 00:27:15.839384: step: 92/530, loss: 0.30513685941696167
2023-01-23 00:27:16.926098: step: 96/530, loss: 0.051180649548769
2023-01-23 00:27:18.013026: step: 100/530, loss: 0.058794356882572174
2023-01-23 00:27:19.109269: step: 104/530, loss: 0.031160736456513405
2023-01-23 00:27:20.211824: step: 108/530, loss: 0.12346458435058594
2023-01-23 00:27:21.343215: step: 112/530, loss: 0.08231782913208008
2023-01-23 00:27:22.493244: step: 116/530, loss: 0.16058455407619476
2023-01-23 00:27:23.607810: step: 120/530, loss: 0.16344527900218964
2023-01-23 00:27:24.715173: step: 124/530, loss: 0.09799690544605255
2023-01-23 00:27:25.828582: step: 128/530, loss: 0.018441438674926758
2023-01-23 00:27:26.933075: step: 132/530, loss: 0.19248907268047333
2023-01-23 00:27:28.052075: step: 136/530, loss: 0.260833740234375
2023-01-23 00:27:29.150785: step: 140/530, loss: 0.24858427047729492
2023-01-23 00:27:30.239064: step: 144/530, loss: 0.05825462564826012
2023-01-23 00:27:31.327915: step: 148/530, loss: 0.03804969787597656
2023-01-23 00:27:32.429886: step: 152/530, loss: 0.11118941754102707
2023-01-23 00:27:33.522354: step: 156/530, loss: 0.060916900634765625
2023-01-23 00:27:34.602310: step: 160/530, loss: 0.06108136102557182
2023-01-23 00:27:35.723586: step: 164/530, loss: 0.1704285740852356
2023-01-23 00:27:36.797965: step: 168/530, loss: 0.08091020584106445
2023-01-23 00:27:37.911656: step: 172/530, loss: 0.09379314631223679
2023-01-23 00:27:39.064954: step: 176/530, loss: 0.16600283980369568
2023-01-23 00:27:40.156435: step: 180/530, loss: 0.03681764751672745
2023-01-23 00:27:41.289000: step: 184/530, loss: 0.07739467918872833
2023-01-23 00:27:42.402573: step: 188/530, loss: 0.03204236179590225
2023-01-23 00:27:43.511282: step: 192/530, loss: 0.4384584426879883
2023-01-23 00:27:44.616655: step: 196/530, loss: 0.082837775349617
2023-01-23 00:27:45.719075: step: 200/530, loss: 0.16306428611278534
2023-01-23 00:27:46.846518: step: 204/530, loss: 0.12127232551574707
2023-01-23 00:27:47.938353: step: 208/530, loss: 0.050431132316589355
2023-01-23 00:27:49.027830: step: 212/530, loss: 0.2567879855632782
2023-01-23 00:27:50.148920: step: 216/530, loss: 0.16017284989356995
2023-01-23 00:27:51.293849: step: 220/530, loss: 0.16926231980323792
2023-01-23 00:27:52.405173: step: 224/530, loss: 0.08518343418836594
2023-01-23 00:27:53.512907: step: 228/530, loss: 0.12667135894298553
2023-01-23 00:27:54.638793: step: 232/530, loss: 0.13655593991279602
2023-01-23 00:27:55.757409: step: 236/530, loss: 0.39121952652931213
2023-01-23 00:27:56.877787: step: 240/530, loss: 0.4892156720161438
2023-01-23 00:27:58.017103: step: 244/530, loss: 0.19624634087085724
2023-01-23 00:27:59.135563: step: 248/530, loss: 0.04846344143152237
2023-01-23 00:28:00.250343: step: 252/530, loss: 0.1293279528617859
2023-01-23 00:28:01.341913: step: 256/530, loss: 0.023111533373594284
2023-01-23 00:28:02.472650: step: 260/530, loss: 0.2309425324201584
2023-01-23 00:28:03.581265: step: 264/530, loss: 0.39034825563430786
2023-01-23 00:28:04.694296: step: 268/530, loss: 0.040932752192020416
2023-01-23 00:28:05.776143: step: 272/530, loss: 0.10498218238353729
2023-01-23 00:28:06.879141: step: 276/530, loss: 0.04104342311620712
2023-01-23 00:28:07.972278: step: 280/530, loss: 0.13160772621631622
2023-01-23 00:28:09.109757: step: 284/530, loss: 0.04770074039697647
2023-01-23 00:28:10.217314: step: 288/530, loss: 0.05871248245239258
2023-01-23 00:28:11.310754: step: 292/530, loss: 0.08321800827980042
2023-01-23 00:28:12.403687: step: 296/530, loss: 0.3971864581108093
2023-01-23 00:28:13.497456: step: 300/530, loss: 0.15843066573143005
2023-01-23 00:28:14.588941: step: 304/530, loss: 0.05259087309241295
2023-01-23 00:28:15.692734: step: 308/530, loss: 0.11440610885620117
2023-01-23 00:28:16.808011: step: 312/530, loss: 0.0426514632999897
2023-01-23 00:28:17.900483: step: 316/530, loss: 0.07652168720960617
2023-01-23 00:28:19.004684: step: 320/530, loss: 0.04016528278589249
2023-01-23 00:28:20.140144: step: 324/530, loss: 0.06114664301276207
2023-01-23 00:28:21.286333: step: 328/530, loss: 0.059960126876831055
2023-01-23 00:28:22.412666: step: 332/530, loss: 0.06624917685985565
2023-01-23 00:28:23.512612: step: 336/530, loss: 0.07056713104248047
2023-01-23 00:28:24.622453: step: 340/530, loss: 0.20618152618408203
2023-01-23 00:28:25.780104: step: 344/530, loss: 0.28959882259368896
2023-01-23 00:28:26.878120: step: 348/530, loss: 0.13309133052825928
2023-01-23 00:28:28.012013: step: 352/530, loss: 0.03675325959920883
2023-01-23 00:28:29.100910: step: 356/530, loss: 0.10258965194225311
2023-01-23 00:28:30.242340: step: 360/530, loss: 0.17018049955368042
2023-01-23 00:28:31.388233: step: 364/530, loss: 0.1614781618118286
2023-01-23 00:28:32.514101: step: 368/530, loss: 0.49032869935035706
2023-01-23 00:28:33.623149: step: 372/530, loss: 0.06695500016212463
2023-01-23 00:28:34.733929: step: 376/530, loss: 0.37270721793174744
2023-01-23 00:28:35.842820: step: 380/530, loss: 0.05695495754480362
2023-01-23 00:28:36.957878: step: 384/530, loss: 0.11721185594797134
2023-01-23 00:28:38.051163: step: 388/530, loss: 0.06376629322767258
2023-01-23 00:28:39.173325: step: 392/530, loss: 0.10203037410974503
2023-01-23 00:28:40.282254: step: 396/530, loss: 0.14311876893043518
2023-01-23 00:28:41.404846: step: 400/530, loss: 0.14815779030323029
2023-01-23 00:28:42.529097: step: 404/530, loss: 0.8976076245307922
2023-01-23 00:28:43.600422: step: 408/530, loss: 0.049604419618844986
2023-01-23 00:28:44.714493: step: 412/530, loss: 0.05662555992603302
2023-01-23 00:28:45.836499: step: 416/530, loss: 0.07676362991333008
2023-01-23 00:28:46.935764: step: 420/530, loss: 0.05551471561193466
2023-01-23 00:28:48.055915: step: 424/530, loss: 0.1177053451538086
2023-01-23 00:28:49.158088: step: 428/530, loss: 0.14917390048503876
2023-01-23 00:28:50.316862: step: 432/530, loss: 0.07037587463855743
2023-01-23 00:28:51.397111: step: 436/530, loss: 0.2415897399187088
2023-01-23 00:28:52.539863: step: 440/530, loss: 0.7074052691459656
2023-01-23 00:28:53.662637: step: 444/530, loss: 0.1987031102180481
2023-01-23 00:28:54.773410: step: 448/530, loss: 0.13592669367790222
2023-01-23 00:28:55.864615: step: 452/530, loss: 0.07063045352697372
2023-01-23 00:28:56.945579: step: 456/530, loss: 0.05031852796673775
2023-01-23 00:28:58.105184: step: 460/530, loss: 0.13677817583084106
2023-01-23 00:28:59.211955: step: 464/530, loss: 0.2800731658935547
2023-01-23 00:29:00.319053: step: 468/530, loss: 0.11101584136486053
2023-01-23 00:29:01.401083: step: 472/530, loss: 0.2019510269165039
2023-01-23 00:29:02.529560: step: 476/530, loss: 0.1960899829864502
2023-01-23 00:29:03.657649: step: 480/530, loss: 0.040073491632938385
2023-01-23 00:29:04.771445: step: 484/530, loss: 0.2950019836425781
2023-01-23 00:29:05.892558: step: 488/530, loss: 0.10425710678100586
2023-01-23 00:29:07.007099: step: 492/530, loss: 0.21908989548683167
2023-01-23 00:29:08.142162: step: 496/530, loss: 0.07490558922290802
2023-01-23 00:29:09.240576: step: 500/530, loss: 0.22998161613941193
2023-01-23 00:29:10.352652: step: 504/530, loss: 0.004678630735725164
2023-01-23 00:29:11.450158: step: 508/530, loss: 0.19590897858142853
2023-01-23 00:29:12.580908: step: 512/530, loss: 0.0851888656616211
2023-01-23 00:29:13.671898: step: 516/530, loss: 0.0888313353061676
2023-01-23 00:29:14.825570: step: 520/530, loss: 0.12855833768844604
2023-01-23 00:29:15.939851: step: 524/530, loss: 0.3092435896396637
2023-01-23 00:29:17.032129: step: 528/530, loss: 0.08574266731739044
2023-01-23 00:29:18.167427: step: 532/530, loss: 0.08121633529663086
2023-01-23 00:29:19.275830: step: 536/530, loss: 0.0470576286315918
2023-01-23 00:29:20.356983: step: 540/530, loss: 0.05300460010766983
2023-01-23 00:29:21.486762: step: 544/530, loss: 0.05453081056475639
2023-01-23 00:29:22.582124: step: 548/530, loss: 0.08517379313707352
2023-01-23 00:29:23.677430: step: 552/530, loss: 0.07322397083044052
2023-01-23 00:29:24.785117: step: 556/530, loss: 0.04077902063727379
2023-01-23 00:29:25.897397: step: 560/530, loss: 0.019483327865600586
2023-01-23 00:29:27.012495: step: 564/530, loss: 0.4246101379394531
2023-01-23 00:29:28.116004: step: 568/530, loss: 1.004377007484436
2023-01-23 00:29:29.212651: step: 572/530, loss: 0.09844322502613068
2023-01-23 00:29:30.331169: step: 576/530, loss: 0.35216182470321655
2023-01-23 00:29:31.424447: step: 580/530, loss: 0.05642843618988991
2023-01-23 00:29:32.546124: step: 584/530, loss: 0.19548234343528748
2023-01-23 00:29:33.652057: step: 588/530, loss: 0.26619473099708557
2023-01-23 00:29:34.796669: step: 592/530, loss: 0.01701502874493599
2023-01-23 00:29:35.925393: step: 596/530, loss: 0.10624275356531143
2023-01-23 00:29:37.052272: step: 600/530, loss: 0.5641342401504517
2023-01-23 00:29:38.184435: step: 604/530, loss: 0.07854967564344406
2023-01-23 00:29:39.303564: step: 608/530, loss: 0.13105639815330505
2023-01-23 00:29:40.432992: step: 612/530, loss: 0.10545094311237335
2023-01-23 00:29:41.524532: step: 616/530, loss: 0.17296594381332397
2023-01-23 00:29:42.642953: step: 620/530, loss: 4.8435893058776855
2023-01-23 00:29:43.733796: step: 624/530, loss: 0.08275661617517471
2023-01-23 00:29:44.890003: step: 628/530, loss: 0.06939706206321716
2023-01-23 00:29:45.977983: step: 632/530, loss: 0.16816312074661255
2023-01-23 00:29:47.103749: step: 636/530, loss: 0.20705966651439667
2023-01-23 00:29:48.213518: step: 640/530, loss: 0.0594182014465332
2023-01-23 00:29:49.305363: step: 644/530, loss: 0.28857794404029846
2023-01-23 00:29:50.427871: step: 648/530, loss: 0.21053582429885864
2023-01-23 00:29:51.537812: step: 652/530, loss: 0.7438284158706665
2023-01-23 00:29:52.637605: step: 656/530, loss: 0.18033218383789062
2023-01-23 00:29:53.728733: step: 660/530, loss: 0.27255547046661377
2023-01-23 00:29:54.844091: step: 664/530, loss: 0.1447506546974182
2023-01-23 00:29:55.946749: step: 668/530, loss: 0.6236919164657593
2023-01-23 00:29:57.051431: step: 672/530, loss: 0.18955735862255096
2023-01-23 00:29:58.151544: step: 676/530, loss: 0.9992786645889282
2023-01-23 00:29:59.250329: step: 680/530, loss: 0.12059192359447479
2023-01-23 00:30:00.330991: step: 684/530, loss: 0.16654592752456665
2023-01-23 00:30:01.427211: step: 688/530, loss: 0.040083982050418854
2023-01-23 00:30:02.525406: step: 692/530, loss: 0.3588658571243286
2023-01-23 00:30:03.649278: step: 696/530, loss: 0.12521058320999146
2023-01-23 00:30:04.753559: step: 700/530, loss: 0.13614550232887268
2023-01-23 00:30:05.850826: step: 704/530, loss: 0.1731891632080078
2023-01-23 00:30:06.963244: step: 708/530, loss: 0.10172943770885468
2023-01-23 00:30:08.119844: step: 712/530, loss: 0.14219379425048828
2023-01-23 00:30:09.209002: step: 716/530, loss: 0.07694966346025467
2023-01-23 00:30:10.360510: step: 720/530, loss: 1.7732086181640625
2023-01-23 00:30:11.473837: step: 724/530, loss: 0.14430752396583557
2023-01-23 00:30:12.578347: step: 728/530, loss: 0.07118859887123108
2023-01-23 00:30:13.701487: step: 732/530, loss: 0.05580034479498863
2023-01-23 00:30:14.832554: step: 736/530, loss: 0.27044758200645447
2023-01-23 00:30:15.940699: step: 740/530, loss: 0.04577532038092613
2023-01-23 00:30:17.041039: step: 744/530, loss: 0.06258101761341095
2023-01-23 00:30:18.141596: step: 748/530, loss: 0.24775853753089905
2023-01-23 00:30:19.232658: step: 752/530, loss: 0.11392946541309357
2023-01-23 00:30:20.334142: step: 756/530, loss: 0.08901243656873703
2023-01-23 00:30:21.476838: step: 760/530, loss: 0.057595159858465195
2023-01-23 00:30:22.571800: step: 764/530, loss: 0.44379279017448425
2023-01-23 00:30:23.700049: step: 768/530, loss: 0.3000926971435547
2023-01-23 00:30:24.810121: step: 772/530, loss: 0.36787793040275574
2023-01-23 00:30:25.924216: step: 776/530, loss: 0.04904355853796005
2023-01-23 00:30:27.031336: step: 780/530, loss: 0.6074905395507812
2023-01-23 00:30:28.123487: step: 784/530, loss: 0.013667488470673561
2023-01-23 00:30:29.245317: step: 788/530, loss: 0.1963481903076172
2023-01-23 00:30:30.343046: step: 792/530, loss: 0.07738657295703888
2023-01-23 00:30:31.475555: step: 796/530, loss: 0.21989822387695312
2023-01-23 00:30:32.580967: step: 800/530, loss: 0.08679161220788956
2023-01-23 00:30:33.697621: step: 804/530, loss: 0.1227174773812294
2023-01-23 00:30:34.830209: step: 808/530, loss: 0.23414096236228943
2023-01-23 00:30:35.942155: step: 812/530, loss: 0.08174066245555878
2023-01-23 00:30:37.048847: step: 816/530, loss: 0.20460662245750427
2023-01-23 00:30:38.175237: step: 820/530, loss: 0.07549504935741425
2023-01-23 00:30:39.303214: step: 824/530, loss: 0.23754271864891052
2023-01-23 00:30:40.417619: step: 828/530, loss: 0.3883371353149414
2023-01-23 00:30:41.553240: step: 832/530, loss: 0.07773430645465851
2023-01-23 00:30:42.653977: step: 836/530, loss: 0.15171414613723755
2023-01-23 00:30:43.738756: step: 840/530, loss: 0.06627267599105835
2023-01-23 00:30:44.869726: step: 844/530, loss: 0.22590437531471252
2023-01-23 00:30:45.955592: step: 848/530, loss: 0.16169938445091248
2023-01-23 00:30:47.066573: step: 852/530, loss: 2.1008481979370117
2023-01-23 00:30:48.155712: step: 856/530, loss: 0.21117496490478516
2023-01-23 00:30:49.286613: step: 860/530, loss: 0.09196414798498154
2023-01-23 00:30:50.383580: step: 864/530, loss: 0.11832189559936523
2023-01-23 00:30:51.483057: step: 868/530, loss: 0.07642853260040283
2023-01-23 00:30:52.578457: step: 872/530, loss: 2.9095101356506348
2023-01-23 00:30:53.670334: step: 876/530, loss: 0.022319747135043144
2023-01-23 00:30:54.787266: step: 880/530, loss: 0.15028639137744904
2023-01-23 00:30:55.898988: step: 884/530, loss: 0.09087555855512619
2023-01-23 00:30:57.006576: step: 888/530, loss: 1.0790647268295288
2023-01-23 00:30:58.103651: step: 892/530, loss: 1.3735277652740479
2023-01-23 00:30:59.197289: step: 896/530, loss: 0.16378679871559143
2023-01-23 00:31:00.291563: step: 900/530, loss: 0.09727010875940323
2023-01-23 00:31:01.415537: step: 904/530, loss: 0.933566153049469
2023-01-23 00:31:02.536787: step: 908/530, loss: 0.15558242797851562
2023-01-23 00:31:03.627317: step: 912/530, loss: 0.19154386222362518
2023-01-23 00:31:04.746565: step: 916/530, loss: 0.40183225274086
2023-01-23 00:31:05.850408: step: 920/530, loss: 0.07803884893655777
2023-01-23 00:31:06.963984: step: 924/530, loss: 0.17959412932395935
2023-01-23 00:31:08.075231: step: 928/530, loss: 0.11197566986083984
2023-01-23 00:31:09.184590: step: 932/530, loss: 0.29285290837287903
2023-01-23 00:31:10.306055: step: 936/530, loss: 0.07945018261671066
2023-01-23 00:31:11.397607: step: 940/530, loss: 0.07374639809131622
2023-01-23 00:31:12.525764: step: 944/530, loss: 0.2392738312482834
2023-01-23 00:31:13.651125: step: 948/530, loss: 0.13567790389060974
2023-01-23 00:31:14.742237: step: 952/530, loss: 0.08202478289604187
2023-01-23 00:31:15.839626: step: 956/530, loss: 0.31894809007644653
2023-01-23 00:31:16.950540: step: 960/530, loss: 0.1318780928850174
2023-01-23 00:31:18.085628: step: 964/530, loss: 0.06217651441693306
2023-01-23 00:31:19.170489: step: 968/530, loss: 0.01972179487347603
2023-01-23 00:31:20.295492: step: 972/530, loss: 0.08963070064783096
2023-01-23 00:31:21.405214: step: 976/530, loss: 0.12298707664012909
2023-01-23 00:31:22.518278: step: 980/530, loss: 0.10794582217931747
2023-01-23 00:31:23.596382: step: 984/530, loss: 0.03538684919476509
2023-01-23 00:31:24.677272: step: 988/530, loss: 0.09443295001983643
2023-01-23 00:31:25.789620: step: 992/530, loss: 0.11618609726428986
2023-01-23 00:31:26.879916: step: 996/530, loss: 0.08606138825416565
2023-01-23 00:31:27.977649: step: 1000/530, loss: 0.1393057256937027
2023-01-23 00:31:29.117857: step: 1004/530, loss: 0.5516961216926575
2023-01-23 00:31:30.271522: step: 1008/530, loss: 0.06300678104162216
2023-01-23 00:31:31.393013: step: 1012/530, loss: 0.3385885953903198
2023-01-23 00:31:32.556546: step: 1016/530, loss: 0.15946274995803833
2023-01-23 00:31:33.689982: step: 1020/530, loss: 0.8286330103874207
2023-01-23 00:31:34.799383: step: 1024/530, loss: 0.06464748084545135
2023-01-23 00:31:35.922304: step: 1028/530, loss: 0.07358107715845108
2023-01-23 00:31:37.031393: step: 1032/530, loss: 0.5551338195800781
2023-01-23 00:31:38.151899: step: 1036/530, loss: 0.15530119836330414
2023-01-23 00:31:39.275685: step: 1040/530, loss: 0.11508283764123917
2023-01-23 00:31:40.384172: step: 1044/530, loss: 0.10041675716638565
2023-01-23 00:31:41.487484: step: 1048/530, loss: 0.044777631759643555
2023-01-23 00:31:42.608043: step: 1052/530, loss: 0.17852826416492462
2023-01-23 00:31:43.738683: step: 1056/530, loss: 0.07283420860767365
2023-01-23 00:31:44.841214: step: 1060/530, loss: 0.02753610722720623
2023-01-23 00:31:45.941959: step: 1064/530, loss: 0.06696224212646484
2023-01-23 00:31:47.046518: step: 1068/530, loss: 0.17500095069408417
2023-01-23 00:31:48.139306: step: 1072/530, loss: 0.05576524883508682
2023-01-23 00:31:49.204755: step: 1076/530, loss: 0.04979858547449112
2023-01-23 00:31:50.304386: step: 1080/530, loss: 0.017035987228155136
2023-01-23 00:31:51.393481: step: 1084/530, loss: 0.03942747041583061
2023-01-23 00:31:52.476823: step: 1088/530, loss: 0.21578015387058258
2023-01-23 00:31:53.582851: step: 1092/530, loss: 0.13594646751880646
2023-01-23 00:31:54.685138: step: 1096/530, loss: 0.4431777894496918
2023-01-23 00:31:55.779930: step: 1100/530, loss: 0.09824438393115997
2023-01-23 00:31:56.906581: step: 1104/530, loss: 0.43484944105148315
2023-01-23 00:31:58.010264: step: 1108/530, loss: 0.1600465327501297
2023-01-23 00:31:59.103236: step: 1112/530, loss: 0.48954397439956665
2023-01-23 00:32:00.202216: step: 1116/530, loss: 0.12431621551513672
2023-01-23 00:32:01.265528: step: 1120/530, loss: 0.05503235012292862
2023-01-23 00:32:02.371406: step: 1124/530, loss: 0.04081964120268822
2023-01-23 00:32:03.521160: step: 1128/530, loss: 0.008269404992461205
2023-01-23 00:32:04.671122: step: 1132/530, loss: 0.2670232653617859
2023-01-23 00:32:05.785628: step: 1136/530, loss: 0.012583445757627487
2023-01-23 00:32:06.891983: step: 1140/530, loss: 0.03821849822998047
2023-01-23 00:32:08.031390: step: 1144/530, loss: 6.483943462371826
2023-01-23 00:32:09.137899: step: 1148/530, loss: 0.2951178550720215
2023-01-23 00:32:10.240321: step: 1152/530, loss: 0.1675799936056137
2023-01-23 00:32:11.376936: step: 1156/530, loss: 0.061385251581668854
2023-01-23 00:32:12.471995: step: 1160/530, loss: 0.05628480762243271
2023-01-23 00:32:13.618565: step: 1164/530, loss: 0.617857813835144
2023-01-23 00:32:14.723333: step: 1168/530, loss: 0.09353180229663849
2023-01-23 00:32:15.847523: step: 1172/530, loss: 0.1562778353691101
2023-01-23 00:32:16.996670: step: 1176/530, loss: 0.4430685043334961
2023-01-23 00:32:18.120783: step: 1180/530, loss: 0.03023557737469673
2023-01-23 00:32:19.202667: step: 1184/530, loss: 0.15332813560962677
2023-01-23 00:32:20.271612: step: 1188/530, loss: 0.14318440854549408
2023-01-23 00:32:21.354263: step: 1192/530, loss: 0.0890265554189682
2023-01-23 00:32:22.466712: step: 1196/530, loss: 0.02219982072710991
2023-01-23 00:32:23.548589: step: 1200/530, loss: 0.05496816709637642
2023-01-23 00:32:24.631564: step: 1204/530, loss: 0.0460217148065567
2023-01-23 00:32:25.715815: step: 1208/530, loss: 0.06803536415100098
2023-01-23 00:32:26.851886: step: 1212/530, loss: 0.021628262475132942
2023-01-23 00:32:27.951688: step: 1216/530, loss: 0.142535999417305
2023-01-23 00:32:29.047034: step: 1220/530, loss: 0.03314189985394478
2023-01-23 00:32:30.133408: step: 1224/530, loss: 0.04489879682660103
2023-01-23 00:32:31.216398: step: 1228/530, loss: 0.03569202497601509
2023-01-23 00:32:32.324440: step: 1232/530, loss: 0.2565673887729645
2023-01-23 00:32:33.465214: step: 1236/530, loss: 0.19846734404563904
2023-01-23 00:32:34.600969: step: 1240/530, loss: 0.1411205381155014
2023-01-23 00:32:35.701271: step: 1244/530, loss: 0.16838568449020386
2023-01-23 00:32:36.805779: step: 1248/530, loss: 0.1854853630065918
2023-01-23 00:32:37.916892: step: 1252/530, loss: 0.014490032568573952
2023-01-23 00:32:39.021307: step: 1256/530, loss: 0.31826668977737427
2023-01-23 00:32:40.105915: step: 1260/530, loss: 0.007297801785171032
2023-01-23 00:32:41.211704: step: 1264/530, loss: 0.06495866924524307
2023-01-23 00:32:42.310894: step: 1268/530, loss: 0.07826481759548187
2023-01-23 00:32:43.431352: step: 1272/530, loss: 0.12443426251411438
2023-01-23 00:32:44.563709: step: 1276/530, loss: 0.05956573411822319
2023-01-23 00:32:45.637411: step: 1280/530, loss: 0.24829530715942383
2023-01-23 00:32:46.751248: step: 1284/530, loss: 0.17577160894870758
2023-01-23 00:32:47.858640: step: 1288/530, loss: 0.012757587246596813
2023-01-23 00:32:48.947006: step: 1292/530, loss: 0.07738790661096573
2023-01-23 00:32:50.052893: step: 1296/530, loss: 0.058518197387456894
2023-01-23 00:32:51.175498: step: 1300/530, loss: 0.04795525223016739
2023-01-23 00:32:52.287792: step: 1304/530, loss: 0.10983534157276154
2023-01-23 00:32:53.373792: step: 1308/530, loss: 0.22822479903697968
2023-01-23 00:32:54.476385: step: 1312/530, loss: 0.0834013968706131
2023-01-23 00:32:55.574421: step: 1316/530, loss: 0.23015937209129333
2023-01-23 00:32:56.666182: step: 1320/530, loss: 0.35937219858169556
2023-01-23 00:32:57.774632: step: 1324/530, loss: 0.15581531822681427
2023-01-23 00:32:58.870000: step: 1328/530, loss: 0.019521618261933327
2023-01-23 00:32:59.964690: step: 1332/530, loss: 0.10836992412805557
2023-01-23 00:33:01.090004: step: 1336/530, loss: 0.20116910338401794
2023-01-23 00:33:02.156954: step: 1340/530, loss: 0.08201270550489426
2023-01-23 00:33:03.294874: step: 1344/530, loss: 0.6198492050170898
2023-01-23 00:33:04.440522: step: 1348/530, loss: 0.06343241035938263
2023-01-23 00:33:05.548996: step: 1352/530, loss: 0.08712625503540039
2023-01-23 00:33:06.643574: step: 1356/530, loss: 0.08887386322021484
2023-01-23 00:33:07.765092: step: 1360/530, loss: 0.23552294075489044
2023-01-23 00:33:08.870909: step: 1364/530, loss: 0.13663749396800995
2023-01-23 00:33:09.957134: step: 1368/530, loss: 0.11390657722949982
2023-01-23 00:33:11.078988: step: 1372/530, loss: 0.06561855971813202
2023-01-23 00:33:12.187483: step: 1376/530, loss: 0.02843928337097168
2023-01-23 00:33:13.292997: step: 1380/530, loss: 0.18968945741653442
2023-01-23 00:33:14.425037: step: 1384/530, loss: 0.3278907835483551
2023-01-23 00:33:15.553921: step: 1388/530, loss: 0.14762306213378906
2023-01-23 00:33:16.660533: step: 1392/530, loss: 0.03297996520996094
2023-01-23 00:33:17.776373: step: 1396/530, loss: 0.16599509119987488
2023-01-23 00:33:18.899308: step: 1400/530, loss: 0.05211487039923668
2023-01-23 00:33:19.993481: step: 1404/530, loss: 0.03898029401898384
2023-01-23 00:33:21.118594: step: 1408/530, loss: 0.3107908368110657
2023-01-23 00:33:22.247868: step: 1412/530, loss: 0.08039645850658417
2023-01-23 00:33:23.363457: step: 1416/530, loss: 0.24170580506324768
2023-01-23 00:33:24.475936: step: 1420/530, loss: 0.5683291554450989
2023-01-23 00:33:25.576333: step: 1424/530, loss: 0.21980924904346466
2023-01-23 00:33:26.674981: step: 1428/530, loss: 0.2698204815387726
2023-01-23 00:33:27.789014: step: 1432/530, loss: 0.038778066635131836
2023-01-23 00:33:28.910612: step: 1436/530, loss: 0.015592003241181374
2023-01-23 00:33:30.031733: step: 1440/530, loss: 0.07093267142772675
2023-01-23 00:33:31.133384: step: 1444/530, loss: 0.11247185617685318
2023-01-23 00:33:32.226874: step: 1448/530, loss: 0.0854862630367279
2023-01-23 00:33:33.352667: step: 1452/530, loss: 0.19423389434814453
2023-01-23 00:33:34.477827: step: 1456/530, loss: 0.4856361448764801
2023-01-23 00:33:35.612035: step: 1460/530, loss: 0.13886868953704834
2023-01-23 00:33:36.755700: step: 1464/530, loss: 0.022584104910492897
2023-01-23 00:33:37.824117: step: 1468/530, loss: 0.03950967639684677
2023-01-23 00:33:38.939702: step: 1472/530, loss: 0.08375759422779083
2023-01-23 00:33:40.075831: step: 1476/530, loss: 0.1788158416748047
2023-01-23 00:33:41.203136: step: 1480/530, loss: 0.06932497024536133
2023-01-23 00:33:42.320204: step: 1484/530, loss: 0.6988540887832642
2023-01-23 00:33:43.424595: step: 1488/530, loss: 0.09924602508544922
2023-01-23 00:33:44.536561: step: 1492/530, loss: 0.08173694461584091
2023-01-23 00:33:45.616915: step: 1496/530, loss: 0.3696770668029785
2023-01-23 00:33:46.703321: step: 1500/530, loss: 0.09256534278392792
2023-01-23 00:33:47.833074: step: 1504/530, loss: 0.5064190030097961
2023-01-23 00:33:48.916879: step: 1508/530, loss: 0.3354575037956238
2023-01-23 00:33:50.007637: step: 1512/530, loss: 0.07976799458265305
2023-01-23 00:33:51.125700: step: 1516/530, loss: 0.07779359817504883
2023-01-23 00:33:52.206400: step: 1520/530, loss: 0.04734072834253311
2023-01-23 00:33:53.303262: step: 1524/530, loss: 0.13560420274734497
2023-01-23 00:33:54.398746: step: 1528/530, loss: 0.634434700012207
2023-01-23 00:33:55.515971: step: 1532/530, loss: 0.09580822288990021
2023-01-23 00:33:56.624214: step: 1536/530, loss: 0.019923312589526176
2023-01-23 00:33:57.730889: step: 1540/530, loss: 0.17399214208126068
2023-01-23 00:33:58.887093: step: 1544/530, loss: 0.3431612253189087
2023-01-23 00:34:00.010470: step: 1548/530, loss: 0.11711979657411575
2023-01-23 00:34:01.147421: step: 1552/530, loss: 0.4007362425327301
2023-01-23 00:34:02.261144: step: 1556/530, loss: 0.027413655072450638
2023-01-23 00:34:03.405436: step: 1560/530, loss: 0.06437353789806366
2023-01-23 00:34:04.524332: step: 1564/530, loss: 0.12603816390037537
2023-01-23 00:34:05.614501: step: 1568/530, loss: 0.15179356932640076
2023-01-23 00:34:06.689995: step: 1572/530, loss: 0.07432813942432404
2023-01-23 00:34:07.793139: step: 1576/530, loss: 0.0698603168129921
2023-01-23 00:34:08.907217: step: 1580/530, loss: 0.19867831468582153
2023-01-23 00:34:09.992785: step: 1584/530, loss: 0.14878816902637482
2023-01-23 00:34:11.137779: step: 1588/530, loss: 0.07033753395080566
2023-01-23 00:34:12.248621: step: 1592/530, loss: 0.1424090415239334
2023-01-23 00:34:13.355089: step: 1596/530, loss: 0.05425385385751724
2023-01-23 00:34:14.461735: step: 1600/530, loss: 0.17768363654613495
2023-01-23 00:34:15.557020: step: 1604/530, loss: 0.1344536542892456
2023-01-23 00:34:16.675535: step: 1608/530, loss: 0.07669587433338165
2023-01-23 00:34:17.809030: step: 1612/530, loss: 0.19627760350704193
2023-01-23 00:34:18.897752: step: 1616/530, loss: 0.22488613426685333
2023-01-23 00:34:19.989505: step: 1620/530, loss: 0.06286501884460449
2023-01-23 00:34:21.101744: step: 1624/530, loss: 0.032280731946229935
2023-01-23 00:34:22.236497: step: 1628/530, loss: 0.040767598897218704
2023-01-23 00:34:23.344452: step: 1632/530, loss: 0.08839156478643417
2023-01-23 00:34:24.431615: step: 1636/530, loss: 0.09683070331811905
2023-01-23 00:34:25.530261: step: 1640/530, loss: 0.15801803767681122
2023-01-23 00:34:26.642772: step: 1644/530, loss: 0.04566001892089844
2023-01-23 00:34:27.753564: step: 1648/530, loss: 0.03453559800982475
2023-01-23 00:34:28.874463: step: 1652/530, loss: 0.2649565637111664
2023-01-23 00:34:29.974150: step: 1656/530, loss: 0.20853376388549805
2023-01-23 00:34:31.088724: step: 1660/530, loss: 0.03739719092845917
2023-01-23 00:34:32.220217: step: 1664/530, loss: 0.9176833033561707
2023-01-23 00:34:33.354210: step: 1668/530, loss: 0.24372054636478424
2023-01-23 00:34:34.464252: step: 1672/530, loss: 1.1824594736099243
2023-01-23 00:34:35.571368: step: 1676/530, loss: 0.10102196037769318
2023-01-23 00:34:36.702530: step: 1680/530, loss: 0.5427728295326233
2023-01-23 00:34:37.799231: step: 1684/530, loss: 0.7511458992958069
2023-01-23 00:34:38.935566: step: 1688/530, loss: 0.07435502856969833
2023-01-23 00:34:40.042129: step: 1692/530, loss: 0.12371456623077393
2023-01-23 00:34:41.154291: step: 1696/530, loss: 0.013656927272677422
2023-01-23 00:34:42.290080: step: 1700/530, loss: 0.546288013458252
2023-01-23 00:34:43.389778: step: 1704/530, loss: 0.12884268164634705
2023-01-23 00:34:44.486097: step: 1708/530, loss: 0.4251531660556793
2023-01-23 00:34:45.580930: step: 1712/530, loss: 0.11277890205383301
2023-01-23 00:34:46.661106: step: 1716/530, loss: 0.8625238537788391
2023-01-23 00:34:47.784129: step: 1720/530, loss: 0.3238413333892822
2023-01-23 00:34:48.888573: step: 1724/530, loss: 0.13582482933998108
2023-01-23 00:34:49.982588: step: 1728/530, loss: 0.08373288810253143
2023-01-23 00:34:51.117791: step: 1732/530, loss: 0.23664750158786774
2023-01-23 00:34:52.230000: step: 1736/530, loss: 0.10480336844921112
2023-01-23 00:34:53.319774: step: 1740/530, loss: 0.07555494457483292
2023-01-23 00:34:54.431296: step: 1744/530, loss: 0.3895745277404785
2023-01-23 00:34:55.559584: step: 1748/530, loss: 0.0558532252907753
2023-01-23 00:34:56.698661: step: 1752/530, loss: 0.534936249256134
2023-01-23 00:34:57.807329: step: 1756/530, loss: 0.491568386554718
2023-01-23 00:34:58.923874: step: 1760/530, loss: 0.24336567521095276
2023-01-23 00:35:00.025096: step: 1764/530, loss: 0.03911319002509117
2023-01-23 00:35:01.121181: step: 1768/530, loss: 0.1109614446759224
2023-01-23 00:35:02.237573: step: 1772/530, loss: 0.09415673464536667
2023-01-23 00:35:03.333106: step: 1776/530, loss: 0.07102489471435547
2023-01-23 00:35:04.445766: step: 1780/530, loss: 0.21890735626220703
2023-01-23 00:35:05.551099: step: 1784/530, loss: 0.27712059020996094
2023-01-23 00:35:06.658596: step: 1788/530, loss: 0.1479993313550949
2023-01-23 00:35:07.782456: step: 1792/530, loss: 0.05909309536218643
2023-01-23 00:35:08.883411: step: 1796/530, loss: 0.7951620817184448
2023-01-23 00:35:10.005249: step: 1800/530, loss: 0.15672674775123596
2023-01-23 00:35:11.115900: step: 1804/530, loss: 0.17226552963256836
2023-01-23 00:35:12.229306: step: 1808/530, loss: 0.09262494742870331
2023-01-23 00:35:13.338117: step: 1812/530, loss: 0.1969434767961502
2023-01-23 00:35:14.450893: step: 1816/530, loss: 0.08065243065357208
2023-01-23 00:35:15.581641: step: 1820/530, loss: 0.23438984155654907
2023-01-23 00:35:16.705776: step: 1824/530, loss: 0.7949447631835938
2023-01-23 00:35:17.830468: step: 1828/530, loss: 0.3645614683628082
2023-01-23 00:35:18.960927: step: 1832/530, loss: 0.10086217522621155
2023-01-23 00:35:20.051447: step: 1836/530, loss: 0.16418743133544922
2023-01-23 00:35:21.158648: step: 1840/530, loss: 0.03284807130694389
2023-01-23 00:35:22.251997: step: 1844/530, loss: 0.04199647903442383
2023-01-23 00:35:23.379726: step: 1848/530, loss: 0.6918651461601257
2023-01-23 00:35:24.477750: step: 1852/530, loss: 0.03935125097632408
2023-01-23 00:35:25.575750: step: 1856/530, loss: 0.15503883361816406
2023-01-23 00:35:26.684970: step: 1860/530, loss: 0.1573176383972168
2023-01-23 00:35:27.811655: step: 1864/530, loss: 0.18531304597854614
2023-01-23 00:35:28.930259: step: 1868/530, loss: 0.9952538013458252
2023-01-23 00:35:30.024331: step: 1872/530, loss: 0.09039059281349182
2023-01-23 00:35:31.129512: step: 1876/530, loss: 0.09948806464672089
2023-01-23 00:35:32.232491: step: 1880/530, loss: 0.21267862617969513
2023-01-23 00:35:33.382918: step: 1884/530, loss: 0.24610663950443268
2023-01-23 00:35:34.495960: step: 1888/530, loss: 0.379660427570343
2023-01-23 00:35:35.636400: step: 1892/530, loss: 0.24018077552318573
2023-01-23 00:35:36.767313: step: 1896/530, loss: 0.12495160102844238
2023-01-23 00:35:37.893774: step: 1900/530, loss: 0.14095859229564667
2023-01-23 00:35:38.984957: step: 1904/530, loss: 0.09711358696222305
2023-01-23 00:35:40.126366: step: 1908/530, loss: 0.11520948261022568
2023-01-23 00:35:41.222027: step: 1912/530, loss: 0.8499228358268738
2023-01-23 00:35:42.320485: step: 1916/530, loss: 0.10925617814064026
2023-01-23 00:35:43.452117: step: 1920/530, loss: 0.1350785791873932
2023-01-23 00:35:44.538089: step: 1924/530, loss: 0.05995321273803711
2023-01-23 00:35:45.655024: step: 1928/530, loss: 0.03709602355957031
2023-01-23 00:35:46.753880: step: 1932/530, loss: 0.3697931170463562
2023-01-23 00:35:47.862562: step: 1936/530, loss: 0.2087252140045166
2023-01-23 00:35:48.990911: step: 1940/530, loss: 0.25694623589515686
2023-01-23 00:35:50.103849: step: 1944/530, loss: 0.0803590789437294
2023-01-23 00:35:51.210861: step: 1948/530, loss: 0.09548091888427734
2023-01-23 00:35:52.326640: step: 1952/530, loss: 0.06707639992237091
2023-01-23 00:35:53.473180: step: 1956/530, loss: 1.132390022277832
2023-01-23 00:35:54.570798: step: 1960/530, loss: 0.01466674730181694
2023-01-23 00:35:55.650761: step: 1964/530, loss: 0.3246227204799652
2023-01-23 00:35:56.746505: step: 1968/530, loss: 0.30153340101242065
2023-01-23 00:35:57.847977: step: 1972/530, loss: 0.5989601016044617
2023-01-23 00:35:58.945301: step: 1976/530, loss: 0.21505257487297058
2023-01-23 00:36:00.039867: step: 1980/530, loss: 0.38150912523269653
2023-01-23 00:36:01.133017: step: 1984/530, loss: 0.14348506927490234
2023-01-23 00:36:02.256041: step: 1988/530, loss: 0.0634654089808464
2023-01-23 00:36:03.345254: step: 1992/530, loss: 0.02373323403298855
2023-01-23 00:36:04.441765: step: 1996/530, loss: 0.06984737515449524
2023-01-23 00:36:05.570393: step: 2000/530, loss: 0.1760483682155609
2023-01-23 00:36:06.732875: step: 2004/530, loss: 0.07238321751356125
2023-01-23 00:36:07.842456: step: 2008/530, loss: 0.14514485001564026
2023-01-23 00:36:08.914233: step: 2012/530, loss: 0.14287766814231873
2023-01-23 00:36:10.036495: step: 2016/530, loss: 0.17567339539527893
2023-01-23 00:36:11.133279: step: 2020/530, loss: 0.12714596092700958
2023-01-23 00:36:12.236245: step: 2024/530, loss: 0.06722183525562286
2023-01-23 00:36:13.357657: step: 2028/530, loss: 0.11953344941139221
2023-01-23 00:36:14.480215: step: 2032/530, loss: 0.09094009548425674
2023-01-23 00:36:15.622250: step: 2036/530, loss: 0.09003925323486328
2023-01-23 00:36:16.740938: step: 2040/530, loss: 0.16840039193630219
2023-01-23 00:36:17.844297: step: 2044/530, loss: 0.4642484188079834
2023-01-23 00:36:18.970883: step: 2048/530, loss: 0.18713703751564026
2023-01-23 00:36:20.076944: step: 2052/530, loss: 0.21268220245838165
2023-01-23 00:36:21.175240: step: 2056/530, loss: 0.12185921519994736
2023-01-23 00:36:22.278211: step: 2060/530, loss: 0.11772609502077103
2023-01-23 00:36:23.375231: step: 2064/530, loss: 0.0825016051530838
2023-01-23 00:36:24.451466: step: 2068/530, loss: 0.26831990480422974
2023-01-23 00:36:25.577026: step: 2072/530, loss: 0.18535655736923218
2023-01-23 00:36:26.668095: step: 2076/530, loss: 0.32517918944358826
2023-01-23 00:36:27.770204: step: 2080/530, loss: 0.16744498908519745
2023-01-23 00:36:28.891903: step: 2084/530, loss: 3.0062737464904785
2023-01-23 00:36:29.977877: step: 2088/530, loss: 0.07003412395715714
2023-01-23 00:36:31.077250: step: 2092/530, loss: 0.08714008331298828
2023-01-23 00:36:32.176030: step: 2096/530, loss: 0.14412860572338104
2023-01-23 00:36:33.315084: step: 2100/530, loss: 0.02461080625653267
2023-01-23 00:36:34.416200: step: 2104/530, loss: 0.09455351531505585
2023-01-23 00:36:35.517818: step: 2108/530, loss: 0.049488164484500885
2023-01-23 00:36:36.638324: step: 2112/530, loss: 0.21966229379177094
2023-01-23 00:36:37.778658: step: 2116/530, loss: 1.3812816143035889
2023-01-23 00:36:38.879301: step: 2120/530, loss: 0.8254890441894531
==================================================
Loss: 0.224
--------------------
Dev: {'event': {'p': 0.5306691449814126, 'r': 0.7603195739014648, 'f1': 0.6250684181718664}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Test: {'event': {'p': 0.5916594265855778, 'r': 0.7937062937062938, 'f1': 0.6779492284718766}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Chinese: {'event': {'p': 0.4943820224719101, 'r': 0.8148148148148148, 'f1': 0.6153846153846153}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Korean: {'event': {'p': 0.4666666666666667, 'r': 0.5555555555555556, 'f1': 0.5072463768115943}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
Russian: {'event': {'p': 0.3617021276595745, 'r': 0.4722222222222222, 'f1': 0.40963855421686746}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 6}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.5708622398414271, 'r': 0.7669773635153129, 'f1': 0.6545454545454545}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Eng Test for Chinese: {'event': {'p': 0.6044052863436123, 'r': 0.7995337995337995, 'f1': 0.6884094330155545}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Sample Chinese: {'event': {'p': 0.6578947368421053, 'r': 0.9259259259259259, 'f1': 0.7692307692307692}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6218961625282167, 'r': 0.7336884154460719, 'f1': 0.6731826511912034}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Eng Test for Korean: {'event': {'p': 0.6148681055155876, 'r': 0.747086247086247, 'f1': 0.6745593264930282}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
Sample Korean: {'event': {'p': 0.7631578947368421, 'r': 0.4603174603174603, 'f1': 0.5742574257425742}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 2}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5862457722660653, 'r': 0.6924101198402131, 'f1': 0.634920634920635}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Eng Test for Russian: {'event': {'p': 0.5994652406417113, 'r': 0.6532634032634033, 'f1': 0.6252091466815394}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
Sample Russian: {'event': {'p': 0.625, 'r': 0.4166666666666667, 'f1': 0.5}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 1}
******************************
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 00:37:18.851300: step: 4/530, loss: 0.36224472522735596
2023-01-23 00:37:19.944174: step: 8/530, loss: 0.08169898390769958
2023-01-23 00:37:21.056809: step: 12/530, loss: 0.11723347008228302
2023-01-23 00:37:22.167078: step: 16/530, loss: 0.11726561188697815
2023-01-23 00:37:23.271130: step: 20/530, loss: 0.18027916550636292
2023-01-23 00:37:24.380966: step: 24/530, loss: 0.06626129150390625
2023-01-23 00:37:25.479326: step: 28/530, loss: 0.10006208717823029
2023-01-23 00:37:26.590439: step: 32/530, loss: 0.24529027938842773
2023-01-23 00:37:27.700409: step: 36/530, loss: 0.060425616800785065
2023-01-23 00:37:28.808814: step: 40/530, loss: 0.08134423196315765
2023-01-23 00:37:29.936235: step: 44/530, loss: 0.024162864312529564
2023-01-23 00:37:31.051526: step: 48/530, loss: 0.3644390106201172
2023-01-23 00:37:32.184738: step: 52/530, loss: 0.10955658555030823
2023-01-23 00:37:33.296289: step: 56/530, loss: 0.15728087723255157
2023-01-23 00:37:34.420778: step: 60/530, loss: 0.10733642429113388
2023-01-23 00:37:35.535454: step: 64/530, loss: 0.010541249066591263
2023-01-23 00:37:36.615137: step: 68/530, loss: 0.13670583069324493
2023-01-23 00:37:37.750514: step: 72/530, loss: 0.07948508858680725
2023-01-23 00:37:38.837002: step: 76/530, loss: 0.052745986729860306
2023-01-23 00:37:39.936447: step: 80/530, loss: 0.04770860821008682
2023-01-23 00:37:41.061115: step: 84/530, loss: 0.0271914005279541
2023-01-23 00:37:42.171678: step: 88/530, loss: 0.11575041711330414
2023-01-23 00:37:43.259202: step: 92/530, loss: 0.25489839911460876
2023-01-23 00:37:44.362844: step: 96/530, loss: 0.05923328548669815
2023-01-23 00:37:45.470281: step: 100/530, loss: 0.376596063375473
2023-01-23 00:37:46.579810: step: 104/530, loss: 0.016396379098296165
2023-01-23 00:37:47.698525: step: 108/530, loss: 0.04903850704431534
2023-01-23 00:37:48.809674: step: 112/530, loss: 0.0548674613237381
2023-01-23 00:37:49.879755: step: 116/530, loss: 0.03580117225646973
2023-01-23 00:37:51.014625: step: 120/530, loss: 0.035443879663944244
2023-01-23 00:37:52.114896: step: 124/530, loss: 0.09235982596874237
2023-01-23 00:37:53.244275: step: 128/530, loss: 0.07010116428136826
2023-01-23 00:37:54.348804: step: 132/530, loss: 0.1550171822309494
2023-01-23 00:37:55.470297: step: 136/530, loss: 0.09939423203468323
2023-01-23 00:37:56.565436: step: 140/530, loss: 0.18047255277633667
2023-01-23 00:37:57.673324: step: 144/530, loss: 0.11910267174243927
2023-01-23 00:37:58.768558: step: 148/530, loss: 0.06516984850168228
2023-01-23 00:37:59.851720: step: 152/530, loss: 0.07480421662330627
2023-01-23 00:38:00.969978: step: 156/530, loss: 0.06669798493385315
2023-01-23 00:38:02.080672: step: 160/530, loss: 0.2969152331352234
2023-01-23 00:38:03.203851: step: 164/530, loss: 0.14896050095558167
2023-01-23 00:38:04.295723: step: 168/530, loss: 0.12872613966464996
2023-01-23 00:38:05.391233: step: 172/530, loss: 0.10578031837940216
2023-01-23 00:38:06.488485: step: 176/530, loss: 0.16356438398361206
2023-01-23 00:38:07.606608: step: 180/530, loss: 0.12344856560230255
2023-01-23 00:38:08.748656: step: 184/530, loss: 0.18796882033348083
2023-01-23 00:38:09.864236: step: 188/530, loss: 0.2580105662345886
2023-01-23 00:38:10.952504: step: 192/530, loss: 0.07540258765220642
2023-01-23 00:38:12.041531: step: 196/530, loss: 0.04785637930035591
2023-01-23 00:38:13.150684: step: 200/530, loss: 0.19221201539039612
2023-01-23 00:38:14.263306: step: 204/530, loss: 0.16617251932621002
2023-01-23 00:38:15.371237: step: 208/530, loss: 0.15216389298439026
2023-01-23 00:38:16.480790: step: 212/530, loss: 0.3022747039794922
2023-01-23 00:38:17.609293: step: 216/530, loss: 0.14795561134815216
2023-01-23 00:38:18.732901: step: 220/530, loss: 0.081329345703125
2023-01-23 00:38:19.847891: step: 224/530, loss: 0.07722587883472443
2023-01-23 00:38:20.966435: step: 228/530, loss: 0.1562521904706955
2023-01-23 00:38:22.072221: step: 232/530, loss: 0.020304013043642044
2023-01-23 00:38:23.201610: step: 236/530, loss: 0.16753073036670685
2023-01-23 00:38:24.301225: step: 240/530, loss: 0.04196987301111221
2023-01-23 00:38:25.415470: step: 244/530, loss: 0.06264229118824005
2023-01-23 00:38:26.486165: step: 248/530, loss: 0.23840151727199554
2023-01-23 00:38:27.579914: step: 252/530, loss: 0.04350433498620987
2023-01-23 00:38:28.684069: step: 256/530, loss: 0.05226287990808487
2023-01-23 00:38:29.815957: step: 260/530, loss: 0.25967827439308167
2023-01-23 00:38:30.898109: step: 264/530, loss: 0.20942655205726624
2023-01-23 00:38:32.013001: step: 268/530, loss: 0.026894044131040573
2023-01-23 00:38:33.152996: step: 272/530, loss: 0.09174290299415588
2023-01-23 00:38:34.271593: step: 276/530, loss: 0.12692275643348694
2023-01-23 00:38:35.374946: step: 280/530, loss: 0.06794138252735138
2023-01-23 00:38:36.453242: step: 284/530, loss: 0.21318918466567993
2023-01-23 00:38:37.570516: step: 288/530, loss: 0.08089981228113174
2023-01-23 00:38:38.665365: step: 292/530, loss: 0.1339005082845688
2023-01-23 00:38:39.769965: step: 296/530, loss: 0.17511996626853943
2023-01-23 00:38:40.877592: step: 300/530, loss: 0.02764458768069744
2023-01-23 00:38:41.979059: step: 304/530, loss: 0.033239271491765976
2023-01-23 00:38:43.096021: step: 308/530, loss: 0.06931314617395401
2023-01-23 00:38:44.181452: step: 312/530, loss: 0.08564615249633789
2023-01-23 00:38:45.299143: step: 316/530, loss: 0.30077144503593445
2023-01-23 00:38:46.431591: step: 320/530, loss: 0.195203959941864
2023-01-23 00:38:47.557461: step: 324/530, loss: 0.18814457952976227
2023-01-23 00:38:48.661378: step: 328/530, loss: 0.42802226543426514
2023-01-23 00:38:49.779400: step: 332/530, loss: 0.13078871369361877
2023-01-23 00:38:50.868750: step: 336/530, loss: 0.1847125142812729
2023-01-23 00:38:51.981843: step: 340/530, loss: 0.25691360235214233
2023-01-23 00:38:53.087732: step: 344/530, loss: 0.01910848543047905
2023-01-23 00:38:54.218808: step: 348/530, loss: 0.13002434372901917
2023-01-23 00:38:55.346389: step: 352/530, loss: 0.3374102711677551
2023-01-23 00:38:56.469160: step: 356/530, loss: 0.12634725868701935
2023-01-23 00:38:57.590826: step: 360/530, loss: 0.14684835076332092
2023-01-23 00:38:58.693656: step: 364/530, loss: 0.24435709416866302
2023-01-23 00:38:59.833051: step: 368/530, loss: 0.12131842970848083
2023-01-23 00:39:00.903375: step: 372/530, loss: 0.031496811658144
2023-01-23 00:39:02.016451: step: 376/530, loss: 0.6800879240036011
2023-01-23 00:39:03.106699: step: 380/530, loss: 0.05104236677289009
2023-01-23 00:39:04.200255: step: 384/530, loss: 0.08195820450782776
2023-01-23 00:39:05.291303: step: 388/530, loss: 0.6275573372840881
2023-01-23 00:39:06.420891: step: 392/530, loss: 0.04400348663330078
2023-01-23 00:39:07.526220: step: 396/530, loss: 0.09596381336450577
2023-01-23 00:39:08.619190: step: 400/530, loss: 0.04238080978393555
2023-01-23 00:39:09.745135: step: 404/530, loss: 0.11941839009523392
2023-01-23 00:39:10.855835: step: 408/530, loss: 0.025572681799530983
2023-01-23 00:39:12.023314: step: 412/530, loss: 0.08564386516809464
2023-01-23 00:39:13.155059: step: 416/530, loss: 0.24502038955688477
2023-01-23 00:39:14.263339: step: 420/530, loss: 0.21368902921676636
2023-01-23 00:39:15.405087: step: 424/530, loss: 0.1127803772687912
2023-01-23 00:39:16.507649: step: 428/530, loss: 0.3384517431259155
2023-01-23 00:39:17.607862: step: 432/530, loss: 0.10947570949792862
2023-01-23 00:39:18.734591: step: 436/530, loss: 0.07433748245239258
2023-01-23 00:39:19.861353: step: 440/530, loss: 0.0066460613161325455
2023-01-23 00:39:20.984174: step: 444/530, loss: 0.15554103255271912
2023-01-23 00:39:22.088025: step: 448/530, loss: 0.08113746345043182
2023-01-23 00:39:23.233727: step: 452/530, loss: 0.01602044142782688
2023-01-23 00:39:24.353055: step: 456/530, loss: 0.29054251313209534
2023-01-23 00:39:25.481569: step: 460/530, loss: 0.09272976219654083
2023-01-23 00:39:26.577930: step: 464/530, loss: 0.13529759645462036
2023-01-23 00:39:27.688350: step: 468/530, loss: 0.12897825241088867
2023-01-23 00:39:28.795574: step: 472/530, loss: 0.09445630013942719
2023-01-23 00:39:29.908037: step: 476/530, loss: 0.07652568817138672
2023-01-23 00:39:30.991535: step: 480/530, loss: 0.17240294814109802
2023-01-23 00:39:32.081801: step: 484/530, loss: 0.04783831536769867
2023-01-23 00:39:33.221936: step: 488/530, loss: 0.26537173986434937
2023-01-23 00:39:34.337846: step: 492/530, loss: 0.15151160955429077
2023-01-23 00:39:35.437283: step: 496/530, loss: 0.07788319885730743
2023-01-23 00:39:36.529066: step: 500/530, loss: 0.0807105079293251
2023-01-23 00:39:37.640504: step: 504/530, loss: 0.09307919442653656
2023-01-23 00:39:38.750712: step: 508/530, loss: 0.07221775501966476
2023-01-23 00:39:39.826833: step: 512/530, loss: 0.055219076573848724
2023-01-23 00:39:40.937659: step: 516/530, loss: 0.07111234962940216
2023-01-23 00:39:42.055671: step: 520/530, loss: 0.11655382812023163
2023-01-23 00:39:43.151006: step: 524/530, loss: 0.04891214519739151
2023-01-23 00:39:44.247333: step: 528/530, loss: 0.5244685411453247
2023-01-23 00:39:45.341149: step: 532/530, loss: 0.09860782325267792
2023-01-23 00:39:46.471065: step: 536/530, loss: 0.15768924355506897
2023-01-23 00:39:47.590134: step: 540/530, loss: 0.023074721917510033
2023-01-23 00:39:48.661787: step: 544/530, loss: 0.10996818542480469
2023-01-23 00:39:49.768270: step: 548/530, loss: 0.14653438329696655
2023-01-23 00:39:50.879128: step: 552/530, loss: 0.02022085152566433
2023-01-23 00:39:51.995497: step: 556/530, loss: 0.13782139122486115
2023-01-23 00:39:53.091584: step: 560/530, loss: 0.11602868884801865
2023-01-23 00:39:54.200446: step: 564/530, loss: 0.16662444174289703
2023-01-23 00:39:55.334122: step: 568/530, loss: 0.06321864575147629
2023-01-23 00:39:56.440005: step: 572/530, loss: 0.14570438861846924
2023-01-23 00:39:57.590484: step: 576/530, loss: 0.030066443607211113
2023-01-23 00:39:58.681688: step: 580/530, loss: 0.06422023475170135
2023-01-23 00:39:59.789121: step: 584/530, loss: 0.10024777054786682
2023-01-23 00:40:00.934079: step: 588/530, loss: 0.11624159663915634
2023-01-23 00:40:02.041395: step: 592/530, loss: 0.10526628792285919
2023-01-23 00:40:03.178938: step: 596/530, loss: 0.2598729133605957
2023-01-23 00:40:04.319425: step: 600/530, loss: 0.23966895043849945
2023-01-23 00:40:05.441943: step: 604/530, loss: 0.1576642096042633
2023-01-23 00:40:06.556503: step: 608/530, loss: 0.23652610182762146
2023-01-23 00:40:07.647325: step: 612/530, loss: 0.21020039916038513
2023-01-23 00:40:08.751948: step: 616/530, loss: 0.13178463280200958
2023-01-23 00:40:09.849750: step: 620/530, loss: 0.062041569501161575
2023-01-23 00:40:10.957106: step: 624/530, loss: 0.12152253091335297
2023-01-23 00:40:12.054358: step: 628/530, loss: 0.04203624650835991
2023-01-23 00:40:13.167482: step: 632/530, loss: 0.08141221851110458
2023-01-23 00:40:14.277951: step: 636/530, loss: 0.03884744644165039
2023-01-23 00:40:15.399138: step: 640/530, loss: 0.3405753970146179
2023-01-23 00:40:16.488353: step: 644/530, loss: 0.04978933557868004
2023-01-23 00:40:17.584177: step: 648/530, loss: 0.03873853757977486
2023-01-23 00:40:18.699400: step: 652/530, loss: 0.06918811798095703
2023-01-23 00:40:19.816932: step: 656/530, loss: 0.3046959936618805
2023-01-23 00:40:20.913034: step: 660/530, loss: 0.04819068685173988
2023-01-23 00:40:21.985480: step: 664/530, loss: 0.14781463146209717
2023-01-23 00:40:23.111828: step: 668/530, loss: 0.16608715057373047
2023-01-23 00:40:24.218037: step: 672/530, loss: 1.6966180801391602
2023-01-23 00:40:25.300542: step: 676/530, loss: 0.01608905754983425
2023-01-23 00:40:26.456731: step: 680/530, loss: 0.0703834518790245
2023-01-23 00:40:27.578504: step: 684/530, loss: 0.38224610686302185
2023-01-23 00:40:28.670373: step: 688/530, loss: 0.01757340505719185
2023-01-23 00:40:29.793160: step: 692/530, loss: 0.11459548771381378
2023-01-23 00:40:30.906276: step: 696/530, loss: 0.18223437666893005
2023-01-23 00:40:32.011706: step: 700/530, loss: 0.12882661819458008
2023-01-23 00:40:33.090651: step: 704/530, loss: 0.16912880539894104
2023-01-23 00:40:34.185263: step: 708/530, loss: 0.03116750717163086
2023-01-23 00:40:35.280501: step: 712/530, loss: 0.23051002621650696
2023-01-23 00:40:36.388127: step: 716/530, loss: 0.03588886186480522
2023-01-23 00:40:37.539773: step: 720/530, loss: 0.029929352924227715
2023-01-23 00:40:38.639791: step: 724/530, loss: 0.11127138137817383
2023-01-23 00:40:39.744720: step: 728/530, loss: 0.10038814693689346
2023-01-23 00:40:40.838270: step: 732/530, loss: 0.047283269464969635
2023-01-23 00:40:41.945331: step: 736/530, loss: 0.11007729172706604
2023-01-23 00:40:43.049732: step: 740/530, loss: 0.04739560931921005
2023-01-23 00:40:44.138326: step: 744/530, loss: 0.00405278243124485
2023-01-23 00:40:45.246144: step: 748/530, loss: 0.020952891558408737
2023-01-23 00:40:46.402843: step: 752/530, loss: 0.04703464359045029
2023-01-23 00:40:47.494107: step: 756/530, loss: 0.09642362594604492
2023-01-23 00:40:48.629357: step: 760/530, loss: 0.24380818009376526
2023-01-23 00:40:49.752853: step: 764/530, loss: 0.008885574527084827
2023-01-23 00:40:50.857301: step: 768/530, loss: 0.07128553092479706
2023-01-23 00:40:51.962688: step: 772/530, loss: 0.22350959479808807
2023-01-23 00:40:53.088447: step: 776/530, loss: 0.14705219864845276
2023-01-23 00:40:54.175934: step: 780/530, loss: 0.06413183361291885
2023-01-23 00:40:55.316841: step: 784/530, loss: 0.06745896488428116
2023-01-23 00:40:56.406026: step: 788/530, loss: 0.03466834872961044
2023-01-23 00:40:57.496022: step: 792/530, loss: 0.4959568977355957
2023-01-23 00:40:58.648449: step: 796/530, loss: 0.08434753865003586
2023-01-23 00:40:59.743962: step: 800/530, loss: 0.03377866744995117
2023-01-23 00:41:00.845952: step: 804/530, loss: 0.6991739273071289
2023-01-23 00:41:01.997555: step: 808/530, loss: 0.4068222939968109
2023-01-23 00:41:03.148081: step: 812/530, loss: 0.16741368174552917
2023-01-23 00:41:04.244899: step: 816/530, loss: 0.03897132724523544
2023-01-23 00:41:05.320861: step: 820/530, loss: 0.05940275266766548
2023-01-23 00:41:06.438561: step: 824/530, loss: 0.13710708916187286
2023-01-23 00:41:07.569073: step: 828/530, loss: 0.07942590862512589
2023-01-23 00:41:08.654982: step: 832/530, loss: 0.06220893934369087
2023-01-23 00:41:09.779877: step: 836/530, loss: 0.1766260266304016
2023-01-23 00:41:10.880102: step: 840/530, loss: 0.46785974502563477
2023-01-23 00:41:11.979462: step: 844/530, loss: 0.03129148483276367
2023-01-23 00:41:13.105782: step: 848/530, loss: 0.05395854264497757
2023-01-23 00:41:14.195300: step: 852/530, loss: 0.10576143860816956
2023-01-23 00:41:15.274506: step: 856/530, loss: 0.11757240444421768
2023-01-23 00:41:16.360815: step: 860/530, loss: 0.44978657364845276
2023-01-23 00:41:17.465965: step: 864/530, loss: 0.03127651289105415
2023-01-23 00:41:18.564040: step: 868/530, loss: 0.07244300842285156
2023-01-23 00:41:19.717446: step: 872/530, loss: 0.13387927412986755
2023-01-23 00:41:20.815779: step: 876/530, loss: 0.10329776257276535
2023-01-23 00:41:21.915708: step: 880/530, loss: 0.08379817008972168
2023-01-23 00:41:23.001317: step: 884/530, loss: 0.036215975880622864
2023-01-23 00:41:24.086455: step: 888/530, loss: 1.1378170251846313
2023-01-23 00:41:25.221899: step: 892/530, loss: 0.1116364523768425
2023-01-23 00:41:26.344437: step: 896/530, loss: 0.3022039830684662
2023-01-23 00:41:27.456990: step: 900/530, loss: 0.10958519577980042
2023-01-23 00:41:28.606257: step: 904/530, loss: 0.03434352949261665
2023-01-23 00:41:29.698751: step: 908/530, loss: 0.05333547666668892
2023-01-23 00:41:30.793052: step: 912/530, loss: 0.06869831681251526
2023-01-23 00:41:31.900765: step: 916/530, loss: 0.04169069603085518
2023-01-23 00:41:33.015570: step: 920/530, loss: 0.12139873951673508
2023-01-23 00:41:34.139322: step: 924/530, loss: 0.1329408586025238
2023-01-23 00:41:35.248947: step: 928/530, loss: 0.03367280960083008
2023-01-23 00:41:36.366033: step: 932/530, loss: 0.05431051552295685
2023-01-23 00:41:37.459014: step: 936/530, loss: 0.14356574416160583
2023-01-23 00:41:38.554917: step: 940/530, loss: 0.1011572852730751
2023-01-23 00:41:39.675606: step: 944/530, loss: 0.010050726123154163
2023-01-23 00:41:40.770622: step: 948/530, loss: 0.10786259174346924
2023-01-23 00:41:41.913642: step: 952/530, loss: 0.010282707400619984
2023-01-23 00:41:43.043245: step: 956/530, loss: 0.5963069796562195
2023-01-23 00:41:44.143856: step: 960/530, loss: 0.09364481270313263
2023-01-23 00:41:45.247302: step: 964/530, loss: 0.1207679808139801
2023-01-23 00:41:46.313663: step: 968/530, loss: 0.05529933050274849
2023-01-23 00:41:47.410791: step: 972/530, loss: 0.015235376544296741
2023-01-23 00:41:48.540169: step: 976/530, loss: 0.20274028182029724
2023-01-23 00:41:49.644863: step: 980/530, loss: 0.7186511754989624
2023-01-23 00:41:50.763234: step: 984/530, loss: 0.1629629135131836
2023-01-23 00:41:51.874105: step: 988/530, loss: 0.13507023453712463
2023-01-23 00:41:52.969605: step: 992/530, loss: 0.23437313735485077
2023-01-23 00:41:54.060006: step: 996/530, loss: 0.0550900474190712
2023-01-23 00:41:55.159705: step: 1000/530, loss: 0.019523335620760918
2023-01-23 00:41:56.296108: step: 1004/530, loss: 0.12377357482910156
2023-01-23 00:41:57.402842: step: 1008/530, loss: 0.4395221769809723
2023-01-23 00:41:58.500994: step: 1012/530, loss: 0.043045803904533386
2023-01-23 00:41:59.586078: step: 1016/530, loss: 0.10103683918714523
2023-01-23 00:42:00.719964: step: 1020/530, loss: 0.06155281513929367
2023-01-23 00:42:01.819805: step: 1024/530, loss: 0.07357282936573029
2023-01-23 00:42:02.995499: step: 1028/530, loss: 0.06413498520851135
2023-01-23 00:42:04.120122: step: 1032/530, loss: 0.16371765732765198
2023-01-23 00:42:05.243910: step: 1036/530, loss: 0.11726627498865128
2023-01-23 00:42:06.327972: step: 1040/530, loss: 0.6850401163101196
2023-01-23 00:42:07.433385: step: 1044/530, loss: 0.06839428097009659
2023-01-23 00:42:08.569403: step: 1048/530, loss: 0.033388711512088776
2023-01-23 00:42:09.632785: step: 1052/530, loss: 0.028673553839325905
2023-01-23 00:42:10.759467: step: 1056/530, loss: 0.19330330193042755
2023-01-23 00:42:11.853465: step: 1060/530, loss: 0.2981095612049103
2023-01-23 00:42:12.944520: step: 1064/530, loss: 0.1984301656484604
2023-01-23 00:42:14.037245: step: 1068/530, loss: 0.20417605340480804
2023-01-23 00:42:15.164301: step: 1072/530, loss: 0.11032648384571075
2023-01-23 00:42:16.270776: step: 1076/530, loss: 0.03764014318585396
2023-01-23 00:42:17.382380: step: 1080/530, loss: 0.2675153315067291
2023-01-23 00:42:18.493784: step: 1084/530, loss: 0.6014558672904968
2023-01-23 00:42:19.582509: step: 1088/530, loss: 0.26674529910087585
2023-01-23 00:42:20.701914: step: 1092/530, loss: 0.09670582413673401
2023-01-23 00:42:21.812706: step: 1096/530, loss: 0.05879020690917969
2023-01-23 00:42:22.914521: step: 1100/530, loss: 0.20290032029151917
2023-01-23 00:42:24.044273: step: 1104/530, loss: 1.4648298025131226
2023-01-23 00:42:25.166905: step: 1108/530, loss: 0.4026739299297333
2023-01-23 00:42:26.272641: step: 1112/530, loss: 0.06233644858002663
2023-01-23 00:42:27.368499: step: 1116/530, loss: 0.03955087810754776
2023-01-23 00:42:28.472924: step: 1120/530, loss: 0.2662582993507385
2023-01-23 00:42:29.599997: step: 1124/530, loss: 0.03257620334625244
2023-01-23 00:42:30.713556: step: 1128/530, loss: 0.05949392169713974
2023-01-23 00:42:31.807994: step: 1132/530, loss: 0.19216357171535492
2023-01-23 00:42:32.925886: step: 1136/530, loss: 0.06876587867736816
2023-01-23 00:42:34.030516: step: 1140/530, loss: 0.2931135296821594
2023-01-23 00:42:35.172722: step: 1144/530, loss: 0.3316488265991211
2023-01-23 00:42:36.258492: step: 1148/530, loss: 0.016428422182798386
2023-01-23 00:42:37.413439: step: 1152/530, loss: 0.009912490844726562
2023-01-23 00:42:38.548179: step: 1156/530, loss: 0.04524817690253258
2023-01-23 00:42:39.682516: step: 1160/530, loss: 0.4253700077533722
2023-01-23 00:42:40.790190: step: 1164/530, loss: 0.04487800598144531
2023-01-23 00:42:41.887117: step: 1168/530, loss: 0.13685666024684906
2023-01-23 00:42:43.026886: step: 1172/530, loss: 0.04532451927661896
2023-01-23 00:42:44.145017: step: 1176/530, loss: 0.09571128338575363
2023-01-23 00:42:45.274088: step: 1180/530, loss: 0.16317157447338104
2023-01-23 00:42:46.373674: step: 1184/530, loss: 0.03981933742761612
2023-01-23 00:42:47.528977: step: 1188/530, loss: 0.17559146881103516
2023-01-23 00:42:48.639750: step: 1192/530, loss: 0.076934814453125
2023-01-23 00:42:49.766832: step: 1196/530, loss: 0.6746654510498047
2023-01-23 00:42:50.901128: step: 1200/530, loss: 0.20122194290161133
2023-01-23 00:42:52.005099: step: 1204/530, loss: 0.05625801533460617
2023-01-23 00:42:53.112124: step: 1208/530, loss: 0.1433342695236206
2023-01-23 00:42:54.211354: step: 1212/530, loss: 0.120702363550663
2023-01-23 00:42:55.334305: step: 1216/530, loss: 0.06711377948522568
2023-01-23 00:42:56.416222: step: 1220/530, loss: 0.10089044272899628
2023-01-23 00:42:57.522902: step: 1224/530, loss: 0.07660436630249023
2023-01-23 00:42:58.629691: step: 1228/530, loss: 0.10002336651086807
2023-01-23 00:42:59.737335: step: 1232/530, loss: 0.008935785852372646
2023-01-23 00:43:00.825719: step: 1236/530, loss: 0.03334970399737358
2023-01-23 00:43:01.925607: step: 1240/530, loss: 0.22614385187625885
2023-01-23 00:43:03.022953: step: 1244/530, loss: 0.0598149299621582
2023-01-23 00:43:04.130207: step: 1248/530, loss: 0.18491224944591522
2023-01-23 00:43:05.221005: step: 1252/530, loss: 0.12284259498119354
2023-01-23 00:43:06.327233: step: 1256/530, loss: 0.10551224648952484
2023-01-23 00:43:07.405677: step: 1260/530, loss: 0.18351221084594727
2023-01-23 00:43:08.509786: step: 1264/530, loss: 0.17852169275283813
2023-01-23 00:43:09.612359: step: 1268/530, loss: 0.05660710483789444
2023-01-23 00:43:10.734610: step: 1272/530, loss: 0.01652536541223526
2023-01-23 00:43:11.873555: step: 1276/530, loss: 0.056099891662597656
2023-01-23 00:43:12.997484: step: 1280/530, loss: 0.1079021468758583
2023-01-23 00:43:14.114132: step: 1284/530, loss: 0.11702223122119904
2023-01-23 00:43:15.219589: step: 1288/530, loss: 0.12205057591199875
2023-01-23 00:43:16.326228: step: 1292/530, loss: 0.17013882100582123
2023-01-23 00:43:17.437454: step: 1296/530, loss: 0.4505516588687897
2023-01-23 00:43:18.531241: step: 1300/530, loss: 0.04913225397467613
2023-01-23 00:43:19.640538: step: 1304/530, loss: 0.007321691606193781
2023-01-23 00:43:20.773981: step: 1308/530, loss: 0.11692790687084198
2023-01-23 00:43:21.869354: step: 1312/530, loss: 0.1647607386112213
2023-01-23 00:43:22.989290: step: 1316/530, loss: 0.0701846107840538
2023-01-23 00:43:24.095303: step: 1320/530, loss: 0.03838348388671875
2023-01-23 00:43:25.215526: step: 1324/530, loss: 0.0946449339389801
2023-01-23 00:43:26.394805: step: 1328/530, loss: 0.1541803479194641
2023-01-23 00:43:27.485511: step: 1332/530, loss: 0.083636574447155
2023-01-23 00:43:28.596694: step: 1336/530, loss: 0.10761566460132599
2023-01-23 00:43:29.694230: step: 1340/530, loss: 0.01571788638830185
2023-01-23 00:43:30.837727: step: 1344/530, loss: 0.061579324305057526
2023-01-23 00:43:31.950034: step: 1348/530, loss: 0.0747842788696289
2023-01-23 00:43:33.055492: step: 1352/530, loss: 0.2404789924621582
2023-01-23 00:43:34.144344: step: 1356/530, loss: 0.06411950290203094
2023-01-23 00:43:35.226360: step: 1360/530, loss: 0.06407604366540909
2023-01-23 00:43:36.312985: step: 1364/530, loss: 0.2542060613632202
2023-01-23 00:43:37.441836: step: 1368/530, loss: 0.060243330895900726
2023-01-23 00:43:38.558219: step: 1372/530, loss: 0.4493376612663269
2023-01-23 00:43:39.654356: step: 1376/530, loss: 0.6244895458221436
2023-01-23 00:43:40.771228: step: 1380/530, loss: 0.03403501585125923
2023-01-23 00:43:41.880953: step: 1384/530, loss: 0.18758173286914825
2023-01-23 00:43:42.982948: step: 1388/530, loss: 0.024759292602539062
2023-01-23 00:43:44.077142: step: 1392/530, loss: 0.06201000511646271
2023-01-23 00:43:45.179118: step: 1396/530, loss: 0.04967174679040909
2023-01-23 00:43:46.304634: step: 1400/530, loss: 0.14865446090698242
2023-01-23 00:43:47.425054: step: 1404/530, loss: 0.083203986287117
2023-01-23 00:43:48.523964: step: 1408/530, loss: 0.13988637924194336
2023-01-23 00:43:49.645397: step: 1412/530, loss: 0.07094764709472656
2023-01-23 00:43:50.792061: step: 1416/530, loss: 0.15718698501586914
2023-01-23 00:43:51.918464: step: 1420/530, loss: 0.34256047010421753
2023-01-23 00:43:53.008698: step: 1424/530, loss: 0.013786209747195244
2023-01-23 00:43:54.118004: step: 1428/530, loss: 0.04166831821203232
2023-01-23 00:43:55.240397: step: 1432/530, loss: 0.02809758111834526
2023-01-23 00:43:56.349243: step: 1436/530, loss: 0.054114725440740585
2023-01-23 00:43:57.447945: step: 1440/530, loss: 0.1906147599220276
2023-01-23 00:43:58.597608: step: 1444/530, loss: 0.01645221747457981
2023-01-23 00:43:59.704371: step: 1448/530, loss: 0.26801052689552307
2023-01-23 00:44:00.800199: step: 1452/530, loss: 0.1848854124546051
2023-01-23 00:44:01.906831: step: 1456/530, loss: 0.04668988287448883
2023-01-23 00:44:03.001607: step: 1460/530, loss: 0.05898289754986763
2023-01-23 00:44:04.079436: step: 1464/530, loss: 0.03276043012738228
2023-01-23 00:44:05.192833: step: 1468/530, loss: 0.12012281268835068
2023-01-23 00:44:06.293633: step: 1472/530, loss: 0.20264868438243866
2023-01-23 00:44:07.397397: step: 1476/530, loss: 0.08479490131139755
2023-01-23 00:44:08.487293: step: 1480/530, loss: 0.12261982262134552
2023-01-23 00:44:09.571771: step: 1484/530, loss: 0.04406576231122017
2023-01-23 00:44:10.672628: step: 1488/530, loss: 0.18016672134399414
2023-01-23 00:44:11.788571: step: 1492/530, loss: 0.01678161695599556
2023-01-23 00:44:12.904939: step: 1496/530, loss: 0.1961621344089508
2023-01-23 00:44:14.014727: step: 1500/530, loss: 0.03058633953332901
2023-01-23 00:44:15.136604: step: 1504/530, loss: 0.026283692568540573
2023-01-23 00:44:16.249705: step: 1508/530, loss: 1.1503907442092896
2023-01-23 00:44:17.341339: step: 1512/530, loss: 0.13508710265159607
2023-01-23 00:44:18.434757: step: 1516/530, loss: 0.09917883574962616
2023-01-23 00:44:19.574358: step: 1520/530, loss: 0.16245366632938385
2023-01-23 00:44:20.679357: step: 1524/530, loss: 0.33379992842674255
2023-01-23 00:44:21.766088: step: 1528/530, loss: 0.07469645142555237
2023-01-23 00:44:22.896665: step: 1532/530, loss: 0.4811992347240448
2023-01-23 00:44:24.003570: step: 1536/530, loss: 0.6457498669624329
2023-01-23 00:44:25.106069: step: 1540/530, loss: 0.05424566566944122
2023-01-23 00:44:26.216862: step: 1544/530, loss: 0.15637606382369995
2023-01-23 00:44:27.328204: step: 1548/530, loss: 0.1795998215675354
2023-01-23 00:44:28.435866: step: 1552/530, loss: 0.018937159329652786
2023-01-23 00:44:29.544357: step: 1556/530, loss: 0.20717038214206696
2023-01-23 00:44:30.680107: step: 1560/530, loss: 0.2970763146877289
2023-01-23 00:44:31.797422: step: 1564/530, loss: 0.017335079610347748
2023-01-23 00:44:32.925857: step: 1568/530, loss: 0.034961700439453125
2023-01-23 00:44:34.036597: step: 1572/530, loss: 0.1570838987827301
2023-01-23 00:44:35.124483: step: 1576/530, loss: 0.19413965940475464
2023-01-23 00:44:36.237913: step: 1580/530, loss: 0.04839807003736496
2023-01-23 00:44:37.333080: step: 1584/530, loss: 0.015035724267363548
2023-01-23 00:44:38.438378: step: 1588/530, loss: 0.10891500115394592
2023-01-23 00:44:39.587242: step: 1592/530, loss: 0.15524645149707794
2023-01-23 00:44:40.680005: step: 1596/530, loss: 0.13787975907325745
2023-01-23 00:44:41.821135: step: 1600/530, loss: 0.016784286126494408
2023-01-23 00:44:42.930923: step: 1604/530, loss: 0.761996328830719
2023-01-23 00:44:44.043609: step: 1608/530, loss: 0.2046799659729004
2023-01-23 00:44:45.141285: step: 1612/530, loss: 0.08629155158996582
2023-01-23 00:44:46.262934: step: 1616/530, loss: 0.02428760752081871
2023-01-23 00:44:47.355526: step: 1620/530, loss: 0.15176203846931458
2023-01-23 00:44:48.475831: step: 1624/530, loss: 0.08319902420043945
2023-01-23 00:44:49.583486: step: 1628/530, loss: 0.15911245346069336
2023-01-23 00:44:50.684361: step: 1632/530, loss: 0.1149345338344574
2023-01-23 00:44:51.769423: step: 1636/530, loss: 0.10317926853895187
2023-01-23 00:44:52.892368: step: 1640/530, loss: 0.10749483108520508
2023-01-23 00:44:54.044442: step: 1644/530, loss: 0.2425212860107422
2023-01-23 00:44:55.158592: step: 1648/530, loss: 0.13477811217308044
2023-01-23 00:44:56.268404: step: 1652/530, loss: 0.08036184310913086
2023-01-23 00:44:57.384107: step: 1656/530, loss: 0.34441354870796204
2023-01-23 00:44:58.503510: step: 1660/530, loss: 0.05651536211371422
2023-01-23 00:44:59.622771: step: 1664/530, loss: 0.07763798534870148
2023-01-23 00:45:00.764084: step: 1668/530, loss: 0.25647610425949097
2023-01-23 00:45:01.879929: step: 1672/530, loss: 0.792915940284729
2023-01-23 00:45:02.994617: step: 1676/530, loss: 0.01355056744068861
2023-01-23 00:45:04.096558: step: 1680/530, loss: 0.059019140899181366
2023-01-23 00:45:05.216151: step: 1684/530, loss: 0.06971187889575958
2023-01-23 00:45:06.326855: step: 1688/530, loss: 0.042878054082393646
2023-01-23 00:45:07.411938: step: 1692/530, loss: 0.1897238790988922
2023-01-23 00:45:08.541747: step: 1696/530, loss: 0.14532537758350372
2023-01-23 00:45:09.647538: step: 1700/530, loss: 0.05813112482428551
2023-01-23 00:45:10.755137: step: 1704/530, loss: 0.043309591710567474
2023-01-23 00:45:11.873428: step: 1708/530, loss: 0.251463383436203
2023-01-23 00:45:12.964892: step: 1712/530, loss: 0.11341853439807892
2023-01-23 00:45:14.073475: step: 1716/530, loss: 0.3857729732990265
2023-01-23 00:45:15.193341: step: 1720/530, loss: 0.059373639523983
2023-01-23 00:45:16.278347: step: 1724/530, loss: 0.1369960755109787
2023-01-23 00:45:17.371341: step: 1728/530, loss: 0.15533065795898438
2023-01-23 00:45:18.494955: step: 1732/530, loss: 0.10133242607116699
2023-01-23 00:45:19.594512: step: 1736/530, loss: 0.009392976760864258
2023-01-23 00:45:20.717159: step: 1740/530, loss: 0.15127259492874146
2023-01-23 00:45:21.819980: step: 1744/530, loss: 0.40107449889183044
2023-01-23 00:45:22.937319: step: 1748/530, loss: 0.253089964389801
2023-01-23 00:45:24.037523: step: 1752/530, loss: 0.13640379905700684
2023-01-23 00:45:25.119751: step: 1756/530, loss: 0.26185142993927
2023-01-23 00:45:26.236463: step: 1760/530, loss: 0.12110863626003265
2023-01-23 00:45:27.322315: step: 1764/530, loss: 0.14644603431224823
2023-01-23 00:45:28.426144: step: 1768/530, loss: 0.03412375599145889
2023-01-23 00:45:29.539733: step: 1772/530, loss: 0.14674320816993713
2023-01-23 00:45:30.638809: step: 1776/530, loss: 0.03385672718286514
2023-01-23 00:45:31.729009: step: 1780/530, loss: 0.027505040168762207
2023-01-23 00:45:32.811074: step: 1784/530, loss: 1.453717589378357
2023-01-23 00:45:33.934469: step: 1788/530, loss: 0.0479624941945076
2023-01-23 00:45:35.062596: step: 1792/530, loss: 0.08169708400964737
2023-01-23 00:45:36.198959: step: 1796/530, loss: 0.1136348694562912
2023-01-23 00:45:37.296969: step: 1800/530, loss: 0.105889230966568
2023-01-23 00:45:38.402594: step: 1804/530, loss: 0.12311048805713654
2023-01-23 00:45:39.502419: step: 1808/530, loss: 0.3427059054374695
2023-01-23 00:45:40.603351: step: 1812/530, loss: 0.24736528098583221
2023-01-23 00:45:41.692652: step: 1816/530, loss: 0.06742402166128159
2023-01-23 00:45:42.775897: step: 1820/530, loss: 0.19215498864650726
2023-01-23 00:45:43.874723: step: 1824/530, loss: 0.2773607075214386
2023-01-23 00:45:44.974217: step: 1828/530, loss: 0.007732868194580078
2023-01-23 00:45:46.035818: step: 1832/530, loss: 0.05819902569055557
2023-01-23 00:45:47.132875: step: 1836/530, loss: 0.021595144644379616
2023-01-23 00:45:48.242352: step: 1840/530, loss: 0.0987127274274826
2023-01-23 00:45:49.369472: step: 1844/530, loss: 0.03133106231689453
2023-01-23 00:45:50.502153: step: 1848/530, loss: 0.14067693054676056
2023-01-23 00:45:51.604964: step: 1852/530, loss: 0.03854823112487793
2023-01-23 00:45:52.726761: step: 1856/530, loss: 0.46442943811416626
2023-01-23 00:45:53.850237: step: 1860/530, loss: 0.11144295334815979
2023-01-23 00:45:54.945629: step: 1864/530, loss: 0.0530390739440918
2023-01-23 00:45:56.064090: step: 1868/530, loss: 0.25548774003982544
2023-01-23 00:45:57.145722: step: 1872/530, loss: 0.04158220440149307
2023-01-23 00:45:58.244391: step: 1876/530, loss: 0.19178669154644012
2023-01-23 00:45:59.338365: step: 1880/530, loss: 0.08530235290527344
2023-01-23 00:46:00.448223: step: 1884/530, loss: 0.08339400589466095
2023-01-23 00:46:01.554352: step: 1888/530, loss: 0.15072917938232422
2023-01-23 00:46:02.643080: step: 1892/530, loss: 0.1369525045156479
2023-01-23 00:46:03.791363: step: 1896/530, loss: 0.10736475884914398
2023-01-23 00:46:04.870829: step: 1900/530, loss: 1.0873714685440063
2023-01-23 00:46:05.969089: step: 1904/530, loss: 0.21266737580299377
2023-01-23 00:46:07.087099: step: 1908/530, loss: 0.11113186180591583
2023-01-23 00:46:08.202389: step: 1912/530, loss: 0.4375871419906616
2023-01-23 00:46:09.312927: step: 1916/530, loss: 0.06430625915527344
2023-01-23 00:46:10.426098: step: 1920/530, loss: 0.17605695128440857
2023-01-23 00:46:11.572317: step: 1924/530, loss: 0.11253967881202698
2023-01-23 00:46:12.675509: step: 1928/530, loss: 0.4085157811641693
2023-01-23 00:46:13.789426: step: 1932/530, loss: 0.12084998935461044
2023-01-23 00:46:14.899116: step: 1936/530, loss: 0.0790262222290039
2023-01-23 00:46:16.006747: step: 1940/530, loss: 0.12296628952026367
2023-01-23 00:46:17.138963: step: 1944/530, loss: 0.1135474145412445
2023-01-23 00:46:18.226525: step: 1948/530, loss: 0.030989982187747955
2023-01-23 00:46:19.321645: step: 1952/530, loss: 0.08686414361000061
2023-01-23 00:46:20.414803: step: 1956/530, loss: 0.3712020814418793
2023-01-23 00:46:21.559398: step: 1960/530, loss: 0.15691861510276794
2023-01-23 00:46:22.684028: step: 1964/530, loss: 0.0353451743721962
2023-01-23 00:46:23.803579: step: 1968/530, loss: 0.01219949685037136
2023-01-23 00:46:24.926336: step: 1972/530, loss: 0.07300257682800293
2023-01-23 00:46:26.028128: step: 1976/530, loss: 0.7963172793388367
2023-01-23 00:46:27.138976: step: 1980/530, loss: 0.014382028952240944
2023-01-23 00:46:28.249228: step: 1984/530, loss: 0.011725043877959251
2023-01-23 00:46:29.383195: step: 1988/530, loss: 0.9076177477836609
2023-01-23 00:46:30.487852: step: 1992/530, loss: 0.43448925018310547
2023-01-23 00:46:31.646343: step: 1996/530, loss: 0.13645966351032257
2023-01-23 00:46:32.738023: step: 2000/530, loss: 0.1092628538608551
2023-01-23 00:46:33.844256: step: 2004/530, loss: 0.05595436319708824
2023-01-23 00:46:34.936209: step: 2008/530, loss: 0.011530399322509766
2023-01-23 00:46:36.047189: step: 2012/530, loss: 0.38748282194137573
2023-01-23 00:46:37.147808: step: 2016/530, loss: 0.07710695266723633
2023-01-23 00:46:38.270777: step: 2020/530, loss: 0.1639409065246582
2023-01-23 00:46:39.391430: step: 2024/530, loss: 0.06237039342522621
2023-01-23 00:46:40.534599: step: 2028/530, loss: 0.09340152144432068
2023-01-23 00:46:41.685926: step: 2032/530, loss: 0.034457016736269
2023-01-23 00:46:42.797894: step: 2036/530, loss: 0.09790392220020294
2023-01-23 00:46:43.889005: step: 2040/530, loss: 0.32078075408935547
2023-01-23 00:46:45.000786: step: 2044/530, loss: 0.09958477318286896
2023-01-23 00:46:46.117746: step: 2048/530, loss: 0.0667843222618103
2023-01-23 00:46:47.220352: step: 2052/530, loss: 0.13015519082546234
2023-01-23 00:46:48.333539: step: 2056/530, loss: 0.1083078384399414
2023-01-23 00:46:49.447224: step: 2060/530, loss: 0.08503742516040802
2023-01-23 00:46:50.580326: step: 2064/530, loss: 1.3333532810211182
2023-01-23 00:46:51.688208: step: 2068/530, loss: 0.17610615491867065
2023-01-23 00:46:52.808947: step: 2072/530, loss: 0.23218633234500885
2023-01-23 00:46:53.897817: step: 2076/530, loss: 0.04601392522454262
2023-01-23 00:46:55.001151: step: 2080/530, loss: 0.10227089375257492
2023-01-23 00:46:56.091575: step: 2084/530, loss: 0.02254486083984375
2023-01-23 00:46:57.180341: step: 2088/530, loss: 0.06414642184972763
2023-01-23 00:46:58.327373: step: 2092/530, loss: 0.11543788760900497
2023-01-23 00:46:59.406662: step: 2096/530, loss: 0.13644686341285706
2023-01-23 00:47:00.493067: step: 2100/530, loss: 0.022280026227235794
2023-01-23 00:47:01.585020: step: 2104/530, loss: 0.055542588233947754
2023-01-23 00:47:02.687053: step: 2108/530, loss: 0.10805568844079971
2023-01-23 00:47:03.773085: step: 2112/530, loss: 0.17468424141407013
2023-01-23 00:47:04.854458: step: 2116/530, loss: 0.05167236179113388
2023-01-23 00:47:05.945753: step: 2120/530, loss: 0.09521299600601196
==================================================
Loss: 0.157
--------------------
Dev: {'event': {'p': 0.6466512702078522, 'r': 0.7456724367509987, 'f1': 0.6926406926406927}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Test: {'event': {'p': 0.6762148337595908, 'r': 0.7703962703962703, 'f1': 0.7202397166984473}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Chinese: {'event': {'p': 0.5797101449275363, 'r': 0.7407407407407407, 'f1': 0.6504065040650405}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Korean: {'event': {'p': 0.6862745098039216, 'r': 0.5555555555555556, 'f1': 0.6140350877192983}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Russian: {'event': {'p': 0.46153846153846156, 'r': 0.5, 'f1': 0.48000000000000004}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
New best korean model...
New best russian model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.5708622398414271, 'r': 0.7669773635153129, 'f1': 0.6545454545454545}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Eng Test for Chinese: {'event': {'p': 0.6044052863436123, 'r': 0.7995337995337995, 'f1': 0.6884094330155545}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Sample Chinese: {'event': {'p': 0.6578947368421053, 'r': 0.9259259259259259, 'f1': 0.7692307692307692}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6466512702078522, 'r': 0.7456724367509987, 'f1': 0.6926406926406927}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Eng Test for Korean: {'event': {'p': 0.6762148337595908, 'r': 0.7703962703962703, 'f1': 0.7202397166984473}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Sample Korean: {'event': {'p': 0.6862745098039216, 'r': 0.5555555555555556, 'f1': 0.6140350877192983}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
--------------------
Eng Dev for Russian: {'event': {'p': 0.6466512702078522, 'r': 0.7456724367509987, 'f1': 0.6926406926406927}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Eng Test for Russian: {'event': {'p': 0.6762148337595908, 'r': 0.7703962703962703, 'f1': 0.7202397166984473}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Sample Russian: {'event': {'p': 0.46153846153846156, 'r': 0.5, 'f1': 0.48000000000000004}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
******************************
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 00:47:53.951569: step: 4/530, loss: 0.11911869049072266
2023-01-23 00:47:55.047019: step: 8/530, loss: 0.05594654381275177
2023-01-23 00:47:56.150509: step: 12/530, loss: 0.06005992740392685
2023-01-23 00:47:57.310077: step: 16/530, loss: 0.10222244262695312
2023-01-23 00:47:58.395003: step: 20/530, loss: 0.03707914426922798
2023-01-23 00:47:59.484209: step: 24/530, loss: 0.3849490284919739
2023-01-23 00:48:00.589546: step: 28/530, loss: 0.0986148864030838
2023-01-23 00:48:01.676144: step: 32/530, loss: 0.017137527465820312
2023-01-23 00:48:02.770964: step: 36/530, loss: 0.04865570366382599
2023-01-23 00:48:03.858284: step: 40/530, loss: 0.06709442287683487
2023-01-23 00:48:04.974249: step: 44/530, loss: 0.029865264892578125
2023-01-23 00:48:06.129556: step: 48/530, loss: 0.03145141527056694
2023-01-23 00:48:07.261569: step: 52/530, loss: 0.06527357548475266
2023-01-23 00:48:08.358613: step: 56/530, loss: 0.007344889920204878
2023-01-23 00:48:09.499966: step: 60/530, loss: 0.08568783104419708
2023-01-23 00:48:10.617284: step: 64/530, loss: 0.06358623504638672
2023-01-23 00:48:11.724657: step: 68/530, loss: 0.010941028594970703
2023-01-23 00:48:12.822259: step: 72/530, loss: 0.10358834266662598
2023-01-23 00:48:13.937526: step: 76/530, loss: 0.03071575053036213
2023-01-23 00:48:15.044228: step: 80/530, loss: 0.06349430233240128
2023-01-23 00:48:16.212356: step: 84/530, loss: 0.049593113362789154
2023-01-23 00:48:17.291559: step: 88/530, loss: 0.13640671968460083
2023-01-23 00:48:18.389956: step: 92/530, loss: 0.09202051162719727
2023-01-23 00:48:19.505909: step: 96/530, loss: 0.11000747978687286
2023-01-23 00:48:20.614640: step: 100/530, loss: 0.0786200538277626
2023-01-23 00:48:21.727337: step: 104/530, loss: 0.21903228759765625
2023-01-23 00:48:22.838713: step: 108/530, loss: 0.08303675800561905
2023-01-23 00:48:23.925798: step: 112/530, loss: 0.07887706905603409
2023-01-23 00:48:25.022085: step: 116/530, loss: 0.06502733379602432
2023-01-23 00:48:26.091381: step: 120/530, loss: 0.021123027428984642
2023-01-23 00:48:27.170903: step: 124/530, loss: 0.013583827763795853
2023-01-23 00:48:28.300804: step: 128/530, loss: 0.08342437446117401
2023-01-23 00:48:29.404917: step: 132/530, loss: 0.19991883635520935
2023-01-23 00:48:30.497205: step: 136/530, loss: 0.010261917486786842
2023-01-23 00:48:31.596031: step: 140/530, loss: 0.17521458864212036
2023-01-23 00:48:32.722341: step: 144/530, loss: 0.5597915649414062
2023-01-23 00:48:33.825429: step: 148/530, loss: 0.22418656945228577
2023-01-23 00:48:34.926067: step: 152/530, loss: 0.027275515720248222
2023-01-23 00:48:36.028373: step: 156/530, loss: 0.03014860302209854
2023-01-23 00:48:37.163042: step: 160/530, loss: 0.0989227294921875
2023-01-23 00:48:38.258658: step: 164/530, loss: 0.24144801497459412
2023-01-23 00:48:39.370392: step: 168/530, loss: 0.6401756405830383
2023-01-23 00:48:40.471297: step: 172/530, loss: 0.15292863547801971
2023-01-23 00:48:41.571251: step: 176/530, loss: 0.05735521391034126
2023-01-23 00:48:42.678269: step: 180/530, loss: 0.11661558598279953
2023-01-23 00:48:43.805306: step: 184/530, loss: 0.102117158472538
2023-01-23 00:48:44.917112: step: 188/530, loss: 0.0296649057418108
2023-01-23 00:48:46.028437: step: 192/530, loss: 0.08524150401353836
2023-01-23 00:48:47.110697: step: 196/530, loss: 0.07382392883300781
2023-01-23 00:48:48.193874: step: 200/530, loss: 0.02957477793097496
2023-01-23 00:48:49.330210: step: 204/530, loss: 0.07235565036535263
2023-01-23 00:48:50.411165: step: 208/530, loss: 0.07224207371473312
2023-01-23 00:48:51.532386: step: 212/530, loss: 0.0077370647341012955
2023-01-23 00:48:52.621965: step: 216/530, loss: 0.05593404918909073
2023-01-23 00:48:53.717147: step: 220/530, loss: 0.3368190824985504
2023-01-23 00:48:54.850451: step: 224/530, loss: 0.054932307451963425
2023-01-23 00:48:55.942577: step: 228/530, loss: 0.05258283391594887
2023-01-23 00:48:57.049737: step: 232/530, loss: 0.8753765821456909
2023-01-23 00:48:58.178060: step: 236/530, loss: 0.2955070734024048
2023-01-23 00:48:59.262615: step: 240/530, loss: 0.024929236620664597
2023-01-23 00:49:00.376532: step: 244/530, loss: 0.027506638318300247
2023-01-23 00:49:01.471447: step: 248/530, loss: 0.2574559152126312
2023-01-23 00:49:02.589215: step: 252/530, loss: 0.07435693591833115
2023-01-23 00:49:03.697236: step: 256/530, loss: 0.14356708526611328
2023-01-23 00:49:04.819747: step: 260/530, loss: 0.024345088750123978
2023-01-23 00:49:05.918464: step: 264/530, loss: 0.08252649754285812
2023-01-23 00:49:07.030286: step: 268/530, loss: 0.05271584540605545
2023-01-23 00:49:08.166984: step: 272/530, loss: 0.05398616939783096
2023-01-23 00:49:09.267301: step: 276/530, loss: 0.03599701076745987
2023-01-23 00:49:10.355192: step: 280/530, loss: 0.30442380905151367
2023-01-23 00:49:11.435538: step: 284/530, loss: 0.012623501010239124
2023-01-23 00:49:12.529513: step: 288/530, loss: 0.04532194137573242
2023-01-23 00:49:13.666564: step: 292/530, loss: 0.13103848695755005
2023-01-23 00:49:14.782177: step: 296/530, loss: 0.13387545943260193
2023-01-23 00:49:15.899287: step: 300/530, loss: 0.13475675880908966
2023-01-23 00:49:17.023782: step: 304/530, loss: 0.13041897118091583
2023-01-23 00:49:18.123407: step: 308/530, loss: 0.024891089648008347
2023-01-23 00:49:19.228773: step: 312/530, loss: 0.06801509857177734
2023-01-23 00:49:20.324832: step: 316/530, loss: 0.06932802498340607
2023-01-23 00:49:21.420244: step: 320/530, loss: 0.13690677285194397
2023-01-23 00:49:22.499314: step: 324/530, loss: 0.055600740015506744
2023-01-23 00:49:23.589717: step: 328/530, loss: 0.11437202244997025
2023-01-23 00:49:24.692734: step: 332/530, loss: 0.02527599409222603
2023-01-23 00:49:25.796565: step: 336/530, loss: 0.1801416277885437
2023-01-23 00:49:26.926728: step: 340/530, loss: 0.1253347396850586
2023-01-23 00:49:28.038507: step: 344/530, loss: 0.14391641318798065
2023-01-23 00:49:29.145785: step: 348/530, loss: 0.4257441461086273
2023-01-23 00:49:30.261509: step: 352/530, loss: 0.02731156349182129
2023-01-23 00:49:31.403423: step: 356/530, loss: 0.09722795337438583
2023-01-23 00:49:32.499482: step: 360/530, loss: 0.08871941268444061
2023-01-23 00:49:33.607904: step: 364/530, loss: 0.0026256563141942024
2023-01-23 00:49:34.720059: step: 368/530, loss: 0.16361045837402344
2023-01-23 00:49:35.821863: step: 372/530, loss: 0.06298217922449112
2023-01-23 00:49:36.948499: step: 376/530, loss: 0.07270222157239914
2023-01-23 00:49:38.041175: step: 380/530, loss: 0.06875000149011612
2023-01-23 00:49:39.130033: step: 384/530, loss: 0.06463241577148438
2023-01-23 00:49:40.223451: step: 388/530, loss: 0.14835090935230255
2023-01-23 00:49:41.311074: step: 392/530, loss: 0.3185749053955078
2023-01-23 00:49:42.412056: step: 396/530, loss: 0.8417788147926331
2023-01-23 00:49:43.553575: step: 400/530, loss: 0.19428329169750214
2023-01-23 00:49:44.658274: step: 404/530, loss: 0.1736827790737152
2023-01-23 00:49:45.754721: step: 408/530, loss: 0.13287745416164398
2023-01-23 00:49:46.868830: step: 412/530, loss: 0.2966168522834778
2023-01-23 00:49:47.984143: step: 416/530, loss: 0.663040280342102
2023-01-23 00:49:49.105848: step: 420/530, loss: 0.08559150993824005
2023-01-23 00:49:50.218061: step: 424/530, loss: 0.43381378054618835
2023-01-23 00:49:51.325179: step: 428/530, loss: 0.10292968899011612
2023-01-23 00:49:52.427408: step: 432/530, loss: 0.04438028484582901
2023-01-23 00:49:53.518532: step: 436/530, loss: 0.11642227321863174
2023-01-23 00:49:54.633038: step: 440/530, loss: 0.054781340062618256
2023-01-23 00:49:55.770602: step: 444/530, loss: 0.05360608547925949
2023-01-23 00:49:56.840198: step: 448/530, loss: 0.027811909094452858
2023-01-23 00:49:57.948650: step: 452/530, loss: 0.08550529181957245
2023-01-23 00:49:59.061094: step: 456/530, loss: 0.06656856834888458
2023-01-23 00:50:00.190348: step: 460/530, loss: 0.04748420789837837
2023-01-23 00:50:01.324976: step: 464/530, loss: 0.07782869040966034
2023-01-23 00:50:02.461444: step: 468/530, loss: 0.056507352739572525
2023-01-23 00:50:03.578318: step: 472/530, loss: 0.15341129899024963
2023-01-23 00:50:04.682595: step: 476/530, loss: 0.029101181775331497
2023-01-23 00:50:05.815904: step: 480/530, loss: 0.2146543562412262
2023-01-23 00:50:06.966773: step: 484/530, loss: 0.06759872287511826
2023-01-23 00:50:08.118096: step: 488/530, loss: 0.18770703673362732
2023-01-23 00:50:09.209505: step: 492/530, loss: 0.09333138912916183
2023-01-23 00:50:10.343986: step: 496/530, loss: 0.07917661964893341
2023-01-23 00:50:11.527835: step: 500/530, loss: 0.06565704196691513
2023-01-23 00:50:12.626603: step: 504/530, loss: 0.6630858778953552
2023-01-23 00:50:13.772828: step: 508/530, loss: 1.6059333086013794
2023-01-23 00:50:14.888380: step: 512/530, loss: 0.18353310227394104
2023-01-23 00:50:16.003136: step: 516/530, loss: 0.2970350980758667
2023-01-23 00:50:17.101277: step: 520/530, loss: 0.09521408379077911
2023-01-23 00:50:18.197129: step: 524/530, loss: 0.03171906620264053
2023-01-23 00:50:19.284344: step: 528/530, loss: 0.0417880043387413
2023-01-23 00:50:20.393646: step: 532/530, loss: 0.09714994579553604
2023-01-23 00:50:21.517701: step: 536/530, loss: 0.08333511650562286
2023-01-23 00:50:22.623016: step: 540/530, loss: 0.10097970813512802
2023-01-23 00:50:23.745808: step: 544/530, loss: 0.08820643275976181
2023-01-23 00:50:24.852246: step: 548/530, loss: 0.21242770552635193
2023-01-23 00:50:25.938361: step: 552/530, loss: 0.03767795488238335
2023-01-23 00:50:27.033507: step: 556/530, loss: 0.0064598084427416325
2023-01-23 00:50:28.095705: step: 560/530, loss: 0.08491519093513489
2023-01-23 00:50:29.212350: step: 564/530, loss: 0.0958637222647667
2023-01-23 00:50:30.350402: step: 568/530, loss: 0.3100414276123047
2023-01-23 00:50:31.427462: step: 572/530, loss: 0.06438927352428436
2023-01-23 00:50:32.538254: step: 576/530, loss: 0.037790488451719284
2023-01-23 00:50:33.644292: step: 580/530, loss: 0.12114611268043518
2023-01-23 00:50:34.746093: step: 584/530, loss: 0.20157796144485474
2023-01-23 00:50:35.841123: step: 588/530, loss: 0.007942711934447289
2023-01-23 00:50:36.943921: step: 592/530, loss: 0.20363445580005646
2023-01-23 00:50:38.065186: step: 596/530, loss: 0.1639750450849533
2023-01-23 00:50:39.210712: step: 600/530, loss: 0.15326690673828125
2023-01-23 00:50:40.295887: step: 604/530, loss: 0.021233271807432175
2023-01-23 00:50:41.399465: step: 608/530, loss: 0.013071263208985329
2023-01-23 00:50:42.498292: step: 612/530, loss: 0.016934489831328392
2023-01-23 00:50:43.609948: step: 616/530, loss: 0.06845493614673615
2023-01-23 00:50:44.724378: step: 620/530, loss: 0.04945418983697891
2023-01-23 00:50:45.830439: step: 624/530, loss: 0.02663288079202175
2023-01-23 00:50:46.952054: step: 628/530, loss: 0.03731508553028107
2023-01-23 00:50:48.029054: step: 632/530, loss: 0.01670842245221138
2023-01-23 00:50:49.152093: step: 636/530, loss: 0.0053452495485544205
2023-01-23 00:50:50.245362: step: 640/530, loss: 0.07053223252296448
2023-01-23 00:50:51.335209: step: 644/530, loss: 0.05582469701766968
2023-01-23 00:50:52.491820: step: 648/530, loss: 0.07306060940027237
2023-01-23 00:50:53.610086: step: 652/530, loss: 0.39343851804733276
2023-01-23 00:50:54.733668: step: 656/530, loss: 0.17465132474899292
2023-01-23 00:50:55.848360: step: 660/530, loss: 0.10805759578943253
2023-01-23 00:50:56.971479: step: 664/530, loss: 0.12455320358276367
2023-01-23 00:50:58.069110: step: 668/530, loss: 0.07217588275671005
2023-01-23 00:50:59.174364: step: 672/530, loss: 0.12222146987915039
2023-01-23 00:51:00.288317: step: 676/530, loss: 0.012021685019135475
2023-01-23 00:51:01.396836: step: 680/530, loss: 0.08690624684095383
2023-01-23 00:51:02.522478: step: 684/530, loss: 0.01951742172241211
2023-01-23 00:51:03.674588: step: 688/530, loss: 0.28196069598197937
2023-01-23 00:51:04.789582: step: 692/530, loss: 0.07948670536279678
2023-01-23 00:51:05.891627: step: 696/530, loss: 0.07117261737585068
2023-01-23 00:51:07.006560: step: 700/530, loss: 0.20772957801818848
2023-01-23 00:51:08.114688: step: 704/530, loss: 0.025627028197050095
2023-01-23 00:51:09.230177: step: 708/530, loss: 0.09152460098266602
2023-01-23 00:51:10.350567: step: 712/530, loss: 0.041408635675907135
2023-01-23 00:51:11.450057: step: 716/530, loss: 0.14207744598388672
2023-01-23 00:51:12.547484: step: 720/530, loss: 0.11624152213335037
2023-01-23 00:51:13.648629: step: 724/530, loss: 0.12275762856006622
2023-01-23 00:51:14.734839: step: 728/530, loss: 0.18236666917800903
2023-01-23 00:51:15.848409: step: 732/530, loss: 0.2133081555366516
2023-01-23 00:51:16.977474: step: 736/530, loss: 0.09168877452611923
2023-01-23 00:51:18.085587: step: 740/530, loss: 0.1224275603890419
2023-01-23 00:51:19.208116: step: 744/530, loss: 0.028417587280273438
2023-01-23 00:51:20.313297: step: 748/530, loss: 0.021269608289003372
2023-01-23 00:51:21.462156: step: 752/530, loss: 0.013565922155976295
2023-01-23 00:51:22.586985: step: 756/530, loss: 0.1359941065311432
2023-01-23 00:51:23.688633: step: 760/530, loss: 0.10326366126537323
2023-01-23 00:51:24.789226: step: 764/530, loss: 0.034735631197690964
2023-01-23 00:51:25.881745: step: 768/530, loss: 0.053417399525642395
2023-01-23 00:51:26.984473: step: 772/530, loss: 0.10511569678783417
2023-01-23 00:51:28.086465: step: 776/530, loss: 0.06361141055822372
2023-01-23 00:51:29.204377: step: 780/530, loss: 0.11846351623535156
2023-01-23 00:51:30.306672: step: 784/530, loss: 0.04683428257703781
2023-01-23 00:51:31.419837: step: 788/530, loss: 0.03210430219769478
2023-01-23 00:51:32.521736: step: 792/530, loss: 0.01716151274740696
2023-01-23 00:51:33.680707: step: 796/530, loss: 0.08280573040246964
2023-01-23 00:51:34.818831: step: 800/530, loss: 0.2534770965576172
2023-01-23 00:51:35.953058: step: 804/530, loss: 0.09977531433105469
2023-01-23 00:51:37.082321: step: 808/530, loss: 0.09530212730169296
2023-01-23 00:51:38.181027: step: 812/530, loss: 0.07445145398378372
2023-01-23 00:51:39.303488: step: 816/530, loss: 0.266034334897995
2023-01-23 00:51:40.407534: step: 820/530, loss: 0.12444248795509338
2023-01-23 00:51:41.523724: step: 824/530, loss: 0.04329118877649307
2023-01-23 00:51:42.616137: step: 828/530, loss: 0.17458286881446838
2023-01-23 00:51:43.747424: step: 832/530, loss: 0.02772388607263565
2023-01-23 00:51:44.857344: step: 836/530, loss: 0.0205248836427927
2023-01-23 00:51:45.979078: step: 840/530, loss: 0.043944455683231354
2023-01-23 00:51:47.068220: step: 844/530, loss: 0.09574851393699646
2023-01-23 00:51:48.186393: step: 848/530, loss: 0.2966393530368805
2023-01-23 00:51:49.276423: step: 852/530, loss: 0.2695699632167816
2023-01-23 00:51:50.401317: step: 856/530, loss: 0.3184199929237366
2023-01-23 00:51:51.539052: step: 860/530, loss: 0.06449492275714874
2023-01-23 00:51:52.643942: step: 864/530, loss: 0.06269311904907227
2023-01-23 00:51:53.747114: step: 868/530, loss: 0.03121483325958252
2023-01-23 00:51:54.877594: step: 872/530, loss: 0.20634803175926208
2023-01-23 00:51:55.965667: step: 876/530, loss: 0.05591907724738121
2023-01-23 00:51:57.059569: step: 880/530, loss: 0.28548121452331543
2023-01-23 00:51:58.167132: step: 884/530, loss: 0.022234417498111725
2023-01-23 00:51:59.264351: step: 888/530, loss: 0.05248622968792915
2023-01-23 00:52:00.383201: step: 892/530, loss: 0.061526820063591
2023-01-23 00:52:01.475808: step: 896/530, loss: 0.0672922134399414
2023-01-23 00:52:02.570017: step: 900/530, loss: 0.141584113240242
2023-01-23 00:52:03.688332: step: 904/530, loss: 0.02793598175048828
2023-01-23 00:52:04.825441: step: 908/530, loss: 0.06663131713867188
2023-01-23 00:52:05.958685: step: 912/530, loss: 0.03127555921673775
2023-01-23 00:52:07.073678: step: 916/530, loss: 0.01583700068295002
2023-01-23 00:52:08.183869: step: 920/530, loss: 0.68163001537323
2023-01-23 00:52:09.262154: step: 924/530, loss: 0.286430686712265
2023-01-23 00:52:10.391329: step: 928/530, loss: 0.06524877995252609
2023-01-23 00:52:11.518941: step: 932/530, loss: 0.7543874979019165
2023-01-23 00:52:12.610681: step: 936/530, loss: 0.1091286689043045
2023-01-23 00:52:13.722779: step: 940/530, loss: 0.3756675720214844
2023-01-23 00:52:14.785804: step: 944/530, loss: 0.29725971817970276
2023-01-23 00:52:15.910712: step: 948/530, loss: 0.15286321938037872
2023-01-23 00:52:17.044691: step: 952/530, loss: 0.30158179998397827
2023-01-23 00:52:18.125224: step: 956/530, loss: 0.08971910178661346
2023-01-23 00:52:19.225161: step: 960/530, loss: 0.11688976734876633
2023-01-23 00:52:20.338732: step: 964/530, loss: 0.09793853759765625
2023-01-23 00:52:21.472323: step: 968/530, loss: 0.08934803307056427
2023-01-23 00:52:22.579296: step: 972/530, loss: 0.030006790533661842
2023-01-23 00:52:23.694669: step: 976/530, loss: 0.10294562578201294
2023-01-23 00:52:24.808173: step: 980/530, loss: 0.20548266172409058
2023-01-23 00:52:25.917861: step: 984/530, loss: 0.10347537696361542
2023-01-23 00:52:27.011753: step: 988/530, loss: 0.017511939629912376
2023-01-23 00:52:28.103356: step: 992/530, loss: 0.06988143920898438
2023-01-23 00:52:29.223773: step: 996/530, loss: 0.1110302284359932
2023-01-23 00:52:30.308415: step: 1000/530, loss: 0.2685500979423523
2023-01-23 00:52:31.425753: step: 1004/530, loss: 0.18499363958835602
2023-01-23 00:52:32.534775: step: 1008/530, loss: 0.14757689833641052
2023-01-23 00:52:33.666887: step: 1012/530, loss: 0.1732262670993805
2023-01-23 00:52:34.783111: step: 1016/530, loss: 0.17172592878341675
2023-01-23 00:52:35.931617: step: 1020/530, loss: 0.2440611720085144
2023-01-23 00:52:37.043438: step: 1024/530, loss: 0.06054963916540146
2023-01-23 00:52:38.160414: step: 1028/530, loss: 0.27140820026397705
2023-01-23 00:52:39.257859: step: 1032/530, loss: 0.030099868774414062
2023-01-23 00:52:40.365502: step: 1036/530, loss: 0.0944155678153038
2023-01-23 00:52:41.455947: step: 1040/530, loss: 0.18252907693386078
2023-01-23 00:52:42.567073: step: 1044/530, loss: 0.03584995120763779
2023-01-23 00:52:43.682088: step: 1048/530, loss: 0.020482826977968216
2023-01-23 00:52:44.798663: step: 1052/530, loss: 0.02874126471579075
2023-01-23 00:52:45.916175: step: 1056/530, loss: 0.23768381774425507
2023-01-23 00:52:47.063166: step: 1060/530, loss: 0.04036913067102432
2023-01-23 00:52:48.184253: step: 1064/530, loss: 0.3108413815498352
2023-01-23 00:52:49.271124: step: 1068/530, loss: 0.18419581651687622
2023-01-23 00:52:50.401075: step: 1072/530, loss: 0.07675810158252716
2023-01-23 00:52:51.543587: step: 1076/530, loss: 0.15113386511802673
2023-01-23 00:52:52.647295: step: 1080/530, loss: 0.13857269287109375
2023-01-23 00:52:53.796648: step: 1084/530, loss: 0.1990751326084137
2023-01-23 00:52:54.909785: step: 1088/530, loss: 0.0037929534446448088
2023-01-23 00:52:56.038104: step: 1092/530, loss: 0.05229482799768448
2023-01-23 00:52:57.161894: step: 1096/530, loss: 0.11247846484184265
2023-01-23 00:52:58.249609: step: 1100/530, loss: 0.4745456278324127
2023-01-23 00:52:59.350344: step: 1104/530, loss: 0.208216592669487
2023-01-23 00:53:00.451691: step: 1108/530, loss: 0.020977400243282318
2023-01-23 00:53:01.569583: step: 1112/530, loss: 0.036166951060295105
2023-01-23 00:53:02.684042: step: 1116/530, loss: 0.11842823028564453
2023-01-23 00:53:03.818165: step: 1120/530, loss: 0.2346639633178711
2023-01-23 00:53:04.921539: step: 1124/530, loss: 0.06267013400793076
2023-01-23 00:53:06.030183: step: 1128/530, loss: 0.15819235146045685
2023-01-23 00:53:07.125041: step: 1132/530, loss: 0.031134678050875664
2023-01-23 00:53:08.230354: step: 1136/530, loss: 0.03771810606122017
2023-01-23 00:53:09.334864: step: 1140/530, loss: 0.04745866358280182
2023-01-23 00:53:10.434465: step: 1144/530, loss: 0.09044208377599716
2023-01-23 00:53:11.558577: step: 1148/530, loss: 0.11263179779052734
2023-01-23 00:53:12.651585: step: 1152/530, loss: 0.07385406643152237
2023-01-23 00:53:13.750223: step: 1156/530, loss: 0.013094283640384674
2023-01-23 00:53:14.842272: step: 1160/530, loss: 0.02526116371154785
2023-01-23 00:53:15.952351: step: 1164/530, loss: 0.09832410514354706
2023-01-23 00:53:17.068872: step: 1168/530, loss: 0.07032763957977295
2023-01-23 00:53:18.175110: step: 1172/530, loss: 0.02007446251809597
2023-01-23 00:53:19.308304: step: 1176/530, loss: 0.0767943412065506
2023-01-23 00:53:20.458245: step: 1180/530, loss: 0.006288337521255016
2023-01-23 00:53:21.604624: step: 1184/530, loss: 0.040837861597537994
2023-01-23 00:53:22.736253: step: 1188/530, loss: 0.03742246702313423
2023-01-23 00:53:23.840042: step: 1192/530, loss: 0.1444648802280426
2023-01-23 00:53:24.921427: step: 1196/530, loss: 0.019832324236631393
2023-01-23 00:53:26.036070: step: 1200/530, loss: 0.016106033697724342
2023-01-23 00:53:27.165200: step: 1204/530, loss: 0.12079861760139465
2023-01-23 00:53:28.276870: step: 1208/530, loss: 0.08075639605522156
2023-01-23 00:53:29.403530: step: 1212/530, loss: 0.09436998516321182
2023-01-23 00:53:30.507636: step: 1216/530, loss: 0.08193521201610565
2023-01-23 00:53:31.604101: step: 1220/530, loss: 0.024799633771181107
2023-01-23 00:53:32.727856: step: 1224/530, loss: 0.33790645003318787
2023-01-23 00:53:33.832519: step: 1228/530, loss: 0.020997188985347748
2023-01-23 00:53:34.950263: step: 1232/530, loss: 0.0569583922624588
2023-01-23 00:53:36.050803: step: 1236/530, loss: 0.14552536606788635
2023-01-23 00:53:37.149658: step: 1240/530, loss: 0.112663134932518
2023-01-23 00:53:38.259871: step: 1244/530, loss: 0.10771408677101135
2023-01-23 00:53:39.331276: step: 1248/530, loss: 0.2917008101940155
2023-01-23 00:53:40.462527: step: 1252/530, loss: 0.024138927459716797
2023-01-23 00:53:41.554186: step: 1256/530, loss: 0.07604708522558212
2023-01-23 00:53:42.641347: step: 1260/530, loss: 0.10218968987464905
2023-01-23 00:53:43.759565: step: 1264/530, loss: 0.1727636605501175
2023-01-23 00:53:44.855719: step: 1268/530, loss: 0.08448926359415054
2023-01-23 00:53:45.973767: step: 1272/530, loss: 0.1318327635526657
2023-01-23 00:53:47.062237: step: 1276/530, loss: 0.001016855239868164
2023-01-23 00:53:48.156593: step: 1280/530, loss: 0.041588593274354935
2023-01-23 00:53:49.239599: step: 1284/530, loss: 0.06368903815746307
2023-01-23 00:53:50.345478: step: 1288/530, loss: 0.02614569664001465
2023-01-23 00:53:51.450569: step: 1292/530, loss: 0.12808971107006073
2023-01-23 00:53:52.571871: step: 1296/530, loss: 0.15766791999340057
2023-01-23 00:53:53.696295: step: 1300/530, loss: 0.3422592282295227
2023-01-23 00:53:54.815336: step: 1304/530, loss: 0.11430913209915161
2023-01-23 00:53:55.915411: step: 1308/530, loss: 0.18840666115283966
2023-01-23 00:53:57.014202: step: 1312/530, loss: 0.017795372754335403
2023-01-23 00:53:58.138673: step: 1316/530, loss: 0.049549005925655365
2023-01-23 00:53:59.244704: step: 1320/530, loss: 0.2594464421272278
2023-01-23 00:54:00.352970: step: 1324/530, loss: 0.3087472915649414
2023-01-23 00:54:01.454542: step: 1328/530, loss: 0.009452497586607933
2023-01-23 00:54:02.569042: step: 1332/530, loss: 0.09292864799499512
2023-01-23 00:54:03.704987: step: 1336/530, loss: 0.1023896262049675
2023-01-23 00:54:04.821942: step: 1340/530, loss: 0.11262637376785278
2023-01-23 00:54:05.921388: step: 1344/530, loss: 0.10290107876062393
2023-01-23 00:54:07.043016: step: 1348/530, loss: 0.019435930997133255
2023-01-23 00:54:08.158355: step: 1352/530, loss: 0.007319331169128418
2023-01-23 00:54:09.280949: step: 1356/530, loss: 0.10708752274513245
2023-01-23 00:54:10.381690: step: 1360/530, loss: 0.13009414076805115
2023-01-23 00:54:11.465704: step: 1364/530, loss: 0.025205519050359726
2023-01-23 00:54:12.596374: step: 1368/530, loss: 0.0754825621843338
2023-01-23 00:54:13.695913: step: 1372/530, loss: 0.11432480812072754
2023-01-23 00:54:14.782812: step: 1376/530, loss: 0.05013017728924751
2023-01-23 00:54:15.894599: step: 1380/530, loss: 0.004275331273674965
2023-01-23 00:54:16.989940: step: 1384/530, loss: 0.7562000155448914
2023-01-23 00:54:18.113462: step: 1388/530, loss: 0.03598523139953613
2023-01-23 00:54:19.218012: step: 1392/530, loss: 0.20649272203445435
2023-01-23 00:54:20.316395: step: 1396/530, loss: 0.25895899534225464
2023-01-23 00:54:21.409663: step: 1400/530, loss: 0.13337011635303497
2023-01-23 00:54:22.526290: step: 1404/530, loss: 0.041832830756902695
2023-01-23 00:54:23.654900: step: 1408/530, loss: 0.05252399295568466
2023-01-23 00:54:24.783476: step: 1412/530, loss: 0.39361023902893066
2023-01-23 00:54:25.889564: step: 1416/530, loss: 0.17604151368141174
2023-01-23 00:54:26.983174: step: 1420/530, loss: 0.015737246721982956
2023-01-23 00:54:28.097044: step: 1424/530, loss: 0.10950168967247009
2023-01-23 00:54:29.218075: step: 1428/530, loss: 0.014858150854706764
2023-01-23 00:54:30.296925: step: 1432/530, loss: 0.02591390535235405
2023-01-23 00:54:31.409987: step: 1436/530, loss: 0.08015008270740509
2023-01-23 00:54:32.516695: step: 1440/530, loss: 0.07703669369220734
2023-01-23 00:54:33.671765: step: 1444/530, loss: 0.048880863934755325
2023-01-23 00:54:34.760384: step: 1448/530, loss: 0.07770642638206482
2023-01-23 00:54:35.871799: step: 1452/530, loss: 0.03424430266022682
2023-01-23 00:54:36.954900: step: 1456/530, loss: 0.013797139748930931
2023-01-23 00:54:38.091780: step: 1460/530, loss: 0.11644693464040756
2023-01-23 00:54:39.186836: step: 1464/530, loss: 0.028011895716190338
2023-01-23 00:54:40.280100: step: 1468/530, loss: 0.04797234386205673
2023-01-23 00:54:41.385878: step: 1472/530, loss: 0.11523942649364471
2023-01-23 00:54:42.526722: step: 1476/530, loss: 0.09139986336231232
2023-01-23 00:54:43.642572: step: 1480/530, loss: 0.20309686660766602
2023-01-23 00:54:44.758246: step: 1484/530, loss: 0.023095274344086647
2023-01-23 00:54:45.848627: step: 1488/530, loss: 0.047832585871219635
2023-01-23 00:54:46.970021: step: 1492/530, loss: 0.12425823509693146
2023-01-23 00:54:48.074857: step: 1496/530, loss: 0.010180855169892311
2023-01-23 00:54:49.173954: step: 1500/530, loss: 0.07949332892894745
2023-01-23 00:54:50.295169: step: 1504/530, loss: 0.04498882219195366
2023-01-23 00:54:51.468806: step: 1508/530, loss: 0.13184386491775513
2023-01-23 00:54:52.578095: step: 1512/530, loss: 0.09427204728126526
2023-01-23 00:54:53.692521: step: 1516/530, loss: 0.25841933488845825
2023-01-23 00:54:54.792336: step: 1520/530, loss: 0.016600705683231354
2023-01-23 00:54:55.938086: step: 1524/530, loss: 0.3405153453350067
2023-01-23 00:54:57.036965: step: 1528/530, loss: 0.06438972055912018
2023-01-23 00:54:58.140161: step: 1532/530, loss: 0.4356212615966797
2023-01-23 00:54:59.225025: step: 1536/530, loss: 0.5848147869110107
2023-01-23 00:55:00.316515: step: 1540/530, loss: 0.05305233225226402
2023-01-23 00:55:01.434867: step: 1544/530, loss: 0.043853759765625
2023-01-23 00:55:02.548847: step: 1548/530, loss: 0.08651427924633026
2023-01-23 00:55:03.652019: step: 1552/530, loss: 0.05195026472210884
2023-01-23 00:55:04.739309: step: 1556/530, loss: 0.3971121907234192
2023-01-23 00:55:05.850313: step: 1560/530, loss: 0.02738790586590767
2023-01-23 00:55:06.936561: step: 1564/530, loss: 0.05520348623394966
2023-01-23 00:55:08.039151: step: 1568/530, loss: 0.03425588458776474
2023-01-23 00:55:09.142986: step: 1572/530, loss: 0.008135700598359108
2023-01-23 00:55:10.232304: step: 1576/530, loss: 0.06154661253094673
2023-01-23 00:55:11.331788: step: 1580/530, loss: 0.09872995316982269
2023-01-23 00:55:12.472281: step: 1584/530, loss: 0.041140079498291016
2023-01-23 00:55:13.568177: step: 1588/530, loss: 0.19032764434814453
2023-01-23 00:55:14.684091: step: 1592/530, loss: 0.19962787628173828
2023-01-23 00:55:15.796606: step: 1596/530, loss: 0.09546937793493271
2023-01-23 00:55:16.926937: step: 1600/530, loss: 0.2381877899169922
2023-01-23 00:55:18.034598: step: 1604/530, loss: 0.04606493562459946
2023-01-23 00:55:19.149680: step: 1608/530, loss: 0.02561226114630699
2023-01-23 00:55:20.277973: step: 1612/530, loss: 0.04352283477783203
2023-01-23 00:55:21.419516: step: 1616/530, loss: 0.04283123090863228
2023-01-23 00:55:22.509294: step: 1620/530, loss: 0.09044961631298065
2023-01-23 00:55:23.607333: step: 1624/530, loss: 0.3653440475463867
2023-01-23 00:55:24.710984: step: 1628/530, loss: 0.06839476525783539
2023-01-23 00:55:25.798121: step: 1632/530, loss: 0.11999340355396271
2023-01-23 00:55:26.904299: step: 1636/530, loss: 0.032875727862119675
2023-01-23 00:55:27.990502: step: 1640/530, loss: 0.003103208728134632
2023-01-23 00:55:29.081266: step: 1644/530, loss: 0.02510986290872097
2023-01-23 00:55:30.199973: step: 1648/530, loss: 0.12627089023590088
2023-01-23 00:55:31.286390: step: 1652/530, loss: 0.11043024063110352
2023-01-23 00:55:32.396443: step: 1656/530, loss: 0.13902896642684937
2023-01-23 00:55:33.509563: step: 1660/530, loss: 0.19835329055786133
2023-01-23 00:55:34.600594: step: 1664/530, loss: 0.03847789764404297
2023-01-23 00:55:35.740036: step: 1668/530, loss: 0.03056039661169052
2023-01-23 00:55:36.863390: step: 1672/530, loss: 0.09128780663013458
2023-01-23 00:55:37.965853: step: 1676/530, loss: 0.0858302116394043
2023-01-23 00:55:39.092075: step: 1680/530, loss: 0.05166025459766388
2023-01-23 00:55:40.183193: step: 1684/530, loss: 0.1438257098197937
2023-01-23 00:55:41.259449: step: 1688/530, loss: 0.08575949817895889
2023-01-23 00:55:42.361266: step: 1692/530, loss: 0.04448442533612251
2023-01-23 00:55:43.501202: step: 1696/530, loss: 0.18154920637607574
2023-01-23 00:55:44.630393: step: 1700/530, loss: 0.0976356565952301
2023-01-23 00:55:45.763661: step: 1704/530, loss: 0.05647869035601616
2023-01-23 00:55:46.888920: step: 1708/530, loss: 0.04309835657477379
2023-01-23 00:55:47.989829: step: 1712/530, loss: 0.05801697075366974
2023-01-23 00:55:49.112847: step: 1716/530, loss: 0.10517054051160812
2023-01-23 00:55:50.227885: step: 1720/530, loss: 0.2723715901374817
2023-01-23 00:55:51.342293: step: 1724/530, loss: 0.09426664561033249
2023-01-23 00:55:52.470714: step: 1728/530, loss: 0.04462461173534393
2023-01-23 00:55:53.602216: step: 1732/530, loss: 0.0062088011763989925
2023-01-23 00:55:54.714092: step: 1736/530, loss: 0.1060112938284874
2023-01-23 00:55:55.812371: step: 1740/530, loss: 0.11627226322889328
2023-01-23 00:55:56.958243: step: 1744/530, loss: 0.09621060639619827
2023-01-23 00:55:58.055007: step: 1748/530, loss: 0.0415617935359478
2023-01-23 00:55:59.165999: step: 1752/530, loss: 0.4230268597602844
2023-01-23 00:56:00.257862: step: 1756/530, loss: 0.10484369099140167
2023-01-23 00:56:01.377242: step: 1760/530, loss: 0.07949161529541016
2023-01-23 00:56:02.494362: step: 1764/530, loss: 0.02367372438311577
2023-01-23 00:56:03.588020: step: 1768/530, loss: 0.26504725217819214
2023-01-23 00:56:04.733186: step: 1772/530, loss: 0.07104086875915527
2023-01-23 00:56:05.847481: step: 1776/530, loss: 0.448211669921875
2023-01-23 00:56:06.952542: step: 1780/530, loss: 0.07855415344238281
2023-01-23 00:56:08.077592: step: 1784/530, loss: 0.02541036531329155
2023-01-23 00:56:09.177755: step: 1788/530, loss: 0.04402752220630646
2023-01-23 00:56:10.306268: step: 1792/530, loss: 0.15280112624168396
2023-01-23 00:56:11.404131: step: 1796/530, loss: 0.08956728130578995
2023-01-23 00:56:12.507806: step: 1800/530, loss: 0.058026693761348724
2023-01-23 00:56:13.609769: step: 1804/530, loss: 0.19854618608951569
2023-01-23 00:56:14.705554: step: 1808/530, loss: 0.09756460785865784
2023-01-23 00:56:15.819579: step: 1812/530, loss: 0.07738981395959854
2023-01-23 00:56:16.904772: step: 1816/530, loss: 0.08537044376134872
2023-01-23 00:56:18.019617: step: 1820/530, loss: 0.043403055518865585
2023-01-23 00:56:19.136025: step: 1824/530, loss: 0.07844428718090057
2023-01-23 00:56:20.235670: step: 1828/530, loss: 0.05578174442052841
2023-01-23 00:56:21.324375: step: 1832/530, loss: 0.04719729721546173
2023-01-23 00:56:22.429477: step: 1836/530, loss: 0.0529266856610775
2023-01-23 00:56:23.534348: step: 1840/530, loss: 0.1260140985250473
2023-01-23 00:56:24.624460: step: 1844/530, loss: 0.8309139609336853
2023-01-23 00:56:25.741319: step: 1848/530, loss: 0.04821648821234703
2023-01-23 00:56:26.835545: step: 1852/530, loss: 0.050139714032411575
2023-01-23 00:56:27.968479: step: 1856/530, loss: 1.1567267179489136
2023-01-23 00:56:29.060285: step: 1860/530, loss: 0.07785234600305557
2023-01-23 00:56:30.167143: step: 1864/530, loss: 0.1178131103515625
2023-01-23 00:56:31.260859: step: 1868/530, loss: 0.12339244037866592
2023-01-23 00:56:32.386256: step: 1872/530, loss: 0.02334156073629856
2023-01-23 00:56:33.491932: step: 1876/530, loss: 0.015031909570097923
2023-01-23 00:56:34.634545: step: 1880/530, loss: 0.08797606825828552
2023-01-23 00:56:35.732397: step: 1884/530, loss: 0.2171286642551422
2023-01-23 00:56:36.844305: step: 1888/530, loss: 0.1767236739397049
2023-01-23 00:56:37.967466: step: 1892/530, loss: 0.0138886459171772
2023-01-23 00:56:39.092263: step: 1896/530, loss: 0.0973726287484169
2023-01-23 00:56:40.192793: step: 1900/530, loss: 0.17795081436634064
2023-01-23 00:56:41.296432: step: 1904/530, loss: 0.05171241983771324
2023-01-23 00:56:42.406901: step: 1908/530, loss: 0.7198076248168945
2023-01-23 00:56:43.513625: step: 1912/530, loss: 0.17739595472812653
2023-01-23 00:56:44.592934: step: 1916/530, loss: 0.02943793497979641
2023-01-23 00:56:45.678882: step: 1920/530, loss: 0.2069990038871765
2023-01-23 00:56:46.794865: step: 1924/530, loss: 0.0882083922624588
2023-01-23 00:56:47.892657: step: 1928/530, loss: 0.08206605166196823
2023-01-23 00:56:48.975992: step: 1932/530, loss: 0.05120064318180084
2023-01-23 00:56:50.092353: step: 1936/530, loss: 0.03551230579614639
2023-01-23 00:56:51.222088: step: 1940/530, loss: 0.056046012789011
2023-01-23 00:56:52.349783: step: 1944/530, loss: 0.05531826242804527
2023-01-23 00:56:53.470297: step: 1948/530, loss: 0.06365184485912323
2023-01-23 00:56:54.581121: step: 1952/530, loss: 0.052738189697265625
2023-01-23 00:56:55.712186: step: 1956/530, loss: 0.10266587883234024
2023-01-23 00:56:56.830223: step: 1960/530, loss: 0.05148601531982422
2023-01-23 00:56:57.976955: step: 1964/530, loss: 0.06124544143676758
2023-01-23 00:56:59.061663: step: 1968/530, loss: 0.08662159740924835
2023-01-23 00:57:00.151852: step: 1972/530, loss: 0.250003457069397
2023-01-23 00:57:01.242145: step: 1976/530, loss: 0.05090451240539551
2023-01-23 00:57:02.353964: step: 1980/530, loss: 0.07934533059597015
2023-01-23 00:57:03.471779: step: 1984/530, loss: 0.03718538209795952
2023-01-23 00:57:04.582503: step: 1988/530, loss: 0.11307653784751892
2023-01-23 00:57:05.696695: step: 1992/530, loss: 0.20911788940429688
2023-01-23 00:57:06.810691: step: 1996/530, loss: 0.10670796036720276
2023-01-23 00:57:07.926575: step: 2000/530, loss: 0.26739901304244995
2023-01-23 00:57:09.019269: step: 2004/530, loss: 0.17810669541358948
2023-01-23 00:57:10.121913: step: 2008/530, loss: 0.10456585884094238
2023-01-23 00:57:11.206281: step: 2012/530, loss: 0.8838997483253479
2023-01-23 00:57:12.339542: step: 2016/530, loss: 0.05686221271753311
2023-01-23 00:57:13.451553: step: 2020/530, loss: 0.0570995919406414
2023-01-23 00:57:14.527247: step: 2024/530, loss: 0.0025862932670861483
2023-01-23 00:57:15.621203: step: 2028/530, loss: 0.10257511585950851
2023-01-23 00:57:16.745997: step: 2032/530, loss: 0.039492033421993256
2023-01-23 00:57:17.835203: step: 2036/530, loss: 0.10757027566432953
2023-01-23 00:57:18.914800: step: 2040/530, loss: 0.05171528086066246
2023-01-23 00:57:19.995465: step: 2044/530, loss: 0.05016450956463814
2023-01-23 00:57:21.111677: step: 2048/530, loss: 0.18939208984375
2023-01-23 00:57:22.238739: step: 2052/530, loss: 0.04572296142578125
2023-01-23 00:57:23.364287: step: 2056/530, loss: 0.14915475249290466
2023-01-23 00:57:24.501066: step: 2060/530, loss: 0.009793151170015335
2023-01-23 00:57:25.628479: step: 2064/530, loss: 0.11170235276222229
2023-01-23 00:57:26.747288: step: 2068/530, loss: 0.15630798041820526
2023-01-23 00:57:27.867560: step: 2072/530, loss: 0.05971813201904297
2023-01-23 00:57:28.965083: step: 2076/530, loss: 0.0030181407928466797
2023-01-23 00:57:30.050830: step: 2080/530, loss: 0.04723968729376793
2023-01-23 00:57:31.153789: step: 2084/530, loss: 0.2330244928598404
2023-01-23 00:57:32.273408: step: 2088/530, loss: 0.019307708367705345
2023-01-23 00:57:33.394846: step: 2092/530, loss: 0.06296195834875107
2023-01-23 00:57:34.513635: step: 2096/530, loss: 0.03877994418144226
2023-01-23 00:57:35.607305: step: 2100/530, loss: 0.011324882507324219
2023-01-23 00:57:36.708735: step: 2104/530, loss: 0.04982485994696617
2023-01-23 00:57:37.824519: step: 2108/530, loss: 0.07450399547815323
2023-01-23 00:57:38.937461: step: 2112/530, loss: 0.2574615478515625
2023-01-23 00:57:40.035362: step: 2116/530, loss: 0.08460921794176102
2023-01-23 00:57:41.163109: step: 2120/530, loss: 0.09280509501695633
==================================================
Loss: 0.124
--------------------
Dev: {'event': {'p': 0.597444089456869, 'r': 0.7470039946737683, 'f1': 0.663905325443787}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Test: {'event': {'p': 0.6259716506630086, 'r': 0.7977855477855478, 'f1': 0.7015116576992056}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Chinese: {'event': {'p': 0.647887323943662, 'r': 0.8518518518518519, 'f1': 0.7360000000000001}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Korean: {'event': {'p': 0.6296296296296297, 'r': 0.5396825396825397, 'f1': 0.5811965811965812}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Russian: {'event': {'p': 0.5405405405405406, 'r': 0.5555555555555556, 'f1': 0.547945205479452}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
New best russian model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.5708622398414271, 'r': 0.7669773635153129, 'f1': 0.6545454545454545}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Eng Test for Chinese: {'event': {'p': 0.6044052863436123, 'r': 0.7995337995337995, 'f1': 0.6884094330155545}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Sample Chinese: {'event': {'p': 0.6578947368421053, 'r': 0.9259259259259259, 'f1': 0.7692307692307692}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6466512702078522, 'r': 0.7456724367509987, 'f1': 0.6926406926406927}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Eng Test for Korean: {'event': {'p': 0.6762148337595908, 'r': 0.7703962703962703, 'f1': 0.7202397166984473}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Sample Korean: {'event': {'p': 0.6862745098039216, 'r': 0.5555555555555556, 'f1': 0.6140350877192983}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
--------------------
Eng Dev for Russian: {'event': {'p': 0.597444089456869, 'r': 0.7470039946737683, 'f1': 0.663905325443787}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Eng Test for Russian: {'event': {'p': 0.6259716506630086, 'r': 0.7977855477855478, 'f1': 0.7015116576992056}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
Sample Russian: {'event': {'p': 0.5405405405405406, 'r': 0.5555555555555556, 'f1': 0.547945205479452}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 8}
******************************
Epoch: 9
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 00:58:28.085792: step: 4/530, loss: 0.059467434883117676
2023-01-23 00:58:29.175682: step: 8/530, loss: 0.06741628795862198
2023-01-23 00:58:30.297967: step: 12/530, loss: 0.0014163493178784847
2023-01-23 00:58:31.415848: step: 16/530, loss: 0.02273840829730034
2023-01-23 00:58:32.516043: step: 20/530, loss: 0.47662153840065
2023-01-23 00:58:33.604196: step: 24/530, loss: 0.3686390817165375
2023-01-23 00:58:34.709966: step: 28/530, loss: 0.013661528006196022
2023-01-23 00:58:35.823065: step: 32/530, loss: 0.10623379051685333
2023-01-23 00:58:36.926963: step: 36/530, loss: 0.039480164647102356
2023-01-23 00:58:38.033920: step: 40/530, loss: 0.055282022804021835
2023-01-23 00:58:39.137209: step: 44/530, loss: 0.04666290432214737
2023-01-23 00:58:40.248301: step: 48/530, loss: 0.09851551055908203
2023-01-23 00:58:41.351591: step: 52/530, loss: 0.0577126070857048
2023-01-23 00:58:42.448169: step: 56/530, loss: 0.043779850006103516
2023-01-23 00:58:43.549242: step: 60/530, loss: 0.03413849323987961
2023-01-23 00:58:44.619915: step: 64/530, loss: 0.00702934293076396
2023-01-23 00:58:45.720913: step: 68/530, loss: 0.22127565741539001
2023-01-23 00:58:46.890240: step: 72/530, loss: 0.1151500791311264
2023-01-23 00:58:48.001183: step: 76/530, loss: 0.07048015296459198
2023-01-23 00:58:49.129228: step: 80/530, loss: 0.316898912191391
2023-01-23 00:58:50.239383: step: 84/530, loss: 0.024481534957885742
2023-01-23 00:58:51.329276: step: 88/530, loss: 0.023911286145448685
2023-01-23 00:58:52.415848: step: 92/530, loss: 0.12105751037597656
2023-01-23 00:58:53.576163: step: 96/530, loss: 0.1114223450422287
2023-01-23 00:58:54.669978: step: 100/530, loss: 0.042087603360414505
2023-01-23 00:58:55.777268: step: 104/530, loss: 0.03492593765258789
2023-01-23 00:58:56.872800: step: 108/530, loss: 0.034452442079782486
2023-01-23 00:58:57.983124: step: 112/530, loss: 0.14111891388893127
2023-01-23 00:58:59.076940: step: 116/530, loss: 0.030294323340058327
2023-01-23 00:59:00.176611: step: 120/530, loss: 0.030425071716308594
2023-01-23 00:59:01.282212: step: 124/530, loss: 0.9508135914802551
2023-01-23 00:59:02.382911: step: 128/530, loss: 0.04664049297571182
2023-01-23 00:59:03.535518: step: 132/530, loss: 0.08364172279834747
2023-01-23 00:59:04.627895: step: 136/530, loss: 0.04367566108703613
2023-01-23 00:59:05.717452: step: 140/530, loss: 0.017160963267087936
2023-01-23 00:59:06.813589: step: 144/530, loss: 0.06891441345214844
2023-01-23 00:59:07.912563: step: 148/530, loss: 0.025079965591430664
2023-01-23 00:59:09.041070: step: 152/530, loss: 0.35502633452415466
2023-01-23 00:59:10.129346: step: 156/530, loss: 0.05305905640125275
2023-01-23 00:59:11.237307: step: 160/530, loss: 0.0020322322379797697
2023-01-23 00:59:12.352414: step: 164/530, loss: 0.16181202232837677
2023-01-23 00:59:13.485862: step: 168/530, loss: 0.11331701278686523
2023-01-23 00:59:14.598573: step: 172/530, loss: 0.06443872302770615
2023-01-23 00:59:15.727536: step: 176/530, loss: 0.053949929773807526
2023-01-23 00:59:16.839570: step: 180/530, loss: 0.06950082629919052
2023-01-23 00:59:17.926013: step: 184/530, loss: 0.07468695938587189
2023-01-23 00:59:19.015152: step: 188/530, loss: 0.01081763580441475
2023-01-23 00:59:20.150787: step: 192/530, loss: 0.02664036676287651
2023-01-23 00:59:21.265891: step: 196/530, loss: 0.1842426359653473
2023-01-23 00:59:22.372049: step: 200/530, loss: 0.0907268300652504
2023-01-23 00:59:23.490984: step: 204/530, loss: 0.07651004940271378
2023-01-23 00:59:24.632672: step: 208/530, loss: 0.09579391777515411
2023-01-23 00:59:25.782427: step: 212/530, loss: 0.12234792858362198
2023-01-23 00:59:26.893966: step: 216/530, loss: 0.47399863600730896
2023-01-23 00:59:28.012691: step: 220/530, loss: 0.10240379720926285
2023-01-23 00:59:29.155327: step: 224/530, loss: 0.14757832884788513
2023-01-23 00:59:30.256171: step: 228/530, loss: 0.02375030517578125
2023-01-23 00:59:31.355098: step: 232/530, loss: 0.06918277591466904
2023-01-23 00:59:32.455989: step: 236/530, loss: 0.12576523423194885
2023-01-23 00:59:33.559745: step: 240/530, loss: 0.03799863159656525
2023-01-23 00:59:34.656041: step: 244/530, loss: 0.044641874730587006
2023-01-23 00:59:35.759427: step: 248/530, loss: 0.12257039546966553
2023-01-23 00:59:36.872039: step: 252/530, loss: 0.10022592544555664
2023-01-23 00:59:37.985400: step: 256/530, loss: 0.0626247376203537
2023-01-23 00:59:39.112940: step: 260/530, loss: 0.0754152312874794
2023-01-23 00:59:40.242027: step: 264/530, loss: 0.0324527733027935
2023-01-23 00:59:41.351182: step: 268/530, loss: 0.07689706981182098
2023-01-23 00:59:42.481627: step: 272/530, loss: 0.2723402976989746
2023-01-23 00:59:43.608751: step: 276/530, loss: 0.03329487144947052
2023-01-23 00:59:44.727039: step: 280/530, loss: 0.10591153800487518
2023-01-23 00:59:45.822644: step: 284/530, loss: 0.1054508239030838
2023-01-23 00:59:46.893289: step: 288/530, loss: 0.09302883595228195
2023-01-23 00:59:48.012469: step: 292/530, loss: 0.4949951171875
2023-01-23 00:59:49.102861: step: 296/530, loss: 0.5504612922668457
2023-01-23 00:59:50.210958: step: 300/530, loss: 0.5561575889587402
2023-01-23 00:59:51.313792: step: 304/530, loss: 0.08872528374195099
2023-01-23 00:59:52.407000: step: 308/530, loss: 0.14894461631774902
2023-01-23 00:59:53.511267: step: 312/530, loss: 0.09469567239284515
2023-01-23 00:59:54.631845: step: 316/530, loss: 0.05680360645055771
2023-01-23 00:59:55.755870: step: 320/530, loss: 0.028053760528564453
2023-01-23 00:59:56.899424: step: 324/530, loss: 0.09207191318273544
2023-01-23 00:59:58.013306: step: 328/530, loss: 0.09661054611206055
2023-01-23 00:59:59.114203: step: 332/530, loss: 0.006581735797226429
2023-01-23 01:00:00.242382: step: 336/530, loss: 0.04672985151410103
2023-01-23 01:00:01.320378: step: 340/530, loss: 0.016573499888181686
2023-01-23 01:00:02.425956: step: 344/530, loss: 0.05010700225830078
2023-01-23 01:00:03.534203: step: 348/530, loss: 0.10732222348451614
2023-01-23 01:00:04.699020: step: 352/530, loss: 0.10449858009815216
2023-01-23 01:00:05.823380: step: 356/530, loss: 0.04569358751177788
2023-01-23 01:00:06.937769: step: 360/530, loss: 0.12227706611156464
2023-01-23 01:00:08.051637: step: 364/530, loss: 0.044361554086208344
2023-01-23 01:00:09.205676: step: 368/530, loss: 0.03411807864904404
2023-01-23 01:00:10.314793: step: 372/530, loss: 0.04581642523407936
2023-01-23 01:00:11.423100: step: 376/530, loss: 0.03163585811853409
2023-01-23 01:00:12.522697: step: 380/530, loss: 0.05841407924890518
2023-01-23 01:00:13.639415: step: 384/530, loss: 0.07240104675292969
2023-01-23 01:00:14.743416: step: 388/530, loss: 0.08861179649829865
2023-01-23 01:00:15.856321: step: 392/530, loss: 0.04914131388068199
2023-01-23 01:00:16.986678: step: 396/530, loss: 0.22335167229175568
2023-01-23 01:00:18.076285: step: 400/530, loss: 0.06992053985595703
2023-01-23 01:00:19.188376: step: 404/530, loss: 0.06421279907226562
2023-01-23 01:00:20.282775: step: 408/530, loss: 0.0355740562081337
2023-01-23 01:00:21.418419: step: 412/530, loss: 0.23547782003879547
2023-01-23 01:00:22.562031: step: 416/530, loss: 0.15474340319633484
2023-01-23 01:00:23.681428: step: 420/530, loss: 0.038662053644657135
2023-01-23 01:00:24.786437: step: 424/530, loss: 0.02536039426922798
2023-01-23 01:00:25.890869: step: 428/530, loss: 0.07532129436731339
2023-01-23 01:00:26.984983: step: 432/530, loss: 0.03606675565242767
2023-01-23 01:00:28.099195: step: 436/530, loss: 0.11642847955226898
2023-01-23 01:00:29.216329: step: 440/530, loss: 0.1911262571811676
2023-01-23 01:00:30.343470: step: 444/530, loss: 0.0046329498291015625
2023-01-23 01:00:31.440602: step: 448/530, loss: 0.051806069910526276
2023-01-23 01:00:32.522434: step: 452/530, loss: 0.011393642984330654
2023-01-23 01:00:33.672075: step: 456/530, loss: 0.05447092279791832
2023-01-23 01:00:34.757047: step: 460/530, loss: 0.03626156225800514
2023-01-23 01:00:35.840291: step: 464/530, loss: 0.28871044516563416
2023-01-23 01:00:36.958593: step: 468/530, loss: 0.1612241268157959
2023-01-23 01:00:38.075538: step: 472/530, loss: 0.03887691721320152
2023-01-23 01:00:39.193133: step: 476/530, loss: 0.03909111022949219
2023-01-23 01:00:40.297097: step: 480/530, loss: 0.020506085827946663
2023-01-23 01:00:41.411030: step: 484/530, loss: 0.1612153947353363
2023-01-23 01:00:42.556377: step: 488/530, loss: 0.5768324732780457
2023-01-23 01:00:43.670437: step: 492/530, loss: 0.04163913428783417
2023-01-23 01:00:44.782193: step: 496/530, loss: 0.05466318503022194
2023-01-23 01:00:45.930493: step: 500/530, loss: 0.01213769894093275
2023-01-23 01:00:47.028489: step: 504/530, loss: 0.03172314167022705
2023-01-23 01:00:48.161377: step: 508/530, loss: 0.14665278792381287
2023-01-23 01:00:49.323921: step: 512/530, loss: 0.18073701858520508
2023-01-23 01:00:50.443764: step: 516/530, loss: 0.03886318579316139
2023-01-23 01:00:51.562467: step: 520/530, loss: 0.10925635695457458
2023-01-23 01:00:52.666919: step: 524/530, loss: 0.5058422088623047
2023-01-23 01:00:53.764942: step: 528/530, loss: 0.04473733901977539
2023-01-23 01:00:54.880641: step: 532/530, loss: 0.07666053622961044
2023-01-23 01:00:55.971223: step: 536/530, loss: 0.05933942645788193
2023-01-23 01:00:57.144055: step: 540/530, loss: 0.073621466755867
2023-01-23 01:00:58.291687: step: 544/530, loss: 0.04668760299682617
2023-01-23 01:00:59.398161: step: 548/530, loss: 0.055408671498298645
2023-01-23 01:01:00.489975: step: 552/530, loss: 0.03224482387304306
2023-01-23 01:01:01.625160: step: 556/530, loss: 0.3635343611240387
2023-01-23 01:01:02.740034: step: 560/530, loss: 0.02834939956665039
2023-01-23 01:01:03.822822: step: 564/530, loss: 0.11555109173059464
2023-01-23 01:01:04.933804: step: 568/530, loss: 0.03168763965368271
2023-01-23 01:01:06.036073: step: 572/530, loss: 0.07923047244548798
2023-01-23 01:01:07.145192: step: 576/530, loss: 0.06916943192481995
2023-01-23 01:01:08.235482: step: 580/530, loss: 0.1113743782043457
2023-01-23 01:01:09.313785: step: 584/530, loss: 0.0602237693965435
2023-01-23 01:01:10.416052: step: 588/530, loss: 0.02346677891910076
2023-01-23 01:01:11.507683: step: 592/530, loss: 0.06817837059497833
2023-01-23 01:01:12.611548: step: 596/530, loss: 0.023755932226777077
2023-01-23 01:01:13.767091: step: 600/530, loss: 0.01371068973094225
2023-01-23 01:01:14.875239: step: 604/530, loss: 0.03939466178417206
2023-01-23 01:01:16.010029: step: 608/530, loss: 0.08455085754394531
2023-01-23 01:01:17.142014: step: 612/530, loss: 0.10320273041725159
2023-01-23 01:01:18.253353: step: 616/530, loss: 0.07854624092578888
2023-01-23 01:01:19.364292: step: 620/530, loss: 0.13549405336380005
2023-01-23 01:01:20.518291: step: 624/530, loss: 0.04325170814990997
2023-01-23 01:01:21.639586: step: 628/530, loss: 0.08605756610631943
2023-01-23 01:01:22.759052: step: 632/530, loss: 0.0449254997074604
2023-01-23 01:01:23.859137: step: 636/530, loss: 0.06233358383178711
2023-01-23 01:01:24.982449: step: 640/530, loss: 0.08319655060768127
2023-01-23 01:01:26.113969: step: 644/530, loss: 0.17743147909641266
2023-01-23 01:01:27.206184: step: 648/530, loss: 0.06862087547779083
2023-01-23 01:01:28.323858: step: 652/530, loss: 0.09276504814624786
2023-01-23 01:01:29.415343: step: 656/530, loss: 0.029688358306884766
2023-01-23 01:01:30.523927: step: 660/530, loss: 0.0371883399784565
2023-01-23 01:01:31.622584: step: 664/530, loss: 0.04769592732191086
2023-01-23 01:01:32.739319: step: 668/530, loss: 0.11620006710290909
2023-01-23 01:01:33.854246: step: 672/530, loss: 0.0788685604929924
2023-01-23 01:01:34.956480: step: 676/530, loss: 0.11887387931346893
2023-01-23 01:01:36.055239: step: 680/530, loss: 0.03980560600757599
2023-01-23 01:01:37.133126: step: 684/530, loss: 0.0112924100831151
2023-01-23 01:01:38.254043: step: 688/530, loss: 0.018542766571044922
2023-01-23 01:01:39.352156: step: 692/530, loss: 0.005323505494743586
2023-01-23 01:01:40.467194: step: 696/530, loss: 0.498462975025177
2023-01-23 01:01:41.566646: step: 700/530, loss: 0.2711736559867859
2023-01-23 01:01:42.675234: step: 704/530, loss: 0.03457784652709961
2023-01-23 01:01:43.778156: step: 708/530, loss: 0.03194618225097656
2023-01-23 01:01:44.874827: step: 712/530, loss: 0.06727543473243713
2023-01-23 01:01:45.990017: step: 716/530, loss: 0.02787027508020401
2023-01-23 01:01:47.108451: step: 720/530, loss: 0.10290078818798065
2023-01-23 01:01:48.207888: step: 724/530, loss: 0.0014772415161132812
2023-01-23 01:01:49.311613: step: 728/530, loss: 0.13221712410449982
2023-01-23 01:01:50.428964: step: 732/530, loss: 1.8202250003814697
2023-01-23 01:01:51.544189: step: 736/530, loss: 0.26255226135253906
2023-01-23 01:01:52.686469: step: 740/530, loss: 0.03638629987835884
2023-01-23 01:01:53.799497: step: 744/530, loss: 0.11133584380149841
2023-01-23 01:01:54.912742: step: 748/530, loss: 0.04976291581988335
2023-01-23 01:01:56.001359: step: 752/530, loss: 0.030758000910282135
2023-01-23 01:01:57.083068: step: 756/530, loss: 0.0846920982003212
2023-01-23 01:01:58.193398: step: 760/530, loss: 0.11802730709314346
2023-01-23 01:01:59.305717: step: 764/530, loss: 0.0611325278878212
2023-01-23 01:02:00.389365: step: 768/530, loss: 0.1037314385175705
2023-01-23 01:02:01.496246: step: 772/530, loss: 0.023491764441132545
2023-01-23 01:02:02.590021: step: 776/530, loss: 0.025437969714403152
2023-01-23 01:02:03.718534: step: 780/530, loss: 0.03173961490392685
2023-01-23 01:02:04.859534: step: 784/530, loss: 0.08323326706886292
2023-01-23 01:02:05.972774: step: 788/530, loss: 0.07005657255649567
2023-01-23 01:02:07.083113: step: 792/530, loss: 0.08603725582361221
2023-01-23 01:02:08.209531: step: 796/530, loss: 0.057090092450380325
2023-01-23 01:02:09.326823: step: 800/530, loss: 0.0837024673819542
2023-01-23 01:02:10.412130: step: 804/530, loss: 0.4514656960964203
2023-01-23 01:02:11.540486: step: 808/530, loss: 0.20156708359718323
2023-01-23 01:02:12.626921: step: 812/530, loss: 0.06731734424829483
2023-01-23 01:02:13.754107: step: 816/530, loss: 0.03028416633605957
2023-01-23 01:02:14.849382: step: 820/530, loss: 0.11520515382289886
2023-01-23 01:02:15.964377: step: 824/530, loss: 0.2195732146501541
2023-01-23 01:02:17.076038: step: 828/530, loss: 0.11928515881299973
2023-01-23 01:02:18.166550: step: 832/530, loss: 0.06800797581672668
2023-01-23 01:02:19.289733: step: 836/530, loss: 0.10840387642383575
2023-01-23 01:02:20.365140: step: 840/530, loss: 0.05319347232580185
2023-01-23 01:02:21.469744: step: 844/530, loss: 0.05626435577869415
2023-01-23 01:02:22.557038: step: 848/530, loss: 0.1913505494594574
2023-01-23 01:02:23.640540: step: 852/530, loss: 0.3311210870742798
2023-01-23 01:02:24.767109: step: 856/530, loss: 0.06856193393468857
2023-01-23 01:02:25.866442: step: 860/530, loss: 0.02766704559326172
2023-01-23 01:02:26.988408: step: 864/530, loss: 0.11915703117847443
2023-01-23 01:02:28.091494: step: 868/530, loss: 0.05146608501672745
2023-01-23 01:02:29.215942: step: 872/530, loss: 0.051688503473997116
2023-01-23 01:02:30.332036: step: 876/530, loss: 0.06542558968067169
2023-01-23 01:02:31.424036: step: 880/530, loss: 0.059754084795713425
2023-01-23 01:02:32.520469: step: 884/530, loss: 0.05255327373743057
2023-01-23 01:02:33.682667: step: 888/530, loss: 0.09187240898609161
2023-01-23 01:02:34.800244: step: 892/530, loss: 0.08481216430664062
2023-01-23 01:02:35.896417: step: 896/530, loss: 0.15302228927612305
2023-01-23 01:02:37.001687: step: 900/530, loss: 0.012938786298036575
2023-01-23 01:02:38.086443: step: 904/530, loss: 0.030353689566254616
2023-01-23 01:02:39.213644: step: 908/530, loss: 0.13592444360256195
2023-01-23 01:02:40.316429: step: 912/530, loss: 0.028123866766691208
2023-01-23 01:02:41.429925: step: 916/530, loss: 0.020467139780521393
2023-01-23 01:02:42.562344: step: 920/530, loss: 0.03194904327392578
2023-01-23 01:02:43.681406: step: 924/530, loss: 0.10587482899427414
2023-01-23 01:02:44.802036: step: 928/530, loss: 0.15732459723949432
2023-01-23 01:02:45.905986: step: 932/530, loss: 0.010158920660614967
2023-01-23 01:02:47.042827: step: 936/530, loss: 0.07161130756139755
2023-01-23 01:02:48.180797: step: 940/530, loss: 0.15675011277198792
2023-01-23 01:02:49.275322: step: 944/530, loss: 0.18385986983776093
2023-01-23 01:02:50.384524: step: 948/530, loss: 0.010151195339858532
2023-01-23 01:02:51.475380: step: 952/530, loss: 0.02192401885986328
2023-01-23 01:02:52.586585: step: 956/530, loss: 0.036783792078495026
2023-01-23 01:02:53.710376: step: 960/530, loss: 0.47565001249313354
2023-01-23 01:02:54.851768: step: 964/530, loss: 0.048403359949588776
2023-01-23 01:02:55.976578: step: 968/530, loss: 0.041521359235048294
2023-01-23 01:02:57.067727: step: 972/530, loss: 0.11711292713880539
2023-01-23 01:02:58.213845: step: 976/530, loss: 0.05844841152429581
2023-01-23 01:02:59.328323: step: 980/530, loss: 0.12454032897949219
2023-01-23 01:03:00.438171: step: 984/530, loss: 0.011598623357713223
2023-01-23 01:03:01.537852: step: 988/530, loss: 0.17863351106643677
2023-01-23 01:03:02.666848: step: 992/530, loss: 0.09128923714160919
2023-01-23 01:03:03.814712: step: 996/530, loss: 0.16409951448440552
2023-01-23 01:03:04.904985: step: 1000/530, loss: 0.11033916473388672
2023-01-23 01:03:06.035484: step: 1004/530, loss: 0.036875154823064804
2023-01-23 01:03:07.171992: step: 1008/530, loss: 0.05740871652960777
2023-01-23 01:03:08.277587: step: 1012/530, loss: 0.06920719146728516
2023-01-23 01:03:09.388528: step: 1016/530, loss: 0.025272943079471588
2023-01-23 01:03:10.505342: step: 1020/530, loss: 0.0780276358127594
2023-01-23 01:03:11.627446: step: 1024/530, loss: 0.04266996309161186
2023-01-23 01:03:12.720965: step: 1028/530, loss: 0.05045013129711151
2023-01-23 01:03:13.831674: step: 1032/530, loss: 0.12587542831897736
2023-01-23 01:03:14.921870: step: 1036/530, loss: 0.047800637781620026
2023-01-23 01:03:16.034018: step: 1040/530, loss: 0.05946522206068039
2023-01-23 01:03:17.160111: step: 1044/530, loss: 0.16668137907981873
2023-01-23 01:03:18.273962: step: 1048/530, loss: 0.06960468739271164
2023-01-23 01:03:19.383110: step: 1052/530, loss: 0.10762587189674377
2023-01-23 01:03:20.491380: step: 1056/530, loss: 0.08002634346485138
2023-01-23 01:03:21.613419: step: 1060/530, loss: 0.18244607746601105
2023-01-23 01:03:22.702893: step: 1064/530, loss: 0.014163590036332607
2023-01-23 01:03:23.836800: step: 1068/530, loss: 0.12196540832519531
2023-01-23 01:03:24.930328: step: 1072/530, loss: 0.33865004777908325
2023-01-23 01:03:26.049797: step: 1076/530, loss: 0.3974939286708832
2023-01-23 01:03:27.127303: step: 1080/530, loss: 0.08966927975416183
2023-01-23 01:03:28.239906: step: 1084/530, loss: 0.03089771419763565
2023-01-23 01:03:29.351946: step: 1088/530, loss: 0.008255625143647194
2023-01-23 01:03:30.459513: step: 1092/530, loss: 0.08978305011987686
2023-01-23 01:03:31.540610: step: 1096/530, loss: 0.06291027367115021
2023-01-23 01:03:32.646679: step: 1100/530, loss: 0.06971579045057297
2023-01-23 01:03:33.754615: step: 1104/530, loss: 0.053247857838869095
2023-01-23 01:03:34.850645: step: 1108/530, loss: 0.02231144905090332
2023-01-23 01:03:35.941463: step: 1112/530, loss: 0.06947823613882065
2023-01-23 01:03:37.071319: step: 1116/530, loss: 0.02197113074362278
2023-01-23 01:03:38.174732: step: 1120/530, loss: 0.08135108649730682
2023-01-23 01:03:39.291558: step: 1124/530, loss: 0.04469728469848633
2023-01-23 01:03:40.427821: step: 1128/530, loss: 0.03761877864599228
2023-01-23 01:03:41.529850: step: 1132/530, loss: 0.24308152496814728
2023-01-23 01:03:42.664438: step: 1136/530, loss: 0.13136939704418182
2023-01-23 01:03:43.769982: step: 1140/530, loss: 0.0869382917881012
2023-01-23 01:03:44.853294: step: 1144/530, loss: 1.1290096044540405
2023-01-23 01:03:45.955915: step: 1148/530, loss: 0.017607593908905983
2023-01-23 01:03:47.062780: step: 1152/530, loss: 0.05117073282599449
2023-01-23 01:03:48.166994: step: 1156/530, loss: 0.11772432178258896
2023-01-23 01:03:49.295983: step: 1160/530, loss: 0.011698246002197266
2023-01-23 01:03:50.418640: step: 1164/530, loss: 0.01843714714050293
2023-01-23 01:03:51.562123: step: 1168/530, loss: 0.02995162084698677
2023-01-23 01:03:52.670763: step: 1172/530, loss: 0.03150139003992081
2023-01-23 01:03:53.805369: step: 1176/530, loss: 0.11452217400074005
2023-01-23 01:03:54.887270: step: 1180/530, loss: 0.08147859573364258
2023-01-23 01:03:56.015373: step: 1184/530, loss: 0.02067422866821289
2023-01-23 01:03:57.139761: step: 1188/530, loss: 0.1286468505859375
2023-01-23 01:03:58.272375: step: 1192/530, loss: 0.1301598995923996
2023-01-23 01:03:59.364587: step: 1196/530, loss: 0.004971504211425781
2023-01-23 01:04:00.474921: step: 1200/530, loss: 0.42529788613319397
2023-01-23 01:04:01.591902: step: 1204/530, loss: 0.12051025778055191
2023-01-23 01:04:02.721700: step: 1208/530, loss: 0.1038203239440918
2023-01-23 01:04:03.861898: step: 1212/530, loss: 0.18087874352931976
2023-01-23 01:04:04.963682: step: 1216/530, loss: 0.04225633293390274
2023-01-23 01:04:06.100821: step: 1220/530, loss: 0.07690220326185226
2023-01-23 01:04:07.208851: step: 1224/530, loss: 0.09403391182422638
2023-01-23 01:04:08.336389: step: 1228/530, loss: 0.6935513019561768
2023-01-23 01:04:09.449508: step: 1232/530, loss: 0.04119567945599556
2023-01-23 01:04:10.529996: step: 1236/530, loss: 0.11418375372886658
2023-01-23 01:04:11.611845: step: 1240/530, loss: 0.031746625900268555
2023-01-23 01:04:12.720564: step: 1244/530, loss: 0.036389730870723724
2023-01-23 01:04:13.837477: step: 1248/530, loss: 0.06745481491088867
2023-01-23 01:04:14.959070: step: 1252/530, loss: 0.04894714429974556
2023-01-23 01:04:16.044632: step: 1256/530, loss: 0.08513341099023819
2023-01-23 01:04:17.156568: step: 1260/530, loss: 0.04502267390489578
2023-01-23 01:04:18.254811: step: 1264/530, loss: 0.1928301751613617
2023-01-23 01:04:19.370202: step: 1268/530, loss: 0.3669787347316742
2023-01-23 01:04:20.461752: step: 1272/530, loss: 0.11448231339454651
2023-01-23 01:04:21.547846: step: 1276/530, loss: 0.04057302325963974
2023-01-23 01:04:22.699241: step: 1280/530, loss: 0.30444374680519104
2023-01-23 01:04:23.814630: step: 1284/530, loss: 0.08582563698291779
2023-01-23 01:04:24.946153: step: 1288/530, loss: 0.13928452134132385
2023-01-23 01:04:26.085934: step: 1292/530, loss: 0.03915577009320259
2023-01-23 01:04:27.177013: step: 1296/530, loss: 0.05849466472864151
2023-01-23 01:04:28.303863: step: 1300/530, loss: 0.05645398795604706
2023-01-23 01:04:29.411994: step: 1304/530, loss: 0.010292625986039639
2023-01-23 01:04:30.491436: step: 1308/530, loss: 0.1323436051607132
2023-01-23 01:04:31.617933: step: 1312/530, loss: 0.07942596822977066
2023-01-23 01:04:32.736768: step: 1316/530, loss: 0.10959644615650177
2023-01-23 01:04:33.838681: step: 1320/530, loss: 0.03783159330487251
2023-01-23 01:04:34.959977: step: 1324/530, loss: 0.016747284680604935
2023-01-23 01:04:36.060141: step: 1328/530, loss: 0.07215280085802078
2023-01-23 01:04:37.183487: step: 1332/530, loss: 0.025126172229647636
2023-01-23 01:04:38.296683: step: 1336/530, loss: 0.0795055404305458
2023-01-23 01:04:39.422940: step: 1340/530, loss: 0.04251251369714737
2023-01-23 01:04:40.529700: step: 1344/530, loss: 0.2454099804162979
2023-01-23 01:04:41.675018: step: 1348/530, loss: 0.09127321094274521
2023-01-23 01:04:42.788437: step: 1352/530, loss: 0.044733621180057526
2023-01-23 01:04:43.911056: step: 1356/530, loss: 0.2725728452205658
2023-01-23 01:04:45.012758: step: 1360/530, loss: 0.10653066635131836
2023-01-23 01:04:46.102176: step: 1364/530, loss: 0.041254233568906784
2023-01-23 01:04:47.241833: step: 1368/530, loss: 0.11273422092199326
2023-01-23 01:04:48.336111: step: 1372/530, loss: 0.03908409923315048
2023-01-23 01:04:49.441241: step: 1376/530, loss: 0.09136947989463806
2023-01-23 01:04:50.537646: step: 1380/530, loss: 0.0916057601571083
2023-01-23 01:04:51.629093: step: 1384/530, loss: 0.022026684135198593
2023-01-23 01:04:52.731980: step: 1388/530, loss: 0.04851255565881729
2023-01-23 01:04:53.843193: step: 1392/530, loss: 0.06088776886463165
2023-01-23 01:04:54.908071: step: 1396/530, loss: 0.02162919007241726
2023-01-23 01:04:56.034646: step: 1400/530, loss: 0.12407321482896805
2023-01-23 01:04:57.147353: step: 1404/530, loss: 0.2935035824775696
2023-01-23 01:04:58.274568: step: 1408/530, loss: 0.016327284276485443
2023-01-23 01:04:59.382483: step: 1412/530, loss: 0.20679211616516113
2023-01-23 01:05:00.484223: step: 1416/530, loss: 0.0630430206656456
2023-01-23 01:05:01.598501: step: 1420/530, loss: 0.043682049959897995
2023-01-23 01:05:02.731677: step: 1424/530, loss: 0.03928108513355255
2023-01-23 01:05:03.847505: step: 1428/530, loss: 0.016768742352724075
2023-01-23 01:05:04.962803: step: 1432/530, loss: 0.07665625214576721
2023-01-23 01:05:06.089536: step: 1436/530, loss: 0.004076576326042414
2023-01-23 01:05:07.200365: step: 1440/530, loss: 0.038597699254751205
2023-01-23 01:05:08.298488: step: 1444/530, loss: 0.01966114155948162
2023-01-23 01:05:09.400280: step: 1448/530, loss: 0.12816362082958221
2023-01-23 01:05:10.519044: step: 1452/530, loss: 0.06268720328807831
2023-01-23 01:05:11.614304: step: 1456/530, loss: 0.0040569305419921875
2023-01-23 01:05:12.722450: step: 1460/530, loss: 0.018898535519838333
2023-01-23 01:05:13.806175: step: 1464/530, loss: 0.7334356904029846
2023-01-23 01:05:14.910889: step: 1468/530, loss: 0.022551918402314186
2023-01-23 01:05:16.003621: step: 1472/530, loss: 0.07510886341333389
2023-01-23 01:05:17.103450: step: 1476/530, loss: 0.05240478366613388
2023-01-23 01:05:18.211533: step: 1480/530, loss: 0.025999926030635834
2023-01-23 01:05:19.301846: step: 1484/530, loss: 0.009007262997329235
2023-01-23 01:05:20.426323: step: 1488/530, loss: 0.07305431365966797
2023-01-23 01:05:21.569263: step: 1492/530, loss: 0.008928585797548294
2023-01-23 01:05:22.680062: step: 1496/530, loss: 0.06958160549402237
2023-01-23 01:05:23.794780: step: 1500/530, loss: 0.04374289512634277
2023-01-23 01:05:24.931966: step: 1504/530, loss: 0.0953243225812912
2023-01-23 01:05:26.030825: step: 1508/530, loss: 0.0019353866809979081
2023-01-23 01:05:27.104117: step: 1512/530, loss: 0.12265358120203018
2023-01-23 01:05:28.188075: step: 1516/530, loss: 0.03210468217730522
2023-01-23 01:05:29.277111: step: 1520/530, loss: 0.021001625806093216
2023-01-23 01:05:30.383876: step: 1524/530, loss: 0.1092386245727539
2023-01-23 01:05:31.493241: step: 1528/530, loss: 0.008463477715849876
2023-01-23 01:05:32.584712: step: 1532/530, loss: 0.045734405517578125
2023-01-23 01:05:33.686055: step: 1536/530, loss: 0.021791458129882812
2023-01-23 01:05:34.803389: step: 1540/530, loss: 0.028057385236024857
2023-01-23 01:05:35.899803: step: 1544/530, loss: 0.07758345454931259
2023-01-23 01:05:37.067815: step: 1548/530, loss: 0.020352650433778763
2023-01-23 01:05:38.173244: step: 1552/530, loss: 0.14214782416820526
2023-01-23 01:05:39.287491: step: 1556/530, loss: 0.041823387145996094
2023-01-23 01:05:40.375695: step: 1560/530, loss: 0.11422014236450195
2023-01-23 01:05:41.469641: step: 1564/530, loss: 0.10865583270788193
2023-01-23 01:05:42.582702: step: 1568/530, loss: 0.09713335335254669
2023-01-23 01:05:43.693683: step: 1572/530, loss: 0.036855410784482956
2023-01-23 01:05:44.779662: step: 1576/530, loss: 0.08533421158790588
2023-01-23 01:05:45.925846: step: 1580/530, loss: 0.13995370268821716
2023-01-23 01:05:47.030753: step: 1584/530, loss: 0.02689371071755886
2023-01-23 01:05:48.138791: step: 1588/530, loss: 0.061470601707696915
2023-01-23 01:05:49.237170: step: 1592/530, loss: 0.37156981229782104
2023-01-23 01:05:50.386684: step: 1596/530, loss: 0.0485624298453331
2023-01-23 01:05:51.526124: step: 1600/530, loss: 0.1754436492919922
2023-01-23 01:05:52.658039: step: 1604/530, loss: 0.19284287095069885
2023-01-23 01:05:53.766497: step: 1608/530, loss: 0.21574535965919495
2023-01-23 01:05:54.881498: step: 1612/530, loss: 0.17788058519363403
2023-01-23 01:05:56.021369: step: 1616/530, loss: 0.017086505889892578
2023-01-23 01:05:57.121707: step: 1620/530, loss: 0.42147207260131836
2023-01-23 01:05:58.213332: step: 1624/530, loss: 0.014336966909468174
2023-01-23 01:05:59.316359: step: 1628/530, loss: 0.029339982196688652
2023-01-23 01:06:00.427767: step: 1632/530, loss: 0.02083911933004856
2023-01-23 01:06:01.538447: step: 1636/530, loss: 0.012180614285171032
2023-01-23 01:06:02.641789: step: 1640/530, loss: 0.048548318445682526
2023-01-23 01:06:03.770814: step: 1644/530, loss: 0.019157838076353073
2023-01-23 01:06:04.882394: step: 1648/530, loss: 0.10239201784133911
2023-01-23 01:06:05.984397: step: 1652/530, loss: 0.016657400876283646
2023-01-23 01:06:07.112729: step: 1656/530, loss: 0.10627421736717224
2023-01-23 01:06:08.223275: step: 1660/530, loss: 0.23718085885047913
2023-01-23 01:06:09.323078: step: 1664/530, loss: 0.03785209730267525
2023-01-23 01:06:10.418723: step: 1668/530, loss: 0.18510520458221436
2023-01-23 01:06:11.518337: step: 1672/530, loss: 0.03379549831151962
2023-01-23 01:06:12.612476: step: 1676/530, loss: 0.04039621353149414
2023-01-23 01:06:13.735612: step: 1680/530, loss: 0.01354975625872612
2023-01-23 01:06:14.842788: step: 1684/530, loss: 0.08295512199401855
2023-01-23 01:06:15.933678: step: 1688/530, loss: 0.5378724336624146
2023-01-23 01:06:17.041004: step: 1692/530, loss: 0.050301551818847656
2023-01-23 01:06:18.172176: step: 1696/530, loss: 0.07720642536878586
2023-01-23 01:06:19.281522: step: 1700/530, loss: 0.01579437218606472
2023-01-23 01:06:20.377899: step: 1704/530, loss: 0.08852110058069229
2023-01-23 01:06:21.473827: step: 1708/530, loss: 0.07513542473316193
2023-01-23 01:06:22.588379: step: 1712/530, loss: 0.18471240997314453
2023-01-23 01:06:23.683818: step: 1716/530, loss: 0.05296935886144638
2023-01-23 01:06:24.795901: step: 1720/530, loss: 0.23193541169166565
2023-01-23 01:06:25.921267: step: 1724/530, loss: 0.19017134606838226
2023-01-23 01:06:27.009595: step: 1728/530, loss: 0.4607086777687073
2023-01-23 01:06:28.116117: step: 1732/530, loss: 1.0089895725250244
2023-01-23 01:06:29.198402: step: 1736/530, loss: 0.05974860116839409
2023-01-23 01:06:30.319112: step: 1740/530, loss: 0.01620645634829998
2023-01-23 01:06:31.429475: step: 1744/530, loss: 0.15811291337013245
2023-01-23 01:06:32.532625: step: 1748/530, loss: 0.04337568208575249
2023-01-23 01:06:33.662694: step: 1752/530, loss: 0.02452678605914116
2023-01-23 01:06:34.780424: step: 1756/530, loss: 0.04370298609137535
2023-01-23 01:06:35.910798: step: 1760/530, loss: 0.02557063102722168
2023-01-23 01:06:37.050560: step: 1764/530, loss: 0.33396807312965393
2023-01-23 01:06:38.138994: step: 1768/530, loss: 0.08546619117259979
2023-01-23 01:06:39.260834: step: 1772/530, loss: 0.009649157524108887
2023-01-23 01:06:40.367523: step: 1776/530, loss: 0.03867368772625923
2023-01-23 01:06:41.463286: step: 1780/530, loss: 0.10215988755226135
2023-01-23 01:06:42.592961: step: 1784/530, loss: 0.07459618896245956
2023-01-23 01:06:43.709247: step: 1788/530, loss: 0.23017263412475586
2023-01-23 01:06:44.801786: step: 1792/530, loss: 0.10287227481603622
2023-01-23 01:06:45.917183: step: 1796/530, loss: 0.07859429717063904
2023-01-23 01:06:47.021575: step: 1800/530, loss: 0.06972646713256836
2023-01-23 01:06:48.125249: step: 1804/530, loss: 0.08223896473646164
2023-01-23 01:06:49.216760: step: 1808/530, loss: 0.007271384820342064
2023-01-23 01:06:50.312314: step: 1812/530, loss: 0.11665526032447815
2023-01-23 01:06:51.465911: step: 1816/530, loss: 0.07261891663074493
2023-01-23 01:06:52.569128: step: 1820/530, loss: 0.013526635244488716
2023-01-23 01:06:53.674888: step: 1824/530, loss: 0.05945263430476189
2023-01-23 01:06:54.757090: step: 1828/530, loss: 0.04386315494775772
2023-01-23 01:06:55.851850: step: 1832/530, loss: 0.01474299468100071
2023-01-23 01:06:56.956227: step: 1836/530, loss: 0.09891348332166672
2023-01-23 01:06:58.045122: step: 1840/530, loss: 0.02595844492316246
2023-01-23 01:06:59.139096: step: 1844/530, loss: 0.04823732376098633
2023-01-23 01:07:00.238704: step: 1848/530, loss: 0.10055723041296005
2023-01-23 01:07:01.342993: step: 1852/530, loss: 0.10621195286512375
2023-01-23 01:07:02.464018: step: 1856/530, loss: 0.006200027652084827
2023-01-23 01:07:03.547263: step: 1860/530, loss: 0.08431287109851837
2023-01-23 01:07:04.641243: step: 1864/530, loss: 0.358629435300827
2023-01-23 01:07:05.775645: step: 1868/530, loss: 0.5737533569335938
2023-01-23 01:07:06.902931: step: 1872/530, loss: 0.11289462447166443
2023-01-23 01:07:08.008864: step: 1876/530, loss: 0.0513484925031662
2023-01-23 01:07:09.146136: step: 1880/530, loss: 0.06045493856072426
2023-01-23 01:07:10.250486: step: 1884/530, loss: 0.0445561446249485
2023-01-23 01:07:11.360072: step: 1888/530, loss: 0.07383691519498825
2023-01-23 01:07:12.464476: step: 1892/530, loss: 0.14242681860923767
2023-01-23 01:07:13.572924: step: 1896/530, loss: 0.27213916182518005
2023-01-23 01:07:14.657248: step: 1900/530, loss: 0.18171927332878113
2023-01-23 01:07:15.762426: step: 1904/530, loss: 0.058362483978271484
2023-01-23 01:07:16.859019: step: 1908/530, loss: 0.13020344078540802
2023-01-23 01:07:17.968401: step: 1912/530, loss: 0.20567511022090912
2023-01-23 01:07:19.061804: step: 1916/530, loss: 0.029943371191620827
2023-01-23 01:07:20.173941: step: 1920/530, loss: 0.06632187217473984
2023-01-23 01:07:21.286474: step: 1924/530, loss: 0.023052597418427467
2023-01-23 01:07:22.397800: step: 1928/530, loss: 0.06741275638341904
2023-01-23 01:07:23.504302: step: 1932/530, loss: 0.05406522750854492
2023-01-23 01:07:24.622926: step: 1936/530, loss: 0.030610274523496628
2023-01-23 01:07:25.734931: step: 1940/530, loss: 0.11733102798461914
2023-01-23 01:07:26.854636: step: 1944/530, loss: 0.09982426464557648
2023-01-23 01:07:27.940720: step: 1948/530, loss: 0.04625272750854492
2023-01-23 01:07:29.065831: step: 1952/530, loss: 0.14949455857276917
2023-01-23 01:07:30.178394: step: 1956/530, loss: 0.04653911665081978
2023-01-23 01:07:31.241791: step: 1960/530, loss: 0.25855380296707153
2023-01-23 01:07:32.335718: step: 1964/530, loss: 0.076437808573246
2023-01-23 01:07:33.441169: step: 1968/530, loss: 0.033800315111875534
2023-01-23 01:07:34.503001: step: 1972/530, loss: 0.5211111307144165
2023-01-23 01:07:35.626020: step: 1976/530, loss: 0.021532397717237473
2023-01-23 01:07:36.773424: step: 1980/530, loss: 0.09326867759227753
2023-01-23 01:07:37.925558: step: 1984/530, loss: 0.013794993981719017
2023-01-23 01:07:39.039062: step: 1988/530, loss: 0.16064491868019104
2023-01-23 01:07:40.201722: step: 1992/530, loss: 0.1874007284641266
2023-01-23 01:07:41.314021: step: 1996/530, loss: 0.08353462815284729
2023-01-23 01:07:42.414812: step: 2000/530, loss: 0.031646180897951126
2023-01-23 01:07:43.508100: step: 2004/530, loss: 0.15700717270374298
2023-01-23 01:07:44.616943: step: 2008/530, loss: 0.06414651870727539
2023-01-23 01:07:45.698479: step: 2012/530, loss: 0.02670001983642578
2023-01-23 01:07:46.801266: step: 2016/530, loss: 0.10737305134534836
2023-01-23 01:07:47.905842: step: 2020/530, loss: 0.05547180026769638
2023-01-23 01:07:49.029688: step: 2024/530, loss: 0.041091155260801315
2023-01-23 01:07:50.120668: step: 2028/530, loss: 0.07718295603990555
2023-01-23 01:07:51.226680: step: 2032/530, loss: 0.01485300064086914
2023-01-23 01:07:52.332649: step: 2036/530, loss: 0.26129063963890076
2023-01-23 01:07:53.465979: step: 2040/530, loss: 0.15680618584156036
2023-01-23 01:07:54.557692: step: 2044/530, loss: 0.02359952963888645
2023-01-23 01:07:55.656941: step: 2048/530, loss: 0.09250812232494354
2023-01-23 01:07:56.753497: step: 2052/530, loss: 0.07625351846218109
2023-01-23 01:07:57.880905: step: 2056/530, loss: 0.03449134901165962
2023-01-23 01:07:58.977960: step: 2060/530, loss: 0.06136827543377876
2023-01-23 01:08:00.078388: step: 2064/530, loss: 0.7650858163833618
2023-01-23 01:08:01.174118: step: 2068/530, loss: 0.03203845024108887
2023-01-23 01:08:02.322761: step: 2072/530, loss: 0.024643398821353912
2023-01-23 01:08:03.427241: step: 2076/530, loss: 0.1855226457118988
2023-01-23 01:08:04.539513: step: 2080/530, loss: 0.014832114800810814
2023-01-23 01:08:05.640111: step: 2084/530, loss: 0.03310804441571236
2023-01-23 01:08:06.777533: step: 2088/530, loss: 0.268356055021286
2023-01-23 01:08:07.964512: step: 2092/530, loss: 0.299412339925766
2023-01-23 01:08:09.067108: step: 2096/530, loss: 0.04766654968261719
2023-01-23 01:08:10.191698: step: 2100/530, loss: 0.07706699520349503
2023-01-23 01:08:11.284415: step: 2104/530, loss: 0.021483946591615677
2023-01-23 01:08:12.394688: step: 2108/530, loss: 0.0529605858027935
2023-01-23 01:08:13.476318: step: 2112/530, loss: 0.06573477387428284
2023-01-23 01:08:14.608725: step: 2116/530, loss: 0.0858016386628151
2023-01-23 01:08:15.694170: step: 2120/530, loss: 0.36201468110084534
==================================================
Loss: 0.109
--------------------
Dev: {'event': {'p': 0.5971370143149284, 'r': 0.7776298268974701, 'f1': 0.6755349913244649}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Test: {'event': {'p': 0.6401673640167364, 'r': 0.8024475524475524, 'f1': 0.7121799844840963}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Chinese: {'event': {'p': 0.569620253164557, 'r': 0.8333333333333334, 'f1': 0.6766917293233082}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Korean: {'event': {'p': 0.6862745098039216, 'r': 0.5555555555555556, 'f1': 0.6140350877192983}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Russian: {'event': {'p': 0.5897435897435898, 'r': 0.6388888888888888, 'f1': 0.6133333333333332}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
New best russian model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.5708622398414271, 'r': 0.7669773635153129, 'f1': 0.6545454545454545}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Eng Test for Chinese: {'event': {'p': 0.6044052863436123, 'r': 0.7995337995337995, 'f1': 0.6884094330155545}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Sample Chinese: {'event': {'p': 0.6578947368421053, 'r': 0.9259259259259259, 'f1': 0.7692307692307692}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6466512702078522, 'r': 0.7456724367509987, 'f1': 0.6926406926406927}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Eng Test for Korean: {'event': {'p': 0.6762148337595908, 'r': 0.7703962703962703, 'f1': 0.7202397166984473}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Sample Korean: {'event': {'p': 0.6862745098039216, 'r': 0.5555555555555556, 'f1': 0.6140350877192983}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5971370143149284, 'r': 0.7776298268974701, 'f1': 0.6755349913244649}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Russian: {'event': {'p': 0.6401673640167364, 'r': 0.8024475524475524, 'f1': 0.7121799844840963}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Russian: {'event': {'p': 0.5897435897435898, 'r': 0.6388888888888888, 'f1': 0.6133333333333332}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
******************************
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 01:09:03.679231: step: 4/530, loss: 0.0834735855460167
2023-01-23 01:09:04.826883: step: 8/530, loss: 0.06531648337841034
2023-01-23 01:09:05.924961: step: 12/530, loss: 0.02104969136416912
2023-01-23 01:09:07.028121: step: 16/530, loss: 1.4563148021697998
2023-01-23 01:09:08.094338: step: 20/530, loss: 0.09583454579114914
2023-01-23 01:09:09.163646: step: 24/530, loss: 0.04431591182947159
2023-01-23 01:09:10.261990: step: 28/530, loss: 0.05222749710083008
2023-01-23 01:09:11.388486: step: 32/530, loss: 0.48342904448509216
2023-01-23 01:09:12.518321: step: 36/530, loss: 0.06960248947143555
2023-01-23 01:09:13.635161: step: 40/530, loss: 0.09375648200511932
2023-01-23 01:09:14.747064: step: 44/530, loss: 0.02256631851196289
2023-01-23 01:09:15.871760: step: 48/530, loss: 0.22881126403808594
2023-01-23 01:09:16.988353: step: 52/530, loss: 0.09813786298036575
2023-01-23 01:09:18.097113: step: 56/530, loss: 0.011032533831894398
2023-01-23 01:09:19.196232: step: 60/530, loss: 0.06088457629084587
2023-01-23 01:09:20.305808: step: 64/530, loss: 0.027191925793886185
2023-01-23 01:09:21.387927: step: 68/530, loss: 0.04366140812635422
2023-01-23 01:09:22.484891: step: 72/530, loss: 0.0096893310546875
2023-01-23 01:09:23.574531: step: 76/530, loss: 0.011082840152084827
2023-01-23 01:09:24.654166: step: 80/530, loss: 0.04648271203041077
2023-01-23 01:09:25.818996: step: 84/530, loss: 0.21836671233177185
2023-01-23 01:09:26.890520: step: 88/530, loss: 0.03273162990808487
2023-01-23 01:09:28.007764: step: 92/530, loss: 0.045271970331668854
2023-01-23 01:09:29.111486: step: 96/530, loss: 0.05436506122350693
2023-01-23 01:09:30.202294: step: 100/530, loss: 0.08144054561853409
2023-01-23 01:09:31.319309: step: 104/530, loss: 0.03153381496667862
2023-01-23 01:09:32.435117: step: 108/530, loss: 0.05513410642743111
2023-01-23 01:09:33.551130: step: 112/530, loss: 0.04428587108850479
2023-01-23 01:09:34.660197: step: 116/530, loss: 0.06590643525123596
2023-01-23 01:09:35.746080: step: 120/530, loss: 0.2835732102394104
2023-01-23 01:09:36.833043: step: 124/530, loss: 0.0005710602272301912
2023-01-23 01:09:37.934273: step: 128/530, loss: 0.0423736572265625
2023-01-23 01:09:39.032061: step: 132/530, loss: 0.1969594955444336
2023-01-23 01:09:40.111041: step: 136/530, loss: 0.046848200261592865
2023-01-23 01:09:41.256811: step: 140/530, loss: 0.11491279304027557
2023-01-23 01:09:42.354357: step: 144/530, loss: 0.08374185860157013
2023-01-23 01:09:43.450691: step: 148/530, loss: 0.3090837299823761
2023-01-23 01:09:44.528627: step: 152/530, loss: 0.1806931048631668
2023-01-23 01:09:45.624106: step: 156/530, loss: 0.07658844441175461
2023-01-23 01:09:46.725780: step: 160/530, loss: 0.0014497756492346525
2023-01-23 01:09:47.793953: step: 164/530, loss: 0.02380204200744629
2023-01-23 01:09:48.888904: step: 168/530, loss: 0.02237396314740181
2023-01-23 01:09:49.978372: step: 172/530, loss: 0.062426187098026276
2023-01-23 01:09:51.088737: step: 176/530, loss: 0.05280666798353195
2023-01-23 01:09:52.209957: step: 180/530, loss: 0.12218570709228516
2023-01-23 01:09:53.310271: step: 184/530, loss: 0.031491946429014206
2023-01-23 01:09:54.414878: step: 188/530, loss: 0.012024307623505592
2023-01-23 01:09:55.526200: step: 192/530, loss: 0.022630594670772552
2023-01-23 01:09:56.644685: step: 196/530, loss: 0.018315697088837624
2023-01-23 01:09:57.760800: step: 200/530, loss: 0.027228165417909622
2023-01-23 01:09:58.871497: step: 204/530, loss: 0.007268715184181929
2023-01-23 01:09:59.973508: step: 208/530, loss: 0.03626976162195206
2023-01-23 01:10:01.108920: step: 212/530, loss: 0.24929890036582947
2023-01-23 01:10:02.232189: step: 216/530, loss: 0.03481864929199219
2023-01-23 01:10:03.334186: step: 220/530, loss: 0.03411092609167099
2023-01-23 01:10:04.433396: step: 224/530, loss: 0.05981817469000816
2023-01-23 01:10:05.541197: step: 228/530, loss: 0.13779029250144958
2023-01-23 01:10:06.635744: step: 232/530, loss: 0.00806660670787096
2023-01-23 01:10:07.738853: step: 236/530, loss: 0.028628967702388763
2023-01-23 01:10:08.868825: step: 240/530, loss: 0.10116253048181534
2023-01-23 01:10:09.976170: step: 244/530, loss: 0.010532760992646217
2023-01-23 01:10:11.056725: step: 248/530, loss: 0.028371762484312057
2023-01-23 01:10:12.186730: step: 252/530, loss: 0.05829181522130966
2023-01-23 01:10:13.264620: step: 256/530, loss: 0.0021398544777184725
2023-01-23 01:10:14.406349: step: 260/530, loss: 0.10395526885986328
2023-01-23 01:10:15.504361: step: 264/530, loss: 0.36564120650291443
2023-01-23 01:10:16.610057: step: 268/530, loss: 0.07277374714612961
2023-01-23 01:10:17.765708: step: 272/530, loss: 0.08302745968103409
2023-01-23 01:10:18.882684: step: 276/530, loss: 0.0510522834956646
2023-01-23 01:10:19.977919: step: 280/530, loss: 0.02546558529138565
2023-01-23 01:10:21.082716: step: 284/530, loss: 0.05524082109332085
2023-01-23 01:10:22.163335: step: 288/530, loss: 0.023154258728027344
2023-01-23 01:10:23.262626: step: 292/530, loss: 0.22347183525562286
2023-01-23 01:10:24.384472: step: 296/530, loss: 0.009690475650131702
2023-01-23 01:10:25.496440: step: 300/530, loss: 0.2514456808567047
2023-01-23 01:10:26.622188: step: 304/530, loss: 0.12265624105930328
2023-01-23 01:10:27.723270: step: 308/530, loss: 0.049795106053352356
2023-01-23 01:10:28.823708: step: 312/530, loss: 0.03181672468781471
2023-01-23 01:10:29.929122: step: 316/530, loss: 0.09142627567052841
2023-01-23 01:10:31.020976: step: 320/530, loss: 0.02604513242840767
2023-01-23 01:10:32.117360: step: 324/530, loss: 0.057601165026426315
2023-01-23 01:10:33.246748: step: 328/530, loss: 0.007393264677375555
2023-01-23 01:10:34.370574: step: 332/530, loss: 0.14607840776443481
2023-01-23 01:10:35.454981: step: 336/530, loss: 0.030007457360625267
2023-01-23 01:10:36.568403: step: 340/530, loss: 0.054877281188964844
2023-01-23 01:10:37.662438: step: 344/530, loss: 0.006588459014892578
2023-01-23 01:10:38.761996: step: 348/530, loss: 0.028640173375606537
2023-01-23 01:10:39.917928: step: 352/530, loss: 0.10570058971643448
2023-01-23 01:10:41.025472: step: 356/530, loss: 0.01734349876642227
2023-01-23 01:10:42.126853: step: 360/530, loss: 0.07597538828849792
2023-01-23 01:10:43.249177: step: 364/530, loss: 0.15829753875732422
2023-01-23 01:10:44.377131: step: 368/530, loss: 0.02716798707842827
2023-01-23 01:10:45.489912: step: 372/530, loss: 0.0546695739030838
2023-01-23 01:10:46.595594: step: 376/530, loss: 0.06157340854406357
2023-01-23 01:10:47.718930: step: 380/530, loss: 0.13005714118480682
2023-01-23 01:10:48.834129: step: 384/530, loss: 0.3410007953643799
2023-01-23 01:10:49.949303: step: 388/530, loss: 0.07926854491233826
2023-01-23 01:10:51.064499: step: 392/530, loss: 0.018945885822176933
2023-01-23 01:10:52.158993: step: 396/530, loss: 0.021465228870511055
2023-01-23 01:10:53.240693: step: 400/530, loss: 0.02206391841173172
2023-01-23 01:10:54.339409: step: 404/530, loss: 0.013283634558320045
2023-01-23 01:10:55.460330: step: 408/530, loss: 0.05972748249769211
2023-01-23 01:10:56.578123: step: 412/530, loss: 0.027878714725375175
2023-01-23 01:10:57.696691: step: 416/530, loss: 0.05552997812628746
2023-01-23 01:10:58.805494: step: 420/530, loss: 0.11758479475975037
2023-01-23 01:10:59.920237: step: 424/530, loss: 0.08100011199712753
2023-01-23 01:11:01.028629: step: 428/530, loss: 0.2722596228122711
2023-01-23 01:11:02.111308: step: 432/530, loss: 0.03753519058227539
2023-01-23 01:11:03.209373: step: 436/530, loss: 0.10826301574707031
2023-01-23 01:11:04.299024: step: 440/530, loss: 0.05514087900519371
2023-01-23 01:11:05.409705: step: 444/530, loss: 0.046673014760017395
2023-01-23 01:11:06.504176: step: 448/530, loss: 0.029434965923428535
2023-01-23 01:11:07.604011: step: 452/530, loss: 0.07514429092407227
2023-01-23 01:11:08.689672: step: 456/530, loss: 0.007110118865966797
2023-01-23 01:11:09.784839: step: 460/530, loss: 0.03357858583331108
2023-01-23 01:11:10.877846: step: 464/530, loss: 0.048253823071718216
2023-01-23 01:11:11.976611: step: 468/530, loss: 0.42511633038520813
2023-01-23 01:11:13.131049: step: 472/530, loss: 0.10517702251672745
2023-01-23 01:11:14.220225: step: 476/530, loss: 0.09064006805419922
2023-01-23 01:11:15.323888: step: 480/530, loss: 0.015919208526611328
2023-01-23 01:11:16.437025: step: 484/530, loss: 0.00928888376802206
2023-01-23 01:11:17.523324: step: 488/530, loss: 0.045835305005311966
2023-01-23 01:11:18.617794: step: 492/530, loss: 0.10745306313037872
2023-01-23 01:11:19.726540: step: 496/530, loss: 0.013304520398378372
2023-01-23 01:11:20.828720: step: 500/530, loss: 0.07792044430971146
2023-01-23 01:11:21.936742: step: 504/530, loss: 0.12546634674072266
2023-01-23 01:11:23.049726: step: 508/530, loss: 0.5122291445732117
2023-01-23 01:11:24.153866: step: 512/530, loss: 0.03413867950439453
2023-01-23 01:11:25.227219: step: 516/530, loss: 0.0019414902199059725
2023-01-23 01:11:26.356627: step: 520/530, loss: 0.0027006627060472965
2023-01-23 01:11:27.465448: step: 524/530, loss: 0.09243831783533096
2023-01-23 01:11:28.590366: step: 528/530, loss: 0.12032070010900497
2023-01-23 01:11:29.727911: step: 532/530, loss: 0.034134864807128906
2023-01-23 01:11:30.826714: step: 536/530, loss: 0.05949496105313301
2023-01-23 01:11:31.933501: step: 540/530, loss: 0.2151658982038498
2023-01-23 01:11:33.028436: step: 544/530, loss: 0.09138303250074387
2023-01-23 01:11:34.133250: step: 548/530, loss: 0.06074059009552002
2023-01-23 01:11:35.234834: step: 552/530, loss: 0.03937659412622452
2023-01-23 01:11:36.370360: step: 556/530, loss: 0.46185609698295593
2023-01-23 01:11:37.540546: step: 560/530, loss: 0.07926788181066513
2023-01-23 01:11:38.656149: step: 564/530, loss: 0.0252514835447073
2023-01-23 01:11:39.757879: step: 568/530, loss: 0.023298712447285652
2023-01-23 01:11:40.849198: step: 572/530, loss: 0.030413247644901276
2023-01-23 01:11:41.938361: step: 576/530, loss: 0.04990358278155327
2023-01-23 01:11:43.036622: step: 580/530, loss: 0.18456298112869263
2023-01-23 01:11:44.149844: step: 584/530, loss: 0.07024664431810379
2023-01-23 01:11:45.265572: step: 588/530, loss: 0.002684021135792136
2023-01-23 01:11:46.375156: step: 592/530, loss: 0.01882925070822239
2023-01-23 01:11:47.502224: step: 596/530, loss: 0.028644084930419922
2023-01-23 01:11:48.601231: step: 600/530, loss: 0.04327097907662392
2023-01-23 01:11:49.723973: step: 604/530, loss: 0.08436079323291779
2023-01-23 01:11:50.830922: step: 608/530, loss: 0.04987182468175888
2023-01-23 01:11:51.915125: step: 612/530, loss: 0.18709707260131836
2023-01-23 01:11:53.027215: step: 616/530, loss: 0.012269115075469017
2023-01-23 01:11:54.152781: step: 620/530, loss: 0.5628917813301086
2023-01-23 01:11:55.247938: step: 624/530, loss: 0.08262629061937332
2023-01-23 01:11:56.339220: step: 628/530, loss: 0.07671672105789185
2023-01-23 01:11:57.477862: step: 632/530, loss: 0.03874702751636505
2023-01-23 01:11:58.597358: step: 636/530, loss: 0.09352779388427734
2023-01-23 01:11:59.713328: step: 640/530, loss: 0.05353522300720215
2023-01-23 01:12:00.814820: step: 644/530, loss: 0.004307246301323175
2023-01-23 01:12:01.881774: step: 648/530, loss: 0.1020701453089714
2023-01-23 01:12:02.993958: step: 652/530, loss: 0.009965991601347923
2023-01-23 01:12:04.069207: step: 656/530, loss: 0.069349005818367
2023-01-23 01:12:05.184826: step: 660/530, loss: 0.038263607770204544
2023-01-23 01:12:06.279035: step: 664/530, loss: 0.013882064260542393
2023-01-23 01:12:07.391795: step: 668/530, loss: 0.021936701610684395
2023-01-23 01:12:08.498828: step: 672/530, loss: 0.04935512691736221
2023-01-23 01:12:09.595810: step: 676/530, loss: 0.0045105936005711555
2023-01-23 01:12:10.720272: step: 680/530, loss: 0.061463452875614166
2023-01-23 01:12:11.832563: step: 684/530, loss: 0.04592590406537056
2023-01-23 01:12:12.921777: step: 688/530, loss: 0.07534332573413849
2023-01-23 01:12:14.075350: step: 692/530, loss: 0.035222575068473816
2023-01-23 01:12:15.165650: step: 696/530, loss: 0.05991983413696289
2023-01-23 01:12:16.278035: step: 700/530, loss: 0.058161258697509766
2023-01-23 01:12:17.392130: step: 704/530, loss: 0.6873898506164551
2023-01-23 01:12:18.483231: step: 708/530, loss: 0.13362407684326172
2023-01-23 01:12:19.593457: step: 712/530, loss: 0.02099323272705078
2023-01-23 01:12:20.706244: step: 716/530, loss: 0.003944134805351496
2023-01-23 01:12:21.800892: step: 720/530, loss: 0.023998450487852097
2023-01-23 01:12:22.896077: step: 724/530, loss: 0.03330354765057564
2023-01-23 01:12:23.992779: step: 728/530, loss: 0.04715704917907715
2023-01-23 01:12:25.114918: step: 732/530, loss: 0.01619720458984375
2023-01-23 01:12:26.234144: step: 736/530, loss: 0.007481765933334827
2023-01-23 01:12:27.371454: step: 740/530, loss: 0.06180219724774361
2023-01-23 01:12:28.472003: step: 744/530, loss: 0.1401459276676178
2023-01-23 01:12:29.587723: step: 748/530, loss: 0.21897634863853455
2023-01-23 01:12:30.696015: step: 752/530, loss: 0.07128188759088516
2023-01-23 01:12:31.814099: step: 756/530, loss: 0.003999615088105202
2023-01-23 01:12:32.944377: step: 760/530, loss: 0.052939701825380325
2023-01-23 01:12:34.044565: step: 764/530, loss: 0.015442252159118652
2023-01-23 01:12:35.163597: step: 768/530, loss: 0.17858104407787323
2023-01-23 01:12:36.278241: step: 772/530, loss: 0.01694483868777752
2023-01-23 01:12:37.385959: step: 776/530, loss: 0.04257345199584961
2023-01-23 01:12:38.480079: step: 780/530, loss: 0.01818552054464817
2023-01-23 01:12:39.593318: step: 784/530, loss: 0.06434686481952667
2023-01-23 01:12:40.687639: step: 788/530, loss: 0.039573170244693756
2023-01-23 01:12:41.809148: step: 792/530, loss: 0.020193099975585938
2023-01-23 01:12:42.940553: step: 796/530, loss: 0.23294369876384735
2023-01-23 01:12:44.053704: step: 800/530, loss: 0.06156263127923012
2023-01-23 01:12:45.160566: step: 804/530, loss: 0.023204898461699486
2023-01-23 01:12:46.259972: step: 808/530, loss: 0.10833749175071716
2023-01-23 01:12:47.359748: step: 812/530, loss: 0.0756952315568924
2023-01-23 01:12:48.464520: step: 816/530, loss: 0.43404093384742737
2023-01-23 01:12:49.559641: step: 820/530, loss: 0.10713472962379456
2023-01-23 01:12:50.647071: step: 824/530, loss: 0.2257017195224762
2023-01-23 01:12:51.749014: step: 828/530, loss: 0.17161358892917633
2023-01-23 01:12:52.851119: step: 832/530, loss: 0.06517940014600754
2023-01-23 01:12:53.962622: step: 836/530, loss: 0.08382339775562286
2023-01-23 01:12:55.068091: step: 840/530, loss: 0.008511734195053577
2023-01-23 01:12:56.180824: step: 844/530, loss: 0.22435151040554047
2023-01-23 01:12:57.274982: step: 848/530, loss: 0.03380937501788139
2023-01-23 01:12:58.374311: step: 852/530, loss: 0.12638626992702484
2023-01-23 01:12:59.484090: step: 856/530, loss: 0.1400773972272873
2023-01-23 01:13:00.567943: step: 860/530, loss: 0.057898808270692825
2023-01-23 01:13:01.662435: step: 864/530, loss: 0.03015538491308689
2023-01-23 01:13:02.780236: step: 868/530, loss: 0.06649813801050186
2023-01-23 01:13:03.888557: step: 872/530, loss: 0.07771673053503036
2023-01-23 01:13:04.991648: step: 876/530, loss: 0.08896628022193909
2023-01-23 01:13:06.092580: step: 880/530, loss: 0.045725442469120026
2023-01-23 01:13:07.185461: step: 884/530, loss: 0.05918693542480469
2023-01-23 01:13:08.270800: step: 888/530, loss: 0.03636446222662926
2023-01-23 01:13:09.408926: step: 892/530, loss: 0.0028726577293127775
2023-01-23 01:13:10.507649: step: 896/530, loss: 0.0045986175537109375
2023-01-23 01:13:11.605656: step: 900/530, loss: 0.12170648574829102
2023-01-23 01:13:12.711039: step: 904/530, loss: 0.14712266623973846
2023-01-23 01:13:13.812782: step: 908/530, loss: 0.10480928421020508
2023-01-23 01:13:14.940152: step: 912/530, loss: 0.013826894573867321
2023-01-23 01:13:16.043086: step: 916/530, loss: 0.003726482391357422
2023-01-23 01:13:17.160496: step: 920/530, loss: 0.03209862485527992
2023-01-23 01:13:18.282532: step: 924/530, loss: 0.028798487037420273
2023-01-23 01:13:19.388636: step: 928/530, loss: 0.04057502746582031
2023-01-23 01:13:20.529117: step: 932/530, loss: 0.812938392162323
2023-01-23 01:13:21.617475: step: 936/530, loss: 0.26519739627838135
2023-01-23 01:13:22.734540: step: 940/530, loss: 0.046123601496219635
2023-01-23 01:13:23.847778: step: 944/530, loss: 0.031608011573553085
2023-01-23 01:13:24.996886: step: 948/530, loss: 0.03800716623663902
2023-01-23 01:13:26.143359: step: 952/530, loss: 0.07375270873308182
2023-01-23 01:13:27.280435: step: 956/530, loss: 0.026720141991972923
2023-01-23 01:13:28.395532: step: 960/530, loss: 0.07317686080932617
2023-01-23 01:13:29.498738: step: 964/530, loss: 0.021296881139278412
2023-01-23 01:13:30.645161: step: 968/530, loss: 0.026706887409090996
2023-01-23 01:13:31.735448: step: 972/530, loss: 0.0815461203455925
2023-01-23 01:13:32.827120: step: 976/530, loss: 0.29885920882225037
2023-01-23 01:13:33.968796: step: 980/530, loss: 0.03130531311035156
2023-01-23 01:13:35.080225: step: 984/530, loss: 0.09579449146986008
2023-01-23 01:13:36.187223: step: 988/530, loss: 0.21842169761657715
2023-01-23 01:13:37.318286: step: 992/530, loss: 0.035544779151678085
2023-01-23 01:13:38.454057: step: 996/530, loss: 0.021796513348817825
2023-01-23 01:13:39.564004: step: 1000/530, loss: 0.04416842758655548
2023-01-23 01:13:40.724310: step: 1004/530, loss: 0.039066411554813385
2023-01-23 01:13:41.882408: step: 1008/530, loss: 0.06291083991527557
2023-01-23 01:13:42.990577: step: 1012/530, loss: 0.09093169867992401
2023-01-23 01:13:44.101433: step: 1016/530, loss: 0.20161285996437073
2023-01-23 01:13:45.241395: step: 1020/530, loss: 0.057431790977716446
2023-01-23 01:13:46.357587: step: 1024/530, loss: 0.07357635349035263
2023-01-23 01:13:47.481524: step: 1028/530, loss: 0.0789494514465332
2023-01-23 01:13:48.593889: step: 1032/530, loss: 0.09398308396339417
2023-01-23 01:13:49.702293: step: 1036/530, loss: 0.03413248062133789
2023-01-23 01:13:50.836516: step: 1040/530, loss: 0.056510262191295624
2023-01-23 01:13:51.937589: step: 1044/530, loss: 0.06041078269481659
2023-01-23 01:13:53.025055: step: 1048/530, loss: 0.07611873000860214
2023-01-23 01:13:54.144346: step: 1052/530, loss: 0.0721227154135704
2023-01-23 01:13:55.234958: step: 1056/530, loss: 0.04976511001586914
2023-01-23 01:13:56.390819: step: 1060/530, loss: 0.08610481768846512
2023-01-23 01:13:57.508182: step: 1064/530, loss: 0.13222475349903107
2023-01-23 01:13:58.626962: step: 1068/530, loss: 0.03965482860803604
2023-01-23 01:13:59.732331: step: 1072/530, loss: 0.14394934475421906
2023-01-23 01:14:00.847727: step: 1076/530, loss: 0.01928567886352539
2023-01-23 01:14:01.929716: step: 1080/530, loss: 0.00718533992767334
2023-01-23 01:14:03.045387: step: 1084/530, loss: 1.941673994064331
2023-01-23 01:14:04.167776: step: 1088/530, loss: 0.2159833014011383
2023-01-23 01:14:05.312147: step: 1092/530, loss: 0.020224381238222122
2023-01-23 01:14:06.399503: step: 1096/530, loss: 0.03317739814519882
2023-01-23 01:14:07.512066: step: 1100/530, loss: 0.046278856694698334
2023-01-23 01:14:08.616338: step: 1104/530, loss: 0.08630237728357315
2023-01-23 01:14:09.713766: step: 1108/530, loss: 0.04170408472418785
2023-01-23 01:14:10.832177: step: 1112/530, loss: 0.03770847246050835
2023-01-23 01:14:11.925446: step: 1116/530, loss: 0.04045286029577255
2023-01-23 01:14:13.037596: step: 1120/530, loss: 0.10530614852905273
2023-01-23 01:14:14.137986: step: 1124/530, loss: 0.013080048374831676
2023-01-23 01:14:15.266033: step: 1128/530, loss: 0.03911328688263893
2023-01-23 01:14:16.410053: step: 1132/530, loss: 0.06311684101819992
2023-01-23 01:14:17.515307: step: 1136/530, loss: 0.3849724531173706
2023-01-23 01:14:18.616655: step: 1140/530, loss: 0.04035468399524689
2023-01-23 01:14:19.734975: step: 1144/530, loss: 0.06432771682739258
2023-01-23 01:14:20.854088: step: 1148/530, loss: 0.0263398177921772
2023-01-23 01:14:21.953741: step: 1152/530, loss: 0.05226574093103409
2023-01-23 01:14:23.074912: step: 1156/530, loss: 0.0528779998421669
2023-01-23 01:14:24.219413: step: 1160/530, loss: 0.035801030695438385
2023-01-23 01:14:25.344190: step: 1164/530, loss: 0.00797119177877903
2023-01-23 01:14:26.444328: step: 1168/530, loss: 0.03395795822143555
2023-01-23 01:14:27.569619: step: 1172/530, loss: 0.11708612740039825
2023-01-23 01:14:28.681856: step: 1176/530, loss: 0.0692654624581337
2023-01-23 01:14:29.788901: step: 1180/530, loss: 0.0196533203125
2023-01-23 01:14:30.890298: step: 1184/530, loss: 0.04314699396491051
2023-01-23 01:14:31.979325: step: 1188/530, loss: 0.03473053127527237
2023-01-23 01:14:33.153767: step: 1192/530, loss: 0.21452751755714417
2023-01-23 01:14:34.307837: step: 1196/530, loss: 0.08094115555286407
2023-01-23 01:14:35.413968: step: 1200/530, loss: 0.002301883650943637
2023-01-23 01:14:36.514786: step: 1204/530, loss: 0.016067886725068092
2023-01-23 01:14:37.607911: step: 1208/530, loss: 0.07824338972568512
2023-01-23 01:14:38.702577: step: 1212/530, loss: 0.060262683779001236
2023-01-23 01:14:39.820111: step: 1216/530, loss: 0.01785602606832981
2023-01-23 01:14:40.914349: step: 1220/530, loss: 0.02940216101706028
2023-01-23 01:14:42.043907: step: 1224/530, loss: 0.04442715644836426
2023-01-23 01:14:43.151467: step: 1228/530, loss: 0.013821602798998356
2023-01-23 01:14:44.229094: step: 1232/530, loss: 0.06709976494312286
2023-01-23 01:14:45.348670: step: 1236/530, loss: 0.22147181630134583
2023-01-23 01:14:46.438197: step: 1240/530, loss: 0.31296637654304504
2023-01-23 01:14:47.539377: step: 1244/530, loss: 0.040456678718328476
2023-01-23 01:14:48.644713: step: 1248/530, loss: 0.004106124397367239
2023-01-23 01:14:49.759988: step: 1252/530, loss: 0.2375870794057846
2023-01-23 01:14:50.885595: step: 1256/530, loss: 0.06646070629358292
2023-01-23 01:14:52.005065: step: 1260/530, loss: 0.10059194266796112
2023-01-23 01:14:53.085524: step: 1264/530, loss: 0.009367180056869984
2023-01-23 01:14:54.212361: step: 1268/530, loss: 0.23852328956127167
2023-01-23 01:14:55.359932: step: 1272/530, loss: 0.06304369121789932
2023-01-23 01:14:56.490021: step: 1276/530, loss: 0.4579445719718933
2023-01-23 01:14:57.582740: step: 1280/530, loss: 0.010230732150375843
2023-01-23 01:14:58.685119: step: 1284/530, loss: 0.06442470848560333
2023-01-23 01:14:59.787027: step: 1288/530, loss: 0.04117155447602272
2023-01-23 01:15:00.905640: step: 1292/530, loss: 0.14889155328273773
2023-01-23 01:15:02.043822: step: 1296/530, loss: 0.038118839263916016
2023-01-23 01:15:03.155452: step: 1300/530, loss: 0.09388618171215057
2023-01-23 01:15:04.291377: step: 1304/530, loss: 0.035646773874759674
2023-01-23 01:15:05.408607: step: 1308/530, loss: 0.36589887738227844
2023-01-23 01:15:06.526164: step: 1312/530, loss: 0.12225160747766495
2023-01-23 01:15:07.648504: step: 1316/530, loss: 0.12188606709241867
2023-01-23 01:15:08.763222: step: 1320/530, loss: 0.0367191806435585
2023-01-23 01:15:09.879072: step: 1324/530, loss: 0.05857901647686958
2023-01-23 01:15:10.983873: step: 1328/530, loss: 0.48173198103904724
2023-01-23 01:15:12.123658: step: 1332/530, loss: 0.0340024009346962
2023-01-23 01:15:13.222643: step: 1336/530, loss: 0.014490509405732155
2023-01-23 01:15:14.321397: step: 1340/530, loss: 0.03950996324419975
2023-01-23 01:15:15.405984: step: 1344/530, loss: 0.02537059783935547
2023-01-23 01:15:16.518774: step: 1348/530, loss: 0.009778786450624466
2023-01-23 01:15:17.618762: step: 1352/530, loss: 0.046988748013973236
2023-01-23 01:15:18.728338: step: 1356/530, loss: 0.04196920618414879
2023-01-23 01:15:19.829990: step: 1360/530, loss: 0.05027418211102486
2023-01-23 01:15:20.963535: step: 1364/530, loss: 0.04635734483599663
2023-01-23 01:15:22.056867: step: 1368/530, loss: 0.10426755249500275
2023-01-23 01:15:23.154839: step: 1372/530, loss: 0.04180192947387695
2023-01-23 01:15:24.266093: step: 1376/530, loss: 0.060674384236335754
2023-01-23 01:15:25.372838: step: 1380/530, loss: 0.04168133810162544
2023-01-23 01:15:26.464418: step: 1384/530, loss: 0.013026809319853783
2023-01-23 01:15:27.604407: step: 1388/530, loss: 0.0715143233537674
2023-01-23 01:15:28.699778: step: 1392/530, loss: 0.06671466678380966
2023-01-23 01:15:29.817465: step: 1396/530, loss: 0.3159492611885071
2023-01-23 01:15:30.940751: step: 1400/530, loss: 0.21715860068798065
2023-01-23 01:15:32.042406: step: 1404/530, loss: 0.11965981125831604
2023-01-23 01:15:33.160657: step: 1408/530, loss: 0.009777355939149857
2023-01-23 01:15:34.261739: step: 1412/530, loss: 0.068603515625
2023-01-23 01:15:35.358783: step: 1416/530, loss: 0.044983960688114166
2023-01-23 01:15:36.499461: step: 1420/530, loss: 0.4129413068294525
2023-01-23 01:15:37.630767: step: 1424/530, loss: 0.08805418014526367
2023-01-23 01:15:38.717028: step: 1428/530, loss: 0.03787889704108238
2023-01-23 01:15:39.806418: step: 1432/530, loss: 0.011502361856400967
2023-01-23 01:15:40.892720: step: 1436/530, loss: 0.16273340582847595
2023-01-23 01:15:41.989481: step: 1440/530, loss: 0.11285905539989471
2023-01-23 01:15:43.085490: step: 1444/530, loss: 0.06554565578699112
2023-01-23 01:15:44.175425: step: 1448/530, loss: 0.013885116204619408
2023-01-23 01:15:45.303097: step: 1452/530, loss: 0.10244350135326385
2023-01-23 01:15:46.398073: step: 1456/530, loss: 0.46494922041893005
2023-01-23 01:15:47.511287: step: 1460/530, loss: 0.1074582114815712
2023-01-23 01:15:48.637727: step: 1464/530, loss: 0.025861645117402077
2023-01-23 01:15:49.744789: step: 1468/530, loss: 0.0388367623090744
2023-01-23 01:15:50.874737: step: 1472/530, loss: 0.05124073103070259
2023-01-23 01:15:51.967255: step: 1476/530, loss: 0.3171003460884094
2023-01-23 01:15:53.082293: step: 1480/530, loss: 0.4540640413761139
2023-01-23 01:15:54.193771: step: 1484/530, loss: 0.40675750374794006
2023-01-23 01:15:55.311540: step: 1488/530, loss: 0.0033395770005881786
2023-01-23 01:15:56.420914: step: 1492/530, loss: 0.3871908187866211
2023-01-23 01:15:57.514766: step: 1496/530, loss: 0.04248657450079918
2023-01-23 01:15:58.622646: step: 1500/530, loss: 0.06422571837902069
2023-01-23 01:15:59.732032: step: 1504/530, loss: 0.12141895294189453
2023-01-23 01:16:00.832780: step: 1508/530, loss: 0.0391656868159771
2023-01-23 01:16:01.914169: step: 1512/530, loss: 0.049579814076423645
2023-01-23 01:16:03.007284: step: 1516/530, loss: 0.07856154441833496
2023-01-23 01:16:04.105922: step: 1520/530, loss: 0.020325278863310814
2023-01-23 01:16:05.209278: step: 1524/530, loss: 0.09964756667613983
2023-01-23 01:16:06.338501: step: 1528/530, loss: 0.18442697823047638
2023-01-23 01:16:07.444307: step: 1532/530, loss: 0.38138407468795776
2023-01-23 01:16:08.595490: step: 1536/530, loss: 0.017789460718631744
2023-01-23 01:16:09.743021: step: 1540/530, loss: 0.12706327438354492
2023-01-23 01:16:10.859434: step: 1544/530, loss: 0.05959014967083931
2023-01-23 01:16:11.980170: step: 1548/530, loss: 0.13648748397827148
2023-01-23 01:16:13.094812: step: 1552/530, loss: 0.020630933344364166
2023-01-23 01:16:14.236229: step: 1556/530, loss: 0.1003485694527626
2023-01-23 01:16:15.394776: step: 1560/530, loss: 0.10602112114429474
2023-01-23 01:16:16.541302: step: 1564/530, loss: 0.0911487564444542
2023-01-23 01:16:17.686591: step: 1568/530, loss: 0.029360296204686165
2023-01-23 01:16:18.826527: step: 1572/530, loss: 0.03755206987261772
2023-01-23 01:16:19.957423: step: 1576/530, loss: 0.09202270209789276
2023-01-23 01:16:21.083576: step: 1580/530, loss: 0.09042072296142578
2023-01-23 01:16:22.213304: step: 1584/530, loss: 0.13148507475852966
2023-01-23 01:16:23.301649: step: 1588/530, loss: 0.019042586907744408
2023-01-23 01:16:24.394953: step: 1592/530, loss: 0.051201630383729935
2023-01-23 01:16:25.540804: step: 1596/530, loss: 0.0725800171494484
2023-01-23 01:16:26.647613: step: 1600/530, loss: 0.024500275030732155
2023-01-23 01:16:27.758720: step: 1604/530, loss: 0.048778679221868515
2023-01-23 01:16:28.862696: step: 1608/530, loss: 0.04110026732087135
2023-01-23 01:16:29.956368: step: 1612/530, loss: 0.14023666083812714
2023-01-23 01:16:31.082923: step: 1616/530, loss: 0.24167995154857635
2023-01-23 01:16:32.206538: step: 1620/530, loss: 0.13343429565429688
2023-01-23 01:16:33.342132: step: 1624/530, loss: 0.3986698091030121
2023-01-23 01:16:34.433138: step: 1628/530, loss: 0.011958790011703968
2023-01-23 01:16:35.557237: step: 1632/530, loss: 0.042142488062381744
2023-01-23 01:16:36.645361: step: 1636/530, loss: 0.0029730796813964844
2023-01-23 01:16:37.749451: step: 1640/530, loss: 0.08714018017053604
2023-01-23 01:16:38.874567: step: 1644/530, loss: 0.08416728675365448
2023-01-23 01:16:39.979411: step: 1648/530, loss: 0.1551641970872879
2023-01-23 01:16:41.061159: step: 1652/530, loss: 0.24525488913059235
2023-01-23 01:16:42.147291: step: 1656/530, loss: 0.624038577079773
2023-01-23 01:16:43.239451: step: 1660/530, loss: 0.04034533351659775
2023-01-23 01:16:44.334019: step: 1664/530, loss: 0.054014015942811966
2023-01-23 01:16:45.445936: step: 1668/530, loss: 0.012287164106965065
2023-01-23 01:16:46.568792: step: 1672/530, loss: 0.4195510745048523
2023-01-23 01:16:47.682704: step: 1676/530, loss: 1.1276097297668457
2023-01-23 01:16:48.783680: step: 1680/530, loss: 0.024541163817048073
2023-01-23 01:16:49.895378: step: 1684/530, loss: 0.05865850672125816
2023-01-23 01:16:51.007773: step: 1688/530, loss: 0.01982259750366211
2023-01-23 01:16:52.163813: step: 1692/530, loss: 0.12230491638183594
2023-01-23 01:16:53.252560: step: 1696/530, loss: 0.03255271911621094
2023-01-23 01:16:54.357740: step: 1700/530, loss: 0.1069973036646843
2023-01-23 01:16:55.459279: step: 1704/530, loss: 0.07531814277172089
2023-01-23 01:16:56.560378: step: 1708/530, loss: 0.016759682446718216
2023-01-23 01:16:57.659473: step: 1712/530, loss: 0.06693068146705627
2023-01-23 01:16:58.788531: step: 1716/530, loss: 0.0857764258980751
2023-01-23 01:16:59.871251: step: 1720/530, loss: 0.018464839085936546
2023-01-23 01:17:00.980663: step: 1724/530, loss: 0.02588810957968235
2023-01-23 01:17:02.073845: step: 1728/530, loss: 0.030108120292425156
2023-01-23 01:17:03.185913: step: 1732/530, loss: 0.03959674760699272
2023-01-23 01:17:04.288061: step: 1736/530, loss: 0.02285795286297798
2023-01-23 01:17:05.386925: step: 1740/530, loss: 0.10198817402124405
2023-01-23 01:17:06.510584: step: 1744/530, loss: 0.08242588490247726
2023-01-23 01:17:07.613529: step: 1748/530, loss: 0.08125295490026474
2023-01-23 01:17:08.712160: step: 1752/530, loss: 0.05591898411512375
2023-01-23 01:17:09.811875: step: 1756/530, loss: 0.04361391067504883
2023-01-23 01:17:10.913901: step: 1760/530, loss: 0.06449469923973083
2023-01-23 01:17:12.047518: step: 1764/530, loss: 0.04774647206068039
2023-01-23 01:17:13.139444: step: 1768/530, loss: 0.10913410782814026
2023-01-23 01:17:14.235272: step: 1772/530, loss: 0.028405381366610527
2023-01-23 01:17:15.325507: step: 1776/530, loss: 0.01448202133178711
2023-01-23 01:17:16.441092: step: 1780/530, loss: 0.5212539434432983
2023-01-23 01:17:17.561142: step: 1784/530, loss: 0.03967972844839096
2023-01-23 01:17:18.667871: step: 1788/530, loss: 0.12832984328269958
2023-01-23 01:17:19.799293: step: 1792/530, loss: 0.05873413011431694
2023-01-23 01:17:20.922953: step: 1796/530, loss: 0.07915592938661575
2023-01-23 01:17:22.071930: step: 1800/530, loss: 0.03998732566833496
2023-01-23 01:17:23.181836: step: 1804/530, loss: 0.0263550765812397
2023-01-23 01:17:24.319345: step: 1808/530, loss: 0.0058193206787109375
2023-01-23 01:17:25.410244: step: 1812/530, loss: 0.012419604696333408
2023-01-23 01:17:26.499508: step: 1816/530, loss: 0.01571207121014595
2023-01-23 01:17:27.604445: step: 1820/530, loss: 0.12479066848754883
2023-01-23 01:17:28.704522: step: 1824/530, loss: 0.023221779614686966
2023-01-23 01:17:29.813040: step: 1828/530, loss: 0.048781681805849075
2023-01-23 01:17:30.942438: step: 1832/530, loss: 0.14184695482254028
2023-01-23 01:17:32.036238: step: 1836/530, loss: 0.056687261909246445
2023-01-23 01:17:33.164378: step: 1840/530, loss: 0.024855613708496094
2023-01-23 01:17:34.255177: step: 1844/530, loss: 0.05488219112157822
2023-01-23 01:17:35.367590: step: 1848/530, loss: 0.009911155328154564
2023-01-23 01:17:36.472616: step: 1852/530, loss: 0.16133423149585724
2023-01-23 01:17:37.577425: step: 1856/530, loss: 0.06242332607507706
2023-01-23 01:17:38.670534: step: 1860/530, loss: 0.29647397994995117
2023-01-23 01:17:39.772417: step: 1864/530, loss: 0.09084615856409073
2023-01-23 01:17:40.867730: step: 1868/530, loss: 0.011372281238436699
2023-01-23 01:17:41.974516: step: 1872/530, loss: 0.055965423583984375
2023-01-23 01:17:43.102339: step: 1876/530, loss: 0.15248116850852966
2023-01-23 01:17:44.204332: step: 1880/530, loss: 0.09900913387537003
2023-01-23 01:17:45.336041: step: 1884/530, loss: 0.005707359407097101
2023-01-23 01:17:46.467192: step: 1888/530, loss: 0.42601072788238525
2023-01-23 01:17:47.578721: step: 1892/530, loss: 0.04569735378026962
2023-01-23 01:17:48.690377: step: 1896/530, loss: 0.036768246442079544
2023-01-23 01:17:49.774142: step: 1900/530, loss: 0.052835848182439804
2023-01-23 01:17:50.889444: step: 1904/530, loss: 0.07460003346204758
2023-01-23 01:17:51.980482: step: 1908/530, loss: 0.0066308025270700455
2023-01-23 01:17:53.093306: step: 1912/530, loss: 0.008951663970947266
2023-01-23 01:17:54.213303: step: 1916/530, loss: 0.0402749702334404
2023-01-23 01:17:55.326470: step: 1920/530, loss: 0.05490460246801376
2023-01-23 01:17:56.422430: step: 1924/530, loss: 0.043356988579034805
2023-01-23 01:17:57.547238: step: 1928/530, loss: 0.08829774707555771
2023-01-23 01:17:58.662095: step: 1932/530, loss: 0.03699655830860138
2023-01-23 01:17:59.763544: step: 1936/530, loss: 0.11772795021533966
2023-01-23 01:18:00.863022: step: 1940/530, loss: 0.12338696420192719
2023-01-23 01:18:02.002797: step: 1944/530, loss: 0.03663668781518936
2023-01-23 01:18:03.084865: step: 1948/530, loss: 0.022455787286162376
2023-01-23 01:18:04.174959: step: 1952/530, loss: 0.03382702171802521
2023-01-23 01:18:05.304011: step: 1956/530, loss: 0.037178803235292435
2023-01-23 01:18:06.403228: step: 1960/530, loss: 0.028437137603759766
2023-01-23 01:18:07.505467: step: 1964/530, loss: 0.12222099304199219
2023-01-23 01:18:08.632073: step: 1968/530, loss: 0.12996742129325867
2023-01-23 01:18:09.733230: step: 1972/530, loss: 0.02355632744729519
2023-01-23 01:18:10.837884: step: 1976/530, loss: 0.013407516293227673
2023-01-23 01:18:11.939894: step: 1980/530, loss: 0.0712771862745285
2023-01-23 01:18:13.076963: step: 1984/530, loss: 0.2157619595527649
2023-01-23 01:18:14.174714: step: 1988/530, loss: 0.011900784447789192
2023-01-23 01:18:15.302347: step: 1992/530, loss: 0.04205045849084854
2023-01-23 01:18:16.401695: step: 1996/530, loss: 0.008880043402314186
2023-01-23 01:18:17.508864: step: 2000/530, loss: 0.09431519359350204
2023-01-23 01:18:18.606534: step: 2004/530, loss: 0.1522396206855774
2023-01-23 01:18:19.749134: step: 2008/530, loss: 0.051564596593379974
2023-01-23 01:18:20.839304: step: 2012/530, loss: 0.07655926048755646
2023-01-23 01:18:21.949530: step: 2016/530, loss: 0.024863576516509056
2023-01-23 01:18:23.045604: step: 2020/530, loss: 0.12144012749195099
2023-01-23 01:18:24.180486: step: 2024/530, loss: 0.0800497978925705
2023-01-23 01:18:25.294596: step: 2028/530, loss: 0.0056365965865552425
2023-01-23 01:18:26.414251: step: 2032/530, loss: 0.005035442300140858
2023-01-23 01:18:27.524276: step: 2036/530, loss: 0.047686293721199036
2023-01-23 01:18:28.671037: step: 2040/530, loss: 0.07552909851074219
2023-01-23 01:18:29.797659: step: 2044/530, loss: 0.04365091398358345
2023-01-23 01:18:30.954067: step: 2048/530, loss: 0.002990531735122204
2023-01-23 01:18:32.107856: step: 2052/530, loss: 0.07317504286766052
2023-01-23 01:18:33.236754: step: 2056/530, loss: 0.13590799272060394
2023-01-23 01:18:34.325234: step: 2060/530, loss: 0.14554038643836975
2023-01-23 01:18:35.448173: step: 2064/530, loss: 0.12408009171485901
2023-01-23 01:18:36.555188: step: 2068/530, loss: 0.0359250083565712
2023-01-23 01:18:37.682189: step: 2072/530, loss: 0.13010473549365997
2023-01-23 01:18:38.764318: step: 2076/530, loss: 0.002796173095703125
2023-01-23 01:18:39.902231: step: 2080/530, loss: 0.07012243568897247
2023-01-23 01:18:41.017396: step: 2084/530, loss: 0.0349484458565712
2023-01-23 01:18:42.111190: step: 2088/530, loss: 0.013703251257538795
2023-01-23 01:18:43.217275: step: 2092/530, loss: 0.025367069989442825
2023-01-23 01:18:44.311883: step: 2096/530, loss: 0.012494039721786976
2023-01-23 01:18:45.388202: step: 2100/530, loss: 0.04867153242230415
2023-01-23 01:18:46.499782: step: 2104/530, loss: 0.07568585127592087
2023-01-23 01:18:47.653045: step: 2108/530, loss: 0.007527160923928022
2023-01-23 01:18:48.752312: step: 2112/530, loss: 0.013137436471879482
2023-01-23 01:18:49.881555: step: 2116/530, loss: 0.012353325262665749
2023-01-23 01:18:50.969059: step: 2120/530, loss: 0.021196747198700905
==================================================
Loss: 0.095
--------------------
Dev: {'event': {'p': 0.6234906695938529, 'r': 0.7563249001331558, 'f1': 0.6835138387484957}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Test: {'event': {'p': 0.6422232601588043, 'r': 0.8012820512820513, 'f1': 0.7129893699766658}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Chinese: {'event': {'p': 0.6081081081081081, 'r': 0.8333333333333334, 'f1': 0.7031250000000001}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Korean: {'event': {'p': 0.6, 'r': 0.5714285714285714, 'f1': 0.5853658536585366}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
Russian: {'event': {'p': 0.4857142857142857, 'r': 0.4722222222222222, 'f1': 0.47887323943661975}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 10}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.5708622398414271, 'r': 0.7669773635153129, 'f1': 0.6545454545454545}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Eng Test for Chinese: {'event': {'p': 0.6044052863436123, 'r': 0.7995337995337995, 'f1': 0.6884094330155545}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Sample Chinese: {'event': {'p': 0.6578947368421053, 'r': 0.9259259259259259, 'f1': 0.7692307692307692}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6466512702078522, 'r': 0.7456724367509987, 'f1': 0.6926406926406927}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Eng Test for Korean: {'event': {'p': 0.6762148337595908, 'r': 0.7703962703962703, 'f1': 0.7202397166984473}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Sample Korean: {'event': {'p': 0.6862745098039216, 'r': 0.5555555555555556, 'f1': 0.6140350877192983}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5971370143149284, 'r': 0.7776298268974701, 'f1': 0.6755349913244649}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Russian: {'event': {'p': 0.6401673640167364, 'r': 0.8024475524475524, 'f1': 0.7121799844840963}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Russian: {'event': {'p': 0.5897435897435898, 'r': 0.6388888888888888, 'f1': 0.6133333333333332}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
******************************
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 01:19:29.921116: step: 4/530, loss: 0.08964863419532776
2023-01-23 01:19:31.006865: step: 8/530, loss: 0.02247953601181507
2023-01-23 01:19:32.131699: step: 12/530, loss: 0.024763204157352448
2023-01-23 01:19:33.256470: step: 16/530, loss: 0.11863622069358826
2023-01-23 01:19:34.379395: step: 20/530, loss: 0.0612177848815918
2023-01-23 01:19:35.494546: step: 24/530, loss: 0.028406143188476562
2023-01-23 01:19:36.597020: step: 28/530, loss: 0.04806508868932724
2023-01-23 01:19:37.726991: step: 32/530, loss: 0.019141722470521927
2023-01-23 01:19:38.827218: step: 36/530, loss: 0.030022049322724342
2023-01-23 01:19:39.963855: step: 40/530, loss: 0.13446128368377686
2023-01-23 01:19:41.083596: step: 44/530, loss: 0.008623600006103516
2023-01-23 01:19:42.185247: step: 48/530, loss: 0.014078712090849876
2023-01-23 01:19:43.297489: step: 52/530, loss: 0.03209686279296875
2023-01-23 01:19:44.397765: step: 56/530, loss: 0.027567386627197266
2023-01-23 01:19:45.513323: step: 60/530, loss: 0.04089780151844025
2023-01-23 01:19:46.620209: step: 64/530, loss: 0.017711259424686432
2023-01-23 01:19:47.745163: step: 68/530, loss: 0.06816921383142471
2023-01-23 01:19:48.837344: step: 72/530, loss: 0.02695159800350666
2023-01-23 01:19:49.978466: step: 76/530, loss: 0.02095775678753853
2023-01-23 01:19:51.079368: step: 80/530, loss: 0.037688061594963074
2023-01-23 01:19:52.173993: step: 84/530, loss: 0.049540139734745026
2023-01-23 01:19:53.283060: step: 88/530, loss: 0.005287385080009699
2023-01-23 01:19:54.405057: step: 92/530, loss: 0.10928115248680115
2023-01-23 01:19:55.506921: step: 96/530, loss: 0.10061845928430557
2023-01-23 01:19:56.592205: step: 100/530, loss: 0.02756796032190323
2023-01-23 01:19:57.697168: step: 104/530, loss: 0.02692422829568386
2023-01-23 01:19:58.782469: step: 108/530, loss: 0.17764797806739807
2023-01-23 01:19:59.923373: step: 112/530, loss: 0.052677348256111145
2023-01-23 01:20:01.038585: step: 116/530, loss: 0.041715528815984726
2023-01-23 01:20:02.154418: step: 120/530, loss: 0.05001135170459747
2023-01-23 01:20:03.258938: step: 124/530, loss: 0.021344946697354317
2023-01-23 01:20:04.370475: step: 128/530, loss: 0.035292696207761765
2023-01-23 01:20:05.474801: step: 132/530, loss: 0.10476885735988617
2023-01-23 01:20:06.587614: step: 136/530, loss: 0.12089284509420395
2023-01-23 01:20:07.721116: step: 140/530, loss: 0.056166935712099075
2023-01-23 01:20:08.843658: step: 144/530, loss: 0.03636594116687775
2023-01-23 01:20:09.943719: step: 148/530, loss: 0.007698822300881147
2023-01-23 01:20:11.054058: step: 152/530, loss: 0.2300596535205841
2023-01-23 01:20:12.181052: step: 156/530, loss: 0.052889633923769
2023-01-23 01:20:13.280520: step: 160/530, loss: 0.07069053500890732
2023-01-23 01:20:14.407912: step: 164/530, loss: 0.044928453862667084
2023-01-23 01:20:15.528314: step: 168/530, loss: 0.00870828703045845
2023-01-23 01:20:16.622912: step: 172/530, loss: 0.03944873809814453
2023-01-23 01:20:17.706622: step: 176/530, loss: 0.004895925521850586
2023-01-23 01:20:18.809395: step: 180/530, loss: 0.3493845462799072
2023-01-23 01:20:19.921907: step: 184/530, loss: 0.03560657799243927
2023-01-23 01:20:21.051630: step: 188/530, loss: 0.0947975218296051
2023-01-23 01:20:22.169074: step: 192/530, loss: 0.13313019275665283
2023-01-23 01:20:23.298086: step: 196/530, loss: 0.0647134780883789
2023-01-23 01:20:24.442754: step: 200/530, loss: 0.04189910739660263
2023-01-23 01:20:25.544413: step: 204/530, loss: 0.46162986755371094
2023-01-23 01:20:26.660306: step: 208/530, loss: 0.053897857666015625
2023-01-23 01:20:27.788700: step: 212/530, loss: 0.0787515640258789
2023-01-23 01:20:28.914434: step: 216/530, loss: 0.05760164558887482
2023-01-23 01:20:29.996593: step: 220/530, loss: 0.060935311019420624
2023-01-23 01:20:31.089054: step: 224/530, loss: 0.19133806228637695
2023-01-23 01:20:32.175877: step: 228/530, loss: 0.01637706719338894
2023-01-23 01:20:33.280885: step: 232/530, loss: 0.0034931180998682976
2023-01-23 01:20:34.362763: step: 236/530, loss: 0.06207694858312607
2023-01-23 01:20:35.488466: step: 240/530, loss: 0.1389867067337036
2023-01-23 01:20:36.598247: step: 244/530, loss: 0.06269846856594086
2023-01-23 01:20:37.698495: step: 248/530, loss: 0.003131961915642023
2023-01-23 01:20:38.809453: step: 252/530, loss: 0.04863929748535156
2023-01-23 01:20:39.931981: step: 256/530, loss: 0.06426163017749786
2023-01-23 01:20:41.037350: step: 260/530, loss: 0.0611545592546463
2023-01-23 01:20:42.142191: step: 264/530, loss: 0.01520681381225586
2023-01-23 01:20:43.267668: step: 268/530, loss: 0.053270816802978516
2023-01-23 01:20:44.366217: step: 272/530, loss: 0.0883183479309082
2023-01-23 01:20:45.486003: step: 276/530, loss: 0.03669586405158043
2023-01-23 01:20:46.599467: step: 280/530, loss: 0.23922061920166016
2023-01-23 01:20:47.718280: step: 284/530, loss: 0.15121793746948242
2023-01-23 01:20:48.817168: step: 288/530, loss: 0.08981809765100479
2023-01-23 01:20:49.931570: step: 292/530, loss: 0.05097770690917969
2023-01-23 01:20:51.041504: step: 296/530, loss: 0.5968635082244873
2023-01-23 01:20:52.137955: step: 300/530, loss: 0.02820425108075142
2023-01-23 01:20:53.248088: step: 304/530, loss: 0.03298044204711914
2023-01-23 01:20:54.369548: step: 308/530, loss: 0.12087040394544601
2023-01-23 01:20:55.464009: step: 312/530, loss: 0.010115813463926315
2023-01-23 01:20:56.557461: step: 316/530, loss: 0.049526214599609375
2023-01-23 01:20:57.677057: step: 320/530, loss: 0.0369388572871685
2023-01-23 01:20:58.755367: step: 324/530, loss: 0.023676013574004173
2023-01-23 01:20:59.875120: step: 328/530, loss: 0.07032632827758789
2023-01-23 01:21:01.000251: step: 332/530, loss: 0.08553314208984375
2023-01-23 01:21:02.095257: step: 336/530, loss: 0.027059080079197884
2023-01-23 01:21:03.216489: step: 340/530, loss: 0.07036428898572922
2023-01-23 01:21:04.331425: step: 344/530, loss: 0.05050468444824219
2023-01-23 01:21:05.454480: step: 348/530, loss: 0.04969625547528267
2023-01-23 01:21:06.579171: step: 352/530, loss: 0.7258001565933228
2023-01-23 01:21:07.677788: step: 356/530, loss: 0.0022842169273644686
2023-01-23 01:21:08.773996: step: 360/530, loss: 0.0031315325759351254
2023-01-23 01:21:09.855405: step: 364/530, loss: 0.07224655151367188
2023-01-23 01:21:10.968213: step: 368/530, loss: 0.056932926177978516
2023-01-23 01:21:12.044990: step: 372/530, loss: 0.03524224832653999
2023-01-23 01:21:13.166986: step: 376/530, loss: 0.09698023647069931
2023-01-23 01:21:14.287397: step: 380/530, loss: 0.07805786281824112
2023-01-23 01:21:15.375728: step: 384/530, loss: 0.0855921283364296
2023-01-23 01:21:16.482124: step: 388/530, loss: 0.10835013538599014
2023-01-23 01:21:17.607039: step: 392/530, loss: 0.021238327026367188
2023-01-23 01:21:18.702567: step: 396/530, loss: 0.0668153315782547
2023-01-23 01:21:19.809830: step: 400/530, loss: 0.05712556838989258
2023-01-23 01:21:20.917393: step: 404/530, loss: 0.05562472343444824
2023-01-23 01:21:22.021112: step: 408/530, loss: 0.13145345449447632
2023-01-23 01:21:23.111366: step: 412/530, loss: 0.16424700617790222
2023-01-23 01:21:24.225660: step: 416/530, loss: 0.01642761379480362
2023-01-23 01:21:25.325583: step: 420/530, loss: 0.04033870995044708
2023-01-23 01:21:26.420225: step: 424/530, loss: 0.006476211827248335
2023-01-23 01:21:27.513318: step: 428/530, loss: 0.003507423447445035
2023-01-23 01:21:28.609032: step: 432/530, loss: 0.008094167336821556
2023-01-23 01:21:29.707381: step: 436/530, loss: 0.27588480710983276
2023-01-23 01:21:30.826096: step: 440/530, loss: 0.17588070034980774
2023-01-23 01:21:31.924650: step: 444/530, loss: 0.08150777965784073
2023-01-23 01:21:33.021520: step: 448/530, loss: 0.06815586239099503
2023-01-23 01:21:34.103977: step: 452/530, loss: 0.006406450178474188
2023-01-23 01:21:35.188443: step: 456/530, loss: 0.047214604914188385
2023-01-23 01:21:36.298182: step: 460/530, loss: 0.03208179771900177
2023-01-23 01:21:37.403767: step: 464/530, loss: 0.03955160453915596
2023-01-23 01:21:38.499384: step: 468/530, loss: 0.056502439081668854
2023-01-23 01:21:39.589715: step: 472/530, loss: 0.05917187035083771
2023-01-23 01:21:40.692578: step: 476/530, loss: 0.033631037920713425
2023-01-23 01:21:41.787707: step: 480/530, loss: 0.040032099932432175
2023-01-23 01:21:42.914714: step: 484/530, loss: 0.18387380242347717
2023-01-23 01:21:44.008217: step: 488/530, loss: 0.003200626466423273
2023-01-23 01:21:45.135749: step: 492/530, loss: 0.18380308151245117
2023-01-23 01:21:46.259119: step: 496/530, loss: 0.0217114444822073
2023-01-23 01:21:47.356701: step: 500/530, loss: 0.021931076422333717
2023-01-23 01:21:48.479293: step: 504/530, loss: 0.13216447830200195
2023-01-23 01:21:49.585833: step: 508/530, loss: 0.04000559076666832
2023-01-23 01:21:50.702987: step: 512/530, loss: 0.02097034454345703
2023-01-23 01:21:51.809195: step: 516/530, loss: 0.015297984704375267
2023-01-23 01:21:52.887931: step: 520/530, loss: 0.03526172786951065
2023-01-23 01:21:53.991998: step: 524/530, loss: 0.46719658374786377
2023-01-23 01:21:55.087934: step: 528/530, loss: 0.036698102951049805
2023-01-23 01:21:56.202284: step: 532/530, loss: 0.2428804486989975
2023-01-23 01:21:57.305124: step: 536/530, loss: 0.052773669362068176
2023-01-23 01:21:58.415299: step: 540/530, loss: 0.0004440784396138042
2023-01-23 01:21:59.532206: step: 544/530, loss: 0.00417327880859375
2023-01-23 01:22:00.646024: step: 548/530, loss: 0.07191815227270126
2023-01-23 01:22:01.758155: step: 552/530, loss: 0.02399730682373047
2023-01-23 01:22:02.921408: step: 556/530, loss: 0.03621072694659233
2023-01-23 01:22:04.030414: step: 560/530, loss: 0.16893033683300018
2023-01-23 01:22:05.120894: step: 564/530, loss: 0.08040142059326172
2023-01-23 01:22:06.234204: step: 568/530, loss: 0.016599148511886597
2023-01-23 01:22:07.389086: step: 572/530, loss: 0.24664005637168884
2023-01-23 01:22:08.503457: step: 576/530, loss: 0.04986991733312607
2023-01-23 01:22:09.598132: step: 580/530, loss: 0.10558776557445526
2023-01-23 01:22:10.736328: step: 584/530, loss: 0.36951446533203125
2023-01-23 01:22:11.857128: step: 588/530, loss: 0.045317839831113815
2023-01-23 01:22:12.972544: step: 592/530, loss: 0.03111591562628746
2023-01-23 01:22:14.084752: step: 596/530, loss: 0.04375341162085533
2023-01-23 01:22:15.198093: step: 600/530, loss: 0.01849212683737278
2023-01-23 01:22:16.288875: step: 604/530, loss: 0.0349031426012516
2023-01-23 01:22:17.370670: step: 608/530, loss: 0.01204538345336914
2023-01-23 01:22:18.460384: step: 612/530, loss: 0.014402390457689762
2023-01-23 01:22:19.574967: step: 616/530, loss: 0.26271793246269226
2023-01-23 01:22:20.675730: step: 620/530, loss: 1.3284703493118286
2023-01-23 01:22:21.783504: step: 624/530, loss: 0.06792745739221573
2023-01-23 01:22:22.915113: step: 628/530, loss: 0.06513457745313644
2023-01-23 01:22:24.027422: step: 632/530, loss: 0.008516788482666016
2023-01-23 01:22:25.122061: step: 636/530, loss: 0.021369457244873047
2023-01-23 01:22:26.195273: step: 640/530, loss: 0.029024600982666016
2023-01-23 01:22:27.281837: step: 644/530, loss: 0.03648862987756729
2023-01-23 01:22:28.416413: step: 648/530, loss: 0.005990028381347656
2023-01-23 01:22:29.510344: step: 652/530, loss: 0.1083964854478836
2023-01-23 01:22:30.594187: step: 656/530, loss: 0.08493395149707794
2023-01-23 01:22:31.713512: step: 660/530, loss: 0.04618282616138458
2023-01-23 01:22:32.813549: step: 664/530, loss: 0.0027610301040112972
2023-01-23 01:22:33.933851: step: 668/530, loss: 0.1387912780046463
2023-01-23 01:22:35.036218: step: 672/530, loss: 0.044145964086055756
2023-01-23 01:22:36.186648: step: 676/530, loss: 0.09207496792078018
2023-01-23 01:22:37.325538: step: 680/530, loss: 0.07142724841833115
2023-01-23 01:22:38.412994: step: 684/530, loss: 0.04970664903521538
2023-01-23 01:22:39.515995: step: 688/530, loss: 0.03837089613080025
2023-01-23 01:22:40.615235: step: 692/530, loss: 0.15382727980613708
2023-01-23 01:22:41.741415: step: 696/530, loss: 0.03988952562212944
2023-01-23 01:22:42.844968: step: 700/530, loss: 0.27731189131736755
2023-01-23 01:22:43.959272: step: 704/530, loss: 0.1183788999915123
2023-01-23 01:22:45.067249: step: 708/530, loss: 0.02717600017786026
2023-01-23 01:22:46.144840: step: 712/530, loss: 0.015778923407197
2023-01-23 01:22:47.237800: step: 716/530, loss: 6.689385414123535
2023-01-23 01:22:48.346819: step: 720/530, loss: 0.10859957337379456
2023-01-23 01:22:49.473824: step: 724/530, loss: 0.16249854862689972
2023-01-23 01:22:50.571782: step: 728/530, loss: 0.004968404769897461
2023-01-23 01:22:51.661813: step: 732/530, loss: 0.07872986793518066
2023-01-23 01:22:52.785673: step: 736/530, loss: 0.09969864040613174
2023-01-23 01:22:53.899498: step: 740/530, loss: 0.05509620159864426
2023-01-23 01:22:54.986627: step: 744/530, loss: 0.022128676995635033
2023-01-23 01:22:56.094098: step: 748/530, loss: 0.0026781796477735043
2023-01-23 01:22:57.196499: step: 752/530, loss: 0.09898748248815536
2023-01-23 01:22:58.293265: step: 756/530, loss: 0.07131247967481613
2023-01-23 01:22:59.386302: step: 760/530, loss: 0.08621535450220108
2023-01-23 01:23:00.499582: step: 764/530, loss: 0.12386369705200195
2023-01-23 01:23:01.610995: step: 768/530, loss: 0.030532479286193848
2023-01-23 01:23:02.719929: step: 772/530, loss: 0.022281788289546967
2023-01-23 01:23:03.856386: step: 776/530, loss: 0.03888406977057457
2023-01-23 01:23:05.014261: step: 780/530, loss: 0.012248135171830654
2023-01-23 01:23:06.173031: step: 784/530, loss: 0.11148204654455185
2023-01-23 01:23:07.286307: step: 788/530, loss: 0.012192582711577415
2023-01-23 01:23:08.403483: step: 792/530, loss: 0.01820354536175728
2023-01-23 01:23:09.519299: step: 796/530, loss: 0.20804691314697266
2023-01-23 01:23:10.626773: step: 800/530, loss: 0.1082301139831543
2023-01-23 01:23:11.739022: step: 804/530, loss: 0.09335007518529892
2023-01-23 01:23:12.833064: step: 808/530, loss: 0.03581352159380913
2023-01-23 01:23:13.925150: step: 812/530, loss: 0.6999807953834534
2023-01-23 01:23:14.990373: step: 816/530, loss: 0.0503966361284256
2023-01-23 01:23:16.092378: step: 820/530, loss: 0.009451841935515404
2023-01-23 01:23:17.222163: step: 824/530, loss: 0.005446339026093483
2023-01-23 01:23:18.334440: step: 828/530, loss: 0.0582975372672081
2023-01-23 01:23:19.442241: step: 832/530, loss: 0.04104194790124893
2023-01-23 01:23:20.554702: step: 836/530, loss: 0.13483142852783203
2023-01-23 01:23:21.667493: step: 840/530, loss: 0.14365415275096893
2023-01-23 01:23:22.777871: step: 844/530, loss: 0.01169199962168932
2023-01-23 01:23:23.852631: step: 848/530, loss: 0.032863810658454895
2023-01-23 01:23:24.947380: step: 852/530, loss: 0.04016037657856941
2023-01-23 01:23:26.076246: step: 856/530, loss: 0.005505370907485485
2023-01-23 01:23:27.168705: step: 860/530, loss: 0.025183584541082382
2023-01-23 01:23:28.252183: step: 864/530, loss: 0.03956041485071182
2023-01-23 01:23:29.362995: step: 868/530, loss: 0.14070911705493927
2023-01-23 01:23:30.461011: step: 872/530, loss: 0.026323700323700905
2023-01-23 01:23:31.580659: step: 876/530, loss: 0.02742145210504532
2023-01-23 01:23:32.710421: step: 880/530, loss: 0.046874236315488815
2023-01-23 01:23:33.832939: step: 884/530, loss: 0.1961050033569336
2023-01-23 01:23:34.949555: step: 888/530, loss: 0.03346848487854004
2023-01-23 01:23:36.054155: step: 892/530, loss: 0.0007472991710528731
2023-01-23 01:23:37.142449: step: 896/530, loss: 0.004427146632224321
2023-01-23 01:23:38.236691: step: 900/530, loss: 0.17340460419654846
2023-01-23 01:23:39.359448: step: 904/530, loss: 0.016116762533783913
2023-01-23 01:23:40.478666: step: 908/530, loss: 0.26669663190841675
2023-01-23 01:23:41.574228: step: 912/530, loss: 0.038085177540779114
2023-01-23 01:23:42.688263: step: 916/530, loss: 0.17962369322776794
2023-01-23 01:23:43.814478: step: 920/530, loss: 0.025181390345096588
2023-01-23 01:23:44.936775: step: 924/530, loss: 0.004583931062370539
2023-01-23 01:23:46.027995: step: 928/530, loss: 0.05066213756799698
2023-01-23 01:23:47.126824: step: 932/530, loss: 0.05351286381483078
2023-01-23 01:23:48.231103: step: 936/530, loss: 0.005134677980095148
2023-01-23 01:23:49.351839: step: 940/530, loss: 0.06675248593091965
2023-01-23 01:23:50.500133: step: 944/530, loss: 0.04150128364562988
2023-01-23 01:23:51.597852: step: 948/530, loss: 0.017281342297792435
2023-01-23 01:23:52.705524: step: 952/530, loss: 0.03934922069311142
2023-01-23 01:23:53.788323: step: 956/530, loss: 0.016982747241854668
2023-01-23 01:23:54.900693: step: 960/530, loss: 0.06882262229919434
2023-01-23 01:23:56.032927: step: 964/530, loss: 0.009514236822724342
2023-01-23 01:23:57.118933: step: 968/530, loss: 0.08088560402393341
2023-01-23 01:23:58.264604: step: 972/530, loss: 0.1286792755126953
2023-01-23 01:23:59.358821: step: 976/530, loss: 0.03190579637885094
2023-01-23 01:24:00.470007: step: 980/530, loss: 0.033347032964229584
2023-01-23 01:24:01.598821: step: 984/530, loss: 0.09323425590991974
2023-01-23 01:24:02.736249: step: 988/530, loss: 0.057544805109500885
2023-01-23 01:24:03.864600: step: 992/530, loss: 0.023393917828798294
2023-01-23 01:24:04.983656: step: 996/530, loss: 0.006495857145637274
2023-01-23 01:24:06.114179: step: 1000/530, loss: 0.05317812040448189
2023-01-23 01:24:07.233401: step: 1004/530, loss: 0.06906137615442276
2023-01-23 01:24:08.354435: step: 1008/530, loss: 0.02431979402899742
2023-01-23 01:24:09.478814: step: 1012/530, loss: 0.05707371234893799
2023-01-23 01:24:10.598602: step: 1016/530, loss: 0.2990041673183441
2023-01-23 01:24:11.720890: step: 1020/530, loss: 0.2590957581996918
2023-01-23 01:24:12.837610: step: 1024/530, loss: 0.04141458123922348
2023-01-23 01:24:13.929135: step: 1028/530, loss: 0.23832359910011292
2023-01-23 01:24:15.049716: step: 1032/530, loss: 0.04406547546386719
2023-01-23 01:24:16.139220: step: 1036/530, loss: 0.03817172348499298
2023-01-23 01:24:17.220361: step: 1040/530, loss: 0.0006984710926190019
2023-01-23 01:24:18.327754: step: 1044/530, loss: 0.09312897175550461
2023-01-23 01:24:19.428345: step: 1048/530, loss: 0.30806446075439453
2023-01-23 01:24:20.565656: step: 1052/530, loss: 0.1998034417629242
2023-01-23 01:24:21.663163: step: 1056/530, loss: 0.0285782590508461
2023-01-23 01:24:22.782531: step: 1060/530, loss: 0.016660405322909355
2023-01-23 01:24:23.909097: step: 1064/530, loss: 0.0252398494631052
2023-01-23 01:24:25.020636: step: 1068/530, loss: 0.11393900215625763
2023-01-23 01:24:26.130579: step: 1072/530, loss: 0.04579200595617294
2023-01-23 01:24:27.200062: step: 1076/530, loss: 0.08616933226585388
2023-01-23 01:24:28.318353: step: 1080/530, loss: 0.012139225378632545
2023-01-23 01:24:29.415698: step: 1084/530, loss: 0.034149982035160065
2023-01-23 01:24:30.517099: step: 1088/530, loss: 0.05119438096880913
2023-01-23 01:24:31.640142: step: 1092/530, loss: 0.04370078817009926
2023-01-23 01:24:32.747501: step: 1096/530, loss: 0.047237493097782135
2023-01-23 01:24:33.850081: step: 1100/530, loss: 0.005970764439553022
2023-01-23 01:24:34.958715: step: 1104/530, loss: 0.038091327995061874
2023-01-23 01:24:36.075616: step: 1108/530, loss: 0.01807422749698162
2023-01-23 01:24:37.162854: step: 1112/530, loss: 0.024179697036743164
2023-01-23 01:24:38.306368: step: 1116/530, loss: 0.26404449343681335
2023-01-23 01:24:39.412534: step: 1120/530, loss: 0.07606907188892365
2023-01-23 01:24:40.533488: step: 1124/530, loss: 0.03739500045776367
2023-01-23 01:24:41.611330: step: 1128/530, loss: 0.0225354190915823
2023-01-23 01:24:42.725239: step: 1132/530, loss: 0.05751834064722061
2023-01-23 01:24:43.832052: step: 1136/530, loss: 0.24944019317626953
2023-01-23 01:24:44.936558: step: 1140/530, loss: 0.009146571159362793
2023-01-23 01:24:46.065592: step: 1144/530, loss: 0.020014572888612747
2023-01-23 01:24:47.156027: step: 1148/530, loss: 0.01992349699139595
2023-01-23 01:24:48.268028: step: 1152/530, loss: 0.09063081443309784
2023-01-23 01:24:49.368652: step: 1156/530, loss: 0.019260788336396217
2023-01-23 01:24:50.462648: step: 1160/530, loss: 0.1189027726650238
2023-01-23 01:24:51.536304: step: 1164/530, loss: 0.008253383450210094
2023-01-23 01:24:52.617031: step: 1168/530, loss: 0.18192434310913086
2023-01-23 01:24:53.707474: step: 1172/530, loss: 0.03202543407678604
2023-01-23 01:24:54.800121: step: 1176/530, loss: 0.006087779998779297
2023-01-23 01:24:55.954911: step: 1180/530, loss: 0.017699718475341797
2023-01-23 01:24:57.106841: step: 1184/530, loss: 0.020438862964510918
2023-01-23 01:24:58.220449: step: 1188/530, loss: 0.18083572387695312
2023-01-23 01:24:59.346340: step: 1192/530, loss: 0.05942139774560928
2023-01-23 01:25:00.441097: step: 1196/530, loss: 0.031481076031923294
2023-01-23 01:25:01.529350: step: 1200/530, loss: 0.10384511947631836
2023-01-23 01:25:02.635072: step: 1204/530, loss: 0.0035838126204907894
2023-01-23 01:25:03.756301: step: 1208/530, loss: 0.03424272686243057
2023-01-23 01:25:04.867691: step: 1212/530, loss: 0.00261936173774302
2023-01-23 01:25:05.988063: step: 1216/530, loss: 0.06642857193946838
2023-01-23 01:25:07.076755: step: 1220/530, loss: 0.05801687389612198
2023-01-23 01:25:08.197817: step: 1224/530, loss: 0.11422616243362427
2023-01-23 01:25:09.320367: step: 1228/530, loss: 0.11314363777637482
2023-01-23 01:25:10.417095: step: 1232/530, loss: 0.006369686219841242
2023-01-23 01:25:11.522851: step: 1236/530, loss: 0.048940468579530716
2023-01-23 01:25:12.608886: step: 1240/530, loss: 0.09101562201976776
2023-01-23 01:25:13.702969: step: 1244/530, loss: 0.025406742468476295
2023-01-23 01:25:14.794200: step: 1248/530, loss: 0.434468537569046
2023-01-23 01:25:15.884123: step: 1252/530, loss: 0.04546623304486275
2023-01-23 01:25:16.997576: step: 1256/530, loss: 0.04888954386115074
2023-01-23 01:25:18.117414: step: 1260/530, loss: 0.025339506566524506
2023-01-23 01:25:19.208844: step: 1264/530, loss: 0.15145409107208252
2023-01-23 01:25:20.319202: step: 1268/530, loss: 0.09872984886169434
2023-01-23 01:25:21.408108: step: 1272/530, loss: 0.07277937233448029
2023-01-23 01:25:22.506327: step: 1276/530, loss: 0.016759490594267845
2023-01-23 01:25:23.601634: step: 1280/530, loss: 0.09770813584327698
2023-01-23 01:25:24.707907: step: 1284/530, loss: 0.015460682101547718
2023-01-23 01:25:25.825445: step: 1288/530, loss: 0.02175579033792019
2023-01-23 01:25:26.928814: step: 1292/530, loss: 0.05364866554737091
2023-01-23 01:25:28.059526: step: 1296/530, loss: 0.012689399532973766
2023-01-23 01:25:29.155315: step: 1300/530, loss: 0.07615194469690323
2023-01-23 01:25:30.242985: step: 1304/530, loss: 0.011107313446700573
2023-01-23 01:25:31.324208: step: 1308/530, loss: 0.026468895375728607
2023-01-23 01:25:32.458846: step: 1312/530, loss: 0.04306092485785484
2023-01-23 01:25:33.583747: step: 1316/530, loss: 0.0030199051834642887
2023-01-23 01:25:34.663955: step: 1320/530, loss: 0.017276287078857422
2023-01-23 01:25:35.798600: step: 1324/530, loss: 0.047972869127988815
2023-01-23 01:25:36.906539: step: 1328/530, loss: 0.03900089114904404
2023-01-23 01:25:38.049141: step: 1332/530, loss: 0.012319850735366344
2023-01-23 01:25:39.210738: step: 1336/530, loss: 0.025771809741854668
2023-01-23 01:25:40.299491: step: 1340/530, loss: 0.0913238525390625
2023-01-23 01:25:41.396201: step: 1344/530, loss: 0.0801122635602951
2023-01-23 01:25:42.507240: step: 1348/530, loss: 0.07319183647632599
2023-01-23 01:25:43.607974: step: 1352/530, loss: 0.025940515100955963
2023-01-23 01:25:44.707869: step: 1356/530, loss: 0.013179494068026543
2023-01-23 01:25:45.824432: step: 1360/530, loss: 0.0041886805556714535
2023-01-23 01:25:46.959958: step: 1364/530, loss: 0.02805519290268421
2023-01-23 01:25:48.095107: step: 1368/530, loss: 0.003676224034279585
2023-01-23 01:25:49.210735: step: 1372/530, loss: 0.010624551214277744
2023-01-23 01:25:50.325390: step: 1376/530, loss: 0.07511921226978302
2023-01-23 01:25:51.444787: step: 1380/530, loss: 0.18047723174095154
2023-01-23 01:25:52.535168: step: 1384/530, loss: 0.014397717081010342
2023-01-23 01:25:53.650398: step: 1388/530, loss: 0.0007568359724245965
2023-01-23 01:25:54.768741: step: 1392/530, loss: 0.05339784920215607
2023-01-23 01:25:55.904650: step: 1396/530, loss: 0.15393885970115662
2023-01-23 01:25:56.992544: step: 1400/530, loss: 0.3205549120903015
2023-01-23 01:25:58.113687: step: 1404/530, loss: 0.14973129332065582
2023-01-23 01:25:59.201398: step: 1408/530, loss: 0.026532746851444244
2023-01-23 01:26:00.326591: step: 1412/530, loss: 0.18216991424560547
2023-01-23 01:26:01.422685: step: 1416/530, loss: 0.0026184082962572575
2023-01-23 01:26:02.523279: step: 1420/530, loss: 0.0292492862790823
2023-01-23 01:26:03.609322: step: 1424/530, loss: 0.007504558656364679
2023-01-23 01:26:04.695701: step: 1428/530, loss: 0.03531865030527115
2023-01-23 01:26:05.807643: step: 1432/530, loss: 0.103765107691288
2023-01-23 01:26:06.967594: step: 1436/530, loss: 0.137089341878891
2023-01-23 01:26:08.075138: step: 1440/530, loss: 0.05499601364135742
2023-01-23 01:26:09.189921: step: 1444/530, loss: 0.04135112836956978
2023-01-23 01:26:10.318432: step: 1448/530, loss: 0.09410267323255539
2023-01-23 01:26:11.430508: step: 1452/530, loss: 0.009761005640029907
2023-01-23 01:26:12.554528: step: 1456/530, loss: 0.007539797108620405
2023-01-23 01:26:13.679850: step: 1460/530, loss: 0.19553260505199432
2023-01-23 01:26:14.784857: step: 1464/530, loss: 0.49554330110549927
2023-01-23 01:26:15.893878: step: 1468/530, loss: 0.22021484375
2023-01-23 01:26:16.975022: step: 1472/530, loss: 0.610744833946228
2023-01-23 01:26:18.072250: step: 1476/530, loss: 0.08355007320642471
2023-01-23 01:26:19.168624: step: 1480/530, loss: 0.029439738020300865
2023-01-23 01:26:20.299241: step: 1484/530, loss: 0.049280356615781784
2023-01-23 01:26:21.395139: step: 1488/530, loss: 0.11735839396715164
2023-01-23 01:26:22.505833: step: 1492/530, loss: 0.002564930822700262
2023-01-23 01:26:23.581282: step: 1496/530, loss: 0.03317832946777344
2023-01-23 01:26:24.715311: step: 1500/530, loss: 0.0918956771492958
2023-01-23 01:26:25.819881: step: 1504/530, loss: 0.022330665960907936
2023-01-23 01:26:26.980665: step: 1508/530, loss: 0.08444252610206604
2023-01-23 01:26:28.101169: step: 1512/530, loss: 0.07895755767822266
2023-01-23 01:26:29.222285: step: 1516/530, loss: 0.00974130630493164
2023-01-23 01:26:30.308738: step: 1520/530, loss: 0.035184480249881744
2023-01-23 01:26:31.416521: step: 1524/530, loss: 0.0067857964895665646
2023-01-23 01:26:32.533001: step: 1528/530, loss: 0.026671219617128372
2023-01-23 01:26:33.621707: step: 1532/530, loss: 0.0470428466796875
2023-01-23 01:26:34.718686: step: 1536/530, loss: 0.021310806274414062
2023-01-23 01:26:35.815088: step: 1540/530, loss: 0.29594412446022034
2023-01-23 01:26:36.937519: step: 1544/530, loss: 0.07302432507276535
2023-01-23 01:26:38.056100: step: 1548/530, loss: 0.03705654293298721
2023-01-23 01:26:39.162236: step: 1552/530, loss: 0.05746441334486008
2023-01-23 01:26:40.278904: step: 1556/530, loss: 0.06561096012592316
2023-01-23 01:26:41.374638: step: 1560/530, loss: 0.049315646290779114
2023-01-23 01:26:42.475053: step: 1564/530, loss: 0.01866288296878338
2023-01-23 01:26:43.560642: step: 1568/530, loss: 0.01026687677949667
2023-01-23 01:26:44.687894: step: 1572/530, loss: 0.3782140612602234
2023-01-23 01:26:45.775462: step: 1576/530, loss: 0.03174915164709091
2023-01-23 01:26:46.894019: step: 1580/530, loss: 0.0519731305539608
2023-01-23 01:26:48.029137: step: 1584/530, loss: 0.06885089725255966
2023-01-23 01:26:49.140544: step: 1588/530, loss: 0.027324486523866653
2023-01-23 01:26:50.252024: step: 1592/530, loss: 0.017322540283203125
2023-01-23 01:26:51.405115: step: 1596/530, loss: 0.06253203749656677
2023-01-23 01:26:52.538009: step: 1600/530, loss: 0.01580047607421875
2023-01-23 01:26:53.650119: step: 1604/530, loss: 0.15220795571804047
2023-01-23 01:26:54.749689: step: 1608/530, loss: 0.03933153301477432
2023-01-23 01:26:55.859613: step: 1612/530, loss: 0.0358029380440712
2023-01-23 01:26:56.951275: step: 1616/530, loss: 0.08002395927906036
2023-01-23 01:26:58.054876: step: 1620/530, loss: 0.010809516534209251
2023-01-23 01:26:59.191962: step: 1624/530, loss: 0.0408916138112545
2023-01-23 01:27:00.285212: step: 1628/530, loss: 0.021119022741913795
2023-01-23 01:27:01.396135: step: 1632/530, loss: 0.06739521026611328
2023-01-23 01:27:02.499147: step: 1636/530, loss: 0.04469342157244682
2023-01-23 01:27:03.585282: step: 1640/530, loss: 0.00572967529296875
2023-01-23 01:27:04.715639: step: 1644/530, loss: 0.010033035650849342
2023-01-23 01:27:05.803353: step: 1648/530, loss: 0.06862048804759979
2023-01-23 01:27:06.900707: step: 1652/530, loss: 0.025652311742305756
2023-01-23 01:27:07.998406: step: 1656/530, loss: 0.017319107428193092
2023-01-23 01:27:09.120711: step: 1660/530, loss: 0.02542905882000923
2023-01-23 01:27:10.245054: step: 1664/530, loss: 0.0934932753443718
2023-01-23 01:27:11.388176: step: 1668/530, loss: 0.04142327606678009
2023-01-23 01:27:12.495705: step: 1672/530, loss: 0.016751479357481003
2023-01-23 01:27:13.618556: step: 1676/530, loss: 0.02858734130859375
2023-01-23 01:27:14.740190: step: 1680/530, loss: 0.04429321363568306
2023-01-23 01:27:15.851719: step: 1684/530, loss: 0.0472647063434124
2023-01-23 01:27:16.956852: step: 1688/530, loss: 0.13532742857933044
2023-01-23 01:27:18.063265: step: 1692/530, loss: 0.07137179374694824
2023-01-23 01:27:19.171897: step: 1696/530, loss: 0.142163947224617
2023-01-23 01:27:20.271136: step: 1700/530, loss: 0.03503751754760742
2023-01-23 01:27:21.356123: step: 1704/530, loss: 0.8746212124824524
2023-01-23 01:27:22.470381: step: 1708/530, loss: 0.03901653364300728
2023-01-23 01:27:23.561633: step: 1712/530, loss: 0.017586277797818184
2023-01-23 01:27:24.678083: step: 1716/530, loss: 0.003415155690163374
2023-01-23 01:27:25.780839: step: 1720/530, loss: 0.36511650681495667
2023-01-23 01:27:26.904958: step: 1724/530, loss: 0.08045588433742523
2023-01-23 01:27:28.011819: step: 1728/530, loss: 0.05283351242542267
2023-01-23 01:27:29.119761: step: 1732/530, loss: 0.08687600493431091
2023-01-23 01:27:30.223612: step: 1736/530, loss: 0.04170827940106392
2023-01-23 01:27:31.318257: step: 1740/530, loss: 0.13895177841186523
2023-01-23 01:27:32.440969: step: 1744/530, loss: 0.017879106104373932
2023-01-23 01:27:33.565824: step: 1748/530, loss: 0.027414703741669655
2023-01-23 01:27:34.675224: step: 1752/530, loss: 0.06810932606458664
2023-01-23 01:27:35.814144: step: 1756/530, loss: 0.019004417583346367
2023-01-23 01:27:36.948961: step: 1760/530, loss: 0.01748180389404297
2023-01-23 01:27:38.053513: step: 1764/530, loss: 0.03506965562701225
2023-01-23 01:27:39.137836: step: 1768/530, loss: 0.07562761008739471
2023-01-23 01:27:40.244310: step: 1772/530, loss: 0.03868556767702103
2023-01-23 01:27:41.355682: step: 1776/530, loss: 0.04110002517700195
2023-01-23 01:27:42.453278: step: 1780/530, loss: 0.0022161006927490234
2023-01-23 01:27:43.554617: step: 1784/530, loss: 0.38225534558296204
2023-01-23 01:27:44.678610: step: 1788/530, loss: 0.04514579847455025
2023-01-23 01:27:45.808971: step: 1792/530, loss: 0.04293088987469673
2023-01-23 01:27:46.920943: step: 1796/530, loss: 0.04873795807361603
2023-01-23 01:27:48.058959: step: 1800/530, loss: 0.068383127450943
2023-01-23 01:27:49.179707: step: 1804/530, loss: 0.03583583980798721
2023-01-23 01:27:50.286871: step: 1808/530, loss: 0.025852110236883163
2023-01-23 01:27:51.417453: step: 1812/530, loss: 0.02477121353149414
2023-01-23 01:27:52.538518: step: 1816/530, loss: 0.17154522240161896
2023-01-23 01:27:53.677559: step: 1820/530, loss: 0.018378447741270065
2023-01-23 01:27:54.769389: step: 1824/530, loss: 0.05001030117273331
2023-01-23 01:27:55.883123: step: 1828/530, loss: 0.04947967454791069
2023-01-23 01:27:56.999479: step: 1832/530, loss: 0.06495733559131622
2023-01-23 01:27:58.138939: step: 1836/530, loss: 0.1112508773803711
2023-01-23 01:27:59.249815: step: 1840/530, loss: 0.03427476808428764
2023-01-23 01:28:00.413041: step: 1844/530, loss: 0.09455899894237518
2023-01-23 01:28:01.526376: step: 1848/530, loss: 0.020157624036073685
2023-01-23 01:28:02.644320: step: 1852/530, loss: 0.08197012543678284
2023-01-23 01:28:03.742936: step: 1856/530, loss: 0.09289780259132385
2023-01-23 01:28:04.864628: step: 1860/530, loss: 0.010397863574326038
2023-01-23 01:28:06.008023: step: 1864/530, loss: 0.05129518732428551
2023-01-23 01:28:07.106150: step: 1868/530, loss: 0.5903326272964478
2023-01-23 01:28:08.188986: step: 1872/530, loss: 0.01797323301434517
2023-01-23 01:28:09.289935: step: 1876/530, loss: 0.07294521480798721
2023-01-23 01:28:10.406371: step: 1880/530, loss: 0.00138940813485533
2023-01-23 01:28:11.532909: step: 1884/530, loss: 0.010287284851074219
2023-01-23 01:28:12.634737: step: 1888/530, loss: 0.02316570281982422
2023-01-23 01:28:13.729202: step: 1892/530, loss: 0.006842136383056641
2023-01-23 01:28:14.823028: step: 1896/530, loss: 0.8414446711540222
2023-01-23 01:28:15.922626: step: 1900/530, loss: 0.018769074231386185
2023-01-23 01:28:17.018225: step: 1904/530, loss: 0.06226663663983345
2023-01-23 01:28:18.148716: step: 1908/530, loss: 0.03171062469482422
2023-01-23 01:28:19.279080: step: 1912/530, loss: 0.028194524347782135
2023-01-23 01:28:20.370178: step: 1916/530, loss: 0.04950986057519913
2023-01-23 01:28:21.476646: step: 1920/530, loss: 0.06573066860437393
2023-01-23 01:28:22.614693: step: 1924/530, loss: 0.03975038602948189
2023-01-23 01:28:23.704734: step: 1928/530, loss: 0.053765106946229935
2023-01-23 01:28:24.811492: step: 1932/530, loss: 0.024614715948700905
2023-01-23 01:28:25.907512: step: 1936/530, loss: 0.003526926040649414
2023-01-23 01:28:27.021105: step: 1940/530, loss: 0.0450170561671257
2023-01-23 01:28:28.150570: step: 1944/530, loss: 0.03073573112487793
2023-01-23 01:28:29.259295: step: 1948/530, loss: 0.054958537220954895
2023-01-23 01:28:30.355043: step: 1952/530, loss: 0.08042354881763458
2023-01-23 01:28:31.441581: step: 1956/530, loss: 0.362433522939682
2023-01-23 01:28:32.578420: step: 1960/530, loss: 0.01531982421875
2023-01-23 01:28:33.706617: step: 1964/530, loss: 0.05685710906982422
2023-01-23 01:28:34.799487: step: 1968/530, loss: 0.10724525153636932
2023-01-23 01:28:35.903626: step: 1972/530, loss: 0.0006605624803341925
2023-01-23 01:28:36.993842: step: 1976/530, loss: 0.023868655785918236
2023-01-23 01:28:38.077298: step: 1980/530, loss: 0.07218912243843079
2023-01-23 01:28:39.185278: step: 1984/530, loss: 0.0767270103096962
2023-01-23 01:28:40.316987: step: 1988/530, loss: 0.034610748291015625
2023-01-23 01:28:41.407990: step: 1992/530, loss: 0.03550998866558075
2023-01-23 01:28:42.497533: step: 1996/530, loss: 0.014169692993164062
2023-01-23 01:28:43.600634: step: 2000/530, loss: 0.10332374274730682
2023-01-23 01:28:44.673864: step: 2004/530, loss: 0.07594108581542969
2023-01-23 01:28:45.778991: step: 2008/530, loss: 0.0193804744631052
2023-01-23 01:28:46.870294: step: 2012/530, loss: 0.027985287830233574
2023-01-23 01:28:47.977674: step: 2016/530, loss: 0.007962321862578392
2023-01-23 01:28:49.112169: step: 2020/530, loss: 0.05670957639813423
2023-01-23 01:28:50.203309: step: 2024/530, loss: 0.010011625476181507
2023-01-23 01:28:51.341966: step: 2028/530, loss: 0.149058535695076
2023-01-23 01:28:52.446938: step: 2032/530, loss: 0.01309061050415039
2023-01-23 01:28:53.558255: step: 2036/530, loss: 0.01413955632597208
2023-01-23 01:28:54.656098: step: 2040/530, loss: 0.18897266685962677
2023-01-23 01:28:55.754838: step: 2044/530, loss: 0.20500129461288452
2023-01-23 01:28:56.861122: step: 2048/530, loss: 0.007315921597182751
2023-01-23 01:28:58.051031: step: 2052/530, loss: 0.10493364185094833
2023-01-23 01:28:59.139123: step: 2056/530, loss: 0.01532754860818386
2023-01-23 01:29:00.248170: step: 2060/530, loss: 0.044478606432676315
2023-01-23 01:29:01.347349: step: 2064/530, loss: 0.17894811928272247
2023-01-23 01:29:02.440462: step: 2068/530, loss: 0.1101846694946289
2023-01-23 01:29:03.559682: step: 2072/530, loss: 0.9316828846931458
2023-01-23 01:29:04.675008: step: 2076/530, loss: 0.004873180761933327
2023-01-23 01:29:05.800471: step: 2080/530, loss: 0.06384678184986115
2023-01-23 01:29:06.923256: step: 2084/530, loss: 0.05898475646972656
2023-01-23 01:29:08.043397: step: 2088/530, loss: 0.014600194059312344
2023-01-23 01:29:09.127300: step: 2092/530, loss: 0.01623525470495224
2023-01-23 01:29:10.211414: step: 2096/530, loss: 0.007298898417502642
2023-01-23 01:29:11.344494: step: 2100/530, loss: 0.03826083987951279
2023-01-23 01:29:12.461373: step: 2104/530, loss: 0.011189555749297142
2023-01-23 01:29:13.567318: step: 2108/530, loss: 0.01828782632946968
2023-01-23 01:29:14.705817: step: 2112/530, loss: 0.021965980529785156
2023-01-23 01:29:15.796320: step: 2116/530, loss: 0.002548742340877652
2023-01-23 01:29:16.925082: step: 2120/530, loss: 0.058190345764160156
==================================================
Loss: 0.092
--------------------
Dev: {'event': {'p': 0.5915201654601862, 'r': 0.7616511318242344, 'f1': 0.6658905704307335}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 11}
Test: {'event': {'p': 0.6262898160610139, 'r': 0.8135198135198135, 'f1': 0.7077313054499366}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 11}
Chinese: {'event': {'p': 0.5584415584415584, 'r': 0.7962962962962963, 'f1': 0.6564885496183205}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 11}
Korean: {'event': {'p': 0.6229508196721312, 'r': 0.6031746031746031, 'f1': 0.6129032258064517}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 11}
Russian: {'event': {'p': 0.4523809523809524, 'r': 0.5277777777777778, 'f1': 0.4871794871794871}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 11}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.5708622398414271, 'r': 0.7669773635153129, 'f1': 0.6545454545454545}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Eng Test for Chinese: {'event': {'p': 0.6044052863436123, 'r': 0.7995337995337995, 'f1': 0.6884094330155545}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
Sample Chinese: {'event': {'p': 0.6578947368421053, 'r': 0.9259259259259259, 'f1': 0.7692307692307692}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 5}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6466512702078522, 'r': 0.7456724367509987, 'f1': 0.6926406926406927}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Eng Test for Korean: {'event': {'p': 0.6762148337595908, 'r': 0.7703962703962703, 'f1': 0.7202397166984473}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
Sample Korean: {'event': {'p': 0.6862745098039216, 'r': 0.5555555555555556, 'f1': 0.6140350877192983}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 7}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5971370143149284, 'r': 0.7776298268974701, 'f1': 0.6755349913244649}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Russian: {'event': {'p': 0.6401673640167364, 'r': 0.8024475524475524, 'f1': 0.7121799844840963}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Russian: {'event': {'p': 0.5897435897435898, 'r': 0.6388888888888888, 'f1': 0.6133333333333332}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
******************************
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 01:29:56.484194: step: 4/530, loss: 0.12217392772436142
2023-01-23 01:29:57.607011: step: 8/530, loss: 0.04355983808636665
2023-01-23 01:29:58.715242: step: 12/530, loss: 0.00415725726634264
2023-01-23 01:29:59.813461: step: 16/530, loss: 0.12369203567504883
2023-01-23 01:30:00.931251: step: 20/530, loss: 0.00567626953125
2023-01-23 01:30:02.009711: step: 24/530, loss: 0.03349151834845543
2023-01-23 01:30:03.115024: step: 28/530, loss: 0.045412540435791016
2023-01-23 01:30:04.240191: step: 32/530, loss: 0.04692840576171875
2023-01-23 01:30:05.340809: step: 36/530, loss: 0.004734134767204523
2023-01-23 01:30:06.431328: step: 40/530, loss: 0.061406850814819336
2023-01-23 01:30:07.524429: step: 44/530, loss: 0.01967925950884819
2023-01-23 01:30:08.627793: step: 48/530, loss: 0.09564915299415588
2023-01-23 01:30:09.712044: step: 52/530, loss: 0.0012290955055505037
2023-01-23 01:30:10.825272: step: 56/530, loss: 0.03349800407886505
2023-01-23 01:30:11.914067: step: 60/530, loss: 0.057605646550655365
2023-01-23 01:30:13.019499: step: 64/530, loss: 0.1997934877872467
2023-01-23 01:30:14.111988: step: 68/530, loss: 0.01654500886797905
2023-01-23 01:30:15.220844: step: 72/530, loss: 0.1611625701189041
2023-01-23 01:30:16.306397: step: 76/530, loss: 0.00711102457717061
2023-01-23 01:30:17.407950: step: 80/530, loss: 0.0069855693727731705
2023-01-23 01:30:18.536927: step: 84/530, loss: 0.06616564095020294
2023-01-23 01:30:19.683667: step: 88/530, loss: 0.5605751872062683
2023-01-23 01:30:20.784351: step: 92/530, loss: 0.07526283711194992
2023-01-23 01:30:21.887334: step: 96/530, loss: 0.3889423608779907
2023-01-23 01:30:23.026839: step: 100/530, loss: 0.002331542782485485
2023-01-23 01:30:24.147762: step: 104/530, loss: 0.05284447595477104
2023-01-23 01:30:25.260645: step: 108/530, loss: 0.028945542871952057
2023-01-23 01:30:26.359287: step: 112/530, loss: 0.007387829013168812
2023-01-23 01:30:27.483245: step: 116/530, loss: 0.0201397892087698
2023-01-23 01:30:28.598779: step: 120/530, loss: 0.011191368103027344
2023-01-23 01:30:29.703646: step: 124/530, loss: 0.03301756829023361
2023-01-23 01:30:30.769474: step: 128/530, loss: 0.0010143041145056486
2023-01-23 01:30:31.860531: step: 132/530, loss: 0.003820768091827631
2023-01-23 01:30:32.993960: step: 136/530, loss: 0.01592733897268772
2023-01-23 01:30:34.134043: step: 140/530, loss: 0.0769595205783844
2023-01-23 01:30:35.254982: step: 144/530, loss: 0.06012621149420738
2023-01-23 01:30:36.352153: step: 148/530, loss: 0.01934204250574112
2023-01-23 01:30:37.448484: step: 152/530, loss: 0.12173499912023544
2023-01-23 01:30:38.568157: step: 156/530, loss: 0.006052779965102673
2023-01-23 01:30:39.655517: step: 160/530, loss: 0.0025989532005041838
2023-01-23 01:30:40.797698: step: 164/530, loss: 0.009674168191850185
2023-01-23 01:30:41.896434: step: 168/530, loss: 0.021408509463071823
2023-01-23 01:30:43.007242: step: 172/530, loss: 0.034229278564453125
2023-01-23 01:30:44.116432: step: 176/530, loss: 0.05949997901916504
2023-01-23 01:30:45.212153: step: 180/530, loss: 0.31714552640914917
2023-01-23 01:30:46.303460: step: 184/530, loss: 0.013253307901322842
2023-01-23 01:30:47.439423: step: 188/530, loss: 0.01837310753762722
2023-01-23 01:30:48.563416: step: 192/530, loss: 0.04658794403076172
2023-01-23 01:30:49.657039: step: 196/530, loss: 0.028780221939086914
2023-01-23 01:30:50.734748: step: 200/530, loss: 0.02681450918316841
2023-01-23 01:30:51.842228: step: 204/530, loss: 0.037584494799375534
2023-01-23 01:30:52.996921: step: 208/530, loss: 0.05729694664478302
2023-01-23 01:30:54.117104: step: 212/530, loss: 0.024480724707245827
2023-01-23 01:30:55.215594: step: 216/530, loss: 0.0057472228072583675
2023-01-23 01:30:56.296996: step: 220/530, loss: 0.1993524432182312
2023-01-23 01:30:57.387790: step: 224/530, loss: 0.04384488984942436
2023-01-23 01:30:58.507017: step: 228/530, loss: 0.08120954036712646
2023-01-23 01:30:59.599320: step: 232/530, loss: 0.08713507652282715
2023-01-23 01:31:00.734129: step: 236/530, loss: 0.04013776779174805
2023-01-23 01:31:01.830822: step: 240/530, loss: 0.026754379272460938
2023-01-23 01:31:02.943711: step: 244/530, loss: 0.012256240472197533
2023-01-23 01:31:04.048666: step: 248/530, loss: 0.021729851141572
2023-01-23 01:31:05.135367: step: 252/530, loss: 0.015575408935546875
2023-01-23 01:31:06.242584: step: 256/530, loss: 0.015318488702178001
2023-01-23 01:31:07.380333: step: 260/530, loss: 0.013233941979706287
2023-01-23 01:31:08.484569: step: 264/530, loss: 0.03330669552087784
2023-01-23 01:31:09.583212: step: 268/530, loss: 0.17449398338794708
2023-01-23 01:31:10.702079: step: 272/530, loss: 0.00700454693287611
2023-01-23 01:31:11.825507: step: 276/530, loss: 0.07040786743164062
2023-01-23 01:31:12.938569: step: 280/530, loss: 0.005203723907470703
2023-01-23 01:31:14.036610: step: 284/530, loss: 0.06285848468542099
2023-01-23 01:31:15.158320: step: 288/530, loss: 0.05106430500745773
2023-01-23 01:31:16.288477: step: 292/530, loss: 0.040328312665224075
2023-01-23 01:31:17.383690: step: 296/530, loss: 0.008420849218964577
2023-01-23 01:31:18.475054: step: 300/530, loss: 0.13301372528076172
2023-01-23 01:31:19.586269: step: 304/530, loss: 0.031146671622991562
2023-01-23 01:31:20.669573: step: 308/530, loss: 0.03583240509033203
2023-01-23 01:31:21.796439: step: 312/530, loss: 0.20479458570480347
2023-01-23 01:31:22.919722: step: 316/530, loss: 0.008874607272446156
2023-01-23 01:31:24.027662: step: 320/530, loss: 0.0280914306640625
2023-01-23 01:31:25.166229: step: 324/530, loss: 0.014903450384736061
2023-01-23 01:31:26.278274: step: 328/530, loss: 0.07563018798828125
2023-01-23 01:31:27.399079: step: 332/530, loss: 0.0005148887867107987
2023-01-23 01:31:28.509493: step: 336/530, loss: 0.06439914554357529
2023-01-23 01:31:29.593549: step: 340/530, loss: 0.03669404983520508
2023-01-23 01:31:30.703175: step: 344/530, loss: 0.04858074337244034
2023-01-23 01:31:31.809097: step: 348/530, loss: 0.15034082531929016
2023-01-23 01:31:32.946279: step: 352/530, loss: 0.04743604734539986
2023-01-23 01:31:34.050001: step: 356/530, loss: 0.004701673984527588
2023-01-23 01:31:35.164459: step: 360/530, loss: 0.03838415443897247
2023-01-23 01:31:36.297081: step: 364/530, loss: 0.016762638464570045
2023-01-23 01:31:37.409104: step: 368/530, loss: 0.0979059487581253
2023-01-23 01:31:38.492489: step: 372/530, loss: 0.0441705696284771
2023-01-23 01:31:39.574879: step: 376/530, loss: 0.0982576310634613
2023-01-23 01:31:40.675637: step: 380/530, loss: 0.16418859362602234
2023-01-23 01:31:41.818784: step: 384/530, loss: 0.007172155659645796
2023-01-23 01:31:42.964168: step: 388/530, loss: 1.0394030809402466
2023-01-23 01:31:44.067463: step: 392/530, loss: 0.008274555206298828
2023-01-23 01:31:45.189377: step: 396/530, loss: 0.050685882568359375
2023-01-23 01:31:46.334197: step: 400/530, loss: 0.035683728754520416
2023-01-23 01:31:47.458649: step: 404/530, loss: 0.03522949293255806
2023-01-23 01:31:48.572491: step: 408/530, loss: 0.03737306594848633
2023-01-23 01:31:49.697726: step: 412/530, loss: 0.010476303286850452
2023-01-23 01:31:50.807417: step: 416/530, loss: 0.027260685339570045
2023-01-23 01:31:51.921961: step: 420/530, loss: 0.0809205025434494
2023-01-23 01:31:53.041245: step: 424/530, loss: 0.07678051292896271
2023-01-23 01:31:54.149252: step: 428/530, loss: 0.014821911230683327
2023-01-23 01:31:55.245581: step: 432/530, loss: 0.006715155206620693
2023-01-23 01:31:56.396588: step: 436/530, loss: 0.006562614813446999
2023-01-23 01:31:57.501757: step: 440/530, loss: 0.02201845683157444
2023-01-23 01:31:58.607299: step: 444/530, loss: 0.04666843265295029
2023-01-23 01:31:59.720213: step: 448/530, loss: 0.03583640977740288
2023-01-23 01:32:00.845008: step: 452/530, loss: 0.2653636932373047
2023-01-23 01:32:01.926088: step: 456/530, loss: 0.01358795166015625
2023-01-23 01:32:03.031334: step: 460/530, loss: 0.023645926266908646
2023-01-23 01:32:04.111580: step: 464/530, loss: 0.0006994247669354081
2023-01-23 01:32:05.193970: step: 468/530, loss: 0.059747982770204544
2023-01-23 01:32:06.304145: step: 472/530, loss: 0.0257110595703125
2023-01-23 01:32:07.439296: step: 476/530, loss: 0.019199514761567116
2023-01-23 01:32:08.563672: step: 480/530, loss: 0.06899251788854599
2023-01-23 01:32:09.672297: step: 484/530, loss: 0.026078414171934128
2023-01-23 01:32:10.764689: step: 488/530, loss: 0.007918357849121094
2023-01-23 01:32:11.859737: step: 492/530, loss: 0.014980316162109375
2023-01-23 01:32:12.978165: step: 496/530, loss: 0.46514204144477844
2023-01-23 01:32:14.064846: step: 500/530, loss: 0.0698794350028038
2023-01-23 01:32:15.183222: step: 504/530, loss: 1.057571291923523
2023-01-23 01:32:16.285471: step: 508/530, loss: 0.006717681884765625
2023-01-23 01:32:17.367082: step: 512/530, loss: 0.11410808563232422
2023-01-23 01:32:18.467377: step: 516/530, loss: 0.023461056873202324
2023-01-23 01:32:19.601709: step: 520/530, loss: 0.019330406561493874
2023-01-23 01:32:20.693472: step: 524/530, loss: 0.017003346234560013
2023-01-23 01:32:21.837110: step: 528/530, loss: 0.02094240114092827
2023-01-23 01:32:22.944197: step: 532/530, loss: 0.03984546661376953
2023-01-23 01:32:24.060420: step: 536/530, loss: 0.19856777787208557
2023-01-23 01:32:25.164227: step: 540/530, loss: 0.1138116866350174
2023-01-23 01:32:26.293164: step: 544/530, loss: 0.013024711981415749
2023-01-23 01:32:27.413105: step: 548/530, loss: 0.0009488106006756425
2023-01-23 01:32:28.535614: step: 552/530, loss: 0.062089256942272186
2023-01-23 01:32:29.637060: step: 556/530, loss: 0.06643286347389221
2023-01-23 01:32:30.759219: step: 560/530, loss: 0.07790813595056534
2023-01-23 01:32:31.850746: step: 564/530, loss: 0.006512498948723078
2023-01-23 01:32:32.993740: step: 568/530, loss: 0.07037000358104706
2023-01-23 01:32:34.099461: step: 572/530, loss: 0.007596397306770086
2023-01-23 01:32:35.191143: step: 576/530, loss: 0.011252403259277344
2023-01-23 01:32:36.316109: step: 580/530, loss: 0.0428893119096756
2023-01-23 01:32:37.412258: step: 584/530, loss: 0.044447995722293854
2023-01-23 01:32:38.536350: step: 588/530, loss: 0.011728476732969284
2023-01-23 01:32:39.615368: step: 592/530, loss: 0.05866604298353195
2023-01-23 01:32:40.714121: step: 596/530, loss: 0.040102627128362656
2023-01-23 01:32:41.817377: step: 600/530, loss: 0.07455454766750336
2023-01-23 01:32:42.907431: step: 604/530, loss: 0.01578970067203045
2023-01-23 01:32:44.017639: step: 608/530, loss: 0.01084680575877428
2023-01-23 01:32:45.110807: step: 612/530, loss: 0.01986847072839737
2023-01-23 01:32:46.226842: step: 616/530, loss: 0.07225351780653
2023-01-23 01:32:47.330861: step: 620/530, loss: 0.012257957831025124
2023-01-23 01:32:48.451986: step: 624/530, loss: 0.011363983154296875
2023-01-23 01:32:49.521867: step: 628/530, loss: 0.01115407980978489
2023-01-23 01:32:50.632084: step: 632/530, loss: 0.049120333045721054
2023-01-23 01:32:51.718425: step: 636/530, loss: 0.04525451362133026
2023-01-23 01:32:52.851757: step: 640/530, loss: 0.22013282775878906
2023-01-23 01:32:53.963867: step: 644/530, loss: 0.037776850163936615
2023-01-23 01:32:55.052985: step: 648/530, loss: 0.0455472469329834
2023-01-23 01:32:56.159376: step: 652/530, loss: 0.12250444293022156
2023-01-23 01:32:57.253715: step: 656/530, loss: 0.07416753470897675
2023-01-23 01:32:58.362854: step: 660/530, loss: 0.2730955183506012
2023-01-23 01:32:59.508073: step: 664/530, loss: 0.11771383136510849
2023-01-23 01:33:00.626504: step: 668/530, loss: 0.023672914132475853
2023-01-23 01:33:01.700221: step: 672/530, loss: 0.05048871040344238
2023-01-23 01:33:02.822642: step: 676/530, loss: 0.028913021087646484
2023-01-23 01:33:03.948452: step: 680/530, loss: 0.05248761549592018
2023-01-23 01:33:05.039794: step: 684/530, loss: 0.13372927904129028
2023-01-23 01:33:06.135470: step: 688/530, loss: 0.031251147389411926
2023-01-23 01:33:07.233506: step: 692/530, loss: 0.1476929783821106
2023-01-23 01:33:08.353450: step: 696/530, loss: 0.0032839300110936165
2023-01-23 01:33:09.472251: step: 700/530, loss: 0.03127546235918999
2023-01-23 01:33:10.568898: step: 704/530, loss: 0.0023738860618323088
2023-01-23 01:33:11.680652: step: 708/530, loss: 0.012925529852509499
2023-01-23 01:33:12.797978: step: 712/530, loss: 0.12085571140050888
2023-01-23 01:33:13.912759: step: 716/530, loss: 0.0068305968306958675
2023-01-23 01:33:15.010672: step: 720/530, loss: 0.008514595218002796
2023-01-23 01:33:16.108509: step: 724/530, loss: 0.019307279959321022
2023-01-23 01:33:17.242595: step: 728/530, loss: 0.023670004680752754
2023-01-23 01:33:18.447303: step: 732/530, loss: 0.026579666882753372
2023-01-23 01:33:19.550201: step: 736/530, loss: 0.041666459292173386
2023-01-23 01:33:20.655398: step: 740/530, loss: 0.01831965520977974
2023-01-23 01:33:21.747780: step: 744/530, loss: 0.026883317157626152
2023-01-23 01:33:22.845273: step: 748/530, loss: 1.3865602016448975
2023-01-23 01:33:24.003243: step: 752/530, loss: 0.018810177221894264
2023-01-23 01:33:25.103942: step: 756/530, loss: 0.03131237253546715
2023-01-23 01:33:26.193089: step: 760/530, loss: 0.060655973851680756
2023-01-23 01:33:27.331588: step: 764/530, loss: 0.09271307289600372
2023-01-23 01:33:28.425345: step: 768/530, loss: 0.017095517367124557
2023-01-23 01:33:29.522056: step: 772/530, loss: 0.0029724121559411287
2023-01-23 01:33:30.644297: step: 776/530, loss: 0.03340339660644531
2023-01-23 01:33:31.766531: step: 780/530, loss: 0.009843254461884499
2023-01-23 01:33:32.876025: step: 784/530, loss: 0.02620868757367134
2023-01-23 01:33:33.984023: step: 788/530, loss: 0.16946296393871307
2023-01-23 01:33:35.069385: step: 792/530, loss: 0.00152845389675349
2023-01-23 01:33:36.181997: step: 796/530, loss: 0.06758613884449005
2023-01-23 01:33:37.288841: step: 800/530, loss: 0.025009775534272194
2023-01-23 01:33:38.400260: step: 804/530, loss: 0.02290639840066433
2023-01-23 01:33:39.512914: step: 808/530, loss: 0.025272177532315254
2023-01-23 01:33:40.618148: step: 812/530, loss: 0.14129333198070526
2023-01-23 01:33:41.727630: step: 816/530, loss: 0.10452881455421448
2023-01-23 01:33:42.823728: step: 820/530, loss: 0.0017179489368572831
2023-01-23 01:33:43.931416: step: 824/530, loss: 0.3946347236633301
2023-01-23 01:33:45.006934: step: 828/530, loss: 0.020306779071688652
2023-01-23 01:33:46.121806: step: 832/530, loss: 0.13113775849342346
2023-01-23 01:33:47.238892: step: 836/530, loss: 0.21663188934326172
2023-01-23 01:33:48.346508: step: 840/530, loss: 0.3175109922885895
2023-01-23 01:33:49.434800: step: 844/530, loss: 0.06110329553484917
2023-01-23 01:33:50.577164: step: 848/530, loss: 0.1135474145412445
2023-01-23 01:33:51.690246: step: 852/530, loss: 0.01379413716495037
2023-01-23 01:33:52.774136: step: 856/530, loss: 0.000433504581451416
2023-01-23 01:33:53.871849: step: 860/530, loss: 0.05575408786535263
2023-01-23 01:33:54.990958: step: 864/530, loss: 0.016370154917240143
2023-01-23 01:33:56.117293: step: 868/530, loss: 0.10320253670215607
2023-01-23 01:33:57.230858: step: 872/530, loss: 0.018551256507635117
2023-01-23 01:33:58.316881: step: 876/530, loss: 0.009125906974077225
2023-01-23 01:33:59.419962: step: 880/530, loss: 0.0428614616394043
2023-01-23 01:34:00.523799: step: 884/530, loss: 0.03135743364691734
2023-01-23 01:34:01.620681: step: 888/530, loss: 0.04365234449505806
2023-01-23 01:34:02.696514: step: 892/530, loss: 0.1356188803911209
2023-01-23 01:34:03.814746: step: 896/530, loss: 0.031800076365470886
2023-01-23 01:34:04.915532: step: 900/530, loss: 0.03432692959904671
2023-01-23 01:34:06.022277: step: 904/530, loss: 0.02647094801068306
2023-01-23 01:34:07.132315: step: 908/530, loss: 0.028005409985780716
2023-01-23 01:34:08.222664: step: 912/530, loss: 0.029528236016631126
2023-01-23 01:34:09.344498: step: 916/530, loss: 0.029340792447328568
2023-01-23 01:34:10.439342: step: 920/530, loss: 0.02888813242316246
2023-01-23 01:34:11.542426: step: 924/530, loss: 0.10296416282653809
2023-01-23 01:34:12.660996: step: 928/530, loss: 0.01380016840994358
2023-01-23 01:34:13.777899: step: 932/530, loss: 0.05210408940911293
2023-01-23 01:34:14.859383: step: 936/530, loss: 0.03244619444012642
2023-01-23 01:34:15.938393: step: 940/530, loss: 0.5938853621482849
2023-01-23 01:34:17.029918: step: 944/530, loss: 0.0017591476207599044
2023-01-23 01:34:18.154909: step: 948/530, loss: 0.08948317170143127
2023-01-23 01:34:19.262626: step: 952/530, loss: 0.025825882330536842
2023-01-23 01:34:20.396018: step: 956/530, loss: 0.05368185415863991
2023-01-23 01:34:21.514589: step: 960/530, loss: 0.009030342102050781
2023-01-23 01:34:22.615260: step: 964/530, loss: 0.02614833600819111
2023-01-23 01:34:23.707692: step: 968/530, loss: 0.11007046699523926
2023-01-23 01:34:24.790677: step: 972/530, loss: 0.03461914137005806
2023-01-23 01:34:25.907730: step: 976/530, loss: 0.08862514793872833
2023-01-23 01:34:27.012055: step: 980/530, loss: 0.009628485888242722
2023-01-23 01:34:28.120759: step: 984/530, loss: 0.28468719124794006
2023-01-23 01:34:29.224400: step: 988/530, loss: 0.03630642965435982
2023-01-23 01:34:30.321827: step: 992/530, loss: 0.007634926121681929
2023-01-23 01:34:31.413899: step: 996/530, loss: 0.008600044064223766
2023-01-23 01:34:32.504312: step: 1000/530, loss: 0.10941076278686523
2023-01-23 01:34:33.638014: step: 1004/530, loss: 0.09134893119335175
2023-01-23 01:34:34.764022: step: 1008/530, loss: 0.10647161304950714
2023-01-23 01:34:35.880130: step: 1012/530, loss: 0.021001815795898438
2023-01-23 01:34:37.000897: step: 1016/530, loss: 0.007102012634277344
2023-01-23 01:34:38.105223: step: 1020/530, loss: 0.03594560548663139
2023-01-23 01:34:39.201249: step: 1024/530, loss: 0.04963388293981552
2023-01-23 01:34:40.313119: step: 1028/530, loss: 0.006227540783584118
2023-01-23 01:34:41.391976: step: 1032/530, loss: 0.057213690131902695
2023-01-23 01:34:42.513808: step: 1036/530, loss: 0.010787582956254482
2023-01-23 01:34:43.604638: step: 1040/530, loss: 0.03327369689941406
2023-01-23 01:34:44.699586: step: 1044/530, loss: 0.02487659454345703
2023-01-23 01:34:45.834787: step: 1048/530, loss: 0.05809640884399414
2023-01-23 01:34:46.919794: step: 1052/530, loss: 0.06843795627355576
2023-01-23 01:34:48.027787: step: 1056/530, loss: 0.08423156291246414
2023-01-23 01:34:49.125795: step: 1060/530, loss: 0.0011695862049236894
2023-01-23 01:34:50.217465: step: 1064/530, loss: 0.019686991348862648
2023-01-23 01:34:51.322363: step: 1068/530, loss: 0.000934600830078125
2023-01-23 01:34:52.413909: step: 1072/530, loss: 0.09884815663099289
2023-01-23 01:34:53.520447: step: 1076/530, loss: 0.03498096764087677
2023-01-23 01:34:54.629440: step: 1080/530, loss: 0.006920528598129749
2023-01-23 01:34:55.750782: step: 1084/530, loss: 0.44732505083084106
2023-01-23 01:34:56.843650: step: 1088/530, loss: 0.028714848682284355
2023-01-23 01:34:57.931300: step: 1092/530, loss: 0.03812284395098686
2023-01-23 01:34:59.019763: step: 1096/530, loss: 0.006140708923339844
2023-01-23 01:35:00.137385: step: 1100/530, loss: 0.045720770955085754
2023-01-23 01:35:01.249439: step: 1104/530, loss: 0.012720775790512562
2023-01-23 01:35:02.366988: step: 1108/530, loss: 0.021930169314146042
2023-01-23 01:35:03.462596: step: 1112/530, loss: 0.016519851982593536
2023-01-23 01:35:04.576133: step: 1116/530, loss: 0.02514674700796604
2023-01-23 01:35:05.703179: step: 1120/530, loss: 0.13176536560058594
2023-01-23 01:35:06.828737: step: 1124/530, loss: 0.047174740582704544
2023-01-23 01:35:07.960710: step: 1128/530, loss: 0.10025063157081604
2023-01-23 01:35:09.047267: step: 1132/530, loss: 0.03635873645544052
2023-01-23 01:35:10.130266: step: 1136/530, loss: 0.07207384705543518
2023-01-23 01:35:11.227619: step: 1140/530, loss: 0.02955608442425728
2023-01-23 01:35:12.324751: step: 1144/530, loss: 0.025429820641875267
2023-01-23 01:35:13.450042: step: 1148/530, loss: 0.08548621833324432
2023-01-23 01:35:14.565060: step: 1152/530, loss: 0.16207322478294373
2023-01-23 01:35:15.636070: step: 1156/530, loss: 0.020700300112366676
2023-01-23 01:35:16.710885: step: 1160/530, loss: 0.002082651946693659
2023-01-23 01:35:17.823325: step: 1164/530, loss: 0.007279396057128906
2023-01-23 01:35:18.908390: step: 1168/530, loss: 0.003183651017025113
2023-01-23 01:35:20.041309: step: 1172/530, loss: 0.018611837178468704
2023-01-23 01:35:21.146800: step: 1176/530, loss: 0.09921710193157196
2023-01-23 01:35:22.253956: step: 1180/530, loss: 0.07083268463611603
2023-01-23 01:35:23.358130: step: 1184/530, loss: 0.025111867114901543
2023-01-23 01:35:24.460438: step: 1188/530, loss: 0.004028988070785999
2023-01-23 01:35:25.547835: step: 1192/530, loss: 0.01356043852865696
2023-01-23 01:35:26.646339: step: 1196/530, loss: 0.0004744529724121094
2023-01-23 01:35:27.760066: step: 1200/530, loss: 0.025488998740911484
2023-01-23 01:35:28.924843: step: 1204/530, loss: 0.009497905150055885
2023-01-23 01:35:30.036028: step: 1208/530, loss: 0.3431139886379242
2023-01-23 01:35:31.140671: step: 1212/530, loss: 0.029784012585878372
2023-01-23 01:35:32.250285: step: 1216/530, loss: 0.017099952325224876
2023-01-23 01:35:33.351022: step: 1220/530, loss: 0.044805239886045456
2023-01-23 01:35:34.452967: step: 1224/530, loss: 0.04540227726101875
2023-01-23 01:35:35.561877: step: 1228/530, loss: 0.021887637674808502
2023-01-23 01:35:36.676400: step: 1232/530, loss: 0.03386092185974121
2023-01-23 01:35:37.779827: step: 1236/530, loss: 0.02501516416668892
2023-01-23 01:35:38.907850: step: 1240/530, loss: 0.02591400034725666
2023-01-23 01:35:40.014128: step: 1244/530, loss: 0.07956273853778839
2023-01-23 01:35:41.115233: step: 1248/530, loss: 0.36626559495925903
2023-01-23 01:35:42.244387: step: 1252/530, loss: 0.01176986750215292
2023-01-23 01:35:43.357750: step: 1256/530, loss: 0.004930878058075905
2023-01-23 01:35:44.495898: step: 1260/530, loss: 0.19106808304786682
2023-01-23 01:35:45.623126: step: 1264/530, loss: 0.03809051588177681
2023-01-23 01:35:46.727335: step: 1268/530, loss: 0.027323437854647636
2023-01-23 01:35:47.824821: step: 1272/530, loss: 0.020868491381406784
2023-01-23 01:35:48.934176: step: 1276/530, loss: 0.025566866621375084
2023-01-23 01:35:50.028254: step: 1280/530, loss: 0.17144207656383514
2023-01-23 01:35:51.123618: step: 1284/530, loss: 0.01393732987344265
2023-01-23 01:35:52.216539: step: 1288/530, loss: 0.021178627386689186
2023-01-23 01:35:53.327957: step: 1292/530, loss: 0.06793908774852753
2023-01-23 01:35:54.429589: step: 1296/530, loss: 0.15275421738624573
2023-01-23 01:35:55.519349: step: 1300/530, loss: 0.09885692596435547
2023-01-23 01:35:56.655747: step: 1304/530, loss: 0.06618261337280273
2023-01-23 01:35:57.734632: step: 1308/530, loss: 0.029015256091952324
2023-01-23 01:35:58.878589: step: 1312/530, loss: 0.037352755665779114
2023-01-23 01:35:59.953416: step: 1316/530, loss: 0.009375429712235928
2023-01-23 01:36:01.103100: step: 1320/530, loss: 0.09770459681749344
2023-01-23 01:36:02.208387: step: 1324/530, loss: 0.03231701999902725
2023-01-23 01:36:03.329904: step: 1328/530, loss: 0.11964817345142365
2023-01-23 01:36:04.487891: step: 1332/530, loss: 0.2794470489025116
2023-01-23 01:36:05.579236: step: 1336/530, loss: 0.014360261149704456
2023-01-23 01:36:06.704269: step: 1340/530, loss: 0.09358978271484375
2023-01-23 01:36:07.796477: step: 1344/530, loss: 0.0189801212400198
2023-01-23 01:36:08.921200: step: 1348/530, loss: 0.05653095245361328
2023-01-23 01:36:10.028419: step: 1352/530, loss: 0.057050321251153946
2023-01-23 01:36:11.112096: step: 1356/530, loss: 0.07047334313392639
2023-01-23 01:36:12.237013: step: 1360/530, loss: 0.04799318313598633
2023-01-23 01:36:13.330077: step: 1364/530, loss: 0.06344003975391388
2023-01-23 01:36:14.422220: step: 1368/530, loss: 0.011250496841967106
2023-01-23 01:36:15.530239: step: 1372/530, loss: 0.18379707634449005
2023-01-23 01:36:16.624289: step: 1376/530, loss: 0.014703750610351562
2023-01-23 01:36:17.712227: step: 1380/530, loss: 0.0005214214324951172
2023-01-23 01:36:18.847152: step: 1384/530, loss: 0.10467061400413513
2023-01-23 01:36:19.948547: step: 1388/530, loss: 0.03388223797082901
2023-01-23 01:36:21.063206: step: 1392/530, loss: 0.28180214762687683
2023-01-23 01:36:22.139816: step: 1396/530, loss: 0.08639049530029297
2023-01-23 01:36:23.294164: step: 1400/530, loss: 0.004028511233627796
2023-01-23 01:36:24.402203: step: 1404/530, loss: 0.05231790617108345
2023-01-23 01:36:25.526352: step: 1408/530, loss: 0.0005071640480309725
2023-01-23 01:36:26.634406: step: 1412/530, loss: 0.023090269416570663
2023-01-23 01:36:27.707069: step: 1416/530, loss: 0.06920156627893448
2023-01-23 01:36:28.860217: step: 1420/530, loss: 0.049269963055849075
2023-01-23 01:36:29.988199: step: 1424/530, loss: 0.03158741071820259
2023-01-23 01:36:31.082301: step: 1428/530, loss: 0.07916012406349182
2023-01-23 01:36:32.200636: step: 1432/530, loss: 0.029845189303159714
2023-01-23 01:36:33.325392: step: 1436/530, loss: 0.0023685453925281763
2023-01-23 01:36:34.449345: step: 1440/530, loss: 0.02087840996682644
2023-01-23 01:36:35.567017: step: 1444/530, loss: 0.010367393493652344
2023-01-23 01:36:36.684420: step: 1448/530, loss: 0.055041778832674026
2023-01-23 01:36:37.802493: step: 1452/530, loss: 0.025073720142245293
2023-01-23 01:36:38.924186: step: 1456/530, loss: 0.014637185260653496
2023-01-23 01:36:40.005693: step: 1460/530, loss: 0.10305138677358627
2023-01-23 01:36:41.097717: step: 1464/530, loss: 0.07657727599143982
2023-01-23 01:36:42.188901: step: 1468/530, loss: 0.00577235221862793
2023-01-23 01:36:43.284530: step: 1472/530, loss: 0.037941742688417435
2023-01-23 01:36:44.405174: step: 1476/530, loss: 0.05729350820183754
2023-01-23 01:36:45.521471: step: 1480/530, loss: 0.04704008251428604
2023-01-23 01:36:46.633090: step: 1484/530, loss: 0.012769078835844994
2023-01-23 01:36:47.733019: step: 1488/530, loss: 0.1735800802707672
2023-01-23 01:36:48.829172: step: 1492/530, loss: 0.03529825434088707
2023-01-23 01:36:49.932818: step: 1496/530, loss: 0.10106156021356583
2023-01-23 01:36:51.030099: step: 1500/530, loss: 0.020718956366181374
2023-01-23 01:36:52.119770: step: 1504/530, loss: 0.016636420041322708
2023-01-23 01:36:53.216519: step: 1508/530, loss: 0.029117537662386894
2023-01-23 01:36:54.341262: step: 1512/530, loss: 0.20411300659179688
2023-01-23 01:36:55.483231: step: 1516/530, loss: 0.09355974197387695
2023-01-23 01:36:56.630658: step: 1520/530, loss: 0.1594589203596115
2023-01-23 01:36:57.713271: step: 1524/530, loss: 0.035562921315431595
2023-01-23 01:36:58.792000: step: 1528/530, loss: 0.030826473608613014
2023-01-23 01:36:59.882326: step: 1532/530, loss: 0.04639816656708717
2023-01-23 01:37:00.978007: step: 1536/530, loss: 0.002740764757618308
2023-01-23 01:37:02.076184: step: 1540/530, loss: 0.01763463020324707
2023-01-23 01:37:03.201761: step: 1544/530, loss: 0.03533878177404404
2023-01-23 01:37:04.290117: step: 1548/530, loss: 0.002085018204525113
2023-01-23 01:37:05.385173: step: 1552/530, loss: 0.038984108716249466
2023-01-23 01:37:06.452053: step: 1556/530, loss: 0.01623830758035183
2023-01-23 01:37:07.573621: step: 1560/530, loss: 0.477698415517807
2023-01-23 01:37:08.682233: step: 1564/530, loss: 0.03649912029504776
2023-01-23 01:37:09.798616: step: 1568/530, loss: 0.05480947718024254
2023-01-23 01:37:10.876393: step: 1572/530, loss: 0.0018564224010333419
2023-01-23 01:37:11.989470: step: 1576/530, loss: 0.08095093071460724
2023-01-23 01:37:13.113844: step: 1580/530, loss: 0.029819583520293236
2023-01-23 01:37:14.195518: step: 1584/530, loss: 0.04954786226153374
2023-01-23 01:37:15.319403: step: 1588/530, loss: 0.04645295441150665
2023-01-23 01:37:16.441210: step: 1592/530, loss: 0.03908901289105415
2023-01-23 01:37:17.513973: step: 1596/530, loss: 0.05355939641594887
2023-01-23 01:37:18.607895: step: 1600/530, loss: 0.05258655548095703
2023-01-23 01:37:19.739057: step: 1604/530, loss: 0.11353526264429092
2023-01-23 01:37:20.830387: step: 1608/530, loss: 0.03134965896606445
2023-01-23 01:37:21.908328: step: 1612/530, loss: 0.03582439571619034
2023-01-23 01:37:23.049874: step: 1616/530, loss: 0.025363540276885033
2023-01-23 01:37:24.166447: step: 1620/530, loss: 0.08655862510204315
2023-01-23 01:37:25.317569: step: 1624/530, loss: 0.001968860626220703
2023-01-23 01:37:26.434294: step: 1628/530, loss: 0.0023981095291674137
2023-01-23 01:37:27.541240: step: 1632/530, loss: 0.0614381805062294
2023-01-23 01:37:28.621787: step: 1636/530, loss: 0.1926080733537674
2023-01-23 01:37:29.722878: step: 1640/530, loss: 0.08081059157848358
2023-01-23 01:37:30.819720: step: 1644/530, loss: 0.1627291738986969
2023-01-23 01:37:31.923900: step: 1648/530, loss: 0.018153857439756393
2023-01-23 01:37:33.033773: step: 1652/530, loss: 0.06737180054187775
2023-01-23 01:37:34.115893: step: 1656/530, loss: 0.42687034606933594
2023-01-23 01:37:35.217582: step: 1660/530, loss: 0.021570205688476562
2023-01-23 01:37:36.313605: step: 1664/530, loss: 0.062410593032836914
2023-01-23 01:37:37.442188: step: 1668/530, loss: 0.15253382921218872
2023-01-23 01:37:38.539651: step: 1672/530, loss: 0.04922495037317276
2023-01-23 01:37:39.656549: step: 1676/530, loss: 0.07331438362598419
2023-01-23 01:37:40.783157: step: 1680/530, loss: 0.012849998660385609
2023-01-23 01:37:41.884424: step: 1684/530, loss: 0.052106477320194244
2023-01-23 01:37:42.994306: step: 1688/530, loss: 0.02233600616455078
2023-01-23 01:37:44.116107: step: 1692/530, loss: 0.06385879218578339
2023-01-23 01:37:45.232277: step: 1696/530, loss: 0.09615517407655716
2023-01-23 01:37:46.318470: step: 1700/530, loss: 0.044299982488155365
2023-01-23 01:37:47.415808: step: 1704/530, loss: 0.024796176701784134
2023-01-23 01:37:48.555002: step: 1708/530, loss: 0.053911250084638596
2023-01-23 01:37:49.656446: step: 1712/530, loss: 0.022984886541962624
2023-01-23 01:37:50.773183: step: 1716/530, loss: 0.1483118087053299
2023-01-23 01:37:51.861610: step: 1720/530, loss: 0.1426558494567871
2023-01-23 01:37:52.974124: step: 1724/530, loss: 0.044199731200933456
2023-01-23 01:37:54.072605: step: 1728/530, loss: 0.0599767230451107
2023-01-23 01:37:55.193325: step: 1732/530, loss: 0.019617414101958275
2023-01-23 01:37:56.309955: step: 1736/530, loss: 0.2137984335422516
2023-01-23 01:37:57.413360: step: 1740/530, loss: 0.012730885297060013
2023-01-23 01:37:58.527805: step: 1744/530, loss: 0.045186806470155716
2023-01-23 01:37:59.622857: step: 1748/530, loss: 0.03270091861486435
2023-01-23 01:38:00.746610: step: 1752/530, loss: 0.05823421850800514
2023-01-23 01:38:01.863588: step: 1756/530, loss: 0.0025764943566173315
2023-01-23 01:38:02.986159: step: 1760/530, loss: 0.02281980589032173
2023-01-23 01:38:04.086889: step: 1764/530, loss: 0.06588523089885712
2023-01-23 01:38:05.176511: step: 1768/530, loss: 0.0008783340454101562
2023-01-23 01:38:06.294860: step: 1772/530, loss: 0.03944587707519531
2023-01-23 01:38:07.402114: step: 1776/530, loss: 0.059264231473207474
2023-01-23 01:38:08.524620: step: 1780/530, loss: 0.0342438705265522
2023-01-23 01:38:09.602243: step: 1784/530, loss: 0.02171487919986248
2023-01-23 01:38:10.740088: step: 1788/530, loss: 0.02807140350341797
2023-01-23 01:38:11.816841: step: 1792/530, loss: 0.012122392654418945
2023-01-23 01:38:12.920948: step: 1796/530, loss: 0.03112201578915119
2023-01-23 01:38:14.009238: step: 1800/530, loss: 0.029650593176484108
2023-01-23 01:38:15.111049: step: 1804/530, loss: 0.0016728402115404606
2023-01-23 01:38:16.212273: step: 1808/530, loss: 0.03131360933184624
2023-01-23 01:38:17.294104: step: 1812/530, loss: 0.041707880795001984
2023-01-23 01:38:18.391292: step: 1816/530, loss: 0.07412929087877274
2023-01-23 01:38:19.546419: step: 1820/530, loss: 0.34434399008750916
2023-01-23 01:38:20.690656: step: 1824/530, loss: 0.12465324252843857
2023-01-23 01:38:21.822746: step: 1828/530, loss: 0.02382803149521351
2023-01-23 01:38:22.949390: step: 1832/530, loss: 6.093580722808838
2023-01-23 01:38:24.066122: step: 1836/530, loss: 0.2687739431858063
2023-01-23 01:38:25.185190: step: 1840/530, loss: 0.10307230800390244
2023-01-23 01:38:26.328151: step: 1844/530, loss: 0.004894256591796875
2023-01-23 01:38:27.417403: step: 1848/530, loss: 0.08389768749475479
2023-01-23 01:38:28.525878: step: 1852/530, loss: 0.02436981163918972
2023-01-23 01:38:29.612805: step: 1856/530, loss: 0.009558772668242455
2023-01-23 01:38:30.713677: step: 1860/530, loss: 0.027902889996767044
2023-01-23 01:38:31.822869: step: 1864/530, loss: 0.016843892633914948
2023-01-23 01:38:32.942590: step: 1868/530, loss: 0.2397083342075348
2023-01-23 01:38:34.019486: step: 1872/530, loss: 0.02057565376162529
2023-01-23 01:38:35.093451: step: 1876/530, loss: 0.05014371871948242
2023-01-23 01:38:36.183115: step: 1880/530, loss: 0.03890800476074219
2023-01-23 01:38:37.321785: step: 1884/530, loss: 0.019967176020145416
2023-01-23 01:38:38.442142: step: 1888/530, loss: 0.040175724774599075
2023-01-23 01:38:39.556026: step: 1892/530, loss: 0.06426181644201279
2023-01-23 01:38:40.690620: step: 1896/530, loss: 0.04157695919275284
2023-01-23 01:38:41.807796: step: 1900/530, loss: 0.02451639249920845
2023-01-23 01:38:42.931247: step: 1904/530, loss: 0.01828775554895401
2023-01-23 01:38:44.026076: step: 1908/530, loss: 0.05919589847326279
2023-01-23 01:38:45.125848: step: 1912/530, loss: 0.059839341789484024
2023-01-23 01:38:46.244242: step: 1916/530, loss: 0.002083253813907504
2023-01-23 01:38:47.326034: step: 1920/530, loss: 0.012130928225815296
2023-01-23 01:38:48.464421: step: 1924/530, loss: 0.0004718780401162803
2023-01-23 01:38:49.607213: step: 1928/530, loss: 0.03372631222009659
2023-01-23 01:38:50.707383: step: 1932/530, loss: 0.20556049048900604
2023-01-23 01:38:51.799545: step: 1936/530, loss: 0.029574299231171608
2023-01-23 01:38:52.897258: step: 1940/530, loss: 0.011908531188964844
2023-01-23 01:38:54.013343: step: 1944/530, loss: 0.019826317206025124
2023-01-23 01:38:55.123585: step: 1948/530, loss: 0.005842399783432484
2023-01-23 01:38:56.251134: step: 1952/530, loss: 0.03626060485839844
2023-01-23 01:38:57.360865: step: 1956/530, loss: 0.010868263430893421
2023-01-23 01:38:58.462314: step: 1960/530, loss: 0.0018940926529467106
2023-01-23 01:38:59.575143: step: 1964/530, loss: 0.0582517646253109
2023-01-23 01:39:00.696689: step: 1968/530, loss: 0.02425565756857395
2023-01-23 01:39:01.825854: step: 1972/530, loss: 0.07246483862400055
2023-01-23 01:39:02.934889: step: 1976/530, loss: 0.00021843911963514984
2023-01-23 01:39:04.063051: step: 1980/530, loss: 0.08026814460754395
2023-01-23 01:39:05.158119: step: 1984/530, loss: 0.029352569952607155
2023-01-23 01:39:06.297363: step: 1988/530, loss: 0.13591709733009338
2023-01-23 01:39:07.405088: step: 1992/530, loss: 0.15342122316360474
2023-01-23 01:39:08.497199: step: 1996/530, loss: 0.005196571350097656
2023-01-23 01:39:09.646044: step: 2000/530, loss: 0.024103974923491478
2023-01-23 01:39:10.761839: step: 2004/530, loss: 0.011603927239775658
2023-01-23 01:39:11.896499: step: 2008/530, loss: 0.05790739133954048
2023-01-23 01:39:13.007855: step: 2012/530, loss: 0.06800079345703125
2023-01-23 01:39:14.118088: step: 2016/530, loss: 0.06087642163038254
2023-01-23 01:39:15.244298: step: 2020/530, loss: 0.014367818832397461
2023-01-23 01:39:16.380492: step: 2024/530, loss: 0.050966836512088776
2023-01-23 01:39:17.472378: step: 2028/530, loss: 0.05780401453375816
2023-01-23 01:39:18.571163: step: 2032/530, loss: 0.008212518878281116
2023-01-23 01:39:19.702784: step: 2036/530, loss: 0.020195960998535156
2023-01-23 01:39:20.818391: step: 2040/530, loss: 0.02652750164270401
2023-01-23 01:39:21.915445: step: 2044/530, loss: 0.0038254738319665194
2023-01-23 01:39:23.032365: step: 2048/530, loss: 0.06252650916576385
2023-01-23 01:39:24.174006: step: 2052/530, loss: 0.1032039150595665
2023-01-23 01:39:25.279418: step: 2056/530, loss: 0.06172027438879013
2023-01-23 01:39:26.384450: step: 2060/530, loss: 0.05524921417236328
2023-01-23 01:39:27.534719: step: 2064/530, loss: 0.01191787701100111
2023-01-23 01:39:28.646113: step: 2068/530, loss: 0.15121574699878693
2023-01-23 01:39:29.757639: step: 2072/530, loss: 0.03222007676959038
2023-01-23 01:39:30.849490: step: 2076/530, loss: 0.0024065019097179174
2023-01-23 01:39:31.946688: step: 2080/530, loss: 0.026377486065030098
2023-01-23 01:39:33.063079: step: 2084/530, loss: 0.01965632662177086
2023-01-23 01:39:34.194678: step: 2088/530, loss: 0.051439620554447174
2023-01-23 01:39:35.333273: step: 2092/530, loss: 0.03644991293549538
2023-01-23 01:39:36.461631: step: 2096/530, loss: 0.06446738541126251
2023-01-23 01:39:37.541041: step: 2100/530, loss: 0.023418238386511803
2023-01-23 01:39:38.639700: step: 2104/530, loss: 0.08159048855304718
2023-01-23 01:39:39.739253: step: 2108/530, loss: 0.10870043188333511
2023-01-23 01:39:40.866425: step: 2112/530, loss: 0.14680452644824982
2023-01-23 01:39:41.970392: step: 2116/530, loss: 0.05283393710851669
2023-01-23 01:39:43.103572: step: 2120/530, loss: 0.015566349029541016
==================================================
Loss: 0.077
--------------------
Dev: {'event': {'p': 0.6449771689497716, 'r': 0.7523302263648469, 'f1': 0.6945298094652735}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Test: {'event': {'p': 0.6692644909887969, 'r': 0.8006993006993007, 'f1': 0.7291058636243036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Chinese: {'event': {'p': 0.6764705882352942, 'r': 0.8518518518518519, 'f1': 0.7540983606557378}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Korean: {'event': {'p': 0.7391304347826086, 'r': 0.5396825396825397, 'f1': 0.6238532110091742}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Russian: {'event': {'p': 0.45714285714285713, 'r': 0.4444444444444444, 'f1': 0.4507042253521127}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
New best chinese model...
New best korean model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6449771689497716, 'r': 0.7523302263648469, 'f1': 0.6945298094652735}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Chinese: {'event': {'p': 0.6692644909887969, 'r': 0.8006993006993007, 'f1': 0.7291058636243036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Chinese: {'event': {'p': 0.6764705882352942, 'r': 0.8518518518518519, 'f1': 0.7540983606557378}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6449771689497716, 'r': 0.7523302263648469, 'f1': 0.6945298094652735}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Korean: {'event': {'p': 0.6692644909887969, 'r': 0.8006993006993007, 'f1': 0.7291058636243036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Korean: {'event': {'p': 0.7391304347826086, 'r': 0.5396825396825397, 'f1': 0.6238532110091742}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5971370143149284, 'r': 0.7776298268974701, 'f1': 0.6755349913244649}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Russian: {'event': {'p': 0.6401673640167364, 'r': 0.8024475524475524, 'f1': 0.7121799844840963}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Russian: {'event': {'p': 0.5897435897435898, 'r': 0.6388888888888888, 'f1': 0.6133333333333332}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
******************************
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 01:40:33.193788: step: 4/530, loss: 0.010338783264160156
2023-01-23 01:40:34.276266: step: 8/530, loss: 0.03937244415283203
2023-01-23 01:40:35.370639: step: 12/530, loss: 0.020406628027558327
2023-01-23 01:40:36.498370: step: 16/530, loss: 0.042916011065244675
2023-01-23 01:40:37.639468: step: 20/530, loss: 0.06998996436595917
2023-01-23 01:40:38.771621: step: 24/530, loss: 0.0072157857939600945
2023-01-23 01:40:39.861359: step: 28/530, loss: 0.025925161316990852
2023-01-23 01:40:40.982052: step: 32/530, loss: 0.00586700439453125
2023-01-23 01:40:42.093874: step: 36/530, loss: 0.05807862430810928
2023-01-23 01:40:43.249038: step: 40/530, loss: 0.016925431787967682
2023-01-23 01:40:44.341170: step: 44/530, loss: 0.013360977172851562
2023-01-23 01:40:45.437654: step: 48/530, loss: 0.03311128541827202
2023-01-23 01:40:46.528330: step: 52/530, loss: 0.03128395229578018
2023-01-23 01:40:47.648627: step: 56/530, loss: 0.0023470879532396793
2023-01-23 01:40:48.762639: step: 60/530, loss: 0.032572176307439804
2023-01-23 01:40:49.848002: step: 64/530, loss: 0.024111270904541016
2023-01-23 01:40:50.985526: step: 68/530, loss: 0.00566492136567831
2023-01-23 01:40:52.075553: step: 72/530, loss: 0.0015707015991210938
2023-01-23 01:40:53.161372: step: 76/530, loss: 0.0338476188480854
2023-01-23 01:40:54.278067: step: 80/530, loss: 0.21581107378005981
2023-01-23 01:40:55.433791: step: 84/530, loss: 0.09263086318969727
2023-01-23 01:40:56.540379: step: 88/530, loss: 0.17962618172168732
2023-01-23 01:40:57.680002: step: 92/530, loss: 0.002164554549381137
2023-01-23 01:40:58.811979: step: 96/530, loss: 0.013078879565000534
2023-01-23 01:40:59.924790: step: 100/530, loss: 0.0051864152774214745
2023-01-23 01:41:01.042867: step: 104/530, loss: 0.012320756912231445
2023-01-23 01:41:02.161312: step: 108/530, loss: 0.06429815292358398
2023-01-23 01:41:03.275353: step: 112/530, loss: 0.06812362372875214
2023-01-23 01:41:04.377495: step: 116/530, loss: 0.009716319851577282
2023-01-23 01:41:05.481393: step: 120/530, loss: 0.024005508050322533
2023-01-23 01:41:06.638694: step: 124/530, loss: 0.1008627861738205
2023-01-23 01:41:07.749054: step: 128/530, loss: 0.007063637487590313
2023-01-23 01:41:08.834397: step: 132/530, loss: 0.03397336229681969
2023-01-23 01:41:09.927260: step: 136/530, loss: 0.047632597386837006
2023-01-23 01:41:11.021055: step: 140/530, loss: 0.0009088516235351562
2023-01-23 01:41:12.113388: step: 144/530, loss: 0.0023310661781579256
2023-01-23 01:41:13.216014: step: 148/530, loss: 0.02565460465848446
2023-01-23 01:41:14.292441: step: 152/530, loss: 0.022119522094726562
2023-01-23 01:41:15.374394: step: 156/530, loss: 0.053354837000370026
2023-01-23 01:41:16.476501: step: 160/530, loss: 0.030416490510106087
2023-01-23 01:41:17.597982: step: 164/530, loss: 0.16296347975730896
2023-01-23 01:41:18.695398: step: 168/530, loss: 0.23141264915466309
2023-01-23 01:41:19.771567: step: 172/530, loss: 0.028998469933867455
2023-01-23 01:41:20.871988: step: 176/530, loss: 0.02377014234662056
2023-01-23 01:41:21.964687: step: 180/530, loss: 0.007561206817626953
2023-01-23 01:41:23.112454: step: 184/530, loss: 0.08007955551147461
2023-01-23 01:41:24.231174: step: 188/530, loss: 0.0014085769653320312
2023-01-23 01:41:25.326423: step: 192/530, loss: 0.009831237606704235
2023-01-23 01:41:26.428494: step: 196/530, loss: 0.04229545593261719
2023-01-23 01:41:27.532334: step: 200/530, loss: 0.018998337909579277
2023-01-23 01:41:28.645756: step: 204/530, loss: 0.032590102404356
2023-01-23 01:41:29.732673: step: 208/530, loss: 0.02253122441470623
2023-01-23 01:41:30.843800: step: 212/530, loss: 0.051273345947265625
2023-01-23 01:41:31.937293: step: 216/530, loss: 0.002879810519516468
2023-01-23 01:41:33.022618: step: 220/530, loss: 0.0307940486818552
2023-01-23 01:41:34.113401: step: 224/530, loss: 0.02374458499252796
2023-01-23 01:41:35.205814: step: 228/530, loss: 0.03650369495153427
2023-01-23 01:41:36.329459: step: 232/530, loss: 0.04383029788732529
2023-01-23 01:41:37.448667: step: 236/530, loss: 0.07303428649902344
2023-01-23 01:41:38.581981: step: 240/530, loss: 0.007997703738510609
2023-01-23 01:41:39.715964: step: 244/530, loss: 0.034932516515254974
2023-01-23 01:41:40.820787: step: 248/530, loss: 0.028576470911502838
2023-01-23 01:41:41.922408: step: 252/530, loss: 0.008052635006606579
2023-01-23 01:41:43.036003: step: 256/530, loss: 0.025313567370176315
2023-01-23 01:41:44.179107: step: 260/530, loss: 0.1439172625541687
2023-01-23 01:41:45.289647: step: 264/530, loss: 0.048309326171875
2023-01-23 01:41:46.406702: step: 268/530, loss: 1.3479048013687134
2023-01-23 01:41:47.532563: step: 272/530, loss: 0.0496278777718544
2023-01-23 01:41:48.631905: step: 276/530, loss: 0.07445869594812393
2023-01-23 01:41:49.750432: step: 280/530, loss: 0.026566125452518463
2023-01-23 01:41:50.860429: step: 284/530, loss: 0.057004641741514206
2023-01-23 01:41:51.969637: step: 288/530, loss: 0.017602598294615746
2023-01-23 01:41:53.080444: step: 292/530, loss: 0.04711494594812393
2023-01-23 01:41:54.186627: step: 296/530, loss: 0.1427549421787262
2023-01-23 01:41:55.307290: step: 300/530, loss: 0.05304918438196182
2023-01-23 01:41:56.449140: step: 304/530, loss: 0.09182686358690262
2023-01-23 01:41:57.569697: step: 308/530, loss: 0.001195764634758234
2023-01-23 01:41:58.693980: step: 312/530, loss: 0.04993772506713867
2023-01-23 01:41:59.765618: step: 316/530, loss: 0.0007867336389608681
2023-01-23 01:42:00.903710: step: 320/530, loss: 0.023862741887569427
2023-01-23 01:42:01.988720: step: 324/530, loss: 0.017171572893857956
2023-01-23 01:42:03.082060: step: 328/530, loss: 0.05512294918298721
2023-01-23 01:42:04.176591: step: 332/530, loss: 0.047381214797496796
2023-01-23 01:42:05.276699: step: 336/530, loss: 0.007836151868104935
2023-01-23 01:42:06.400371: step: 340/530, loss: 0.0010083199013024569
2023-01-23 01:42:07.511857: step: 344/530, loss: 0.052090834826231
2023-01-23 01:42:08.595645: step: 348/530, loss: 0.00030536652775481343
2023-01-23 01:42:09.710275: step: 352/530, loss: 0.0531742125749588
2023-01-23 01:42:10.831157: step: 356/530, loss: 0.07771263271570206
2023-01-23 01:42:11.950625: step: 360/530, loss: 0.02699895203113556
2023-01-23 01:42:13.044198: step: 364/530, loss: 0.08803115040063858
2023-01-23 01:42:14.151020: step: 368/530, loss: 0.03445129096508026
2023-01-23 01:42:15.259960: step: 372/530, loss: 0.3445380926132202
2023-01-23 01:42:16.363419: step: 376/530, loss: 0.005825424566864967
2023-01-23 01:42:17.432240: step: 380/530, loss: 0.050376322120428085
2023-01-23 01:42:18.560205: step: 384/530, loss: 0.016491984948515892
2023-01-23 01:42:19.681734: step: 388/530, loss: 0.009643363766372204
2023-01-23 01:42:20.794233: step: 392/530, loss: 0.006291198544204235
2023-01-23 01:42:21.917298: step: 396/530, loss: 0.053534507751464844
2023-01-23 01:42:23.064813: step: 400/530, loss: 0.06223764643073082
2023-01-23 01:42:24.196177: step: 404/530, loss: 0.14410322904586792
2023-01-23 01:42:25.343220: step: 408/530, loss: 0.015216636471450329
2023-01-23 01:42:26.438383: step: 412/530, loss: 0.0102570541203022
2023-01-23 01:42:27.538355: step: 416/530, loss: 0.017113065347075462
2023-01-23 01:42:28.662921: step: 420/530, loss: 0.04796038195490837
2023-01-23 01:42:29.733486: step: 424/530, loss: 0.0007107734563760459
2023-01-23 01:42:30.848661: step: 428/530, loss: 0.021693039685487747
2023-01-23 01:42:31.958493: step: 432/530, loss: 0.0009634018060751259
2023-01-23 01:42:33.050792: step: 436/530, loss: 0.011694908142089844
2023-01-23 01:42:34.151639: step: 440/530, loss: 0.012576961889863014
2023-01-23 01:42:35.273730: step: 444/530, loss: 0.0637701004743576
2023-01-23 01:42:36.386729: step: 448/530, loss: 0.007513142190873623
2023-01-23 01:42:37.506870: step: 452/530, loss: 0.030734064057469368
2023-01-23 01:42:38.624256: step: 456/530, loss: 0.06175249069929123
2023-01-23 01:42:39.724387: step: 460/530, loss: 0.0865272581577301
2023-01-23 01:42:40.842451: step: 464/530, loss: 0.02545337751507759
2023-01-23 01:42:41.938855: step: 468/530, loss: 0.006183624733239412
2023-01-23 01:42:43.045465: step: 472/530, loss: 0.032352447509765625
2023-01-23 01:42:44.141754: step: 476/530, loss: 0.035086870193481445
2023-01-23 01:42:45.277519: step: 480/530, loss: 0.00989389419555664
2023-01-23 01:42:46.371307: step: 484/530, loss: 0.028569508343935013
2023-01-23 01:42:47.506425: step: 488/530, loss: 0.015160275623202324
2023-01-23 01:42:48.617859: step: 492/530, loss: 0.04662156105041504
2023-01-23 01:42:49.735547: step: 496/530, loss: 0.3977595865726471
2023-01-23 01:42:50.820035: step: 500/530, loss: 0.016504287719726562
2023-01-23 01:42:51.933845: step: 504/530, loss: 0.005976009648293257
2023-01-23 01:42:53.041449: step: 508/530, loss: 0.045073606073856354
2023-01-23 01:42:54.147239: step: 512/530, loss: 0.0394803062081337
2023-01-23 01:42:55.248032: step: 516/530, loss: 0.04611530154943466
2023-01-23 01:42:56.340244: step: 520/530, loss: 0.023482704535126686
2023-01-23 01:42:57.429113: step: 524/530, loss: 0.02788562886416912
2023-01-23 01:42:58.532535: step: 528/530, loss: 0.026611899957060814
2023-01-23 01:42:59.633014: step: 532/530, loss: 0.008923912420868874
2023-01-23 01:43:00.733566: step: 536/530, loss: 0.010407638736069202
2023-01-23 01:43:01.835804: step: 540/530, loss: 0.023578930646181107
2023-01-23 01:43:02.943744: step: 544/530, loss: 0.026604462414979935
2023-01-23 01:43:04.048540: step: 548/530, loss: 0.10553817451000214
2023-01-23 01:43:05.148354: step: 552/530, loss: 0.021996211260557175
2023-01-23 01:43:06.273475: step: 556/530, loss: 0.06420020759105682
2023-01-23 01:43:07.384171: step: 560/530, loss: 0.09322868287563324
2023-01-23 01:43:08.482031: step: 564/530, loss: 0.34221163392066956
2023-01-23 01:43:09.579361: step: 568/530, loss: 0.08991508185863495
2023-01-23 01:43:10.689539: step: 572/530, loss: 0.0015178680187091231
2023-01-23 01:43:11.835199: step: 576/530, loss: 0.014760208316147327
2023-01-23 01:43:12.952171: step: 580/530, loss: 0.10044021904468536
2023-01-23 01:43:14.049947: step: 584/530, loss: 0.06441430747509003
2023-01-23 01:43:15.204790: step: 588/530, loss: 0.006491375155746937
2023-01-23 01:43:16.318255: step: 592/530, loss: 0.05071773752570152
2023-01-23 01:43:17.441808: step: 596/530, loss: 0.14585629105567932
2023-01-23 01:43:18.537147: step: 600/530, loss: 0.043434906750917435
2023-01-23 01:43:19.638565: step: 604/530, loss: 0.007934189401566982
2023-01-23 01:43:20.743160: step: 608/530, loss: 0.05602607876062393
2023-01-23 01:43:21.845875: step: 612/530, loss: 0.003832912538200617
2023-01-23 01:43:22.938948: step: 616/530, loss: 0.024837495759129524
2023-01-23 01:43:24.046667: step: 620/530, loss: 0.0011158466804772615
2023-01-23 01:43:25.175093: step: 624/530, loss: 0.02927389182150364
2023-01-23 01:43:26.286421: step: 628/530, loss: 0.17319431900978088
2023-01-23 01:43:27.407401: step: 632/530, loss: 0.008128928951919079
2023-01-23 01:43:28.511312: step: 636/530, loss: 0.03719482570886612
2023-01-23 01:43:29.595239: step: 640/530, loss: 0.2760624885559082
2023-01-23 01:43:30.704949: step: 644/530, loss: 0.013302231207489967
2023-01-23 01:43:31.839908: step: 648/530, loss: 0.3628973066806793
2023-01-23 01:43:32.942277: step: 652/530, loss: 0.08431144058704376
2023-01-23 01:43:34.096525: step: 656/530, loss: 0.08350582420825958
2023-01-23 01:43:35.187048: step: 660/530, loss: 0.02348480373620987
2023-01-23 01:43:36.264099: step: 664/530, loss: 0.04370307922363281
2023-01-23 01:43:37.367527: step: 668/530, loss: 0.09541530162096024
2023-01-23 01:43:38.477449: step: 672/530, loss: 0.035933684557676315
2023-01-23 01:43:39.593114: step: 676/530, loss: 0.07130423933267593
2023-01-23 01:43:40.706623: step: 680/530, loss: 0.006678295321762562
2023-01-23 01:43:41.806208: step: 684/530, loss: 0.011517524719238281
2023-01-23 01:43:42.906486: step: 688/530, loss: 0.0009331703186035156
2023-01-23 01:43:44.062410: step: 692/530, loss: 0.03302412107586861
2023-01-23 01:43:45.171538: step: 696/530, loss: 0.017586994916200638
2023-01-23 01:43:46.269470: step: 700/530, loss: 0.0015340804820880294
2023-01-23 01:43:47.368318: step: 704/530, loss: 0.2513389587402344
2023-01-23 01:43:48.479123: step: 708/530, loss: 0.03002472035586834
2023-01-23 01:43:49.584832: step: 712/530, loss: 0.0988689437508583
2023-01-23 01:43:50.672249: step: 716/530, loss: 0.003219032194465399
2023-01-23 01:43:51.771481: step: 720/530, loss: 0.10665331035852432
2023-01-23 01:43:52.863462: step: 724/530, loss: 0.046952441334724426
2023-01-23 01:43:53.971068: step: 728/530, loss: 0.015474224463105202
2023-01-23 01:43:55.062393: step: 732/530, loss: 0.011149119585752487
2023-01-23 01:43:56.167378: step: 736/530, loss: 0.0017066956497728825
2023-01-23 01:43:57.273648: step: 740/530, loss: 0.09497762471437454
2023-01-23 01:43:58.432409: step: 744/530, loss: 0.027863884344697
2023-01-23 01:43:59.546451: step: 748/530, loss: 0.03333025053143501
2023-01-23 01:44:00.643242: step: 752/530, loss: 0.06128654628992081
2023-01-23 01:44:01.721162: step: 756/530, loss: 0.047747902572155
2023-01-23 01:44:02.865277: step: 760/530, loss: 0.022834395989775658
2023-01-23 01:44:03.971784: step: 764/530, loss: 0.1315334290266037
2023-01-23 01:44:05.068515: step: 768/530, loss: 0.07128391414880753
2023-01-23 01:44:06.179052: step: 772/530, loss: 0.01073226984590292
2023-01-23 01:44:07.286680: step: 776/530, loss: 0.0070396424271166325
2023-01-23 01:44:08.406395: step: 780/530, loss: 0.020084762945771217
2023-01-23 01:44:09.510804: step: 784/530, loss: 0.08755950629711151
2023-01-23 01:44:10.630928: step: 788/530, loss: 0.048429109156131744
2023-01-23 01:44:11.727183: step: 792/530, loss: 0.07939396053552628
2023-01-23 01:44:12.836538: step: 796/530, loss: 0.024200439453125
2023-01-23 01:44:13.954586: step: 800/530, loss: 0.060389235615730286
2023-01-23 01:44:15.060343: step: 804/530, loss: 0.012849807739257812
2023-01-23 01:44:16.182622: step: 808/530, loss: 0.009954930283129215
2023-01-23 01:44:17.287954: step: 812/530, loss: 0.01673135906457901
2023-01-23 01:44:18.400557: step: 816/530, loss: 0.07015933841466904
2023-01-23 01:44:19.521376: step: 820/530, loss: 0.0017228127690032125
2023-01-23 01:44:20.667365: step: 824/530, loss: 0.008235502988100052
2023-01-23 01:44:21.746474: step: 828/530, loss: 0.03177709877490997
2023-01-23 01:44:22.849326: step: 832/530, loss: 0.023003483191132545
2023-01-23 01:44:23.969245: step: 836/530, loss: 0.050423528999090195
2023-01-23 01:44:25.080696: step: 840/530, loss: 0.05669365078210831
2023-01-23 01:44:26.170598: step: 844/530, loss: 0.031569670885801315
2023-01-23 01:44:27.258912: step: 848/530, loss: 0.02751808427274227
2023-01-23 01:44:28.368471: step: 852/530, loss: 0.0030496600084006786
2023-01-23 01:44:29.476801: step: 856/530, loss: 0.03961982578039169
2023-01-23 01:44:30.570636: step: 860/530, loss: 0.08732762932777405
2023-01-23 01:44:31.665712: step: 864/530, loss: 0.036478426307439804
2023-01-23 01:44:32.732464: step: 868/530, loss: 0.10954676568508148
2023-01-23 01:44:33.835305: step: 872/530, loss: 0.028359128162264824
2023-01-23 01:44:34.981254: step: 876/530, loss: 0.032311439514160156
2023-01-23 01:44:36.084349: step: 880/530, loss: 0.018230844289064407
2023-01-23 01:44:37.168469: step: 884/530, loss: 0.01276321429759264
2023-01-23 01:44:38.280040: step: 888/530, loss: 0.010893153958022594
2023-01-23 01:44:39.394472: step: 892/530, loss: 0.02268095314502716
2023-01-23 01:44:40.508976: step: 896/530, loss: 0.0025853158440440893
2023-01-23 01:44:41.600105: step: 900/530, loss: 0.01673908159136772
2023-01-23 01:44:42.685681: step: 904/530, loss: 0.073175810277462
2023-01-23 01:44:43.808869: step: 908/530, loss: 0.0021816908847540617
2023-01-23 01:44:44.895915: step: 912/530, loss: 0.006593227386474609
2023-01-23 01:44:46.000863: step: 916/530, loss: 0.02126750908792019
2023-01-23 01:44:47.102510: step: 920/530, loss: 0.013964463025331497
2023-01-23 01:44:48.222851: step: 924/530, loss: 0.03364090994000435
2023-01-23 01:44:49.347973: step: 928/530, loss: 0.009216021746397018
2023-01-23 01:44:50.481673: step: 932/530, loss: 0.02861194685101509
2023-01-23 01:44:51.589850: step: 936/530, loss: 0.03366098552942276
2023-01-23 01:44:52.710092: step: 940/530, loss: 0.055822089314460754
2023-01-23 01:44:53.817189: step: 944/530, loss: 0.006997585296630859
2023-01-23 01:44:54.918795: step: 948/530, loss: 0.028049517422914505
2023-01-23 01:44:56.031962: step: 952/530, loss: 0.011530017480254173
2023-01-23 01:44:57.112365: step: 956/530, loss: 0.036008644849061966
2023-01-23 01:44:58.215426: step: 960/530, loss: 0.0007014751899987459
2023-01-23 01:44:59.333287: step: 964/530, loss: 0.040674399584531784
2023-01-23 01:45:00.455072: step: 968/530, loss: 0.0021470070350915194
2023-01-23 01:45:01.573103: step: 972/530, loss: 0.03356514126062393
2023-01-23 01:45:02.720911: step: 976/530, loss: 0.012336350046098232
2023-01-23 01:45:03.820615: step: 980/530, loss: 0.007206535432487726
2023-01-23 01:45:04.926260: step: 984/530, loss: 0.009570646099746227
2023-01-23 01:45:06.015095: step: 988/530, loss: 0.05348358303308487
2023-01-23 01:45:07.107145: step: 992/530, loss: 0.019399693235754967
2023-01-23 01:45:08.203321: step: 996/530, loss: 0.1037638708949089
2023-01-23 01:45:09.313177: step: 1000/530, loss: 0.013699246570467949
2023-01-23 01:45:10.454568: step: 1004/530, loss: 0.06087846681475639
2023-01-23 01:45:11.550267: step: 1008/530, loss: 0.007978105917572975
2023-01-23 01:45:12.634714: step: 1012/530, loss: 0.03927498310804367
2023-01-23 01:45:13.735499: step: 1016/530, loss: 0.017318058758974075
2023-01-23 01:45:14.830142: step: 1020/530, loss: 0.006558513268828392
2023-01-23 01:45:15.916201: step: 1024/530, loss: 0.030318165197968483
2023-01-23 01:45:17.007626: step: 1028/530, loss: 0.06049642711877823
2023-01-23 01:45:18.121959: step: 1032/530, loss: 0.0031309130135923624
2023-01-23 01:45:19.221916: step: 1036/530, loss: 0.0031955719459801912
2023-01-23 01:45:20.335989: step: 1040/530, loss: 0.18545348942279816
2023-01-23 01:45:21.435457: step: 1044/530, loss: 0.01234884187579155
2023-01-23 01:45:22.528763: step: 1048/530, loss: 0.03277568891644478
2023-01-23 01:45:23.647514: step: 1052/530, loss: 0.0341181755065918
2023-01-23 01:45:24.756948: step: 1056/530, loss: 0.03468380123376846
2023-01-23 01:45:25.874339: step: 1060/530, loss: 0.08007068932056427
2023-01-23 01:45:26.946573: step: 1064/530, loss: 0.0023735046852380037
2023-01-23 01:45:28.028618: step: 1068/530, loss: 0.011370993219316006
2023-01-23 01:45:29.131608: step: 1072/530, loss: 0.0012920380104333162
2023-01-23 01:45:30.233739: step: 1076/530, loss: 0.0025459290482103825
2023-01-23 01:45:31.328854: step: 1080/530, loss: 0.029685402289032936
2023-01-23 01:45:32.450878: step: 1084/530, loss: 0.09148693084716797
2023-01-23 01:45:33.621838: step: 1088/530, loss: 0.01048264466226101
2023-01-23 01:45:34.753151: step: 1092/530, loss: 0.013360404409468174
2023-01-23 01:45:35.848089: step: 1096/530, loss: 0.0662989392876625
2023-01-23 01:45:36.977628: step: 1100/530, loss: 0.01094288844615221
2023-01-23 01:45:38.046042: step: 1104/530, loss: 0.006637859158217907
2023-01-23 01:45:39.158425: step: 1108/530, loss: 0.08928364515304565
2023-01-23 01:45:40.261552: step: 1112/530, loss: 0.005601406097412109
2023-01-23 01:45:41.348779: step: 1116/530, loss: 0.003394508268684149
2023-01-23 01:45:42.491643: step: 1120/530, loss: 0.062195394188165665
2023-01-23 01:45:43.601392: step: 1124/530, loss: 0.006798744201660156
2023-01-23 01:45:44.732160: step: 1128/530, loss: 0.06677937507629395
2023-01-23 01:45:45.841419: step: 1132/530, loss: 0.017731856554746628
2023-01-23 01:45:46.955533: step: 1136/530, loss: 0.017788507044315338
2023-01-23 01:45:48.042456: step: 1140/530, loss: 0.1297626495361328
2023-01-23 01:45:49.135631: step: 1144/530, loss: 0.05836191028356552
2023-01-23 01:45:50.252656: step: 1148/530, loss: 0.049906209111213684
2023-01-23 01:45:51.354950: step: 1152/530, loss: 0.05413494259119034
2023-01-23 01:45:52.497645: step: 1156/530, loss: 0.06308393180370331
2023-01-23 01:45:53.599383: step: 1160/530, loss: 0.3992176949977875
2023-01-23 01:45:54.703355: step: 1164/530, loss: 0.05857410654425621
2023-01-23 01:45:55.807895: step: 1168/530, loss: 0.006541872397065163
2023-01-23 01:45:56.952296: step: 1172/530, loss: 0.031515009701251984
2023-01-23 01:45:58.070282: step: 1176/530, loss: 0.026569174602627754
2023-01-23 01:45:59.185764: step: 1180/530, loss: 0.03496980667114258
2023-01-23 01:46:00.293681: step: 1184/530, loss: 0.008834362030029297
2023-01-23 01:46:01.370436: step: 1188/530, loss: 0.0043354216031730175
2023-01-23 01:46:02.484853: step: 1192/530, loss: 0.0486297607421875
2023-01-23 01:46:03.558756: step: 1196/530, loss: 0.006222677417099476
2023-01-23 01:46:04.678763: step: 1200/530, loss: 0.036500170826911926
2023-01-23 01:46:05.794194: step: 1204/530, loss: 0.012458229437470436
2023-01-23 01:46:06.906286: step: 1208/530, loss: 0.05542612075805664
2023-01-23 01:46:08.006738: step: 1212/530, loss: 0.022995758801698685
2023-01-23 01:46:09.096601: step: 1216/530, loss: 0.0016830742824822664
2023-01-23 01:46:10.207878: step: 1220/530, loss: 0.25324830412864685
2023-01-23 01:46:11.325857: step: 1224/530, loss: 0.02370157465338707
2023-01-23 01:46:12.427617: step: 1228/530, loss: 0.0323239341378212
2023-01-23 01:46:13.526922: step: 1232/530, loss: 0.08043403923511505
2023-01-23 01:46:14.653293: step: 1236/530, loss: 0.009507370181381702
2023-01-23 01:46:15.782081: step: 1240/530, loss: 0.0159454345703125
2023-01-23 01:46:16.908293: step: 1244/530, loss: 0.0008348464616574347
2023-01-23 01:46:18.008257: step: 1248/530, loss: 0.02211456373333931
2023-01-23 01:46:19.089382: step: 1252/530, loss: 0.12255540490150452
2023-01-23 01:46:20.187702: step: 1256/530, loss: 0.0025011301040649414
2023-01-23 01:46:21.300395: step: 1260/530, loss: 0.10497932881116867
2023-01-23 01:46:22.394558: step: 1264/530, loss: 0.1726401150226593
2023-01-23 01:46:23.497569: step: 1268/530, loss: 0.029425431042909622
2023-01-23 01:46:24.580115: step: 1272/530, loss: 0.01004643552005291
2023-01-23 01:46:25.693392: step: 1276/530, loss: 0.05260968208312988
2023-01-23 01:46:26.799903: step: 1280/530, loss: 0.2399439811706543
2023-01-23 01:46:27.910296: step: 1284/530, loss: 6.712939262390137
2023-01-23 01:46:29.017187: step: 1288/530, loss: 0.01891613006591797
2023-01-23 01:46:30.125940: step: 1292/530, loss: 0.04805717617273331
2023-01-23 01:46:31.245896: step: 1296/530, loss: 0.02878108061850071
2023-01-23 01:46:32.320557: step: 1300/530, loss: 0.03209738805890083
2023-01-23 01:46:33.429338: step: 1304/530, loss: 0.08726797252893448
2023-01-23 01:46:34.524116: step: 1308/530, loss: 0.0014278412563726306
2023-01-23 01:46:35.617200: step: 1312/530, loss: 0.004249954596161842
2023-01-23 01:46:36.759501: step: 1316/530, loss: 0.02029249630868435
2023-01-23 01:46:37.897187: step: 1320/530, loss: 0.02229156531393528
2023-01-23 01:46:38.996536: step: 1324/530, loss: 0.02374943718314171
2023-01-23 01:46:40.122108: step: 1328/530, loss: 0.03050074726343155
2023-01-23 01:46:41.240951: step: 1332/530, loss: 0.042876724153757095
2023-01-23 01:46:42.382936: step: 1336/530, loss: 0.016658782958984375
2023-01-23 01:46:43.479712: step: 1340/530, loss: 0.02742738649249077
2023-01-23 01:46:44.586924: step: 1344/530, loss: 0.02523946948349476
2023-01-23 01:46:45.697471: step: 1348/530, loss: 0.00893106497824192
2023-01-23 01:46:46.805738: step: 1352/530, loss: 0.03062267228960991
2023-01-23 01:46:47.904605: step: 1356/530, loss: 0.052423857152462006
2023-01-23 01:46:49.005499: step: 1360/530, loss: 0.009342575445771217
2023-01-23 01:46:50.103887: step: 1364/530, loss: 0.00614166259765625
2023-01-23 01:46:51.213680: step: 1368/530, loss: 0.04463396221399307
2023-01-23 01:46:52.324182: step: 1372/530, loss: 0.01674785651266575
2023-01-23 01:46:53.457970: step: 1376/530, loss: 0.0039504049345850945
2023-01-23 01:46:54.564291: step: 1380/530, loss: 1.4564108848571777
2023-01-23 01:46:55.649818: step: 1384/530, loss: 0.047625090926885605
2023-01-23 01:46:56.779581: step: 1388/530, loss: 0.027584457769989967
2023-01-23 01:46:57.869493: step: 1392/530, loss: 0.3598521053791046
2023-01-23 01:46:58.981502: step: 1396/530, loss: 0.004367828369140625
2023-01-23 01:47:00.085020: step: 1400/530, loss: 0.011169862933456898
2023-01-23 01:47:01.196345: step: 1404/530, loss: 0.14048127830028534
2023-01-23 01:47:02.297594: step: 1408/530, loss: 0.03316135331988335
2023-01-23 01:47:03.428186: step: 1412/530, loss: 0.05842571333050728
2023-01-23 01:47:04.578084: step: 1416/530, loss: 0.12167854607105255
2023-01-23 01:47:05.701200: step: 1420/530, loss: 0.0013815403217449784
2023-01-23 01:47:06.813515: step: 1424/530, loss: 0.07725677639245987
2023-01-23 01:47:07.965674: step: 1428/530, loss: 0.03309068828821182
2023-01-23 01:47:09.076642: step: 1432/530, loss: 0.0003942489856854081
2023-01-23 01:47:10.192044: step: 1436/530, loss: 0.06089820712804794
2023-01-23 01:47:11.293351: step: 1440/530, loss: 0.0882258415222168
2023-01-23 01:47:12.384141: step: 1444/530, loss: 0.0553835853934288
2023-01-23 01:47:13.504716: step: 1448/530, loss: 0.07328605651855469
2023-01-23 01:47:14.607731: step: 1452/530, loss: 0.08356419205665588
2023-01-23 01:47:15.688571: step: 1456/530, loss: 0.05502531677484512
2023-01-23 01:47:16.772652: step: 1460/530, loss: 0.00025014879065565765
2023-01-23 01:47:17.899310: step: 1464/530, loss: 0.0031418802682310343
2023-01-23 01:47:18.990635: step: 1468/530, loss: 0.004596996121108532
2023-01-23 01:47:20.102229: step: 1472/530, loss: 0.016309166327118874
2023-01-23 01:47:21.219396: step: 1476/530, loss: 0.05700664594769478
2023-01-23 01:47:22.308916: step: 1480/530, loss: 0.04704780504107475
2023-01-23 01:47:23.425845: step: 1484/530, loss: 0.1345779448747635
2023-01-23 01:47:24.531672: step: 1488/530, loss: 0.04135751724243164
2023-01-23 01:47:25.637066: step: 1492/530, loss: 0.010322571732103825
2023-01-23 01:47:26.786824: step: 1496/530, loss: 0.036879923194646835
2023-01-23 01:47:27.909406: step: 1500/530, loss: 0.0373961441218853
2023-01-23 01:47:29.004411: step: 1504/530, loss: 0.004534626379609108
2023-01-23 01:47:30.127439: step: 1508/530, loss: 0.04933672025799751
2023-01-23 01:47:31.214944: step: 1512/530, loss: 0.01965947076678276
2023-01-23 01:47:32.324088: step: 1516/530, loss: 0.0012077331775799394
2023-01-23 01:47:33.442397: step: 1520/530, loss: 0.032839585095644
2023-01-23 01:47:34.551203: step: 1524/530, loss: 0.029497431591153145
2023-01-23 01:47:35.650233: step: 1528/530, loss: 0.005555152893066406
2023-01-23 01:47:36.765726: step: 1532/530, loss: 0.06750015914440155
2023-01-23 01:47:37.862411: step: 1536/530, loss: 0.005693912506103516
2023-01-23 01:47:38.952595: step: 1540/530, loss: 0.016314124688506126
2023-01-23 01:47:40.082963: step: 1544/530, loss: 0.07892932742834091
2023-01-23 01:47:41.211994: step: 1548/530, loss: 0.07702398300170898
2023-01-23 01:47:42.362788: step: 1552/530, loss: 0.09778318554162979
2023-01-23 01:47:43.471194: step: 1556/530, loss: 0.00705642718821764
2023-01-23 01:47:44.602940: step: 1560/530, loss: 0.09829993546009064
2023-01-23 01:47:45.708318: step: 1564/530, loss: 0.03918581083416939
2023-01-23 01:47:46.817425: step: 1568/530, loss: 0.02735462412238121
2023-01-23 01:47:47.899707: step: 1572/530, loss: 0.01922469213604927
2023-01-23 01:47:48.988221: step: 1576/530, loss: 0.03327655792236328
2023-01-23 01:47:50.145169: step: 1580/530, loss: 0.07415008544921875
2023-01-23 01:47:51.245346: step: 1584/530, loss: 0.10505485534667969
2023-01-23 01:47:52.318163: step: 1588/530, loss: 0.0026955604553222656
2023-01-23 01:47:53.430812: step: 1592/530, loss: 0.016434907913208008
2023-01-23 01:47:54.529460: step: 1596/530, loss: 0.027814485132694244
2023-01-23 01:47:55.642136: step: 1600/530, loss: 0.03342628479003906
2023-01-23 01:47:56.787774: step: 1604/530, loss: 0.03882265090942383
2023-01-23 01:47:57.907547: step: 1608/530, loss: 0.025252485647797585
2023-01-23 01:47:58.985728: step: 1612/530, loss: 0.014138794504106045
2023-01-23 01:48:00.100922: step: 1616/530, loss: 0.018446732312440872
2023-01-23 01:48:01.227558: step: 1620/530, loss: 0.3163818418979645
2023-01-23 01:48:02.332916: step: 1624/530, loss: 0.009291458874940872
2023-01-23 01:48:03.432701: step: 1628/530, loss: 0.11868336796760559
2023-01-23 01:48:04.589162: step: 1632/530, loss: 0.007417869754135609
2023-01-23 01:48:05.688942: step: 1636/530, loss: 0.025185395032167435
2023-01-23 01:48:06.777957: step: 1640/530, loss: 0.0011060715187340975
2023-01-23 01:48:07.903815: step: 1644/530, loss: 0.014728737063705921
2023-01-23 01:48:08.987623: step: 1648/530, loss: 0.0027950764633715153
2023-01-23 01:48:10.095294: step: 1652/530, loss: 0.04572421312332153
2023-01-23 01:48:11.201375: step: 1656/530, loss: 0.020482921972870827
2023-01-23 01:48:12.322583: step: 1660/530, loss: 0.02772236056625843
2023-01-23 01:48:13.411254: step: 1664/530, loss: 0.00012240410433150828
2023-01-23 01:48:14.525397: step: 1668/530, loss: 0.02552185207605362
2023-01-23 01:48:15.631628: step: 1672/530, loss: 0.05476951599121094
2023-01-23 01:48:16.732992: step: 1676/530, loss: 0.002781009767204523
2023-01-23 01:48:17.851541: step: 1680/530, loss: 0.004648399539291859
2023-01-23 01:48:18.950222: step: 1684/530, loss: 0.03226395696401596
2023-01-23 01:48:20.073301: step: 1688/530, loss: 0.04018755257129669
2023-01-23 01:48:21.206009: step: 1692/530, loss: 0.01406173687428236
2023-01-23 01:48:22.326265: step: 1696/530, loss: 0.18474669754505157
2023-01-23 01:48:23.443014: step: 1700/530, loss: 0.00690460205078125
2023-01-23 01:48:24.576179: step: 1704/530, loss: 0.023449230939149857
2023-01-23 01:48:25.668302: step: 1708/530, loss: 0.025321578606963158
2023-01-23 01:48:26.780659: step: 1712/530, loss: 0.013655662536621094
2023-01-23 01:48:27.908181: step: 1716/530, loss: 0.027897071093320847
2023-01-23 01:48:29.009706: step: 1720/530, loss: 0.0948280394077301
2023-01-23 01:48:30.096599: step: 1724/530, loss: 0.03072824515402317
2023-01-23 01:48:31.191766: step: 1728/530, loss: 0.033811189234256744
2023-01-23 01:48:32.297163: step: 1732/530, loss: 0.20510853826999664
2023-01-23 01:48:33.402649: step: 1736/530, loss: 0.05476036295294762
2023-01-23 01:48:34.530252: step: 1740/530, loss: 0.014009762555360794
2023-01-23 01:48:35.614550: step: 1744/530, loss: 0.07911892235279083
2023-01-23 01:48:36.722272: step: 1748/530, loss: 0.011137008666992188
2023-01-23 01:48:37.838498: step: 1752/530, loss: 0.011971366591751575
2023-01-23 01:48:38.950846: step: 1756/530, loss: 0.013309288769960403
2023-01-23 01:48:40.016666: step: 1760/530, loss: 0.002271938370540738
2023-01-23 01:48:41.097181: step: 1764/530, loss: 0.012990761548280716
2023-01-23 01:48:42.230799: step: 1768/530, loss: 0.04801464080810547
2023-01-23 01:48:43.341962: step: 1772/530, loss: 0.02437558025121689
2023-01-23 01:48:44.465765: step: 1776/530, loss: 0.022745704278349876
2023-01-23 01:48:45.564127: step: 1780/530, loss: 0.03569002449512482
2023-01-23 01:48:46.667383: step: 1784/530, loss: 0.014173602685332298
2023-01-23 01:48:47.770865: step: 1788/530, loss: 0.011558150872588158
2023-01-23 01:48:48.896892: step: 1792/530, loss: 0.00604171771556139
2023-01-23 01:48:49.984860: step: 1796/530, loss: 0.005278396420180798
2023-01-23 01:48:51.069286: step: 1800/530, loss: 0.016076279804110527
2023-01-23 01:48:52.186188: step: 1804/530, loss: 0.09397892653942108
2023-01-23 01:48:53.296610: step: 1808/530, loss: 0.009065408259630203
2023-01-23 01:48:54.405041: step: 1812/530, loss: 0.016848040744662285
2023-01-23 01:48:55.490281: step: 1816/530, loss: 0.033849477767944336
2023-01-23 01:48:56.596604: step: 1820/530, loss: 0.008006667718291283
2023-01-23 01:48:57.730513: step: 1824/530, loss: 0.035149671137332916
2023-01-23 01:48:58.843375: step: 1828/530, loss: 0.031958676874637604
2023-01-23 01:48:59.957729: step: 1832/530, loss: 0.016405105590820312
2023-01-23 01:49:01.047069: step: 1836/530, loss: 0.03271064907312393
2023-01-23 01:49:02.200764: step: 1840/530, loss: 0.04124289005994797
2023-01-23 01:49:03.294308: step: 1844/530, loss: 0.002760601229965687
2023-01-23 01:49:04.404887: step: 1848/530, loss: 0.06742048263549805
2023-01-23 01:49:05.494726: step: 1852/530, loss: 0.25570470094680786
2023-01-23 01:49:06.601566: step: 1856/530, loss: 0.023184681311249733
2023-01-23 01:49:07.715277: step: 1860/530, loss: 0.009247493930161
2023-01-23 01:49:08.794304: step: 1864/530, loss: 0.026656342670321465
2023-01-23 01:49:09.897098: step: 1868/530, loss: 0.04822807386517525
2023-01-23 01:49:11.008569: step: 1872/530, loss: 0.062307167798280716
2023-01-23 01:49:12.094383: step: 1876/530, loss: 0.019462300464510918
2023-01-23 01:49:13.206022: step: 1880/530, loss: 0.09912419319152832
2023-01-23 01:49:14.307973: step: 1884/530, loss: 0.05363216623663902
2023-01-23 01:49:15.413016: step: 1888/530, loss: 0.006085253320634365
2023-01-23 01:49:16.500643: step: 1892/530, loss: 0.004158305935561657
2023-01-23 01:49:17.600932: step: 1896/530, loss: 0.051998332142829895
2023-01-23 01:49:18.749553: step: 1900/530, loss: 0.03031158447265625
2023-01-23 01:49:19.874742: step: 1904/530, loss: 0.3368871212005615
2023-01-23 01:49:20.977258: step: 1908/530, loss: 0.2325790375471115
2023-01-23 01:49:22.060818: step: 1912/530, loss: 0.07373352348804474
2023-01-23 01:49:23.160305: step: 1916/530, loss: 0.00828332919627428
2023-01-23 01:49:24.279746: step: 1920/530, loss: 0.04751787334680557
2023-01-23 01:49:25.361526: step: 1924/530, loss: 0.02096271514892578
2023-01-23 01:49:26.455732: step: 1928/530, loss: 0.0014201164012774825
2023-01-23 01:49:27.597609: step: 1932/530, loss: 0.016643429175019264
2023-01-23 01:49:28.740401: step: 1936/530, loss: 0.023142432793974876
2023-01-23 01:49:29.861088: step: 1940/530, loss: 0.001769638154655695
2023-01-23 01:49:30.988890: step: 1944/530, loss: 0.020806312561035156
2023-01-23 01:49:32.092821: step: 1948/530, loss: 0.028652288019657135
2023-01-23 01:49:33.209303: step: 1952/530, loss: 0.032911013811826706
2023-01-23 01:49:34.331968: step: 1956/530, loss: 0.021462060511112213
2023-01-23 01:49:35.425774: step: 1960/530, loss: 0.03213653713464737
2023-01-23 01:49:36.568506: step: 1964/530, loss: 0.09073762595653534
2023-01-23 01:49:37.714114: step: 1968/530, loss: 0.029110753908753395
2023-01-23 01:49:38.816917: step: 1972/530, loss: 0.7114695310592651
2023-01-23 01:49:39.909403: step: 1976/530, loss: 0.029550934210419655
2023-01-23 01:49:41.022195: step: 1980/530, loss: 0.1934029459953308
2023-01-23 01:49:42.135549: step: 1984/530, loss: 0.04341850429773331
2023-01-23 01:49:43.227137: step: 1988/530, loss: 0.06282548606395721
2023-01-23 01:49:44.303804: step: 1992/530, loss: 0.048888206481933594
2023-01-23 01:49:45.388251: step: 1996/530, loss: 0.0530853271484375
2023-01-23 01:49:46.508444: step: 2000/530, loss: 0.015187466517090797
2023-01-23 01:49:47.638639: step: 2004/530, loss: 0.04696941375732422
2023-01-23 01:49:48.735580: step: 2008/530, loss: 0.43210849165916443
2023-01-23 01:49:49.869450: step: 2012/530, loss: 0.014079475775361061
2023-01-23 01:49:50.964773: step: 2016/530, loss: 0.023248672485351562
2023-01-23 01:49:52.092932: step: 2020/530, loss: 0.03494957089424133
2023-01-23 01:49:53.226492: step: 2024/530, loss: 0.19624005258083344
2023-01-23 01:49:54.355937: step: 2028/530, loss: 0.015550232492387295
2023-01-23 01:49:55.458697: step: 2032/530, loss: 0.02035827562212944
2023-01-23 01:49:56.593100: step: 2036/530, loss: 0.08617305755615234
2023-01-23 01:49:57.709982: step: 2040/530, loss: 0.028662491589784622
2023-01-23 01:49:58.806845: step: 2044/530, loss: 0.014487648382782936
2023-01-23 01:49:59.908983: step: 2048/530, loss: 0.8045014142990112
2023-01-23 01:50:01.037847: step: 2052/530, loss: 0.1203043982386589
2023-01-23 01:50:02.172022: step: 2056/530, loss: 0.1416303664445877
2023-01-23 01:50:03.281537: step: 2060/530, loss: 0.005613232031464577
2023-01-23 01:50:04.384466: step: 2064/530, loss: 0.023755835369229317
2023-01-23 01:50:05.506355: step: 2068/530, loss: 0.02379455603659153
2023-01-23 01:50:06.637404: step: 2072/530, loss: 0.02495441399514675
2023-01-23 01:50:07.739039: step: 2076/530, loss: 0.09492950886487961
2023-01-23 01:50:08.840984: step: 2080/530, loss: 0.001062583876773715
2023-01-23 01:50:09.936910: step: 2084/530, loss: 0.05751362070441246
2023-01-23 01:50:11.061612: step: 2088/530, loss: 0.05487098544836044
2023-01-23 01:50:12.161503: step: 2092/530, loss: 0.004440784454345703
2023-01-23 01:50:13.241803: step: 2096/530, loss: 0.0067605976946651936
2023-01-23 01:50:14.333588: step: 2100/530, loss: 0.03372316434979439
2023-01-23 01:50:15.462068: step: 2104/530, loss: 0.17055433988571167
2023-01-23 01:50:16.545429: step: 2108/530, loss: 0.04817914962768555
2023-01-23 01:50:17.658888: step: 2112/530, loss: 0.025104330852627754
2023-01-23 01:50:18.758171: step: 2116/530, loss: 0.14019203186035156
2023-01-23 01:50:19.892687: step: 2120/530, loss: 0.0209871307015419
==================================================
Loss: 0.067
--------------------
Dev: {'event': {'p': 0.5741293532338309, 'r': 0.7683089214380826, 'f1': 0.6571753986332575}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Test: {'event': {'p': 0.6260311640696609, 'r': 0.796037296037296, 'f1': 0.7008722421754746}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Chinese: {'event': {'p': 0.5679012345679012, 'r': 0.8518518518518519, 'f1': 0.6814814814814814}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Korean: {'event': {'p': 0.6415094339622641, 'r': 0.5396825396825397, 'f1': 0.5862068965517241}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
Russian: {'event': {'p': 0.38636363636363635, 'r': 0.4722222222222222, 'f1': 0.425}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 13}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6449771689497716, 'r': 0.7523302263648469, 'f1': 0.6945298094652735}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Chinese: {'event': {'p': 0.6692644909887969, 'r': 0.8006993006993007, 'f1': 0.7291058636243036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Chinese: {'event': {'p': 0.6764705882352942, 'r': 0.8518518518518519, 'f1': 0.7540983606557378}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6449771689497716, 'r': 0.7523302263648469, 'f1': 0.6945298094652735}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Korean: {'event': {'p': 0.6692644909887969, 'r': 0.8006993006993007, 'f1': 0.7291058636243036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Korean: {'event': {'p': 0.7391304347826086, 'r': 0.5396825396825397, 'f1': 0.6238532110091742}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5971370143149284, 'r': 0.7776298268974701, 'f1': 0.6755349913244649}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Russian: {'event': {'p': 0.6401673640167364, 'r': 0.8024475524475524, 'f1': 0.7121799844840963}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Russian: {'event': {'p': 0.5897435897435898, 'r': 0.6388888888888888, 'f1': 0.6133333333333332}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
******************************
Epoch: 14
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 01:50:59.002391: step: 4/530, loss: 0.04702253267168999
2023-01-23 01:51:00.106346: step: 8/530, loss: 0.053995512425899506
2023-01-23 01:51:01.215402: step: 12/530, loss: 0.06028447300195694
2023-01-23 01:51:02.325089: step: 16/530, loss: 0.061688877642154694
2023-01-23 01:51:03.420711: step: 20/530, loss: 0.019106674939393997
2023-01-23 01:51:04.553754: step: 24/530, loss: 0.05822276696562767
2023-01-23 01:51:05.656358: step: 28/530, loss: 0.010633086785674095
2023-01-23 01:51:06.747821: step: 32/530, loss: 0.0030896186362951994
2023-01-23 01:51:07.861096: step: 36/530, loss: 0.010391426272690296
2023-01-23 01:51:08.949151: step: 40/530, loss: 0.05177793651819229
2023-01-23 01:51:10.069330: step: 44/530, loss: 0.006768893916159868
2023-01-23 01:51:11.175309: step: 48/530, loss: 0.0005341529613360763
2023-01-23 01:51:12.282476: step: 52/530, loss: 0.034753940999507904
2023-01-23 01:51:13.374126: step: 56/530, loss: 0.005556297022849321
2023-01-23 01:51:14.457692: step: 60/530, loss: 0.0033323289826512337
2023-01-23 01:51:15.568050: step: 64/530, loss: 0.018329525366425514
2023-01-23 01:51:16.683385: step: 68/530, loss: 0.022192668169736862
2023-01-23 01:51:17.767063: step: 72/530, loss: 0.011812853626906872
2023-01-23 01:51:18.841986: step: 76/530, loss: 0.00901184044778347
2023-01-23 01:51:19.936303: step: 80/530, loss: 0.011128759942948818
2023-01-23 01:51:21.019202: step: 84/530, loss: 0.014445876702666283
2023-01-23 01:51:22.151559: step: 88/530, loss: 0.0047130584716796875
2023-01-23 01:51:23.282173: step: 92/530, loss: 0.028824998065829277
2023-01-23 01:51:24.390537: step: 96/530, loss: 0.04604749381542206
2023-01-23 01:51:25.522948: step: 100/530, loss: 0.04545726999640465
2023-01-23 01:51:26.623684: step: 104/530, loss: 0.18642081320285797
2023-01-23 01:51:27.711967: step: 108/530, loss: 0.03371763229370117
2023-01-23 01:51:28.845579: step: 112/530, loss: 0.06488686054944992
2023-01-23 01:51:29.967521: step: 116/530, loss: 0.011842155829071999
2023-01-23 01:51:31.060045: step: 120/530, loss: 0.035103797912597656
2023-01-23 01:51:32.186574: step: 124/530, loss: 0.012880897149443626
2023-01-23 01:51:33.300503: step: 128/530, loss: 0.018087053671479225
2023-01-23 01:51:34.378314: step: 132/530, loss: 0.006425953004509211
2023-01-23 01:51:35.579332: step: 136/530, loss: 0.01656184159219265
2023-01-23 01:51:36.694339: step: 140/530, loss: 0.09010204672813416
2023-01-23 01:51:37.817768: step: 144/530, loss: 0.0386720672249794
2023-01-23 01:51:38.945798: step: 148/530, loss: 0.013581561855971813
2023-01-23 01:51:40.025580: step: 152/530, loss: 0.0008546829340048134
2023-01-23 01:51:41.119528: step: 156/530, loss: 0.009652567096054554
2023-01-23 01:51:42.236226: step: 160/530, loss: 0.07323838025331497
2023-01-23 01:51:43.336986: step: 164/530, loss: 0.022803688421845436
2023-01-23 01:51:44.462369: step: 168/530, loss: 0.03015890344977379
2023-01-23 01:51:45.571835: step: 172/530, loss: 0.0009258746867999434
2023-01-23 01:51:46.671589: step: 176/530, loss: 0.023730754852294922
2023-01-23 01:51:47.802345: step: 180/530, loss: 0.0020950317848473787
2023-01-23 01:51:48.882084: step: 184/530, loss: 0.4135301411151886
2023-01-23 01:51:49.995141: step: 188/530, loss: 0.02744932286441326
2023-01-23 01:51:51.107738: step: 192/530, loss: 0.00901031494140625
2023-01-23 01:51:52.231495: step: 196/530, loss: 0.2015785276889801
2023-01-23 01:51:53.332819: step: 200/530, loss: 0.026627065613865852
2023-01-23 01:51:54.441088: step: 204/530, loss: 0.0015189171535894275
2023-01-23 01:51:55.536241: step: 208/530, loss: 0.056769564747810364
2023-01-23 01:51:56.635354: step: 212/530, loss: 0.0029735565185546875
2023-01-23 01:51:57.775675: step: 216/530, loss: 0.027938079088926315
2023-01-23 01:51:58.896330: step: 220/530, loss: 0.14071951806545258
2023-01-23 01:51:59.981834: step: 224/530, loss: 0.03213090822100639
2023-01-23 01:52:01.129400: step: 228/530, loss: 0.1904449462890625
2023-01-23 01:52:02.224853: step: 232/530, loss: 0.0886446014046669
2023-01-23 01:52:03.352072: step: 236/530, loss: 0.02261791191995144
2023-01-23 01:52:04.452474: step: 240/530, loss: 0.04552135244011879
2023-01-23 01:52:05.571724: step: 244/530, loss: 0.0033027648460119963
2023-01-23 01:52:06.664650: step: 248/530, loss: 0.05379519611597061
2023-01-23 01:52:07.756170: step: 252/530, loss: 0.04106717184185982
2023-01-23 01:52:08.884900: step: 256/530, loss: 0.07275620102882385
2023-01-23 01:52:10.001347: step: 260/530, loss: 0.0029544830322265625
2023-01-23 01:52:11.101977: step: 264/530, loss: 0.03281726688146591
2023-01-23 01:52:12.194361: step: 268/530, loss: 0.055399514734745026
2023-01-23 01:52:13.282626: step: 272/530, loss: 0.0007381439208984375
2023-01-23 01:52:14.393956: step: 276/530, loss: 0.03278714418411255
2023-01-23 01:52:15.493586: step: 280/530, loss: 0.0396793857216835
2023-01-23 01:52:16.642518: step: 284/530, loss: 0.026972388848662376
2023-01-23 01:52:17.750302: step: 288/530, loss: 0.14087219536304474
2023-01-23 01:52:18.861061: step: 292/530, loss: 0.06204567104578018
2023-01-23 01:52:19.954731: step: 296/530, loss: 0.023462487384676933
2023-01-23 01:52:21.057829: step: 300/530, loss: 0.020273970440030098
2023-01-23 01:52:22.158044: step: 304/530, loss: 0.35043519735336304
2023-01-23 01:52:23.278827: step: 308/530, loss: 0.09835606068372726
2023-01-23 01:52:24.362233: step: 312/530, loss: 0.03778839111328125
2023-01-23 01:52:25.463913: step: 316/530, loss: 0.011099433526396751
2023-01-23 01:52:26.564633: step: 320/530, loss: 0.024808691814541817
2023-01-23 01:52:27.659029: step: 324/530, loss: 0.0012960435124114156
2023-01-23 01:52:28.753508: step: 328/530, loss: 0.21228285133838654
2023-01-23 01:52:29.839905: step: 332/530, loss: 0.01964855194091797
2023-01-23 01:52:30.935145: step: 336/530, loss: 0.014302825555205345
2023-01-23 01:52:32.043967: step: 340/530, loss: 0.0023017884232103825
2023-01-23 01:52:33.180845: step: 344/530, loss: 0.0010913849109783769
2023-01-23 01:52:34.295095: step: 348/530, loss: 0.007652043830603361
2023-01-23 01:52:35.390110: step: 352/530, loss: 0.009154558181762695
2023-01-23 01:52:36.485830: step: 356/530, loss: 0.03599219396710396
2023-01-23 01:52:37.588691: step: 360/530, loss: 0.011194229125976562
2023-01-23 01:52:38.708745: step: 364/530, loss: 0.005347633734345436
2023-01-23 01:52:39.806239: step: 368/530, loss: 0.0017028808360919356
2023-01-23 01:52:40.895261: step: 372/530, loss: 0.026422597467899323
2023-01-23 01:52:41.975424: step: 376/530, loss: 0.04452910274267197
2023-01-23 01:52:43.062389: step: 380/530, loss: 0.0005995750543661416
2023-01-23 01:52:44.151015: step: 384/530, loss: 0.01575031317770481
2023-01-23 01:52:45.241869: step: 388/530, loss: 0.0006193161243572831
2023-01-23 01:52:46.339540: step: 392/530, loss: 0.0525602325797081
2023-01-23 01:52:47.478940: step: 396/530, loss: 0.03415260463953018
2023-01-23 01:52:48.579941: step: 400/530, loss: 0.026873396709561348
2023-01-23 01:52:49.693911: step: 404/530, loss: 0.0029591561760753393
2023-01-23 01:52:50.782483: step: 408/530, loss: 0.03813915327191353
2023-01-23 01:52:51.865261: step: 412/530, loss: 0.03328828886151314
2023-01-23 01:52:52.952947: step: 416/530, loss: 0.03896684572100639
2023-01-23 01:52:54.054334: step: 420/530, loss: 0.0037037848960608244
2023-01-23 01:52:55.172781: step: 424/530, loss: 0.01860809326171875
2023-01-23 01:52:56.245177: step: 428/530, loss: 0.0035160065162926912
2023-01-23 01:52:57.369263: step: 432/530, loss: 0.01439514197409153
2023-01-23 01:52:58.465380: step: 436/530, loss: 0.0042327879928052425
2023-01-23 01:52:59.580173: step: 440/530, loss: 0.017043257132172585
2023-01-23 01:53:00.668903: step: 444/530, loss: 0.006049538031220436
2023-01-23 01:53:01.764764: step: 448/530, loss: 0.06287059932947159
2023-01-23 01:53:02.879064: step: 452/530, loss: 0.010165786370635033
2023-01-23 01:53:03.973109: step: 456/530, loss: 0.0024124146439135075
2023-01-23 01:53:05.067686: step: 460/530, loss: 0.005789518356323242
2023-01-23 01:53:06.187790: step: 464/530, loss: 0.056801509112119675
2023-01-23 01:53:07.303145: step: 468/530, loss: 0.023688506335020065
2023-01-23 01:53:08.406436: step: 472/530, loss: 0.08715686947107315
2023-01-23 01:53:09.468926: step: 476/530, loss: 0.017769623547792435
2023-01-23 01:53:10.585511: step: 480/530, loss: 0.13071098923683167
2023-01-23 01:53:11.685127: step: 484/530, loss: 0.010578442364931107
2023-01-23 01:53:12.789075: step: 488/530, loss: 0.013220597058534622
2023-01-23 01:53:13.924251: step: 492/530, loss: 0.0063967229798436165
2023-01-23 01:53:15.031616: step: 496/530, loss: 0.03955917805433273
2023-01-23 01:53:16.145635: step: 500/530, loss: 0.013597965240478516
2023-01-23 01:53:17.240007: step: 504/530, loss: 0.04321122169494629
2023-01-23 01:53:18.372101: step: 508/530, loss: 0.005224895663559437
2023-01-23 01:53:19.485903: step: 512/530, loss: 0.026416493579745293
2023-01-23 01:53:20.574793: step: 516/530, loss: 0.0160430446267128
2023-01-23 01:53:21.643981: step: 520/530, loss: 0.033298298716545105
2023-01-23 01:53:22.768632: step: 524/530, loss: 0.033376120030879974
2023-01-23 01:53:23.867712: step: 528/530, loss: 0.00105199811514467
2023-01-23 01:53:24.966746: step: 532/530, loss: 0.06494121253490448
2023-01-23 01:53:26.058804: step: 536/530, loss: 0.06349873542785645
2023-01-23 01:53:27.158571: step: 540/530, loss: 0.03936271741986275
2023-01-23 01:53:28.296272: step: 544/530, loss: 0.0035247982013970613
2023-01-23 01:53:29.404349: step: 548/530, loss: 0.009364891797304153
2023-01-23 01:53:30.523268: step: 552/530, loss: 0.05418434366583824
2023-01-23 01:53:31.672267: step: 556/530, loss: 0.03356046602129936
2023-01-23 01:53:32.777099: step: 560/530, loss: 0.006576729007065296
2023-01-23 01:53:33.921455: step: 564/530, loss: 0.08402281254529953
2023-01-23 01:53:35.028785: step: 568/530, loss: 0.022785712033510208
2023-01-23 01:53:36.128113: step: 572/530, loss: 0.0566926971077919
2023-01-23 01:53:37.246535: step: 576/530, loss: 0.0031988145783543587
2023-01-23 01:53:38.388965: step: 580/530, loss: 0.058861732482910156
2023-01-23 01:53:39.501770: step: 584/530, loss: 0.004862308502197266
2023-01-23 01:53:40.608527: step: 588/530, loss: 0.04411335289478302
2023-01-23 01:53:41.698246: step: 592/530, loss: 0.032705213874578476
2023-01-23 01:53:42.815413: step: 596/530, loss: 0.035577964037656784
2023-01-23 01:53:43.965829: step: 600/530, loss: 0.11690273135900497
2023-01-23 01:53:45.093283: step: 604/530, loss: 0.035485364496707916
2023-01-23 01:53:46.175981: step: 608/530, loss: 0.04994511604309082
2023-01-23 01:53:47.269698: step: 612/530, loss: 0.00014781951904296875
2023-01-23 01:53:48.391961: step: 616/530, loss: 0.02391967922449112
2023-01-23 01:53:49.537821: step: 620/530, loss: 0.03444986045360565
2023-01-23 01:53:50.663503: step: 624/530, loss: 0.024228285998106003
2023-01-23 01:53:51.798753: step: 628/530, loss: 0.02290506474673748
2023-01-23 01:53:52.925931: step: 632/530, loss: 0.06472358852624893
2023-01-23 01:53:54.017093: step: 636/530, loss: 0.00258216867223382
2023-01-23 01:53:55.131955: step: 640/530, loss: 0.07961063832044601
2023-01-23 01:53:56.235314: step: 644/530, loss: 0.013646173290908337
2023-01-23 01:53:57.321048: step: 648/530, loss: 0.01931281015276909
2023-01-23 01:53:58.421917: step: 652/530, loss: 0.04296741262078285
2023-01-23 01:53:59.552067: step: 656/530, loss: 0.02165203168988228
2023-01-23 01:54:00.681657: step: 660/530, loss: 0.012423706240952015
2023-01-23 01:54:01.783752: step: 664/530, loss: 0.0005661010509356856
2023-01-23 01:54:02.879720: step: 668/530, loss: 0.06245794519782066
2023-01-23 01:54:03.967911: step: 672/530, loss: 0.038239289075136185
2023-01-23 01:54:05.074527: step: 676/530, loss: 0.03986511379480362
2023-01-23 01:54:06.177344: step: 680/530, loss: 0.05547704920172691
2023-01-23 01:54:07.275998: step: 684/530, loss: 0.0011751174461096525
2023-01-23 01:54:08.378988: step: 688/530, loss: 0.01283874548971653
2023-01-23 01:54:09.507183: step: 692/530, loss: 0.012485838495194912
2023-01-23 01:54:10.594325: step: 696/530, loss: 0.03501176834106445
2023-01-23 01:54:11.703020: step: 700/530, loss: 0.011805725283920765
2023-01-23 01:54:12.820092: step: 704/530, loss: 0.03932938724756241
2023-01-23 01:54:13.969278: step: 708/530, loss: 0.004594612400978804
2023-01-23 01:54:15.084285: step: 712/530, loss: 0.01157989539206028
2023-01-23 01:54:16.182080: step: 716/530, loss: 0.001975917723029852
2023-01-23 01:54:17.293688: step: 720/530, loss: 0.013444637879729271
2023-01-23 01:54:18.388195: step: 724/530, loss: 0.0134156234562397
2023-01-23 01:54:19.505193: step: 728/530, loss: 0.01780243031680584
2023-01-23 01:54:20.615340: step: 732/530, loss: 0.004899597726762295
2023-01-23 01:54:21.717078: step: 736/530, loss: 0.03235134482383728
2023-01-23 01:54:22.821015: step: 740/530, loss: 0.015716170892119408
2023-01-23 01:54:23.911345: step: 744/530, loss: 0.015531444922089577
2023-01-23 01:54:24.999679: step: 748/530, loss: 0.024732496589422226
2023-01-23 01:54:26.119048: step: 752/530, loss: 0.08232907950878143
2023-01-23 01:54:27.216266: step: 756/530, loss: 0.028269385918974876
2023-01-23 01:54:28.317188: step: 760/530, loss: 0.0457274429500103
2023-01-23 01:54:29.458725: step: 764/530, loss: 0.028673935681581497
2023-01-23 01:54:30.572878: step: 768/530, loss: 0.12333240360021591
2023-01-23 01:54:31.647796: step: 772/530, loss: 0.011832332238554955
2023-01-23 01:54:32.779977: step: 776/530, loss: 0.0030558586586266756
2023-01-23 01:54:33.931942: step: 780/530, loss: 0.12677001953125
2023-01-23 01:54:35.042046: step: 784/530, loss: 0.08717412501573563
2023-01-23 01:54:36.151852: step: 788/530, loss: 0.03781528398394585
2023-01-23 01:54:37.260991: step: 792/530, loss: 0.009796691127121449
2023-01-23 01:54:38.334897: step: 796/530, loss: 0.03370647504925728
2023-01-23 01:54:39.459831: step: 800/530, loss: 0.03340645134449005
2023-01-23 01:54:40.568355: step: 804/530, loss: 0.019536305218935013
2023-01-23 01:54:41.691216: step: 808/530, loss: 0.006667518988251686
2023-01-23 01:54:42.763396: step: 812/530, loss: 0.005557251162827015
2023-01-23 01:54:43.903581: step: 816/530, loss: 0.22441402077674866
2023-01-23 01:54:44.991011: step: 820/530, loss: 0.038706209510564804
2023-01-23 01:54:46.124646: step: 824/530, loss: 0.0004555225314106792
2023-01-23 01:54:47.258318: step: 828/530, loss: 0.05806303024291992
2023-01-23 01:54:48.361754: step: 832/530, loss: 0.00952692050486803
2023-01-23 01:54:49.447469: step: 836/530, loss: 0.06042361259460449
2023-01-23 01:54:50.562122: step: 840/530, loss: 0.11796483397483826
2023-01-23 01:54:51.654388: step: 844/530, loss: 0.005104636773467064
2023-01-23 01:54:52.743092: step: 848/530, loss: 0.009807109832763672
2023-01-23 01:54:53.870226: step: 852/530, loss: 0.019356727600097656
2023-01-23 01:54:54.984257: step: 856/530, loss: 0.049624063074588776
2023-01-23 01:54:56.110162: step: 860/530, loss: 0.04485110938549042
2023-01-23 01:54:57.188712: step: 864/530, loss: 0.000164031982421875
2023-01-23 01:54:58.329382: step: 868/530, loss: 0.0826214849948883
2023-01-23 01:54:59.464237: step: 872/530, loss: 0.06108064949512482
2023-01-23 01:55:00.605109: step: 876/530, loss: 0.03638935089111328
2023-01-23 01:55:01.707327: step: 880/530, loss: 0.02673196792602539
2023-01-23 01:55:02.861846: step: 884/530, loss: 0.032164763659238815
2023-01-23 01:55:03.986708: step: 888/530, loss: 0.0740235298871994
2023-01-23 01:55:05.069313: step: 892/530, loss: 0.01280899066478014
2023-01-23 01:55:06.186883: step: 896/530, loss: 0.12015514075756073
2023-01-23 01:55:07.311108: step: 900/530, loss: 0.013498758897185326
2023-01-23 01:55:08.422137: step: 904/530, loss: 0.05314045026898384
2023-01-23 01:55:09.541097: step: 908/530, loss: 0.031987667083740234
2023-01-23 01:55:10.643071: step: 912/530, loss: 0.00016460419283248484
2023-01-23 01:55:11.756139: step: 916/530, loss: 0.04135780781507492
2023-01-23 01:55:12.844308: step: 920/530, loss: 0.03375639393925667
2023-01-23 01:55:13.955026: step: 924/530, loss: 0.0018406867748126388
2023-01-23 01:55:15.063553: step: 928/530, loss: 0.05179310217499733
2023-01-23 01:55:16.184252: step: 932/530, loss: 0.04589195176959038
2023-01-23 01:55:17.290516: step: 936/530, loss: 0.008453321643173695
2023-01-23 01:55:18.371352: step: 940/530, loss: 0.030608177185058594
2023-01-23 01:55:19.482220: step: 944/530, loss: 0.0008788108825683594
2023-01-23 01:55:20.604612: step: 948/530, loss: 0.012353443540632725
2023-01-23 01:55:21.729109: step: 952/530, loss: 0.03370209038257599
2023-01-23 01:55:22.827593: step: 956/530, loss: 0.026050997897982597
2023-01-23 01:55:23.942423: step: 960/530, loss: 0.01186981238424778
2023-01-23 01:55:25.049909: step: 964/530, loss: 0.03475773334503174
2023-01-23 01:55:26.138984: step: 968/530, loss: 0.049370668828487396
2023-01-23 01:55:27.225586: step: 972/530, loss: 0.04371605068445206
2023-01-23 01:55:28.351646: step: 976/530, loss: 0.0364263541996479
2023-01-23 01:55:29.466933: step: 980/530, loss: 0.06429455429315567
2023-01-23 01:55:30.550864: step: 984/530, loss: 0.010004807263612747
2023-01-23 01:55:31.629826: step: 988/530, loss: 0.043923333287239075
2023-01-23 01:55:32.719690: step: 992/530, loss: 0.0003027915954589844
2023-01-23 01:55:33.835608: step: 996/530, loss: 0.01919269748032093
2023-01-23 01:55:34.903106: step: 1000/530, loss: 0.004035663791000843
2023-01-23 01:55:35.992837: step: 1004/530, loss: 0.014319324865937233
2023-01-23 01:55:37.102813: step: 1008/530, loss: 0.07364041358232498
2023-01-23 01:55:38.224756: step: 1012/530, loss: 0.0019920349586755037
2023-01-23 01:55:39.363802: step: 1016/530, loss: 0.020370198413729668
2023-01-23 01:55:40.475497: step: 1020/530, loss: 0.0007961273076944053
2023-01-23 01:55:41.565644: step: 1024/530, loss: 0.025880910456180573
2023-01-23 01:55:42.684104: step: 1028/530, loss: 0.014011383056640625
2023-01-23 01:55:43.797102: step: 1032/530, loss: 0.004825020208954811
2023-01-23 01:55:44.929942: step: 1036/530, loss: 0.01976175233721733
2023-01-23 01:55:46.042777: step: 1040/530, loss: 0.04754295572638512
2023-01-23 01:55:47.125726: step: 1044/530, loss: 0.018389130011200905
2023-01-23 01:55:48.226688: step: 1048/530, loss: 0.005770969204604626
2023-01-23 01:55:49.368486: step: 1052/530, loss: 0.019846726208925247
2023-01-23 01:55:50.463642: step: 1056/530, loss: 0.0004981040838174522
2023-01-23 01:55:51.565443: step: 1060/530, loss: 0.0172592643648386
2023-01-23 01:55:52.676368: step: 1064/530, loss: 0.08783312141895294
2023-01-23 01:55:53.780269: step: 1068/530, loss: 0.07395347952842712
2023-01-23 01:55:54.876273: step: 1072/530, loss: 0.011962438002228737
2023-01-23 01:55:55.970220: step: 1076/530, loss: 0.05137849226593971
2023-01-23 01:55:57.104244: step: 1080/530, loss: 0.1057291030883789
2023-01-23 01:55:58.200270: step: 1084/530, loss: 0.026575280353426933
2023-01-23 01:55:59.280094: step: 1088/530, loss: 0.11547289043664932
2023-01-23 01:56:00.388431: step: 1092/530, loss: 0.07589836418628693
2023-01-23 01:56:01.493702: step: 1096/530, loss: 0.0512331984937191
2023-01-23 01:56:02.574867: step: 1100/530, loss: 0.0018918991554528475
2023-01-23 01:56:03.683417: step: 1104/530, loss: 0.00016336441331077367
2023-01-23 01:56:04.798822: step: 1108/530, loss: 0.04985189810395241
2023-01-23 01:56:05.890539: step: 1112/530, loss: 0.001569557236507535
2023-01-23 01:56:07.003451: step: 1116/530, loss: 0.07535958290100098
2023-01-23 01:56:08.133656: step: 1120/530, loss: 0.08077564090490341
2023-01-23 01:56:09.255373: step: 1124/530, loss: 0.04405088350176811
2023-01-23 01:56:10.376120: step: 1128/530, loss: 0.026410294696688652
2023-01-23 01:56:11.497592: step: 1132/530, loss: 0.02624998241662979
2023-01-23 01:56:12.605911: step: 1136/530, loss: 0.022647762671113014
2023-01-23 01:56:13.711328: step: 1140/530, loss: 0.07612466812133789
2023-01-23 01:56:14.832379: step: 1144/530, loss: 0.05960845947265625
2023-01-23 01:56:15.924315: step: 1148/530, loss: 0.0007684707525186241
2023-01-23 01:56:17.046845: step: 1152/530, loss: 0.0053043365478515625
2023-01-23 01:56:18.150267: step: 1156/530, loss: 0.005918025970458984
2023-01-23 01:56:19.244685: step: 1160/530, loss: 0.0027459862176328897
2023-01-23 01:56:20.388709: step: 1164/530, loss: 0.021146010607481003
2023-01-23 01:56:21.487241: step: 1168/530, loss: 0.06417503207921982
2023-01-23 01:56:22.577369: step: 1172/530, loss: 0.03320322185754776
2023-01-23 01:56:23.694180: step: 1176/530, loss: 0.028713228181004524
2023-01-23 01:56:24.814937: step: 1180/530, loss: 0.011194038204848766
2023-01-23 01:56:25.926073: step: 1184/530, loss: 0.01003799494355917
2023-01-23 01:56:27.036709: step: 1188/530, loss: 0.11275014281272888
2023-01-23 01:56:28.138819: step: 1192/530, loss: 0.005667686462402344
2023-01-23 01:56:29.243449: step: 1196/530, loss: 0.026314545422792435
2023-01-23 01:56:30.343878: step: 1200/530, loss: 0.037932634353637695
2023-01-23 01:56:31.479656: step: 1204/530, loss: 0.006468009669333696
2023-01-23 01:56:32.574166: step: 1208/530, loss: 0.012236976996064186
2023-01-23 01:56:33.711666: step: 1212/530, loss: 0.043326761573553085
2023-01-23 01:56:34.813152: step: 1216/530, loss: 0.2075360119342804
2023-01-23 01:56:35.904593: step: 1220/530, loss: 0.8059371709823608
2023-01-23 01:56:37.050750: step: 1224/530, loss: 0.01635437086224556
2023-01-23 01:56:38.146530: step: 1228/530, loss: 0.0451078899204731
2023-01-23 01:56:39.261437: step: 1232/530, loss: 0.10109567642211914
2023-01-23 01:56:40.365908: step: 1236/530, loss: 0.004776477813720703
2023-01-23 01:56:41.475671: step: 1240/530, loss: 0.031247520819306374
2023-01-23 01:56:42.575448: step: 1244/530, loss: 0.019735049456357956
2023-01-23 01:56:43.711280: step: 1248/530, loss: 0.0036596297286450863
2023-01-23 01:56:44.837386: step: 1252/530, loss: 0.039902493357658386
2023-01-23 01:56:45.942506: step: 1256/530, loss: 0.007407188415527344
2023-01-23 01:56:47.069709: step: 1260/530, loss: 0.10271687805652618
2023-01-23 01:56:48.219572: step: 1264/530, loss: 0.006028842646628618
2023-01-23 01:56:49.310954: step: 1268/530, loss: 0.0051541803404688835
2023-01-23 01:56:50.387789: step: 1272/530, loss: 0.031397055834531784
2023-01-23 01:56:51.503108: step: 1276/530, loss: 0.020188044756650925
2023-01-23 01:56:52.620884: step: 1280/530, loss: 0.001955747604370117
2023-01-23 01:56:53.737453: step: 1284/530, loss: 0.03940620273351669
2023-01-23 01:56:54.821916: step: 1288/530, loss: 0.02541809156537056
2023-01-23 01:56:55.919183: step: 1292/530, loss: 0.18013162910938263
2023-01-23 01:56:57.034829: step: 1296/530, loss: 0.04410620033740997
2023-01-23 01:56:58.126497: step: 1300/530, loss: 0.026226330548524857
2023-01-23 01:56:59.226230: step: 1304/530, loss: 0.0007550239679403603
2023-01-23 01:57:00.324936: step: 1308/530, loss: 0.033626750111579895
2023-01-23 01:57:01.415535: step: 1312/530, loss: 0.023047257214784622
2023-01-23 01:57:02.504616: step: 1316/530, loss: 0.05268258973956108
2023-01-23 01:57:03.626675: step: 1320/530, loss: 0.01068801898509264
2023-01-23 01:57:04.713643: step: 1324/530, loss: 0.011422348208725452
2023-01-23 01:57:05.841458: step: 1328/530, loss: 0.05138666555285454
2023-01-23 01:57:06.927514: step: 1332/530, loss: 0.3285846710205078
2023-01-23 01:57:08.029500: step: 1336/530, loss: 0.00407142611220479
2023-01-23 01:57:09.127367: step: 1340/530, loss: 0.0057833194732666016
2023-01-23 01:57:10.229348: step: 1344/530, loss: 0.0175718292593956
2023-01-23 01:57:11.367218: step: 1348/530, loss: 0.06573142856359482
2023-01-23 01:57:12.463434: step: 1352/530, loss: 0.04876232147216797
2023-01-23 01:57:13.521845: step: 1356/530, loss: 0.01550216693431139
2023-01-23 01:57:14.598462: step: 1360/530, loss: 0.06156163290143013
2023-01-23 01:57:15.698192: step: 1364/530, loss: 0.0991780236363411
2023-01-23 01:57:16.777483: step: 1368/530, loss: 0.1291217803955078
2023-01-23 01:57:17.873354: step: 1372/530, loss: 0.03913154825568199
2023-01-23 01:57:18.995426: step: 1376/530, loss: 0.018185734748840332
2023-01-23 01:57:20.136656: step: 1380/530, loss: 0.005368709564208984
2023-01-23 01:57:21.282299: step: 1384/530, loss: 0.01321945246309042
2023-01-23 01:57:22.376319: step: 1388/530, loss: 0.012521934695541859
2023-01-23 01:57:23.545756: step: 1392/530, loss: 0.16168007254600525
2023-01-23 01:57:24.655945: step: 1396/530, loss: 0.004801750183105469
2023-01-23 01:57:25.741175: step: 1400/530, loss: 0.044954873621463776
2023-01-23 01:57:26.856845: step: 1404/530, loss: 0.08139253407716751
2023-01-23 01:57:27.977768: step: 1408/530, loss: 0.034287452697753906
2023-01-23 01:57:29.108636: step: 1412/530, loss: 0.023468876257538795
2023-01-23 01:57:30.227736: step: 1416/530, loss: 0.04912176355719566
2023-01-23 01:57:31.297361: step: 1420/530, loss: 0.00845184363424778
2023-01-23 01:57:32.435679: step: 1424/530, loss: 0.04271573945879936
2023-01-23 01:57:33.549659: step: 1428/530, loss: 0.06381885707378387
2023-01-23 01:57:34.647691: step: 1432/530, loss: 0.019021034240722656
2023-01-23 01:57:35.758686: step: 1436/530, loss: 0.07922086864709854
2023-01-23 01:57:36.859097: step: 1440/530, loss: 0.00045027732267044485
2023-01-23 01:57:37.979517: step: 1444/530, loss: 0.015250968746840954
2023-01-23 01:57:39.081012: step: 1448/530, loss: 0.0007928848499432206
2023-01-23 01:57:40.192706: step: 1452/530, loss: 0.08685141056776047
2023-01-23 01:57:41.268480: step: 1456/530, loss: 0.014615059830248356
2023-01-23 01:57:42.364155: step: 1460/530, loss: 0.0018489836947992444
2023-01-23 01:57:43.456746: step: 1464/530, loss: 0.009445381350815296
2023-01-23 01:57:44.588698: step: 1468/530, loss: 0.011879540048539639
2023-01-23 01:57:45.708435: step: 1472/530, loss: 0.1129993349313736
2023-01-23 01:57:46.799591: step: 1476/530, loss: 0.014867305755615234
2023-01-23 01:57:47.917754: step: 1480/530, loss: 0.0007789612282067537
2023-01-23 01:57:49.039165: step: 1484/530, loss: 0.0024732588790357113
2023-01-23 01:57:50.161945: step: 1488/530, loss: 0.06359024345874786
2023-01-23 01:57:51.313510: step: 1492/530, loss: 0.014087867923080921
2023-01-23 01:57:52.420786: step: 1496/530, loss: 0.4675951898097992
2023-01-23 01:57:53.520586: step: 1500/530, loss: 0.15122851729393005
2023-01-23 01:57:54.632578: step: 1504/530, loss: 0.0023272514808923006
2023-01-23 01:57:55.747497: step: 1508/530, loss: 0.0027468204498291016
2023-01-23 01:57:56.866565: step: 1512/530, loss: 0.022343730553984642
2023-01-23 01:57:57.963798: step: 1516/530, loss: 0.0004454970476217568
2023-01-23 01:57:59.046825: step: 1520/530, loss: 0.006854343228042126
2023-01-23 01:58:00.186650: step: 1524/530, loss: 0.014994526281952858
2023-01-23 01:58:01.279425: step: 1528/530, loss: 0.007521724794059992
2023-01-23 01:58:02.366806: step: 1532/530, loss: 0.003412151476368308
2023-01-23 01:58:03.470347: step: 1536/530, loss: 0.02092576026916504
2023-01-23 01:58:04.598775: step: 1540/530, loss: 0.005639362148940563
2023-01-23 01:58:05.723951: step: 1544/530, loss: 0.04359016567468643
2023-01-23 01:58:06.817320: step: 1548/530, loss: 0.08413977921009064
2023-01-23 01:58:07.907374: step: 1552/530, loss: 0.027789782732725143
2023-01-23 01:58:09.031769: step: 1556/530, loss: 0.004153442569077015
2023-01-23 01:58:10.122915: step: 1560/530, loss: 0.03072538413107395
2023-01-23 01:58:11.249385: step: 1564/530, loss: 0.02431678958237171
2023-01-23 01:58:12.378804: step: 1568/530, loss: 0.07511663436889648
2023-01-23 01:58:13.516494: step: 1572/530, loss: 0.042697906494140625
2023-01-23 01:58:14.620391: step: 1576/530, loss: 0.06186962127685547
2023-01-23 01:58:15.733749: step: 1580/530, loss: 0.00678176898509264
2023-01-23 01:58:16.821698: step: 1584/530, loss: 0.03982076793909073
2023-01-23 01:58:17.920207: step: 1588/530, loss: 0.11752519756555557
2023-01-23 01:58:19.074649: step: 1592/530, loss: 0.04287855699658394
2023-01-23 01:58:20.173404: step: 1596/530, loss: 0.004877281375229359
2023-01-23 01:58:21.279109: step: 1600/530, loss: 0.0007444381481036544
2023-01-23 01:58:22.385974: step: 1604/530, loss: 0.02773820050060749
2023-01-23 01:58:23.462916: step: 1608/530, loss: 0.33338847756385803
2023-01-23 01:58:24.564658: step: 1612/530, loss: 0.04131712764501572
2023-01-23 01:58:25.689917: step: 1616/530, loss: 0.11539671570062637
2023-01-23 01:58:26.819016: step: 1620/530, loss: 0.0984533280134201
2023-01-23 01:58:27.939179: step: 1624/530, loss: 0.09835352748632431
2023-01-23 01:58:29.059354: step: 1628/530, loss: 0.0024851798079907894
2023-01-23 01:58:30.207782: step: 1632/530, loss: 0.013050270266830921
2023-01-23 01:58:31.299297: step: 1636/530, loss: 0.14514796435832977
2023-01-23 01:58:32.401288: step: 1640/530, loss: 0.006684637162834406
2023-01-23 01:58:33.535561: step: 1644/530, loss: 0.021122360602021217
2023-01-23 01:58:34.634274: step: 1648/530, loss: 0.08370376378297806
2023-01-23 01:58:35.717070: step: 1652/530, loss: 0.038909342139959335
2023-01-23 01:58:36.823786: step: 1656/530, loss: 0.024690985679626465
2023-01-23 01:58:37.905248: step: 1660/530, loss: 0.0675228163599968
2023-01-23 01:58:39.027348: step: 1664/530, loss: 0.04369344934821129
2023-01-23 01:58:40.098217: step: 1668/530, loss: 0.06066736951470375
2023-01-23 01:58:41.195107: step: 1672/530, loss: 0.10701408982276917
2023-01-23 01:58:42.298323: step: 1676/530, loss: 0.010109711438417435
2023-01-23 01:58:43.378034: step: 1680/530, loss: 0.030431080609560013
2023-01-23 01:58:44.483717: step: 1684/530, loss: 0.016868973150849342
2023-01-23 01:58:45.593130: step: 1688/530, loss: 0.004961490631103516
2023-01-23 01:58:46.718588: step: 1692/530, loss: 0.053442858159542084
2023-01-23 01:58:47.829447: step: 1696/530, loss: 0.002344322158023715
2023-01-23 01:58:48.928675: step: 1700/530, loss: 0.003222990082576871
2023-01-23 01:58:50.026494: step: 1704/530, loss: 0.01374893169850111
2023-01-23 01:58:51.101280: step: 1708/530, loss: 0.001385164214298129
2023-01-23 01:58:52.215221: step: 1712/530, loss: 0.024440240114927292
2023-01-23 01:58:53.306012: step: 1716/530, loss: 0.004100179765373468
2023-01-23 01:58:54.419087: step: 1720/530, loss: 0.009533119387924671
2023-01-23 01:58:55.559521: step: 1724/530, loss: 0.018368912860751152
2023-01-23 01:58:56.645075: step: 1728/530, loss: 0.055997755378484726
2023-01-23 01:58:57.735757: step: 1732/530, loss: 0.009659767150878906
2023-01-23 01:58:58.836671: step: 1736/530, loss: 0.06765079498291016
2023-01-23 01:58:59.948007: step: 1740/530, loss: 0.011044216342270374
2023-01-23 01:59:01.059715: step: 1744/530, loss: 0.012182426638901234
2023-01-23 01:59:02.138672: step: 1748/530, loss: 0.0028264999855309725
2023-01-23 01:59:03.265322: step: 1752/530, loss: 0.027657318860292435
2023-01-23 01:59:04.391949: step: 1756/530, loss: 0.04594878852367401
2023-01-23 01:59:05.467162: step: 1760/530, loss: 0.024839449673891068
2023-01-23 01:59:06.576223: step: 1764/530, loss: 0.029146576300263405
2023-01-23 01:59:07.663357: step: 1768/530, loss: 0.003691005753353238
2023-01-23 01:59:08.762403: step: 1772/530, loss: 0.012962198816239834
2023-01-23 01:59:09.867023: step: 1776/530, loss: 0.0243682861328125
2023-01-23 01:59:10.953187: step: 1780/530, loss: 0.7046001553535461
2023-01-23 01:59:12.061122: step: 1784/530, loss: 0.02164335362613201
2023-01-23 01:59:13.185293: step: 1788/530, loss: 0.020779799669981003
2023-01-23 01:59:14.318218: step: 1792/530, loss: 0.005387115757912397
2023-01-23 01:59:15.439543: step: 1796/530, loss: 0.04198188707232475
2023-01-23 01:59:16.568663: step: 1800/530, loss: 0.005226612091064453
2023-01-23 01:59:17.714761: step: 1804/530, loss: 0.028284218162298203
2023-01-23 01:59:18.844766: step: 1808/530, loss: 0.06694754958152771
2023-01-23 01:59:19.946311: step: 1812/530, loss: 0.03285827487707138
2023-01-23 01:59:21.063476: step: 1816/530, loss: 0.059444572776556015
2023-01-23 01:59:22.203888: step: 1820/530, loss: 0.040041398257017136
2023-01-23 01:59:23.317901: step: 1824/530, loss: 0.18622493743896484
2023-01-23 01:59:24.420213: step: 1828/530, loss: 0.09272956848144531
2023-01-23 01:59:25.504889: step: 1832/530, loss: 0.0005753517034463584
2023-01-23 01:59:26.604899: step: 1836/530, loss: 0.02573680877685547
2023-01-23 01:59:27.706212: step: 1840/530, loss: 0.0005391120794229209
2023-01-23 01:59:28.815521: step: 1844/530, loss: 0.017215155065059662
2023-01-23 01:59:29.952593: step: 1848/530, loss: 0.05284767225384712
2023-01-23 01:59:31.057633: step: 1852/530, loss: 0.002670764923095703
2023-01-23 01:59:32.167738: step: 1856/530, loss: 0.06721992790699005
2023-01-23 01:59:33.258760: step: 1860/530, loss: 0.00736846961081028
2023-01-23 01:59:34.344687: step: 1864/530, loss: 0.025576304644346237
2023-01-23 01:59:35.479272: step: 1868/530, loss: 0.004384136293083429
2023-01-23 01:59:36.582165: step: 1872/530, loss: 0.022989653050899506
2023-01-23 01:59:37.682829: step: 1876/530, loss: 0.0003863335005007684
2023-01-23 01:59:38.803962: step: 1880/530, loss: 0.22870245575904846
2023-01-23 01:59:39.897747: step: 1884/530, loss: 0.042016223073005676
2023-01-23 01:59:40.972398: step: 1888/530, loss: 0.0003993511199951172
2023-01-23 01:59:42.074854: step: 1892/530, loss: 0.031127452850341797
2023-01-23 01:59:43.174273: step: 1896/530, loss: 0.009677315130829811
2023-01-23 01:59:44.272045: step: 1900/530, loss: 0.005593490786850452
2023-01-23 01:59:45.402527: step: 1904/530, loss: 0.03399648889899254
2023-01-23 01:59:46.542705: step: 1908/530, loss: 0.00026960374088957906
2023-01-23 01:59:47.638864: step: 1912/530, loss: 0.10045433044433594
2023-01-23 01:59:48.735843: step: 1916/530, loss: 0.05294227600097656
2023-01-23 01:59:49.823101: step: 1920/530, loss: 0.008403397165238857
2023-01-23 01:59:50.949681: step: 1924/530, loss: 0.014225197024643421
2023-01-23 01:59:52.096657: step: 1928/530, loss: 0.019710540771484375
2023-01-23 01:59:53.192009: step: 1932/530, loss: 0.045116521418094635
2023-01-23 01:59:54.306151: step: 1936/530, loss: 0.028953934088349342
2023-01-23 01:59:55.397502: step: 1940/530, loss: 0.02074890211224556
2023-01-23 01:59:56.508477: step: 1944/530, loss: 0.0022242546547204256
2023-01-23 01:59:57.617192: step: 1948/530, loss: 0.011640453711152077
2023-01-23 01:59:58.710008: step: 1952/530, loss: 0.00682830810546875
2023-01-23 01:59:59.827591: step: 1956/530, loss: 0.08938580006361008
2023-01-23 02:00:00.932700: step: 1960/530, loss: 0.16871434450149536
2023-01-23 02:00:02.027084: step: 1964/530, loss: 0.000920200371183455
2023-01-23 02:00:03.166262: step: 1968/530, loss: 0.0002769470156636089
2023-01-23 02:00:04.271563: step: 1972/530, loss: 0.05166321247816086
2023-01-23 02:00:05.389304: step: 1976/530, loss: 0.046921394765377045
2023-01-23 02:00:06.493960: step: 1980/530, loss: 0.0009542942279949784
2023-01-23 02:00:07.614363: step: 1984/530, loss: 0.03886003792285919
2023-01-23 02:00:08.723266: step: 1988/530, loss: 0.012433338910341263
2023-01-23 02:00:09.825025: step: 1992/530, loss: 0.0513768196105957
2023-01-23 02:00:10.933001: step: 1996/530, loss: 0.0006297111394815147
2023-01-23 02:00:12.034357: step: 2000/530, loss: 0.04782819747924805
2023-01-23 02:00:13.152920: step: 2004/530, loss: 0.036470796912908554
2023-01-23 02:00:14.266920: step: 2008/530, loss: 1.2993037700653076
2023-01-23 02:00:15.343146: step: 2012/530, loss: 0.024122904986143112
2023-01-23 02:00:16.469907: step: 2016/530, loss: 0.07287292927503586
2023-01-23 02:00:17.590651: step: 2020/530, loss: 0.007452202029526234
2023-01-23 02:00:18.709842: step: 2024/530, loss: 0.023409079760313034
2023-01-23 02:00:19.826421: step: 2028/530, loss: 0.028469443321228027
2023-01-23 02:00:20.931824: step: 2032/530, loss: 0.03767271339893341
2023-01-23 02:00:22.043616: step: 2036/530, loss: 0.028090573847293854
2023-01-23 02:00:23.161006: step: 2040/530, loss: 0.0036323547828942537
2023-01-23 02:00:24.280057: step: 2044/530, loss: 0.04720459133386612
2023-01-23 02:00:25.383229: step: 2048/530, loss: 0.04097576066851616
2023-01-23 02:00:26.483882: step: 2052/530, loss: 0.003047657199203968
2023-01-23 02:00:27.570380: step: 2056/530, loss: 0.695419430732727
2023-01-23 02:00:28.658844: step: 2060/530, loss: 0.0984870195388794
2023-01-23 02:00:29.723833: step: 2064/530, loss: 0.05054507404565811
2023-01-23 02:00:30.821103: step: 2068/530, loss: 0.040987778455019
2023-01-23 02:00:31.932104: step: 2072/530, loss: 0.03736119344830513
2023-01-23 02:00:33.051457: step: 2076/530, loss: 0.001831150148063898
2023-01-23 02:00:34.173566: step: 2080/530, loss: 0.05985241010785103
2023-01-23 02:00:35.289349: step: 2084/530, loss: 0.00640482921153307
2023-01-23 02:00:36.405143: step: 2088/530, loss: 0.025707054883241653
2023-01-23 02:00:37.490785: step: 2092/530, loss: 0.09310808032751083
2023-01-23 02:00:38.595141: step: 2096/530, loss: 0.029081057757139206
2023-01-23 02:00:39.722326: step: 2100/530, loss: 0.013036632910370827
2023-01-23 02:00:40.845245: step: 2104/530, loss: 0.031297825276851654
2023-01-23 02:00:41.954968: step: 2108/530, loss: 0.04550447687506676
2023-01-23 02:00:43.074111: step: 2112/530, loss: 0.04033670201897621
2023-01-23 02:00:44.180716: step: 2116/530, loss: 0.05769810825586319
2023-01-23 02:00:45.307029: step: 2120/530, loss: 0.06925149261951447
==================================================
Loss: 0.045
--------------------
Dev: {'event': {'p': 0.5871369294605809, 'r': 0.7536617842876165, 'f1': 0.660058309037901}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 14}
Test: {'event': {'p': 0.648320895522388, 'r': 0.8100233100233101, 'f1': 0.7202072538860103}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 14}
Chinese: {'event': {'p': 0.581081081081081, 'r': 0.7962962962962963, 'f1': 0.6718749999999999}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 14}
Korean: {'event': {'p': 0.7115384615384616, 'r': 0.5873015873015873, 'f1': 0.6434782608695652}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 14}
Russian: {'event': {'p': 0.4523809523809524, 'r': 0.5277777777777778, 'f1': 0.4871794871794871}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 14}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6449771689497716, 'r': 0.7523302263648469, 'f1': 0.6945298094652735}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Chinese: {'event': {'p': 0.6692644909887969, 'r': 0.8006993006993007, 'f1': 0.7291058636243036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Chinese: {'event': {'p': 0.6764705882352942, 'r': 0.8518518518518519, 'f1': 0.7540983606557378}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6449771689497716, 'r': 0.7523302263648469, 'f1': 0.6945298094652735}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Korean: {'event': {'p': 0.6692644909887969, 'r': 0.8006993006993007, 'f1': 0.7291058636243036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Korean: {'event': {'p': 0.7391304347826086, 'r': 0.5396825396825397, 'f1': 0.6238532110091742}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5971370143149284, 'r': 0.7776298268974701, 'f1': 0.6755349913244649}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Russian: {'event': {'p': 0.6401673640167364, 'r': 0.8024475524475524, 'f1': 0.7121799844840963}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Russian: {'event': {'p': 0.5897435897435898, 'r': 0.6388888888888888, 'f1': 0.6133333333333332}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
******************************
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 02:01:24.767998: step: 4/530, loss: 0.03840242326259613
2023-01-23 02:01:25.879249: step: 8/530, loss: 0.009069633670151234
2023-01-23 02:01:26.995575: step: 12/530, loss: 0.006418037693947554
2023-01-23 02:01:28.103115: step: 16/530, loss: 0.00023794174194335938
2023-01-23 02:01:29.221511: step: 20/530, loss: 0.024641182273626328
2023-01-23 02:01:30.319593: step: 24/530, loss: 0.0530790314078331
2023-01-23 02:01:31.419932: step: 28/530, loss: 0.007640648167580366
2023-01-23 02:01:32.511616: step: 32/530, loss: 0.011955547146499157
2023-01-23 02:01:33.593650: step: 36/530, loss: 0.040782734751701355
2023-01-23 02:01:34.693754: step: 40/530, loss: 0.000847935676574707
2023-01-23 02:01:35.794122: step: 44/530, loss: 0.034110214561223984
2023-01-23 02:01:36.926001: step: 48/530, loss: 0.007599306292831898
2023-01-23 02:01:38.046022: step: 52/530, loss: 0.002668237779289484
2023-01-23 02:01:39.211610: step: 56/530, loss: 0.02303457260131836
2023-01-23 02:01:40.274913: step: 60/530, loss: 0.008165931329131126
2023-01-23 02:01:41.371913: step: 64/530, loss: 0.0008536339155398309
2023-01-23 02:01:42.461659: step: 68/530, loss: 0.005838251207023859
2023-01-23 02:01:43.560793: step: 72/530, loss: 0.02844543568789959
2023-01-23 02:01:44.653485: step: 76/530, loss: 0.04478492960333824
2023-01-23 02:01:45.794491: step: 80/530, loss: 4.138946678722277e-05
2023-01-23 02:01:46.903678: step: 84/530, loss: 0.0214754119515419
2023-01-23 02:01:48.020529: step: 88/530, loss: 0.005344104953110218
2023-01-23 02:01:49.158083: step: 92/530, loss: 0.037993647158145905
2023-01-23 02:01:50.251817: step: 96/530, loss: 3.0243398214224726e-05
2023-01-23 02:01:51.384774: step: 100/530, loss: 0.0031784535385668278
2023-01-23 02:01:52.477341: step: 104/530, loss: 0.003102970076724887
2023-01-23 02:01:53.569864: step: 108/530, loss: 0.010702324099838734
2023-01-23 02:01:54.673743: step: 112/530, loss: 0.018754959106445312
2023-01-23 02:01:55.770953: step: 116/530, loss: 0.0634412094950676
2023-01-23 02:01:56.867713: step: 120/530, loss: 0.04991002380847931
2023-01-23 02:01:57.979818: step: 124/530, loss: 0.015558863058686256
2023-01-23 02:01:59.084473: step: 128/530, loss: 0.002147102262824774
2023-01-23 02:02:00.216249: step: 132/530, loss: 0.00147247314453125
2023-01-23 02:02:01.319406: step: 136/530, loss: 0.028916455805301666
2023-01-23 02:02:02.422910: step: 140/530, loss: 0.004498386289924383
2023-01-23 02:02:03.516464: step: 144/530, loss: 0.0010434150462970138
2023-01-23 02:02:04.604722: step: 148/530, loss: 0.04522104188799858
2023-01-23 02:02:05.704904: step: 152/530, loss: 0.011435126885771751
2023-01-23 02:02:06.802092: step: 156/530, loss: 6.771087646484375e-05
2023-01-23 02:02:07.909034: step: 160/530, loss: 0.03163528069853783
2023-01-23 02:02:08.985791: step: 164/530, loss: 0.008217906579375267
2023-01-23 02:02:10.084713: step: 168/530, loss: 0.003614234970882535
2023-01-23 02:02:11.221281: step: 172/530, loss: 0.044017985463142395
2023-01-23 02:02:12.362482: step: 176/530, loss: 0.0057722097262740135
2023-01-23 02:02:13.461922: step: 180/530, loss: 0.0001218795805471018
2023-01-23 02:02:14.571243: step: 184/530, loss: 0.00022239684767555445
2023-01-23 02:02:15.684509: step: 188/530, loss: 0.04460444673895836
2023-01-23 02:02:16.764401: step: 192/530, loss: 0.01856975629925728
2023-01-23 02:02:17.872079: step: 196/530, loss: 0.012131595984101295
2023-01-23 02:02:18.974918: step: 200/530, loss: 0.003978061955422163
2023-01-23 02:02:20.073627: step: 204/530, loss: 0.007702064234763384
2023-01-23 02:02:21.179396: step: 208/530, loss: 0.014125823974609375
2023-01-23 02:02:22.299723: step: 212/530, loss: 0.015476226806640625
2023-01-23 02:02:23.410908: step: 216/530, loss: 0.0036568641662597656
2023-01-23 02:02:24.550767: step: 220/530, loss: 0.025734614580869675
2023-01-23 02:02:25.678739: step: 224/530, loss: 0.018188001587986946
2023-01-23 02:02:26.769415: step: 228/530, loss: 0.022769736126065254
2023-01-23 02:02:27.887859: step: 232/530, loss: 0.027862204238772392
2023-01-23 02:02:28.971786: step: 236/530, loss: 0.05745887756347656
2023-01-23 02:02:30.061444: step: 240/530, loss: 0.025739002972841263
2023-01-23 02:02:31.147663: step: 244/530, loss: 1.544952465337701e-05
2023-01-23 02:02:32.261690: step: 248/530, loss: 0.04292182996869087
2023-01-23 02:02:33.362126: step: 252/530, loss: 0.026149630546569824
2023-01-23 02:02:34.487161: step: 256/530, loss: 0.005676746368408203
2023-01-23 02:02:35.579963: step: 260/530, loss: 0.003265380859375
2023-01-23 02:02:36.676033: step: 264/530, loss: 0.065595343708992
2023-01-23 02:02:37.778218: step: 268/530, loss: 0.005357789807021618
2023-01-23 02:02:38.886416: step: 272/530, loss: 0.018476469442248344
2023-01-23 02:02:39.968198: step: 276/530, loss: 0.008679008111357689
2023-01-23 02:02:41.079204: step: 280/530, loss: 0.0465240515768528
2023-01-23 02:02:42.179131: step: 284/530, loss: 0.05339546501636505
2023-01-23 02:02:43.294996: step: 288/530, loss: 0.016270209103822708
2023-01-23 02:02:44.392680: step: 292/530, loss: 0.016114234924316406
2023-01-23 02:02:45.495204: step: 296/530, loss: 0.02471294440329075
2023-01-23 02:02:46.568654: step: 300/530, loss: 0.0001739501894917339
2023-01-23 02:02:47.661038: step: 304/530, loss: 0.0020293237175792456
2023-01-23 02:02:48.791430: step: 308/530, loss: 0.09704923629760742
2023-01-23 02:02:49.874819: step: 312/530, loss: 0.019133806228637695
2023-01-23 02:02:50.977070: step: 316/530, loss: 0.01810932159423828
2023-01-23 02:02:52.074398: step: 320/530, loss: 0.003530168440192938
2023-01-23 02:02:53.193465: step: 324/530, loss: 0.0002617835998535156
2023-01-23 02:02:54.315095: step: 328/530, loss: 0.013393307104706764
2023-01-23 02:02:55.408900: step: 332/530, loss: 0.03494396060705185
2023-01-23 02:02:56.556104: step: 336/530, loss: 0.0034837722778320312
2023-01-23 02:02:57.638120: step: 340/530, loss: 0.02880272828042507
2023-01-23 02:02:58.753093: step: 344/530, loss: 0.003423309186473489
2023-01-23 02:02:59.858070: step: 348/530, loss: 0.017697572708129883
2023-01-23 02:03:00.986050: step: 352/530, loss: 0.007029914762824774
2023-01-23 02:03:02.087661: step: 356/530, loss: 0.0052734375931322575
2023-01-23 02:03:03.175191: step: 360/530, loss: 0.015992354601621628
2023-01-23 02:03:04.294061: step: 364/530, loss: 0.0542660728096962
2023-01-23 02:03:05.414617: step: 368/530, loss: 0.004149436950683594
2023-01-23 02:03:06.508395: step: 372/530, loss: 0.010693073272705078
2023-01-23 02:03:07.635023: step: 376/530, loss: 0.010441207326948643
2023-01-23 02:03:08.750920: step: 380/530, loss: 0.005313968751579523
2023-01-23 02:03:09.853541: step: 384/530, loss: 0.04609241336584091
2023-01-23 02:03:10.970467: step: 388/530, loss: 0.022980879992246628
2023-01-23 02:03:12.106272: step: 392/530, loss: 0.0005656242719851434
2023-01-23 02:03:13.214350: step: 396/530, loss: 0.02291107177734375
2023-01-23 02:03:14.324582: step: 400/530, loss: 0.04540662840008736
2023-01-23 02:03:15.417544: step: 404/530, loss: 0.05089666694402695
2023-01-23 02:03:16.530472: step: 408/530, loss: 0.0479000099003315
2023-01-23 02:03:17.601382: step: 412/530, loss: 0.03380577638745308
2023-01-23 02:03:18.725461: step: 416/530, loss: 0.052324485033750534
2023-01-23 02:03:19.845137: step: 420/530, loss: 0.014741898514330387
2023-01-23 02:03:20.953078: step: 424/530, loss: 0.05988769605755806
2023-01-23 02:03:22.044420: step: 428/530, loss: 0.025874996557831764
2023-01-23 02:03:23.145542: step: 432/530, loss: 0.0030241012573242188
2023-01-23 02:03:24.235091: step: 436/530, loss: 0.012413645163178444
2023-01-23 02:03:25.347041: step: 440/530, loss: 0.023438835516572
2023-01-23 02:03:26.445719: step: 444/530, loss: 0.0017874717013910413
2023-01-23 02:03:27.524901: step: 448/530, loss: 0.007959174923598766
2023-01-23 02:03:28.643598: step: 452/530, loss: 0.012431908398866653
2023-01-23 02:03:29.733550: step: 456/530, loss: 0.005193615332245827
2023-01-23 02:03:30.839075: step: 460/530, loss: 0.07342529296875
2023-01-23 02:03:31.940111: step: 464/530, loss: 0.01830902136862278
2023-01-23 02:03:33.042153: step: 468/530, loss: 0.12217597663402557
2023-01-23 02:03:34.152083: step: 472/530, loss: 0.012664414942264557
2023-01-23 02:03:35.262588: step: 476/530, loss: 0.010254954919219017
2023-01-23 02:03:36.372316: step: 480/530, loss: 0.00870370864868164
2023-01-23 02:03:37.496118: step: 484/530, loss: 0.03427162021398544
2023-01-23 02:03:38.587770: step: 488/530, loss: 0.03593731299042702
2023-01-23 02:03:39.689534: step: 492/530, loss: 0.016793059185147285
2023-01-23 02:03:40.837787: step: 496/530, loss: 0.01389703806489706
2023-01-23 02:03:41.954808: step: 500/530, loss: 0.0063329702243208885
2023-01-23 02:03:43.073103: step: 504/530, loss: 0.612633228302002
2023-01-23 02:03:44.176644: step: 508/530, loss: 0.03549759462475777
2023-01-23 02:03:45.302591: step: 512/530, loss: 0.15078334510326385
2023-01-23 02:03:46.379102: step: 516/530, loss: 0.002058267593383789
2023-01-23 02:03:47.497730: step: 520/530, loss: 0.004456329625099897
2023-01-23 02:03:48.594212: step: 524/530, loss: 0.001306819962337613
2023-01-23 02:03:49.680892: step: 528/530, loss: 0.0025599480140954256
2023-01-23 02:03:50.787858: step: 532/530, loss: 0.03457145765423775
2023-01-23 02:03:51.889764: step: 536/530, loss: 0.08291168510913849
2023-01-23 02:03:53.002287: step: 540/530, loss: 0.09893875569105148
2023-01-23 02:03:54.100042: step: 544/530, loss: 0.05193014442920685
2023-01-23 02:03:55.231444: step: 548/530, loss: 0.026662444695830345
2023-01-23 02:03:56.368475: step: 552/530, loss: 0.0039231302216649055
2023-01-23 02:03:57.471394: step: 556/530, loss: 0.0011560439597815275
2023-01-23 02:03:58.553914: step: 560/530, loss: 0.02017073705792427
2023-01-23 02:03:59.649175: step: 564/530, loss: 0.017523575574159622
2023-01-23 02:04:00.769707: step: 568/530, loss: 0.05107874795794487
2023-01-23 02:04:01.863022: step: 572/530, loss: 0.03371162340044975
2023-01-23 02:04:02.995890: step: 576/530, loss: 0.015005683526396751
2023-01-23 02:04:04.109026: step: 580/530, loss: 0.0010227203601971269
2023-01-23 02:04:05.230643: step: 584/530, loss: 0.0069373128935694695
2023-01-23 02:04:06.338767: step: 588/530, loss: 0.0036689757835119963
2023-01-23 02:04:07.425197: step: 592/530, loss: 0.01164999045431614
2023-01-23 02:04:08.546273: step: 596/530, loss: 0.0009566307417117059
2023-01-23 02:04:09.681476: step: 600/530, loss: 0.10820828378200531
2023-01-23 02:04:10.761319: step: 604/530, loss: 0.02452840842306614
2023-01-23 02:04:11.854170: step: 608/530, loss: 0.032178595662117004
2023-01-23 02:04:12.961209: step: 612/530, loss: 0.03753180801868439
2023-01-23 02:04:14.080632: step: 616/530, loss: 0.008643722161650658
2023-01-23 02:04:15.191002: step: 620/530, loss: 0.00036826133145950735
2023-01-23 02:04:16.293934: step: 624/530, loss: 0.0019894361030310392
2023-01-23 02:04:17.400256: step: 628/530, loss: 0.012667560949921608
2023-01-23 02:04:18.532096: step: 632/530, loss: 0.0326550267636776
2023-01-23 02:04:19.671977: step: 636/530, loss: 0.02403888665139675
2023-01-23 02:04:20.810146: step: 640/530, loss: 0.00953369215130806
2023-01-23 02:04:21.887251: step: 644/530, loss: 0.021070100367069244
2023-01-23 02:04:23.011052: step: 648/530, loss: 0.0033937455154955387
2023-01-23 02:04:24.126303: step: 652/530, loss: 0.031713105738162994
2023-01-23 02:04:25.208163: step: 656/530, loss: 0.012997722253203392
2023-01-23 02:04:26.285855: step: 660/530, loss: 0.004050063900649548
2023-01-23 02:04:27.397998: step: 664/530, loss: 0.045154571533203125
2023-01-23 02:04:28.542632: step: 668/530, loss: 0.008099079132080078
2023-01-23 02:04:29.655477: step: 672/530, loss: 0.005531025119125843
2023-01-23 02:04:30.771545: step: 676/530, loss: 0.01414504088461399
2023-01-23 02:04:31.866254: step: 680/530, loss: 0.0023255348205566406
2023-01-23 02:04:33.006913: step: 684/530, loss: 0.05395030975341797
2023-01-23 02:04:34.119641: step: 688/530, loss: 0.00413126964122057
2023-01-23 02:04:35.249313: step: 692/530, loss: 0.020533179864287376
2023-01-23 02:04:36.332515: step: 696/530, loss: 0.008992671966552734
2023-01-23 02:04:37.418847: step: 700/530, loss: 0.005629253573715687
2023-01-23 02:04:38.520121: step: 704/530, loss: 0.036220453679561615
2023-01-23 02:04:39.619226: step: 708/530, loss: 0.015161609277129173
2023-01-23 02:04:40.774129: step: 712/530, loss: 0.34428828954696655
2023-01-23 02:04:41.871800: step: 716/530, loss: 0.05602912977337837
2023-01-23 02:04:42.972220: step: 720/530, loss: 0.0003578186151571572
2023-01-23 02:04:44.087759: step: 724/530, loss: 0.008083343505859375
2023-01-23 02:04:45.218966: step: 728/530, loss: 0.003274965099990368
2023-01-23 02:04:46.314683: step: 732/530, loss: 0.059556201100349426
2023-01-23 02:04:47.421284: step: 736/530, loss: 0.014365101233124733
2023-01-23 02:04:48.532952: step: 740/530, loss: 0.0006901741144247353
2023-01-23 02:04:49.645542: step: 744/530, loss: 0.019325971603393555
2023-01-23 02:04:50.756899: step: 748/530, loss: 0.05002956464886665
2023-01-23 02:04:51.891207: step: 752/530, loss: 0.015990352258086205
2023-01-23 02:04:52.996177: step: 756/530, loss: 0.00857400894165039
2023-01-23 02:04:54.138243: step: 760/530, loss: 0.0022113800514489412
2023-01-23 02:04:55.240443: step: 764/530, loss: 0.00019302369037177414
2023-01-23 02:04:56.346869: step: 768/530, loss: 0.08483857661485672
2023-01-23 02:04:57.437452: step: 772/530, loss: 0.014361190609633923
2023-01-23 02:04:58.540689: step: 776/530, loss: 0.13020524382591248
2023-01-23 02:04:59.654933: step: 780/530, loss: 0.5335664749145508
2023-01-23 02:05:00.767034: step: 784/530, loss: 0.033621788024902344
2023-01-23 02:05:01.865612: step: 788/530, loss: 0.007825278677046299
2023-01-23 02:05:02.993681: step: 792/530, loss: 0.02518320083618164
2023-01-23 02:05:04.072442: step: 796/530, loss: 0.12295150756835938
2023-01-23 02:05:05.164299: step: 800/530, loss: 0.03141040727496147
2023-01-23 02:05:06.265963: step: 804/530, loss: 0.004620742984116077
2023-01-23 02:05:07.353213: step: 808/530, loss: 0.010891055688261986
2023-01-23 02:05:08.485371: step: 812/530, loss: 0.03944864124059677
2023-01-23 02:05:09.581923: step: 816/530, loss: 0.045034077018499374
2023-01-23 02:05:10.693468: step: 820/530, loss: 0.0368741974234581
2023-01-23 02:05:11.829125: step: 824/530, loss: 0.00417981157079339
2023-01-23 02:05:12.907206: step: 828/530, loss: 0.019805049523711205
2023-01-23 02:05:14.008441: step: 832/530, loss: 0.02046079747378826
2023-01-23 02:05:15.127582: step: 836/530, loss: 0.03033618815243244
2023-01-23 02:05:16.225775: step: 840/530, loss: 0.07592006027698517
2023-01-23 02:05:17.327133: step: 844/530, loss: 0.002530002733692527
2023-01-23 02:05:18.474883: step: 848/530, loss: 0.009886790066957474
2023-01-23 02:05:19.575418: step: 852/530, loss: 0.06473427265882492
2023-01-23 02:05:20.693675: step: 856/530, loss: 0.0004981040838174522
2023-01-23 02:05:21.824014: step: 860/530, loss: 0.0020929337479174137
2023-01-23 02:05:22.967887: step: 864/530, loss: 0.002754306886345148
2023-01-23 02:05:24.123341: step: 868/530, loss: 0.01937265321612358
2023-01-23 02:05:25.214698: step: 872/530, loss: 0.003805398941040039
2023-01-23 02:05:26.340859: step: 876/530, loss: 0.0018307685386389494
2023-01-23 02:05:27.438653: step: 880/530, loss: 0.03172473981976509
2023-01-23 02:05:28.582192: step: 884/530, loss: 0.01272659283131361
2023-01-23 02:05:29.685424: step: 888/530, loss: 0.0021369934547692537
2023-01-23 02:05:30.783963: step: 892/530, loss: 0.0118598947301507
2023-01-23 02:05:31.890298: step: 896/530, loss: 0.027636097744107246
2023-01-23 02:05:33.035800: step: 900/530, loss: 0.004925918765366077
2023-01-23 02:05:34.168341: step: 904/530, loss: 0.0002288818359375
2023-01-23 02:05:35.270362: step: 908/530, loss: 0.02348318137228489
2023-01-23 02:05:36.362275: step: 912/530, loss: 7.82012939453125e-05
2023-01-23 02:05:37.465737: step: 916/530, loss: 0.007669543847441673
2023-01-23 02:05:38.562211: step: 920/530, loss: 2.47955322265625e-05
2023-01-23 02:05:39.646112: step: 924/530, loss: 0.15422238409519196
2023-01-23 02:05:40.790614: step: 928/530, loss: 0.03189344331622124
2023-01-23 02:05:41.915475: step: 932/530, loss: 0.009030628018081188
2023-01-23 02:05:43.020258: step: 936/530, loss: 0.028885841369628906
2023-01-23 02:05:44.162714: step: 940/530, loss: 0.01490101870149374
2023-01-23 02:05:45.286025: step: 944/530, loss: 0.02431516721844673
2023-01-23 02:05:46.391865: step: 948/530, loss: 0.07218370586633682
2023-01-23 02:05:47.524395: step: 952/530, loss: 0.05511894449591637
2023-01-23 02:05:48.635444: step: 956/530, loss: 0.026274681091308594
2023-01-23 02:05:49.746015: step: 960/530, loss: 0.009793853387236595
2023-01-23 02:05:50.830771: step: 964/530, loss: 0.01799640618264675
2023-01-23 02:05:51.959110: step: 968/530, loss: 0.03685379400849342
2023-01-23 02:05:53.090361: step: 972/530, loss: 0.04366359859704971
2023-01-23 02:05:54.204426: step: 976/530, loss: 0.0006680488586425781
2023-01-23 02:05:55.303808: step: 980/530, loss: 0.03017336316406727
2023-01-23 02:05:56.406596: step: 984/530, loss: 0.05321183428168297
2023-01-23 02:05:57.504667: step: 988/530, loss: 0.0317266471683979
2023-01-23 02:05:58.633915: step: 992/530, loss: 0.05910377576947212
2023-01-23 02:05:59.739632: step: 996/530, loss: 0.06197796016931534
2023-01-23 02:06:00.862627: step: 1000/530, loss: 0.00122489919885993
2023-01-23 02:06:01.968824: step: 1004/530, loss: 0.009475327096879482
2023-01-23 02:06:03.071061: step: 1008/530, loss: 0.005061936564743519
2023-01-23 02:06:04.166024: step: 1012/530, loss: 0.06972198188304901
2023-01-23 02:06:05.271119: step: 1016/530, loss: 0.0006240844959393144
2023-01-23 02:06:06.357370: step: 1020/530, loss: 0.04617580398917198
2023-01-23 02:06:07.438981: step: 1024/530, loss: 0.006876469124108553
2023-01-23 02:06:08.579263: step: 1028/530, loss: 0.0519350990653038
2023-01-23 02:06:09.682136: step: 1032/530, loss: 0.011633205227553844
2023-01-23 02:06:10.816639: step: 1036/530, loss: 0.017735058441758156
2023-01-23 02:06:11.921308: step: 1040/530, loss: 0.04231987148523331
2023-01-23 02:06:13.033568: step: 1044/530, loss: 0.014898204244673252
2023-01-23 02:06:14.139668: step: 1048/530, loss: 0.022055961191654205
2023-01-23 02:06:15.249638: step: 1052/530, loss: 0.0467718169093132
2023-01-23 02:06:16.320353: step: 1056/530, loss: 0.009108162485063076
2023-01-23 02:06:17.403549: step: 1060/530, loss: 0.018407821655273438
2023-01-23 02:06:18.492430: step: 1064/530, loss: 0.023163510486483574
2023-01-23 02:06:19.602592: step: 1068/530, loss: 0.015588188543915749
2023-01-23 02:06:20.729573: step: 1072/530, loss: 0.01715545728802681
2023-01-23 02:06:21.810165: step: 1076/530, loss: 0.004157352726906538
2023-01-23 02:06:22.950886: step: 1080/530, loss: 0.10756760090589523
2023-01-23 02:06:24.044123: step: 1084/530, loss: 0.007722282316535711
2023-01-23 02:06:25.154701: step: 1088/530, loss: 0.25852030515670776
2023-01-23 02:06:26.302300: step: 1092/530, loss: 0.0028404234908521175
2023-01-23 02:06:27.391450: step: 1096/530, loss: 0.02288227155804634
2023-01-23 02:06:28.483054: step: 1100/530, loss: 0.03561963886022568
2023-01-23 02:06:29.572865: step: 1104/530, loss: 0.02105865441262722
2023-01-23 02:06:30.675265: step: 1108/530, loss: 0.02662849612534046
2023-01-23 02:06:31.800981: step: 1112/530, loss: 0.06679821014404297
2023-01-23 02:06:32.924770: step: 1116/530, loss: 0.02941122092306614
2023-01-23 02:06:34.023270: step: 1120/530, loss: 0.0052242279052734375
2023-01-23 02:06:35.165501: step: 1124/530, loss: 0.000965118408203125
2023-01-23 02:06:36.264920: step: 1128/530, loss: 0.003691721009090543
2023-01-23 02:06:37.343500: step: 1132/530, loss: 0.054492950439453125
2023-01-23 02:06:38.468686: step: 1136/530, loss: 0.015259837731719017
2023-01-23 02:06:39.555827: step: 1140/530, loss: 0.0229174941778183
2023-01-23 02:06:40.649578: step: 1144/530, loss: 0.0075460439547896385
2023-01-23 02:06:41.769651: step: 1148/530, loss: 0.022366667166352272
2023-01-23 02:06:42.855478: step: 1152/530, loss: 0.013931477442383766
2023-01-23 02:06:43.962290: step: 1156/530, loss: 0.0032839300110936165
2023-01-23 02:06:45.054994: step: 1160/530, loss: 0.02798900566995144
2023-01-23 02:06:46.146708: step: 1164/530, loss: 0.022859765216708183
2023-01-23 02:06:47.231710: step: 1168/530, loss: 0.0017206191550940275
2023-01-23 02:06:48.350788: step: 1172/530, loss: 0.008795070461928844
2023-01-23 02:06:49.468055: step: 1176/530, loss: 0.21655330061912537
2023-01-23 02:06:50.576116: step: 1180/530, loss: 0.02131366729736328
2023-01-23 02:06:51.708431: step: 1184/530, loss: 0.06843052059412003
2023-01-23 02:06:52.827985: step: 1188/530, loss: 0.05016050487756729
2023-01-23 02:06:53.931952: step: 1192/530, loss: 0.05927343666553497
2023-01-23 02:06:55.044387: step: 1196/530, loss: 0.0058654784224927425
2023-01-23 02:06:56.132297: step: 1200/530, loss: 0.1620623618364334
2023-01-23 02:06:57.244388: step: 1204/530, loss: 0.0029786110389977694
2023-01-23 02:06:58.365374: step: 1208/530, loss: 0.00979471206665039
2023-01-23 02:06:59.482976: step: 1212/530, loss: 0.009833144955337048
2023-01-23 02:07:00.616849: step: 1216/530, loss: 0.03238401189446449
2023-01-23 02:07:01.722824: step: 1220/530, loss: 0.05477018281817436
2023-01-23 02:07:02.838719: step: 1224/530, loss: 0.015384006313979626
2023-01-23 02:07:03.961654: step: 1228/530, loss: 0.05691862106323242
2023-01-23 02:07:05.078279: step: 1232/530, loss: 0.02624073065817356
2023-01-23 02:07:06.237955: step: 1236/530, loss: 0.024321652948856354
2023-01-23 02:07:07.355588: step: 1240/530, loss: 0.0011670112144201994
2023-01-23 02:07:08.491541: step: 1244/530, loss: 0.13921470940113068
2023-01-23 02:07:09.579500: step: 1248/530, loss: 0.0004746437189169228
2023-01-23 02:07:10.704546: step: 1252/530, loss: 0.08361601829528809
2023-01-23 02:07:11.860876: step: 1256/530, loss: 0.03683442994952202
2023-01-23 02:07:12.952850: step: 1260/530, loss: 0.01796703413128853
2023-01-23 02:07:14.031335: step: 1264/530, loss: 0.0005685806390829384
2023-01-23 02:07:15.167942: step: 1268/530, loss: 0.012295866385102272
2023-01-23 02:07:16.303940: step: 1272/530, loss: 0.024425983428955078
2023-01-23 02:07:17.419888: step: 1276/530, loss: 0.0015705585246905684
2023-01-23 02:07:18.569691: step: 1280/530, loss: 0.013979816809296608
2023-01-23 02:07:19.677941: step: 1284/530, loss: 0.01157372072339058
2023-01-23 02:07:20.791311: step: 1288/530, loss: 0.2807699143886566
2023-01-23 02:07:21.932388: step: 1292/530, loss: 0.005910873878747225
2023-01-23 02:07:23.057763: step: 1296/530, loss: 0.003741645719856024
2023-01-23 02:07:24.184248: step: 1300/530, loss: 0.21141962707042694
2023-01-23 02:07:25.311070: step: 1304/530, loss: 0.042479708790779114
2023-01-23 02:07:26.427151: step: 1308/530, loss: 0.1723569929599762
2023-01-23 02:07:27.539152: step: 1312/530, loss: 0.09767894446849823
2023-01-23 02:07:28.675375: step: 1316/530, loss: 0.039337158203125
2023-01-23 02:07:29.794327: step: 1320/530, loss: 0.0754978209733963
2023-01-23 02:07:30.863123: step: 1324/530, loss: 0.004464626312255859
2023-01-23 02:07:31.983988: step: 1328/530, loss: 0.04487276077270508
2023-01-23 02:07:33.106959: step: 1332/530, loss: 0.009469224140048027
2023-01-23 02:07:34.210805: step: 1336/530, loss: 0.01969289779663086
2023-01-23 02:07:35.346942: step: 1340/530, loss: 0.07884535938501358
2023-01-23 02:07:36.436641: step: 1344/530, loss: 0.05041675642132759
2023-01-23 02:07:37.540241: step: 1348/530, loss: 0.023331500589847565
2023-01-23 02:07:38.651766: step: 1352/530, loss: 0.06804981827735901
2023-01-23 02:07:39.742701: step: 1356/530, loss: 0.006998634431511164
2023-01-23 02:07:40.863075: step: 1360/530, loss: 0.037338923662900925
2023-01-23 02:07:41.990877: step: 1364/530, loss: 0.04044532775878906
2023-01-23 02:07:43.095983: step: 1368/530, loss: 0.04161481931805611
2023-01-23 02:07:44.181149: step: 1372/530, loss: 0.6274380683898926
2023-01-23 02:07:45.275243: step: 1376/530, loss: 0.06226787716150284
2023-01-23 02:07:46.373800: step: 1380/530, loss: 0.0027858258690685034
2023-01-23 02:07:47.519527: step: 1384/530, loss: 0.009277534671127796
2023-01-23 02:07:48.646494: step: 1388/530, loss: 0.023471739143133163
2023-01-23 02:07:49.752354: step: 1392/530, loss: 0.010932731442153454
2023-01-23 02:07:50.838253: step: 1396/530, loss: 0.033903125673532486
2023-01-23 02:07:51.930983: step: 1400/530, loss: 0.004085254389792681
2023-01-23 02:07:53.039757: step: 1404/530, loss: 0.012323570437729359
2023-01-23 02:07:54.132951: step: 1408/530, loss: 0.0011724949581548572
2023-01-23 02:07:55.249335: step: 1412/530, loss: 0.044562362134456635
2023-01-23 02:07:56.346426: step: 1416/530, loss: 0.0334782600402832
2023-01-23 02:07:57.444932: step: 1420/530, loss: 0.0332433246076107
2023-01-23 02:07:58.564669: step: 1424/530, loss: 0.03523731231689453
2023-01-23 02:07:59.684391: step: 1428/530, loss: 0.004351711366325617
2023-01-23 02:08:00.829342: step: 1432/530, loss: 0.008992379531264305
2023-01-23 02:08:01.959059: step: 1436/530, loss: 0.03551445156335831
2023-01-23 02:08:03.082606: step: 1440/530, loss: 0.008700896054506302
2023-01-23 02:08:04.209979: step: 1444/530, loss: 0.03925041854381561
2023-01-23 02:08:05.328452: step: 1448/530, loss: 0.002571630524471402
2023-01-23 02:08:06.443351: step: 1452/530, loss: 0.01748218573629856
2023-01-23 02:08:07.599686: step: 1456/530, loss: 0.00038423537625931203
2023-01-23 02:08:08.708730: step: 1460/530, loss: 0.11973171681165695
2023-01-23 02:08:09.825570: step: 1464/530, loss: 0.02832183800637722
2023-01-23 02:08:10.910615: step: 1468/530, loss: 0.03799581527709961
2023-01-23 02:08:12.032987: step: 1472/530, loss: 0.07473854720592499
2023-01-23 02:08:13.118291: step: 1476/530, loss: 0.005482101812958717
2023-01-23 02:08:14.227535: step: 1480/530, loss: 0.00017824172391556203
2023-01-23 02:08:15.330902: step: 1484/530, loss: 0.0015570640098303556
2023-01-23 02:08:16.436646: step: 1488/530, loss: 0.003506946610286832
2023-01-23 02:08:17.514810: step: 1492/530, loss: 0.09422293305397034
2023-01-23 02:08:18.645682: step: 1496/530, loss: 0.007080745883285999
2023-01-23 02:08:19.779122: step: 1500/530, loss: 0.0014700889587402344
2023-01-23 02:08:20.892924: step: 1504/530, loss: 0.031247805804014206
2023-01-23 02:08:22.002281: step: 1508/530, loss: 0.09658461064100266
2023-01-23 02:08:23.085075: step: 1512/530, loss: 0.044455386698246
2023-01-23 02:08:24.204239: step: 1516/530, loss: 0.03336143493652344
2023-01-23 02:08:25.324228: step: 1520/530, loss: 0.012038039974868298
2023-01-23 02:08:26.410043: step: 1524/530, loss: 0.4502524435520172
2023-01-23 02:08:27.495790: step: 1528/530, loss: 0.025072479620575905
2023-01-23 02:08:28.604682: step: 1532/530, loss: 0.007258415222167969
2023-01-23 02:08:29.718327: step: 1536/530, loss: 0.004117202945053577
2023-01-23 02:08:30.850819: step: 1540/530, loss: 0.001439905259758234
2023-01-23 02:08:32.003053: step: 1544/530, loss: 0.009568024426698685
2023-01-23 02:08:33.112109: step: 1548/530, loss: 0.0367489829659462
2023-01-23 02:08:34.216834: step: 1552/530, loss: 0.003459978150203824
2023-01-23 02:08:35.339822: step: 1556/530, loss: 0.014469528570771217
2023-01-23 02:08:36.447747: step: 1560/530, loss: 0.026285268366336823
2023-01-23 02:08:37.563075: step: 1564/530, loss: 0.010631131939589977
2023-01-23 02:08:38.674378: step: 1568/530, loss: 0.06253137439489365
2023-01-23 02:08:39.801210: step: 1572/530, loss: 0.0058743953704833984
2023-01-23 02:08:40.896557: step: 1576/530, loss: 0.0008081435807980597
2023-01-23 02:08:42.010462: step: 1580/530, loss: 0.014841699972748756
2023-01-23 02:08:43.125086: step: 1584/530, loss: 0.0303923599421978
2023-01-23 02:08:44.238330: step: 1588/530, loss: 0.020233154296875
2023-01-23 02:08:45.349812: step: 1592/530, loss: 0.00054340367205441
2023-01-23 02:08:46.462284: step: 1596/530, loss: 0.0015866756439208984
2023-01-23 02:08:47.584284: step: 1600/530, loss: 0.023419713601469994
2023-01-23 02:08:48.692054: step: 1604/530, loss: 0.0007610321044921875
2023-01-23 02:08:49.805869: step: 1608/530, loss: 0.008882475085556507
2023-01-23 02:08:50.944094: step: 1612/530, loss: 0.025136185809969902
2023-01-23 02:08:52.057590: step: 1616/530, loss: 0.0573999397456646
2023-01-23 02:08:53.201893: step: 1620/530, loss: 0.06960811465978622
2023-01-23 02:08:54.340705: step: 1624/530, loss: 0.013595867902040482
2023-01-23 02:08:55.434825: step: 1628/530, loss: 0.0018093109829351306
2023-01-23 02:08:56.556697: step: 1632/530, loss: 0.008505702018737793
2023-01-23 02:08:57.679282: step: 1636/530, loss: 0.00020599365234375
2023-01-23 02:08:58.809055: step: 1640/530, loss: 0.04881725460290909
2023-01-23 02:08:59.954418: step: 1644/530, loss: 0.05637397989630699
2023-01-23 02:09:01.077214: step: 1648/530, loss: 0.026079177856445312
2023-01-23 02:09:02.185157: step: 1652/530, loss: 0.0010074615711346269
2023-01-23 02:09:03.385353: step: 1656/530, loss: 0.01110844686627388
2023-01-23 02:09:04.502448: step: 1660/530, loss: 0.028516102582216263
2023-01-23 02:09:05.584182: step: 1664/530, loss: 0.03979663923382759
2023-01-23 02:09:06.698835: step: 1668/530, loss: 1.2816070318222046
2023-01-23 02:09:07.794439: step: 1672/530, loss: 0.02012329176068306
2023-01-23 02:09:08.892972: step: 1676/530, loss: 0.007733821868896484
2023-01-23 02:09:10.019201: step: 1680/530, loss: 0.007509517949074507
2023-01-23 02:09:11.120816: step: 1684/530, loss: 0.0038934231270104647
2023-01-23 02:09:12.206663: step: 1688/530, loss: 0.02810950204730034
2023-01-23 02:09:13.293499: step: 1692/530, loss: 0.044361017644405365
2023-01-23 02:09:14.400807: step: 1696/530, loss: 0.11027304828166962
2023-01-23 02:09:15.528261: step: 1700/530, loss: 5.426407005870715e-05
2023-01-23 02:09:16.638148: step: 1704/530, loss: 0.036669157445430756
2023-01-23 02:09:17.758729: step: 1708/530, loss: 0.043581772595644
2023-01-23 02:09:18.884646: step: 1712/530, loss: 0.023237133398652077
2023-01-23 02:09:19.993003: step: 1716/530, loss: 0.0337887741625309
2023-01-23 02:09:21.079923: step: 1720/530, loss: 0.017784500494599342
2023-01-23 02:09:22.192241: step: 1724/530, loss: 0.0017353057628497481
2023-01-23 02:09:23.283475: step: 1728/530, loss: 0.03257398679852486
2023-01-23 02:09:24.390286: step: 1732/530, loss: 0.002972411923110485
2023-01-23 02:09:25.470870: step: 1736/530, loss: 0.017431069165468216
2023-01-23 02:09:26.623838: step: 1740/530, loss: 0.007779788691550493
2023-01-23 02:09:27.707585: step: 1744/530, loss: 0.06137056648731232
2023-01-23 02:09:28.818998: step: 1748/530, loss: 0.021506119519472122
2023-01-23 02:09:29.925758: step: 1752/530, loss: 0.023546982556581497
2023-01-23 02:09:31.022974: step: 1756/530, loss: 0.004004573915153742
2023-01-23 02:09:32.112240: step: 1760/530, loss: 0.0021692276932299137
2023-01-23 02:09:33.235533: step: 1764/530, loss: 0.0023047446738928556
2023-01-23 02:09:34.392877: step: 1768/530, loss: 0.09165382385253906
2023-01-23 02:09:35.484094: step: 1772/530, loss: 0.07605700939893723
2023-01-23 02:09:36.588594: step: 1776/530, loss: 0.00102910993155092
2023-01-23 02:09:37.689907: step: 1780/530, loss: 0.029495811089873314
2023-01-23 02:09:38.812700: step: 1784/530, loss: 0.012430811300873756
2023-01-23 02:09:39.923607: step: 1788/530, loss: 0.03245430067181587
2023-01-23 02:09:41.035399: step: 1792/530, loss: 0.006335926242172718
2023-01-23 02:09:42.134023: step: 1796/530, loss: 0.0017846107948571444
2023-01-23 02:09:43.256295: step: 1800/530, loss: 0.0445735938847065
2023-01-23 02:09:44.347931: step: 1804/530, loss: 0.011932088062167168
2023-01-23 02:09:45.477061: step: 1808/530, loss: 0.03533673286437988
2023-01-23 02:09:46.570160: step: 1812/530, loss: 0.019838904961943626
2023-01-23 02:09:47.669097: step: 1816/530, loss: 0.022262001410126686
2023-01-23 02:09:48.778119: step: 1820/530, loss: 0.024143362417817116
2023-01-23 02:09:49.881425: step: 1824/530, loss: 0.031217576935887337
2023-01-23 02:09:51.001852: step: 1828/530, loss: 0.0005869388696737587
2023-01-23 02:09:52.106675: step: 1832/530, loss: 0.038331225514411926
2023-01-23 02:09:53.204869: step: 1836/530, loss: 0.03635158762335777
2023-01-23 02:09:54.352871: step: 1840/530, loss: 0.0013438225723803043
2023-01-23 02:09:55.497295: step: 1844/530, loss: 0.5774036645889282
2023-01-23 02:09:56.645152: step: 1848/530, loss: 0.01458129845559597
2023-01-23 02:09:57.765515: step: 1852/530, loss: 0.07336712628602982
2023-01-23 02:09:58.899075: step: 1856/530, loss: 0.0931333601474762
2023-01-23 02:09:59.995229: step: 1860/530, loss: 0.007402515504509211
2023-01-23 02:10:01.096984: step: 1864/530, loss: 0.004745769780129194
2023-01-23 02:10:02.220217: step: 1868/530, loss: 0.016877364367246628
2023-01-23 02:10:03.325109: step: 1872/530, loss: 0.009440422058105469
2023-01-23 02:10:04.439496: step: 1876/530, loss: 0.010044110007584095
2023-01-23 02:10:05.560043: step: 1880/530, loss: 0.011895943433046341
2023-01-23 02:10:06.671163: step: 1884/530, loss: 1.2731469869613647
2023-01-23 02:10:07.754542: step: 1888/530, loss: 0.00010795593698276207
2023-01-23 02:10:08.883207: step: 1892/530, loss: 0.03233356773853302
2023-01-23 02:10:10.003611: step: 1896/530, loss: 0.021082306280732155
2023-01-23 02:10:11.100720: step: 1900/530, loss: 0.0005115509266033769
2023-01-23 02:10:12.213603: step: 1904/530, loss: 0.0410245917737484
2023-01-23 02:10:13.303102: step: 1908/530, loss: 0.014094257727265358
2023-01-23 02:10:14.460398: step: 1912/530, loss: 0.011416626162827015
2023-01-23 02:10:15.570723: step: 1916/530, loss: 0.005322170443832874
2023-01-23 02:10:16.695460: step: 1920/530, loss: 0.03090343438088894
2023-01-23 02:10:17.817872: step: 1924/530, loss: 0.008490943349897861
2023-01-23 02:10:18.930884: step: 1928/530, loss: 0.004160786047577858
2023-01-23 02:10:20.089329: step: 1932/530, loss: 0.021747207269072533
2023-01-23 02:10:21.195997: step: 1936/530, loss: 0.01864147186279297
2023-01-23 02:10:22.288356: step: 1940/530, loss: 0.036138057708740234
2023-01-23 02:10:23.438643: step: 1944/530, loss: 0.007146930787712336
2023-01-23 02:10:24.546974: step: 1948/530, loss: 1.71661376953125e-05
2023-01-23 02:10:25.644725: step: 1952/530, loss: 0.0022264481522142887
2023-01-23 02:10:26.743655: step: 1956/530, loss: 0.019896602258086205
2023-01-23 02:10:27.853932: step: 1960/530, loss: 0.010755825787782669
2023-01-23 02:10:28.964346: step: 1964/530, loss: 0.008393336087465286
2023-01-23 02:10:30.082558: step: 1968/530, loss: 0.01708192750811577
2023-01-23 02:10:31.189831: step: 1972/530, loss: 0.01895160786807537
2023-01-23 02:10:32.307965: step: 1976/530, loss: 0.007607078179717064
2023-01-23 02:10:33.440305: step: 1980/530, loss: 0.0017756461165845394
2023-01-23 02:10:34.563647: step: 1984/530, loss: 0.03867168352007866
2023-01-23 02:10:35.670567: step: 1988/530, loss: 0.012145495042204857
2023-01-23 02:10:36.784269: step: 1992/530, loss: 0.014162588864564896
2023-01-23 02:10:37.880540: step: 1996/530, loss: 0.018490267917513847
2023-01-23 02:10:39.041658: step: 2000/530, loss: 0.12102717906236649
2023-01-23 02:10:40.133101: step: 2004/530, loss: 0.0005085945595055819
2023-01-23 02:10:41.218324: step: 2008/530, loss: 8.344650268554688e-05
2023-01-23 02:10:42.312440: step: 2012/530, loss: 0.026729583740234375
2023-01-23 02:10:43.410905: step: 2016/530, loss: 0.06280127167701721
2023-01-23 02:10:44.540595: step: 2020/530, loss: 0.00139532086905092
2023-01-23 02:10:45.637897: step: 2024/530, loss: 0.0075057027861475945
2023-01-23 02:10:46.743373: step: 2028/530, loss: 0.029274560511112213
2023-01-23 02:10:47.836607: step: 2032/530, loss: 0.02344655990600586
2023-01-23 02:10:48.952025: step: 2036/530, loss: 0.05932817608118057
2023-01-23 02:10:50.046737: step: 2040/530, loss: 0.035944364964962006
2023-01-23 02:10:51.149542: step: 2044/530, loss: 0.02032174915075302
2023-01-23 02:10:52.269882: step: 2048/530, loss: 0.053028397262096405
2023-01-23 02:10:53.381990: step: 2052/530, loss: 0.0640474334359169
2023-01-23 02:10:54.476623: step: 2056/530, loss: 0.051745299249887466
2023-01-23 02:10:55.585688: step: 2060/530, loss: 0.0018241762882098556
2023-01-23 02:10:56.703359: step: 2064/530, loss: 0.0402621254324913
2023-01-23 02:10:57.821160: step: 2068/530, loss: 0.01775200292468071
2023-01-23 02:10:58.932554: step: 2072/530, loss: 0.00011148452904308215
2023-01-23 02:11:00.053204: step: 2076/530, loss: 0.012066412717103958
2023-01-23 02:11:01.142236: step: 2080/530, loss: 0.06936779618263245
2023-01-23 02:11:02.245112: step: 2084/530, loss: 0.04780597612261772
2023-01-23 02:11:03.349297: step: 2088/530, loss: 0.019060945138335228
2023-01-23 02:11:04.460160: step: 2092/530, loss: 0.0015701055526733398
2023-01-23 02:11:05.566958: step: 2096/530, loss: 0.0025784492027014494
2023-01-23 02:11:06.684328: step: 2100/530, loss: 0.0008533477666787803
2023-01-23 02:11:07.815444: step: 2104/530, loss: 0.007522392552345991
2023-01-23 02:11:08.942518: step: 2108/530, loss: 0.051296330988407135
2023-01-23 02:11:10.061236: step: 2112/530, loss: 0.02603931352496147
2023-01-23 02:11:11.164048: step: 2116/530, loss: 0.002379989717155695
2023-01-23 02:11:12.285863: step: 2120/530, loss: 0.01710519939661026
==================================================
Loss: 0.037
--------------------
Dev: {'event': {'p': 0.586171310629515, 'r': 0.7563249001331558, 'f1': 0.6604651162790698}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Test: {'event': {'p': 0.650093808630394, 'r': 0.8076923076923077, 'f1': 0.7203742203742204}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Chinese: {'event': {'p': 0.5945945945945946, 'r': 0.8148148148148148, 'f1': 0.6875}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Korean: {'event': {'p': 0.6491228070175439, 'r': 0.5873015873015873, 'f1': 0.6166666666666668}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
Russian: {'event': {'p': 0.5277777777777778, 'r': 0.5277777777777778, 'f1': 0.5277777777777778}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 15}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6449771689497716, 'r': 0.7523302263648469, 'f1': 0.6945298094652735}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Chinese: {'event': {'p': 0.6692644909887969, 'r': 0.8006993006993007, 'f1': 0.7291058636243036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Chinese: {'event': {'p': 0.6764705882352942, 'r': 0.8518518518518519, 'f1': 0.7540983606557378}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6449771689497716, 'r': 0.7523302263648469, 'f1': 0.6945298094652735}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Korean: {'event': {'p': 0.6692644909887969, 'r': 0.8006993006993007, 'f1': 0.7291058636243036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Korean: {'event': {'p': 0.7391304347826086, 'r': 0.5396825396825397, 'f1': 0.6238532110091742}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5971370143149284, 'r': 0.7776298268974701, 'f1': 0.6755349913244649}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Russian: {'event': {'p': 0.6401673640167364, 'r': 0.8024475524475524, 'f1': 0.7121799844840963}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Russian: {'event': {'p': 0.5897435897435898, 'r': 0.6388888888888888, 'f1': 0.6133333333333332}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
******************************
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 02:11:51.796184: step: 4/530, loss: 0.0026096345391124487
2023-01-23 02:11:52.903354: step: 8/530, loss: 0.008737373165786266
2023-01-23 02:11:53.984600: step: 12/530, loss: 0.05006594583392143
2023-01-23 02:11:55.073871: step: 16/530, loss: 0.0007851123809814453
2023-01-23 02:11:56.218945: step: 20/530, loss: 0.006977224722504616
2023-01-23 02:11:57.320841: step: 24/530, loss: 0.0014032365288585424
2023-01-23 02:11:58.449932: step: 28/530, loss: 0.0013179780216887593
2023-01-23 02:11:59.530730: step: 32/530, loss: 0.003001833101734519
2023-01-23 02:12:00.625274: step: 36/530, loss: 0.006005573086440563
2023-01-23 02:12:01.710532: step: 40/530, loss: 0.07602062821388245
2023-01-23 02:12:02.825657: step: 44/530, loss: 0.009712410159409046
2023-01-23 02:12:03.946693: step: 48/530, loss: 0.014066696166992188
2023-01-23 02:12:05.042677: step: 52/530, loss: 0.00030856134253554046
2023-01-23 02:12:06.144868: step: 56/530, loss: 0.09133699536323547
2023-01-23 02:12:07.305626: step: 60/530, loss: 0.01047430094331503
2023-01-23 02:12:08.390346: step: 64/530, loss: 0.004975557327270508
2023-01-23 02:12:09.501275: step: 68/530, loss: 0.03455772250890732
2023-01-23 02:12:10.599541: step: 72/530, loss: 0.005787086207419634
2023-01-23 02:12:11.755630: step: 76/530, loss: 0.026619913056492805
2023-01-23 02:12:12.880191: step: 80/530, loss: 0.0002605438348837197
2023-01-23 02:12:13.966991: step: 84/530, loss: 0.005034064874053001
2023-01-23 02:12:15.087555: step: 88/530, loss: 0.008485604077577591
2023-01-23 02:12:16.205734: step: 92/530, loss: 0.025510119274258614
2023-01-23 02:12:17.295624: step: 96/530, loss: 0.003732109209522605
2023-01-23 02:12:18.392056: step: 100/530, loss: 0.0235642921179533
2023-01-23 02:12:19.497321: step: 104/530, loss: 0.008184242062270641
2023-01-23 02:12:20.615113: step: 108/530, loss: 0.00490150460973382
2023-01-23 02:12:21.733373: step: 112/530, loss: 0.03522300720214844
2023-01-23 02:12:22.811488: step: 116/530, loss: 0.005222320556640625
2023-01-23 02:12:23.927560: step: 120/530, loss: 0.01125946082174778
2023-01-23 02:12:25.013543: step: 124/530, loss: 0.010607719421386719
2023-01-23 02:12:26.114386: step: 128/530, loss: 0.03161945194005966
2023-01-23 02:12:27.206478: step: 132/530, loss: 0.0026453970931470394
2023-01-23 02:12:28.319650: step: 136/530, loss: 0.0019149781437590718
2023-01-23 02:12:29.449421: step: 140/530, loss: 0.005530357360839844
2023-01-23 02:12:30.516639: step: 144/530, loss: 0.472377210855484
2023-01-23 02:12:31.652999: step: 148/530, loss: 0.0025650025345385075
2023-01-23 02:12:32.767399: step: 152/530, loss: 0.0034577371552586555
2023-01-23 02:12:33.904330: step: 156/530, loss: 0.003615093184635043
2023-01-23 02:12:35.022617: step: 160/530, loss: 0.17555637657642365
2023-01-23 02:12:36.131853: step: 164/530, loss: 0.002581977751106024
2023-01-23 02:12:37.230397: step: 168/530, loss: 0.026271535083651543
2023-01-23 02:12:38.359462: step: 172/530, loss: 0.019331859424710274
2023-01-23 02:12:39.464703: step: 176/530, loss: 0.0004039764462504536
2023-01-23 02:12:40.590831: step: 180/530, loss: 0.012410067953169346
2023-01-23 02:12:41.703371: step: 184/530, loss: 0.05592861399054527
2023-01-23 02:12:42.819131: step: 188/530, loss: 0.04153309017419815
2023-01-23 02:12:43.920014: step: 192/530, loss: 0.009405993856489658
2023-01-23 02:12:45.037637: step: 196/530, loss: 0.01063756924122572
2023-01-23 02:12:46.126836: step: 200/530, loss: 0.030408715829253197
2023-01-23 02:12:47.241509: step: 204/530, loss: 1.430511474609375e-05
2023-01-23 02:12:48.360382: step: 208/530, loss: 0.08489446341991425
2023-01-23 02:12:49.474508: step: 212/530, loss: 0.0008311271667480469
2023-01-23 02:12:50.595581: step: 216/530, loss: 0.0012578964233398438
2023-01-23 02:12:51.730971: step: 220/530, loss: 0.001083803130313754
2023-01-23 02:12:52.812147: step: 224/530, loss: 0.00426530884578824
2023-01-23 02:12:53.908357: step: 228/530, loss: 0.0009167671087197959
2023-01-23 02:12:55.040906: step: 232/530, loss: 0.044957924634218216
2023-01-23 02:12:56.132117: step: 236/530, loss: 0.006188249681144953
2023-01-23 02:12:57.260596: step: 240/530, loss: 0.004193687345832586
2023-01-23 02:12:58.343881: step: 244/530, loss: 0.041961051523685455
2023-01-23 02:12:59.462433: step: 248/530, loss: 0.016870975494384766
2023-01-23 02:13:00.571339: step: 252/530, loss: 0.07717037200927734
2023-01-23 02:13:01.690137: step: 256/530, loss: 0.030640553683042526
2023-01-23 02:13:02.800631: step: 260/530, loss: 0.001344871474429965
2023-01-23 02:13:03.941347: step: 264/530, loss: 0.008956718258559704
2023-01-23 02:13:05.040795: step: 268/530, loss: 0.0279680248349905
2023-01-23 02:13:06.132284: step: 272/530, loss: 0.011220455169677734
2023-01-23 02:13:07.221064: step: 276/530, loss: 0.0028352737426757812
2023-01-23 02:13:08.319778: step: 280/530, loss: 0.03299360349774361
2023-01-23 02:13:09.428674: step: 284/530, loss: 0.0014082908164709806
2023-01-23 02:13:10.549570: step: 288/530, loss: 0.0166015625
2023-01-23 02:13:11.651315: step: 292/530, loss: 0.02297210693359375
2023-01-23 02:13:12.750714: step: 296/530, loss: 0.0012806892627850175
2023-01-23 02:13:13.903417: step: 300/530, loss: 0.0901295617222786
2023-01-23 02:13:15.027084: step: 304/530, loss: 0.476127028465271
2023-01-23 02:13:16.108782: step: 308/530, loss: 0.006267356686294079
2023-01-23 02:13:17.221123: step: 312/530, loss: 0.022666500881314278
2023-01-23 02:13:18.337558: step: 316/530, loss: 0.014592742547392845
2023-01-23 02:13:19.464790: step: 320/530, loss: 0.0005290984991006553
2023-01-23 02:13:20.597935: step: 324/530, loss: 0.011837197467684746
2023-01-23 02:13:21.701331: step: 328/530, loss: 0.008163833059370518
2023-01-23 02:13:22.839857: step: 332/530, loss: 0.03495226055383682
2023-01-23 02:13:23.934056: step: 336/530, loss: 0.0020742416381835938
2023-01-23 02:13:25.058575: step: 340/530, loss: 0.012751484289765358
2023-01-23 02:13:26.146061: step: 344/530, loss: 0.023176193237304688
2023-01-23 02:13:27.277288: step: 348/530, loss: 0.00091724400408566
2023-01-23 02:13:28.384766: step: 352/530, loss: 0.0646636039018631
2023-01-23 02:13:29.525772: step: 356/530, loss: 0.006764411926269531
2023-01-23 02:13:30.628463: step: 360/530, loss: 0.0021659613121300936
2023-01-23 02:13:31.746599: step: 364/530, loss: 0.016031693667173386
2023-01-23 02:13:32.855590: step: 368/530, loss: 0.2545141279697418
2023-01-23 02:13:33.960766: step: 372/530, loss: 0.029867172241210938
2023-01-23 02:13:35.098911: step: 376/530, loss: 0.019176291301846504
2023-01-23 02:13:36.194927: step: 380/530, loss: 0.005105781834572554
2023-01-23 02:13:37.271045: step: 384/530, loss: 0.0037616731133311987
2023-01-23 02:13:38.391206: step: 388/530, loss: 0.0009654999012127519
2023-01-23 02:13:39.495104: step: 392/530, loss: 0.004054916091263294
2023-01-23 02:13:40.634700: step: 396/530, loss: 0.024544525891542435
2023-01-23 02:13:41.724979: step: 400/530, loss: 0.0023601532448083162
2023-01-23 02:13:42.798333: step: 404/530, loss: 0.020042039453983307
2023-01-23 02:13:43.893585: step: 408/530, loss: 0.007198929786682129
2023-01-23 02:13:44.994279: step: 412/530, loss: 0.02568025514483452
2023-01-23 02:13:46.107959: step: 416/530, loss: 0.027436351403594017
2023-01-23 02:13:47.215230: step: 420/530, loss: 0.0005029678577557206
2023-01-23 02:13:48.305193: step: 424/530, loss: 0.051404621452093124
2023-01-23 02:13:49.410693: step: 428/530, loss: 0.0075965882278978825
2023-01-23 02:13:50.521558: step: 432/530, loss: 0.0012785912258550525
2023-01-23 02:13:51.628416: step: 436/530, loss: 0.0546293780207634
2023-01-23 02:13:52.762320: step: 440/530, loss: 0.030843354761600494
2023-01-23 02:13:53.865910: step: 444/530, loss: 0.02581319771707058
2023-01-23 02:13:54.999886: step: 448/530, loss: 0.006031990051269531
2023-01-23 02:13:56.141721: step: 452/530, loss: 0.03751411288976669
2023-01-23 02:13:57.244929: step: 456/530, loss: 0.01381225697696209
2023-01-23 02:13:58.358645: step: 460/530, loss: 0.14594613015651703
2023-01-23 02:13:59.452192: step: 464/530, loss: 0.009919356554746628
2023-01-23 02:14:00.541521: step: 468/530, loss: 0.04968976974487305
2023-01-23 02:14:01.662905: step: 472/530, loss: 0.0009607315296307206
2023-01-23 02:14:02.774490: step: 476/530, loss: 0.021875428035855293
2023-01-23 02:14:03.899520: step: 480/530, loss: 0.0008830070728436112
2023-01-23 02:14:05.028902: step: 484/530, loss: 0.10106706619262695
2023-01-23 02:14:06.156063: step: 488/530, loss: 0.03615245968103409
2023-01-23 02:14:07.256696: step: 492/530, loss: 0.0011098862159997225
2023-01-23 02:14:08.366272: step: 496/530, loss: 0.037485696375370026
2023-01-23 02:14:09.495807: step: 500/530, loss: 0.008068657480180264
2023-01-23 02:14:10.622066: step: 504/530, loss: 0.0007484436500817537
2023-01-23 02:14:11.722595: step: 508/530, loss: 0.0028930664993822575
2023-01-23 02:14:12.836769: step: 512/530, loss: 0.06997394561767578
2023-01-23 02:14:13.940451: step: 516/530, loss: 0.0004976272466592491
2023-01-23 02:14:15.078653: step: 520/530, loss: 0.009317588992416859
2023-01-23 02:14:16.169013: step: 524/530, loss: 0.040335655212402344
2023-01-23 02:14:17.254881: step: 528/530, loss: 0.009569501504302025
2023-01-23 02:14:18.353032: step: 532/530, loss: 0.01207876205444336
2023-01-23 02:14:19.461723: step: 536/530, loss: 0.00047512055607512593
2023-01-23 02:14:20.601985: step: 540/530, loss: 0.061328887939453125
2023-01-23 02:14:21.724181: step: 544/530, loss: 0.02001495473086834
2023-01-23 02:14:22.827917: step: 548/530, loss: 0.00834197923541069
2023-01-23 02:14:23.938072: step: 552/530, loss: 0.14684951305389404
2023-01-23 02:14:25.039182: step: 556/530, loss: 0.13284379243850708
2023-01-23 02:14:26.145733: step: 560/530, loss: 0.07882557064294815
2023-01-23 02:14:27.288059: step: 564/530, loss: 0.014153195545077324
2023-01-23 02:14:28.380017: step: 568/530, loss: 0.0015981197357177734
2023-01-23 02:14:29.487418: step: 572/530, loss: 0.00620117224752903
2023-01-23 02:14:30.609985: step: 576/530, loss: 0.02842097170650959
2023-01-23 02:14:31.725835: step: 580/530, loss: 0.0009136199951171875
2023-01-23 02:14:32.860834: step: 584/530, loss: 0.018334578722715378
2023-01-23 02:14:33.948424: step: 588/530, loss: 0.0417022667825222
2023-01-23 02:14:35.060241: step: 592/530, loss: 0.0021401403937488794
2023-01-23 02:14:36.233686: step: 596/530, loss: 0.027335835620760918
2023-01-23 02:14:37.367974: step: 600/530, loss: 0.00942163448780775
2023-01-23 02:14:38.474621: step: 604/530, loss: 0.0005393982282839715
2023-01-23 02:14:39.596416: step: 608/530, loss: 0.004176282789558172
2023-01-23 02:14:40.713927: step: 612/530, loss: 0.004477500915527344
2023-01-23 02:14:41.823464: step: 616/530, loss: 0.02010359801352024
2023-01-23 02:14:42.902499: step: 620/530, loss: 0.003826999804005027
2023-01-23 02:14:44.018239: step: 624/530, loss: 0.010530472733080387
2023-01-23 02:14:45.113539: step: 628/530, loss: 0.48352622985839844
2023-01-23 02:14:46.239992: step: 632/530, loss: 0.004313468933105469
2023-01-23 02:14:47.326058: step: 636/530, loss: 0.029853105545043945
2023-01-23 02:14:48.408287: step: 640/530, loss: 0.0017503738636150956
2023-01-23 02:14:49.567623: step: 644/530, loss: 0.09529876708984375
2023-01-23 02:14:50.713208: step: 648/530, loss: 0.009164620190858841
2023-01-23 02:14:51.820672: step: 652/530, loss: 0.001909398939460516
2023-01-23 02:14:52.978517: step: 656/530, loss: 0.015333461575210094
2023-01-23 02:14:54.078742: step: 660/530, loss: 0.012388992123305798
2023-01-23 02:14:55.191121: step: 664/530, loss: 0.027003003284335136
2023-01-23 02:14:56.295373: step: 668/530, loss: 0.022673320025205612
2023-01-23 02:14:57.431585: step: 672/530, loss: 0.05640869215130806
2023-01-23 02:14:58.517113: step: 676/530, loss: 0.18259334564208984
2023-01-23 02:14:59.629027: step: 680/530, loss: 0.05725069344043732
2023-01-23 02:15:00.733696: step: 684/530, loss: 0.016090011224150658
2023-01-23 02:15:01.839894: step: 688/530, loss: 0.00819478090852499
2023-01-23 02:15:02.945399: step: 692/530, loss: 0.004620933905243874
2023-01-23 02:15:04.049781: step: 696/530, loss: 0.03376026079058647
2023-01-23 02:15:05.143692: step: 700/530, loss: 0.000614166259765625
2023-01-23 02:15:06.261501: step: 704/530, loss: 0.005454635713249445
2023-01-23 02:15:07.356737: step: 708/530, loss: 0.011223411187529564
2023-01-23 02:15:08.455772: step: 712/530, loss: 0.03956909477710724
2023-01-23 02:15:09.583499: step: 716/530, loss: 0.00919080339372158
2023-01-23 02:15:10.691526: step: 720/530, loss: 0.09515400230884552
2023-01-23 02:15:11.805194: step: 724/530, loss: 0.006445407867431641
2023-01-23 02:15:12.901952: step: 728/530, loss: 0.0006406783941201866
2023-01-23 02:15:13.978565: step: 732/530, loss: 0.008631658740341663
2023-01-23 02:15:15.083990: step: 736/530, loss: 0.01547927875071764
2023-01-23 02:15:16.200875: step: 740/530, loss: 0.013899898156523705
2023-01-23 02:15:17.299603: step: 744/530, loss: 0.007287025451660156
2023-01-23 02:15:18.405531: step: 748/530, loss: 0.060418032109737396
2023-01-23 02:15:19.519005: step: 752/530, loss: 0.013784694485366344
2023-01-23 02:15:20.633240: step: 756/530, loss: 0.004078865051269531
2023-01-23 02:15:21.721758: step: 760/530, loss: 0.005148029420524836
2023-01-23 02:15:22.825545: step: 764/530, loss: 0.002786636585369706
2023-01-23 02:15:23.953961: step: 768/530, loss: 0.009826707653701305
2023-01-23 02:15:25.040852: step: 772/530, loss: 0.0002690315304789692
2023-01-23 02:15:26.167024: step: 776/530, loss: 0.0018097878200933337
2023-01-23 02:15:27.270833: step: 780/530, loss: 0.00013165474229026586
2023-01-23 02:15:28.374623: step: 784/530, loss: 0.051764775067567825
2023-01-23 02:15:29.503614: step: 788/530, loss: 0.010389518924057484
2023-01-23 02:15:30.620068: step: 792/530, loss: 0.0006260871887207031
2023-01-23 02:15:31.760118: step: 796/530, loss: 0.012496472336351871
2023-01-23 02:15:32.863116: step: 800/530, loss: 0.08666171878576279
2023-01-23 02:15:33.968976: step: 804/530, loss: 0.011906290426850319
2023-01-23 02:15:35.071205: step: 808/530, loss: 0.012635231018066406
2023-01-23 02:15:36.210676: step: 812/530, loss: 0.012938880361616611
2023-01-23 02:15:37.312335: step: 816/530, loss: 0.028399372473359108
2023-01-23 02:15:38.428788: step: 820/530, loss: 0.09615077823400497
2023-01-23 02:15:39.503345: step: 824/530, loss: 0.0004273414670024067
2023-01-23 02:15:40.610895: step: 828/530, loss: 0.02262573316693306
2023-01-23 02:15:41.743754: step: 832/530, loss: 0.02915208414196968
2023-01-23 02:15:42.874340: step: 836/530, loss: 0.0334194153547287
2023-01-23 02:15:43.983469: step: 840/530, loss: 0.00044498444185592234
2023-01-23 02:15:45.114078: step: 844/530, loss: 0.1068183034658432
2023-01-23 02:15:46.240444: step: 848/530, loss: 0.02968454547226429
2023-01-23 02:15:47.356282: step: 852/530, loss: 0.09853249043226242
2023-01-23 02:15:48.478467: step: 856/530, loss: 0.0004447936953511089
2023-01-23 02:15:49.598912: step: 860/530, loss: 0.031416039913892746
2023-01-23 02:15:50.704814: step: 864/530, loss: 0.2399987280368805
2023-01-23 02:15:51.819043: step: 868/530, loss: 0.11753010749816895
2023-01-23 02:15:52.950503: step: 872/530, loss: 0.04470062255859375
2023-01-23 02:15:54.074769: step: 876/530, loss: 0.018079757690429688
2023-01-23 02:15:55.183044: step: 880/530, loss: 0.021625136956572533
2023-01-23 02:15:56.274602: step: 884/530, loss: 0.004472064785659313
2023-01-23 02:15:57.406045: step: 888/530, loss: 0.02916712872684002
2023-01-23 02:15:58.529483: step: 892/530, loss: 0.000257641077041626
2023-01-23 02:15:59.654139: step: 896/530, loss: 0.001990032382309437
2023-01-23 02:16:00.770478: step: 900/530, loss: 0.0047844890505075455
2023-01-23 02:16:01.917704: step: 904/530, loss: 0.013147926889359951
2023-01-23 02:16:03.014797: step: 908/530, loss: 0.016425324603915215
2023-01-23 02:16:04.118343: step: 912/530, loss: 0.01337738148868084
2023-01-23 02:16:05.225329: step: 916/530, loss: 0.0005602836608886719
2023-01-23 02:16:06.328386: step: 920/530, loss: 0.025411320850253105
2023-01-23 02:16:07.479138: step: 924/530, loss: 0.03919658809900284
2023-01-23 02:16:08.593892: step: 928/530, loss: 0.009774064645171165
2023-01-23 02:16:09.688226: step: 932/530, loss: 0.0007413864368572831
2023-01-23 02:16:10.794460: step: 936/530, loss: 0.010137938894331455
2023-01-23 02:16:11.878792: step: 940/530, loss: 0.05636034160852432
2023-01-23 02:16:13.006750: step: 944/530, loss: 0.006942367646843195
2023-01-23 02:16:14.117235: step: 948/530, loss: 0.08903008699417114
2023-01-23 02:16:15.258231: step: 952/530, loss: 0.0013545036781579256
2023-01-23 02:16:16.385416: step: 956/530, loss: 0.0007080078357830644
2023-01-23 02:16:17.476788: step: 960/530, loss: 0.05321807786822319
2023-01-23 02:16:18.589238: step: 964/530, loss: 0.03147897496819496
2023-01-23 02:16:19.700418: step: 968/530, loss: 0.019057273864746094
2023-01-23 02:16:20.826211: step: 972/530, loss: 0.03451404720544815
2023-01-23 02:16:21.959142: step: 976/530, loss: 0.00665626535192132
2023-01-23 02:16:23.069434: step: 980/530, loss: 0.00017919539823196828
2023-01-23 02:16:24.168165: step: 984/530, loss: 0.01682901382446289
2023-01-23 02:16:25.272815: step: 988/530, loss: 0.0006068229558877647
2023-01-23 02:16:26.395235: step: 992/530, loss: 0.041375160217285156
2023-01-23 02:16:27.495035: step: 996/530, loss: 0.008054685778915882
2023-01-23 02:16:28.603898: step: 1000/530, loss: 0.0034139633644372225
2023-01-23 02:16:29.711714: step: 1004/530, loss: 0.09210024029016495
2023-01-23 02:16:30.831054: step: 1008/530, loss: 0.06712131202220917
2023-01-23 02:16:31.933503: step: 1012/530, loss: 0.027309799566864967
2023-01-23 02:16:33.040198: step: 1016/530, loss: 0.002092075301334262
2023-01-23 02:16:34.157889: step: 1020/530, loss: 0.017806099727749825
2023-01-23 02:16:35.274448: step: 1024/530, loss: 0.15123941004276276
2023-01-23 02:16:36.395074: step: 1028/530, loss: 0.0025316239334642887
2023-01-23 02:16:37.512978: step: 1032/530, loss: 0.020592212677001953
2023-01-23 02:16:38.634372: step: 1036/530, loss: 0.0052585601806640625
2023-01-23 02:16:39.743429: step: 1040/530, loss: 0.022068405523896217
2023-01-23 02:16:40.866253: step: 1044/530, loss: 0.026339245960116386
2023-01-23 02:16:41.967704: step: 1048/530, loss: 0.01343383826315403
2023-01-23 02:16:43.074368: step: 1052/530, loss: 0.0006569862016476691
2023-01-23 02:16:44.167820: step: 1056/530, loss: 0.024186039343476295
2023-01-23 02:16:45.282273: step: 1060/530, loss: 0.009835625067353249
2023-01-23 02:16:46.413881: step: 1064/530, loss: 0.00011072159395553172
2023-01-23 02:16:47.529337: step: 1068/530, loss: 0.085893914103508
2023-01-23 02:16:48.630166: step: 1072/530, loss: 0.02461276203393936
2023-01-23 02:16:49.802111: step: 1076/530, loss: 0.02232734113931656
2023-01-23 02:16:50.915638: step: 1080/530, loss: 0.01565737836062908
2023-01-23 02:16:52.048178: step: 1084/530, loss: 0.02214031293988228
2023-01-23 02:16:53.157888: step: 1088/530, loss: 0.00012235641770530492
2023-01-23 02:16:54.277285: step: 1092/530, loss: 0.0033653259743005037
2023-01-23 02:16:55.378942: step: 1096/530, loss: 0.5417042374610901
2023-01-23 02:16:56.504031: step: 1100/530, loss: 0.0035800933837890625
2023-01-23 02:16:57.628792: step: 1104/530, loss: 0.02330474741756916
2023-01-23 02:16:58.734840: step: 1108/530, loss: 0.001342868898063898
2023-01-23 02:16:59.813354: step: 1112/530, loss: -1.144409225162235e-06
2023-01-23 02:17:00.934242: step: 1116/530, loss: 0.0027744295075535774
2023-01-23 02:17:02.062955: step: 1120/530, loss: 0.0069938660599291325
2023-01-23 02:17:03.183634: step: 1124/530, loss: 0.10436997562646866
2023-01-23 02:17:04.312605: step: 1128/530, loss: 0.020429611206054688
2023-01-23 02:17:05.437237: step: 1132/530, loss: 0.00021419525728560984
2023-01-23 02:17:06.562299: step: 1136/530, loss: 0.0010223388671875
2023-01-23 02:17:07.660871: step: 1140/530, loss: 0.00876159593462944
2023-01-23 02:17:08.794165: step: 1144/530, loss: 0.005516433622688055
2023-01-23 02:17:09.878536: step: 1148/530, loss: 0.004676151089370251
2023-01-23 02:17:11.015932: step: 1152/530, loss: 0.01613597944378853
2023-01-23 02:17:12.136123: step: 1156/530, loss: 0.006712150759994984
2023-01-23 02:17:13.259609: step: 1160/530, loss: 0.08199349045753479
2023-01-23 02:17:14.354673: step: 1164/530, loss: 0.002145290607586503
2023-01-23 02:17:15.471494: step: 1168/530, loss: 0.02720623090863228
2023-01-23 02:17:16.607810: step: 1172/530, loss: 0.0070053101517260075
2023-01-23 02:17:17.710549: step: 1176/530, loss: 0.0006077289581298828
2023-01-23 02:17:18.825249: step: 1180/530, loss: 0.006890153978019953
2023-01-23 02:17:19.935679: step: 1184/530, loss: 0.0015504838665947318
2023-01-23 02:17:21.047516: step: 1188/530, loss: 0.0063339234329760075
2023-01-23 02:17:22.138077: step: 1192/530, loss: 0.09852425754070282
2023-01-23 02:17:23.227820: step: 1196/530, loss: 0.04136495664715767
2023-01-23 02:17:24.351055: step: 1200/530, loss: 0.0794849544763565
2023-01-23 02:17:25.454812: step: 1204/530, loss: 0.03389853239059448
2023-01-23 02:17:26.572944: step: 1208/530, loss: 0.00020675659470725805
2023-01-23 02:17:27.706583: step: 1212/530, loss: 0.015740204602479935
2023-01-23 02:17:28.805684: step: 1216/530, loss: 0.014971543103456497
2023-01-23 02:17:29.913391: step: 1220/530, loss: 0.0011601329315453768
2023-01-23 02:17:31.026782: step: 1224/530, loss: 0.04130592569708824
2023-01-23 02:17:32.161605: step: 1228/530, loss: 0.0010036468738690019
2023-01-23 02:17:33.288786: step: 1232/530, loss: 0.0008438110235147178
2023-01-23 02:17:34.384677: step: 1236/530, loss: 0.026101304218173027
2023-01-23 02:17:35.469489: step: 1240/530, loss: 0.03869905322790146
2023-01-23 02:17:36.566417: step: 1244/530, loss: 0.014095974154770374
2023-01-23 02:17:37.695369: step: 1248/530, loss: 0.0408666618168354
2023-01-23 02:17:38.855707: step: 1252/530, loss: 0.04023304209113121
2023-01-23 02:17:39.992243: step: 1256/530, loss: 0.04168128967285156
2023-01-23 02:17:41.112850: step: 1260/530, loss: 0.0017606735927984118
2023-01-23 02:17:42.244733: step: 1264/530, loss: 0.08702965080738068
2023-01-23 02:17:43.377033: step: 1268/530, loss: 0.006293678190559149
2023-01-23 02:17:44.479359: step: 1272/530, loss: 0.018437767401337624
2023-01-23 02:17:45.563019: step: 1276/530, loss: 0.00019989015709143132
2023-01-23 02:17:46.686022: step: 1280/530, loss: 0.03458233177661896
2023-01-23 02:17:47.805041: step: 1284/530, loss: 0.04725909233093262
2023-01-23 02:17:48.916081: step: 1288/530, loss: 0.004369544796645641
2023-01-23 02:17:50.039573: step: 1292/530, loss: 0.14484548568725586
2023-01-23 02:17:51.136737: step: 1296/530, loss: 0.04737739637494087
2023-01-23 02:17:52.250485: step: 1300/530, loss: 0.017830276861786842
2023-01-23 02:17:53.377631: step: 1304/530, loss: 0.05960889160633087
2023-01-23 02:17:54.466722: step: 1308/530, loss: 0.013987923040986061
2023-01-23 02:17:55.558081: step: 1312/530, loss: 0.059500597417354584
2023-01-23 02:17:56.712269: step: 1316/530, loss: 0.004475403111428022
2023-01-23 02:17:57.813370: step: 1320/530, loss: 0.036643028259277344
2023-01-23 02:17:58.911754: step: 1324/530, loss: 0.003297424176707864
2023-01-23 02:18:00.033030: step: 1328/530, loss: 0.09255476295948029
2023-01-23 02:18:01.175031: step: 1332/530, loss: 0.07465648651123047
2023-01-23 02:18:02.283821: step: 1336/530, loss: 0.016371821984648705
2023-01-23 02:18:03.409130: step: 1340/530, loss: 0.008239460177719593
2023-01-23 02:18:04.543350: step: 1344/530, loss: 0.0009898185962811112
2023-01-23 02:18:05.680965: step: 1348/530, loss: 0.0026920319069176912
2023-01-23 02:18:06.797259: step: 1352/530, loss: 0.006384659092873335
2023-01-23 02:18:07.900314: step: 1356/530, loss: 0.0018002509605139494
2023-01-23 02:18:09.050885: step: 1360/530, loss: 0.010363388806581497
2023-01-23 02:18:10.185046: step: 1364/530, loss: 0.03910541534423828
2023-01-23 02:18:11.307087: step: 1368/530, loss: 0.08220481872558594
2023-01-23 02:18:12.415420: step: 1372/530, loss: 0.051215123385190964
2023-01-23 02:18:13.500453: step: 1376/530, loss: 0.02475719526410103
2023-01-23 02:18:14.617844: step: 1380/530, loss: 0.00834035873413086
2023-01-23 02:18:15.719546: step: 1384/530, loss: 0.012173652648925781
2023-01-23 02:18:16.846389: step: 1388/530, loss: 0.01556462049484253
2023-01-23 02:18:17.938225: step: 1392/530, loss: 0.0032630921341478825
2023-01-23 02:18:19.049923: step: 1396/530, loss: 0.022950172424316406
2023-01-23 02:18:20.160713: step: 1400/530, loss: 0.017870904877781868
2023-01-23 02:18:21.291114: step: 1404/530, loss: 0.018709564581513405
2023-01-23 02:18:22.401746: step: 1408/530, loss: 0.0019338608253747225
2023-01-23 02:18:23.532922: step: 1412/530, loss: 0.0017212391830980778
2023-01-23 02:18:24.674710: step: 1416/530, loss: 0.03352975845336914
2023-01-23 02:18:25.770267: step: 1420/530, loss: 0.01043720357120037
2023-01-23 02:18:26.898846: step: 1424/530, loss: 0.0127401826903224
2023-01-23 02:18:28.016779: step: 1428/530, loss: 0.023438643664121628
2023-01-23 02:18:29.138105: step: 1432/530, loss: 0.0009836197132244706
2023-01-23 02:18:30.246397: step: 1436/530, loss: 0.0030391693580895662
2023-01-23 02:18:31.372043: step: 1440/530, loss: 0.0015737534267827868
2023-01-23 02:18:32.487898: step: 1444/530, loss: 0.00190143589861691
2023-01-23 02:18:33.587481: step: 1448/530, loss: 0.008566570468246937
2023-01-23 02:18:34.684804: step: 1452/530, loss: 8.57353225001134e-05
2023-01-23 02:18:35.778023: step: 1456/530, loss: 0.06895885616540909
2023-01-23 02:18:36.892976: step: 1460/530, loss: 0.0032720565795898438
2023-01-23 02:18:37.979619: step: 1464/530, loss: 0.0038191794883459806
2023-01-23 02:18:39.080440: step: 1468/530, loss: 0.00015020370483398438
2023-01-23 02:18:40.184773: step: 1472/530, loss: 0.007961606606841087
2023-01-23 02:18:41.290480: step: 1476/530, loss: 0.0033529282081872225
2023-01-23 02:18:42.420928: step: 1480/530, loss: 0.00021104812913108617
2023-01-23 02:18:43.505222: step: 1484/530, loss: 0.0024018287658691406
2023-01-23 02:18:44.616804: step: 1488/530, loss: 0.011574173346161842
2023-01-23 02:18:45.769942: step: 1492/530, loss: 0.0013336181873455644
2023-01-23 02:18:46.855889: step: 1496/530, loss: 0.0016519785858690739
2023-01-23 02:18:47.945907: step: 1500/530, loss: 0.008941650390625
2023-01-23 02:18:49.052950: step: 1504/530, loss: 0.01779651641845703
2023-01-23 02:18:50.152368: step: 1508/530, loss: 0.039354514330625534
2023-01-23 02:18:51.252745: step: 1512/530, loss: 0.05947704240679741
2023-01-23 02:18:52.369197: step: 1516/530, loss: 0.047955796122550964
2023-01-23 02:18:53.527275: step: 1520/530, loss: 0.011865329928696156
2023-01-23 02:18:54.644417: step: 1524/530, loss: 0.006604385562241077
2023-01-23 02:18:55.766952: step: 1528/530, loss: 0.004587078001350164
2023-01-23 02:18:56.902777: step: 1532/530, loss: 0.004681682679802179
2023-01-23 02:18:58.033183: step: 1536/530, loss: 0.055883027613162994
2023-01-23 02:18:59.149659: step: 1540/530, loss: 0.004079401958733797
2023-01-23 02:19:00.272972: step: 1544/530, loss: 0.03232517093420029
2023-01-23 02:19:01.424272: step: 1548/530, loss: 0.011879158206284046
2023-01-23 02:19:02.533048: step: 1552/530, loss: 0.015729952603578568
2023-01-23 02:19:03.647050: step: 1556/530, loss: 0.008579254150390625
2023-01-23 02:19:04.751735: step: 1560/530, loss: 0.0006083488697186112
2023-01-23 02:19:05.889087: step: 1564/530, loss: 0.03473472595214844
2023-01-23 02:19:07.011046: step: 1568/530, loss: 0.0174452792853117
2023-01-23 02:19:08.110938: step: 1572/530, loss: 0.007180976681411266
2023-01-23 02:19:09.233313: step: 1576/530, loss: 0.0038840770721435547
2023-01-23 02:19:10.340172: step: 1580/530, loss: 0.32468509674072266
2023-01-23 02:19:11.470227: step: 1584/530, loss: 0.0002134323149221018
2023-01-23 02:19:12.580359: step: 1588/530, loss: 0.0013719559647142887
2023-01-23 02:19:13.682358: step: 1592/530, loss: 0.029858112335205078
2023-01-23 02:19:14.798092: step: 1596/530, loss: 0.0034971237182617188
2023-01-23 02:19:15.910908: step: 1600/530, loss: 0.005486297886818647
2023-01-23 02:19:17.067384: step: 1604/530, loss: 0.02865924872457981
2023-01-23 02:19:18.176555: step: 1608/530, loss: 0.024501444771885872
2023-01-23 02:19:19.303094: step: 1612/530, loss: 0.08277097344398499
2023-01-23 02:19:20.412700: step: 1616/530, loss: 0.04843711853027344
2023-01-23 02:19:21.512949: step: 1620/530, loss: 0.019440174102783203
2023-01-23 02:19:22.616044: step: 1624/530, loss: 0.003404855728149414
2023-01-23 02:19:23.781539: step: 1628/530, loss: 0.012141036801040173
2023-01-23 02:19:24.919675: step: 1632/530, loss: 0.02066192589700222
2023-01-23 02:19:26.056609: step: 1636/530, loss: 0.032501984387636185
2023-01-23 02:19:27.159621: step: 1640/530, loss: 0.0032460689544677734
2023-01-23 02:19:28.286376: step: 1644/530, loss: 0.0456174835562706
2023-01-23 02:19:29.396958: step: 1648/530, loss: 0.0013841629261150956
2023-01-23 02:19:30.528138: step: 1652/530, loss: 0.02473926544189453
2023-01-23 02:19:31.671021: step: 1656/530, loss: 0.02271904982626438
2023-01-23 02:19:32.815434: step: 1660/530, loss: 0.00816803053021431
2023-01-23 02:19:33.945074: step: 1664/530, loss: 0.002902221865952015
2023-01-23 02:19:35.065098: step: 1668/530, loss: 0.031546879559755325
2023-01-23 02:19:36.180371: step: 1672/530, loss: 0.005530166905373335
2023-01-23 02:19:37.285445: step: 1676/530, loss: 0.017757035791873932
2023-01-23 02:19:38.375184: step: 1680/530, loss: 0.0009286880376748741
2023-01-23 02:19:39.470164: step: 1684/530, loss: 0.009922122582793236
2023-01-23 02:19:40.586037: step: 1688/530, loss: 0.014352631755173206
2023-01-23 02:19:41.670848: step: 1692/530, loss: 0.016274547204375267
2023-01-23 02:19:42.756721: step: 1696/530, loss: 0.012370157055556774
2023-01-23 02:19:43.855973: step: 1700/530, loss: 0.00052642822265625
2023-01-23 02:19:44.976132: step: 1704/530, loss: 0.06131858751177788
2023-01-23 02:19:46.076671: step: 1708/530, loss: 0.030119895935058594
2023-01-23 02:19:47.171537: step: 1712/530, loss: 0.011890602298080921
2023-01-23 02:19:48.267417: step: 1716/530, loss: 0.019771575927734375
2023-01-23 02:19:49.372504: step: 1720/530, loss: 0.08073930442333221
2023-01-23 02:19:50.494111: step: 1724/530, loss: 0.0028011694084852934
2023-01-23 02:19:51.594124: step: 1728/530, loss: 0.07083974033594131
2023-01-23 02:19:52.712627: step: 1732/530, loss: 0.027170753106474876
2023-01-23 02:19:53.833524: step: 1736/530, loss: 0.03600182756781578
2023-01-23 02:19:54.936047: step: 1740/530, loss: 1.2782566547393799
2023-01-23 02:19:56.035818: step: 1744/530, loss: 0.02714400365948677
2023-01-23 02:19:57.145308: step: 1748/530, loss: 0.007042550947517157
2023-01-23 02:19:58.270378: step: 1752/530, loss: 0.0006359577528201044
2023-01-23 02:19:59.357940: step: 1756/530, loss: 0.00020213128300383687
2023-01-23 02:20:00.498694: step: 1760/530, loss: 0.010347938165068626
2023-01-23 02:20:01.575331: step: 1764/530, loss: 0.02387523651123047
2023-01-23 02:20:02.683894: step: 1768/530, loss: 0.01089630089700222
2023-01-23 02:20:03.799022: step: 1772/530, loss: 0.07758770138025284
2023-01-23 02:20:04.979158: step: 1776/530, loss: 0.02532673068344593
2023-01-23 02:20:06.081703: step: 1780/530, loss: 0.002962446305900812
2023-01-23 02:20:07.156244: step: 1784/530, loss: 0.6591671705245972
2023-01-23 02:20:08.292451: step: 1788/530, loss: 0.034917399287223816
2023-01-23 02:20:09.447532: step: 1792/530, loss: 0.0007560729864053428
2023-01-23 02:20:10.550304: step: 1796/530, loss: 0.12798985838890076
2023-01-23 02:20:11.656510: step: 1800/530, loss: 0.006716489791870117
2023-01-23 02:20:12.752755: step: 1804/530, loss: 0.05302458256483078
2023-01-23 02:20:13.882085: step: 1808/530, loss: 0.005708026699721813
2023-01-23 02:20:14.990110: step: 1812/530, loss: 0.014288521371781826
2023-01-23 02:20:16.086079: step: 1816/530, loss: 0.001903533935546875
2023-01-23 02:20:17.188974: step: 1820/530, loss: 0.36050042510032654
2023-01-23 02:20:18.272797: step: 1824/530, loss: 0.005066824145615101
2023-01-23 02:20:19.376506: step: 1828/530, loss: 0.10884599387645721
2023-01-23 02:20:20.497573: step: 1832/530, loss: 0.0005013465997762978
2023-01-23 02:20:21.618845: step: 1836/530, loss: 0.04595642164349556
2023-01-23 02:20:22.771310: step: 1840/530, loss: 0.049460601061582565
2023-01-23 02:20:23.890306: step: 1844/530, loss: 0.02969665639102459
2023-01-23 02:20:25.077757: step: 1848/530, loss: 0.049024634063243866
2023-01-23 02:20:26.192775: step: 1852/530, loss: 0.04389185085892677
2023-01-23 02:20:27.315129: step: 1856/530, loss: 0.0017632603412494063
2023-01-23 02:20:28.423511: step: 1860/530, loss: 0.011154556646943092
2023-01-23 02:20:29.525444: step: 1864/530, loss: 0.054690077900886536
2023-01-23 02:20:30.632480: step: 1868/530, loss: 0.0006351470947265625
2023-01-23 02:20:31.738280: step: 1872/530, loss: 0.02438100054860115
2023-01-23 02:20:32.871279: step: 1876/530, loss: 0.00036525726318359375
2023-01-23 02:20:34.027507: step: 1880/530, loss: 0.047116659581661224
2023-01-23 02:20:35.134393: step: 1884/530, loss: 0.017323588952422142
2023-01-23 02:20:36.292822: step: 1888/530, loss: 0.005760383792221546
2023-01-23 02:20:37.396139: step: 1892/530, loss: 0.006068515591323376
2023-01-23 02:20:38.498213: step: 1896/530, loss: 0.012779808603227139
2023-01-23 02:20:39.588398: step: 1900/530, loss: 0.028653431683778763
2023-01-23 02:20:40.677938: step: 1904/530, loss: 0.025748729705810547
2023-01-23 02:20:41.764900: step: 1908/530, loss: 0.001165974186733365
2023-01-23 02:20:42.853681: step: 1912/530, loss: 0.09264449775218964
2023-01-23 02:20:43.974125: step: 1916/530, loss: 0.030138254165649414
2023-01-23 02:20:45.089522: step: 1920/530, loss: 0.08005218952894211
2023-01-23 02:20:46.160412: step: 1924/530, loss: 0.0014788627158850431
2023-01-23 02:20:47.272317: step: 1928/530, loss: 0.03776111826300621
2023-01-23 02:20:48.382602: step: 1932/530, loss: 0.0024306774139404297
2023-01-23 02:20:49.514779: step: 1936/530, loss: 0.0034062385093420744
2023-01-23 02:20:50.604811: step: 1940/530, loss: 0.04630127176642418
2023-01-23 02:20:51.743316: step: 1944/530, loss: 0.00444340705871582
2023-01-23 02:20:52.861573: step: 1948/530, loss: 0.016202669590711594
2023-01-23 02:20:53.975499: step: 1952/530, loss: 0.044142868369817734
2023-01-23 02:20:55.103034: step: 1956/530, loss: 0.032686758786439896
2023-01-23 02:20:56.211022: step: 1960/530, loss: 0.005498790647834539
2023-01-23 02:20:57.315845: step: 1964/530, loss: 0.0027975437697023153
2023-01-23 02:20:58.439368: step: 1968/530, loss: 0.009188652038574219
2023-01-23 02:20:59.536426: step: 1972/530, loss: 0.011859416961669922
2023-01-23 02:21:00.664783: step: 1976/530, loss: 0.20896291732788086
2023-01-23 02:21:01.803213: step: 1980/530, loss: 0.030010033398866653
2023-01-23 02:21:02.929057: step: 1984/530, loss: 0.07112963497638702
2023-01-23 02:21:04.021931: step: 1988/530, loss: 0.06819553673267365
2023-01-23 02:21:05.125021: step: 1992/530, loss: 0.0008634566911496222
2023-01-23 02:21:06.262062: step: 1996/530, loss: 0.027050208300352097
2023-01-23 02:21:07.371616: step: 2000/530, loss: 0.009219515137374401
2023-01-23 02:21:08.479259: step: 2004/530, loss: 4.3201445805607364e-05
2023-01-23 02:21:09.640133: step: 2008/530, loss: 0.03811082988977432
2023-01-23 02:21:10.759427: step: 2012/530, loss: 0.030016329139471054
2023-01-23 02:21:11.896627: step: 2016/530, loss: 0.0031457901932299137
2023-01-23 02:21:13.005307: step: 2020/530, loss: 0.0024652481079101562
2023-01-23 02:21:14.100811: step: 2024/530, loss: 0.03889341279864311
2023-01-23 02:21:15.236565: step: 2028/530, loss: 0.0028830289375036955
2023-01-23 02:21:16.355156: step: 2032/530, loss: 0.005615234375
2023-01-23 02:21:17.465222: step: 2036/530, loss: 0.0007209301693364978
2023-01-23 02:21:18.597478: step: 2040/530, loss: 0.03858451917767525
2023-01-23 02:21:19.702031: step: 2044/530, loss: 0.0026111602783203125
2023-01-23 02:21:20.822343: step: 2048/530, loss: 0.03425021097064018
2023-01-23 02:21:21.947665: step: 2052/530, loss: 0.03392324596643448
2023-01-23 02:21:23.040039: step: 2056/530, loss: 0.026357173919677734
2023-01-23 02:21:24.172191: step: 2060/530, loss: 0.0012678145430982113
2023-01-23 02:21:25.261539: step: 2064/530, loss: 0.003803253173828125
2023-01-23 02:21:26.367900: step: 2068/530, loss: 0.06784587353467941
2023-01-23 02:21:27.465135: step: 2072/530, loss: 0.0005203246837481856
2023-01-23 02:21:28.586893: step: 2076/530, loss: 0.0056588174775242805
2023-01-23 02:21:29.701341: step: 2080/530, loss: 0.05423889309167862
2023-01-23 02:21:30.828226: step: 2084/530, loss: 0.01734619215130806
2023-01-23 02:21:31.917484: step: 2088/530, loss: 0.0034699440002441406
2023-01-23 02:21:33.023299: step: 2092/530, loss: 0.09937791526317596
2023-01-23 02:21:34.158342: step: 2096/530, loss: 0.004464149475097656
2023-01-23 02:21:35.264886: step: 2100/530, loss: 0.008090019226074219
2023-01-23 02:21:36.359868: step: 2104/530, loss: 0.004296112339943647
2023-01-23 02:21:37.507906: step: 2108/530, loss: 0.007798671722412109
2023-01-23 02:21:38.601388: step: 2112/530, loss: 0.004139900207519531
2023-01-23 02:21:39.718256: step: 2116/530, loss: 0.027470208704471588
2023-01-23 02:21:40.828128: step: 2120/530, loss: 0.002394723938778043
==================================================
Loss: 0.032
--------------------
Dev: {'event': {'p': 0.6097297297297297, 'r': 0.7509986684420772, 'f1': 0.6730310262529833}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
Test: {'event': {'p': 0.6394052044609665, 'r': 0.8018648018648019, 'f1': 0.7114788004136504}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
Chinese: {'event': {'p': 0.6428571428571429, 'r': 0.8333333333333334, 'f1': 0.7258064516129034}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
Korean: {'event': {'p': 0.6792452830188679, 'r': 0.5714285714285714, 'f1': 0.6206896551724137}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
Russian: {'event': {'p': 0.4166666666666667, 'r': 0.4166666666666667, 'f1': 0.4166666666666667}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 16}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6449771689497716, 'r': 0.7523302263648469, 'f1': 0.6945298094652735}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Chinese: {'event': {'p': 0.6692644909887969, 'r': 0.8006993006993007, 'f1': 0.7291058636243036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Chinese: {'event': {'p': 0.6764705882352942, 'r': 0.8518518518518519, 'f1': 0.7540983606557378}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6449771689497716, 'r': 0.7523302263648469, 'f1': 0.6945298094652735}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Korean: {'event': {'p': 0.6692644909887969, 'r': 0.8006993006993007, 'f1': 0.7291058636243036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Korean: {'event': {'p': 0.7391304347826086, 'r': 0.5396825396825397, 'f1': 0.6238532110091742}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5971370143149284, 'r': 0.7776298268974701, 'f1': 0.6755349913244649}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Russian: {'event': {'p': 0.6401673640167364, 'r': 0.8024475524475524, 'f1': 0.7121799844840963}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Russian: {'event': {'p': 0.5897435897435898, 'r': 0.6388888888888888, 'f1': 0.6133333333333332}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
******************************
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 02:22:20.307208: step: 4/530, loss: 0.0014448165893554688
2023-01-23 02:22:21.421394: step: 8/530, loss: 0.010218429379165173
2023-01-23 02:22:22.553652: step: 12/530, loss: 0.07780561596155167
2023-01-23 02:22:23.705666: step: 16/530, loss: 0.7697376012802124
2023-01-23 02:22:24.810739: step: 20/530, loss: 0.026992131024599075
2023-01-23 02:22:25.931292: step: 24/530, loss: 0.005077171139419079
2023-01-23 02:22:27.035465: step: 28/530, loss: 0.0009737968211993575
2023-01-23 02:22:28.136861: step: 32/530, loss: 0.003857135772705078
2023-01-23 02:22:29.230631: step: 36/530, loss: 0.00013504027447197586
2023-01-23 02:22:30.337021: step: 40/530, loss: 0.005188846495002508
2023-01-23 02:22:31.474385: step: 44/530, loss: 0.0016004563076421618
2023-01-23 02:22:32.564448: step: 48/530, loss: 0.0042930603958666325
2023-01-23 02:22:33.678946: step: 52/530, loss: 0.010409165173768997
2023-01-23 02:22:34.802611: step: 56/530, loss: 0.057645462453365326
2023-01-23 02:22:35.909208: step: 60/530, loss: 0.02639141120016575
2023-01-23 02:22:37.053196: step: 64/530, loss: 0.000263023393927142
2023-01-23 02:22:38.166022: step: 68/530, loss: 0.002488470170646906
2023-01-23 02:22:39.292745: step: 72/530, loss: 0.004537153523415327
2023-01-23 02:22:40.390130: step: 76/530, loss: 0.0009065628401003778
2023-01-23 02:22:41.494380: step: 80/530, loss: 0.001922607421875
2023-01-23 02:22:42.596645: step: 84/530, loss: 0.0006616592290811241
2023-01-23 02:22:43.696101: step: 88/530, loss: 0.0059552667662501335
2023-01-23 02:22:44.811613: step: 92/530, loss: 0.0014220238663256168
2023-01-23 02:22:45.937904: step: 96/530, loss: 0.003830528352409601
2023-01-23 02:22:47.030417: step: 100/530, loss: 0.006626129150390625
2023-01-23 02:22:48.160242: step: 104/530, loss: 0.0006578445318154991
2023-01-23 02:22:49.252310: step: 108/530, loss: 0.6272986531257629
2023-01-23 02:22:50.343937: step: 112/530, loss: 0.0014255524147301912
2023-01-23 02:22:51.458932: step: 116/530, loss: 0.010433768853545189
2023-01-23 02:22:52.556157: step: 120/530, loss: 0.02750416100025177
2023-01-23 02:22:53.649948: step: 124/530, loss: 0.018428804352879524
2023-01-23 02:22:54.764961: step: 128/530, loss: 0.1627538651227951
2023-01-23 02:22:55.878975: step: 132/530, loss: 0.0002609252987895161
2023-01-23 02:22:56.997959: step: 136/530, loss: 0.049125757068395615
2023-01-23 02:22:58.078301: step: 140/530, loss: 0.0004446029488462955
2023-01-23 02:22:59.210803: step: 144/530, loss: 0.19546298682689667
2023-01-23 02:23:00.315867: step: 148/530, loss: 0.025575732812285423
2023-01-23 02:23:01.420341: step: 152/530, loss: 0.0008000374073162675
2023-01-23 02:23:02.572926: step: 156/530, loss: 0.012858295813202858
2023-01-23 02:23:03.669283: step: 160/530, loss: 0.015578222461044788
2023-01-23 02:23:04.763135: step: 164/530, loss: 0.05391797795891762
2023-01-23 02:23:05.867564: step: 168/530, loss: 0.0004455566231627017
2023-01-23 02:23:06.968123: step: 172/530, loss: 0.01202402077615261
2023-01-23 02:23:08.090072: step: 176/530, loss: 0.001851940294727683
2023-01-23 02:23:09.204060: step: 180/530, loss: 0.040908049792051315
2023-01-23 02:23:10.326474: step: 184/530, loss: 0.003222560975700617
2023-01-23 02:23:11.437414: step: 188/530, loss: 0.007326317019760609
2023-01-23 02:23:12.554488: step: 192/530, loss: 0.016690731048583984
2023-01-23 02:23:13.662682: step: 196/530, loss: 0.01824788935482502
2023-01-23 02:23:14.812612: step: 200/530, loss: 0.003951549530029297
2023-01-23 02:23:15.911346: step: 204/530, loss: 0.10313473641872406
2023-01-23 02:23:16.983482: step: 208/530, loss: 0.0009653091547079384
2023-01-23 02:23:18.096663: step: 212/530, loss: 0.004527473356574774
2023-01-23 02:23:19.183693: step: 216/530, loss: 0.006493187043815851
2023-01-23 02:23:20.274179: step: 220/530, loss: 0.005120372865349054
2023-01-23 02:23:21.407611: step: 224/530, loss: 0.009389781393110752
2023-01-23 02:23:22.538415: step: 228/530, loss: 0.11678294837474823
2023-01-23 02:23:23.629955: step: 232/530, loss: 0.01537313498556614
2023-01-23 02:23:24.781596: step: 236/530, loss: 0.001144027803093195
2023-01-23 02:23:25.896240: step: 240/530, loss: 0.006143069360405207
2023-01-23 02:23:26.991998: step: 244/530, loss: 0.0010856628650799394
2023-01-23 02:23:28.172918: step: 248/530, loss: 0.07156830281019211
2023-01-23 02:23:29.241741: step: 252/530, loss: 0.002552032470703125
2023-01-23 02:23:30.350009: step: 256/530, loss: 0.49163171648979187
2023-01-23 02:23:31.465307: step: 260/530, loss: 0.002796077635139227
2023-01-23 02:23:32.574162: step: 264/530, loss: 0.06929449737071991
2023-01-23 02:23:33.669149: step: 268/530, loss: 0.014154244214296341
2023-01-23 02:23:34.770723: step: 272/530, loss: 0.0005712032434530556
2023-01-23 02:23:35.874741: step: 276/530, loss: 0.018225956708192825
2023-01-23 02:23:37.003185: step: 280/530, loss: 0.08001823723316193
2023-01-23 02:23:38.093945: step: 284/530, loss: 0.007810402195900679
2023-01-23 02:23:39.237403: step: 288/530, loss: 0.033522892743349075
2023-01-23 02:23:40.344971: step: 292/530, loss: 0.0025755881797522306
2023-01-23 02:23:41.444822: step: 296/530, loss: 0.032387733459472656
2023-01-23 02:23:42.597418: step: 300/530, loss: 0.04019508138298988
2023-01-23 02:23:43.693763: step: 304/530, loss: 6.67572021484375e-05
2023-01-23 02:23:44.792692: step: 308/530, loss: 0.00018591881962493062
2023-01-23 02:23:45.892503: step: 312/530, loss: 0.0056649683974683285
2023-01-23 02:23:47.057215: step: 316/530, loss: 0.000644302403088659
2023-01-23 02:23:48.182473: step: 320/530, loss: 0.060369398444890976
2023-01-23 02:23:49.302316: step: 324/530, loss: 0.02066974714398384
2023-01-23 02:23:50.406504: step: 328/530, loss: 0.029868222773075104
2023-01-23 02:23:51.516561: step: 332/530, loss: 0.010073757730424404
2023-01-23 02:23:52.640968: step: 336/530, loss: 0.015745854005217552
2023-01-23 02:23:53.731599: step: 340/530, loss: 0.05678978189826012
2023-01-23 02:23:54.853059: step: 344/530, loss: 0.04481000825762749
2023-01-23 02:23:55.975776: step: 348/530, loss: 0.0015425682067871094
2023-01-23 02:23:57.095529: step: 352/530, loss: 0.0005639076698571444
2023-01-23 02:23:58.194420: step: 356/530, loss: 0.0049591064453125
2023-01-23 02:23:59.339923: step: 360/530, loss: 0.002276897430419922
2023-01-23 02:24:00.455898: step: 364/530, loss: 0.009274577721953392
2023-01-23 02:24:01.566603: step: 368/530, loss: 0.014779853634536266
2023-01-23 02:24:02.671654: step: 372/530, loss: 0.013894558884203434
2023-01-23 02:24:03.813052: step: 376/530, loss: 0.0003088951052632183
2023-01-23 02:24:04.941124: step: 380/530, loss: 0.034830473363399506
2023-01-23 02:24:06.019089: step: 384/530, loss: 0.0005460739484988153
2023-01-23 02:24:07.127381: step: 388/530, loss: 0.025982379913330078
2023-01-23 02:24:08.212289: step: 392/530, loss: 0.005467033479362726
2023-01-23 02:24:09.310583: step: 396/530, loss: 0.003776168916374445
2023-01-23 02:24:10.435116: step: 400/530, loss: 0.045676421374082565
2023-01-23 02:24:11.533005: step: 404/530, loss: 0.0002334117889404297
2023-01-23 02:24:12.654885: step: 408/530, loss: 0.031914424151182175
2023-01-23 02:24:13.778538: step: 412/530, loss: 0.04085502773523331
2023-01-23 02:24:14.894816: step: 416/530, loss: 0.0005533219082280993
2023-01-23 02:24:16.017439: step: 420/530, loss: 0.0004146576102357358
2023-01-23 02:24:17.123880: step: 424/530, loss: 0.015208244323730469
2023-01-23 02:24:18.224084: step: 428/530, loss: 0.06183815374970436
2023-01-23 02:24:19.316379: step: 432/530, loss: 0.005413723178207874
2023-01-23 02:24:20.436624: step: 436/530, loss: 0.0002808094141073525
2023-01-23 02:24:21.535783: step: 440/530, loss: 0.001342392060905695
2023-01-23 02:24:22.663035: step: 444/530, loss: 0.0001523971586721018
2023-01-23 02:24:23.765531: step: 448/530, loss: 0.12129536271095276
2023-01-23 02:24:24.858687: step: 452/530, loss: 0.02196807973086834
2023-01-23 02:24:25.964270: step: 456/530, loss: 0.002911186311393976
2023-01-23 02:24:27.087841: step: 460/530, loss: 0.019698239862918854
2023-01-23 02:24:28.204891: step: 464/530, loss: 0.0006911277887411416
2023-01-23 02:24:29.310868: step: 468/530, loss: 0.0035709382500499487
2023-01-23 02:24:30.400191: step: 472/530, loss: 0.022966384887695312
2023-01-23 02:24:31.512004: step: 476/530, loss: 0.007455635350197554
2023-01-23 02:24:32.646908: step: 480/530, loss: 0.00420646695420146
2023-01-23 02:24:33.761626: step: 484/530, loss: 0.029030703008174896
2023-01-23 02:24:34.877110: step: 488/530, loss: 0.008334135636687279
2023-01-23 02:24:35.982746: step: 492/530, loss: 0.058210086077451706
2023-01-23 02:24:37.134410: step: 496/530, loss: 0.01308908499777317
2023-01-23 02:24:38.214310: step: 500/530, loss: 0.013102435506880283
2023-01-23 02:24:39.309927: step: 504/530, loss: 0.018065262585878372
2023-01-23 02:24:40.412535: step: 508/530, loss: 0.020305633544921875
2023-01-23 02:24:41.530610: step: 512/530, loss: 0.03859882056713104
2023-01-23 02:24:42.648946: step: 516/530, loss: 0.012969780713319778
2023-01-23 02:24:43.768390: step: 520/530, loss: 0.004222106654196978
2023-01-23 02:24:44.846996: step: 524/530, loss: 0.0008533478248864412
2023-01-23 02:24:45.930261: step: 528/530, loss: 0.00029535291832871735
2023-01-23 02:24:47.067341: step: 532/530, loss: 0.02418975904583931
2023-01-23 02:24:48.165691: step: 536/530, loss: 0.0007802486652508378
2023-01-23 02:24:49.272284: step: 540/530, loss: 0.07002153992652893
2023-01-23 02:24:50.408344: step: 544/530, loss: 0.00782232265919447
2023-01-23 02:24:51.504820: step: 548/530, loss: 0.026316644623875618
2023-01-23 02:24:52.621281: step: 552/530, loss: 0.08285784721374512
2023-01-23 02:24:53.727445: step: 556/530, loss: 0.13837261497974396
2023-01-23 02:24:54.834359: step: 560/530, loss: 0.0020817758049815893
2023-01-23 02:24:55.964867: step: 564/530, loss: 0.00945348758250475
2023-01-23 02:24:57.102718: step: 568/530, loss: 0.0014045715797692537
2023-01-23 02:24:58.195184: step: 572/530, loss: 0.049512770026922226
2023-01-23 02:24:59.296370: step: 576/530, loss: 0.016512585803866386
2023-01-23 02:25:00.433077: step: 580/530, loss: 0.0007040023920126259
2023-01-23 02:25:01.587667: step: 584/530, loss: 0.014866066165268421
2023-01-23 02:25:02.711571: step: 588/530, loss: 0.015486050397157669
2023-01-23 02:25:03.786085: step: 592/530, loss: 0.026675604283809662
2023-01-23 02:25:04.859332: step: 596/530, loss: 0.4199257791042328
2023-01-23 02:25:05.955439: step: 600/530, loss: 0.005817413330078125
2023-01-23 02:25:07.035947: step: 604/530, loss: 0.00019946099200751632
2023-01-23 02:25:08.134398: step: 608/530, loss: 0.04819921776652336
2023-01-23 02:25:09.262247: step: 612/530, loss: 0.04078993573784828
2023-01-23 02:25:10.384249: step: 616/530, loss: 0.07472534477710724
2023-01-23 02:25:11.519053: step: 620/530, loss: 5.755424717790447e-05
2023-01-23 02:25:12.623610: step: 624/530, loss: 0.01546626165509224
2023-01-23 02:25:13.736018: step: 628/530, loss: 0.021909713745117188
2023-01-23 02:25:14.870672: step: 632/530, loss: 0.0010271072387695312
2023-01-23 02:25:15.969196: step: 636/530, loss: 0.004310893826186657
2023-01-23 02:25:17.078548: step: 640/530, loss: 0.0010842562187463045
2023-01-23 02:25:18.172696: step: 644/530, loss: 0.00028781889704987407
2023-01-23 02:25:19.279095: step: 648/530, loss: 0.00011148452904308215
2023-01-23 02:25:20.403094: step: 652/530, loss: 0.00046243667020462453
2023-01-23 02:25:21.538230: step: 656/530, loss: 0.011238956823945045
2023-01-23 02:25:22.622261: step: 660/530, loss: 0.003329467959702015
2023-01-23 02:25:23.754986: step: 664/530, loss: 0.0005368232959881425
2023-01-23 02:25:24.847102: step: 668/530, loss: 0.011597633361816406
2023-01-23 02:25:25.934435: step: 672/530, loss: 0.0012506007915362716
2023-01-23 02:25:27.059419: step: 676/530, loss: 0.06612415611743927
2023-01-23 02:25:28.154904: step: 680/530, loss: 0.05307193100452423
2023-01-23 02:25:29.257697: step: 684/530, loss: 0.04668540880084038
2023-01-23 02:25:30.372943: step: 688/530, loss: 0.04380912706255913
2023-01-23 02:25:31.481486: step: 692/530, loss: 0.017929984256625175
2023-01-23 02:25:32.597095: step: 696/530, loss: 0.006539058871567249
2023-01-23 02:25:33.710364: step: 700/530, loss: 0.0019691467750817537
2023-01-23 02:25:34.850052: step: 704/530, loss: 0.0007365703349933028
2023-01-23 02:25:35.971596: step: 708/530, loss: 0.010886765085160732
2023-01-23 02:25:37.065274: step: 712/530, loss: 0.03156595304608345
2023-01-23 02:25:38.171856: step: 716/530, loss: 0.029905986040830612
2023-01-23 02:25:39.267572: step: 720/530, loss: 0.002662849612534046
2023-01-23 02:25:40.405687: step: 724/530, loss: 0.024061013013124466
2023-01-23 02:25:41.525351: step: 728/530, loss: 0.004641151521354914
2023-01-23 02:25:42.613698: step: 732/530, loss: 0.006412720773369074
2023-01-23 02:25:43.708941: step: 736/530, loss: 0.06767654418945312
2023-01-23 02:25:44.790570: step: 740/530, loss: 0.019868278875947
2023-01-23 02:25:45.889612: step: 744/530, loss: 0.01916370540857315
2023-01-23 02:25:46.991174: step: 748/530, loss: 0.07350406795740128
2023-01-23 02:25:48.079379: step: 752/530, loss: 0.0066051483154296875
2023-01-23 02:25:49.185405: step: 756/530, loss: 0.1249973326921463
2023-01-23 02:25:50.285515: step: 760/530, loss: 0.03013324737548828
2023-01-23 02:25:51.401500: step: 764/530, loss: 0.00017642974853515625
2023-01-23 02:25:52.519543: step: 768/530, loss: 0.00016336441331077367
2023-01-23 02:25:53.630764: step: 772/530, loss: 0.01298151072114706
2023-01-23 02:25:54.711163: step: 776/530, loss: 0.024737929925322533
2023-01-23 02:25:55.831722: step: 780/530, loss: 0.00292549142614007
2023-01-23 02:25:56.949170: step: 784/530, loss: 7.390975952148438e-05
2023-01-23 02:25:58.052241: step: 788/530, loss: 0.0022426603827625513
2023-01-23 02:25:59.147569: step: 792/530, loss: 0.07834243774414062
2023-01-23 02:26:00.269110: step: 796/530, loss: 0.005349159240722656
2023-01-23 02:26:01.372463: step: 800/530, loss: 0.022838031873106956
2023-01-23 02:26:02.493725: step: 804/530, loss: 0.045226193964481354
2023-01-23 02:26:03.609778: step: 808/530, loss: 0.00441131554543972
2023-01-23 02:26:04.708218: step: 812/530, loss: 0.4004550874233246
2023-01-23 02:26:05.844136: step: 816/530, loss: 0.048462674021720886
2023-01-23 02:26:06.953532: step: 820/530, loss: 0.0003896713024005294
2023-01-23 02:26:08.076353: step: 824/530, loss: 0.002521391026675701
2023-01-23 02:26:09.209842: step: 828/530, loss: 0.04993181303143501
2023-01-23 02:26:10.328330: step: 832/530, loss: 0.006475258152931929
2023-01-23 02:26:11.436672: step: 836/530, loss: 0.0036249160766601562
2023-01-23 02:26:12.524065: step: 840/530, loss: 0.001237201620824635
2023-01-23 02:26:13.635821: step: 844/530, loss: 0.012454223819077015
2023-01-23 02:26:14.735332: step: 848/530, loss: 0.04208245128393173
2023-01-23 02:26:15.842103: step: 852/530, loss: 0.04520421102643013
2023-01-23 02:26:16.925854: step: 856/530, loss: 0.025693703442811966
2023-01-23 02:26:18.050636: step: 860/530, loss: 0.00781869888305664
2023-01-23 02:26:19.135964: step: 864/530, loss: 0.018005656078457832
2023-01-23 02:26:20.265873: step: 868/530, loss: 0.007506656926125288
2023-01-23 02:26:21.381216: step: 872/530, loss: 0.0045302389189600945
2023-01-23 02:26:22.509099: step: 876/530, loss: 0.006920624058693647
2023-01-23 02:26:23.623057: step: 880/530, loss: 0.0008099555852822959
2023-01-23 02:26:24.740883: step: 884/530, loss: 0.006557369604706764
2023-01-23 02:26:25.869016: step: 888/530, loss: 0.03865756839513779
2023-01-23 02:26:26.960776: step: 892/530, loss: 0.03716907650232315
2023-01-23 02:26:28.055970: step: 896/530, loss: 0.012309838086366653
2023-01-23 02:26:29.166541: step: 900/530, loss: 0.09240760654211044
2023-01-23 02:26:30.246821: step: 904/530, loss: 0.0033102035522460938
2023-01-23 02:26:31.335076: step: 908/530, loss: 0.0028446197975426912
2023-01-23 02:26:32.445963: step: 912/530, loss: 0.006618213839828968
2023-01-23 02:26:33.549277: step: 916/530, loss: 0.00742950476706028
2023-01-23 02:26:34.669512: step: 920/530, loss: 0.0037856101989746094
2023-01-23 02:26:35.769798: step: 924/530, loss: 0.33206939697265625
2023-01-23 02:26:36.906259: step: 928/530, loss: 0.01862478442490101
2023-01-23 02:26:38.041128: step: 932/530, loss: 0.018245648592710495
2023-01-23 02:26:39.112071: step: 936/530, loss: 0.005423545837402344
2023-01-23 02:26:40.192748: step: 940/530, loss: 0.0021450042258948088
2023-01-23 02:26:41.284277: step: 944/530, loss: 0.01322860736399889
2023-01-23 02:26:42.397674: step: 948/530, loss: 0.0042719366028904915
2023-01-23 02:26:43.493027: step: 952/530, loss: 0.008036327548325062
2023-01-23 02:26:44.591468: step: 956/530, loss: 0.001439094659872353
2023-01-23 02:26:45.698503: step: 960/530, loss: 0.004388093948364258
2023-01-23 02:26:46.825922: step: 964/530, loss: 0.002310418989509344
2023-01-23 02:26:47.924145: step: 968/530, loss: 0.05793743208050728
2023-01-23 02:26:49.061478: step: 972/530, loss: 0.016104554757475853
2023-01-23 02:26:50.155907: step: 976/530, loss: 0.0019298553233966231
2023-01-23 02:26:51.245852: step: 980/530, loss: 0.0005709647666662931
2023-01-23 02:26:52.326301: step: 984/530, loss: 0.013628673739731312
2023-01-23 02:26:53.434563: step: 988/530, loss: 0.0021984102204442024
2023-01-23 02:26:54.575080: step: 992/530, loss: 0.0018981933826580644
2023-01-23 02:26:55.725819: step: 996/530, loss: 0.0006200313218869269
2023-01-23 02:26:56.825392: step: 1000/530, loss: 0.0013141632080078125
2023-01-23 02:26:57.927986: step: 1004/530, loss: 0.0003028392675332725
2023-01-23 02:26:59.044306: step: 1008/530, loss: 0.0624542236328125
2023-01-23 02:27:00.177819: step: 1012/530, loss: 0.010038947686553001
2023-01-23 02:27:01.292604: step: 1016/530, loss: 0.00207347865216434
2023-01-23 02:27:02.397792: step: 1020/530, loss: 0.0008069038158282638
2023-01-23 02:27:03.542234: step: 1024/530, loss: 0.022597646340727806
2023-01-23 02:27:04.641508: step: 1028/530, loss: 0.01680469512939453
2023-01-23 02:27:05.750157: step: 1032/530, loss: 0.0006066322675906122
2023-01-23 02:27:06.874363: step: 1036/530, loss: 0.030229568481445312
2023-01-23 02:27:07.993448: step: 1040/530, loss: 0.006845283322036266
2023-01-23 02:27:09.105816: step: 1044/530, loss: 0.010268783196806908
2023-01-23 02:27:10.222732: step: 1048/530, loss: 0.06993541866540909
2023-01-23 02:27:11.322465: step: 1052/530, loss: 0.005876445677131414
2023-01-23 02:27:12.457567: step: 1056/530, loss: 0.010522461496293545
2023-01-23 02:27:13.575993: step: 1060/530, loss: 0.06326141208410263
2023-01-23 02:27:14.714974: step: 1064/530, loss: 0.00012912749662064016
2023-01-23 02:27:15.817920: step: 1068/530, loss: 0.00051965715829283
2023-01-23 02:27:16.920474: step: 1072/530, loss: 0.00010814666165970266
2023-01-23 02:27:18.017957: step: 1076/530, loss: 0.047141075134277344
2023-01-23 02:27:19.138985: step: 1080/530, loss: 0.015032959170639515
2023-01-23 02:27:20.250077: step: 1084/530, loss: 0.004160690121352673
2023-01-23 02:27:21.372982: step: 1088/530, loss: 0.015010643750429153
2023-01-23 02:27:22.485314: step: 1092/530, loss: 0.003953408915549517
2023-01-23 02:27:23.600590: step: 1096/530, loss: 0.007323170080780983
2023-01-23 02:27:24.710330: step: 1100/530, loss: 0.04953975975513458
2023-01-23 02:27:25.837170: step: 1104/530, loss: 0.008510207757353783
2023-01-23 02:27:26.943500: step: 1108/530, loss: 0.006116438191384077
2023-01-23 02:27:28.084383: step: 1112/530, loss: 0.05720578506588936
2023-01-23 02:27:29.178958: step: 1116/530, loss: 0.0023756027221679688
2023-01-23 02:27:30.315663: step: 1120/530, loss: 0.03934650495648384
2023-01-23 02:27:31.411153: step: 1124/530, loss: 0.052307795733213425
2023-01-23 02:27:32.545908: step: 1128/530, loss: 0.0009531974792480469
2023-01-23 02:27:33.673467: step: 1132/530, loss: 0.08214350044727325
2023-01-23 02:27:34.779023: step: 1136/530, loss: 0.012887381948530674
2023-01-23 02:27:35.881105: step: 1140/530, loss: 0.025521278381347656
2023-01-23 02:27:36.985605: step: 1144/530, loss: 0.013566065579652786
2023-01-23 02:27:38.101403: step: 1148/530, loss: 0.0010683536529541016
2023-01-23 02:27:39.212151: step: 1152/530, loss: 0.13899211585521698
2023-01-23 02:27:40.301543: step: 1156/530, loss: 0.018077468499541283
2023-01-23 02:27:41.424521: step: 1160/530, loss: 0.263627827167511
2023-01-23 02:27:42.531902: step: 1164/530, loss: 4.711151268566027e-05
2023-01-23 02:27:43.621818: step: 1168/530, loss: 0.0001961708185262978
2023-01-23 02:27:44.722990: step: 1172/530, loss: 0.0324854850769043
2023-01-23 02:27:45.846326: step: 1176/530, loss: 0.44663000106811523
2023-01-23 02:27:46.937656: step: 1180/530, loss: 0.00045080186100676656
2023-01-23 02:27:48.081509: step: 1184/530, loss: 0.015191745944321156
2023-01-23 02:27:49.197071: step: 1188/530, loss: 0.004278946202248335
2023-01-23 02:27:50.323382: step: 1192/530, loss: 0.001898098038509488
2023-01-23 02:27:51.440070: step: 1196/530, loss: 0.1506543606519699
2023-01-23 02:27:52.520349: step: 1200/530, loss: 0.002842593239620328
2023-01-23 02:27:53.622313: step: 1204/530, loss: 0.0010952949523925781
2023-01-23 02:27:54.741743: step: 1208/530, loss: 0.0014229774242267013
2023-01-23 02:27:55.852506: step: 1212/530, loss: 0.002802085829898715
2023-01-23 02:27:56.962962: step: 1216/530, loss: 0.001006698701530695
2023-01-23 02:27:58.057810: step: 1220/530, loss: 0.002110767411068082
2023-01-23 02:27:59.163754: step: 1224/530, loss: 0.00084686279296875
2023-01-23 02:28:00.286163: step: 1228/530, loss: 0.046021416783332825
2023-01-23 02:28:01.420885: step: 1232/530, loss: 0.011029434390366077
2023-01-23 02:28:02.524467: step: 1236/530, loss: 0.009351730346679688
2023-01-23 02:28:03.666989: step: 1240/530, loss: 0.09081153571605682
2023-01-23 02:28:04.760898: step: 1244/530, loss: 0.0023753151763230562
2023-01-23 02:28:05.859427: step: 1248/530, loss: 0.005281639285385609
2023-01-23 02:28:06.967060: step: 1252/530, loss: 0.03441214561462402
2023-01-23 02:28:08.079922: step: 1256/530, loss: 0.018236350268125534
2023-01-23 02:28:09.202524: step: 1260/530, loss: 0.016182422637939453
2023-01-23 02:28:10.322915: step: 1264/530, loss: 0.03475761413574219
2023-01-23 02:28:11.369934: step: 1268/530, loss: 0.015668869018554688
2023-01-23 02:28:12.446313: step: 1272/530, loss: 0.0037629129365086555
2023-01-23 02:28:13.568911: step: 1276/530, loss: 0.013821984641253948
2023-01-23 02:28:14.702157: step: 1280/530, loss: 0.008289003744721413
2023-01-23 02:28:15.800915: step: 1284/530, loss: 0.010158920660614967
2023-01-23 02:28:16.956133: step: 1288/530, loss: 0.06707501411437988
2023-01-23 02:28:18.069049: step: 1292/530, loss: 0.016602326184511185
2023-01-23 02:28:19.144040: step: 1296/530, loss: 0.0032186508178710938
2023-01-23 02:28:20.268788: step: 1300/530, loss: 0.0208711139857769
2023-01-23 02:28:21.398652: step: 1304/530, loss: 0.0171751007437706
2023-01-23 02:28:22.499184: step: 1308/530, loss: 0.0004302978632040322
2023-01-23 02:28:23.622225: step: 1312/530, loss: 0.007154989521950483
2023-01-23 02:28:24.708003: step: 1316/530, loss: 0.0006483078468590975
2023-01-23 02:28:25.833091: step: 1320/530, loss: 0.0193968303501606
2023-01-23 02:28:26.924096: step: 1324/530, loss: 0.002743244171142578
2023-01-23 02:28:28.065269: step: 1328/530, loss: 0.055486202239990234
2023-01-23 02:28:29.195266: step: 1332/530, loss: 3.814696901827119e-05
2023-01-23 02:28:30.324239: step: 1336/530, loss: 0.002487754914909601
2023-01-23 02:28:31.417278: step: 1340/530, loss: 0.06938514858484268
2023-01-23 02:28:32.505889: step: 1344/530, loss: 0.006404876708984375
2023-01-23 02:28:33.636695: step: 1348/530, loss: 0.0020507811568677425
2023-01-23 02:28:34.732515: step: 1352/530, loss: 6.337166269076988e-05
2023-01-23 02:28:35.841426: step: 1356/530, loss: 0.011004543863236904
2023-01-23 02:28:36.969549: step: 1360/530, loss: 0.011021668091416359
2023-01-23 02:28:38.134343: step: 1364/530, loss: 0.00020847321138717234
2023-01-23 02:28:39.258140: step: 1368/530, loss: 0.01799039915204048
2023-01-23 02:28:40.371421: step: 1372/530, loss: 0.009519101120531559
2023-01-23 02:28:41.467644: step: 1376/530, loss: 0.0018707275157794356
2023-01-23 02:28:42.603825: step: 1380/530, loss: 0.004285669419914484
2023-01-23 02:28:43.711658: step: 1384/530, loss: 0.01641540601849556
2023-01-23 02:28:44.835596: step: 1388/530, loss: 0.02902202680706978
2023-01-23 02:28:45.938983: step: 1392/530, loss: 0.06374301761388779
2023-01-23 02:28:47.040959: step: 1396/530, loss: 0.02755141258239746
2023-01-23 02:28:48.148196: step: 1400/530, loss: 0.04143853113055229
2023-01-23 02:28:49.308253: step: 1404/530, loss: 0.008482742123305798
2023-01-23 02:28:50.429122: step: 1408/530, loss: 0.01750326156616211
2023-01-23 02:28:51.605395: step: 1412/530, loss: 0.005590343382209539
2023-01-23 02:28:52.735993: step: 1416/530, loss: 0.01011571940034628
2023-01-23 02:28:53.887120: step: 1420/530, loss: 0.04805183783173561
2023-01-23 02:28:55.038037: step: 1424/530, loss: 0.03670348972082138
2023-01-23 02:28:56.150172: step: 1428/530, loss: 0.0006895065307617188
2023-01-23 02:28:57.280085: step: 1432/530, loss: 0.009813213720917702
2023-01-23 02:28:58.391731: step: 1436/530, loss: 0.09463150799274445
2023-01-23 02:28:59.513554: step: 1440/530, loss: 0.0005071639898233116
2023-01-23 02:29:00.613863: step: 1444/530, loss: 0.012918567284941673
2023-01-23 02:29:01.717643: step: 1448/530, loss: 0.0014408588176593184
2023-01-23 02:29:02.842424: step: 1452/530, loss: 0.05398865044116974
2023-01-23 02:29:03.970179: step: 1456/530, loss: 0.0016940117347985506
2023-01-23 02:29:05.072604: step: 1460/530, loss: 0.00015649796114303172
2023-01-23 02:29:06.160294: step: 1464/530, loss: 0.04098358377814293
2023-01-23 02:29:07.282296: step: 1468/530, loss: 0.08411483466625214
2023-01-23 02:29:08.386830: step: 1472/530, loss: 0.01969590224325657
2023-01-23 02:29:09.504302: step: 1476/530, loss: 0.023730851709842682
2023-01-23 02:29:10.612042: step: 1480/530, loss: 1.133135437965393
2023-01-23 02:29:11.726221: step: 1484/530, loss: 0.005062961485236883
2023-01-23 02:29:12.862581: step: 1488/530, loss: 0.03160534054040909
2023-01-23 02:29:13.984718: step: 1492/530, loss: 0.0005936622619628906
2023-01-23 02:29:15.082539: step: 1496/530, loss: 0.0010514259338378906
2023-01-23 02:29:16.197912: step: 1500/530, loss: 0.019589615985751152
2023-01-23 02:29:17.286034: step: 1504/530, loss: 0.03720245137810707
2023-01-23 02:29:18.388173: step: 1508/530, loss: 0.004843330476433039
2023-01-23 02:29:19.532806: step: 1512/530, loss: 0.010355734266340733
2023-01-23 02:29:20.635688: step: 1516/530, loss: 0.003432035678997636
2023-01-23 02:29:21.758837: step: 1520/530, loss: 0.0013755798572674394
2023-01-23 02:29:22.857106: step: 1524/530, loss: 0.0015692710876464844
2023-01-23 02:29:23.959729: step: 1528/530, loss: 0.0005036354414187372
2023-01-23 02:29:25.067341: step: 1532/530, loss: 0.009550381451845169
2023-01-23 02:29:26.168724: step: 1536/530, loss: 0.02171912230551243
2023-01-23 02:29:27.314300: step: 1540/530, loss: 0.008292770013213158
2023-01-23 02:29:28.445887: step: 1544/530, loss: 0.0006641388172283769
2023-01-23 02:29:29.519094: step: 1548/530, loss: 0.004772603511810303
2023-01-23 02:29:30.636847: step: 1552/530, loss: 0.06319675594568253
2023-01-23 02:29:31.736082: step: 1556/530, loss: 0.01020803488790989
2023-01-23 02:29:32.848467: step: 1560/530, loss: 0.03091888502240181
2023-01-23 02:29:33.953175: step: 1564/530, loss: 0.1375046670436859
2023-01-23 02:29:35.065385: step: 1568/530, loss: 0.1253339797258377
2023-01-23 02:29:36.190143: step: 1572/530, loss: 0.6169979572296143
2023-01-23 02:29:37.316078: step: 1576/530, loss: 0.00706715602427721
2023-01-23 02:29:38.426185: step: 1580/530, loss: 0.02337600104510784
2023-01-23 02:29:39.547262: step: 1584/530, loss: 0.0005942345014773309
2023-01-23 02:29:40.652295: step: 1588/530, loss: 0.0015623093349859118
2023-01-23 02:29:41.769013: step: 1592/530, loss: 0.004889869596809149
2023-01-23 02:29:42.882725: step: 1596/530, loss: 0.0002951383648905903
2023-01-23 02:29:44.004247: step: 1600/530, loss: 0.023521041497588158
2023-01-23 02:29:45.109784: step: 1604/530, loss: 0.002965402789413929
2023-01-23 02:29:46.202053: step: 1608/530, loss: 0.02208738401532173
2023-01-23 02:29:47.350017: step: 1612/530, loss: 0.0007821082836017013
2023-01-23 02:29:48.488432: step: 1616/530, loss: 0.026735972613096237
2023-01-23 02:29:49.622009: step: 1620/530, loss: 0.04595356062054634
2023-01-23 02:29:50.711440: step: 1624/530, loss: 0.01731548272073269
2023-01-23 02:29:51.842912: step: 1628/530, loss: 7.343292963923886e-06
2023-01-23 02:29:53.030335: step: 1632/530, loss: 0.05352676659822464
2023-01-23 02:29:54.176960: step: 1636/530, loss: 0.03643341362476349
2023-01-23 02:29:55.262575: step: 1640/530, loss: 0.0003656387561932206
2023-01-23 02:29:56.403326: step: 1644/530, loss: 0.0871182456612587
2023-01-23 02:29:57.519378: step: 1648/530, loss: 0.021767806261777878
2023-01-23 02:29:58.651276: step: 1652/530, loss: 0.1720612645149231
2023-01-23 02:29:59.770887: step: 1656/530, loss: 0.06254511326551437
2023-01-23 02:30:00.885131: step: 1660/530, loss: 0.01138153113424778
2023-01-23 02:30:02.002590: step: 1664/530, loss: 0.03359236940741539
2023-01-23 02:30:03.109054: step: 1668/530, loss: 0.001922559691593051
2023-01-23 02:30:04.194030: step: 1672/530, loss: 0.19638358056545258
2023-01-23 02:30:05.319117: step: 1676/530, loss: 0.0018589973915368319
2023-01-23 02:30:06.421714: step: 1680/530, loss: 0.007766914553940296
2023-01-23 02:30:07.545030: step: 1684/530, loss: 0.003131961915642023
2023-01-23 02:30:08.651497: step: 1688/530, loss: 0.001168537070043385
2023-01-23 02:30:09.762765: step: 1692/530, loss: 0.0058494568802416325
2023-01-23 02:30:10.891527: step: 1696/530, loss: 0.01965651474893093
2023-01-23 02:30:11.990299: step: 1700/530, loss: 0.0018943786853924394
2023-01-23 02:30:13.095729: step: 1704/530, loss: 0.12588845193386078
2023-01-23 02:30:14.225081: step: 1708/530, loss: 0.042249299585819244
2023-01-23 02:30:15.314083: step: 1712/530, loss: 0.003041601274162531
2023-01-23 02:30:16.438589: step: 1716/530, loss: 0.004197502508759499
2023-01-23 02:30:17.581073: step: 1720/530, loss: 0.12388534843921661
2023-01-23 02:30:18.666191: step: 1724/530, loss: 0.01287984848022461
2023-01-23 02:30:19.799626: step: 1728/530, loss: 0.04360847547650337
2023-01-23 02:30:20.944504: step: 1732/530, loss: 0.04967312887310982
2023-01-23 02:30:22.056420: step: 1736/530, loss: 0.0017263413174077868
2023-01-23 02:30:23.159428: step: 1740/530, loss: 0.0005640029557980597
2023-01-23 02:30:24.289992: step: 1744/530, loss: 0.05066833272576332
2023-01-23 02:30:25.443498: step: 1748/530, loss: 0.012136077508330345
2023-01-23 02:30:26.542080: step: 1752/530, loss: 0.007398128975182772
2023-01-23 02:30:27.654806: step: 1756/530, loss: 0.06604347378015518
2023-01-23 02:30:28.839772: step: 1760/530, loss: 0.07191848754882812
2023-01-23 02:30:29.959046: step: 1764/530, loss: 0.0009829520713537931
2023-01-23 02:30:31.068423: step: 1768/530, loss: 0.0003837585391011089
2023-01-23 02:30:32.178363: step: 1772/530, loss: 0.07267170399427414
2023-01-23 02:30:33.269025: step: 1776/530, loss: 0.04729194566607475
2023-01-23 02:30:34.352511: step: 1780/530, loss: 0.0005975246313028038
2023-01-23 02:30:35.464694: step: 1784/530, loss: 0.0007963180541992188
2023-01-23 02:30:36.581974: step: 1788/530, loss: 0.003995037171989679
2023-01-23 02:30:37.670123: step: 1792/530, loss: 0.0062049152329564095
2023-01-23 02:30:38.774045: step: 1796/530, loss: 0.0180877223610878
2023-01-23 02:30:39.879245: step: 1800/530, loss: 0.03542742878198624
2023-01-23 02:30:40.987510: step: 1804/530, loss: 0.007823467254638672
2023-01-23 02:30:42.122207: step: 1808/530, loss: 0.03264360502362251
2023-01-23 02:30:43.252170: step: 1812/530, loss: 0.032199956476688385
2023-01-23 02:30:44.357630: step: 1816/530, loss: 0.00252113351598382
2023-01-23 02:30:45.501269: step: 1820/530, loss: 0.010976314544677734
2023-01-23 02:30:46.578755: step: 1824/530, loss: 0.022455643862485886
2023-01-23 02:30:47.682559: step: 1828/530, loss: 0.0027786255814135075
2023-01-23 02:30:48.804951: step: 1832/530, loss: 0.14431552588939667
2023-01-23 02:30:49.906569: step: 1836/530, loss: 0.014445018954575062
2023-01-23 02:30:51.002016: step: 1840/530, loss: 0.04419555887579918
2023-01-23 02:30:52.132935: step: 1844/530, loss: 0.00693435687571764
2023-01-23 02:30:53.246422: step: 1848/530, loss: 0.008030891418457031
2023-01-23 02:30:54.331819: step: 1852/530, loss: 0.004249763675034046
2023-01-23 02:30:55.448722: step: 1856/530, loss: 0.05397143214941025
2023-01-23 02:30:56.558161: step: 1860/530, loss: 0.050740115344524384
2023-01-23 02:30:57.686742: step: 1864/530, loss: 0.008066559210419655
2023-01-23 02:30:58.782519: step: 1868/530, loss: 0.007135581690818071
2023-01-23 02:30:59.868600: step: 1872/530, loss: 0.01119381282478571
2023-01-23 02:31:00.995809: step: 1876/530, loss: 0.01633424684405327
2023-01-23 02:31:02.134414: step: 1880/530, loss: 0.001943397568538785
2023-01-23 02:31:03.252076: step: 1884/530, loss: 0.02282531186938286
2023-01-23 02:31:04.391931: step: 1888/530, loss: 0.002081585116684437
2023-01-23 02:31:05.516017: step: 1892/530, loss: 0.0017817497719079256
2023-01-23 02:31:06.592531: step: 1896/530, loss: 0.0016619681846350431
2023-01-23 02:31:07.675922: step: 1900/530, loss: 0.0036008835304528475
2023-01-23 02:31:08.810344: step: 1904/530, loss: 0.004469871520996094
2023-01-23 02:31:09.886622: step: 1908/530, loss: 0.0018893718952313066
2023-01-23 02:31:10.991823: step: 1912/530, loss: 0.00920410268008709
2023-01-23 02:31:12.116698: step: 1916/530, loss: 0.025570059195160866
2023-01-23 02:31:13.236669: step: 1920/530, loss: 0.022469710558652878
2023-01-23 02:31:14.364018: step: 1924/530, loss: 0.0013681412674486637
2023-01-23 02:31:15.520120: step: 1928/530, loss: 0.0003390312194824219
2023-01-23 02:31:16.611065: step: 1932/530, loss: 0.006837748922407627
2023-01-23 02:31:17.724682: step: 1936/530, loss: 0.01760253868997097
2023-01-23 02:31:18.854822: step: 1940/530, loss: 0.02842344157397747
2023-01-23 02:31:19.945176: step: 1944/530, loss: 0.004081821534782648
2023-01-23 02:31:21.075202: step: 1948/530, loss: 0.024408437311649323
2023-01-23 02:31:22.168757: step: 1952/530, loss: 0.0008460045210085809
2023-01-23 02:31:23.278415: step: 1956/530, loss: 0.0230820644646883
2023-01-23 02:31:24.399011: step: 1960/530, loss: 0.004494190216064453
2023-01-23 02:31:25.523612: step: 1964/530, loss: 0.01319127157330513
2023-01-23 02:31:26.647479: step: 1968/530, loss: 0.0295123104006052
2023-01-23 02:31:27.786136: step: 1972/530, loss: 0.03885011747479439
2023-01-23 02:31:28.919720: step: 1976/530, loss: 0.011473655700683594
2023-01-23 02:31:30.024748: step: 1980/530, loss: 0.013992500491440296
2023-01-23 02:31:31.153161: step: 1984/530, loss: 0.034926414489746094
2023-01-23 02:31:32.272305: step: 1988/530, loss: 0.006973314099013805
2023-01-23 02:31:33.351972: step: 1992/530, loss: 0.014472723007202148
2023-01-23 02:31:34.464164: step: 1996/530, loss: 0.04264340549707413
2023-01-23 02:31:35.574579: step: 2000/530, loss: 0.012286758050322533
2023-01-23 02:31:36.683989: step: 2004/530, loss: 0.011006737127900124
2023-01-23 02:31:37.798152: step: 2008/530, loss: 0.006806612014770508
2023-01-23 02:31:38.919311: step: 2012/530, loss: 0.0011075973743572831
2023-01-23 02:31:40.030008: step: 2016/530, loss: 0.00903930701315403
2023-01-23 02:31:41.143825: step: 2020/530, loss: 0.030427835881710052
2023-01-23 02:31:42.237785: step: 2024/530, loss: 0.016294801607728004
2023-01-23 02:31:43.362120: step: 2028/530, loss: 0.048102568835020065
2023-01-23 02:31:44.458359: step: 2032/530, loss: 0.026589298620820045
2023-01-23 02:31:45.570442: step: 2036/530, loss: 0.030198097229003906
2023-01-23 02:31:46.683148: step: 2040/530, loss: 0.0032948972657322884
2023-01-23 02:31:47.813260: step: 2044/530, loss: 0.005795955657958984
2023-01-23 02:31:48.910605: step: 2048/530, loss: 0.04451313242316246
2023-01-23 02:31:49.986896: step: 2052/530, loss: 0.024013806134462357
2023-01-23 02:31:51.096700: step: 2056/530, loss: 0.003892520209774375
2023-01-23 02:31:52.182178: step: 2060/530, loss: 0.015264512039721012
2023-01-23 02:31:53.311630: step: 2064/530, loss: 0.0035377503372728825
2023-01-23 02:31:54.451799: step: 2068/530, loss: 0.004120826721191406
2023-01-23 02:31:55.569450: step: 2072/530, loss: 0.03057260625064373
2023-01-23 02:31:56.688859: step: 2076/530, loss: 0.013895321637392044
2023-01-23 02:31:57.812298: step: 2080/530, loss: 0.03908119350671768
2023-01-23 02:31:58.906493: step: 2084/530, loss: 0.006292152684181929
2023-01-23 02:32:00.033457: step: 2088/530, loss: 0.030089663341641426
2023-01-23 02:32:01.171108: step: 2092/530, loss: 0.07492685317993164
2023-01-23 02:32:02.248455: step: 2096/530, loss: 0.08126763999462128
2023-01-23 02:32:03.362851: step: 2100/530, loss: 0.08265075832605362
2023-01-23 02:32:04.505985: step: 2104/530, loss: 0.03354005888104439
2023-01-23 02:32:05.605406: step: 2108/530, loss: 6.65664701955393e-05
2023-01-23 02:32:06.720448: step: 2112/530, loss: 0.014124584384262562
2023-01-23 02:32:07.842940: step: 2116/530, loss: 0.02004718966782093
2023-01-23 02:32:08.958013: step: 2120/530, loss: 0.0010485649108886719
==================================================
Loss: 0.031
--------------------
Dev: {'event': {'p': 0.6169527896995708, 'r': 0.7656458055925432, 'f1': 0.683303624480095}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
Test: {'event': {'p': 0.6591454632741238, 'r': 0.8001165501165501, 'f1': 0.7228217952092656}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
Chinese: {'event': {'p': 0.6493506493506493, 'r': 0.9259259259259259, 'f1': 0.7633587786259541}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
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': 17}
Russian: {'event': {'p': 0.47368421052631576, 'r': 0.5, 'f1': 0.4864864864864865}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 17}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6449771689497716, 'r': 0.7523302263648469, 'f1': 0.6945298094652735}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Chinese: {'event': {'p': 0.6692644909887969, 'r': 0.8006993006993007, 'f1': 0.7291058636243036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Chinese: {'event': {'p': 0.6764705882352942, 'r': 0.8518518518518519, 'f1': 0.7540983606557378}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6449771689497716, 'r': 0.7523302263648469, 'f1': 0.6945298094652735}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Korean: {'event': {'p': 0.6692644909887969, 'r': 0.8006993006993007, 'f1': 0.7291058636243036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Korean: {'event': {'p': 0.7391304347826086, 'r': 0.5396825396825397, 'f1': 0.6238532110091742}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5971370143149284, 'r': 0.7776298268974701, 'f1': 0.6755349913244649}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Russian: {'event': {'p': 0.6401673640167364, 'r': 0.8024475524475524, 'f1': 0.7121799844840963}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Russian: {'event': {'p': 0.5897435897435898, 'r': 0.6388888888888888, 'f1': 0.6133333333333332}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
******************************
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 02:32:48.559033: step: 4/530, loss: 0.015538406558334827
2023-01-23 02:32:49.656337: step: 8/530, loss: 0.00010309219942428172
2023-01-23 02:32:50.755704: step: 12/530, loss: 0.004303836729377508
2023-01-23 02:32:51.885579: step: 16/530, loss: 0.016955042257905006
2023-01-23 02:32:53.014536: step: 20/530, loss: 0.00020675659470725805
2023-01-23 02:32:54.112568: step: 24/530, loss: 0.027109241113066673
2023-01-23 02:32:55.233069: step: 28/530, loss: 0.03707714006304741
2023-01-23 02:32:56.332984: step: 32/530, loss: 0.0035808563698083162
2023-01-23 02:32:57.427674: step: 36/530, loss: 0.010753536596894264
2023-01-23 02:32:58.569057: step: 40/530, loss: 0.0924493744969368
2023-01-23 02:32:59.669871: step: 44/530, loss: 0.05271138995885849
2023-01-23 02:33:00.770111: step: 48/530, loss: 0.018538713455200195
2023-01-23 02:33:01.877405: step: 52/530, loss: 0.0024030685890465975
2023-01-23 02:33:02.997666: step: 56/530, loss: 0.004207992926239967
2023-01-23 02:33:04.100434: step: 60/530, loss: 0.027288056910037994
2023-01-23 02:33:05.205969: step: 64/530, loss: 0.0019202232360839844
2023-01-23 02:33:06.294538: step: 68/530, loss: 0.007225990295410156
2023-01-23 02:33:07.394668: step: 72/530, loss: 0.005442047491669655
2023-01-23 02:33:08.515593: step: 76/530, loss: 0.0031801224686205387
2023-01-23 02:33:09.604627: step: 80/530, loss: 0.018955161795020103
2023-01-23 02:33:10.719115: step: 84/530, loss: 0.03357210010290146
2023-01-23 02:33:11.823394: step: 88/530, loss: 0.04536399990320206
2023-01-23 02:33:12.920652: step: 92/530, loss: 0.014856052584946156
2023-01-23 02:33:14.021259: step: 96/530, loss: 0.014833355322480202
2023-01-23 02:33:15.135291: step: 100/530, loss: 0.48924142122268677
2023-01-23 02:33:16.237801: step: 104/530, loss: 0.022322725504636765
2023-01-23 02:33:17.376213: step: 108/530, loss: 0.0014595985412597656
2023-01-23 02:33:18.510726: step: 112/530, loss: 0.030552484095096588
2023-01-23 02:33:19.615793: step: 116/530, loss: 0.23088565468788147
2023-01-23 02:33:20.732355: step: 120/530, loss: 0.003956031985580921
2023-01-23 02:33:21.838749: step: 124/530, loss: 0.002081298967823386
2023-01-23 02:33:22.941953: step: 128/530, loss: 0.0001837253657868132
2023-01-23 02:33:24.080284: step: 132/530, loss: 0.02134404331445694
2023-01-23 02:33:25.191781: step: 136/530, loss: 0.0015944242477416992
2023-01-23 02:33:26.297814: step: 140/530, loss: 0.00046958925668150187
2023-01-23 02:33:27.438576: step: 144/530, loss: 0.05222949758172035
2023-01-23 02:33:28.567100: step: 148/530, loss: 0.14044417440891266
2023-01-23 02:33:29.674152: step: 152/530, loss: 0.010602761059999466
2023-01-23 02:33:30.765314: step: 156/530, loss: 0.006151819601655006
2023-01-23 02:33:31.868930: step: 160/530, loss: 0.501025915145874
2023-01-23 02:33:32.995239: step: 164/530, loss: 0.02580413781106472
2023-01-23 02:33:34.108323: step: 168/530, loss: 0.019426966086030006
2023-01-23 02:33:35.212441: step: 172/530, loss: 0.015244388952851295
2023-01-23 02:33:36.376727: step: 176/530, loss: 0.05114803463220596
2023-01-23 02:33:37.491673: step: 180/530, loss: 0.008577799424529076
2023-01-23 02:33:38.596750: step: 184/530, loss: 0.019380569458007812
2023-01-23 02:33:39.706466: step: 188/530, loss: 0.0034818649291992188
2023-01-23 02:33:40.844279: step: 192/530, loss: 0.003602647688239813
2023-01-23 02:33:41.962981: step: 196/530, loss: 0.03370017930865288
2023-01-23 02:33:43.072805: step: 200/530, loss: 0.04303693771362305
2023-01-23 02:33:44.166114: step: 204/530, loss: 0.017069054767489433
2023-01-23 02:33:45.316334: step: 208/530, loss: 0.000293731689453125
2023-01-23 02:33:46.442781: step: 212/530, loss: 0.0003974914725404233
2023-01-23 02:33:47.525984: step: 216/530, loss: 0.0039803506806492805
2023-01-23 02:33:48.665724: step: 220/530, loss: 0.001768350601196289
2023-01-23 02:33:49.745022: step: 224/530, loss: 0.01432584598660469
2023-01-23 02:33:50.834910: step: 228/530, loss: 0.01977372169494629
2023-01-23 02:33:51.958757: step: 232/530, loss: 0.0009492874378338456
2023-01-23 02:33:53.059325: step: 236/530, loss: 0.0005287170642986894
2023-01-23 02:33:54.237801: step: 240/530, loss: 0.021034814417362213
2023-01-23 02:33:55.347823: step: 244/530, loss: 0.018206119537353516
2023-01-23 02:33:56.483479: step: 248/530, loss: 0.001902771065942943
2023-01-23 02:33:57.601315: step: 252/530, loss: 0.007700443267822266
2023-01-23 02:33:58.695541: step: 256/530, loss: 7.534027099609375e-05
2023-01-23 02:33:59.815800: step: 260/530, loss: 0.0032901763916015625
2023-01-23 02:34:00.950524: step: 264/530, loss: 0.00017814636521507055
2023-01-23 02:34:02.031948: step: 268/530, loss: 0.0002706051163841039
2023-01-23 02:34:03.162483: step: 272/530, loss: 0.02653331682085991
2023-01-23 02:34:04.271876: step: 276/530, loss: 0.004841804504394531
2023-01-23 02:34:05.389179: step: 280/530, loss: 0.0033611299004405737
2023-01-23 02:34:06.499217: step: 284/530, loss: 0.07295341789722443
2023-01-23 02:34:07.613995: step: 288/530, loss: 0.0005941391573287547
2023-01-23 02:34:08.756440: step: 292/530, loss: 0.010306740179657936
2023-01-23 02:34:09.843910: step: 296/530, loss: 0.0021865845192223787
2023-01-23 02:34:10.950214: step: 300/530, loss: 0.0004426002560649067
2023-01-23 02:34:12.044441: step: 304/530, loss: 0.04763620346784592
2023-01-23 02:34:13.125403: step: 308/530, loss: 0.013392258435487747
2023-01-23 02:34:14.263897: step: 312/530, loss: 0.008871651254594326
2023-01-23 02:34:15.400587: step: 316/530, loss: 0.005811118986457586
2023-01-23 02:34:16.540195: step: 320/530, loss: 0.022293759509921074
2023-01-23 02:34:17.639667: step: 324/530, loss: 0.0020002364180982113
2023-01-23 02:34:18.743401: step: 328/530, loss: 0.0330398827791214
2023-01-23 02:34:19.856908: step: 332/530, loss: 0.00025930406991392374
2023-01-23 02:34:20.976336: step: 336/530, loss: 0.03254289552569389
2023-01-23 02:34:22.099262: step: 340/530, loss: 0.00011692046246025711
2023-01-23 02:34:23.203828: step: 344/530, loss: 0.0008636474376544356
2023-01-23 02:34:24.302894: step: 348/530, loss: 0.004574966616928577
2023-01-23 02:34:25.424307: step: 352/530, loss: 0.004576397128403187
2023-01-23 02:34:26.526870: step: 356/530, loss: 0.0005890846368856728
2023-01-23 02:34:27.639737: step: 360/530, loss: -1.1444089977885596e-06
2023-01-23 02:34:28.730121: step: 364/530, loss: 0.000111627574369777
2023-01-23 02:34:29.876913: step: 368/530, loss: 0.003235054202377796
2023-01-23 02:34:30.986078: step: 372/530, loss: 0.011699390597641468
2023-01-23 02:34:32.104411: step: 376/530, loss: 0.004066848661750555
2023-01-23 02:34:33.260729: step: 380/530, loss: 0.0002948761102743447
2023-01-23 02:34:34.388938: step: 384/530, loss: 0.0039044858422130346
2023-01-23 02:34:35.502381: step: 388/530, loss: 0.019080735743045807
2023-01-23 02:34:36.598674: step: 392/530, loss: 0.00011539459956111386
2023-01-23 02:34:37.711595: step: 396/530, loss: 0.0013751983642578125
2023-01-23 02:34:38.826723: step: 400/530, loss: 0.031068991869688034
2023-01-23 02:34:39.960400: step: 404/530, loss: 0.016893481835722923
2023-01-23 02:34:41.112179: step: 408/530, loss: 0.0004928589332848787
2023-01-23 02:34:42.221953: step: 412/530, loss: 0.03213987499475479
2023-01-23 02:34:43.348414: step: 416/530, loss: 0.012542724609375
2023-01-23 02:34:44.402271: step: 420/530, loss: 0.42835816740989685
2023-01-23 02:34:45.505501: step: 424/530, loss: 0.0012778282398357987
2023-01-23 02:34:46.599732: step: 428/530, loss: 0.00319499964825809
2023-01-23 02:34:47.756246: step: 432/530, loss: 0.023506546393036842
2023-01-23 02:34:48.909198: step: 436/530, loss: 0.0023518563248217106
2023-01-23 02:34:50.027401: step: 440/530, loss: 0.04606781154870987
2023-01-23 02:34:51.188635: step: 444/530, loss: 0.01867084577679634
2023-01-23 02:34:52.300655: step: 448/530, loss: 0.004562568850815296
2023-01-23 02:34:53.443068: step: 452/530, loss: 0.02485079877078533
2023-01-23 02:34:54.549418: step: 456/530, loss: 0.005431652069091797
2023-01-23 02:34:55.652987: step: 460/530, loss: 0.048281479626894
2023-01-23 02:34:56.753274: step: 464/530, loss: 0.020136166363954544
2023-01-23 02:34:57.874477: step: 468/530, loss: 0.0009610175620764494
2023-01-23 02:34:58.965960: step: 472/530, loss: 0.11516576260328293
2023-01-23 02:35:00.070995: step: 476/530, loss: 0.016741467639803886
2023-01-23 02:35:01.185260: step: 480/530, loss: 0.000522232090588659
2023-01-23 02:35:02.337677: step: 484/530, loss: 0.022007465362548828
2023-01-23 02:35:03.433673: step: 488/530, loss: 0.021456528455018997
2023-01-23 02:35:04.516968: step: 492/530, loss: 0.018104268237948418
2023-01-23 02:35:05.642759: step: 496/530, loss: 0.015808487311005592
2023-01-23 02:35:06.741271: step: 500/530, loss: 0.029055356979370117
2023-01-23 02:35:07.832760: step: 504/530, loss: 0.0161114688962698
2023-01-23 02:35:08.919068: step: 508/530, loss: 0.00018653868755791336
2023-01-23 02:35:10.036436: step: 512/530, loss: 0.007222556974738836
2023-01-23 02:35:11.139306: step: 516/530, loss: 0.010155295953154564
2023-01-23 02:35:12.244347: step: 520/530, loss: 0.02970104105770588
2023-01-23 02:35:13.335483: step: 524/530, loss: 0.0001541137753520161
2023-01-23 02:35:14.445020: step: 528/530, loss: 0.0009910583030432463
2023-01-23 02:35:15.551135: step: 532/530, loss: 0.006185054779052734
2023-01-23 02:35:16.644934: step: 536/530, loss: 0.003994321916252375
2023-01-23 02:35:17.746833: step: 540/530, loss: 0.014900398440659046
2023-01-23 02:35:18.852791: step: 544/530, loss: 0.0010254860389977694
2023-01-23 02:35:19.952497: step: 548/530, loss: 0.00048160552978515625
2023-01-23 02:35:21.051034: step: 552/530, loss: 0.18701010942459106
2023-01-23 02:35:22.131074: step: 556/530, loss: 0.0036806107964366674
2023-01-23 02:35:23.236084: step: 560/530, loss: 0.005240059457719326
2023-01-23 02:35:24.320296: step: 564/530, loss: 0.010839272290468216
2023-01-23 02:35:25.444383: step: 568/530, loss: 0.011540602892637253
2023-01-23 02:35:26.533832: step: 572/530, loss: 0.00151996617205441
2023-01-23 02:35:27.652825: step: 576/530, loss: 0.0014375686878338456
2023-01-23 02:35:28.768789: step: 580/530, loss: 0.10259618610143661
2023-01-23 02:35:29.873143: step: 584/530, loss: 0.00822744332253933
2023-01-23 02:35:30.945564: step: 588/530, loss: 0.019188832491636276
2023-01-23 02:35:32.047941: step: 592/530, loss: 0.013908673077821732
2023-01-23 02:35:33.178004: step: 596/530, loss: 0.034647177904844284
2023-01-23 02:35:34.281313: step: 600/530, loss: 0.021599579602479935
2023-01-23 02:35:35.381749: step: 604/530, loss: 0.0003159523184876889
2023-01-23 02:35:36.478402: step: 608/530, loss: 0.0006524086347781122
2023-01-23 02:35:37.608969: step: 612/530, loss: 0.009001636877655983
2023-01-23 02:35:38.721023: step: 616/530, loss: 0.013050413690507412
2023-01-23 02:35:39.850561: step: 620/530, loss: 0.0023550032638013363
2023-01-23 02:35:40.964949: step: 624/530, loss: 0.039183422923088074
2023-01-23 02:35:42.076698: step: 628/530, loss: 0.022510241717100143
2023-01-23 02:35:43.171080: step: 632/530, loss: 0.05098772048950195
2023-01-23 02:35:44.276577: step: 636/530, loss: 0.010355758480727673
2023-01-23 02:35:45.389547: step: 640/530, loss: 0.02342822775244713
2023-01-23 02:35:46.493753: step: 644/530, loss: 0.018220901489257812
2023-01-23 02:35:47.609950: step: 648/530, loss: -3.0851362680550665e-05
2023-01-23 02:35:48.726677: step: 652/530, loss: 0.012862730771303177
2023-01-23 02:35:49.814775: step: 656/530, loss: 0.12144008278846741
2023-01-23 02:35:50.928708: step: 660/530, loss: 7.724761962890625e-05
2023-01-23 02:35:52.087474: step: 664/530, loss: 0.024877214804291725
2023-01-23 02:35:53.209596: step: 668/530, loss: 0.024576187133789062
2023-01-23 02:35:54.300504: step: 672/530, loss: 0.001784896943718195
2023-01-23 02:35:55.406958: step: 676/530, loss: 0.009118652902543545
2023-01-23 02:35:56.487039: step: 680/530, loss: 0.00015435219393111765
2023-01-23 02:35:57.582730: step: 684/530, loss: 0.00161066057626158
2023-01-23 02:35:58.670302: step: 688/530, loss: 0.00672836322337389
2023-01-23 02:35:59.752975: step: 692/530, loss: 0.7931879758834839
2023-01-23 02:36:00.866117: step: 696/530, loss: 0.005603981204330921
2023-01-23 02:36:01.979494: step: 700/530, loss: 0.009859275072813034
2023-01-23 02:36:03.112052: step: 704/530, loss: 0.24037614464759827
2023-01-23 02:36:04.223430: step: 708/530, loss: 7.867813110351562e-05
2023-01-23 02:36:05.348847: step: 712/530, loss: 0.18329600989818573
2023-01-23 02:36:06.425369: step: 716/530, loss: 0.00334587087854743
2023-01-23 02:36:07.527195: step: 720/530, loss: 0.08267302811145782
2023-01-23 02:36:08.632503: step: 724/530, loss: 0.0005297660827636719
2023-01-23 02:36:09.735304: step: 728/530, loss: 0.005096435546875
2023-01-23 02:36:10.842095: step: 732/530, loss: 0.0003702164103742689
2023-01-23 02:36:11.940741: step: 736/530, loss: 0.0314258337020874
2023-01-23 02:36:13.034646: step: 740/530, loss: 0.0048768045380711555
2023-01-23 02:36:14.161873: step: 744/530, loss: 0.010059737600386143
2023-01-23 02:36:15.243163: step: 748/530, loss: 0.05085020139813423
2023-01-23 02:36:16.378589: step: 752/530, loss: 0.03216400370001793
2023-01-23 02:36:17.491153: step: 756/530, loss: 0.0208601001650095
2023-01-23 02:36:18.592960: step: 760/530, loss: 0.029767656698822975
2023-01-23 02:36:19.737709: step: 764/530, loss: 5.3119660151423886e-05
2023-01-23 02:36:20.872131: step: 768/530, loss: 0.0013719559647142887
2023-01-23 02:36:21.959237: step: 772/530, loss: 0.02174057997763157
2023-01-23 02:36:23.064549: step: 776/530, loss: 0.001155853271484375
2023-01-23 02:36:24.149935: step: 780/530, loss: 0.14572611451148987
2023-01-23 02:36:25.256302: step: 784/530, loss: 0.0017318249447271228
2023-01-23 02:36:26.364543: step: 788/530, loss: 0.06550540775060654
2023-01-23 02:36:27.472657: step: 792/530, loss: 0.016634799540042877
2023-01-23 02:36:28.598273: step: 796/530, loss: 0.015673398971557617
2023-01-23 02:36:29.695584: step: 800/530, loss: 0.002036619232967496
2023-01-23 02:36:30.786347: step: 804/530, loss: 0.00023374558077193797
2023-01-23 02:36:31.900199: step: 808/530, loss: 0.0007801055908203125
2023-01-23 02:36:32.993996: step: 812/530, loss: 0.00719795236364007
2023-01-23 02:36:34.089465: step: 816/530, loss: 0.0022953986190259457
2023-01-23 02:36:35.197094: step: 820/530, loss: 0.0043548583053052425
2023-01-23 02:36:36.293101: step: 824/530, loss: 0.021163560450077057
2023-01-23 02:36:37.399807: step: 828/530, loss: 0.017868518829345703
2023-01-23 02:36:38.521675: step: 832/530, loss: 0.10996018350124359
2023-01-23 02:36:39.663179: step: 836/530, loss: 0.004439258482307196
2023-01-23 02:36:40.769098: step: 840/530, loss: 0.020337535068392754
2023-01-23 02:36:41.850824: step: 844/530, loss: 0.0018639564514160156
2023-01-23 02:36:42.957824: step: 848/530, loss: 0.016733933240175247
2023-01-23 02:36:44.058833: step: 852/530, loss: 0.008910560980439186
2023-01-23 02:36:45.154380: step: 856/530, loss: 0.018204832449555397
2023-01-23 02:36:46.244273: step: 860/530, loss: 0.006949901580810547
2023-01-23 02:36:47.357278: step: 864/530, loss: 0.006422758102416992
2023-01-23 02:36:48.477139: step: 868/530, loss: 0.0007054328452795744
2023-01-23 02:36:49.589148: step: 872/530, loss: 0.043793678283691406
2023-01-23 02:36:50.682588: step: 876/530, loss: 0.0029680251609534025
2023-01-23 02:36:51.779046: step: 880/530, loss: 0.022115685045719147
2023-01-23 02:36:52.903217: step: 884/530, loss: 0.012332010082900524
2023-01-23 02:36:54.006525: step: 888/530, loss: 0.0007526398403570056
2023-01-23 02:36:55.119771: step: 892/530, loss: 0.006965446751564741
2023-01-23 02:36:56.231091: step: 896/530, loss: 0.0022890090476721525
2023-01-23 02:36:57.334142: step: 900/530, loss: 0.09139204770326614
2023-01-23 02:36:58.457317: step: 904/530, loss: 0.022707652300596237
2023-01-23 02:36:59.557726: step: 908/530, loss: 0.04201870039105415
2023-01-23 02:37:00.634767: step: 912/530, loss: 0.037773940712213516
2023-01-23 02:37:01.719810: step: 916/530, loss: 0.01642465591430664
2023-01-23 02:37:02.836820: step: 920/530, loss: 0.027944182977080345
2023-01-23 02:37:03.942951: step: 924/530, loss: 0.0032597542740404606
2023-01-23 02:37:05.020357: step: 928/530, loss: 0.0019674301147460938
2023-01-23 02:37:06.117800: step: 932/530, loss: 0.03970353677868843
2023-01-23 02:37:07.239718: step: 936/530, loss: 0.023433685302734375
2023-01-23 02:37:08.326052: step: 940/530, loss: 0.025008391588926315
2023-01-23 02:37:09.437498: step: 944/530, loss: 0.004248475655913353
2023-01-23 02:37:10.550446: step: 948/530, loss: 0.0020300389733165503
2023-01-23 02:37:11.675538: step: 952/530, loss: 0.0002847671858035028
2023-01-23 02:37:12.773048: step: 956/530, loss: 0.02259097620844841
2023-01-23 02:37:13.878400: step: 960/530, loss: 0.0003372192441020161
2023-01-23 02:37:15.001488: step: 964/530, loss: 0.0007192611810751259
2023-01-23 02:37:16.146145: step: 968/530, loss: 5.1021575927734375e-05
2023-01-23 02:37:17.273163: step: 972/530, loss: 0.058175280690193176
2023-01-23 02:37:18.373965: step: 976/530, loss: 0.007278156001120806
2023-01-23 02:37:19.458832: step: 980/530, loss: 0.00102405552752316
2023-01-23 02:37:20.595287: step: 984/530, loss: 0.00042400360689498484
2023-01-23 02:37:21.706362: step: 988/530, loss: 0.012501525692641735
2023-01-23 02:37:22.829702: step: 992/530, loss: 0.005577182397246361
2023-01-23 02:37:23.913160: step: 996/530, loss: 0.01881866529583931
2023-01-23 02:37:25.015872: step: 1000/530, loss: 0.00030345917912200093
2023-01-23 02:37:26.181103: step: 1004/530, loss: 0.01647014729678631
2023-01-23 02:37:27.301366: step: 1008/530, loss: 0.04443302005529404
2023-01-23 02:37:28.407810: step: 1012/530, loss: 0.023709489032626152
2023-01-23 02:37:29.508578: step: 1016/530, loss: 0.0029163360595703125
2023-01-23 02:37:30.641744: step: 1020/530, loss: 0.03952503204345703
2023-01-23 02:37:31.739536: step: 1024/530, loss: 0.07119293510913849
2023-01-23 02:37:32.855301: step: 1028/530, loss: 0.05188923329114914
2023-01-23 02:37:33.975199: step: 1032/530, loss: 0.09085045009851456
2023-01-23 02:37:35.085587: step: 1036/530, loss: 0.02921009249985218
2023-01-23 02:37:36.195844: step: 1040/530, loss: 0.05702047049999237
2023-01-23 02:37:37.295338: step: 1044/530, loss: 0.0001164436325780116
2023-01-23 02:37:38.420237: step: 1048/530, loss: 0.004671192262321711
2023-01-23 02:37:39.529238: step: 1052/530, loss: 0.17353801429271698
2023-01-23 02:37:40.619479: step: 1056/530, loss: 8.840561349643394e-05
2023-01-23 02:37:41.731214: step: 1060/530, loss: 0.01607656478881836
2023-01-23 02:37:42.850993: step: 1064/530, loss: 0.00016078949556685984
2023-01-23 02:37:43.978423: step: 1068/530, loss: 0.026284312829375267
2023-01-23 02:37:45.099697: step: 1072/530, loss: 0.0002891063631977886
2023-01-23 02:37:46.204413: step: 1076/530, loss: 0.0008088588947430253
2023-01-23 02:37:47.281472: step: 1080/530, loss: 0.003712570760399103
2023-01-23 02:37:48.367511: step: 1084/530, loss: 0.0003281593380961567
2023-01-23 02:37:49.476962: step: 1088/530, loss: 0.002109432127326727
2023-01-23 02:37:50.601699: step: 1092/530, loss: 0.008589553646743298
2023-01-23 02:37:51.699619: step: 1096/530, loss: 0.004763794131577015
2023-01-23 02:37:52.813027: step: 1100/530, loss: 0.017424870282411575
2023-01-23 02:37:53.914136: step: 1104/530, loss: 0.18673038482666016
2023-01-23 02:37:55.062958: step: 1108/530, loss: 0.07209110260009766
2023-01-23 02:37:56.154107: step: 1112/530, loss: 0.04773082584142685
2023-01-23 02:37:57.242110: step: 1116/530, loss: 0.004270744509994984
2023-01-23 02:37:58.346693: step: 1120/530, loss: 0.002678489778190851
2023-01-23 02:37:59.464477: step: 1124/530, loss: 0.0006042004097253084
2023-01-23 02:38:00.569924: step: 1128/530, loss: 0.0003546714724507183
2023-01-23 02:38:01.709624: step: 1132/530, loss: 0.0033932209480553865
2023-01-23 02:38:02.809907: step: 1136/530, loss: 0.027182389050722122
2023-01-23 02:38:03.951898: step: 1140/530, loss: 0.025155067443847656
2023-01-23 02:38:05.055147: step: 1144/530, loss: -5.0067901611328125e-06
2023-01-23 02:38:06.151828: step: 1148/530, loss: 0.005621051881462336
2023-01-23 02:38:07.242634: step: 1152/530, loss: 0.005864906124770641
2023-01-23 02:38:08.313984: step: 1156/530, loss: 0.0001346349745290354
2023-01-23 02:38:09.414496: step: 1160/530, loss: 0.06018419191241264
2023-01-23 02:38:10.519569: step: 1164/530, loss: 0.0012487411731854081
2023-01-23 02:38:11.633326: step: 1168/530, loss: 0.028756260871887207
2023-01-23 02:38:12.746466: step: 1172/530, loss: 0.005887698847800493
2023-01-23 02:38:13.809230: step: 1176/530, loss: 0.005175781436264515
2023-01-23 02:38:14.915653: step: 1180/530, loss: 4.7206878662109375e-05
2023-01-23 02:38:16.044225: step: 1184/530, loss: 0.05222377926111221
2023-01-23 02:38:17.135044: step: 1188/530, loss: 0.06117239221930504
2023-01-23 02:38:18.226502: step: 1192/530, loss: 0.011347579769790173
2023-01-23 02:38:19.349491: step: 1196/530, loss: 0.0015993118286132812
2023-01-23 02:38:20.436107: step: 1200/530, loss: 0.0009314537164755166
2023-01-23 02:38:21.560102: step: 1204/530, loss: 0.013143539428710938
2023-01-23 02:38:22.680511: step: 1208/530, loss: 0.007003211881965399
2023-01-23 02:38:23.805682: step: 1212/530, loss: 0.323643296957016
2023-01-23 02:38:24.899458: step: 1216/530, loss: 0.11925859749317169
2023-01-23 02:38:26.024625: step: 1220/530, loss: 0.01886158064007759
2023-01-23 02:38:27.112081: step: 1224/530, loss: 0.005920982453972101
2023-01-23 02:38:28.224525: step: 1228/530, loss: 0.1177511215209961
2023-01-23 02:38:29.355122: step: 1232/530, loss: 0.22948989272117615
2023-01-23 02:38:30.459387: step: 1236/530, loss: 0.0021741867531090975
2023-01-23 02:38:31.554203: step: 1240/530, loss: 0.0008554458618164062
2023-01-23 02:38:32.645503: step: 1244/530, loss: 5.073547436040826e-05
2023-01-23 02:38:33.732283: step: 1248/530, loss: 0.0016447067027911544
2023-01-23 02:38:34.806049: step: 1252/530, loss: 0.0376313216984272
2023-01-23 02:38:35.933273: step: 1256/530, loss: 0.0007063865195959806
2023-01-23 02:38:37.020533: step: 1260/530, loss: 0.024647142738103867
2023-01-23 02:38:38.103180: step: 1264/530, loss: 0.021284889429807663
2023-01-23 02:38:39.212268: step: 1268/530, loss: 0.09582366794347763
2023-01-23 02:38:40.333593: step: 1272/530, loss: 0.0066734314896166325
2023-01-23 02:38:41.441743: step: 1276/530, loss: 0.034357450902462006
2023-01-23 02:38:42.531607: step: 1280/530, loss: 0.037011146545410156
2023-01-23 02:38:43.633507: step: 1284/530, loss: 0.01544332504272461
2023-01-23 02:38:44.757019: step: 1288/530, loss: 0.05303249508142471
2023-01-23 02:38:45.870375: step: 1292/530, loss: 0.0011049271561205387
2023-01-23 02:38:46.966102: step: 1296/530, loss: 0.010771751403808594
2023-01-23 02:38:48.087822: step: 1300/530, loss: 0.011503983289003372
2023-01-23 02:38:49.191047: step: 1304/530, loss: 0.014945602975785732
2023-01-23 02:38:50.291623: step: 1308/530, loss: 0.0007500648498535156
2023-01-23 02:38:51.392879: step: 1312/530, loss: 0.013756513595581055
2023-01-23 02:38:52.492357: step: 1316/530, loss: 0.00014634132094215602
2023-01-23 02:38:53.613173: step: 1320/530, loss: 0.0002094268857035786
2023-01-23 02:38:54.731619: step: 1324/530, loss: 0.06457634270191193
2023-01-23 02:38:55.851672: step: 1328/530, loss: 0.03155803680419922
2023-01-23 02:38:56.958646: step: 1332/530, loss: 0.0036422729026526213
2023-01-23 02:38:58.054857: step: 1336/530, loss: 0.13641805946826935
2023-01-23 02:38:59.186412: step: 1340/530, loss: 0.02289733849465847
2023-01-23 02:39:00.255873: step: 1344/530, loss: 0.00011153220839332789
2023-01-23 02:39:01.379059: step: 1348/530, loss: 0.00653152447193861
2023-01-23 02:39:02.480516: step: 1352/530, loss: 3.533363633323461e-05
2023-01-23 02:39:03.620231: step: 1356/530, loss: 0.01332855224609375
2023-01-23 02:39:04.723118: step: 1360/530, loss: 0.0009347915765829384
2023-01-23 02:39:05.866775: step: 1364/530, loss: 0.006294441409409046
2023-01-23 02:39:06.966634: step: 1368/530, loss: 0.0006768703460693359
2023-01-23 02:39:08.073975: step: 1372/530, loss: 0.02087097242474556
2023-01-23 02:39:09.170061: step: 1376/530, loss: 0.0005721867200918496
2023-01-23 02:39:10.319570: step: 1380/530, loss: 0.020159531384706497
2023-01-23 02:39:11.451225: step: 1384/530, loss: 0.05679168924689293
2023-01-23 02:39:12.564330: step: 1388/530, loss: 0.04632997885346413
2023-01-23 02:39:13.649894: step: 1392/530, loss: 0.007859897799789906
2023-01-23 02:39:14.759254: step: 1396/530, loss: 0.004583167843520641
2023-01-23 02:39:15.854359: step: 1400/530, loss: 0.03721633180975914
2023-01-23 02:39:16.958929: step: 1404/530, loss: 0.05515632778406143
2023-01-23 02:39:18.053128: step: 1408/530, loss: 0.04446087032556534
2023-01-23 02:39:19.179300: step: 1412/530, loss: 0.03361453860998154
2023-01-23 02:39:20.280677: step: 1416/530, loss: 0.00042362214298918843
2023-01-23 02:39:21.349449: step: 1420/530, loss: 5.545616295421496e-05
2023-01-23 02:39:22.444089: step: 1424/530, loss: 0.06790123134851456
2023-01-23 02:39:23.538916: step: 1428/530, loss: 0.014075184240937233
2023-01-23 02:39:24.657624: step: 1432/530, loss: 0.01500854454934597
2023-01-23 02:39:25.766531: step: 1436/530, loss: 0.007605075836181641
2023-01-23 02:39:26.856569: step: 1440/530, loss: 0.007139969151467085
2023-01-23 02:39:28.022210: step: 1444/530, loss: 0.00014781951904296875
2023-01-23 02:39:29.106954: step: 1448/530, loss: 0.023858357220888138
2023-01-23 02:39:30.225620: step: 1452/530, loss: 0.00028104783268645406
2023-01-23 02:39:31.329397: step: 1456/530, loss: 0.025980280712246895
2023-01-23 02:39:32.398809: step: 1460/530, loss: 0.016693973913788795
2023-01-23 02:39:33.496158: step: 1464/530, loss: 0.008809184655547142
2023-01-23 02:39:34.599242: step: 1468/530, loss: 0.0070022582076489925
2023-01-23 02:39:35.706074: step: 1472/530, loss: 0.0016303539741784334
2023-01-23 02:39:36.815589: step: 1476/530, loss: 0.06903534382581711
2023-01-23 02:39:37.971935: step: 1480/530, loss: 0.0017650604713708162
2023-01-23 02:39:39.051293: step: 1484/530, loss: 0.0031463622581213713
2023-01-23 02:39:40.147383: step: 1488/530, loss: 0.07946892082691193
2023-01-23 02:39:41.284054: step: 1492/530, loss: 0.01411895826458931
2023-01-23 02:39:42.369530: step: 1496/530, loss: 0.04037361219525337
2023-01-23 02:39:43.445329: step: 1500/530, loss: 9.250640869140625e-05
2023-01-23 02:39:44.558680: step: 1504/530, loss: 0.012080097571015358
2023-01-23 02:39:45.690260: step: 1508/530, loss: 0.0013203620910644531
2023-01-23 02:39:46.806078: step: 1512/530, loss: 0.008947658352553844
2023-01-23 02:39:47.906627: step: 1516/530, loss: 0.023270893841981888
2023-01-23 02:39:49.021233: step: 1520/530, loss: 0.015252781100571156
2023-01-23 02:39:50.154809: step: 1524/530, loss: 0.0014043807750567794
2023-01-23 02:39:51.279107: step: 1528/530, loss: 0.004772949498146772
2023-01-23 02:39:52.359302: step: 1532/530, loss: 0.003431701799854636
2023-01-23 02:39:53.490085: step: 1536/530, loss: 0.025314711034297943
2023-01-23 02:39:54.586129: step: 1540/530, loss: 0.010156822390854359
2023-01-23 02:39:55.691585: step: 1544/530, loss: 0.0037425996270030737
2023-01-23 02:39:56.803917: step: 1548/530, loss: 0.0001510620058979839
2023-01-23 02:39:57.888378: step: 1552/530, loss: 0.0036911964416503906
2023-01-23 02:39:58.994611: step: 1556/530, loss: 0.00013236999802757055
2023-01-23 02:40:00.101110: step: 1560/530, loss: 0.0006529808160848916
2023-01-23 02:40:01.229983: step: 1564/530, loss: 0.10707416385412216
2023-01-23 02:40:02.329016: step: 1568/530, loss: 0.05747414007782936
2023-01-23 02:40:03.431865: step: 1572/530, loss: 0.0020286559592932463
2023-01-23 02:40:04.537103: step: 1576/530, loss: 0.006119442172348499
2023-01-23 02:40:05.648869: step: 1580/530, loss: 0.00829172134399414
2023-01-23 02:40:06.755153: step: 1584/530, loss: 0.03436412662267685
2023-01-23 02:40:07.842643: step: 1588/530, loss: 0.000941848789807409
2023-01-23 02:40:08.951098: step: 1592/530, loss: 0.05208345502614975
2023-01-23 02:40:10.064691: step: 1596/530, loss: 0.06081562116742134
2023-01-23 02:40:11.144120: step: 1600/530, loss: 0.00010342597670387477
2023-01-23 02:40:12.215793: step: 1604/530, loss: 3.967285010730848e-05
2023-01-23 02:40:13.328447: step: 1608/530, loss: 0.004682731814682484
2023-01-23 02:40:14.416164: step: 1612/530, loss: 0.7012049555778503
2023-01-23 02:40:15.514143: step: 1616/530, loss: 0.005007839296013117
2023-01-23 02:40:16.591829: step: 1620/530, loss: 0.029549788683652878
2023-01-23 02:40:17.702489: step: 1624/530, loss: 0.04130697250366211
2023-01-23 02:40:18.803103: step: 1628/530, loss: 0.005343914031982422
2023-01-23 02:40:19.938321: step: 1632/530, loss: 0.1487049013376236
2023-01-23 02:40:21.049642: step: 1636/530, loss: 0.00945434533059597
2023-01-23 02:40:22.147857: step: 1640/530, loss: 0.022394943982362747
2023-01-23 02:40:23.248319: step: 1644/530, loss: 0.06925764679908752
2023-01-23 02:40:24.339821: step: 1648/530, loss: 0.02374572865664959
2023-01-23 02:40:25.477246: step: 1652/530, loss: 0.0027790190652012825
2023-01-23 02:40:26.573412: step: 1656/530, loss: 0.015136432833969593
2023-01-23 02:40:27.683184: step: 1660/530, loss: 0.044382572174072266
2023-01-23 02:40:28.805078: step: 1664/530, loss: 0.0006704330444335938
2023-01-23 02:40:29.902805: step: 1668/530, loss: 0.003330803010612726
2023-01-23 02:40:30.993369: step: 1672/530, loss: 0.015287494286894798
2023-01-23 02:40:32.083638: step: 1676/530, loss: 0.0016093254089355469
2023-01-23 02:40:33.199956: step: 1680/530, loss: 0.049257468432188034
2023-01-23 02:40:34.341800: step: 1684/530, loss: 0.01935148425400257
2023-01-23 02:40:35.426424: step: 1688/530, loss: 0.0006874084938317537
2023-01-23 02:40:36.518227: step: 1692/530, loss: 0.020571382716298103
2023-01-23 02:40:37.625321: step: 1696/530, loss: 0.3436241149902344
2023-01-23 02:40:38.754937: step: 1700/530, loss: 0.0077949524857103825
2023-01-23 02:40:39.862013: step: 1704/530, loss: 0.014030742458999157
2023-01-23 02:40:40.935593: step: 1708/530, loss: 0.003091955091804266
2023-01-23 02:40:42.014527: step: 1712/530, loss: 0.0004459381161723286
2023-01-23 02:40:43.131865: step: 1716/530, loss: 0.09762582182884216
2023-01-23 02:40:44.253807: step: 1720/530, loss: 0.006093787960708141
2023-01-23 02:40:45.363249: step: 1724/530, loss: 0.02343130111694336
2023-01-23 02:40:46.454232: step: 1728/530, loss: 0.0009000301361083984
2023-01-23 02:40:47.581528: step: 1732/530, loss: 0.0010390281677246094
2023-01-23 02:40:48.702646: step: 1736/530, loss: 0.0038806914817541838
2023-01-23 02:40:49.809434: step: 1740/530, loss: 1.487731969973538e-05
2023-01-23 02:40:50.922646: step: 1744/530, loss: 0.0025426866486668587
2023-01-23 02:40:52.002879: step: 1748/530, loss: 0.01592388190329075
2023-01-23 02:40:53.123452: step: 1752/530, loss: 0.0025650025345385075
2023-01-23 02:40:54.245845: step: 1756/530, loss: 0.00018539429584052414
2023-01-23 02:40:55.322486: step: 1760/530, loss: 0.004696178715676069
2023-01-23 02:40:56.424939: step: 1764/530, loss: 0.00021696090698242188
2023-01-23 02:40:57.543186: step: 1768/530, loss: 0.009579754434525967
2023-01-23 02:40:58.679474: step: 1772/530, loss: 0.24316748976707458
2023-01-23 02:40:59.802860: step: 1776/530, loss: 0.03547258675098419
2023-01-23 02:41:00.901305: step: 1780/530, loss: 0.09324925392866135
2023-01-23 02:41:02.019627: step: 1784/530, loss: 0.005812454503029585
2023-01-23 02:41:03.157203: step: 1788/530, loss: 0.0005620956653729081
2023-01-23 02:41:04.256399: step: 1792/530, loss: 0.025864887982606888
2023-01-23 02:41:05.353807: step: 1796/530, loss: 0.002695178845897317
2023-01-23 02:41:06.429424: step: 1800/530, loss: 0.011013984680175781
2023-01-23 02:41:07.531227: step: 1804/530, loss: 0.00029315947904251516
2023-01-23 02:41:08.662538: step: 1808/530, loss: 0.022449970245361328
2023-01-23 02:41:09.760919: step: 1812/530, loss: 0.00017137527174782008
2023-01-23 02:41:10.905211: step: 1816/530, loss: 0.06276092678308487
2023-01-23 02:41:12.007732: step: 1820/530, loss: 0.0011528015602380037
2023-01-23 02:41:13.093426: step: 1824/530, loss: 0.00099859235342592
2023-01-23 02:41:14.213227: step: 1828/530, loss: 0.0012840271228924394
2023-01-23 02:41:15.356238: step: 1832/530, loss: 0.0395539291203022
2023-01-23 02:41:16.477019: step: 1836/530, loss: 0.03256263956427574
2023-01-23 02:41:17.594437: step: 1840/530, loss: 0.006854057312011719
2023-01-23 02:41:18.722594: step: 1844/530, loss: 0.026057148352265358
2023-01-23 02:41:19.832263: step: 1848/530, loss: 0.05324840545654297
2023-01-23 02:41:20.940008: step: 1852/530, loss: 0.0158431064337492
2023-01-23 02:41:22.061155: step: 1856/530, loss: 0.04741191864013672
2023-01-23 02:41:23.170703: step: 1860/530, loss: 0.007835007272660732
2023-01-23 02:41:24.316831: step: 1864/530, loss: 0.036286354064941406
2023-01-23 02:41:25.413073: step: 1868/530, loss: 0.0020513059571385384
2023-01-23 02:41:26.508541: step: 1872/530, loss: 0.0014045715797692537
2023-01-23 02:41:27.580199: step: 1876/530, loss: 0.004722500219941139
2023-01-23 02:41:28.667506: step: 1880/530, loss: 0.05336952209472656
2023-01-23 02:41:29.771477: step: 1884/530, loss: 0.002191829727962613
2023-01-23 02:41:30.892550: step: 1888/530, loss: 0.00035943987313658
2023-01-23 02:41:32.021829: step: 1892/530, loss: 0.0009249686845578253
2023-01-23 02:41:33.159286: step: 1896/530, loss: 0.003943490795791149
2023-01-23 02:41:34.228409: step: 1900/530, loss: 0.00026044846163131297
2023-01-23 02:41:35.323305: step: 1904/530, loss: 0.010267066769301891
2023-01-23 02:41:36.433764: step: 1908/530, loss: 0.015498924069106579
2023-01-23 02:41:37.544155: step: 1912/530, loss: 0.005458545871078968
2023-01-23 02:41:38.656074: step: 1916/530, loss: 0.0021534920670092106
2023-01-23 02:41:39.778228: step: 1920/530, loss: 0.010009193792939186
2023-01-23 02:41:40.892386: step: 1924/530, loss: 0.00035324099007993937
2023-01-23 02:41:42.014360: step: 1928/530, loss: 0.11067288368940353
2023-01-23 02:41:43.109436: step: 1932/530, loss: 0.0017961800331249833
2023-01-23 02:41:44.199513: step: 1936/530, loss: 0.0023491859901696444
2023-01-23 02:41:45.311355: step: 1940/530, loss: 0.018761729821562767
2023-01-23 02:41:46.397715: step: 1944/530, loss: 0.0020810128189623356
2023-01-23 02:41:47.507867: step: 1948/530, loss: 0.29024773836135864
2023-01-23 02:41:48.642265: step: 1952/530, loss: 0.003209781600162387
2023-01-23 02:41:49.742355: step: 1956/530, loss: 0.0015465737087652087
2023-01-23 02:41:50.857372: step: 1960/530, loss: 0.012009143829345703
2023-01-23 02:41:51.963137: step: 1964/530, loss: 0.01633596420288086
2023-01-23 02:41:53.087778: step: 1968/530, loss: 0.00499801617115736
2023-01-23 02:41:54.200894: step: 1972/530, loss: 1.3351441339182202e-06
2023-01-23 02:41:55.317151: step: 1976/530, loss: 0.06334781646728516
2023-01-23 02:41:56.432475: step: 1980/530, loss: 0.04197588190436363
2023-01-23 02:41:57.543036: step: 1984/530, loss: 0.27490195631980896
2023-01-23 02:41:58.672916: step: 1988/530, loss: 0.0019353866809979081
2023-01-23 02:41:59.770607: step: 1992/530, loss: 0.00024890899658203125
2023-01-23 02:42:00.858301: step: 1996/530, loss: 2.9304625059012324e-05
2023-01-23 02:42:01.957783: step: 2000/530, loss: 0.0029045583214610815
2023-01-23 02:42:03.054293: step: 2004/530, loss: 0.005679797846823931
2023-01-23 02:42:04.165928: step: 2008/530, loss: 0.028824234381318092
2023-01-23 02:42:05.269043: step: 2012/530, loss: 0.00569419888779521
2023-01-23 02:42:06.379284: step: 2016/530, loss: 0.03195934370160103
2023-01-23 02:42:07.463115: step: 2020/530, loss: 0.012851143255829811
2023-01-23 02:42:08.539757: step: 2024/530, loss: 0.05117626488208771
2023-01-23 02:42:09.650834: step: 2028/530, loss: -1.468658410885837e-05
2023-01-23 02:42:10.782841: step: 2032/530, loss: 0.0016850472893565893
2023-01-23 02:42:11.864111: step: 2036/530, loss: 0.0027854086365550756
2023-01-23 02:42:12.975269: step: 2040/530, loss: 0.03502919524908066
2023-01-23 02:42:14.081570: step: 2044/530, loss: 0.0008890152676030993
2023-01-23 02:42:15.191228: step: 2048/530, loss: 0.012233376502990723
2023-01-23 02:42:16.287883: step: 2052/530, loss: 0.0004127502324990928
2023-01-23 02:42:17.407526: step: 2056/530, loss: 0.005877113435417414
2023-01-23 02:42:18.515020: step: 2060/530, loss: 0.00423431396484375
2023-01-23 02:42:19.632181: step: 2064/530, loss: 0.0005033016204833984
2023-01-23 02:42:20.753928: step: 2068/530, loss: 0.02495880238711834
2023-01-23 02:42:21.860311: step: 2072/530, loss: 0.0012793303467333317
2023-01-23 02:42:22.945217: step: 2076/530, loss: 0.021669864654541016
2023-01-23 02:42:24.059386: step: 2080/530, loss: 0.4046580195426941
2023-01-23 02:42:25.216320: step: 2084/530, loss: 0.0008994102827273309
2023-01-23 02:42:26.333022: step: 2088/530, loss: 0.12079425156116486
2023-01-23 02:42:27.431058: step: 2092/530, loss: 0.01052160281687975
2023-01-23 02:42:28.551681: step: 2096/530, loss: 0.022985078394412994
2023-01-23 02:42:29.678603: step: 2100/530, loss: 3.4809112548828125e-05
2023-01-23 02:42:30.760117: step: 2104/530, loss: 0.02949695661664009
2023-01-23 02:42:31.887033: step: 2108/530, loss: 0.0043350220657885075
2023-01-23 02:42:32.989107: step: 2112/530, loss: 0.0072761536575853825
2023-01-23 02:42:34.072278: step: 2116/530, loss: 0.3526698052883148
2023-01-23 02:42:35.206961: step: 2120/530, loss: 0.006498909089714289
==================================================
Loss: 0.030
--------------------
Dev: {'event': {'p': 0.5793650793650794, 'r': 0.7776298268974701, 'f1': 0.6640136441159751}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
Test: {'event': {'p': 0.6375286041189931, 'r': 0.8117715617715617, 'f1': 0.7141758523455524}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
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': 18}
Korean: {'event': {'p': 0.6724137931034483, 'r': 0.6190476190476191, 'f1': 0.6446280991735537}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
Russian: {'event': {'p': 0.4523809523809524, 'r': 0.5277777777777778, 'f1': 0.4871794871794871}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 18}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6449771689497716, 'r': 0.7523302263648469, 'f1': 0.6945298094652735}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Chinese: {'event': {'p': 0.6692644909887969, 'r': 0.8006993006993007, 'f1': 0.7291058636243036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Chinese: {'event': {'p': 0.6764705882352942, 'r': 0.8518518518518519, 'f1': 0.7540983606557378}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6449771689497716, 'r': 0.7523302263648469, 'f1': 0.6945298094652735}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Korean: {'event': {'p': 0.6692644909887969, 'r': 0.8006993006993007, 'f1': 0.7291058636243036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Korean: {'event': {'p': 0.7391304347826086, 'r': 0.5396825396825397, 'f1': 0.6238532110091742}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5971370143149284, 'r': 0.7776298268974701, 'f1': 0.6755349913244649}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Russian: {'event': {'p': 0.6401673640167364, 'r': 0.8024475524475524, 'f1': 0.7121799844840963}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Russian: {'event': {'p': 0.5897435897435898, 'r': 0.6388888888888888, 'f1': 0.6133333333333332}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
******************************
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 02:43:14.478341: step: 4/530, loss: 0.0034091949928551912
2023-01-23 02:43:15.563181: step: 8/530, loss: 0.0019034385913982987
2023-01-23 02:43:16.706498: step: 12/530, loss: 0.031867220997810364
2023-01-23 02:43:17.788342: step: 16/530, loss: 0.0018473626114428043
2023-01-23 02:43:18.881591: step: 20/530, loss: 0.0009202957153320312
2023-01-23 02:43:19.954017: step: 24/530, loss: 0.010785293765366077
2023-01-23 02:43:21.047602: step: 28/530, loss: 0.044645603746175766
2023-01-23 02:43:22.122596: step: 32/530, loss: 0.0032550811301916838
2023-01-23 02:43:23.235495: step: 36/530, loss: 0.024207307025790215
2023-01-23 02:43:24.350544: step: 40/530, loss: 0.005213928408920765
2023-01-23 02:43:25.445800: step: 44/530, loss: 0.6288784146308899
2023-01-23 02:43:26.527528: step: 48/530, loss: 0.00022392271785065532
2023-01-23 02:43:27.647664: step: 52/530, loss: 0.15328730642795563
2023-01-23 02:43:28.779743: step: 56/530, loss: 0.018764590844511986
2023-01-23 02:43:29.893921: step: 60/530, loss: 4.0721897676121444e-05
2023-01-23 02:43:30.995404: step: 64/530, loss: 0.00045776370097883046
2023-01-23 02:43:32.072172: step: 68/530, loss: 0.00021629333787132055
2023-01-23 02:43:33.243334: step: 72/530, loss: 0.026780128479003906
2023-01-23 02:43:34.346708: step: 76/530, loss: 0.02058105543255806
2023-01-23 02:43:35.447453: step: 80/530, loss: 0.0008292198181152344
2023-01-23 02:43:36.546954: step: 84/530, loss: 0.003988075535744429
2023-01-23 02:43:37.672683: step: 88/530, loss: 0.04498253017663956
2023-01-23 02:43:38.795697: step: 92/530, loss: 0.002807998564094305
2023-01-23 02:43:39.976134: step: 96/530, loss: 0.04000682756304741
2023-01-23 02:43:41.075191: step: 100/530, loss: 0.002509593963623047
2023-01-23 02:43:42.197594: step: 104/530, loss: 0.007209682371467352
2023-01-23 02:43:43.329276: step: 108/530, loss: 0.0013561248779296875
2023-01-23 02:43:44.394236: step: 112/530, loss: 0.02415313757956028
2023-01-23 02:43:45.515252: step: 116/530, loss: 0.002601051237434149
2023-01-23 02:43:46.611482: step: 120/530, loss: 0.002884387969970703
2023-01-23 02:43:47.707609: step: 124/530, loss: 8.18252592580393e-05
2023-01-23 02:43:48.788473: step: 128/530, loss: 0.0002881288528442383
2023-01-23 02:43:49.895772: step: 132/530, loss: 0.022058868780732155
2023-01-23 02:43:50.979915: step: 136/530, loss: 0.01372599508613348
2023-01-23 02:43:52.088173: step: 140/530, loss: 0.004072952084243298
2023-01-23 02:43:53.183888: step: 144/530, loss: 0.02881307527422905
2023-01-23 02:43:54.276623: step: 148/530, loss: 0.005015516187995672
2023-01-23 02:43:55.360545: step: 152/530, loss: 0.013761281967163086
2023-01-23 02:43:56.488376: step: 156/530, loss: 0.005974388215690851
2023-01-23 02:43:57.607712: step: 160/530, loss: 0.00023908614821266383
2023-01-23 02:43:58.696013: step: 164/530, loss: 0.03368755429983139
2023-01-23 02:43:59.789074: step: 168/530, loss: 0.0037100552581250668
2023-01-23 02:44:00.896562: step: 172/530, loss: 0.016433047130703926
2023-01-23 02:44:02.047546: step: 176/530, loss: 0.004917907994240522
2023-01-23 02:44:03.165456: step: 180/530, loss: 0.04632911458611488
2023-01-23 02:44:04.246575: step: 184/530, loss: 0.003569984342902899
2023-01-23 02:44:05.321321: step: 188/530, loss: 0.02788066864013672
2023-01-23 02:44:06.429254: step: 192/530, loss: 0.01816578023135662
2023-01-23 02:44:07.515681: step: 196/530, loss: 0.0038685323670506477
2023-01-23 02:44:08.631130: step: 200/530, loss: 0.00527148274704814
2023-01-23 02:44:09.761543: step: 204/530, loss: 0.0329379066824913
2023-01-23 02:44:10.855767: step: 208/530, loss: 3.948211815441027e-05
2023-01-23 02:44:11.992391: step: 212/530, loss: 0.01047058217227459
2023-01-23 02:44:13.102772: step: 216/530, loss: 0.013763809576630592
2023-01-23 02:44:14.225822: step: 220/530, loss: 0.0038690567016601562
2023-01-23 02:44:15.327435: step: 224/530, loss: 0.0023657798301428556
2023-01-23 02:44:16.423368: step: 228/530, loss: 0.014734364114701748
2023-01-23 02:44:17.546822: step: 232/530, loss: 0.0008111476781778038
2023-01-23 02:44:18.654120: step: 236/530, loss: 0.14696788787841797
2023-01-23 02:44:19.767931: step: 240/530, loss: 0.0006644249078817666
2023-01-23 02:44:20.871501: step: 244/530, loss: 0.012244701385498047
2023-01-23 02:44:21.942256: step: 248/530, loss: 0.009781074710190296
2023-01-23 02:44:23.039075: step: 252/530, loss: 0.007044220343232155
2023-01-23 02:44:24.138118: step: 256/530, loss: 0.012603282928466797
2023-01-23 02:44:25.251357: step: 260/530, loss: 0.012927437201142311
2023-01-23 02:44:26.350269: step: 264/530, loss: 0.0013759852154180408
2023-01-23 02:44:27.436744: step: 268/530, loss: 0.00262794503942132
2023-01-23 02:44:28.534074: step: 272/530, loss: 0.00012855530076194555
2023-01-23 02:44:29.631648: step: 276/530, loss: 0.012608624063432217
2023-01-23 02:44:30.758348: step: 280/530, loss: 0.0007369041559286416
2023-01-23 02:44:31.854125: step: 284/530, loss: 0.0003531932889018208
2023-01-23 02:44:32.984343: step: 288/530, loss: 0.0015770912868902087
2023-01-23 02:44:34.090247: step: 292/530, loss: 0.00454025249928236
2023-01-23 02:44:35.215452: step: 296/530, loss: 0.03350086137652397
2023-01-23 02:44:36.329225: step: 300/530, loss: 0.09072523564100266
2023-01-23 02:44:37.412169: step: 304/530, loss: 0.045365143567323685
2023-01-23 02:44:38.517140: step: 308/530, loss: 0.0015707970596849918
2023-01-23 02:44:39.617990: step: 312/530, loss: 0.018577218055725098
2023-01-23 02:44:40.743987: step: 316/530, loss: 0.006319618318229914
2023-01-23 02:44:41.875799: step: 320/530, loss: 0.005485344212502241
2023-01-23 02:44:42.954430: step: 324/530, loss: 0.010674476623535156
2023-01-23 02:44:44.078282: step: 328/530, loss: 0.17406940460205078
2023-01-23 02:44:45.184103: step: 332/530, loss: 0.0005251884576864541
2023-01-23 02:44:46.296784: step: 336/530, loss: 0.023634053766727448
2023-01-23 02:44:47.412093: step: 340/530, loss: 0.03794508054852486
2023-01-23 02:44:48.509852: step: 344/530, loss: 3.700256274896674e-05
2023-01-23 02:44:49.607947: step: 348/530, loss: 0.0004760742303915322
2023-01-23 02:44:50.741697: step: 352/530, loss: 0.0010686874156817794
2023-01-23 02:44:51.846072: step: 356/530, loss: 0.0005650520324707031
2023-01-23 02:44:52.947920: step: 360/530, loss: 0.0023110390175133944
2023-01-23 02:44:54.068350: step: 364/530, loss: 0.27877846360206604
2023-01-23 02:44:55.160143: step: 368/530, loss: 0.00013256072998046875
2023-01-23 02:44:56.272894: step: 372/530, loss: 0.06950131058692932
2023-01-23 02:44:57.357487: step: 376/530, loss: 0.000293540972052142
2023-01-23 02:44:58.463493: step: 380/530, loss: 0.03360772505402565
2023-01-23 02:44:59.577622: step: 384/530, loss: 2.4127959477482364e-05
2023-01-23 02:45:00.671517: step: 388/530, loss: 0.0009849548805505037
2023-01-23 02:45:01.776352: step: 392/530, loss: 0.0013438225723803043
2023-01-23 02:45:02.895030: step: 396/530, loss: 0.007925224490463734
2023-01-23 02:45:03.983439: step: 400/530, loss: 0.005747795104980469
2023-01-23 02:45:05.065674: step: 404/530, loss: 0.12380104511976242
2023-01-23 02:45:06.145074: step: 408/530, loss: 0.00047712327796034515
2023-01-23 02:45:07.236907: step: 412/530, loss: 0.005205434747040272
2023-01-23 02:45:08.321670: step: 416/530, loss: 0.0001520156947663054
2023-01-23 02:45:09.431263: step: 420/530, loss: 0.002767849015071988
2023-01-23 02:45:10.548979: step: 424/530, loss: 0.028301334008574486
2023-01-23 02:45:11.631055: step: 428/530, loss: 0.0032245637848973274
2023-01-23 02:45:12.745617: step: 432/530, loss: 0.004717600531876087
2023-01-23 02:45:13.873620: step: 436/530, loss: 0.0007719040149822831
2023-01-23 02:45:14.993712: step: 440/530, loss: 0.003094196319580078
2023-01-23 02:45:16.096069: step: 444/530, loss: 0.08459696918725967
2023-01-23 02:45:17.201429: step: 448/530, loss: 0.004091834649443626
2023-01-23 02:45:18.323154: step: 452/530, loss: 0.0009126663208007812
2023-01-23 02:45:19.436760: step: 456/530, loss: 0.028426742181181908
2023-01-23 02:45:20.547466: step: 460/530, loss: 2.3841855636419496e-06
2023-01-23 02:45:21.647509: step: 464/530, loss: 0.00263385777361691
2023-01-23 02:45:22.775382: step: 468/530, loss: 0.02220935933291912
2023-01-23 02:45:23.856805: step: 472/530, loss: 0.03517866134643555
2023-01-23 02:45:24.954365: step: 476/530, loss: 0.01036615390330553
2023-01-23 02:45:26.072206: step: 480/530, loss: 0.11877574771642685
2023-01-23 02:45:27.184743: step: 484/530, loss: 0.0001546859712107107
2023-01-23 02:45:28.303860: step: 488/530, loss: 0.00022540093050338328
2023-01-23 02:45:29.455645: step: 492/530, loss: 0.010837174020707607
2023-01-23 02:45:30.562830: step: 496/530, loss: 0.011769247241318226
2023-01-23 02:45:31.664313: step: 500/530, loss: 0.006908082868903875
2023-01-23 02:45:32.770263: step: 504/530, loss: 0.02253875695168972
2023-01-23 02:45:33.840732: step: 508/530, loss: 3.0231476557673886e-05
2023-01-23 02:45:34.919794: step: 512/530, loss: 0.0017405509715899825
2023-01-23 02:45:36.042519: step: 516/530, loss: 0.026087380945682526
2023-01-23 02:45:37.164107: step: 520/530, loss: 0.06235980987548828
2023-01-23 02:45:38.291655: step: 524/530, loss: 0.01061716116964817
2023-01-23 02:45:39.395696: step: 528/530, loss: 0.015833426266908646
2023-01-23 02:45:40.521180: step: 532/530, loss: 0.006182003300637007
2023-01-23 02:45:41.650910: step: 536/530, loss: 0.01676889695227146
2023-01-23 02:45:42.807217: step: 540/530, loss: 0.0006196975591592491
2023-01-23 02:45:43.923984: step: 544/530, loss: 0.001897621201351285
2023-01-23 02:45:45.028159: step: 548/530, loss: 0.0015483855968341231
2023-01-23 02:45:46.127573: step: 552/530, loss: 0.01638955995440483
2023-01-23 02:45:47.224492: step: 556/530, loss: 0.034158192574977875
2023-01-23 02:45:48.320976: step: 560/530, loss: 0.00027751922607421875
2023-01-23 02:45:49.407010: step: 564/530, loss: 0.0030271292198449373
2023-01-23 02:45:50.493169: step: 568/530, loss: 0.0021017075050622225
2023-01-23 02:45:51.590275: step: 572/530, loss: 0.012898731976747513
2023-01-23 02:45:52.688794: step: 576/530, loss: 0.04820384830236435
2023-01-23 02:45:53.831977: step: 580/530, loss: 0.001486110733821988
2023-01-23 02:45:54.990728: step: 584/530, loss: 0.03345317766070366
2023-01-23 02:45:56.112709: step: 588/530, loss: 0.00045843125553801656
2023-01-23 02:45:57.219419: step: 592/530, loss: 0.012680530548095703
2023-01-23 02:45:58.313855: step: 596/530, loss: 0.37928637862205505
2023-01-23 02:45:59.416486: step: 600/530, loss: 0.015897369012236595
2023-01-23 02:46:00.539568: step: 604/530, loss: 0.005233574192970991
2023-01-23 02:46:01.647943: step: 608/530, loss: 6.2041015625
2023-01-23 02:46:02.775984: step: 612/530, loss: 0.0319274440407753
2023-01-23 02:46:03.862248: step: 616/530, loss: 0.06821155548095703
2023-01-23 02:46:04.967312: step: 620/530, loss: 0.023381341248750687
2023-01-23 02:46:06.068749: step: 624/530, loss: 0.009149646386504173
2023-01-23 02:46:07.162404: step: 628/530, loss: 0.0005740165943279862
2023-01-23 02:46:08.263035: step: 632/530, loss: 0.0010797500144690275
2023-01-23 02:46:09.339670: step: 636/530, loss: 0.005460548214614391
2023-01-23 02:46:10.424320: step: 640/530, loss: 0.0027456283569335938
2023-01-23 02:46:11.547144: step: 644/530, loss: 1.888275073724799e-05
2023-01-23 02:46:12.649455: step: 648/530, loss: 0.003803444094955921
2023-01-23 02:46:13.758834: step: 652/530, loss: 0.002662467770278454
2023-01-23 02:46:14.875162: step: 656/530, loss: 0.4119015634059906
2023-01-23 02:46:15.999572: step: 660/530, loss: 0.033118247985839844
2023-01-23 02:46:17.113634: step: 664/530, loss: 0.0003365039883647114
2023-01-23 02:46:18.227501: step: 668/530, loss: 0.022732913494110107
2023-01-23 02:46:19.337007: step: 672/530, loss: 0.11164913326501846
2023-01-23 02:46:20.434044: step: 676/530, loss: 0.006422615144401789
2023-01-23 02:46:21.518764: step: 680/530, loss: 0.0001486778346588835
2023-01-23 02:46:22.638547: step: 684/530, loss: 0.0013898849720135331
2023-01-23 02:46:23.764847: step: 688/530, loss: 0.004419135861098766
2023-01-23 02:46:24.865777: step: 692/530, loss: 0.06912650913000107
2023-01-23 02:46:25.969970: step: 696/530, loss: 0.003159713465720415
2023-01-23 02:46:27.074965: step: 700/530, loss: 0.030974864959716797
2023-01-23 02:46:28.186492: step: 704/530, loss: 0.0015718459617346525
2023-01-23 02:46:29.325632: step: 708/530, loss: 0.05807838216423988
2023-01-23 02:46:30.402872: step: 712/530, loss: 0.002372622722759843
2023-01-23 02:46:31.516797: step: 716/530, loss: 0.005496427416801453
2023-01-23 02:46:32.619163: step: 720/530, loss: 0.00978460256010294
2023-01-23 02:46:33.753398: step: 724/530, loss: 0.0036508559715002775
2023-01-23 02:46:34.838569: step: 728/530, loss: 0.04507208243012428
2023-01-23 02:46:35.952377: step: 732/530, loss: 0.06725358963012695
2023-01-23 02:46:37.082493: step: 736/530, loss: 2.517700158932712e-05
2023-01-23 02:46:38.192533: step: 740/530, loss: 0.06271419674158096
2023-01-23 02:46:39.283357: step: 744/530, loss: 0.03714122995734215
2023-01-23 02:46:40.380113: step: 748/530, loss: 0.012750553898513317
2023-01-23 02:46:41.465176: step: 752/530, loss: 0.033313848078250885
2023-01-23 02:46:42.547944: step: 756/530, loss: 0.00023412704467773438
2023-01-23 02:46:43.627322: step: 760/530, loss: 0.0010076522594317794
2023-01-23 02:46:44.700783: step: 764/530, loss: 0.01904602162539959
2023-01-23 02:46:45.772790: step: 768/530, loss: 0.03557164594531059
2023-01-23 02:46:46.879894: step: 772/530, loss: 0.06672267615795135
2023-01-23 02:46:47.998411: step: 776/530, loss: 0.0001180648832814768
2023-01-23 02:46:49.084244: step: 780/530, loss: 1.0299683708581142e-05
2023-01-23 02:46:50.197034: step: 784/530, loss: 0.042052604258060455
2023-01-23 02:46:51.323775: step: 788/530, loss: 1.0829336643218994
2023-01-23 02:46:52.421574: step: 792/530, loss: 0.007277870550751686
2023-01-23 02:46:53.526585: step: 796/530, loss: 0.0016148567665368319
2023-01-23 02:46:54.640005: step: 800/530, loss: 0.004467988386750221
2023-01-23 02:46:55.754955: step: 804/530, loss: 0.3038408160209656
2023-01-23 02:46:56.859123: step: 808/530, loss: 0.004821968264877796
2023-01-23 02:46:57.977939: step: 812/530, loss: 0.019588088616728783
2023-01-23 02:46:59.075018: step: 816/530, loss: 0.008867979049682617
2023-01-23 02:47:00.230236: step: 820/530, loss: 0.4668981432914734
2023-01-23 02:47:01.341717: step: 824/530, loss: 0.0013471603160724044
2023-01-23 02:47:02.444300: step: 828/530, loss: 0.02161569520831108
2023-01-23 02:47:03.581915: step: 832/530, loss: 0.007617759983986616
2023-01-23 02:47:04.711737: step: 836/530, loss: 0.006304549984633923
2023-01-23 02:47:05.792193: step: 840/530, loss: 4.138946678722277e-05
2023-01-23 02:47:06.900467: step: 844/530, loss: 0.0031252861954271793
2023-01-23 02:47:08.021038: step: 848/530, loss: 0.0004732370434794575
2023-01-23 02:47:09.123776: step: 852/530, loss: 0.012659072875976562
2023-01-23 02:47:10.243471: step: 856/530, loss: 0.03408327326178551
2023-01-23 02:47:11.334010: step: 860/530, loss: 0.44312822818756104
2023-01-23 02:47:12.406656: step: 864/530, loss: 0.005470371339470148
2023-01-23 02:47:13.535999: step: 868/530, loss: 0.0005792618030682206
2023-01-23 02:47:14.644831: step: 872/530, loss: 0.010272979736328125
2023-01-23 02:47:15.750829: step: 876/530, loss: 0.0034227371215820312
2023-01-23 02:47:16.852804: step: 880/530, loss: 0.030771778896450996
2023-01-23 02:47:17.939605: step: 884/530, loss: 0.6555532217025757
2023-01-23 02:47:19.029057: step: 888/530, loss: 2.498626781743951e-05
2023-01-23 02:47:20.138861: step: 892/530, loss: 2.8908289095852524e-07
2023-01-23 02:47:21.239148: step: 896/530, loss: 0.0002452850458212197
2023-01-23 02:47:22.346662: step: 900/530, loss: 0.009789371863007545
2023-01-23 02:47:23.479563: step: 904/530, loss: 0.7422406077384949
2023-01-23 02:47:24.546843: step: 908/530, loss: 0.06669817864894867
2023-01-23 02:47:25.686430: step: 912/530, loss: 0.0007894918671809137
2023-01-23 02:47:26.813760: step: 916/530, loss: 0.015140151605010033
2023-01-23 02:47:27.909865: step: 920/530, loss: 0.0004150390450377017
2023-01-23 02:47:29.020111: step: 924/530, loss: 0.00042724609375
2023-01-23 02:47:30.143088: step: 928/530, loss: 9.1552734375e-05
2023-01-23 02:47:31.256272: step: 932/530, loss: 0.004136275965720415
2023-01-23 02:47:32.381256: step: 936/530, loss: 0.004865026567131281
2023-01-23 02:47:33.503904: step: 940/530, loss: 0.01209402084350586
2023-01-23 02:47:34.602221: step: 944/530, loss: 0.9639291763305664
2023-01-23 02:47:35.715535: step: 948/530, loss: 0.001890468643978238
2023-01-23 02:47:36.865224: step: 952/530, loss: 0.04224586859345436
2023-01-23 02:47:37.957210: step: 956/530, loss: 0.021381568163633347
2023-01-23 02:47:39.090976: step: 960/530, loss: 0.006392288487404585
2023-01-23 02:47:40.220721: step: 964/530, loss: 0.025151537731289864
2023-01-23 02:47:41.318069: step: 968/530, loss: 0.068425752222538
2023-01-23 02:47:42.405168: step: 972/530, loss: 0.0042781829833984375
2023-01-23 02:47:43.483124: step: 976/530, loss: 0.0666540116071701
2023-01-23 02:47:44.573987: step: 980/530, loss: 0.012535477057099342
2023-01-23 02:47:45.702964: step: 984/530, loss: 0.005095815751701593
2023-01-23 02:47:46.812700: step: 988/530, loss: 0.007094860076904297
2023-01-23 02:47:47.900817: step: 992/530, loss: 0.0004225731245242059
2023-01-23 02:47:49.017820: step: 996/530, loss: 0.03543434292078018
2023-01-23 02:47:50.129829: step: 1000/530, loss: 0.013332461938261986
2023-01-23 02:47:51.246310: step: 1004/530, loss: 0.027044106274843216
2023-01-23 02:47:52.387208: step: 1008/530, loss: 0.04256897047162056
2023-01-23 02:47:53.494822: step: 1012/530, loss: 0.010259628295898438
2023-01-23 02:47:54.598238: step: 1016/530, loss: 0.02849479950964451
2023-01-23 02:47:55.684284: step: 1020/530, loss: 0.00013093948655296117
2023-01-23 02:47:56.773985: step: 1024/530, loss: 0.0160504337400198
2023-01-23 02:47:57.867357: step: 1028/530, loss: 0.0008813858148641884
2023-01-23 02:47:58.974061: step: 1032/530, loss: 0.009639930911362171
2023-01-23 02:48:00.069205: step: 1036/530, loss: 0.01188507117331028
2023-01-23 02:48:01.198092: step: 1040/530, loss: 0.16213148832321167
2023-01-23 02:48:02.283624: step: 1044/530, loss: 0.0029811635613441467
2023-01-23 02:48:03.409699: step: 1048/530, loss: 0.024472856894135475
2023-01-23 02:48:04.509117: step: 1052/530, loss: 0.0312594436109066
2023-01-23 02:48:05.583269: step: 1056/530, loss: 0.05646343529224396
2023-01-23 02:48:06.695932: step: 1060/530, loss: 0.001609897706657648
2023-01-23 02:48:07.800149: step: 1064/530, loss: 0.017012977972626686
2023-01-23 02:48:08.890481: step: 1068/530, loss: 8.544922457076609e-05
2023-01-23 02:48:10.026415: step: 1072/530, loss: 0.09310703724622726
2023-01-23 02:48:11.124397: step: 1076/530, loss: 0.0007383346674032509
2023-01-23 02:48:12.230689: step: 1080/530, loss: 0.036528777331113815
2023-01-23 02:48:13.337855: step: 1084/530, loss: 0.08380565792322159
2023-01-23 02:48:14.473780: step: 1088/530, loss: 0.004727697465568781
2023-01-23 02:48:15.556898: step: 1092/530, loss: 0.005180931184440851
2023-01-23 02:48:16.670270: step: 1096/530, loss: 0.02166728861629963
2023-01-23 02:48:17.771739: step: 1100/530, loss: 0.002404499100521207
2023-01-23 02:48:18.870063: step: 1104/530, loss: 0.0031962874345481396
2023-01-23 02:48:20.055616: step: 1108/530, loss: 0.020989038050174713
2023-01-23 02:48:21.196278: step: 1112/530, loss: 0.006503391079604626
2023-01-23 02:48:22.298192: step: 1116/530, loss: 0.019374562427401543
2023-01-23 02:48:23.422916: step: 1120/530, loss: 0.00011310577974654734
2023-01-23 02:48:24.511520: step: 1124/530, loss: 4.048794289701618e-05
2023-01-23 02:48:25.624687: step: 1128/530, loss: 0.0201478973031044
2023-01-23 02:48:26.726277: step: 1132/530, loss: 0.00022983551025390625
2023-01-23 02:48:27.807829: step: 1136/530, loss: 0.009818077087402344
2023-01-23 02:48:28.896577: step: 1140/530, loss: 0.00019598007202148438
2023-01-23 02:48:30.030113: step: 1144/530, loss: 0.009396982379257679
2023-01-23 02:48:31.118873: step: 1148/530, loss: 0.034554291516542435
2023-01-23 02:48:32.217357: step: 1152/530, loss: 0.00870513916015625
2023-01-23 02:48:33.308699: step: 1156/530, loss: 0.002601146697998047
2023-01-23 02:48:34.409152: step: 1160/530, loss: -9.5367431640625e-07
2023-01-23 02:48:35.527260: step: 1164/530, loss: 0.0006130218971520662
2023-01-23 02:48:36.639186: step: 1168/530, loss: 0.01850605010986328
2023-01-23 02:48:37.751980: step: 1172/530, loss: 0.006359672639518976
2023-01-23 02:48:38.896780: step: 1176/530, loss: 0.008261299692094326
2023-01-23 02:48:40.019115: step: 1180/530, loss: 0.0049537657760083675
2023-01-23 02:48:41.167736: step: 1184/530, loss: 0.014668751507997513
2023-01-23 02:48:42.271104: step: 1188/530, loss: 0.0007142424583435059
2023-01-23 02:48:43.386949: step: 1192/530, loss: 0.014633560553193092
2023-01-23 02:48:44.492292: step: 1196/530, loss: 0.00015501974849030375
2023-01-23 02:48:45.590592: step: 1200/530, loss: 0.009972954168915749
2023-01-23 02:48:46.691689: step: 1204/530, loss: 0.1317215859889984
2023-01-23 02:48:47.780043: step: 1208/530, loss: 0.002022361848503351
2023-01-23 02:48:48.852655: step: 1212/530, loss: 0.00047302249004133046
2023-01-23 02:48:49.979129: step: 1216/530, loss: 0.0024082183372229338
2023-01-23 02:48:51.084221: step: 1220/530, loss: 0.17281703650951385
2023-01-23 02:48:52.175264: step: 1224/530, loss: 0.03386878967285156
2023-01-23 02:48:53.278716: step: 1228/530, loss: 0.02229137346148491
2023-01-23 02:48:54.372109: step: 1232/530, loss: 4.1961669921875e-05
2023-01-23 02:48:55.460779: step: 1236/530, loss: 0.001348781632259488
2023-01-23 02:48:56.551572: step: 1240/530, loss: 1.7070771718863398e-05
2023-01-23 02:48:57.653986: step: 1244/530, loss: 0.036410141736269
2023-01-23 02:48:58.757317: step: 1248/530, loss: 0.0038714411202818155
2023-01-23 02:48:59.880556: step: 1252/530, loss: 0.07400169968605042
2023-01-23 02:49:01.032149: step: 1256/530, loss: 0.00035009384737350047
2023-01-23 02:49:02.162943: step: 1260/530, loss: 0.007288026623427868
2023-01-23 02:49:03.275022: step: 1264/530, loss: 0.0009682655218057334
2023-01-23 02:49:04.380106: step: 1268/530, loss: 8.00132766016759e-05
2023-01-23 02:49:05.470113: step: 1272/530, loss: 0.00016698837862350047
2023-01-23 02:49:06.570794: step: 1276/530, loss: 0.01668071746826172
2023-01-23 02:49:07.664560: step: 1280/530, loss: 0.045046236366033554
2023-01-23 02:49:08.768184: step: 1284/530, loss: 0.007641696836799383
2023-01-23 02:49:09.908468: step: 1288/530, loss: 0.0012553215492516756
2023-01-23 02:49:11.011680: step: 1292/530, loss: 0.007515001576393843
2023-01-23 02:49:12.136432: step: 1296/530, loss: 0.013015221804380417
2023-01-23 02:49:13.249456: step: 1300/530, loss: 0.08292216807603836
2023-01-23 02:49:14.331281: step: 1304/530, loss: 0.004078865051269531
2023-01-23 02:49:15.432475: step: 1308/530, loss: 0.04541473463177681
2023-01-23 02:49:16.533069: step: 1312/530, loss: 0.0204180721193552
2023-01-23 02:49:17.633784: step: 1316/530, loss: 0.008442306891083717
2023-01-23 02:49:18.746294: step: 1320/530, loss: 0.02502145804464817
2023-01-23 02:49:19.836252: step: 1324/530, loss: 0.005723190493881702
2023-01-23 02:49:20.926083: step: 1328/530, loss: 0.0024667263496667147
2023-01-23 02:49:22.027665: step: 1332/530, loss: 0.044756900519132614
2023-01-23 02:49:23.158579: step: 1336/530, loss: 0.03814239427447319
2023-01-23 02:49:24.251016: step: 1340/530, loss: 0.009924125857651234
2023-01-23 02:49:25.335148: step: 1344/530, loss: 0.06864146888256073
2023-01-23 02:49:26.456638: step: 1348/530, loss: 0.029261494055390358
2023-01-23 02:49:27.542228: step: 1352/530, loss: 0.013843536376953125
2023-01-23 02:49:28.620341: step: 1356/530, loss: 0.019724274054169655
2023-01-23 02:49:29.715091: step: 1360/530, loss: 0.002116656396538019
2023-01-23 02:49:30.816231: step: 1364/530, loss: 8.77380352903856e-06
2023-01-23 02:49:31.911240: step: 1368/530, loss: 0.0008076310041360557
2023-01-23 02:49:33.009980: step: 1372/530, loss: 0.004234886262565851
2023-01-23 02:49:34.140979: step: 1376/530, loss: 0.0653219223022461
2023-01-23 02:49:35.228468: step: 1380/530, loss: 0.00426483154296875
2023-01-23 02:49:36.317956: step: 1384/530, loss: 0.004421901423484087
2023-01-23 02:49:37.437325: step: 1388/530, loss: 0.03896503522992134
2023-01-23 02:49:38.514005: step: 1392/530, loss: 1.52587890625e-05
2023-01-23 02:49:39.635676: step: 1396/530, loss: 1.621246337890625e-05
2023-01-23 02:49:40.745857: step: 1400/530, loss: 0.010278606787323952
2023-01-23 02:49:41.857311: step: 1404/530, loss: 0.020675277337431908
2023-01-23 02:49:42.970622: step: 1408/530, loss: 0.00064172747079283
2023-01-23 02:49:44.065140: step: 1412/530, loss: 0.013917803764343262
2023-01-23 02:49:45.176062: step: 1416/530, loss: 4.9400332500226796e-05
2023-01-23 02:49:46.283414: step: 1420/530, loss: 0.0021236420143395662
2023-01-23 02:49:47.365816: step: 1424/530, loss: 0.0009799957042559981
2023-01-23 02:49:48.484360: step: 1428/530, loss: 0.04166078940033913
2023-01-23 02:49:49.609775: step: 1432/530, loss: 0.001198721001856029
2023-01-23 02:49:50.760598: step: 1436/530, loss: 9.279251389671117e-05
2023-01-23 02:49:51.885940: step: 1440/530, loss: 0.1728280633687973
2023-01-23 02:49:53.006357: step: 1444/530, loss: 7.343292236328125e-05
2023-01-23 02:49:54.100455: step: 1448/530, loss: 0.03286729007959366
2023-01-23 02:49:55.222407: step: 1452/530, loss: 0.06603384017944336
2023-01-23 02:49:56.311900: step: 1456/530, loss: 0.00038566591683775187
2023-01-23 02:49:57.406704: step: 1460/530, loss: 0.0004103660467080772
2023-01-23 02:49:58.488310: step: 1464/530, loss: 0.022350406274199486
2023-01-23 02:49:59.606686: step: 1468/530, loss: 8.578300185035914e-05
2023-01-23 02:50:00.703431: step: 1472/530, loss: 0.0057597397826612
2023-01-23 02:50:01.810674: step: 1476/530, loss: 1.468658410885837e-05
2023-01-23 02:50:02.934794: step: 1480/530, loss: 0.035652924329042435
2023-01-23 02:50:04.043205: step: 1484/530, loss: 0.02006225660443306
2023-01-23 02:50:05.125142: step: 1488/530, loss: 0.004315400030463934
2023-01-23 02:50:06.257023: step: 1492/530, loss: 0.0440157875418663
2023-01-23 02:50:07.393975: step: 1496/530, loss: 0.0006309509044513106
2023-01-23 02:50:08.484447: step: 1500/530, loss: 0.01628723181784153
2023-01-23 02:50:09.573788: step: 1504/530, loss: 0.0033539533615112305
2023-01-23 02:50:10.686148: step: 1508/530, loss: 0.0008552551153115928
2023-01-23 02:50:11.856066: step: 1512/530, loss: 0.0022017478477209806
2023-01-23 02:50:12.960741: step: 1516/530, loss: 0.07858486473560333
2023-01-23 02:50:14.067219: step: 1520/530, loss: 0.156391441822052
2023-01-23 02:50:15.170936: step: 1524/530, loss: 0.003317594761028886
2023-01-23 02:50:16.277023: step: 1528/530, loss: 0.0031710625626146793
2023-01-23 02:50:17.373325: step: 1532/530, loss: 0.03515835106372833
2023-01-23 02:50:18.503496: step: 1536/530, loss: 0.0077110291458666325
2023-01-23 02:50:19.633011: step: 1540/530, loss: 0.003881359240040183
2023-01-23 02:50:20.726419: step: 1544/530, loss: 0.019438840448856354
2023-01-23 02:50:21.827797: step: 1548/530, loss: 0.0017639161087572575
2023-01-23 02:50:22.962558: step: 1552/530, loss: 0.09869042038917542
2023-01-23 02:50:24.056716: step: 1556/530, loss: 0.026928137987852097
2023-01-23 02:50:25.153923: step: 1560/530, loss: 0.00115118024405092
2023-01-23 02:50:26.242783: step: 1564/530, loss: 0.0004074096796102822
2023-01-23 02:50:27.369752: step: 1568/530, loss: 0.05402183532714844
2023-01-23 02:50:28.487478: step: 1572/530, loss: 0.007879257202148438
2023-01-23 02:50:29.562964: step: 1576/530, loss: 0.016720199957489967
2023-01-23 02:50:30.697248: step: 1580/530, loss: 0.03910808637738228
2023-01-23 02:50:31.815011: step: 1584/530, loss: 0.01147689949721098
2023-01-23 02:50:32.940675: step: 1588/530, loss: 0.010814475826919079
2023-01-23 02:50:34.037399: step: 1592/530, loss: 7.90119229350239e-05
2023-01-23 02:50:35.137789: step: 1596/530, loss: 0.0009774684440344572
2023-01-23 02:50:36.269311: step: 1600/530, loss: 6.017685154802166e-05
2023-01-23 02:50:37.357995: step: 1604/530, loss: 0.00023078919912222773
2023-01-23 02:50:38.463221: step: 1608/530, loss: 0.012811469845473766
2023-01-23 02:50:39.564266: step: 1612/530, loss: 0.012253952212631702
2023-01-23 02:50:40.651248: step: 1616/530, loss: 3.2424929941043956e-06
2023-01-23 02:50:41.741789: step: 1620/530, loss: 0.0021566867362707853
2023-01-23 02:50:42.850348: step: 1624/530, loss: 0.0004830360412597656
2023-01-23 02:50:43.982453: step: 1628/530, loss: 0.027592848986387253
2023-01-23 02:50:45.077424: step: 1632/530, loss: 0.05040645971894264
2023-01-23 02:50:46.163865: step: 1636/530, loss: 0.0016323089366778731
2023-01-23 02:50:47.280059: step: 1640/530, loss: 0.014081288129091263
2023-01-23 02:50:48.404580: step: 1644/530, loss: 0.015056419186294079
2023-01-23 02:50:49.519006: step: 1648/530, loss: 0.0013641358818858862
2023-01-23 02:50:50.628437: step: 1652/530, loss: 7.83920258982107e-05
2023-01-23 02:50:51.761000: step: 1656/530, loss: 0.0814613327383995
2023-01-23 02:50:52.895211: step: 1660/530, loss: 0.02677326276898384
2023-01-23 02:50:54.026380: step: 1664/530, loss: 0.0051132203079760075
2023-01-23 02:50:55.134203: step: 1668/530, loss: 0.0009502411121502519
2023-01-23 02:50:56.276526: step: 1672/530, loss: 0.033921051770448685
2023-01-23 02:50:57.375052: step: 1676/530, loss: 0.004532623570412397
2023-01-23 02:50:58.468823: step: 1680/530, loss: 0.011680603958666325
2023-01-23 02:50:59.553040: step: 1684/530, loss: 0.06151679903268814
2023-01-23 02:51:00.669163: step: 1688/530, loss: 0.03455018997192383
2023-01-23 02:51:01.799529: step: 1692/530, loss: 0.004935741424560547
2023-01-23 02:51:02.919536: step: 1696/530, loss: 0.00011367797560524195
2023-01-23 02:51:04.021338: step: 1700/530, loss: 0.02002906985580921
2023-01-23 02:51:05.153997: step: 1704/530, loss: 0.01657142862677574
2023-01-23 02:51:06.257834: step: 1708/530, loss: 0.04720735922455788
2023-01-23 02:51:07.346852: step: 1712/530, loss: 0.00019030571274925023
2023-01-23 02:51:08.474052: step: 1716/530, loss: 0.0916501060128212
2023-01-23 02:51:09.581022: step: 1720/530, loss: 0.0005937576061114669
2023-01-23 02:51:10.724319: step: 1724/530, loss: 0.0009849548805505037
2023-01-23 02:51:11.832243: step: 1728/530, loss: 0.42615824937820435
2023-01-23 02:51:12.988781: step: 1732/530, loss: 0.014369201846420765
2023-01-23 02:51:14.092201: step: 1736/530, loss: 0.007511854637414217
2023-01-23 02:51:15.185113: step: 1740/530, loss: 0.0006941318861208856
2023-01-23 02:51:16.291182: step: 1744/530, loss: 0.01081695593893528
2023-01-23 02:51:17.388595: step: 1748/530, loss: 0.009366368874907494
2023-01-23 02:51:18.487693: step: 1752/530, loss: 0.002460479736328125
2023-01-23 02:51:19.594595: step: 1756/530, loss: 0.07039991766214371
2023-01-23 02:51:20.732849: step: 1760/530, loss: 0.006768703460693359
2023-01-23 02:51:21.845590: step: 1764/530, loss: 0.10855960845947266
2023-01-23 02:51:22.972537: step: 1768/530, loss: 0.04037828743457794
2023-01-23 02:51:24.074198: step: 1772/530, loss: 0.0015172958374023438
2023-01-23 02:51:25.186461: step: 1776/530, loss: 1.7505884898127988e-05
2023-01-23 02:51:26.315997: step: 1780/530, loss: 0.008764267899096012
2023-01-23 02:51:27.423254: step: 1784/530, loss: 0.004359626676887274
2023-01-23 02:51:28.522367: step: 1788/530, loss: 0.008399391546845436
2023-01-23 02:51:29.663382: step: 1792/530, loss: 0.024730682373046875
2023-01-23 02:51:30.770262: step: 1796/530, loss: 0.03802294656634331
2023-01-23 02:51:31.911324: step: 1800/530, loss: 0.047095589339733124
2023-01-23 02:51:33.021287: step: 1804/530, loss: 0.005465054884552956
2023-01-23 02:51:34.111746: step: 1808/530, loss: 0.00023422240337822586
2023-01-23 02:51:35.238478: step: 1812/530, loss: 0.05126752704381943
2023-01-23 02:51:36.351435: step: 1816/530, loss: 0.03438548743724823
2023-01-23 02:51:37.466976: step: 1820/530, loss: 0.04506521299481392
2023-01-23 02:51:38.566467: step: 1824/530, loss: 0.020792581140995026
2023-01-23 02:51:39.657522: step: 1828/530, loss: 0.00799856148660183
2023-01-23 02:51:40.766813: step: 1832/530, loss: 0.011962890625
2023-01-23 02:51:41.890533: step: 1836/530, loss: 0.031734466552734375
2023-01-23 02:51:43.007994: step: 1840/530, loss: 0.0014396667247638106
2023-01-23 02:51:44.123243: step: 1844/530, loss: 0.10179100185632706
2023-01-23 02:51:45.212864: step: 1848/530, loss: 0.012831592932343483
2023-01-23 02:51:46.311202: step: 1852/530, loss: 0.004360771272331476
2023-01-23 02:51:47.429960: step: 1856/530, loss: 0.0007726669427938759
2023-01-23 02:51:48.536592: step: 1860/530, loss: 0.0006330490577965975
2023-01-23 02:51:49.654744: step: 1864/530, loss: 0.005430984776467085
2023-01-23 02:51:50.772385: step: 1868/530, loss: 0.0020674229599535465
2023-01-23 02:51:51.862621: step: 1872/530, loss: 0.006577706430107355
2023-01-23 02:51:52.945909: step: 1876/530, loss: 0.00012111663818359375
2023-01-23 02:51:54.038094: step: 1880/530, loss: 0.00033164024353027344
2023-01-23 02:51:55.133558: step: 1884/530, loss: 0.03621979057788849
2023-01-23 02:51:56.243079: step: 1888/530, loss: 0.023960687220096588
2023-01-23 02:51:57.337675: step: 1892/530, loss: 0.003901863005012274
2023-01-23 02:51:58.464454: step: 1896/530, loss: 0.020878203213214874
2023-01-23 02:51:59.563951: step: 1900/530, loss: 0.0003599167102947831
2023-01-23 02:52:00.650823: step: 1904/530, loss: 0.003304100129753351
2023-01-23 02:52:01.737351: step: 1908/530, loss: 6.389618647517636e-05
2023-01-23 02:52:02.855384: step: 1912/530, loss: 0.008986282162368298
2023-01-23 02:52:03.945683: step: 1916/530, loss: 0.002562618348747492
2023-01-23 02:52:05.044140: step: 1920/530, loss: 7.114410982467234e-05
2023-01-23 02:52:06.143343: step: 1924/530, loss: 0.0005035400390625
2023-01-23 02:52:07.246708: step: 1928/530, loss: 0.00018787384033203125
2023-01-23 02:52:08.360758: step: 1932/530, loss: 0.009007548913359642
2023-01-23 02:52:09.476675: step: 1936/530, loss: 0.004380607977509499
2023-01-23 02:52:10.578884: step: 1940/530, loss: -4.00543194700731e-06
2023-01-23 02:52:11.681172: step: 1944/530, loss: 0.030496977269649506
2023-01-23 02:52:12.817177: step: 1948/530, loss: 0.018125154078006744
2023-01-23 02:52:13.920886: step: 1952/530, loss: 0.08990593254566193
2023-01-23 02:52:15.015312: step: 1956/530, loss: 0.0001548767031636089
2023-01-23 02:52:16.130011: step: 1960/530, loss: 0.14841556549072266
2023-01-23 02:52:17.234173: step: 1964/530, loss: 0.014743233099579811
2023-01-23 02:52:18.359499: step: 1968/530, loss: 0.0007826805231161416
2023-01-23 02:52:19.455783: step: 1972/530, loss: 0.0006612777942791581
2023-01-23 02:52:20.566898: step: 1976/530, loss: 0.008655548095703125
2023-01-23 02:52:21.697330: step: 1980/530, loss: 0.02308177947998047
2023-01-23 02:52:22.803541: step: 1984/530, loss: 0.001957798143848777
2023-01-23 02:52:23.907998: step: 1988/530, loss: 0.030045509338378906
2023-01-23 02:52:24.998309: step: 1992/530, loss: 0.0010838508605957031
2023-01-23 02:52:26.078032: step: 1996/530, loss: 0.0029673578683286905
2023-01-23 02:52:27.193021: step: 2000/530, loss: 0.0028097154572606087
2023-01-23 02:52:28.290126: step: 2004/530, loss: 0.0008169173961505294
2023-01-23 02:52:29.368338: step: 2008/530, loss: 0.010988712310791016
2023-01-23 02:52:30.463135: step: 2012/530, loss: 0.004591751378029585
2023-01-23 02:52:31.563350: step: 2016/530, loss: 0.00115966796875
2023-01-23 02:52:32.686309: step: 2020/530, loss: 0.022836877033114433
2023-01-23 02:52:33.773791: step: 2024/530, loss: 0.014849472790956497
2023-01-23 02:52:34.895615: step: 2028/530, loss: 0.000903701817151159
2023-01-23 02:52:36.001133: step: 2032/530, loss: 0.0006887436029501259
2023-01-23 02:52:37.117913: step: 2036/530, loss: 0.015825653448700905
2023-01-23 02:52:38.212809: step: 2040/530, loss: 0.0892999917268753
2023-01-23 02:52:39.309844: step: 2044/530, loss: 0.02092280425131321
2023-01-23 02:52:40.431856: step: 2048/530, loss: 0.007922648452222347
2023-01-23 02:52:41.507253: step: 2052/530, loss: 0.008164215832948685
2023-01-23 02:52:42.597416: step: 2056/530, loss: 0.005188322626054287
2023-01-23 02:52:43.705685: step: 2060/530, loss: 0.000285911577520892
2023-01-23 02:52:44.812728: step: 2064/530, loss: 0.0011363982921466231
2023-01-23 02:52:45.912989: step: 2068/530, loss: 0.00215568533167243
2023-01-23 02:52:47.080328: step: 2072/530, loss: 0.006918382365256548
2023-01-23 02:52:48.186165: step: 2076/530, loss: 0.025876808911561966
2023-01-23 02:52:49.307281: step: 2080/530, loss: 0.008435249328613281
2023-01-23 02:52:50.402621: step: 2084/530, loss: 0.0009778976673260331
2023-01-23 02:52:51.493579: step: 2088/530, loss: 0.0005497932434082031
2023-01-23 02:52:52.584449: step: 2092/530, loss: 0.02659912221133709
2023-01-23 02:52:53.700297: step: 2096/530, loss: 0.0002971649228129536
2023-01-23 02:52:54.778994: step: 2100/530, loss: 0.00221424107439816
2023-01-23 02:52:55.873356: step: 2104/530, loss: 0.01221923902630806
2023-01-23 02:52:56.954382: step: 2108/530, loss: 0.0394987128674984
2023-01-23 02:52:58.081058: step: 2112/530, loss: 0.012666893191635609
2023-01-23 02:52:59.195041: step: 2116/530, loss: 0.011446761898696423
2023-01-23 02:53:00.288471: step: 2120/530, loss: 0.0004986763233318925
==================================================
Loss: 0.042
--------------------
Dev: {'event': {'p': 0.5771144278606966, 'r': 0.7723035952063915, 'f1': 0.6605922551252847}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
Test: {'event': {'p': 0.6271949572264746, 'r': 0.8117715617715617, 'f1': 0.7076454152908306}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
Chinese: {'event': {'p': 0.6282051282051282, 'r': 0.9074074074074074, 'f1': 0.7424242424242423}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
Korean: {'event': {'p': 0.6296296296296297, 'r': 0.5396825396825397, 'f1': 0.5811965811965812}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
Russian: {'event': {'p': 0.5, 'r': 0.6111111111111112, 'f1': 0.55}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 19}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6449771689497716, 'r': 0.7523302263648469, 'f1': 0.6945298094652735}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Chinese: {'event': {'p': 0.6692644909887969, 'r': 0.8006993006993007, 'f1': 0.7291058636243036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Chinese: {'event': {'p': 0.6764705882352942, 'r': 0.8518518518518519, 'f1': 0.7540983606557378}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6449771689497716, 'r': 0.7523302263648469, 'f1': 0.6945298094652735}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Korean: {'event': {'p': 0.6692644909887969, 'r': 0.8006993006993007, 'f1': 0.7291058636243036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Korean: {'event': {'p': 0.7391304347826086, 'r': 0.5396825396825397, 'f1': 0.6238532110091742}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5971370143149284, 'r': 0.7776298268974701, 'f1': 0.6755349913244649}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Russian: {'event': {'p': 0.6401673640167364, 'r': 0.8024475524475524, 'f1': 0.7121799844840963}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Russian: {'event': {'p': 0.5897435897435898, 'r': 0.6388888888888888, 'f1': 0.6133333333333332}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
******************************
Epoch: 20
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 02:53:39.628021: step: 4/530, loss: 0.013702202588319778
2023-01-23 02:53:40.746674: step: 8/530, loss: 0.0011085510486736894
2023-01-23 02:53:41.859775: step: 12/530, loss: 0.0001623153657419607
2023-01-23 02:53:43.006861: step: 16/530, loss: 0.001183366752229631
2023-01-23 02:53:44.094413: step: 20/530, loss: 0.000568008457776159
2023-01-23 02:53:45.165509: step: 24/530, loss: 0.0005524635780602694
2023-01-23 02:53:46.279639: step: 28/530, loss: 0.009451866149902344
2023-01-23 02:53:47.383729: step: 32/530, loss: 0.06998118758201599
2023-01-23 02:53:48.510827: step: 36/530, loss: 0.04846648871898651
2023-01-23 02:53:49.632590: step: 40/530, loss: 0.007088661193847656
2023-01-23 02:53:50.707541: step: 44/530, loss: 0.019867420196533203
2023-01-23 02:53:51.847043: step: 48/530, loss: 0.0013003349304199219
2023-01-23 02:53:52.946778: step: 52/530, loss: 0.01750764809548855
2023-01-23 02:53:54.044456: step: 56/530, loss: 0.011864567175507545
2023-01-23 02:53:55.139737: step: 60/530, loss: 0.00046215057955123484
2023-01-23 02:53:56.223717: step: 64/530, loss: 0.0007159233209677041
2023-01-23 02:53:57.320108: step: 68/530, loss: 0.007852363400161266
2023-01-23 02:53:58.410003: step: 72/530, loss: 0.00015840530977584422
2023-01-23 02:53:59.499846: step: 76/530, loss: 0.007292747963219881
2023-01-23 02:54:00.600277: step: 80/530, loss: 0.00016679764667060226
2023-01-23 02:54:01.709001: step: 84/530, loss: 0.015070153400301933
2023-01-23 02:54:02.780178: step: 88/530, loss: 0.0012836456298828125
2023-01-23 02:54:03.895535: step: 92/530, loss: 0.0015808106400072575
2023-01-23 02:54:05.007644: step: 96/530, loss: 0.0002468109014444053
2023-01-23 02:54:06.103534: step: 100/530, loss: 0.002647066256031394
2023-01-23 02:54:07.198747: step: 104/530, loss: 0.02456836774945259
2023-01-23 02:54:08.317459: step: 108/530, loss: 0.06033115088939667
2023-01-23 02:54:09.416910: step: 112/530, loss: 1.819133831304498e-05
2023-01-23 02:54:10.514167: step: 116/530, loss: 0.016558362171053886
2023-01-23 02:54:11.599744: step: 120/530, loss: 0.029140951111912727
2023-01-23 02:54:12.703751: step: 124/530, loss: 0.04360942915081978
2023-01-23 02:54:13.833923: step: 128/530, loss: 0.047702886164188385
2023-01-23 02:54:14.940077: step: 132/530, loss: 0.00558738736435771
2023-01-23 02:54:16.049702: step: 136/530, loss: 0.004562950227409601
2023-01-23 02:54:17.161177: step: 140/530, loss: 0.0001352310209767893
2023-01-23 02:54:18.283721: step: 144/530, loss: 0.0012454986572265625
2023-01-23 02:54:19.387560: step: 148/530, loss: 0.03179344907402992
2023-01-23 02:54:20.490159: step: 152/530, loss: 0.8701611161231995
2023-01-23 02:54:21.583931: step: 156/530, loss: 0.0002997875271830708
2023-01-23 02:54:22.700396: step: 160/530, loss: 0.000621795654296875
2023-01-23 02:54:23.805067: step: 164/530, loss: 0.02601451799273491
2023-01-23 02:54:24.957590: step: 168/530, loss: 0.018696118146181107
2023-01-23 02:54:26.069027: step: 172/530, loss: 0.0031511306297034025
2023-01-23 02:54:27.183052: step: 176/530, loss: 0.0005868911975994706
2023-01-23 02:54:28.293102: step: 180/530, loss: 0.00574684189632535
2023-01-23 02:54:29.395715: step: 184/530, loss: 0.03121156617999077
2023-01-23 02:54:30.497445: step: 188/530, loss: 0.0011748314136639237
2023-01-23 02:54:31.626649: step: 192/530, loss: 0.01318140048533678
2023-01-23 02:54:32.730888: step: 196/530, loss: 0.02394542656838894
2023-01-23 02:54:33.858462: step: 200/530, loss: 0.007840156555175781
2023-01-23 02:54:34.944976: step: 204/530, loss: 0.04470319673418999
2023-01-23 02:54:36.035974: step: 208/530, loss: 0.0007863998762331903
2023-01-23 02:54:37.145034: step: 212/530, loss: 0.0051017762161791325
2023-01-23 02:54:38.266526: step: 216/530, loss: 0.012769317254424095
2023-01-23 02:54:39.358761: step: 220/530, loss: 0.0030887604225426912
2023-01-23 02:54:40.439407: step: 224/530, loss: 0.009069729596376419
2023-01-23 02:54:41.565437: step: 228/530, loss: 0.014878702349960804
2023-01-23 02:54:42.654869: step: 232/530, loss: 0.007018184754997492
2023-01-23 02:54:43.725063: step: 236/530, loss: 0.015143834054470062
2023-01-23 02:54:44.867644: step: 240/530, loss: 0.07363662868738174
2023-01-23 02:54:45.977605: step: 244/530, loss: 0.06507330387830734
2023-01-23 02:54:47.093804: step: 248/530, loss: 0.0012275695335119963
2023-01-23 02:54:48.196800: step: 252/530, loss: 0.009775925427675247
2023-01-23 02:54:49.336885: step: 256/530, loss: 0.003391456790268421
2023-01-23 02:54:50.515133: step: 260/530, loss: 0.02909889444708824
2023-01-23 02:54:51.601559: step: 264/530, loss: 1.9550323031580774e-06
2023-01-23 02:54:52.718990: step: 268/530, loss: 0.012193870730698109
2023-01-23 02:54:53.867169: step: 272/530, loss: 0.0007455825689248741
2023-01-23 02:54:54.965095: step: 276/530, loss: 9.193420555675402e-05
2023-01-23 02:54:56.076171: step: 280/530, loss: 0.008006667718291283
2023-01-23 02:54:57.212247: step: 284/530, loss: 0.00024709702120162547
2023-01-23 02:54:58.303625: step: 288/530, loss: 0.0006490707746706903
2023-01-23 02:54:59.397295: step: 292/530, loss: 0.03775904327630997
2023-01-23 02:55:00.557450: step: 296/530, loss: 0.06860389560461044
2023-01-23 02:55:01.660985: step: 300/530, loss: 0.025400161743164062
2023-01-23 02:55:02.788987: step: 304/530, loss: 0.11770230531692505
2023-01-23 02:55:03.925352: step: 308/530, loss: 0.004616546910256147
2023-01-23 02:55:05.043880: step: 312/530, loss: 0.0016580582596361637
2023-01-23 02:55:06.129346: step: 316/530, loss: 0.037839125841856
2023-01-23 02:55:07.212373: step: 320/530, loss: 0.006119346711784601
2023-01-23 02:55:08.330082: step: 324/530, loss: 0.0006593704456463456
2023-01-23 02:55:09.433808: step: 328/530, loss: 0.0012426853645592928
2023-01-23 02:55:10.530079: step: 332/530, loss: 0.008990669623017311
2023-01-23 02:55:11.641529: step: 336/530, loss: 0.0012235641479492188
2023-01-23 02:55:12.741982: step: 340/530, loss: 0.05049324035644531
2023-01-23 02:55:13.870697: step: 344/530, loss: 5.760193016612902e-05
2023-01-23 02:55:14.977717: step: 348/530, loss: 0.0004986763233318925
2023-01-23 02:55:16.087407: step: 352/530, loss: 0.0029499055817723274
2023-01-23 02:55:17.193686: step: 356/530, loss: 0.004632187075912952
2023-01-23 02:55:18.289430: step: 360/530, loss: 0.019753742963075638
2023-01-23 02:55:19.399205: step: 364/530, loss: -4.8220157623291016e-05
2023-01-23 02:55:20.518743: step: 368/530, loss: 0.0250410083681345
2023-01-23 02:55:21.641645: step: 372/530, loss: 0.06525502353906631
2023-01-23 02:55:22.749476: step: 376/530, loss: 0.002073430921882391
2023-01-23 02:55:23.842094: step: 380/530, loss: 0.022220993414521217
2023-01-23 02:55:24.940942: step: 384/530, loss: 0.0005358696216717362
2023-01-23 02:55:26.033637: step: 388/530, loss: 0.00350189208984375
2023-01-23 02:55:27.115385: step: 392/530, loss: 0.003215694334357977
2023-01-23 02:55:28.217982: step: 396/530, loss: 0.0018817901145666838
2023-01-23 02:55:29.294892: step: 400/530, loss: 0.0002195358247263357
2023-01-23 02:55:30.397458: step: 404/530, loss: 0.011682892218232155
2023-01-23 02:55:31.515026: step: 408/530, loss: 0.0019309043418616056
2023-01-23 02:55:32.621257: step: 412/530, loss: 0.035097602754831314
2023-01-23 02:55:33.733276: step: 416/530, loss: 0.038558389991521835
2023-01-23 02:55:34.831238: step: 420/530, loss: 0.009222984313964844
2023-01-23 02:55:35.891212: step: 424/530, loss: 0.004097986500710249
2023-01-23 02:55:36.997562: step: 428/530, loss: 0.0017765045631676912
2023-01-23 02:55:38.121947: step: 432/530, loss: 0.015746690332889557
2023-01-23 02:55:39.229882: step: 436/530, loss: 0.0035184859298169613
2023-01-23 02:55:40.320251: step: 440/530, loss: 0.004490661434829235
2023-01-23 02:55:41.433496: step: 444/530, loss: 6.985665095271543e-05
2023-01-23 02:55:42.531524: step: 448/530, loss: 0.0006153106805868447
2023-01-23 02:55:43.626114: step: 452/530, loss: 0.0016108513809740543
2023-01-23 02:55:44.714801: step: 456/530, loss: 0.0014966963790357113
2023-01-23 02:55:45.846026: step: 460/530, loss: 0.010564805008471012
2023-01-23 02:55:46.925111: step: 464/530, loss: 0.005067062564194202
2023-01-23 02:55:48.081779: step: 468/530, loss: 0.022270966321229935
2023-01-23 02:55:49.191651: step: 472/530, loss: 0.00055017473641783
2023-01-23 02:55:50.305529: step: 476/530, loss: 0.0006603241199627519
2023-01-23 02:55:51.407186: step: 480/530, loss: 0.021640967577695847
2023-01-23 02:55:52.563093: step: 484/530, loss: 0.0022422790061682463
2023-01-23 02:55:53.680726: step: 488/530, loss: 0.0013174057239666581
2023-01-23 02:55:54.776578: step: 492/530, loss: 0.004908084869384766
2023-01-23 02:55:55.873052: step: 496/530, loss: 0.01400079671293497
2023-01-23 02:55:56.969969: step: 500/530, loss: 0.0022152424789965153
2023-01-23 02:55:58.078241: step: 504/530, loss: 0.0030012130737304688
2023-01-23 02:55:59.188365: step: 508/530, loss: 0.001694679376669228
2023-01-23 02:56:00.266321: step: 512/530, loss: 0.0004158973752055317
2023-01-23 02:56:01.367515: step: 516/530, loss: 0.06253807246685028
2023-01-23 02:56:02.459749: step: 520/530, loss: 0.01295175589621067
2023-01-23 02:56:03.572755: step: 524/530, loss: 0.05713405832648277
2023-01-23 02:56:04.683604: step: 528/530, loss: 0.21823176741600037
2023-01-23 02:56:05.784444: step: 532/530, loss: 0.0009615898597985506
2023-01-23 02:56:06.878476: step: 536/530, loss: 1.9073486328125e-06
2023-01-23 02:56:07.983101: step: 540/530, loss: 0.011937523260712624
2023-01-23 02:56:09.071857: step: 544/530, loss: 0.0006996155134402215
2023-01-23 02:56:10.172030: step: 548/530, loss: 0.03397512435913086
2023-01-23 02:56:11.321275: step: 552/530, loss: 0.02670135535299778
2023-01-23 02:56:12.426287: step: 556/530, loss: 0.047303106635808945
2023-01-23 02:56:13.493096: step: 560/530, loss: 1.730919029796496e-05
2023-01-23 02:56:14.639056: step: 564/530, loss: 0.0040111541748046875
2023-01-23 02:56:15.762051: step: 568/530, loss: 0.0013871192932128906
2023-01-23 02:56:16.877826: step: 572/530, loss: 0.004490089137107134
2023-01-23 02:56:17.982216: step: 576/530, loss: 0.004046845715492964
2023-01-23 02:56:19.091762: step: 580/530, loss: 0.02622690238058567
2023-01-23 02:56:20.194215: step: 584/530, loss: 0.00133848178666085
2023-01-23 02:56:21.292978: step: 588/530, loss: 0.0017461776733398438
2023-01-23 02:56:22.457594: step: 592/530, loss: 0.019324207678437233
2023-01-23 02:56:23.566665: step: 596/530, loss: 0.003932380583137274
2023-01-23 02:56:24.654073: step: 600/530, loss: 0.0020681379828602076
2023-01-23 02:56:25.751905: step: 604/530, loss: 0.007012557704001665
2023-01-23 02:56:26.839777: step: 608/530, loss: 0.008876514621078968
2023-01-23 02:56:27.969579: step: 612/530, loss: 0.0004070281866006553
2023-01-23 02:56:29.049015: step: 616/530, loss: 0.03316166624426842
2023-01-23 02:56:30.150232: step: 620/530, loss: 0.007374954409897327
2023-01-23 02:56:31.249291: step: 624/530, loss: 0.005403781309723854
2023-01-23 02:56:32.378687: step: 628/530, loss: 0.013536644168198109
2023-01-23 02:56:33.466197: step: 632/530, loss: 9.51766996877268e-05
2023-01-23 02:56:34.574181: step: 636/530, loss: 6.29425048828125e-05
2023-01-23 02:56:35.664682: step: 640/530, loss: 0.004754448309540749
2023-01-23 02:56:36.756528: step: 644/530, loss: 0.0035243036691099405
2023-01-23 02:56:37.872150: step: 648/530, loss: 0.003586387727409601
2023-01-23 02:56:39.005878: step: 652/530, loss: 0.01120004616677761
2023-01-23 02:56:40.085974: step: 656/530, loss: 0.01255579013377428
2023-01-23 02:56:41.201747: step: 660/530, loss: 0.03167724609375
2023-01-23 02:56:42.305829: step: 664/530, loss: 0.004136466886848211
2023-01-23 02:56:43.399760: step: 668/530, loss: 0.0165910255163908
2023-01-23 02:56:44.479322: step: 672/530, loss: 0.00047321320744231343
2023-01-23 02:56:45.598248: step: 676/530, loss: 0.08018293976783752
2023-01-23 02:56:46.704202: step: 680/530, loss: 0.0019296646350994706
2023-01-23 02:56:47.838826: step: 684/530, loss: 3.7765505112474784e-05
2023-01-23 02:56:48.956864: step: 688/530, loss: -4.673004241340095e-06
2023-01-23 02:56:50.046048: step: 692/530, loss: 0.007663154974579811
2023-01-23 02:56:51.151926: step: 696/530, loss: 0.024094389751553535
2023-01-23 02:56:52.331146: step: 700/530, loss: 0.09568710625171661
2023-01-23 02:56:53.462296: step: 704/530, loss: 0.0001312255917582661
2023-01-23 02:56:54.573498: step: 708/530, loss: 0.0025327682960778475
2023-01-23 02:56:55.696895: step: 712/530, loss: 0.011421775445342064
2023-01-23 02:56:56.797713: step: 716/530, loss: 0.0010828018421307206
2023-01-23 02:56:57.924742: step: 720/530, loss: 0.007840251550078392
2023-01-23 02:56:59.022963: step: 724/530, loss: 0.00012283325486350805
2023-01-23 02:57:00.142580: step: 728/530, loss: 0.12658576667308807
2023-01-23 02:57:01.206092: step: 732/530, loss: 0.0002840518718585372
2023-01-23 02:57:02.324784: step: 736/530, loss: 0.001406002091243863
2023-01-23 02:57:03.437797: step: 740/530, loss: 0.0004659653059206903
2023-01-23 02:57:04.550444: step: 744/530, loss: 1.8501283193472773e-05
2023-01-23 02:57:05.676637: step: 748/530, loss: 0.03036480024456978
2023-01-23 02:57:06.793804: step: 752/530, loss: 0.146479994058609
2023-01-23 02:57:07.891812: step: 756/530, loss: 3.280639793956652e-05
2023-01-23 02:57:09.007102: step: 760/530, loss: 0.0037858011201024055
2023-01-23 02:57:10.110903: step: 764/530, loss: 0.0036580085288733244
2023-01-23 02:57:11.250198: step: 768/530, loss: 0.0005910873296670616
2023-01-23 02:57:12.360518: step: 772/530, loss: 0.0027942657470703125
2023-01-23 02:57:13.426883: step: 776/530, loss: 0.004878806881606579
2023-01-23 02:57:14.558378: step: 780/530, loss: 0.030193326994776726
2023-01-23 02:57:15.651933: step: 784/530, loss: 0.003887701081112027
2023-01-23 02:57:16.784895: step: 788/530, loss: 0.07249746471643448
2023-01-23 02:57:17.888821: step: 792/530, loss: 0.00020618439884856343
2023-01-23 02:57:18.996038: step: 796/530, loss: 0.004320526495575905
2023-01-23 02:57:20.099617: step: 800/530, loss: -5.817413239128655e-06
2023-01-23 02:57:21.193931: step: 804/530, loss: 0.0012645244132727385
2023-01-23 02:57:22.296828: step: 808/530, loss: 0.10172891616821289
2023-01-23 02:57:23.414035: step: 812/530, loss: 0.027861882001161575
2023-01-23 02:57:24.537510: step: 816/530, loss: 9.536744300930877e-07
2023-01-23 02:57:25.631511: step: 820/530, loss: 0.015621853061020374
2023-01-23 02:57:26.707031: step: 824/530, loss: 0.00679359445348382
2023-01-23 02:57:27.800041: step: 828/530, loss: 0.006345176603645086
2023-01-23 02:57:28.934028: step: 832/530, loss: 0.0034237862564623356
2023-01-23 02:57:30.030040: step: 836/530, loss: 0.013395404443144798
2023-01-23 02:57:31.122721: step: 840/530, loss: 0.0001733779936330393
2023-01-23 02:57:32.229791: step: 844/530, loss: 0.00018520356388762593
2023-01-23 02:57:33.330258: step: 848/530, loss: 0.02094755321741104
2023-01-23 02:57:34.451862: step: 852/530, loss: 0.07129726558923721
2023-01-23 02:57:35.535395: step: 856/530, loss: 0.003086281009018421
2023-01-23 02:57:36.633362: step: 860/530, loss: 0.00028972624568268657
2023-01-23 02:57:37.742191: step: 864/530, loss: 0.020303726196289062
2023-01-23 02:57:38.865326: step: 868/530, loss: 0.028679655864834785
2023-01-23 02:57:39.981427: step: 872/530, loss: 0.05021009221673012
2023-01-23 02:57:41.078798: step: 876/530, loss: 0.015396595932543278
2023-01-23 02:57:42.190104: step: 880/530, loss: 0.005320835392922163
2023-01-23 02:57:43.299212: step: 884/530, loss: 0.006844186689704657
2023-01-23 02:57:44.460019: step: 888/530, loss: 0.0005314826848916709
2023-01-23 02:57:45.556782: step: 892/530, loss: 0.015700342133641243
2023-01-23 02:57:46.657375: step: 896/530, loss: 2.3365020751953125e-05
2023-01-23 02:57:47.773965: step: 900/530, loss: 0.0110359201207757
2023-01-23 02:57:48.882632: step: 904/530, loss: 0.008791351690888405
2023-01-23 02:57:50.000827: step: 908/530, loss: 0.0004482269287109375
2023-01-23 02:57:51.098388: step: 912/530, loss: 4.4441225327318534e-05
2023-01-23 02:57:52.216495: step: 916/530, loss: 0.021976852789521217
2023-01-23 02:57:53.332436: step: 920/530, loss: 0.008385514840483665
2023-01-23 02:57:54.473721: step: 924/530, loss: 0.007043648045510054
2023-01-23 02:57:55.565713: step: 928/530, loss: 0.004284095950424671
2023-01-23 02:57:56.683272: step: 932/530, loss: 0.0027051924262195826
2023-01-23 02:57:57.789236: step: 936/530, loss: 0.012682247906923294
2023-01-23 02:57:58.892281: step: 940/530, loss: 0.05198821797966957
2023-01-23 02:57:59.996660: step: 944/530, loss: 0.08935842663049698
2023-01-23 02:58:01.087663: step: 948/530, loss: 1.7833710444392636e-05
2023-01-23 02:58:02.191339: step: 952/530, loss: 0.006075191777199507
2023-01-23 02:58:03.300045: step: 956/530, loss: 0.14893826842308044
2023-01-23 02:58:04.428560: step: 960/530, loss: 0.0017613411182537675
2023-01-23 02:58:05.534516: step: 964/530, loss: 0.009627008810639381
2023-01-23 02:58:06.651433: step: 968/530, loss: 0.020511675626039505
2023-01-23 02:58:07.785204: step: 972/530, loss: 0.020804787054657936
2023-01-23 02:58:08.907052: step: 976/530, loss: 0.0073333741165697575
2023-01-23 02:58:10.029231: step: 980/530, loss: 0.0011839866638183594
2023-01-23 02:58:11.127317: step: 984/530, loss: 9.016990952659398e-05
2023-01-23 02:58:12.220817: step: 988/530, loss: 0.005725824739784002
2023-01-23 02:58:13.336118: step: 992/530, loss: 0.0002807617129292339
2023-01-23 02:58:14.466306: step: 996/530, loss: 0.0009922027820721269
2023-01-23 02:58:15.571632: step: 1000/530, loss: 0.0020875930786132812
2023-01-23 02:58:16.667109: step: 1004/530, loss: 0.0006810188642702997
2023-01-23 02:58:17.762452: step: 1008/530, loss: 6.794929504394531e-05
2023-01-23 02:58:18.862401: step: 1012/530, loss: 0.007236385717988014
2023-01-23 02:58:19.977082: step: 1016/530, loss: 0.003933525178581476
2023-01-23 02:58:21.079270: step: 1020/530, loss: 0.0019006729125976562
2023-01-23 02:58:22.163895: step: 1024/530, loss: 0.00023651123046875
2023-01-23 02:58:23.297497: step: 1028/530, loss: 0.04137764126062393
2023-01-23 02:58:24.395500: step: 1032/530, loss: -2.8610227218450746e-06
2023-01-23 02:58:25.495895: step: 1036/530, loss: 0.06641516089439392
2023-01-23 02:58:26.587734: step: 1040/530, loss: 0.0001000881238724105
2023-01-23 02:58:27.676372: step: 1044/530, loss: 0.011546516790986061
2023-01-23 02:58:28.772935: step: 1048/530, loss: 0.00047621727571822703
2023-01-23 02:58:29.885347: step: 1052/530, loss: 0.025702668353915215
2023-01-23 02:58:30.955901: step: 1056/530, loss: 0.00927886925637722
2023-01-23 02:58:32.054693: step: 1060/530, loss: 0.0007946968544274569
2023-01-23 02:58:33.165086: step: 1064/530, loss: 0.003356552217155695
2023-01-23 02:58:34.297560: step: 1068/530, loss: 0.10069771111011505
2023-01-23 02:58:35.389182: step: 1072/530, loss: 0.023482704535126686
2023-01-23 02:58:36.494141: step: 1076/530, loss: -2.346038854739163e-05
2023-01-23 02:58:37.598463: step: 1080/530, loss: 0.003303623292595148
2023-01-23 02:58:38.669158: step: 1084/530, loss: 0.0033012391068041325
2023-01-23 02:58:39.784936: step: 1088/530, loss: 0.0002801895316224545
2023-01-23 02:58:40.901463: step: 1092/530, loss: 0.0003284454287495464
2023-01-23 02:58:42.020451: step: 1096/530, loss: 0.002607154892757535
2023-01-23 02:58:43.118303: step: 1100/530, loss: 0.003906536381691694
2023-01-23 02:58:44.200237: step: 1104/530, loss: 0.0004486083926167339
2023-01-23 02:58:45.293425: step: 1108/530, loss: 0.0004220008850097656
2023-01-23 02:58:46.402327: step: 1112/530, loss: 0.002198886824771762
2023-01-23 02:58:47.515666: step: 1116/530, loss: 0.036374930292367935
2023-01-23 02:58:48.621197: step: 1120/530, loss: 0.06577225029468536
2023-01-23 02:58:49.739996: step: 1124/530, loss: 0.03767261654138565
2023-01-23 02:58:50.874151: step: 1128/530, loss: 3.633499363786541e-05
2023-01-23 02:58:51.951811: step: 1132/530, loss: 0.007889151573181152
2023-01-23 02:58:53.032471: step: 1136/530, loss: 0.0010631084442138672
2023-01-23 02:58:54.143164: step: 1140/530, loss: 0.022317886352539062
2023-01-23 02:58:55.256513: step: 1144/530, loss: 0.01177682913839817
2023-01-23 02:58:56.343482: step: 1148/530, loss: 0.000872707343660295
2023-01-23 02:58:57.428419: step: 1152/530, loss: 0.007864522747695446
2023-01-23 02:58:58.545805: step: 1156/530, loss: 0.004351616371423006
2023-01-23 02:58:59.677519: step: 1160/530, loss: 0.007796669378876686
2023-01-23 02:59:00.772493: step: 1164/530, loss: 0.002498817630112171
2023-01-23 02:59:01.919106: step: 1168/530, loss: 0.00023498536029364914
2023-01-23 02:59:03.046289: step: 1172/530, loss: 0.006945705506950617
2023-01-23 02:59:04.123580: step: 1176/530, loss: 0.014984702691435814
2023-01-23 02:59:05.198967: step: 1180/530, loss: 0.007767581846565008
2023-01-23 02:59:06.292510: step: 1184/530, loss: 0.10443844646215439
2023-01-23 02:59:07.395968: step: 1188/530, loss: 0.008370781317353249
2023-01-23 02:59:08.502899: step: 1192/530, loss: 0.00087823870126158
2023-01-23 02:59:09.592808: step: 1196/530, loss: 0.013243675231933594
2023-01-23 02:59:10.672856: step: 1200/530, loss: 0.010766602121293545
2023-01-23 02:59:11.770482: step: 1204/530, loss: 0.0030880451668053865
2023-01-23 02:59:12.916521: step: 1208/530, loss: 0.0040108682587742805
2023-01-23 02:59:14.010802: step: 1212/530, loss: 0.0008795738685876131
2023-01-23 02:59:15.110413: step: 1216/530, loss: 0.00023183823213912547
2023-01-23 02:59:16.203794: step: 1220/530, loss: 0.01147537212818861
2023-01-23 02:59:17.336998: step: 1224/530, loss: 0.0035400390625
2023-01-23 02:59:18.467326: step: 1228/530, loss: 0.004630470648407936
2023-01-23 02:59:19.579100: step: 1232/530, loss: 0.0013826369540765882
2023-01-23 02:59:20.675975: step: 1236/530, loss: 0.0034570693969726562
2023-01-23 02:59:21.796752: step: 1240/530, loss: 0.029636478051543236
2023-01-23 02:59:22.886229: step: 1244/530, loss: 0.003082466311752796
2023-01-23 02:59:24.020723: step: 1248/530, loss: 5.6076052715070546e-05
2023-01-23 02:59:25.116337: step: 1252/530, loss: 0.004104518797248602
2023-01-23 02:59:26.217434: step: 1256/530, loss: 0.005885315127670765
2023-01-23 02:59:27.336529: step: 1260/530, loss: 0.00041828156099654734
2023-01-23 02:59:28.423815: step: 1264/530, loss: 0.006185627076774836
2023-01-23 02:59:29.525397: step: 1268/530, loss: 0.0018439292907714844
2023-01-23 02:59:30.616193: step: 1272/530, loss: 0.043486595153808594
2023-01-23 02:59:31.705383: step: 1276/530, loss: 0.0005762100336141884
2023-01-23 02:59:32.813499: step: 1280/530, loss: 0.04392519220709801
2023-01-23 02:59:33.947839: step: 1284/530, loss: 0.020858382806181908
2023-01-23 02:59:35.071585: step: 1288/530, loss: 0.0015802383422851562
2023-01-23 02:59:36.180519: step: 1292/530, loss: 0.001987361814826727
2023-01-23 02:59:37.301036: step: 1296/530, loss: 2.520737886428833
2023-01-23 02:59:38.407154: step: 1300/530, loss: 0.0012183666694909334
2023-01-23 02:59:39.510900: step: 1304/530, loss: 0.00046410562936216593
2023-01-23 02:59:40.598025: step: 1308/530, loss: 0.004085922613739967
2023-01-23 02:59:41.699025: step: 1312/530, loss: 0.0003492355172056705
2023-01-23 02:59:42.793043: step: 1316/530, loss: 0.1049533411860466
2023-01-23 02:59:43.896322: step: 1320/530, loss: 0.002922534942626953
2023-01-23 02:59:45.025839: step: 1324/530, loss: 0.011168098077178001
2023-01-23 02:59:46.174113: step: 1328/530, loss: 0.03147849813103676
2023-01-23 02:59:47.283125: step: 1332/530, loss: 0.016718769446015358
2023-01-23 02:59:48.410107: step: 1336/530, loss: 0.003756809514015913
2023-01-23 02:59:49.521841: step: 1340/530, loss: 0.00523719796910882
2023-01-23 02:59:50.630564: step: 1344/530, loss: 2.593994213384576e-05
2023-01-23 02:59:51.732974: step: 1348/530, loss: 0.013735294342041016
2023-01-23 02:59:52.853144: step: 1352/530, loss: 0.022109031677246094
2023-01-23 02:59:53.977991: step: 1356/530, loss: 3.452301098150201e-05
2023-01-23 02:59:55.089006: step: 1360/530, loss: 0.016129398718476295
2023-01-23 02:59:56.185804: step: 1364/530, loss: 9.5367431640625e-06
2023-01-23 02:59:57.273832: step: 1368/530, loss: 0.0016930580604821444
2023-01-23 02:59:58.382402: step: 1372/530, loss: 0.0326780304312706
2023-01-23 02:59:59.514700: step: 1376/530, loss: 0.068964384496212
2023-01-23 03:00:00.629434: step: 1380/530, loss: 0.005650997161865234
2023-01-23 03:00:01.759801: step: 1384/530, loss: 0.0001960754452738911
2023-01-23 03:00:02.864069: step: 1388/530, loss: 0.01739673502743244
2023-01-23 03:00:03.931573: step: 1392/530, loss: 0.00039539337740279734
2023-01-23 03:00:05.015324: step: 1396/530, loss: 0.0188217181712389
2023-01-23 03:00:06.119979: step: 1400/530, loss: 0.0019685744773596525
2023-01-23 03:00:07.227026: step: 1404/530, loss: 0.06984911113977432
2023-01-23 03:00:08.329129: step: 1408/530, loss: 0.0022966384422034025
2023-01-23 03:00:09.447236: step: 1412/530, loss: 0.0014090538024902344
2023-01-23 03:00:10.539424: step: 1416/530, loss: 0.036104965955019
2023-01-23 03:00:11.659446: step: 1420/530, loss: 0.008893776684999466
2023-01-23 03:00:12.778260: step: 1424/530, loss: 0.0008678436279296875
2023-01-23 03:00:13.898273: step: 1428/530, loss: 0.09487000107765198
2023-01-23 03:00:15.007147: step: 1432/530, loss: 0.005013275425881147
2023-01-23 03:00:16.113052: step: 1436/530, loss: 0.00045433046761900187
2023-01-23 03:00:17.223539: step: 1440/530, loss: 0.0005047321319580078
2023-01-23 03:00:18.351731: step: 1444/530, loss: 0.002739048097282648
2023-01-23 03:00:19.444498: step: 1448/530, loss: 0.008296584710478783
2023-01-23 03:00:20.577222: step: 1452/530, loss: 0.000815963838249445
2023-01-23 03:00:21.700771: step: 1456/530, loss: 0.017080115154385567
2023-01-23 03:00:22.817990: step: 1460/530, loss: 0.6368786692619324
2023-01-23 03:00:23.934405: step: 1464/530, loss: 5.892513751983643
2023-01-23 03:00:25.044065: step: 1468/530, loss: 0.034474946558475494
2023-01-23 03:00:26.157790: step: 1472/530, loss: 0.001537752104923129
2023-01-23 03:00:27.266244: step: 1476/530, loss: 0.027782535180449486
2023-01-23 03:00:28.375298: step: 1480/530, loss: 0.03053741529583931
2023-01-23 03:00:29.480419: step: 1484/530, loss: 0.011218547821044922
2023-01-23 03:00:30.600726: step: 1488/530, loss: 0.00045604706974700093
2023-01-23 03:00:31.701016: step: 1492/530, loss: 0.07214794307947159
2023-01-23 03:00:32.789762: step: 1496/530, loss: 0.05027732998132706
2023-01-23 03:00:33.893634: step: 1500/530, loss: 0.0002788543642964214
2023-01-23 03:00:34.985518: step: 1504/530, loss: 0.0003163337823934853
2023-01-23 03:00:36.096872: step: 1508/530, loss: 0.007839154452085495
2023-01-23 03:00:37.199006: step: 1512/530, loss: 0.05560602620244026
2023-01-23 03:00:38.288783: step: 1516/530, loss: 0.0016209125751629472
2023-01-23 03:00:39.406170: step: 1520/530, loss: 0.006072712130844593
2023-01-23 03:00:40.504098: step: 1524/530, loss: 0.07927601784467697
2023-01-23 03:00:41.591149: step: 1528/530, loss: 0.05301971361041069
2023-01-23 03:00:42.664894: step: 1532/530, loss: 0.014274120330810547
2023-01-23 03:00:43.812459: step: 1536/530, loss: 0.00013399124145507812
2023-01-23 03:00:44.936924: step: 1540/530, loss: 0.2528859078884125
2023-01-23 03:00:46.049038: step: 1544/530, loss: 0.015109063126146793
2023-01-23 03:00:47.149136: step: 1548/530, loss: 0.006765175145119429
2023-01-23 03:00:48.255351: step: 1552/530, loss: 0.005243110936135054
2023-01-23 03:00:49.373508: step: 1556/530, loss: 2.86102294921875e-05
2023-01-23 03:00:50.501035: step: 1560/530, loss: 0.011653185822069645
2023-01-23 03:00:51.590314: step: 1564/530, loss: 0.03421726077795029
2023-01-23 03:00:52.712781: step: 1568/530, loss: 0.03194742277264595
2023-01-23 03:00:53.786561: step: 1572/530, loss: 0.002777958055958152
2023-01-23 03:00:54.867824: step: 1576/530, loss: 9.393692380399443e-06
2023-01-23 03:00:55.938079: step: 1580/530, loss: 0.0002262592315673828
2023-01-23 03:00:57.038633: step: 1584/530, loss: 0.0006759644020348787
2023-01-23 03:00:58.141132: step: 1588/530, loss: 0.006273651495575905
2023-01-23 03:00:59.228702: step: 1592/530, loss: 0.001735258148983121
2023-01-23 03:01:00.361940: step: 1596/530, loss: 0.04846210405230522
2023-01-23 03:01:01.463871: step: 1600/530, loss: 0.0015045165782794356
2023-01-23 03:01:02.551851: step: 1604/530, loss: 0.004803276155143976
2023-01-23 03:01:03.684561: step: 1608/530, loss: 5.836486889165826e-05
2023-01-23 03:01:04.823291: step: 1612/530, loss: 0.021181296557188034
2023-01-23 03:01:05.923185: step: 1616/530, loss: 0.0016685485607013106
2023-01-23 03:01:07.024006: step: 1620/530, loss: 0.010678291320800781
2023-01-23 03:01:08.120202: step: 1624/530, loss: 0.0006398201221600175
2023-01-23 03:01:09.237870: step: 1628/530, loss: 0.02193737030029297
2023-01-23 03:01:10.312444: step: 1632/530, loss: 0.017219066619873047
2023-01-23 03:01:11.428185: step: 1636/530, loss: 0.005360889248549938
2023-01-23 03:01:12.570225: step: 1640/530, loss: 0.0017593384254723787
2023-01-23 03:01:13.676101: step: 1644/530, loss: 0.001151275704614818
2023-01-23 03:01:14.779085: step: 1648/530, loss: 0.037880513817071915
2023-01-23 03:01:15.892439: step: 1652/530, loss: 0.03352966159582138
2023-01-23 03:01:17.026660: step: 1656/530, loss: 0.00021305083646439016
2023-01-23 03:01:18.125724: step: 1660/530, loss: 0.004274225328117609
2023-01-23 03:01:19.247839: step: 1664/530, loss: 0.5841953158378601
2023-01-23 03:01:20.339629: step: 1668/530, loss: 0.004036832135170698
2023-01-23 03:01:21.438704: step: 1672/530, loss: 0.02430119551718235
2023-01-23 03:01:22.516132: step: 1676/530, loss: 0.010055947117507458
2023-01-23 03:01:23.613363: step: 1680/530, loss: 0.0040635112673044205
2023-01-23 03:01:24.719948: step: 1684/530, loss: 0.01917877234518528
2023-01-23 03:01:25.822245: step: 1688/530, loss: 0.0027620315086096525
2023-01-23 03:01:26.928283: step: 1692/530, loss: 0.0018906593322753906
2023-01-23 03:01:28.044746: step: 1696/530, loss: 0.045891571789979935
2023-01-23 03:01:29.138175: step: 1700/530, loss: 0.029369354248046875
2023-01-23 03:01:30.241414: step: 1704/530, loss: 2.0694733393611386e-05
2023-01-23 03:01:31.365647: step: 1708/530, loss: 0.004292869474738836
2023-01-23 03:01:32.473365: step: 1712/530, loss: 0.0661342591047287
2023-01-23 03:01:33.592810: step: 1716/530, loss: 0.0003841400321107358
2023-01-23 03:01:34.711364: step: 1720/530, loss: 0.014523698017001152
2023-01-23 03:01:35.831810: step: 1724/530, loss: 0.0015240192878991365
2023-01-23 03:01:36.966497: step: 1728/530, loss: 8.869171324477065e-06
2023-01-23 03:01:38.060685: step: 1732/530, loss: 0.0001852035493357107
2023-01-23 03:01:39.161237: step: 1736/530, loss: 0.0012662888038903475
2023-01-23 03:01:40.269887: step: 1740/530, loss: 0.0020177841652184725
2023-01-23 03:01:41.403661: step: 1744/530, loss: 0.07132712006568909
2023-01-23 03:01:42.495084: step: 1748/530, loss: 0.0010319710709154606
2023-01-23 03:01:43.586481: step: 1752/530, loss: 3.070831371587701e-05
2023-01-23 03:01:44.704629: step: 1756/530, loss: 0.0236361026763916
2023-01-23 03:01:45.798035: step: 1760/530, loss: 0.01700725592672825
2023-01-23 03:01:46.909653: step: 1764/530, loss: 0.016237638890743256
2023-01-23 03:01:48.001272: step: 1768/530, loss: 0.0021445690654218197
2023-01-23 03:01:49.113957: step: 1772/530, loss: 0.04841356351971626
2023-01-23 03:01:50.228131: step: 1776/530, loss: 8.487701961712446e-06
2023-01-23 03:01:51.310487: step: 1780/530, loss: 0.0085296630859375
2023-01-23 03:01:52.415143: step: 1784/530, loss: 0.0010553359752520919
2023-01-23 03:01:53.534657: step: 1788/530, loss: 0.055750466883182526
2023-01-23 03:01:54.661111: step: 1792/530, loss: 0.0027425766456872225
2023-01-23 03:01:55.770529: step: 1796/530, loss: 0.04624443128705025
2023-01-23 03:01:56.857176: step: 1800/530, loss: 0.005002832505851984
2023-01-23 03:01:57.954076: step: 1804/530, loss: 0.0008607864729128778
2023-01-23 03:01:59.053281: step: 1808/530, loss: 0.021225357428193092
2023-01-23 03:02:00.147981: step: 1812/530, loss: 0.00011014939082087949
2023-01-23 03:02:01.273067: step: 1816/530, loss: 8.77380352903856e-06
2023-01-23 03:02:02.415231: step: 1820/530, loss: 0.01788168027997017
2023-01-23 03:02:03.514936: step: 1824/530, loss: 0.05901694670319557
2023-01-23 03:02:04.644056: step: 1828/530, loss: 0.0024751664604991674
2023-01-23 03:02:05.769801: step: 1832/530, loss: 0.049889758229255676
2023-01-23 03:02:06.875007: step: 1836/530, loss: 0.0010969162685796618
2023-01-23 03:02:07.962326: step: 1840/530, loss: 0.0012890816433355212
2023-01-23 03:02:09.064350: step: 1844/530, loss: 8.087158494163305e-05
2023-01-23 03:02:10.161530: step: 1848/530, loss: 0.0037783621810376644
2023-01-23 03:02:11.283496: step: 1852/530, loss: 5.197524842515122e-06
2023-01-23 03:02:12.407251: step: 1856/530, loss: 0.020339393988251686
2023-01-23 03:02:13.504413: step: 1860/530, loss: 0.00945138931274414
2023-01-23 03:02:14.642211: step: 1864/530, loss: 0.02587261237204075
2023-01-23 03:02:15.751848: step: 1868/530, loss: 4.625320343620842e-06
2023-01-23 03:02:16.842766: step: 1872/530, loss: 0.0034822942689061165
2023-01-23 03:02:17.959303: step: 1876/530, loss: 0.0008013725164346397
2023-01-23 03:02:19.065353: step: 1880/530, loss: 0.016428470611572266
2023-01-23 03:02:20.117979: step: 1884/530, loss: 0.0006886482588015497
2023-01-23 03:02:21.258194: step: 1888/530, loss: 0.008295392617583275
2023-01-23 03:02:22.367535: step: 1892/530, loss: 0.028010845184326172
2023-01-23 03:02:23.467146: step: 1896/530, loss: 0.05603837966918945
2023-01-23 03:02:24.552851: step: 1900/530, loss: 0.035078953951597214
2023-01-23 03:02:25.656662: step: 1904/530, loss: 0.0004676342068705708
2023-01-23 03:02:26.786385: step: 1908/530, loss: 0.004656520672142506
2023-01-23 03:02:27.892021: step: 1912/530, loss: 5.617141869151965e-05
2023-01-23 03:02:29.025501: step: 1916/530, loss: 0.06429300457239151
2023-01-23 03:02:30.093649: step: 1920/530, loss: 0.006229258142411709
2023-01-23 03:02:31.199170: step: 1924/530, loss: 0.015364741906523705
2023-01-23 03:02:32.334573: step: 1928/530, loss: 0.09784059971570969
2023-01-23 03:02:33.418332: step: 1932/530, loss: 0.003754520323127508
2023-01-23 03:02:34.506728: step: 1936/530, loss: 0.0009252548334188759
2023-01-23 03:02:35.593536: step: 1940/530, loss: 0.021436309441924095
2023-01-23 03:02:36.731659: step: 1944/530, loss: 0.010712528601288795
2023-01-23 03:02:37.843571: step: 1948/530, loss: 0.0016798734432086349
2023-01-23 03:02:38.924145: step: 1952/530, loss: 0.000510787998791784
2023-01-23 03:02:40.005489: step: 1956/530, loss: 0.0033443449065089226
2023-01-23 03:02:41.118679: step: 1960/530, loss: 0.0024662972427904606
2023-01-23 03:02:42.221642: step: 1964/530, loss: 0.00020227434288244694
2023-01-23 03:02:43.320024: step: 1968/530, loss: 0.03358955681324005
2023-01-23 03:02:44.413620: step: 1972/530, loss: 0.06409893184900284
2023-01-23 03:02:45.524409: step: 1976/530, loss: 0.0022865296341478825
2023-01-23 03:02:46.606473: step: 1980/530, loss: 0.0816129520535469
2023-01-23 03:02:47.715068: step: 1984/530, loss: 0.024106215685606003
2023-01-23 03:02:48.834394: step: 1988/530, loss: 0.00022811889357399195
2023-01-23 03:02:49.935570: step: 1992/530, loss: 0.0008514404762536287
2023-01-23 03:02:51.037380: step: 1996/530, loss: 0.05869140848517418
2023-01-23 03:02:52.139685: step: 2000/530, loss: 0.006288766860961914
2023-01-23 03:02:53.268923: step: 2004/530, loss: 0.004698467440903187
2023-01-23 03:02:54.403149: step: 2008/530, loss: 6.0749054682673886e-05
2023-01-23 03:02:55.518067: step: 2012/530, loss: 0.37041524052619934
2023-01-23 03:02:56.617975: step: 2016/530, loss: 0.029657555744051933
2023-01-23 03:02:57.751445: step: 2020/530, loss: 3.604888843256049e-05
2023-01-23 03:02:58.903363: step: 2024/530, loss: 0.04117755964398384
2023-01-23 03:03:00.029034: step: 2028/530, loss: 0.016595078632235527
2023-01-23 03:03:01.134690: step: 2032/530, loss: 0.0004937172052450478
2023-01-23 03:03:02.209758: step: 2036/530, loss: 0.00011639595322776586
2023-01-23 03:03:03.321126: step: 2040/530, loss: 0.00011329651169944555
2023-01-23 03:03:04.426860: step: 2044/530, loss: 0.026999760419130325
2023-01-23 03:03:05.561670: step: 2048/530, loss: 0.0006911277887411416
2023-01-23 03:03:06.669590: step: 2052/530, loss: 0.00013442040653899312
2023-01-23 03:03:07.786105: step: 2056/530, loss: 0.0051156519912183285
2023-01-23 03:03:08.887925: step: 2060/530, loss: 0.10337970405817032
2023-01-23 03:03:09.981056: step: 2064/530, loss: 0.0008745193481445312
2023-01-23 03:03:11.081289: step: 2068/530, loss: 0.007480621337890625
2023-01-23 03:03:12.209335: step: 2072/530, loss: 0.0010400294559076428
2023-01-23 03:03:13.294814: step: 2076/530, loss: 0.000244140625
2023-01-23 03:03:14.393605: step: 2080/530, loss: 0.00175733573269099
2023-01-23 03:03:15.530370: step: 2084/530, loss: 0.00104265206027776
2023-01-23 03:03:16.671823: step: 2088/530, loss: 0.014296531677246094
2023-01-23 03:03:17.765048: step: 2092/530, loss: 0.10305872559547424
2023-01-23 03:03:18.876930: step: 2096/530, loss: 0.011514091864228249
2023-01-23 03:03:19.968986: step: 2100/530, loss: 0.0003814697265625
2023-01-23 03:03:21.073122: step: 2104/530, loss: 0.042704202234745026
2023-01-23 03:03:22.174279: step: 2108/530, loss: 0.0033733367454260588
2023-01-23 03:03:23.279569: step: 2112/530, loss: 0.0008620262378826737
2023-01-23 03:03:24.376801: step: 2116/530, loss: 0.0004953384632244706
2023-01-23 03:03:25.487808: step: 2120/530, loss: 0.09318371117115021
==================================================
Loss: 0.036
--------------------
Dev: {'event': {'p': 0.59958071278826, 'r': 0.7616511318242344, 'f1': 0.6709677419354839}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 20}
Test: {'event': {'p': 0.6527255639097744, 'r': 0.8094405594405595, 'f1': 0.722684703433923}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 20}
Chinese: {'event': {'p': 0.6351351351351351, 'r': 0.8703703703703703, 'f1': 0.734375}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 20}
Korean: {'event': {'p': 0.7045454545454546, 'r': 0.49206349206349204, 'f1': 0.5794392523364486}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 20}
Russian: {'event': {'p': 0.4864864864864865, 'r': 0.5, 'f1': 0.4931506849315069}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 20}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6449771689497716, 'r': 0.7523302263648469, 'f1': 0.6945298094652735}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Chinese: {'event': {'p': 0.6692644909887969, 'r': 0.8006993006993007, 'f1': 0.7291058636243036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Chinese: {'event': {'p': 0.6764705882352942, 'r': 0.8518518518518519, 'f1': 0.7540983606557378}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6449771689497716, 'r': 0.7523302263648469, 'f1': 0.6945298094652735}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Korean: {'event': {'p': 0.6692644909887969, 'r': 0.8006993006993007, 'f1': 0.7291058636243036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Korean: {'event': {'p': 0.7391304347826086, 'r': 0.5396825396825397, 'f1': 0.6238532110091742}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5971370143149284, 'r': 0.7776298268974701, 'f1': 0.6755349913244649}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Russian: {'event': {'p': 0.6401673640167364, 'r': 0.8024475524475524, 'f1': 0.7121799844840963}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Russian: {'event': {'p': 0.5897435897435898, 'r': 0.6388888888888888, 'f1': 0.6133333333333332}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
******************************
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 03:04:04.814127: step: 4/530, loss: 0.005220795050263405
2023-01-23 03:04:05.914986: step: 8/530, loss: 0.0014435768825933337
2023-01-23 03:04:06.986396: step: 12/530, loss: 0.010496092028915882
2023-01-23 03:04:08.111537: step: 16/530, loss: 0.022896479815244675
2023-01-23 03:04:09.221445: step: 20/530, loss: 0.0010209083557128906
2023-01-23 03:04:10.346520: step: 24/530, loss: 0.0005056381342001259
2023-01-23 03:04:11.475724: step: 28/530, loss: 0.04812159761786461
2023-01-23 03:04:12.580295: step: 32/530, loss: 0.0010648727184161544
2023-01-23 03:04:13.671276: step: 36/530, loss: 0.008623314090073109
2023-01-23 03:04:14.790418: step: 40/530, loss: 0.002969122026115656
2023-01-23 03:04:15.913291: step: 44/530, loss: 0.009552001953125
2023-01-23 03:04:17.011322: step: 48/530, loss: 0.01859302446246147
2023-01-23 03:04:18.144268: step: 52/530, loss: 0.009499549865722656
2023-01-23 03:04:19.279030: step: 56/530, loss: 0.031667519360780716
2023-01-23 03:04:20.378167: step: 60/530, loss: 2.975463939947076e-05
2023-01-23 03:04:21.492939: step: 64/530, loss: 0.021511554718017578
2023-01-23 03:04:22.609020: step: 68/530, loss: 0.28213050961494446
2023-01-23 03:04:23.733429: step: 72/530, loss: 0.0024738311767578125
2023-01-23 03:04:24.864419: step: 76/530, loss: 0.05939216911792755
2023-01-23 03:04:25.956713: step: 80/530, loss: 0.04792824015021324
2023-01-23 03:04:27.067487: step: 84/530, loss: 0.0018741608364507556
2023-01-23 03:04:28.160326: step: 88/530, loss: 0.002627086825668812
2023-01-23 03:04:29.260724: step: 92/530, loss: 0.032552435994148254
2023-01-23 03:04:30.352532: step: 96/530, loss: 0.00012044906907249242
2023-01-23 03:04:31.489042: step: 100/530, loss: 0.013947868719696999
2023-01-23 03:04:32.617497: step: 104/530, loss: 0.0003714561462402344
2023-01-23 03:04:33.715011: step: 108/530, loss: 0.026905346661806107
2023-01-23 03:04:34.858004: step: 112/530, loss: 0.0006355285877361894
2023-01-23 03:04:35.950788: step: 116/530, loss: 0.00066547398455441
2023-01-23 03:04:37.038452: step: 120/530, loss: 0.00015764236741233617
2023-01-23 03:04:38.125438: step: 124/530, loss: 0.000476646440802142
2023-01-23 03:04:39.227229: step: 128/530, loss: 0.0022202550899237394
2023-01-23 03:04:40.326906: step: 132/530, loss: 6.599425978492945e-05
2023-01-23 03:04:41.442828: step: 136/530, loss: 0.09879417717456818
2023-01-23 03:04:42.547261: step: 140/530, loss: 0.00018053053645417094
2023-01-23 03:04:43.646736: step: 144/530, loss: 0.006721877958625555
2023-01-23 03:04:44.760710: step: 148/530, loss: 0.022664451971650124
2023-01-23 03:04:45.867555: step: 152/530, loss: 0.0009610176202841103
2023-01-23 03:04:46.965098: step: 156/530, loss: 0.005118560511618853
2023-01-23 03:04:48.110530: step: 160/530, loss: 0.0034122467041015625
2023-01-23 03:04:49.225320: step: 164/530, loss: 0.00017228125943802297
2023-01-23 03:04:50.309527: step: 168/530, loss: 0.0029002188239246607
2023-01-23 03:04:51.394564: step: 172/530, loss: 0.018877696245908737
2023-01-23 03:04:52.514536: step: 176/530, loss: 0.006978893186897039
2023-01-23 03:04:53.601308: step: 180/530, loss: 2.7751922971219756e-05
2023-01-23 03:04:54.694033: step: 184/530, loss: 0.01998930051922798
2023-01-23 03:04:55.799943: step: 188/530, loss: 0.007425894029438496
2023-01-23 03:04:56.911903: step: 192/530, loss: 0.0015660285716876388
2023-01-23 03:04:58.002392: step: 196/530, loss: 0.25065168738365173
2023-01-23 03:04:59.093389: step: 200/530, loss: 0.008869933895766735
2023-01-23 03:05:00.193587: step: 204/530, loss: 0.11607913672924042
2023-01-23 03:05:01.327305: step: 208/530, loss: 0.01905803754925728
2023-01-23 03:05:02.427141: step: 212/530, loss: 0.0019712448120117188
2023-01-23 03:05:03.531415: step: 216/530, loss: 0.0059667592868208885
2023-01-23 03:05:04.644222: step: 220/530, loss: 0.040360454469919205
2023-01-23 03:05:05.740950: step: 224/530, loss: 0.6400712728500366
2023-01-23 03:05:06.865454: step: 228/530, loss: 0.0016618729569017887
2023-01-23 03:05:07.975396: step: 232/530, loss: 0.03634977340698242
2023-01-23 03:05:09.076773: step: 236/530, loss: 0.01165542658418417
2023-01-23 03:05:10.141303: step: 240/530, loss: 0.00030431748018600047
2023-01-23 03:05:11.297047: step: 244/530, loss: 0.000702381192240864
2023-01-23 03:05:12.401858: step: 248/530, loss: 0.01600813865661621
2023-01-23 03:05:13.498476: step: 252/530, loss: 0.012385440059006214
2023-01-23 03:05:14.624631: step: 256/530, loss: 0.0031621933449059725
2023-01-23 03:05:15.731685: step: 260/530, loss: 0.00155887589789927
2023-01-23 03:05:16.847012: step: 264/530, loss: 0.015993738546967506
2023-01-23 03:05:17.945491: step: 268/530, loss: 0.008565139956772327
2023-01-23 03:05:19.043727: step: 272/530, loss: 0.0017847062554210424
2023-01-23 03:05:20.159849: step: 276/530, loss: 0.0001866340753622353
2023-01-23 03:05:21.280152: step: 280/530, loss: 0.003197956131771207
2023-01-23 03:05:22.367521: step: 284/530, loss: 0.01449365634471178
2023-01-23 03:05:23.508050: step: 288/530, loss: 0.00026226043701171875
2023-01-23 03:05:24.601280: step: 292/530, loss: 0.013360501267015934
2023-01-23 03:05:25.729304: step: 296/530, loss: 0.0008565902826376259
2023-01-23 03:05:26.851346: step: 300/530, loss: 0.003094291780143976
2023-01-23 03:05:27.950385: step: 304/530, loss: 0.00167503347620368
2023-01-23 03:05:29.060872: step: 308/530, loss: 0.09138841927051544
2023-01-23 03:05:30.157612: step: 312/530, loss: 0.04195060953497887
2023-01-23 03:05:31.266876: step: 316/530, loss: 0.0033664703369140625
2023-01-23 03:05:32.382022: step: 320/530, loss: 8.678436643094756e-06
2023-01-23 03:05:33.507050: step: 324/530, loss: 0.03383312374353409
2023-01-23 03:05:34.628527: step: 328/530, loss: 0.0005852699396200478
2023-01-23 03:05:35.731701: step: 332/530, loss: 0.0005355834728106856
2023-01-23 03:05:36.815979: step: 336/530, loss: 0.004864883609116077
2023-01-23 03:05:37.899485: step: 340/530, loss: 9.450913057662547e-05
2023-01-23 03:05:38.994393: step: 344/530, loss: 0.005634212400764227
2023-01-23 03:05:40.108815: step: 348/530, loss: 0.0009313583141192794
2023-01-23 03:05:41.211030: step: 352/530, loss: 0.002052498050034046
2023-01-23 03:05:42.308790: step: 356/530, loss: 0.0025899887550622225
2023-01-23 03:05:43.401911: step: 360/530, loss: 0.06435515731573105
2023-01-23 03:05:44.502534: step: 364/530, loss: 0.0010286332108080387
2023-01-23 03:05:45.621166: step: 368/530, loss: 1.76429750808893e-06
2023-01-23 03:05:46.703578: step: 372/530, loss: 0.012348556891083717
2023-01-23 03:05:47.824993: step: 376/530, loss: 2.6035308110294864e-05
2023-01-23 03:05:48.919764: step: 380/530, loss: 0.04826488718390465
2023-01-23 03:05:50.025538: step: 384/530, loss: 0.014689350500702858
2023-01-23 03:05:51.120065: step: 388/530, loss: 5.187988426769152e-05
2023-01-23 03:05:52.225516: step: 392/530, loss: 0.009760474786162376
2023-01-23 03:05:53.315032: step: 396/530, loss: 0.004920005798339844
2023-01-23 03:05:54.420889: step: 400/530, loss: 0.0144538888707757
2023-01-23 03:05:55.523237: step: 404/530, loss: 7.62939453125e-06
2023-01-23 03:05:56.644515: step: 408/530, loss: 2.6607514882925898e-05
2023-01-23 03:05:57.763506: step: 412/530, loss: 0.013176250271499157
2023-01-23 03:05:58.863312: step: 416/530, loss: 4.0531158447265625e-06
2023-01-23 03:05:59.944471: step: 420/530, loss: 0.0016982138622552156
2023-01-23 03:06:01.045912: step: 424/530, loss: 0.006275653839111328
2023-01-23 03:06:02.138056: step: 428/530, loss: 0.00026187897310592234
2023-01-23 03:06:03.258539: step: 432/530, loss: 0.011815833859145641
2023-01-23 03:06:04.371718: step: 436/530, loss: 0.0057960511185228825
2023-01-23 03:06:05.466770: step: 440/530, loss: 0.00037450791569426656
2023-01-23 03:06:06.591951: step: 444/530, loss: 0.00012493133544921875
2023-01-23 03:06:07.753710: step: 448/530, loss: 0.00014171600923873484
2023-01-23 03:06:08.875377: step: 452/530, loss: 0.005940246395766735
2023-01-23 03:06:10.016005: step: 456/530, loss: -5.722045557376987e-07
2023-01-23 03:06:11.129605: step: 460/530, loss: 0.053108785301446915
2023-01-23 03:06:12.233052: step: 464/530, loss: 0.005061912816017866
2023-01-23 03:06:13.347293: step: 468/530, loss: 0.1517396867275238
2023-01-23 03:06:14.479768: step: 472/530, loss: 0.13978537917137146
2023-01-23 03:06:15.576156: step: 476/530, loss: 0.00673522986471653
2023-01-23 03:06:16.694443: step: 480/530, loss: 0.014184570871293545
2023-01-23 03:06:17.788322: step: 484/530, loss: 0.00040225981501862407
2023-01-23 03:06:18.908120: step: 488/530, loss: 0.0009510517120361328
2023-01-23 03:06:19.998727: step: 492/530, loss: 0.005855655297636986
2023-01-23 03:06:21.106484: step: 496/530, loss: 0.04139576107263565
2023-01-23 03:06:22.216923: step: 500/530, loss: 0.00010526627011131495
2023-01-23 03:06:23.339858: step: 504/530, loss: 0.21094922721385956
2023-01-23 03:06:24.408526: step: 508/530, loss: 0.0017601967556402087
2023-01-23 03:06:25.506420: step: 512/530, loss: 0.0002006530703511089
2023-01-23 03:06:26.617569: step: 516/530, loss: 0.008532715030014515
2023-01-23 03:06:27.717906: step: 520/530, loss: 0.0022155761253088713
2023-01-23 03:06:28.817049: step: 524/530, loss: 0.003313255263492465
2023-01-23 03:06:29.907987: step: 528/530, loss: 0.04838543012738228
2023-01-23 03:06:31.021161: step: 532/530, loss: 0.0440642386674881
2023-01-23 03:06:32.128661: step: 536/530, loss: 0.015325736254453659
2023-01-23 03:06:33.226361: step: 540/530, loss: 0.016004370525479317
2023-01-23 03:06:34.331054: step: 544/530, loss: 0.0019083976512774825
2023-01-23 03:06:35.425637: step: 548/530, loss: 1.4209747860149946e-05
2023-01-23 03:06:36.563837: step: 552/530, loss: 0.011877727694809437
2023-01-23 03:06:37.678390: step: 556/530, loss: 5.113704681396484
2023-01-23 03:06:38.754662: step: 560/530, loss: 0.060760498046875
2023-01-23 03:06:39.855500: step: 564/530, loss: 0.0001332283136434853
2023-01-23 03:06:40.987689: step: 568/530, loss: 0.01604766771197319
2023-01-23 03:06:42.051468: step: 572/530, loss: 3.709793236339465e-05
2023-01-23 03:06:43.138823: step: 576/530, loss: 0.0377134345471859
2023-01-23 03:06:44.248362: step: 580/530, loss: 0.0007618427625857294
2023-01-23 03:06:45.356404: step: 584/530, loss: 0.0034811736550182104
2023-01-23 03:06:46.455971: step: 588/530, loss: 0.0023624419700354338
2023-01-23 03:06:47.546228: step: 592/530, loss: 0.0011046171421185136
2023-01-23 03:06:48.632533: step: 596/530, loss: 0.011535263620316982
2023-01-23 03:06:49.761361: step: 600/530, loss: 0.02174224890768528
2023-01-23 03:06:50.890848: step: 604/530, loss: 0.00499992398545146
2023-01-23 03:06:51.995191: step: 608/530, loss: 0.004269504453986883
2023-01-23 03:06:53.111298: step: 612/530, loss: 0.027096843346953392
2023-01-23 03:06:54.220179: step: 616/530, loss: 0.12083053588867188
2023-01-23 03:06:55.304925: step: 620/530, loss: 0.0006939053419046104
2023-01-23 03:06:56.394852: step: 624/530, loss: 0.003638315247371793
2023-01-23 03:06:57.500075: step: 628/530, loss: 0.00696067837998271
2023-01-23 03:06:58.597250: step: 632/530, loss: 9.12666364456527e-05
2023-01-23 03:06:59.725741: step: 636/530, loss: 0.016834449023008347
2023-01-23 03:07:00.882840: step: 640/530, loss: 0.012977124191820621
2023-01-23 03:07:01.979310: step: 644/530, loss: 5.092620995128527e-05
2023-01-23 03:07:03.085589: step: 648/530, loss: 0.0681210532784462
2023-01-23 03:07:04.194373: step: 652/530, loss: 7.41958647267893e-05
2023-01-23 03:07:05.264477: step: 656/530, loss: 0.003253936767578125
2023-01-23 03:07:06.385504: step: 660/530, loss: 0.9449615478515625
2023-01-23 03:07:07.494566: step: 664/530, loss: 0.0018711090087890625
2023-01-23 03:07:08.629617: step: 668/530, loss: 0.0023601532448083162
2023-01-23 03:07:09.725979: step: 672/530, loss: 0.0005748749244958162
2023-01-23 03:07:10.840124: step: 676/530, loss: 4.1580202378099784e-05
2023-01-23 03:07:11.970581: step: 680/530, loss: 0.001959228655323386
2023-01-23 03:07:13.063456: step: 684/530, loss: 0.0007136345375329256
2023-01-23 03:07:14.167467: step: 688/530, loss: 0.012615394778549671
2023-01-23 03:07:15.308944: step: 692/530, loss: 0.06530018150806427
2023-01-23 03:07:16.428390: step: 696/530, loss: 0.03249035030603409
2023-01-23 03:07:17.521349: step: 700/530, loss: 9.641647193348035e-05
2023-01-23 03:07:18.706768: step: 704/530, loss: 0.01230621337890625
2023-01-23 03:07:19.813547: step: 708/530, loss: 0.004474544897675514
2023-01-23 03:07:20.929498: step: 712/530, loss: 0.003972435370087624
2023-01-23 03:07:22.035753: step: 716/530, loss: 1.392364538332913e-05
2023-01-23 03:07:23.138078: step: 720/530, loss: 0.020096970722079277
2023-01-23 03:07:24.218015: step: 724/530, loss: 0.002680015517398715
2023-01-23 03:07:25.328202: step: 728/530, loss: 4.816055661649443e-05
2023-01-23 03:07:26.423320: step: 732/530, loss: 0.00805683247745037
2023-01-23 03:07:27.551094: step: 736/530, loss: 0.04042300954461098
2023-01-23 03:07:28.656382: step: 740/530, loss: 0.0035667421761900187
2023-01-23 03:07:29.768720: step: 744/530, loss: 0.026675034314393997
2023-01-23 03:07:30.872459: step: 748/530, loss: 0.00019130707369185984
2023-01-23 03:07:31.958630: step: 752/530, loss: 0.1128196269273758
2023-01-23 03:07:33.076654: step: 756/530, loss: 0.002897071884945035
2023-01-23 03:07:34.188637: step: 760/530, loss: 0.021552467718720436
2023-01-23 03:07:35.279170: step: 764/530, loss: 0.0003197670157533139
2023-01-23 03:07:36.353341: step: 768/530, loss: 0.003800678299739957
2023-01-23 03:07:37.457460: step: 772/530, loss: 8.430481102550402e-05
2023-01-23 03:07:38.566775: step: 776/530, loss: 0.047208309173583984
2023-01-23 03:07:39.684591: step: 780/530, loss: 0.4871490001678467
2023-01-23 03:07:40.802082: step: 784/530, loss: 0.026512717828154564
2023-01-23 03:07:41.900291: step: 788/530, loss: 0.0709049254655838
2023-01-23 03:07:43.018410: step: 792/530, loss: 0.025051211938261986
2023-01-23 03:07:44.137707: step: 796/530, loss: 0.009515953250229359
2023-01-23 03:07:45.255093: step: 800/530, loss: 0.006145763676613569
2023-01-23 03:07:46.407800: step: 804/530, loss: 0.022965049371123314
2023-01-23 03:07:47.508844: step: 808/530, loss: 0.01587848737835884
2023-01-23 03:07:48.634284: step: 812/530, loss: 0.0017555237282067537
2023-01-23 03:07:49.753087: step: 816/530, loss: 0.010108566842973232
2023-01-23 03:07:50.851276: step: 820/530, loss: 0.00017671583918854594
2023-01-23 03:07:51.963482: step: 824/530, loss: 0.1538395881652832
2023-01-23 03:07:53.041071: step: 828/530, loss: 0.02229447476565838
2023-01-23 03:07:54.171612: step: 832/530, loss: 0.004184722900390625
2023-01-23 03:07:55.296595: step: 836/530, loss: 0.04305100440979004
2023-01-23 03:07:56.404950: step: 840/530, loss: 0.0006993293645791709
2023-01-23 03:07:57.537590: step: 844/530, loss: 0.007149124518036842
2023-01-23 03:07:58.648150: step: 848/530, loss: 2.021789623540826e-05
2023-01-23 03:07:59.761136: step: 852/530, loss: 2.3937225705594756e-05
2023-01-23 03:08:00.897076: step: 856/530, loss: 0.0026364328805357218
2023-01-23 03:08:01.993449: step: 860/530, loss: 0.019340135157108307
2023-01-23 03:08:03.115664: step: 864/530, loss: 0.03844489902257919
2023-01-23 03:08:04.213472: step: 868/530, loss: 0.000363254570402205
2023-01-23 03:08:05.373258: step: 872/530, loss: 0.0005132198566570878
2023-01-23 03:08:06.496727: step: 876/530, loss: 0.000294590019620955
2023-01-23 03:08:07.612988: step: 880/530, loss: 4.873275611316785e-05
2023-01-23 03:08:08.716644: step: 884/530, loss: 0.004424953367561102
2023-01-23 03:08:09.823842: step: 888/530, loss: 0.00740509107708931
2023-01-23 03:08:10.929663: step: 892/530, loss: 0.04560208320617676
2023-01-23 03:08:12.035402: step: 896/530, loss: 0.5973265171051025
2023-01-23 03:08:13.134430: step: 900/530, loss: 0.0002993583620991558
2023-01-23 03:08:14.259930: step: 904/530, loss: 0.0004534721374511719
2023-01-23 03:08:15.371130: step: 908/530, loss: 0.0058956146240234375
2023-01-23 03:08:16.458139: step: 912/530, loss: 0.003862094832584262
2023-01-23 03:08:17.573620: step: 916/530, loss: 1.364870548248291
2023-01-23 03:08:18.671270: step: 920/530, loss: 8.811950829112902e-05
2023-01-23 03:08:19.801987: step: 924/530, loss: 0.0002382278471486643
2023-01-23 03:08:20.893174: step: 928/530, loss: 0.04688673093914986
2023-01-23 03:08:21.980557: step: 932/530, loss: 0.030300522223114967
2023-01-23 03:08:23.083255: step: 936/530, loss: 0.00010261536226607859
2023-01-23 03:08:24.179265: step: 940/530, loss: 0.03785572201013565
2023-01-23 03:08:25.292275: step: 944/530, loss: 0.012190056033432484
2023-01-23 03:08:26.398359: step: 948/530, loss: 0.059978339821100235
2023-01-23 03:08:27.496253: step: 952/530, loss: 0.03271036222577095
2023-01-23 03:08:28.602670: step: 956/530, loss: 0.005850410554558039
2023-01-23 03:08:29.698598: step: 960/530, loss: 0.0003733634948730469
2023-01-23 03:08:30.811294: step: 964/530, loss: 0.006627464666962624
2023-01-23 03:08:31.925615: step: 968/530, loss: 0.0023478984367102385
2023-01-23 03:08:33.036924: step: 972/530, loss: 0.0005533219082280993
2023-01-23 03:08:34.141680: step: 976/530, loss: 0.00254478445276618
2023-01-23 03:08:35.208561: step: 980/530, loss: 5.559921555686742e-05
2023-01-23 03:08:36.289182: step: 984/530, loss: 0.004350090399384499
2023-01-23 03:08:37.382251: step: 988/530, loss: 0.01745014265179634
2023-01-23 03:08:38.486912: step: 992/530, loss: 0.00801706314086914
2023-01-23 03:08:39.595493: step: 996/530, loss: 0.0001888275146484375
2023-01-23 03:08:40.724599: step: 1000/530, loss: 0.011542893014848232
2023-01-23 03:08:41.815013: step: 1004/530, loss: 9.15527380129788e-06
2023-01-23 03:08:42.922778: step: 1008/530, loss: 0.4879912734031677
2023-01-23 03:08:44.052578: step: 1012/530, loss: 0.00011711120896507055
2023-01-23 03:08:45.160239: step: 1016/530, loss: 0.0652977004647255
2023-01-23 03:08:46.244730: step: 1020/530, loss: 0.00016574861365370452
2023-01-23 03:08:47.358392: step: 1024/530, loss: 0.0002658844168763608
2023-01-23 03:08:48.480175: step: 1028/530, loss: 0.002760982606559992
2023-01-23 03:08:49.578009: step: 1032/530, loss: 0.004348087590187788
2023-01-23 03:08:50.673403: step: 1036/530, loss: 0.00039949416532181203
2023-01-23 03:08:51.793704: step: 1040/530, loss: 0.024202918633818626
2023-01-23 03:08:52.910323: step: 1044/530, loss: 0.00033216478186659515
2023-01-23 03:08:54.021347: step: 1048/530, loss: 1.4066695257497486e-05
2023-01-23 03:08:55.116545: step: 1052/530, loss: 0.17680606245994568
2023-01-23 03:08:56.203155: step: 1056/530, loss: 0.0007547378772869706
2023-01-23 03:08:57.307735: step: 1060/530, loss: 0.02746753767132759
2023-01-23 03:08:58.403055: step: 1064/530, loss: 0.0013050079578533769
2023-01-23 03:08:59.490228: step: 1068/530, loss: 0.00905618630349636
2023-01-23 03:09:00.596607: step: 1072/530, loss: 0.003548908280208707
2023-01-23 03:09:01.712513: step: 1076/530, loss: 0.00011405945406295359
2023-01-23 03:09:02.797497: step: 1080/530, loss: 0.00024857520475052297
2023-01-23 03:09:03.887340: step: 1084/530, loss: 2.784729076665826e-05
2023-01-23 03:09:04.999217: step: 1088/530, loss: 7.25746140233241e-05
2023-01-23 03:09:06.085862: step: 1092/530, loss: 0.002909755567088723
2023-01-23 03:09:07.223085: step: 1096/530, loss: 0.00884027499705553
2023-01-23 03:09:08.328033: step: 1100/530, loss: 0.008242321200668812
2023-01-23 03:09:09.439228: step: 1104/530, loss: 0.0010475158924236894
2023-01-23 03:09:10.541731: step: 1108/530, loss: 0.0036596297286450863
2023-01-23 03:09:11.638047: step: 1112/530, loss: 0.02861328050494194
2023-01-23 03:09:12.720262: step: 1116/530, loss: 0.046180155128240585
2023-01-23 03:09:13.821111: step: 1120/530, loss: 0.015436363406479359
2023-01-23 03:09:14.922502: step: 1124/530, loss: 6.017685154802166e-05
2023-01-23 03:09:15.994761: step: 1128/530, loss: 0.0001220703125
2023-01-23 03:09:17.096571: step: 1132/530, loss: 0.0005414009792730212
2023-01-23 03:09:18.185843: step: 1136/530, loss: 0.0029452324379235506
2023-01-23 03:09:19.280519: step: 1140/530, loss: 0.00018806457228492945
2023-01-23 03:09:20.384373: step: 1144/530, loss: 7.572174217784777e-05
2023-01-23 03:09:21.489806: step: 1148/530, loss: 0.010421943850815296
2023-01-23 03:09:22.608673: step: 1152/530, loss: 2.689361645025201e-05
2023-01-23 03:09:23.718714: step: 1156/530, loss: 0.011257171630859375
2023-01-23 03:09:24.820832: step: 1160/530, loss: 0.0001506805419921875
2023-01-23 03:09:25.911555: step: 1164/530, loss: 0.00923233013600111
2023-01-23 03:09:26.992919: step: 1168/530, loss: 0.01772146299481392
2023-01-23 03:09:28.065191: step: 1172/530, loss: 0.00010910034325206652
2023-01-23 03:09:29.157278: step: 1176/530, loss: 5.626678466796875e-05
2023-01-23 03:09:30.250118: step: 1180/530, loss: 0.0054565430618822575
2023-01-23 03:09:31.359977: step: 1184/530, loss: 4.57763671875e-05
2023-01-23 03:09:32.454262: step: 1188/530, loss: 9.121894981944934e-05
2023-01-23 03:09:33.540164: step: 1192/530, loss: -1.5258785879268544e-06
2023-01-23 03:09:34.655129: step: 1196/530, loss: 0.0007101059309206903
2023-01-23 03:09:35.741244: step: 1200/530, loss: 0.004572677426040173
2023-01-23 03:09:36.875418: step: 1204/530, loss: 0.0070664407685399055
2023-01-23 03:09:37.977807: step: 1208/530, loss: 0.013383341021835804
2023-01-23 03:09:39.067300: step: 1212/530, loss: 0.0008581161382608116
2023-01-23 03:09:40.148165: step: 1216/530, loss: 0.00032415392342954874
2023-01-23 03:09:41.260517: step: 1220/530, loss: 0.08208665996789932
2023-01-23 03:09:42.370160: step: 1224/530, loss: 0.0001976490020751953
2023-01-23 03:09:43.472192: step: 1228/530, loss: 0.00046663283137604594
2023-01-23 03:09:44.588434: step: 1232/530, loss: 0.01401443500071764
2023-01-23 03:09:45.690741: step: 1236/530, loss: 5.1212315156590194e-05
2023-01-23 03:09:46.806538: step: 1240/530, loss: 0.051000308245420456
2023-01-23 03:09:47.924199: step: 1244/530, loss: 0.018848992884159088
2023-01-23 03:09:49.001845: step: 1248/530, loss: 4.839897155761719e-05
2023-01-23 03:09:50.103921: step: 1252/530, loss: 0.5384510159492493
2023-01-23 03:09:51.190838: step: 1256/530, loss: 1.9073486612342094e-07
2023-01-23 03:09:52.293436: step: 1260/530, loss: 0.00114526750985533
2023-01-23 03:09:53.402318: step: 1264/530, loss: 0.028896141797304153
2023-01-23 03:09:54.492287: step: 1268/530, loss: 0.046811964362859726
2023-01-23 03:09:55.605342: step: 1272/530, loss: 0.06894226372241974
2023-01-23 03:09:56.700397: step: 1276/530, loss: 0.006539058405905962
2023-01-23 03:09:57.785682: step: 1280/530, loss: 0.0001682281435932964
2023-01-23 03:09:58.888541: step: 1284/530, loss: 0.012586211785674095
2023-01-23 03:09:59.977543: step: 1288/530, loss: 0.09386825561523438
2023-01-23 03:10:01.092844: step: 1292/530, loss: 0.0007105827680788934
2023-01-23 03:10:02.211702: step: 1296/530, loss: 0.028109168633818626
2023-01-23 03:10:03.350111: step: 1300/530, loss: 0.002482795622199774
2023-01-23 03:10:04.454430: step: 1304/530, loss: 0.00031070708064362407
2023-01-23 03:10:05.547536: step: 1308/530, loss: 0.01983346976339817
2023-01-23 03:10:06.645083: step: 1312/530, loss: 0.0002649307425599545
2023-01-23 03:10:07.748634: step: 1316/530, loss: 0.0022909166291356087
2023-01-23 03:10:08.862092: step: 1320/530, loss: 0.0003948688681703061
2023-01-23 03:10:09.953827: step: 1324/530, loss: 0.0005290985573083162
2023-01-23 03:10:11.049887: step: 1328/530, loss: 0.0003675461048260331
2023-01-23 03:10:12.184076: step: 1332/530, loss: 0.037842560559511185
2023-01-23 03:10:13.264769: step: 1336/530, loss: 0.023119354620575905
2023-01-23 03:10:14.389005: step: 1340/530, loss: 0.00843734759837389
2023-01-23 03:10:15.492837: step: 1344/530, loss: 0.0018355369102209806
2023-01-23 03:10:16.605564: step: 1348/530, loss: 0.0003505706845317036
2023-01-23 03:10:17.687846: step: 1352/530, loss: 0.0495484359562397
2023-01-23 03:10:18.775388: step: 1356/530, loss: 0.018940448760986328
2023-01-23 03:10:19.892506: step: 1360/530, loss: 0.0015443802112713456
2023-01-23 03:10:20.976473: step: 1364/530, loss: 0.000851058925036341
2023-01-23 03:10:22.082926: step: 1368/530, loss: 0.0019054414005950093
2023-01-23 03:10:23.168129: step: 1372/530, loss: 0.09177283942699432
2023-01-23 03:10:24.284583: step: 1376/530, loss: 0.047292523086071014
2023-01-23 03:10:25.383217: step: 1380/530, loss: 0.0025266646407544613
2023-01-23 03:10:26.483977: step: 1384/530, loss: 0.0012206077808514237
2023-01-23 03:10:27.590057: step: 1388/530, loss: 0.021045496687293053
2023-01-23 03:10:28.675756: step: 1392/530, loss: 0.0014844894176349044
2023-01-23 03:10:29.776982: step: 1396/530, loss: 0.027077436447143555
2023-01-23 03:10:30.916723: step: 1400/530, loss: 0.016130639240145683
2023-01-23 03:10:32.024377: step: 1404/530, loss: 0.0004931449657306075
2023-01-23 03:10:33.185445: step: 1408/530, loss: 3.166198803228326e-05
2023-01-23 03:10:34.285926: step: 1412/530, loss: 0.014764023013412952
2023-01-23 03:10:35.380568: step: 1416/530, loss: 0.00995016098022461
2023-01-23 03:10:36.473171: step: 1420/530, loss: 0.0008300780900754035
2023-01-23 03:10:37.559726: step: 1424/530, loss: 0.005065536592155695
2023-01-23 03:10:38.691439: step: 1428/530, loss: 0.00044145583524368703
2023-01-23 03:10:39.788256: step: 1432/530, loss: 0.009423637762665749
2023-01-23 03:10:40.914367: step: 1436/530, loss: 0.0014270782703533769
2023-01-23 03:10:42.025302: step: 1440/530, loss: 0.0047393799759447575
2023-01-23 03:10:43.173265: step: 1444/530, loss: 0.006506109610199928
2023-01-23 03:10:44.264155: step: 1448/530, loss: 0.00292377476580441
2023-01-23 03:10:45.374046: step: 1452/530, loss: 0.10083892941474915
2023-01-23 03:10:46.477040: step: 1456/530, loss: 0.001064205076545477
2023-01-23 03:10:47.575343: step: 1460/530, loss: 0.0017686843639239669
2023-01-23 03:10:48.686654: step: 1464/530, loss: 0.0010738372802734375
2023-01-23 03:10:49.767201: step: 1468/530, loss: 0.012791706249117851
2023-01-23 03:10:50.852909: step: 1472/530, loss: 0.00105543143581599
2023-01-23 03:10:51.943488: step: 1476/530, loss: 0.0002208113728556782
2023-01-23 03:10:53.057027: step: 1480/530, loss: 0.012577056884765625
2023-01-23 03:10:54.192634: step: 1484/530, loss: 1.1444091796875e-05
2023-01-23 03:10:55.296114: step: 1488/530, loss: 0.00029892922611907125
2023-01-23 03:10:56.413881: step: 1492/530, loss: 3.471374657237902e-05
2023-01-23 03:10:57.528534: step: 1496/530, loss: 0.0011487007141113281
2023-01-23 03:10:58.644620: step: 1500/530, loss: 0.009208393283188343
2023-01-23 03:10:59.742921: step: 1504/530, loss: 0.002470684237778187
2023-01-23 03:11:00.879957: step: 1508/530, loss: 0.0017355919117107987
2023-01-23 03:11:01.985883: step: 1512/530, loss: 0.004153442569077015
2023-01-23 03:11:03.079636: step: 1516/530, loss: 0.01511373557150364
2023-01-23 03:11:04.183173: step: 1520/530, loss: 0.025942228734493256
2023-01-23 03:11:05.268399: step: 1524/530, loss: 0.016079138964414597
2023-01-23 03:11:06.389132: step: 1528/530, loss: 0.01818518526852131
2023-01-23 03:11:07.502735: step: 1532/530, loss: 0.04637184366583824
2023-01-23 03:11:08.578938: step: 1536/530, loss: 0.000736236572265625
2023-01-23 03:11:09.679204: step: 1540/530, loss: 0.005008840933442116
2023-01-23 03:11:10.762063: step: 1544/530, loss: 0.035138990730047226
2023-01-23 03:11:11.881818: step: 1548/530, loss: 0.0015506267081946135
2023-01-23 03:11:12.995191: step: 1552/530, loss: 0.031310271471738815
2023-01-23 03:11:14.102697: step: 1556/530, loss: 0.15729141235351562
2023-01-23 03:11:15.244662: step: 1560/530, loss: 0.001617860863916576
2023-01-23 03:11:16.369826: step: 1564/530, loss: 0.031832315027713776
2023-01-23 03:11:17.458732: step: 1568/530, loss: 0.005492973141372204
2023-01-23 03:11:18.549693: step: 1572/530, loss: 0.0015227317344397306
2023-01-23 03:11:19.668127: step: 1576/530, loss: 0.002660751575604081
2023-01-23 03:11:20.753530: step: 1580/530, loss: 2.613067590573337e-05
2023-01-23 03:11:21.866557: step: 1584/530, loss: 0.000690078770276159
2023-01-23 03:11:22.967538: step: 1588/530, loss: 0.002153110457584262
2023-01-23 03:11:24.081751: step: 1592/530, loss: 0.00014038085646461695
2023-01-23 03:11:25.180203: step: 1596/530, loss: 0.003947925288230181
2023-01-23 03:11:26.292963: step: 1600/530, loss: 0.02417907677590847
2023-01-23 03:11:27.392457: step: 1604/530, loss: 0.008671760559082031
2023-01-23 03:11:28.492071: step: 1608/530, loss: 0.006177139468491077
2023-01-23 03:11:29.592792: step: 1612/530, loss: 0.0005815505865029991
2023-01-23 03:11:30.681941: step: 1616/530, loss: 0.016411496326327324
2023-01-23 03:11:31.816301: step: 1620/530, loss: 0.0018385887378826737
2023-01-23 03:11:32.925985: step: 1624/530, loss: 0.0010951042640954256
2023-01-23 03:11:34.007186: step: 1628/530, loss: -1.373290979245212e-05
2023-01-23 03:11:35.111489: step: 1632/530, loss: 0.0010644913418218493
2023-01-23 03:11:36.212206: step: 1636/530, loss: 0.0031946422532200813
2023-01-23 03:11:37.312056: step: 1640/530, loss: 0.03508109971880913
2023-01-23 03:11:38.422053: step: 1644/530, loss: 0.0035972597543150187
2023-01-23 03:11:39.540239: step: 1648/530, loss: 0.060037851333618164
2023-01-23 03:11:40.631848: step: 1652/530, loss: 0.00016860962205100805
2023-01-23 03:11:41.737092: step: 1656/530, loss: 2.5272369384765625e-05
2023-01-23 03:11:42.837902: step: 1660/530, loss: 0.023647308349609375
2023-01-23 03:11:43.950971: step: 1664/530, loss: 0.018071748316287994
2023-01-23 03:11:45.035463: step: 1668/530, loss: 0.0003309726598672569
2023-01-23 03:11:46.136889: step: 1672/530, loss: 0.02766113355755806
2023-01-23 03:11:47.251673: step: 1676/530, loss: 0.0031376839615404606
2023-01-23 03:11:48.374995: step: 1680/530, loss: 0.000985479331575334
2023-01-23 03:11:49.456619: step: 1684/530, loss: 0.005018997006118298
2023-01-23 03:11:50.528987: step: 1688/530, loss: 0.7209326028823853
2023-01-23 03:11:51.647899: step: 1692/530, loss: 0.006072712130844593
2023-01-23 03:11:52.750771: step: 1696/530, loss: 0.0005210876697674394
2023-01-23 03:11:53.853348: step: 1700/530, loss: 0.0035539628006517887
2023-01-23 03:11:54.951433: step: 1704/530, loss: 0.25266438722610474
2023-01-23 03:11:56.066234: step: 1708/530, loss: 0.005540752317756414
2023-01-23 03:11:57.196674: step: 1712/530, loss: 0.05774059146642685
2023-01-23 03:11:58.305710: step: 1716/530, loss: 0.0017560005653649569
2023-01-23 03:11:59.417918: step: 1720/530, loss: 0.005229854490607977
2023-01-23 03:12:00.515215: step: 1724/530, loss: 0.017778875306248665
2023-01-23 03:12:01.633980: step: 1728/530, loss: 0.00939102191478014
2023-01-23 03:12:02.743357: step: 1732/530, loss: 0.010485458187758923
2023-01-23 03:12:03.860332: step: 1736/530, loss: 0.007012749090790749
2023-01-23 03:12:04.944102: step: 1740/530, loss: 0.005204105284065008
2023-01-23 03:12:06.035423: step: 1744/530, loss: 0.02857828326523304
2023-01-23 03:12:07.131118: step: 1748/530, loss: 0.003041219897568226
2023-01-23 03:12:08.226243: step: 1752/530, loss: 0.014059782959520817
2023-01-23 03:12:09.335623: step: 1756/530, loss: 0.002980137011036277
2023-01-23 03:12:10.454830: step: 1760/530, loss: 0.023015404120087624
2023-01-23 03:12:11.564700: step: 1764/530, loss: 0.0009369373437948525
2023-01-23 03:12:12.677895: step: 1768/530, loss: 0.21640634536743164
2023-01-23 03:12:13.778089: step: 1772/530, loss: 0.008955764584243298
2023-01-23 03:12:14.875548: step: 1776/530, loss: 0.00010452271089889109
2023-01-23 03:12:15.965195: step: 1780/530, loss: 0.005344581790268421
2023-01-23 03:12:17.051146: step: 1784/530, loss: 0.036281779408454895
2023-01-23 03:12:18.166466: step: 1788/530, loss: 0.009711075574159622
2023-01-23 03:12:19.272957: step: 1792/530, loss: 0.006456566043198109
2023-01-23 03:12:20.373809: step: 1796/530, loss: 0.1239846721291542
2023-01-23 03:12:21.460791: step: 1800/530, loss: 0.01740856096148491
2023-01-23 03:12:22.560468: step: 1804/530, loss: 0.022455215454101562
2023-01-23 03:12:23.681971: step: 1808/530, loss: 0.002722358563914895
2023-01-23 03:12:24.777505: step: 1812/530, loss: 0.004055118653923273
2023-01-23 03:12:25.933929: step: 1816/530, loss: 3.542900230968371e-05
2023-01-23 03:12:27.032379: step: 1820/530, loss: 0.000489354133605957
2023-01-23 03:12:28.174157: step: 1824/530, loss: 0.0008420467493124306
2023-01-23 03:12:29.295128: step: 1828/530, loss: 0.12214889377355576
2023-01-23 03:12:30.413258: step: 1832/530, loss: 0.03563747555017471
2023-01-23 03:12:31.533368: step: 1836/530, loss: 0.00022373200044967234
2023-01-23 03:12:32.630480: step: 1840/530, loss: 2.4890900022001006e-05
2023-01-23 03:12:33.752303: step: 1844/530, loss: 0.01895151101052761
2023-01-23 03:12:34.858102: step: 1848/530, loss: 0.11069031059741974
2023-01-23 03:12:35.956798: step: 1852/530, loss: 0.001604270888492465
2023-01-23 03:12:37.043449: step: 1856/530, loss: 0.00043888093205168843
2023-01-23 03:12:38.105247: step: 1860/530, loss: 0.0004282951704226434
2023-01-23 03:12:39.180486: step: 1864/530, loss: 0.005627441219985485
2023-01-23 03:12:40.284330: step: 1868/530, loss: 0.007857704535126686
2023-01-23 03:12:41.382870: step: 1872/530, loss: 6.437301635742188e-05
2023-01-23 03:12:42.541385: step: 1876/530, loss: 0.0009330749744549394
2023-01-23 03:12:43.649012: step: 1880/530, loss: 0.033197786659002304
2023-01-23 03:12:44.747739: step: 1884/530, loss: 0.007854461669921875
2023-01-23 03:12:45.868815: step: 1888/530, loss: 0.000150775900692679
2023-01-23 03:12:46.960412: step: 1892/530, loss: 0.009442711248993874
2023-01-23 03:12:48.052194: step: 1896/530, loss: 0.0042969705536961555
2023-01-23 03:12:49.179035: step: 1900/530, loss: 0.0037317276000976562
2023-01-23 03:12:50.282036: step: 1904/530, loss: 0.00022001266188453883
2023-01-23 03:12:51.367677: step: 1908/530, loss: 0.012866782955825329
2023-01-23 03:12:52.464458: step: 1912/530, loss: 0.0015930176014080644
2023-01-23 03:12:53.563421: step: 1916/530, loss: 0.006220245733857155
2023-01-23 03:12:54.648205: step: 1920/530, loss: 0.012356949038803577
2023-01-23 03:12:55.770640: step: 1924/530, loss: 0.001119327498599887
2023-01-23 03:12:56.898574: step: 1928/530, loss: 0.00033969880314543843
2023-01-23 03:12:58.014953: step: 1932/530, loss: 0.005018997471779585
2023-01-23 03:12:59.101376: step: 1936/530, loss: 0.00010938644845737144
2023-01-23 03:13:00.200166: step: 1940/530, loss: 0.0006373882060870528
2023-01-23 03:13:01.280631: step: 1944/530, loss: 0.0007758140563964844
2023-01-23 03:13:02.399353: step: 1948/530, loss: 0.001622962998226285
2023-01-23 03:13:03.547685: step: 1952/530, loss: 0.007097435183823109
2023-01-23 03:13:04.660938: step: 1956/530, loss: 0.01904139667749405
2023-01-23 03:13:05.772926: step: 1960/530, loss: 0.0015006065368652344
2023-01-23 03:13:06.896735: step: 1964/530, loss: 0.004491615574806929
2023-01-23 03:13:08.006416: step: 1968/530, loss: 0.00012521744065452367
2023-01-23 03:13:09.112079: step: 1972/530, loss: 0.00010499954805709422
2023-01-23 03:13:10.207259: step: 1976/530, loss: 0.01228790357708931
2023-01-23 03:13:11.336135: step: 1980/530, loss: 0.04665551334619522
2023-01-23 03:13:12.449411: step: 1984/530, loss: 0.02315979078412056
2023-01-23 03:13:13.557786: step: 1988/530, loss: 0.001349210855551064
2023-01-23 03:13:14.646705: step: 1992/530, loss: 0.0018367768498137593
2023-01-23 03:13:15.734178: step: 1996/530, loss: 0.011182880960404873
2023-01-23 03:13:16.822644: step: 2000/530, loss: 0.0030622482299804688
2023-01-23 03:13:17.947858: step: 2004/530, loss: 0.018260573968291283
2023-01-23 03:13:19.081718: step: 2008/530, loss: 0.06368732452392578
2023-01-23 03:13:20.189654: step: 2012/530, loss: 0.039682384580373764
2023-01-23 03:13:21.299778: step: 2016/530, loss: 0.00018529893714003265
2023-01-23 03:13:22.418315: step: 2020/530, loss: 0.016443347558379173
2023-01-23 03:13:23.534197: step: 2024/530, loss: 0.00123090751003474
2023-01-23 03:13:24.676864: step: 2028/530, loss: 0.002041387604549527
2023-01-23 03:13:25.818294: step: 2032/530, loss: 0.012533235363662243
2023-01-23 03:13:26.917745: step: 2036/530, loss: 0.01345901470631361
2023-01-23 03:13:28.013423: step: 2040/530, loss: 0.04271411895751953
2023-01-23 03:13:29.121397: step: 2044/530, loss: 9.765625145519152e-05
2023-01-23 03:13:30.268594: step: 2048/530, loss: 0.002914142794907093
2023-01-23 03:13:31.399400: step: 2052/530, loss: 0.15699510276317596
2023-01-23 03:13:32.483359: step: 2056/530, loss: 0.0002851486497092992
2023-01-23 03:13:33.613233: step: 2060/530, loss: 0.0015765189891681075
2023-01-23 03:13:34.756172: step: 2064/530, loss: 0.0018166541121900082
2023-01-23 03:13:35.859477: step: 2068/530, loss: 0.00585250835865736
2023-01-23 03:13:36.930845: step: 2072/530, loss: 0.0664762482047081
2023-01-23 03:13:38.036627: step: 2076/530, loss: 0.017146587371826172
2023-01-23 03:13:39.131759: step: 2080/530, loss: 0.033246710896492004
2023-01-23 03:13:40.269547: step: 2084/530, loss: 0.00276527414098382
2023-01-23 03:13:41.378419: step: 2088/530, loss: 0.010992812924087048
2023-01-23 03:13:42.468707: step: 2092/530, loss: 0.04770393297076225
2023-01-23 03:13:43.546075: step: 2096/530, loss: 0.00011959076073253527
2023-01-23 03:13:44.693329: step: 2100/530, loss: 0.026585737243294716
2023-01-23 03:13:45.784198: step: 2104/530, loss: 0.005973625462502241
2023-01-23 03:13:46.922515: step: 2108/530, loss: 0.010623455047607422
2023-01-23 03:13:48.063180: step: 2112/530, loss: 0.0046437024138867855
2023-01-23 03:13:49.211564: step: 2116/530, loss: 0.0008586883777752519
2023-01-23 03:13:50.302537: step: 2120/530, loss: 0.0050712586380541325
==================================================
Loss: 0.037
--------------------
Dev: {'event': {'p': 0.6002143622722401, 'r': 0.7456724367509987, 'f1': 0.665083135391924}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
Test: {'event': {'p': 0.6443711728685821, 'r': 0.7972027972027972, 'f1': 0.7126855952070851}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
Chinese: {'event': {'p': 0.6714285714285714, 'r': 0.8703703703703703, 'f1': 0.7580645161290323}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
Korean: {'event': {'p': 0.7317073170731707, 'r': 0.47619047619047616, 'f1': 0.576923076923077}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
Russian: {'event': {'p': 0.4444444444444444, 'r': 0.4444444444444444, 'f1': 0.4444444444444444}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 21}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6449771689497716, 'r': 0.7523302263648469, 'f1': 0.6945298094652735}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Chinese: {'event': {'p': 0.6692644909887969, 'r': 0.8006993006993007, 'f1': 0.7291058636243036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Chinese: {'event': {'p': 0.6764705882352942, 'r': 0.8518518518518519, 'f1': 0.7540983606557378}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Korean: {'event': {'p': 0.6449771689497716, 'r': 0.7523302263648469, 'f1': 0.6945298094652735}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Korean: {'event': {'p': 0.6692644909887969, 'r': 0.8006993006993007, 'f1': 0.7291058636243036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Korean: {'event': {'p': 0.7391304347826086, 'r': 0.5396825396825397, 'f1': 0.6238532110091742}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5971370143149284, 'r': 0.7776298268974701, 'f1': 0.6755349913244649}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Russian: {'event': {'p': 0.6401673640167364, 'r': 0.8024475524475524, 'f1': 0.7121799844840963}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Russian: {'event': {'p': 0.5897435897435898, 'r': 0.6388888888888888, 'f1': 0.6133333333333332}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
******************************
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 03:14:29.331496: step: 4/530, loss: 0.0003976345178671181
2023-01-23 03:14:30.451702: step: 8/530, loss: 0.0723840594291687
2023-01-23 03:14:31.580530: step: 12/530, loss: 9.5367431640625e-05
2023-01-23 03:14:32.704933: step: 16/530, loss: 0.00391731271520257
2023-01-23 03:14:33.791832: step: 20/530, loss: 0.00043735504732467234
2023-01-23 03:14:34.886882: step: 24/530, loss: 0.0018428802723065019
2023-01-23 03:14:35.980931: step: 28/530, loss: 0.0005863189580850303
2023-01-23 03:14:37.082274: step: 32/530, loss: 0.00014181136793922633
2023-01-23 03:14:38.220203: step: 36/530, loss: 0.0005159378051757812
2023-01-23 03:14:39.320946: step: 40/530, loss: 0.03040151484310627
2023-01-23 03:14:40.441044: step: 44/530, loss: 0.007854843512177467
2023-01-23 03:14:41.549597: step: 48/530, loss: 0.013159465976059437
2023-01-23 03:14:42.681710: step: 52/530, loss: 0.006870078854262829
2023-01-23 03:14:43.783557: step: 56/530, loss: 0.006834126077592373
2023-01-23 03:14:44.886377: step: 60/530, loss: 1.959800829354208e-05
2023-01-23 03:14:45.995324: step: 64/530, loss: 0.0008382797241210938
2023-01-23 03:14:47.080619: step: 68/530, loss: 0.0019088268745690584
2023-01-23 03:14:48.172933: step: 72/530, loss: 0.004424715414643288
2023-01-23 03:14:49.267087: step: 76/530, loss: 0.0006326198927126825
2023-01-23 03:14:50.411227: step: 80/530, loss: 0.08639007061719894
2023-01-23 03:14:51.498180: step: 84/530, loss: 1.029968279908644e-05
2023-01-23 03:14:52.605284: step: 88/530, loss: 0.019137192517518997
2023-01-23 03:14:53.706673: step: 92/530, loss: 0.00012807846360374242
2023-01-23 03:14:54.803309: step: 96/530, loss: 8.921623521018773e-05
2023-01-23 03:14:55.909935: step: 100/530, loss: 0.0021835328079760075
2023-01-23 03:14:57.006469: step: 104/530, loss: 0.0018634796142578125
2023-01-23 03:14:58.095654: step: 108/530, loss: 0.002501869108527899
2023-01-23 03:14:59.164460: step: 112/530, loss: 0.03804483264684677
2023-01-23 03:15:00.270826: step: 116/530, loss: 0.0011772155994549394
2023-01-23 03:15:01.354556: step: 120/530, loss: 1.3303757441462949e-05
2023-01-23 03:15:02.441703: step: 124/530, loss: 0.009917545132339
2023-01-23 03:15:03.525584: step: 128/530, loss: 0.007371139712631702
2023-01-23 03:15:04.644206: step: 132/530, loss: 0.04135332256555557
2023-01-23 03:15:05.728008: step: 136/530, loss: 0.00012865067401435226
2023-01-23 03:15:06.800220: step: 140/530, loss: 0.05237245559692383
2023-01-23 03:15:07.903734: step: 144/530, loss: 0.00015254021855071187
2023-01-23 03:15:09.022300: step: 148/530, loss: 0.28070932626724243
2023-01-23 03:15:10.128730: step: 152/530, loss: 0.005045128054916859
2023-01-23 03:15:11.235765: step: 156/530, loss: 0.002064323518425226
2023-01-23 03:15:12.356761: step: 160/530, loss: 0.0004643440479412675
2023-01-23 03:15:13.472369: step: 164/530, loss: 0.0088355066254735
2023-01-23 03:15:14.571917: step: 168/530, loss: 0.0002476692316122353
2023-01-23 03:15:15.679595: step: 172/530, loss: 0.18677674233913422
2023-01-23 03:15:16.771265: step: 176/530, loss: 0.02877178229391575
2023-01-23 03:15:17.889513: step: 180/530, loss: 0.016104411333799362
2023-01-23 03:15:19.009830: step: 184/530, loss: 0.03168316185474396
2023-01-23 03:15:20.120297: step: 188/530, loss: 7.364750490523875e-05
2023-01-23 03:15:21.232719: step: 192/530, loss: 0.005032348912209272
2023-01-23 03:15:22.338245: step: 196/530, loss: 0.0005095482338219881
2023-01-23 03:15:23.470369: step: 200/530, loss: 4.0340422856388614e-05
2023-01-23 03:15:24.563669: step: 204/530, loss: 0.0012983321212232113
2023-01-23 03:15:25.658022: step: 208/530, loss: 0.011368894949555397
2023-01-23 03:15:26.741694: step: 212/530, loss: 3.528594970703125e-05
2023-01-23 03:15:27.860925: step: 216/530, loss: 0.0027915954124182463
2023-01-23 03:15:28.952617: step: 220/530, loss: 0.0021087646018713713
2023-01-23 03:15:30.083337: step: 224/530, loss: 0.0012569427490234375
2023-01-23 03:15:31.166607: step: 228/530, loss: 3.066063072765246e-05
2023-01-23 03:15:32.258928: step: 232/530, loss: 0.000271701836027205
2023-01-23 03:15:33.371959: step: 236/530, loss: 0.00025196076603606343
2023-01-23 03:15:34.486218: step: 240/530, loss: 0.000667572021484375
2023-01-23 03:15:35.592605: step: 244/530, loss: 0.021225357428193092
2023-01-23 03:15:36.719011: step: 248/530, loss: 0.000194549560546875
2023-01-23 03:15:37.820800: step: 252/530, loss: 9.059906915354077e-06
2023-01-23 03:15:38.925641: step: 256/530, loss: 5.34057608092553e-06
2023-01-23 03:15:40.023790: step: 260/530, loss: 0.0009078502771444619
2023-01-23 03:15:41.109721: step: 264/530, loss: 0.0025032043922692537
2023-01-23 03:15:42.227341: step: 268/530, loss: 0.0019360543228685856
2023-01-23 03:15:43.338634: step: 272/530, loss: 0.0733974426984787
2023-01-23 03:15:44.452812: step: 276/530, loss: 0.000774383544921875
2023-01-23 03:15:45.557338: step: 280/530, loss: 0.02871309034526348
2023-01-23 03:15:46.669522: step: 284/530, loss: 0.015671921893954277
2023-01-23 03:15:47.801212: step: 288/530, loss: 0.0007848739624023438
2023-01-23 03:15:48.908509: step: 292/530, loss: 0.014094734564423561
2023-01-23 03:15:50.014876: step: 296/530, loss: 0.0025188445579260588
2023-01-23 03:15:51.163399: step: 300/530, loss: 0.0035118102096021175
2023-01-23 03:15:52.243524: step: 304/530, loss: 0.0019347190391272306
2023-01-23 03:15:53.343181: step: 308/530, loss: 0.0015083312755450606
2023-01-23 03:15:54.469803: step: 312/530, loss: 0.008204078301787376
2023-01-23 03:15:55.551313: step: 316/530, loss: 0.0050065042451024055
2023-01-23 03:15:56.642587: step: 320/530, loss: 0.0004498481866903603
2023-01-23 03:15:57.729859: step: 324/530, loss: 0.0012167930835857987
2023-01-23 03:15:58.809151: step: 328/530, loss: 0.008488655090332031
2023-01-23 03:15:59.922853: step: 332/530, loss: 0.02094249613583088
2023-01-23 03:16:01.065328: step: 336/530, loss: 0.0036266804672777653
2023-01-23 03:16:02.148496: step: 340/530, loss: 0.0006717205396853387
2023-01-23 03:16:03.279343: step: 344/530, loss: 0.003299427218735218
2023-01-23 03:16:04.382456: step: 348/530, loss: 0.0003722667752299458
2023-01-23 03:16:05.503602: step: 352/530, loss: 0.0003857612609863281
2023-01-23 03:16:06.645217: step: 356/530, loss: 0.012955093756318092
2023-01-23 03:16:07.754116: step: 360/530, loss: 5.327165126800537e-05
2023-01-23 03:16:08.849143: step: 364/530, loss: 0.0012156486045569181
2023-01-23 03:16:09.954727: step: 368/530, loss: 5.52177443751134e-05
2023-01-23 03:16:11.051025: step: 372/530, loss: 0.0017345428932458162
2023-01-23 03:16:12.180341: step: 376/530, loss: 1.8215177988167852e-05
2023-01-23 03:16:13.315002: step: 380/530, loss: 0.0064684865064918995
2023-01-23 03:16:14.428648: step: 384/530, loss: 0.0003680229128804058
2023-01-23 03:16:15.529143: step: 388/530, loss: 0.03520164638757706
2023-01-23 03:16:16.644446: step: 392/530, loss: 0.04322004318237305
2023-01-23 03:16:17.733828: step: 396/530, loss: 0.021910380572080612
2023-01-23 03:16:18.837544: step: 400/530, loss: 0.0017875672783702612
2023-01-23 03:16:19.947165: step: 404/530, loss: 0.00012631416029762477
2023-01-23 03:16:21.032600: step: 408/530, loss: 0.0010340691078454256
2023-01-23 03:16:22.144153: step: 412/530, loss: 0.0024124146439135075
2023-01-23 03:16:23.238230: step: 416/530, loss: 0.00013246535672806203
2023-01-23 03:16:24.340322: step: 420/530, loss: 0.011876678094267845
2023-01-23 03:16:25.430243: step: 424/530, loss: 0.001030922052450478
2023-01-23 03:16:26.525926: step: 428/530, loss: 0.0006758690578863025
2023-01-23 03:16:27.622084: step: 432/530, loss: 0.00838174857199192
2023-01-23 03:16:28.720174: step: 436/530, loss: 0.0007442474598065019
2023-01-23 03:16:29.809859: step: 440/530, loss: 0.00013618469529319555
2023-01-23 03:16:30.924374: step: 444/530, loss: 0.032279398292303085
2023-01-23 03:16:32.016952: step: 448/530, loss: 0.0067418101243674755
2023-01-23 03:16:33.095710: step: 452/530, loss: 0.0001356124848825857
2023-01-23 03:16:34.205948: step: 456/530, loss: 0.004150962922722101
2023-01-23 03:16:35.289177: step: 460/530, loss: 0.02308959886431694
2023-01-23 03:16:36.408485: step: 464/530, loss: 2.7084352041129023e-05
2023-01-23 03:16:37.526523: step: 468/530, loss: 7.905960228526965e-05
2023-01-23 03:16:38.651385: step: 472/530, loss: 0.0030261040665209293
2023-01-23 03:16:39.780421: step: 476/530, loss: 0.010237502865493298
2023-01-23 03:16:40.888049: step: 480/530, loss: 0.00848464947193861
2023-01-23 03:16:42.002929: step: 484/530, loss: 0.04960937798023224
2023-01-23 03:16:43.138284: step: 488/530, loss: 0.0007406234508380294
2023-01-23 03:16:44.222261: step: 492/530, loss: 0.05589485168457031
2023-01-23 03:16:45.303295: step: 496/530, loss: 0.00010499954805709422
2023-01-23 03:16:46.405711: step: 500/530, loss: 0.008489036001265049
2023-01-23 03:16:47.505908: step: 504/530, loss: 0.0075667379423975945
2023-01-23 03:16:48.638194: step: 508/530, loss: 0.036260221153497696
2023-01-23 03:16:49.747048: step: 512/530, loss: 0.8706932067871094
2023-01-23 03:16:50.855165: step: 516/530, loss: 0.004640483763068914
2023-01-23 03:16:51.957508: step: 520/530, loss: 0.000419425981817767
2023-01-23 03:16:53.026723: step: 524/530, loss: 0.0025835991837084293
2023-01-23 03:16:54.154894: step: 528/530, loss: 0.002392769092693925
2023-01-23 03:16:55.264650: step: 532/530, loss: 0.0637846291065216
2023-01-23 03:16:56.371049: step: 536/530, loss: 0.004237628076225519
2023-01-23 03:16:57.446960: step: 540/530, loss: 0.01355358399450779
2023-01-23 03:16:58.564068: step: 544/530, loss: 0.004283618647605181
2023-01-23 03:16:59.667975: step: 548/530, loss: 0.013311577029526234
2023-01-23 03:17:00.811734: step: 552/530, loss: 0.0060933115892112255
2023-01-23 03:17:01.881981: step: 556/530, loss: 0.04587965086102486
2023-01-23 03:17:02.987455: step: 560/530, loss: 0.0002696514129638672
2023-01-23 03:17:04.092238: step: 564/530, loss: 0.002296066377311945
2023-01-23 03:17:05.201452: step: 568/530, loss: 0.0070247650146484375
2023-01-23 03:17:06.341630: step: 572/530, loss: 0.029396986588835716
2023-01-23 03:17:07.443466: step: 576/530, loss: 4.0185448597185314e-05
2023-01-23 03:17:08.514035: step: 580/530, loss: 0.0011550902854651213
2023-01-23 03:17:09.634547: step: 584/530, loss: 0.0033814432099461555
2023-01-23 03:17:10.740667: step: 588/530, loss: 0.016238784417510033
2023-01-23 03:17:11.856572: step: 592/530, loss: 0.14269722998142242
2023-01-23 03:17:12.968004: step: 596/530, loss: 0.03598785772919655
2023-01-23 03:17:14.069618: step: 600/530, loss: 0.008385753259062767
2023-01-23 03:17:15.163523: step: 604/530, loss: 0.00024166106595657766
2023-01-23 03:17:16.292195: step: 608/530, loss: 0.0035868645645678043
2023-01-23 03:17:17.391665: step: 612/530, loss: 0.0011723518837243319
2023-01-23 03:17:18.535274: step: 616/530, loss: 0.001582336495630443
2023-01-23 03:17:19.676990: step: 620/530, loss: 0.024824142456054688
2023-01-23 03:17:20.746776: step: 624/530, loss: 0.0008823394891805947
2023-01-23 03:17:21.881368: step: 628/530, loss: 0.002735233400017023
2023-01-23 03:17:22.974316: step: 632/530, loss: 0.000911331211682409
2023-01-23 03:17:24.063886: step: 636/530, loss: 0.0002845764101948589
2023-01-23 03:17:25.216030: step: 640/530, loss: 0.015321922488510609
2023-01-23 03:17:26.304130: step: 644/530, loss: 0.006480979733169079
2023-01-23 03:17:27.429054: step: 648/530, loss: 0.005180645268410444
2023-01-23 03:17:28.532288: step: 652/530, loss: 0.008174420334398746
2023-01-23 03:17:29.622059: step: 656/530, loss: 0.026570606976747513
2023-01-23 03:17:30.716872: step: 660/530, loss: 0.014085614122450352
2023-01-23 03:17:31.823884: step: 664/530, loss: 0.003076934954151511
2023-01-23 03:17:32.993959: step: 668/530, loss: 0.00023622512526344508
2023-01-23 03:17:34.098207: step: 672/530, loss: 0.004090643022209406
2023-01-23 03:17:35.216207: step: 676/530, loss: 0.0003572463756427169
2023-01-23 03:17:36.321731: step: 680/530, loss: 0.018599510192871094
2023-01-23 03:17:37.426908: step: 684/530, loss: 0.0008249282836914062
2023-01-23 03:17:38.568076: step: 688/530, loss: 0.00023307801166083664
2023-01-23 03:17:39.686162: step: 692/530, loss: 8.277892629848793e-05
2023-01-23 03:17:40.760383: step: 696/530, loss: -3.814697606685513e-07
2023-01-23 03:17:41.874302: step: 700/530, loss: 0.00012264252291060984
2023-01-23 03:17:42.990104: step: 704/530, loss: 0.0019449234241619706
2023-01-23 03:17:44.091099: step: 708/530, loss: 0.00043258670484647155
2023-01-23 03:17:45.257479: step: 712/530, loss: 0.06276588141918182
2023-01-23 03:17:46.376034: step: 716/530, loss: 0.008349991403520107
2023-01-23 03:17:47.471042: step: 720/530, loss: 0.0009480953449383378
2023-01-23 03:17:48.569105: step: 724/530, loss: 0.0006827354081906378
2023-01-23 03:17:49.657753: step: 728/530, loss: 3.223419116693549e-05
2023-01-23 03:17:50.725669: step: 732/530, loss: 0.001206684042699635
2023-01-23 03:17:51.851107: step: 736/530, loss: 0.00024499892606399953
2023-01-23 03:17:52.941633: step: 740/530, loss: 0.008846950717270374
2023-01-23 03:17:54.060293: step: 744/530, loss: 0.02328777313232422
2023-01-23 03:17:55.157387: step: 748/530, loss: 0.04045991972088814
2023-01-23 03:17:56.272191: step: 752/530, loss: 0.002870941301807761
2023-01-23 03:17:57.378608: step: 756/530, loss: 0.01673445664346218
2023-01-23 03:17:58.442142: step: 760/530, loss: 0.004992750473320484
2023-01-23 03:17:59.512110: step: 764/530, loss: 0.014320469461381435
2023-01-23 03:18:00.627287: step: 768/530, loss: 0.04595832899212837
2023-01-23 03:18:01.733062: step: 772/530, loss: 0.0014236450660973787
2023-01-23 03:18:02.825802: step: 776/530, loss: 0.016146229580044746
2023-01-23 03:18:03.939439: step: 780/530, loss: 0.005085754673928022
2023-01-23 03:18:05.061817: step: 784/530, loss: 0.025014806538820267
2023-01-23 03:18:06.154437: step: 788/530, loss: 0.00013332365779206157
2023-01-23 03:18:07.261857: step: 792/530, loss: -7.82012921263231e-06
2023-01-23 03:18:08.351951: step: 796/530, loss: 0.025908375158905983
2023-01-23 03:18:09.455214: step: 800/530, loss: 0.00031108857365325093
2023-01-23 03:18:10.558240: step: 804/530, loss: 0.04907989501953125
2023-01-23 03:18:11.676194: step: 808/530, loss: 0.006317520514130592
2023-01-23 03:18:12.786663: step: 812/530, loss: 3.814698175119702e-06
2023-01-23 03:18:13.874859: step: 816/530, loss: 0.010487556457519531
2023-01-23 03:18:14.966531: step: 820/530, loss: 0.009267854504287243
2023-01-23 03:18:16.048691: step: 824/530, loss: 0.0009135246509686112
2023-01-23 03:18:17.147594: step: 828/530, loss: 1.9454957509879023e-05
2023-01-23 03:18:18.269813: step: 832/530, loss: 0.00038547517033293843
2023-01-23 03:18:19.356976: step: 836/530, loss: 0.003556156298145652
2023-01-23 03:18:20.472608: step: 840/530, loss: 0.002094459719955921
2023-01-23 03:18:21.569889: step: 844/530, loss: 0.005781507585197687
2023-01-23 03:18:22.662594: step: 848/530, loss: 0.0008722305065020919
2023-01-23 03:18:23.754849: step: 852/530, loss: 0.0002157211274607107
2023-01-23 03:18:24.860818: step: 856/530, loss: 0.022112656384706497
2023-01-23 03:18:25.975122: step: 860/530, loss: 0.0009470939403399825
2023-01-23 03:18:27.073322: step: 864/530, loss: 0.00062646868173033
2023-01-23 03:18:28.177769: step: 868/530, loss: 0.01717204973101616
2023-01-23 03:18:29.282344: step: 872/530, loss: 0.04960909113287926
2023-01-23 03:18:30.400180: step: 876/530, loss: 0.3084259033203125
2023-01-23 03:18:31.479842: step: 880/530, loss: 0.0038666725158691406
2023-01-23 03:18:32.583400: step: 884/530, loss: 1.33514404296875e-05
2023-01-23 03:18:33.667856: step: 888/530, loss: 0.00017509459576103836
2023-01-23 03:18:34.747207: step: 892/530, loss: 5.9819223679369316e-05
2023-01-23 03:18:35.855385: step: 896/530, loss: 0.057565879076719284
2023-01-23 03:18:36.963627: step: 900/530, loss: 0.0015078544383868575
2023-01-23 03:18:38.094753: step: 904/530, loss: 0.012163257226347923
2023-01-23 03:18:39.207891: step: 908/530, loss: 0.0001146316499216482
2023-01-23 03:18:40.328359: step: 912/530, loss: 1.8501283193472773e-05
2023-01-23 03:18:41.415821: step: 916/530, loss: 4.272460864740424e-05
2023-01-23 03:18:42.535040: step: 920/530, loss: 0.0014146805042400956
2023-01-23 03:18:43.639668: step: 924/530, loss: 0.07103166729211807
2023-01-23 03:18:44.715914: step: 928/530, loss: 0.00173273088876158
2023-01-23 03:18:45.793727: step: 932/530, loss: 0.0008845329284667969
2023-01-23 03:18:46.877749: step: 936/530, loss: 0.0010318756103515625
2023-01-23 03:18:47.966504: step: 940/530, loss: 0.0018466949695721269
2023-01-23 03:18:49.075707: step: 944/530, loss: 0.0009229898569174111
2023-01-23 03:18:50.184005: step: 948/530, loss: 0.013654994778335094
2023-01-23 03:18:51.327697: step: 952/530, loss: 0.0005373954772949219
2023-01-23 03:18:52.431607: step: 956/530, loss: 0.006377506535500288
2023-01-23 03:18:53.525498: step: 960/530, loss: 4.305839684093371e-05
2023-01-23 03:18:54.632652: step: 964/530, loss: 0.020833779126405716
2023-01-23 03:18:55.772514: step: 968/530, loss: 0.0005011558532714844
2023-01-23 03:18:56.880104: step: 972/530, loss: 0.020433997735381126
2023-01-23 03:18:57.971931: step: 976/530, loss: 6.198883056640625e-05
2023-01-23 03:18:59.118277: step: 980/530, loss: 0.00235919957049191
2023-01-23 03:19:00.207841: step: 984/530, loss: 2.403259350103326e-05
2023-01-23 03:19:01.354425: step: 988/530, loss: 0.0014646530617028475
2023-01-23 03:19:02.489020: step: 992/530, loss: 0.0170409195125103
2023-01-23 03:19:03.604861: step: 996/530, loss: 0.00012083053297828883
2023-01-23 03:19:04.696820: step: 1000/530, loss: 5.91278057981981e-06
2023-01-23 03:19:05.836310: step: 1004/530, loss: 9.784699068404734e-05
2023-01-23 03:19:06.938602: step: 1008/530, loss: 0.04106420278549194
2023-01-23 03:19:08.055616: step: 1012/530, loss: 0.00188703543972224
2023-01-23 03:19:09.161015: step: 1016/530, loss: 0.052794601768255234
2023-01-23 03:19:10.275762: step: 1020/530, loss: 0.0004684448358602822
2023-01-23 03:19:11.354897: step: 1024/530, loss: 0.0006625175592489541
2023-01-23 03:19:12.457641: step: 1028/530, loss: 0.0030277250334620476
2023-01-23 03:19:13.592179: step: 1032/530, loss: 0.00536193884909153
2023-01-23 03:19:14.696924: step: 1036/530, loss: 0.00016222000704146922
2023-01-23 03:19:15.849306: step: 1040/530, loss: 0.0004039764462504536
2023-01-23 03:19:16.978438: step: 1044/530, loss: 3.705024573719129e-05
2023-01-23 03:19:18.104243: step: 1048/530, loss: 1.3446808225126006e-05
2023-01-23 03:19:19.223990: step: 1052/530, loss: 0.0007089137798175216
2023-01-23 03:19:20.317944: step: 1056/530, loss: 0.001898956368677318
2023-01-23 03:19:21.435879: step: 1060/530, loss: 0.08673210442066193
2023-01-23 03:19:22.553483: step: 1064/530, loss: 0.024607278406620026
2023-01-23 03:19:23.679624: step: 1068/530, loss: 0.003500127699226141
2023-01-23 03:19:24.797319: step: 1072/530, loss: 0.00025043488130904734
2023-01-23 03:19:25.913081: step: 1076/530, loss: 0.03418693691492081
2023-01-23 03:19:27.027824: step: 1080/530, loss: 0.0018697292543947697
2023-01-23 03:19:28.146291: step: 1084/530, loss: 0.002153778215870261
2023-01-23 03:19:29.269720: step: 1088/530, loss: 0.0015455245738849044
2023-01-23 03:19:30.384400: step: 1092/530, loss: 0.0006849289056845009
2023-01-23 03:19:31.512807: step: 1096/530, loss: 0.00514488248154521
2023-01-23 03:19:32.618729: step: 1100/530, loss: 0.0028198242653161287
2023-01-23 03:19:33.704635: step: 1104/530, loss: 0.033954717218875885
2023-01-23 03:19:34.802897: step: 1108/530, loss: 6.742477853549644e-05
2023-01-23 03:19:35.904415: step: 1112/530, loss: 0.0024618147872388363
2023-01-23 03:19:37.005870: step: 1116/530, loss: 0.0015536308055743575
2023-01-23 03:19:38.118655: step: 1120/530, loss: 0.012928854674100876
2023-01-23 03:19:39.229255: step: 1124/530, loss: 0.0012012481456622481
2023-01-23 03:19:40.308001: step: 1128/530, loss: 0.00042724609375
2023-01-23 03:19:41.401093: step: 1132/530, loss: 0.0010509490966796875
2023-01-23 03:19:42.505319: step: 1136/530, loss: 0.0011124759912490845
2023-01-23 03:19:43.595048: step: 1140/530, loss: 0.0035295486450195312
2023-01-23 03:19:44.709042: step: 1144/530, loss: 0.004352736286818981
2023-01-23 03:19:45.800812: step: 1148/530, loss: 0.004186725709587336
2023-01-23 03:19:46.881284: step: 1152/530, loss: 0.0003269195731263608
2023-01-23 03:19:47.980055: step: 1156/530, loss: 0.003506183624267578
2023-01-23 03:19:49.072399: step: 1160/530, loss: 0.0007779121515341103
2023-01-23 03:19:50.152305: step: 1164/530, loss: 0.0012259007198736072
2023-01-23 03:19:51.247586: step: 1168/530, loss: 0.00035476687480695546
2023-01-23 03:19:52.354480: step: 1172/530, loss: 0.3261560797691345
2023-01-23 03:19:53.467086: step: 1176/530, loss: 0.002636814257130027
2023-01-23 03:19:54.589709: step: 1180/530, loss: 0.00030994415283203125
2023-01-23 03:19:55.693300: step: 1184/530, loss: 0.00011863708641612902
2023-01-23 03:19:56.818020: step: 1188/530, loss: 0.017110252752900124
2023-01-23 03:19:57.919098: step: 1192/530, loss: 2.8324127924861386e-05
2023-01-23 03:19:59.003531: step: 1196/530, loss: 0.005969715304672718
2023-01-23 03:20:00.089688: step: 1200/530, loss: 0.5043748617172241
2023-01-23 03:20:01.211682: step: 1204/530, loss: 0.005442619323730469
2023-01-23 03:20:02.320017: step: 1208/530, loss: 0.008517075330018997
2023-01-23 03:20:03.422813: step: 1212/530, loss: 0.10449686646461487
2023-01-23 03:20:04.539630: step: 1216/530, loss: 0.00749282818287611
2023-01-23 03:20:05.656363: step: 1220/530, loss: 0.00422515906393528
2023-01-23 03:20:06.785088: step: 1224/530, loss: 1.2816870212554932
2023-01-23 03:20:07.859866: step: 1228/530, loss: -1.0013580322265625e-05
2023-01-23 03:20:08.968176: step: 1232/530, loss: 0.005074501037597656
2023-01-23 03:20:10.061343: step: 1236/530, loss: 0.04412341117858887
2023-01-23 03:20:11.176819: step: 1240/530, loss: 0.010665512643754482
2023-01-23 03:20:12.309246: step: 1244/530, loss: 0.0008766174432821572
2023-01-23 03:20:13.402070: step: 1248/530, loss: 0.0002544403250794858
2023-01-23 03:20:14.518314: step: 1252/530, loss: 0.08309125900268555
2023-01-23 03:20:15.625380: step: 1256/530, loss: 0.03335275501012802
2023-01-23 03:20:16.712350: step: 1260/530, loss: 0.0006405829917639494
2023-01-23 03:20:17.809414: step: 1264/530, loss: 0.009982299990952015
2023-01-23 03:20:18.902755: step: 1268/530, loss: 5.14984130859375e-05
2023-01-23 03:20:19.971102: step: 1272/530, loss: 0.014845085330307484
2023-01-23 03:20:21.083384: step: 1276/530, loss: 0.0006991386180743575
2023-01-23 03:20:22.187923: step: 1280/530, loss: 0.01333694439381361
2023-01-23 03:20:23.276994: step: 1284/530, loss: 0.0013908863766118884
2023-01-23 03:20:24.377927: step: 1288/530, loss: 0.0005038261879235506
2023-01-23 03:20:25.478399: step: 1292/530, loss: 0.0001253128139069304
2023-01-23 03:20:26.586100: step: 1296/530, loss: 0.04228544235229492
2023-01-23 03:20:27.694870: step: 1300/530, loss: 2.1457672119140625e-05
2023-01-23 03:20:28.827325: step: 1304/530, loss: 0.013326907530426979
2023-01-23 03:20:29.913126: step: 1308/530, loss: 0.0006330490577965975
2023-01-23 03:20:31.016228: step: 1312/530, loss: 0.08600423485040665
2023-01-23 03:20:32.125492: step: 1316/530, loss: 7.266998727573082e-05
2023-01-23 03:20:33.236420: step: 1320/530, loss: 0.00010452271089889109
2023-01-23 03:20:34.334470: step: 1324/530, loss: 0.03246946632862091
2023-01-23 03:20:35.434462: step: 1328/530, loss: 0.0005215167766436934
2023-01-23 03:20:36.556639: step: 1332/530, loss: 0.0013937473995611072
2023-01-23 03:20:37.676608: step: 1336/530, loss: 0.004111194983124733
2023-01-23 03:20:38.797479: step: 1340/530, loss: 0.04070339351892471
2023-01-23 03:20:39.915323: step: 1344/530, loss: 0.043186187744140625
2023-01-23 03:20:41.012688: step: 1348/530, loss: 0.006456160452216864
2023-01-23 03:20:42.108472: step: 1352/530, loss: 0.008366155438125134
2023-01-23 03:20:43.251954: step: 1356/530, loss: 0.008889198303222656
2023-01-23 03:20:44.346923: step: 1360/530, loss: 0.0006443500169552863
2023-01-23 03:20:45.429505: step: 1364/530, loss: 0.0143890380859375
2023-01-23 03:20:46.523541: step: 1368/530, loss: 0.00018167495727539062
2023-01-23 03:20:47.603425: step: 1372/530, loss: 1.792907642084174e-05
2023-01-23 03:20:48.734600: step: 1376/530, loss: 0.0018383980495855212
2023-01-23 03:20:49.847965: step: 1380/530, loss: 0.01601867564022541
2023-01-23 03:20:50.955436: step: 1384/530, loss: 0.044692136347293854
2023-01-23 03:20:52.106966: step: 1388/530, loss: 0.057747840881347656
2023-01-23 03:20:53.198442: step: 1392/530, loss: 0.0002559661807026714
2023-01-23 03:20:54.293784: step: 1396/530, loss: 0.00120887765660882
2023-01-23 03:20:55.395114: step: 1400/530, loss: 0.0016321182483807206
2023-01-23 03:20:56.502187: step: 1404/530, loss: 0.010409926995635033
2023-01-23 03:20:57.642863: step: 1408/530, loss: 0.009701347909867764
2023-01-23 03:20:58.776877: step: 1412/530, loss: 0.003151798387989402
2023-01-23 03:20:59.888286: step: 1416/530, loss: 0.0027456283569335938
2023-01-23 03:21:00.999703: step: 1420/530, loss: 0.02613067626953125
2023-01-23 03:21:02.118583: step: 1424/530, loss: 0.07314015179872513
2023-01-23 03:21:03.224348: step: 1428/530, loss: 0.5101076364517212
2023-01-23 03:21:04.332404: step: 1432/530, loss: 0.016321564093232155
2023-01-23 03:21:05.436799: step: 1436/530, loss: 0.00026526450528763235
2023-01-23 03:21:06.548340: step: 1440/530, loss: 0.018955565989017487
2023-01-23 03:21:07.656033: step: 1444/530, loss: 0.004082346335053444
2023-01-23 03:21:08.780671: step: 1448/530, loss: 0.02451639249920845
2023-01-23 03:21:09.866223: step: 1452/530, loss: 0.0017275810241699219
2023-01-23 03:21:10.979617: step: 1456/530, loss: 0.05800151824951172
2023-01-23 03:21:12.072673: step: 1460/530, loss: 0.003689384553581476
2023-01-23 03:21:13.202447: step: 1464/530, loss: 0.061934471130371094
2023-01-23 03:21:14.331309: step: 1468/530, loss: 0.0007879257318563759
2023-01-23 03:21:15.448430: step: 1472/530, loss: 0.02274627611041069
2023-01-23 03:21:16.523878: step: 1476/530, loss: 0.006922912783920765
2023-01-23 03:21:17.631351: step: 1480/530, loss: 0.022803355008363724
2023-01-23 03:21:18.727088: step: 1484/530, loss: 2.4223329091910273e-05
2023-01-23 03:21:19.813833: step: 1488/530, loss: 0.09159398823976517
2023-01-23 03:21:20.931014: step: 1492/530, loss: 0.001693677855655551
2023-01-23 03:21:22.033767: step: 1496/530, loss: 0.027047349140048027
2023-01-23 03:21:23.170087: step: 1500/530, loss: 0.025938892737030983
2023-01-23 03:21:24.292383: step: 1504/530, loss: 0.006134796421974897
2023-01-23 03:21:25.390036: step: 1508/530, loss: 0.010800862684845924
2023-01-23 03:21:26.463287: step: 1512/530, loss: 0.0016693114303052425
2023-01-23 03:21:27.559110: step: 1516/530, loss: 0.0024861812125891447
2023-01-23 03:21:28.657283: step: 1520/530, loss: 0.0006982803461141884
2023-01-23 03:21:29.777861: step: 1524/530, loss: 0.005189323332160711
2023-01-23 03:21:30.904303: step: 1528/530, loss: 0.048064421862363815
2023-01-23 03:21:32.019465: step: 1532/530, loss: 0.0012525558704510331
2023-01-23 03:21:33.119219: step: 1536/530, loss: 0.0011914253700524569
2023-01-23 03:21:34.213381: step: 1540/530, loss: 0.05544796213507652
2023-01-23 03:21:35.312002: step: 1544/530, loss: 0.03422355651855469
2023-01-23 03:21:36.411580: step: 1548/530, loss: 0.026355935260653496
2023-01-23 03:21:37.527534: step: 1552/530, loss: 0.002795839449390769
2023-01-23 03:21:38.678316: step: 1556/530, loss: 0.027133941650390625
2023-01-23 03:21:39.792475: step: 1560/530, loss: 0.01924610137939453
2023-01-23 03:21:40.894616: step: 1564/530, loss: 9.851455979514867e-05
2023-01-23 03:21:42.010024: step: 1568/530, loss: 0.003003883408382535
2023-01-23 03:21:43.107558: step: 1572/530, loss: 0.000716781651135534
2023-01-23 03:21:44.192010: step: 1576/530, loss: 0.006088065914809704
2023-01-23 03:21:45.274991: step: 1580/530, loss: 0.00209465017542243
2023-01-23 03:21:46.377240: step: 1584/530, loss: 0.026086904108524323
2023-01-23 03:21:47.487802: step: 1588/530, loss: 0.0016064643859863281
2023-01-23 03:21:48.576944: step: 1592/530, loss: 0.005140113644301891
2023-01-23 03:21:49.669927: step: 1596/530, loss: 0.0002264022914459929
2023-01-23 03:21:50.760169: step: 1600/530, loss: 0.007840538397431374
2023-01-23 03:21:51.842555: step: 1604/530, loss: 0.00015954970149323344
2023-01-23 03:21:52.930568: step: 1608/530, loss: 0.025756072252988815
2023-01-23 03:21:54.056570: step: 1612/530, loss: 1.9550323486328125e-05
2023-01-23 03:21:55.167450: step: 1616/530, loss: 0.00357818603515625
2023-01-23 03:21:56.272111: step: 1620/530, loss: 0.0004165649588685483
2023-01-23 03:21:57.382930: step: 1624/530, loss: 0.018174361437559128
2023-01-23 03:21:58.520050: step: 1628/530, loss: 0.0745948776602745
2023-01-23 03:21:59.615300: step: 1632/530, loss: 0.00011482238915050402
2023-01-23 03:22:00.722611: step: 1636/530, loss: 0.01668567769229412
2023-01-23 03:22:01.825964: step: 1640/530, loss: 0.007037449162453413
2023-01-23 03:22:02.943779: step: 1644/530, loss: 0.00028247834416106343
2023-01-23 03:22:04.025999: step: 1648/530, loss: 0.00013208389282226562
2023-01-23 03:22:05.115098: step: 1652/530, loss: 5.6743621826171875e-05
2023-01-23 03:22:06.213826: step: 1656/530, loss: 0.0015368461608886719
2023-01-23 03:22:07.327718: step: 1660/530, loss: 0.0030134201515465975
2023-01-23 03:22:08.457718: step: 1664/530, loss: 0.0008429527515545487
2023-01-23 03:22:09.573919: step: 1668/530, loss: 0.1338164359331131
2023-01-23 03:22:10.693142: step: 1672/530, loss: 0.001293182373046875
2023-01-23 03:22:11.788013: step: 1676/530, loss: 0.004181480500847101
2023-01-23 03:22:12.906858: step: 1680/530, loss: 0.021399687975645065
2023-01-23 03:22:14.017326: step: 1684/530, loss: 0.0029786110389977694
2023-01-23 03:22:15.086206: step: 1688/530, loss: 0.009052181616425514
2023-01-23 03:22:16.198455: step: 1692/530, loss: 0.00313396449200809
2023-01-23 03:22:17.318056: step: 1696/530, loss: 0.0006866455078125
2023-01-23 03:22:18.425667: step: 1700/530, loss: 0.0005804062238894403
2023-01-23 03:22:19.556309: step: 1704/530, loss: 0.015380478464066982
2023-01-23 03:22:20.678166: step: 1708/530, loss: 0.0005458832019940019
2023-01-23 03:22:21.786440: step: 1712/530, loss: 0.09722118079662323
2023-01-23 03:22:22.930485: step: 1716/530, loss: 0.0046180724166333675
2023-01-23 03:22:24.052717: step: 1720/530, loss: 0.014525937847793102
2023-01-23 03:22:25.126451: step: 1724/530, loss: 1.9836426872643642e-05
2023-01-23 03:22:26.172772: step: 1728/530, loss: 0.035836268216371536
2023-01-23 03:22:27.262515: step: 1732/530, loss: 2.2315980459097773e-05
2023-01-23 03:22:28.382603: step: 1736/530, loss: 0.0034383772872388363
2023-01-23 03:22:29.502430: step: 1740/530, loss: -6.294250852079131e-06
2023-01-23 03:22:30.627526: step: 1744/530, loss: 0.0009846687316894531
2023-01-23 03:22:31.735963: step: 1748/530, loss: 0.004477024078369141
2023-01-23 03:22:32.817934: step: 1752/530, loss: 0.0009902954334393144
2023-01-23 03:22:33.961216: step: 1756/530, loss: 1.8596649169921875e-05
2023-01-23 03:22:35.085384: step: 1760/530, loss: 0.0003364563162904233
2023-01-23 03:22:36.192438: step: 1764/530, loss: 0.03831992298364639
2023-01-23 03:22:37.298934: step: 1768/530, loss: 0.00010576248314464465
2023-01-23 03:22:38.412632: step: 1772/530, loss: 0.003054332686588168
2023-01-23 03:22:39.507189: step: 1776/530, loss: 4.601478394761216e-06
2023-01-23 03:22:40.591663: step: 1780/530, loss: 0.0038658143021166325
2023-01-23 03:22:41.702062: step: 1784/530, loss: 0.0040381429716944695
2023-01-23 03:22:42.798886: step: 1788/530, loss: 0.0007472038851119578
2023-01-23 03:22:43.899889: step: 1792/530, loss: 0.0008172988891601562
2023-01-23 03:22:45.013954: step: 1796/530, loss: 5.559921555686742e-05
2023-01-23 03:22:46.098517: step: 1800/530, loss: 1.583099401614163e-05
2023-01-23 03:22:47.220821: step: 1804/530, loss: 0.00021667481632903218
2023-01-23 03:22:48.322957: step: 1808/530, loss: 0.00011234283010708168
2023-01-23 03:22:49.454948: step: 1812/530, loss: 0.012704659253358841
2023-01-23 03:22:50.585721: step: 1816/530, loss: 0.004326343536376953
2023-01-23 03:22:51.686574: step: 1820/530, loss: 7.934570021461695e-05
2023-01-23 03:22:52.804238: step: 1824/530, loss: 0.003646564669907093
2023-01-23 03:22:53.878625: step: 1828/530, loss: 0.0010173798073083162
2023-01-23 03:22:54.953672: step: 1832/530, loss: 0.014623928815126419
2023-01-23 03:22:56.051254: step: 1836/530, loss: 0.0008357047918252647
2023-01-23 03:22:57.153020: step: 1840/530, loss: 2.0122528439969756e-05
2023-01-23 03:22:58.260725: step: 1844/530, loss: 0.021237945184111595
2023-01-23 03:22:59.359928: step: 1848/530, loss: 0.00845479965209961
2023-01-23 03:23:00.454384: step: 1852/530, loss: 0.0033786774147301912
2023-01-23 03:23:01.552171: step: 1856/530, loss: 1.258850079466356e-05
2023-01-23 03:23:02.670246: step: 1860/530, loss: 0.01694471947848797
2023-01-23 03:23:03.809582: step: 1864/530, loss: 0.018485261127352715
2023-01-23 03:23:04.925146: step: 1868/530, loss: 0.004404640290886164
2023-01-23 03:23:06.025566: step: 1872/530, loss: 3.1280520488508046e-05
2023-01-23 03:23:07.129996: step: 1876/530, loss: 0.013298416510224342
2023-01-23 03:23:08.257195: step: 1880/530, loss: 0.047537706792354584
2023-01-23 03:23:09.361121: step: 1884/530, loss: 0.00022721290588378906
2023-01-23 03:23:10.479516: step: 1888/530, loss: 0.0003864288446493447
2023-01-23 03:23:11.580318: step: 1892/530, loss: 0.0007467747200280428
2023-01-23 03:23:12.702539: step: 1896/530, loss: 0.0008653640979900956
2023-01-23 03:23:13.817955: step: 1900/530, loss: 0.0008832932217046618
2023-01-23 03:23:14.936318: step: 1904/530, loss: 5.416870044427924e-05
2023-01-23 03:23:16.078825: step: 1908/530, loss: 8.22067231638357e-05
2023-01-23 03:23:17.196463: step: 1912/530, loss: 0.00596466101706028
2023-01-23 03:23:18.291455: step: 1916/530, loss: 0.0001983642578125
2023-01-23 03:23:19.396336: step: 1920/530, loss: 0.0003845214960165322
2023-01-23 03:23:20.503920: step: 1924/530, loss: 7.79151960159652e-05
2023-01-23 03:23:21.601082: step: 1928/530, loss: 0.024324703961610794
2023-01-23 03:23:22.675055: step: 1932/530, loss: 0.001174163888208568
2023-01-23 03:23:23.765392: step: 1936/530, loss: 0.0005849838489666581
2023-01-23 03:23:24.878083: step: 1940/530, loss: 0.00019521712965797633
2023-01-23 03:23:25.974889: step: 1944/530, loss: 0.025488663464784622
2023-01-23 03:23:27.080442: step: 1948/530, loss: 0.0009419441339559853
2023-01-23 03:23:28.185522: step: 1952/530, loss: 0.04294757917523384
2023-01-23 03:23:29.290132: step: 1956/530, loss: 6.980896432651207e-05
2023-01-23 03:23:30.406360: step: 1960/530, loss: 0.03148479387164116
2023-01-23 03:23:31.517888: step: 1964/530, loss: 0.019302941858768463
2023-01-23 03:23:32.646833: step: 1968/530, loss: 0.008126449771225452
2023-01-23 03:23:33.775091: step: 1972/530, loss: 0.0011161804432049394
2023-01-23 03:23:34.877986: step: 1976/530, loss: 0.010176753625273705
2023-01-23 03:23:35.979980: step: 1980/530, loss: 0.00593180675059557
2023-01-23 03:23:37.075918: step: 1984/530, loss: 0.01613016054034233
2023-01-23 03:23:38.165792: step: 1988/530, loss: 0.0032448293641209602
2023-01-23 03:23:39.269095: step: 1992/530, loss: 0.005726432893425226
2023-01-23 03:23:40.368285: step: 1996/530, loss: 0.00026531220646575093
2023-01-23 03:23:41.487868: step: 2000/530, loss: 4.405975414556451e-05
2023-01-23 03:23:42.619032: step: 2004/530, loss: 0.0003266334533691406
2023-01-23 03:23:43.703851: step: 2008/530, loss: 0.016266725957393646
2023-01-23 03:23:44.825573: step: 2012/530, loss: 0.0010808944934979081
2023-01-23 03:23:45.999819: step: 2016/530, loss: 0.0034533501602709293
2023-01-23 03:23:47.104248: step: 2020/530, loss: 0.008124828338623047
2023-01-23 03:23:48.199164: step: 2024/530, loss: 7.705688767600805e-05
2023-01-23 03:23:49.307874: step: 2028/530, loss: 0.00010957718041026965
2023-01-23 03:23:50.426915: step: 2032/530, loss: 0.019656755030155182
2023-01-23 03:23:51.533935: step: 2036/530, loss: 0.021117210388183594
2023-01-23 03:23:52.685999: step: 2040/530, loss: 0.0003597259637899697
2023-01-23 03:23:53.832367: step: 2044/530, loss: 0.0007114410400390625
2023-01-23 03:23:54.931317: step: 2048/530, loss: 0.02782921865582466
2023-01-23 03:23:56.038234: step: 2052/530, loss: 0.02720027044415474
2023-01-23 03:23:57.160408: step: 2056/530, loss: 0.0007640838739462197
2023-01-23 03:23:58.278303: step: 2060/530, loss: 0.0013050080742686987
2023-01-23 03:23:59.383888: step: 2064/530, loss: 0.02047717012465
2023-01-23 03:24:00.520714: step: 2068/530, loss: 0.015955066308379173
2023-01-23 03:24:01.628922: step: 2072/530, loss: 0.00010824203491210938
2023-01-23 03:24:02.712962: step: 2076/530, loss: 0.0002804756222758442
2023-01-23 03:24:03.815114: step: 2080/530, loss: 0.002164554549381137
2023-01-23 03:24:04.903816: step: 2084/530, loss: 0.02267751842737198
2023-01-23 03:24:06.027106: step: 2088/530, loss: 4.2629242670955136e-05
2023-01-23 03:24:07.129727: step: 2092/530, loss: 0.002406788058578968
2023-01-23 03:24:08.245484: step: 2096/530, loss: 0.0003466606140136719
2023-01-23 03:24:09.359879: step: 2100/530, loss: 0.0883968323469162
2023-01-23 03:24:10.451988: step: 2104/530, loss: 2.3460386728402227e-05
2023-01-23 03:24:11.551752: step: 2108/530, loss: 0.004645824432373047
2023-01-23 03:24:12.676506: step: 2112/530, loss: 0.011185836978256702
2023-01-23 03:24:13.774130: step: 2116/530, loss: 0.016965484246611595
2023-01-23 03:24:14.888332: step: 2120/530, loss: 0.047889139503240585
==================================================
Loss: 0.019
--------------------
Dev: {'event': {'p': 0.5873340143003064, 'r': 0.7656458055925432, 'f1': 0.6647398843930636}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Test: {'event': {'p': 0.6496487119437939, 'r': 0.8082750582750583, 'f1': 0.7203323811996885}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Chinese: {'event': {'p': 0.5789473684210527, 'r': 0.8148148148148148, 'f1': 0.6769230769230768}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Korean: {'event': {'p': 0.6721311475409836, 'r': 0.6507936507936508, 'f1': 0.6612903225806451}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Russian: {'event': {'p': 0.39473684210526316, 'r': 0.4166666666666667, 'f1': 0.40540540540540543}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
New best korean model...
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6449771689497716, 'r': 0.7523302263648469, 'f1': 0.6945298094652735}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Chinese: {'event': {'p': 0.6692644909887969, 'r': 0.8006993006993007, 'f1': 0.7291058636243036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Chinese: {'event': {'p': 0.6764705882352942, 'r': 0.8518518518518519, 'f1': 0.7540983606557378}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5873340143003064, 'r': 0.7656458055925432, 'f1': 0.6647398843930636}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Eng Test for Korean: {'event': {'p': 0.6496487119437939, 'r': 0.8082750582750583, 'f1': 0.7203323811996885}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Sample Korean: {'event': {'p': 0.6721311475409836, 'r': 0.6507936507936508, 'f1': 0.6612903225806451}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5971370143149284, 'r': 0.7776298268974701, 'f1': 0.6755349913244649}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Russian: {'event': {'p': 0.6401673640167364, 'r': 0.8024475524475524, 'f1': 0.7121799844840963}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Russian: {'event': {'p': 0.5897435897435898, 'r': 0.6388888888888888, 'f1': 0.6133333333333332}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
******************************
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 03:25:01.882314: step: 4/530, loss: 0.001223230268806219
2023-01-23 03:25:02.988324: step: 8/530, loss: 0.0003259658988099545
2023-01-23 03:25:04.108725: step: 12/530, loss: 0.1738794893026352
2023-01-23 03:25:05.205773: step: 16/530, loss: 0.0008614063845016062
2023-01-23 03:25:06.298904: step: 20/530, loss: 0.004119491670280695
2023-01-23 03:25:07.389925: step: 24/530, loss: 0.010311508551239967
2023-01-23 03:25:08.497064: step: 28/530, loss: 0.0067477719858288765
2023-01-23 03:25:09.590711: step: 32/530, loss: 0.030724050477147102
2023-01-23 03:25:10.700881: step: 36/530, loss: 1.277923547604587e-05
2023-01-23 03:25:11.792799: step: 40/530, loss: 0.0001356124848825857
2023-01-23 03:25:12.904395: step: 44/530, loss: 6.675720101156912e-07
2023-01-23 03:25:14.017874: step: 48/530, loss: 0.000358772260369733
2023-01-23 03:25:15.141849: step: 52/530, loss: 0.0010837555164471269
2023-01-23 03:25:16.288523: step: 56/530, loss: 0.002117633819580078
2023-01-23 03:25:17.395957: step: 60/530, loss: 0.03319740295410156
2023-01-23 03:25:18.569493: step: 64/530, loss: 0.0018774033524096012
2023-01-23 03:25:19.689302: step: 68/530, loss: 0.0018703460227698088
2023-01-23 03:25:20.782569: step: 72/530, loss: 0.006689739413559437
2023-01-23 03:25:21.883247: step: 76/530, loss: 0.655320405960083
2023-01-23 03:25:22.988093: step: 80/530, loss: 0.006328773684799671
2023-01-23 03:25:24.104116: step: 84/530, loss: 1.430511474609375e-05
2023-01-23 03:25:25.188101: step: 88/530, loss: 0.005216026678681374
2023-01-23 03:25:26.272218: step: 92/530, loss: 0.0012471199734136462
2023-01-23 03:25:27.386728: step: 96/530, loss: 0.0008646965143270791
2023-01-23 03:25:28.485105: step: 100/530, loss: 5.922317723161541e-05
2023-01-23 03:25:29.616462: step: 104/530, loss: 0.06308680027723312
2023-01-23 03:25:30.709746: step: 108/530, loss: 0.006271076388657093
2023-01-23 03:25:31.773889: step: 112/530, loss: 0.00993957556784153
2023-01-23 03:25:32.921818: step: 116/530, loss: 0.03684253618121147
2023-01-23 03:25:34.027680: step: 120/530, loss: 0.00023345947556663305
2023-01-23 03:25:35.117151: step: 124/530, loss: 0.005297183990478516
2023-01-23 03:25:36.228431: step: 128/530, loss: 0.0022068978287279606
2023-01-23 03:25:37.336122: step: 132/530, loss: 0.06721878051757812
2023-01-23 03:25:38.432713: step: 136/530, loss: 3.62396240234375e-05
2023-01-23 03:25:39.525123: step: 140/530, loss: 0.0019158362410962582
2023-01-23 03:25:40.637746: step: 144/530, loss: 0.007707977667450905
2023-01-23 03:25:41.744959: step: 148/530, loss: 0.00526771554723382
2023-01-23 03:25:42.838832: step: 152/530, loss: 0.019206427037715912
2023-01-23 03:25:43.954897: step: 156/530, loss: 0.024002360180020332
2023-01-23 03:25:45.047932: step: 160/530, loss: 0.0004898071638308465
2023-01-23 03:25:46.148894: step: 164/530, loss: 0.0011127472389489412
2023-01-23 03:25:47.269783: step: 168/530, loss: 0.005709266755729914
2023-01-23 03:25:48.366632: step: 172/530, loss: 0.008604193106293678
2023-01-23 03:25:49.494009: step: 176/530, loss: -1.430511474609375e-06
2023-01-23 03:25:50.612287: step: 180/530, loss: 0.0034673691261559725
2023-01-23 03:25:51.750181: step: 184/530, loss: 0.0011022567050531507
2023-01-23 03:25:52.847072: step: 188/530, loss: 0.00027079583378508687
2023-01-23 03:25:53.930208: step: 192/530, loss: 0.02292327769100666
2023-01-23 03:25:55.034631: step: 196/530, loss: 0.0003555298026185483
2023-01-23 03:25:56.132257: step: 200/530, loss: 0.010971642099320889
2023-01-23 03:25:57.279723: step: 204/530, loss: 0.013446426950395107
2023-01-23 03:25:58.374939: step: 208/530, loss: 6.69479341013357e-05
2023-01-23 03:25:59.459503: step: 212/530, loss: 7.181167893577367e-05
2023-01-23 03:26:00.613498: step: 216/530, loss: 7.500648644054309e-05
2023-01-23 03:26:01.696768: step: 220/530, loss: 0.0002321243373444304
2023-01-23 03:26:02.849894: step: 224/530, loss: 0.040443990379571915
2023-01-23 03:26:03.961656: step: 228/530, loss: 0.00324935931712389
2023-01-23 03:26:05.050196: step: 232/530, loss: 0.009080648422241211
2023-01-23 03:26:06.160394: step: 236/530, loss: 0.0015554428100585938
2023-01-23 03:26:07.261301: step: 240/530, loss: 0.0017174005042761564
2023-01-23 03:26:08.362813: step: 244/530, loss: 0.002349853515625
2023-01-23 03:26:09.466351: step: 248/530, loss: 0.0004907607799395919
2023-01-23 03:26:10.562282: step: 252/530, loss: 0.011743927374482155
2023-01-23 03:26:11.665226: step: 256/530, loss: 0.0059282779693603516
2023-01-23 03:26:12.793917: step: 260/530, loss: 2.2792815798311494e-05
2023-01-23 03:26:13.898063: step: 264/530, loss: 0.003955650143325329
2023-01-23 03:26:14.986404: step: 268/530, loss: 0.026785852387547493
2023-01-23 03:26:16.098291: step: 272/530, loss: 4.425048973644152e-05
2023-01-23 03:26:17.200808: step: 276/530, loss: 0.003799057099968195
2023-01-23 03:26:18.300292: step: 280/530, loss: 0.0005006790161132812
2023-01-23 03:26:19.415563: step: 284/530, loss: 0.04760046303272247
2023-01-23 03:26:20.533339: step: 288/530, loss: 0.007458948064595461
2023-01-23 03:26:21.671969: step: 292/530, loss: 0.0013801574241369963
2023-01-23 03:26:22.800497: step: 296/530, loss: 1.5719053745269775
2023-01-23 03:26:23.890023: step: 300/530, loss: 0.04180707782506943
2023-01-23 03:26:24.991415: step: 304/530, loss: 0.0007768630748614669
2023-01-23 03:26:26.124774: step: 308/530, loss: 5.6838991440599784e-05
2023-01-23 03:26:27.234442: step: 312/530, loss: 0.0017410278087481856
2023-01-23 03:26:28.342803: step: 316/530, loss: 0.022579574957489967
2023-01-23 03:26:29.441734: step: 320/530, loss: 0.0325225368142128
2023-01-23 03:26:30.554259: step: 324/530, loss: 0.0003025055048055947
2023-01-23 03:26:31.662523: step: 328/530, loss: 9.479522850597277e-05
2023-01-23 03:26:32.763496: step: 332/530, loss: 0.006933259777724743
2023-01-23 03:26:33.856364: step: 336/530, loss: 0.013144874945282936
2023-01-23 03:26:34.971483: step: 340/530, loss: 0.020781993865966797
2023-01-23 03:26:36.101145: step: 344/530, loss: 0.2155187726020813
2023-01-23 03:26:37.217727: step: 348/530, loss: 0.006764793302863836
2023-01-23 03:26:38.333679: step: 352/530, loss: 0.03321046754717827
2023-01-23 03:26:39.419463: step: 356/530, loss: 0.00022153854661155492
2023-01-23 03:26:40.536898: step: 360/530, loss: 0.0005739211919717491
2023-01-23 03:26:41.669072: step: 364/530, loss: 0.007083797827363014
2023-01-23 03:26:42.773775: step: 368/530, loss: -6.103515261202119e-06
2023-01-23 03:26:43.881228: step: 372/530, loss: 0.0037605285178869963
2023-01-23 03:26:44.981528: step: 376/530, loss: 0.00016059876361396164
2023-01-23 03:26:46.098343: step: 380/530, loss: 0.017607450485229492
2023-01-23 03:26:47.226755: step: 384/530, loss: 0.03431444242596626
2023-01-23 03:26:48.336587: step: 388/530, loss: 0.0032397271133959293
2023-01-23 03:26:49.450123: step: 392/530, loss: 0.0005640983581542969
2023-01-23 03:26:50.583614: step: 396/530, loss: 0.0010150909656658769
2023-01-23 03:26:51.714536: step: 400/530, loss: 0.0014982223510742188
2023-01-23 03:26:52.803786: step: 404/530, loss: 0.019080162048339844
2023-01-23 03:26:53.914639: step: 408/530, loss: 0.022403717041015625
2023-01-23 03:26:55.025903: step: 412/530, loss: 0.0003603935183491558
2023-01-23 03:26:56.117164: step: 416/530, loss: 0.009385108947753906
2023-01-23 03:26:57.236114: step: 420/530, loss: 0.0025144575629383326
2023-01-23 03:26:58.307854: step: 424/530, loss: 5.435944331111386e-06
2023-01-23 03:26:59.405035: step: 428/530, loss: 0.0005411148304119706
2023-01-23 03:27:00.510258: step: 432/530, loss: 0.000263214111328125
2023-01-23 03:27:01.623802: step: 436/530, loss: 0.002623271895572543
2023-01-23 03:27:02.702816: step: 440/530, loss: 0.00019550323486328125
2023-01-23 03:27:03.798204: step: 444/530, loss: 0.0003775119548663497
2023-01-23 03:27:04.910371: step: 448/530, loss: 0.0038082122337073088
2023-01-23 03:27:06.003948: step: 452/530, loss: 3.900528099620715e-05
2023-01-23 03:27:07.088244: step: 456/530, loss: 0.029935408383607864
2023-01-23 03:27:08.220565: step: 460/530, loss: 0.0007833242416381836
2023-01-23 03:27:09.358007: step: 464/530, loss: 3.833770824712701e-05
2023-01-23 03:27:10.481215: step: 468/530, loss: 0.025014305487275124
2023-01-23 03:27:11.584998: step: 472/530, loss: 0.010751771740615368
2023-01-23 03:27:12.691647: step: 476/530, loss: 0.048979952931404114
2023-01-23 03:27:13.790206: step: 480/530, loss: 0.04413461685180664
2023-01-23 03:27:14.890098: step: 484/530, loss: 0.00740890484303236
2023-01-23 03:27:15.993824: step: 488/530, loss: 0.0014662742614746094
2023-01-23 03:27:17.095326: step: 492/530, loss: 0.0017795562744140625
2023-01-23 03:27:18.201906: step: 496/530, loss: 0.00013723372831009328
2023-01-23 03:27:19.326562: step: 500/530, loss: 0.09296799451112747
2023-01-23 03:27:20.450712: step: 504/530, loss: 0.09633350372314453
2023-01-23 03:27:21.550348: step: 508/530, loss: 0.0009740829700604081
2023-01-23 03:27:22.658488: step: 512/530, loss: 0.001823043916374445
2023-01-23 03:27:23.777490: step: 516/530, loss: 0.00019025802612304688
2023-01-23 03:27:24.886681: step: 520/530, loss: 6.771087555534905e-06
2023-01-23 03:27:26.009259: step: 524/530, loss: 0.0031440737657248974
2023-01-23 03:27:27.107162: step: 528/530, loss: 0.0050182342529296875
2023-01-23 03:27:28.228779: step: 532/530, loss: 0.04634227976202965
2023-01-23 03:27:29.350366: step: 536/530, loss: 7.362366159213707e-05
2023-01-23 03:27:30.474469: step: 540/530, loss: 0.014524650759994984
2023-01-23 03:27:31.559022: step: 544/530, loss: 0.0012355804210528731
2023-01-23 03:27:32.681593: step: 548/530, loss: 0.0051246643997728825
2023-01-23 03:27:33.780419: step: 552/530, loss: 0.00019512177095748484
2023-01-23 03:27:34.907956: step: 556/530, loss: 0.0004864693037234247
2023-01-23 03:27:35.999250: step: 560/530, loss: 0.045590780675411224
2023-01-23 03:27:37.106177: step: 564/530, loss: 0.5763065218925476
2023-01-23 03:27:38.234059: step: 568/530, loss: 0.0009144783252850175
2023-01-23 03:27:39.332157: step: 572/530, loss: 0.04613819345831871
2023-01-23 03:27:40.443695: step: 576/530, loss: 0.00035260917502455413
2023-01-23 03:27:41.550916: step: 580/530, loss: 0.00043716432992368937
2023-01-23 03:27:42.661999: step: 584/530, loss: 0.04950008541345596
2023-01-23 03:27:43.793206: step: 588/530, loss: 0.0010515213944017887
2023-01-23 03:27:44.940046: step: 592/530, loss: 7.295608156709932e-06
2023-01-23 03:27:46.038418: step: 596/530, loss: 0.0004485130193643272
2023-01-23 03:27:47.147360: step: 600/530, loss: 0.05837049335241318
2023-01-23 03:27:48.259363: step: 604/530, loss: 0.020619869232177734
2023-01-23 03:27:49.364007: step: 608/530, loss: 0.007382392883300781
2023-01-23 03:27:50.434038: step: 612/530, loss: 0.00658416748046875
2023-01-23 03:27:51.539327: step: 616/530, loss: 0.00838317908346653
2023-01-23 03:27:52.626644: step: 620/530, loss: 0.01456451416015625
2023-01-23 03:27:53.732177: step: 624/530, loss: 0.007539558224380016
2023-01-23 03:27:54.839966: step: 628/530, loss: 0.005856609903275967
2023-01-23 03:27:55.936386: step: 632/530, loss: 0.0017355919117107987
2023-01-23 03:27:57.050873: step: 636/530, loss: 0.0003650665457826108
2023-01-23 03:27:58.175273: step: 640/530, loss: 0.042017269879579544
2023-01-23 03:27:59.249817: step: 644/530, loss: 0.0003281593380961567
2023-01-23 03:28:00.356237: step: 648/530, loss: 0.010825205594301224
2023-01-23 03:28:01.453599: step: 652/530, loss: 0.03243480250239372
2023-01-23 03:28:02.530591: step: 656/530, loss: 0.0012981414329260588
2023-01-23 03:28:03.683507: step: 660/530, loss: 0.000619268452282995
2023-01-23 03:28:04.759533: step: 664/530, loss: 0.00185737619176507
2023-01-23 03:28:05.843865: step: 668/530, loss: 0.0005755424499511719
2023-01-23 03:28:06.954422: step: 672/530, loss: 0.011188507080078125
2023-01-23 03:28:08.053241: step: 676/530, loss: 0.006601238157600164
2023-01-23 03:28:09.142269: step: 680/530, loss: 0.0029247284401208162
2023-01-23 03:28:10.234210: step: 684/530, loss: 0.009040451608598232
2023-01-23 03:28:11.380516: step: 688/530, loss: 8.964539119915571e-06
2023-01-23 03:28:12.467654: step: 692/530, loss: 0.0006734848138876259
2023-01-23 03:28:13.553846: step: 696/530, loss: 0.000293731689453125
2023-01-23 03:28:14.676691: step: 700/530, loss: 0.4883761405944824
2023-01-23 03:28:15.771550: step: 704/530, loss: 0.00230236048810184
2023-01-23 03:28:16.885235: step: 708/530, loss: 0.008263016119599342
2023-01-23 03:28:17.996328: step: 712/530, loss: 0.00038132668123580515
2023-01-23 03:28:19.093771: step: 716/530, loss: 0.00845184363424778
2023-01-23 03:28:20.214148: step: 720/530, loss: 0.02366333082318306
2023-01-23 03:28:21.313258: step: 724/530, loss: 0.0014160156715661287
2023-01-23 03:28:22.437979: step: 728/530, loss: 4.4345855712890625e-05
2023-01-23 03:28:23.569397: step: 732/530, loss: 0.00022201538376975805
2023-01-23 03:28:24.690536: step: 736/530, loss: 0.0008140563732013106
2023-01-23 03:28:25.797329: step: 740/530, loss: 0.007577800657600164
2023-01-23 03:28:26.908435: step: 744/530, loss: 0.0001604080171091482
2023-01-23 03:28:28.030072: step: 748/530, loss: 0.029819585382938385
2023-01-23 03:28:29.127787: step: 752/530, loss: 6.828308687545359e-05
2023-01-23 03:28:30.242440: step: 756/530, loss: 0.0733589231967926
2023-01-23 03:28:31.346334: step: 760/530, loss: 0.016954900696873665
2023-01-23 03:28:32.452196: step: 764/530, loss: 0.00044803618220612407
2023-01-23 03:28:33.562983: step: 768/530, loss: 0.00041484832763671875
2023-01-23 03:28:34.677097: step: 772/530, loss: 0.0025035827420651913
2023-01-23 03:28:35.795589: step: 776/530, loss: 0.0026735307183116674
2023-01-23 03:28:36.865729: step: 780/530, loss: 2.2506712411995977e-05
2023-01-23 03:28:37.965345: step: 784/530, loss: 0.0019132614834234118
2023-01-23 03:28:39.101970: step: 788/530, loss: 0.002827930264174938
2023-01-23 03:28:40.217509: step: 792/530, loss: 0.022905398160219193
2023-01-23 03:28:41.339560: step: 796/530, loss: 0.03483419120311737
2023-01-23 03:28:42.468760: step: 800/530, loss: 0.0018978118896484375
2023-01-23 03:28:43.564538: step: 804/530, loss: 0.004006767179816961
2023-01-23 03:28:44.650626: step: 808/530, loss: 0.02750072441995144
2023-01-23 03:28:45.799472: step: 812/530, loss: 0.054307177662849426
2023-01-23 03:28:46.892007: step: 816/530, loss: 0.00027027129544876516
2023-01-23 03:28:47.987963: step: 820/530, loss: 0.0004173278866801411
2023-01-23 03:28:49.097138: step: 824/530, loss: 0.0001218795805471018
2023-01-23 03:28:50.246494: step: 828/530, loss: 0.060800742357969284
2023-01-23 03:28:51.361582: step: 832/530, loss: 0.00015048982459120452
2023-01-23 03:28:52.451270: step: 836/530, loss: 0.017201997339725494
2023-01-23 03:28:53.545441: step: 840/530, loss: 0.00020256043353583664
2023-01-23 03:28:54.639148: step: 844/530, loss: 0.00136737828142941
2023-01-23 03:28:55.784334: step: 848/530, loss: 4.749298022943549e-05
2023-01-23 03:28:56.902385: step: 852/530, loss: 0.018430422991514206
2023-01-23 03:28:58.007010: step: 856/530, loss: 0.002789330668747425
2023-01-23 03:28:59.140836: step: 860/530, loss: 0.01636352576315403
2023-01-23 03:29:00.236883: step: 864/530, loss: 0.002908372785896063
2023-01-23 03:29:01.319742: step: 868/530, loss: 0.009708167053759098
2023-01-23 03:29:02.427701: step: 872/530, loss: 0.004147339146584272
2023-01-23 03:29:03.520564: step: 876/530, loss: 6.895065598655492e-05
2023-01-23 03:29:04.617207: step: 880/530, loss: 0.019960401579737663
2023-01-23 03:29:05.748597: step: 884/530, loss: 0.011982726864516735
2023-01-23 03:29:06.839686: step: 888/530, loss: 0.0012177468743175268
2023-01-23 03:29:07.970300: step: 892/530, loss: 0.031755831092596054
2023-01-23 03:29:09.057806: step: 896/530, loss: 0.0010133743053302169
2023-01-23 03:29:10.198522: step: 900/530, loss: 0.0001554012269480154
2023-01-23 03:29:11.312938: step: 904/530, loss: 0.06439266353845596
2023-01-23 03:29:12.459342: step: 908/530, loss: 0.006093025207519531
2023-01-23 03:29:13.575431: step: 912/530, loss: 0.002510452177375555
2023-01-23 03:29:14.671503: step: 916/530, loss: 0.001956939697265625
2023-01-23 03:29:15.785941: step: 920/530, loss: 0.008199977688491344
2023-01-23 03:29:16.865185: step: 924/530, loss: 0.00013809204392600805
2023-01-23 03:29:17.971211: step: 928/530, loss: 0.00019268988398835063
2023-01-23 03:29:19.075257: step: 932/530, loss: 0.01661110110580921
2023-01-23 03:29:20.168270: step: 936/530, loss: 0.003295993898063898
2023-01-23 03:29:21.276401: step: 940/530, loss: 0.005607128143310547
2023-01-23 03:29:22.388292: step: 944/530, loss: 0.05993795394897461
2023-01-23 03:29:23.480681: step: 948/530, loss: 0.0001770019589457661
2023-01-23 03:29:24.565983: step: 952/530, loss: 0.00013265610323287547
2023-01-23 03:29:25.658984: step: 956/530, loss: 0.03682594373822212
2023-01-23 03:29:26.778741: step: 960/530, loss: 0.007557678502053022
2023-01-23 03:29:27.871529: step: 964/530, loss: 0.004063415341079235
2023-01-23 03:29:28.968347: step: 968/530, loss: 0.0008279799949377775
2023-01-23 03:29:30.075109: step: 972/530, loss: -1.1873245966853574e-05
2023-01-23 03:29:31.170690: step: 976/530, loss: 0.009339523501694202
2023-01-23 03:29:32.262315: step: 980/530, loss: 2.7465821403893642e-05
2023-01-23 03:29:33.380752: step: 984/530, loss: 0.04427976906299591
2023-01-23 03:29:34.463472: step: 988/530, loss: 0.00028553008451126516
2023-01-23 03:29:35.587775: step: 992/530, loss: 0.013398361392319202
2023-01-23 03:29:36.705614: step: 996/530, loss: 0.013470841571688652
2023-01-23 03:29:37.815395: step: 1000/530, loss: 0.0009891510708257556
2023-01-23 03:29:38.906064: step: 1004/530, loss: 0.020771121606230736
2023-01-23 03:29:40.033628: step: 1008/530, loss: 0.0033872604835778475
2023-01-23 03:29:41.128220: step: 1012/530, loss: 0.00011854172043967992
2023-01-23 03:29:42.222811: step: 1016/530, loss: 4.320144944358617e-05
2023-01-23 03:29:43.364649: step: 1020/530, loss: 0.002172183943912387
2023-01-23 03:29:44.487030: step: 1024/530, loss: 0.01824493333697319
2023-01-23 03:29:45.577161: step: 1028/530, loss: -1.5258789289873675e-06
2023-01-23 03:29:46.687475: step: 1032/530, loss: 0.0057586668990552425
2023-01-23 03:29:47.856097: step: 1036/530, loss: 0.00696220388635993
2023-01-23 03:29:48.966548: step: 1040/530, loss: -8.96453821042087e-06
2023-01-23 03:29:50.096242: step: 1044/530, loss: 0.0012565612560138106
2023-01-23 03:29:51.227170: step: 1048/530, loss: 0.005820846650749445
2023-01-23 03:29:52.319220: step: 1052/530, loss: 0.008389520458877087
2023-01-23 03:29:53.417149: step: 1056/530, loss: 0.0006235122564248741
2023-01-23 03:29:54.500139: step: 1060/530, loss: 0.01103820838034153
2023-01-23 03:29:55.604984: step: 1064/530, loss: 0.00092740060063079
2023-01-23 03:29:56.716071: step: 1068/530, loss: 0.0005703926435671747
2023-01-23 03:29:57.804381: step: 1072/530, loss: 0.04490146413445473
2023-01-23 03:29:58.943721: step: 1076/530, loss: 0.0005027771112509072
2023-01-23 03:30:00.083057: step: 1080/530, loss: 0.024184800684452057
2023-01-23 03:30:01.207893: step: 1084/530, loss: 0.005805111024528742
2023-01-23 03:30:02.302719: step: 1088/530, loss: 0.043514348566532135
2023-01-23 03:30:03.424292: step: 1092/530, loss: 0.0004415511793922633
2023-01-23 03:30:04.529930: step: 1096/530, loss: 0.001503944513387978
2023-01-23 03:30:05.627640: step: 1100/530, loss: 0.007948732003569603
2023-01-23 03:30:06.751806: step: 1104/530, loss: 0.00040602684020996094
2023-01-23 03:30:07.911593: step: 1108/530, loss: 0.007936859503388405
2023-01-23 03:30:09.010924: step: 1112/530, loss: 0.009998702444136143
2023-01-23 03:30:10.149730: step: 1116/530, loss: 0.0008195877308025956
2023-01-23 03:30:11.283885: step: 1120/530, loss: 0.026778889819979668
2023-01-23 03:30:12.403823: step: 1124/530, loss: 0.02886371687054634
2023-01-23 03:30:13.519499: step: 1128/530, loss: 0.0005548477056436241
2023-01-23 03:30:14.622243: step: 1132/530, loss: 0.0006591796991415322
2023-01-23 03:30:15.759747: step: 1136/530, loss: 0.014800643548369408
2023-01-23 03:30:16.903920: step: 1140/530, loss: 0.7176936268806458
2023-01-23 03:30:18.016658: step: 1144/530, loss: 0.0008934020879678428
2023-01-23 03:30:19.150091: step: 1148/530, loss: 7.200241088867188e-05
2023-01-23 03:30:20.245048: step: 1152/530, loss: 0.012579060159623623
2023-01-23 03:30:21.345689: step: 1156/530, loss: 5.722046125811175e-07
2023-01-23 03:30:22.456244: step: 1160/530, loss: 0.00027236941969022155
2023-01-23 03:30:23.542361: step: 1164/530, loss: 0.00017967224994208664
2023-01-23 03:30:24.651209: step: 1168/530, loss: 8.773804438533261e-06
2023-01-23 03:30:25.779822: step: 1172/530, loss: 0.015769243240356445
2023-01-23 03:30:26.886374: step: 1176/530, loss: 0.00031766892061568797
2023-01-23 03:30:27.989542: step: 1180/530, loss: 0.0007321357843466103
2023-01-23 03:30:29.100043: step: 1184/530, loss: 0.0004665374872274697
2023-01-23 03:30:30.176461: step: 1188/530, loss: 0.000419425981817767
2023-01-23 03:30:31.273648: step: 1192/530, loss: 0.00047931671724654734
2023-01-23 03:30:32.372485: step: 1196/530, loss: 0.0027671335265040398
2023-01-23 03:30:33.474060: step: 1200/530, loss: 0.012008501216769218
2023-01-23 03:30:34.554663: step: 1204/530, loss: 4.215240551275201e-05
2023-01-23 03:30:35.648352: step: 1208/530, loss: 0.0010000228649005294
2023-01-23 03:30:36.750633: step: 1212/530, loss: 0.0024730681907385588
2023-01-23 03:30:37.869775: step: 1216/530, loss: 9.880066500045359e-05
2023-01-23 03:30:38.975387: step: 1220/530, loss: 0.001472854521125555
2023-01-23 03:30:40.106460: step: 1224/530, loss: 0.005084419623017311
2023-01-23 03:30:41.184748: step: 1228/530, loss: 3.938675217796117e-05
2023-01-23 03:30:42.276507: step: 1232/530, loss: 4.4488908315543085e-05
2023-01-23 03:30:43.372790: step: 1236/530, loss: 0.0020829676650464535
2023-01-23 03:30:44.445054: step: 1240/530, loss: 0.00021967888460494578
2023-01-23 03:30:45.530359: step: 1244/530, loss: 0.0005834579933434725
2023-01-23 03:30:46.645598: step: 1248/530, loss: 1.850128137448337e-05
2023-01-23 03:30:47.788970: step: 1252/530, loss: 0.03547334671020508
2023-01-23 03:30:48.899267: step: 1256/530, loss: 0.02529440075159073
2023-01-23 03:30:50.002272: step: 1260/530, loss: 0.00463447580114007
2023-01-23 03:30:51.110401: step: 1264/530, loss: 0.10710448771715164
2023-01-23 03:30:52.184365: step: 1268/530, loss: 0.0029116631485521793
2023-01-23 03:30:53.306456: step: 1272/530, loss: 0.002628421876579523
2023-01-23 03:30:54.411264: step: 1276/530, loss: 0.006462669465690851
2023-01-23 03:30:55.502538: step: 1280/530, loss: 0.001979351043701172
2023-01-23 03:30:56.588232: step: 1284/530, loss: 0.0221710205078125
2023-01-23 03:30:57.694635: step: 1288/530, loss: 0.0002401351957814768
2023-01-23 03:30:58.793871: step: 1292/530, loss: 0.002731370972469449
2023-01-23 03:30:59.865840: step: 1296/530, loss: 0.004636764992028475
2023-01-23 03:31:00.958726: step: 1300/530, loss: 0.33591651916503906
2023-01-23 03:31:02.061654: step: 1304/530, loss: 0.004771137144416571
2023-01-23 03:31:03.161457: step: 1308/530, loss: 0.00010414123971713707
2023-01-23 03:31:04.262660: step: 1312/530, loss: 0.0019754411187022924
2023-01-23 03:31:05.362857: step: 1316/530, loss: 0.00037937163142487407
2023-01-23 03:31:06.450193: step: 1320/530, loss: 0.017027854919433594
2023-01-23 03:31:07.606420: step: 1324/530, loss: 0.0301939956843853
2023-01-23 03:31:08.698052: step: 1328/530, loss: 0.1273849457502365
2023-01-23 03:31:09.814065: step: 1332/530, loss: 0.005249977111816406
2023-01-23 03:31:10.928981: step: 1336/530, loss: 0.01485443115234375
2023-01-23 03:31:12.096893: step: 1340/530, loss: 0.04502906650304794
2023-01-23 03:31:13.213638: step: 1344/530, loss: 0.01974649354815483
2023-01-23 03:31:14.295170: step: 1348/530, loss: 0.0020643712487071753
2023-01-23 03:31:15.406519: step: 1352/530, loss: 0.0002511978382244706
2023-01-23 03:31:16.541612: step: 1356/530, loss: 0.03373584523797035
2023-01-23 03:31:17.630385: step: 1360/530, loss: 0.0005797863123007119
2023-01-23 03:31:18.726675: step: 1364/530, loss: 0.016827011480927467
2023-01-23 03:31:19.816093: step: 1368/530, loss: -6.48498553346144e-06
2023-01-23 03:31:20.946784: step: 1372/530, loss: 8.96453821042087e-06
2023-01-23 03:31:22.042371: step: 1376/530, loss: 6.732940528308973e-05
2023-01-23 03:31:23.150595: step: 1380/530, loss: 0.0025796890258789062
2023-01-23 03:31:24.248037: step: 1384/530, loss: 0.0007453918224200606
2023-01-23 03:31:25.368493: step: 1388/530, loss: 0.01558532752096653
2023-01-23 03:31:26.497283: step: 1392/530, loss: 0.014037705026566982
2023-01-23 03:31:27.610963: step: 1396/530, loss: 0.0004398345772642642
2023-01-23 03:31:28.696726: step: 1400/530, loss: 0.0005353927845135331
2023-01-23 03:31:29.796456: step: 1404/530, loss: 0.003597831819206476
2023-01-23 03:31:30.887227: step: 1408/530, loss: 0.026904871687293053
2023-01-23 03:31:31.969511: step: 1412/530, loss: 4.425048973644152e-05
2023-01-23 03:31:33.080449: step: 1416/530, loss: 0.002578639890998602
2023-01-23 03:31:34.209350: step: 1420/530, loss: 0.04206442832946777
2023-01-23 03:31:35.324367: step: 1424/530, loss: 0.0002612113894429058
2023-01-23 03:31:36.402072: step: 1428/530, loss: 0.0006733656045980752
2023-01-23 03:31:37.516975: step: 1432/530, loss: 0.0008470535976812243
2023-01-23 03:31:38.622290: step: 1436/530, loss: 0.023834897205233574
2023-01-23 03:31:39.691979: step: 1440/530, loss: -6.198883056640625e-06
2023-01-23 03:31:40.778725: step: 1444/530, loss: 0.0002265930233988911
2023-01-23 03:31:41.837042: step: 1448/530, loss: 0.005977678578346968
2023-01-23 03:31:42.939954: step: 1452/530, loss: 0.0013768196804448962
2023-01-23 03:31:44.027481: step: 1456/530, loss: 0.596026599407196
2023-01-23 03:31:45.105493: step: 1460/530, loss: 0.007172965910285711
2023-01-23 03:31:46.237396: step: 1464/530, loss: 0.005070686340332031
2023-01-23 03:31:47.336997: step: 1468/530, loss: 0.04132404178380966
2023-01-23 03:31:48.436980: step: 1472/530, loss: 0.0007271766662597656
2023-01-23 03:31:49.550017: step: 1476/530, loss: 0.003949403762817383
2023-01-23 03:31:50.650449: step: 1480/530, loss: 5.726814561057836e-05
2023-01-23 03:31:51.737046: step: 1484/530, loss: 1.430511474609375e-06
2023-01-23 03:31:52.820542: step: 1488/530, loss: 0.008794165216386318
2023-01-23 03:31:53.939184: step: 1492/530, loss: 0.02519082836806774
2023-01-23 03:31:55.014723: step: 1496/530, loss: 1.869201696536038e-05
2023-01-23 03:31:56.117269: step: 1500/530, loss: 0.018928242847323418
2023-01-23 03:31:57.237085: step: 1504/530, loss: 0.0009658813942223787
2023-01-23 03:31:58.324278: step: 1508/530, loss: 0.03637199476361275
2023-01-23 03:31:59.423179: step: 1512/530, loss: 0.001326751778833568
2023-01-23 03:32:00.530081: step: 1516/530, loss: -4.9591067181609105e-06
2023-01-23 03:32:01.604366: step: 1520/530, loss: 0.000580838299356401
2023-01-23 03:32:02.694196: step: 1524/530, loss: 0.004694509785622358
2023-01-23 03:32:03.810270: step: 1528/530, loss: 0.0007190704345703125
2023-01-23 03:32:04.952486: step: 1532/530, loss: 0.041944313794374466
2023-01-23 03:32:06.100725: step: 1536/530, loss: 0.0783195048570633
2023-01-23 03:32:07.205368: step: 1540/530, loss: 0.0011120795970782638
2023-01-23 03:32:08.328099: step: 1544/530, loss: 0.03445339575409889
2023-01-23 03:32:09.425707: step: 1548/530, loss: 2.3937223886605352e-05
2023-01-23 03:32:10.546444: step: 1552/530, loss: 0.00269393902271986
2023-01-23 03:32:11.633705: step: 1556/530, loss: 3.0994415283203125e-06
2023-01-23 03:32:12.764561: step: 1560/530, loss: 0.0025085448287427425
2023-01-23 03:32:13.866882: step: 1564/530, loss: 0.0025135038886219263
2023-01-23 03:32:14.974225: step: 1568/530, loss: 0.03264026716351509
2023-01-23 03:32:16.052849: step: 1572/530, loss: 0.022303033620119095
2023-01-23 03:32:17.171986: step: 1576/530, loss: 0.0024772644974291325
2023-01-23 03:32:18.272489: step: 1580/530, loss: 0.0011322021018713713
2023-01-23 03:32:19.396520: step: 1584/530, loss: 8.306503877975047e-05
2023-01-23 03:32:20.511505: step: 1588/530, loss: 0.04471893608570099
2023-01-23 03:32:21.606225: step: 1592/530, loss: 1.4114380974206142e-05
2023-01-23 03:32:22.697721: step: 1596/530, loss: 0.006565404124557972
2023-01-23 03:32:23.792792: step: 1600/530, loss: 2.822876012942288e-05
2023-01-23 03:32:24.893239: step: 1604/530, loss: 0.0061675552278757095
2023-01-23 03:32:26.012587: step: 1608/530, loss: 0.0013930320274084806
2023-01-23 03:32:27.108831: step: 1612/530, loss: 0.0004811763938050717
2023-01-23 03:32:28.190294: step: 1616/530, loss: 0.002718257950618863
2023-01-23 03:32:29.329143: step: 1620/530, loss: 0.0006052970420569181
2023-01-23 03:32:30.425123: step: 1624/530, loss: 0.017832566052675247
2023-01-23 03:32:31.512348: step: 1628/530, loss: 0.00026798248291015625
2023-01-23 03:32:32.597822: step: 1632/530, loss: 5.674362455465598e-06
2023-01-23 03:32:33.677487: step: 1636/530, loss: 0.0008571147918701172
2023-01-23 03:32:34.767319: step: 1640/530, loss: 6.3419347497983836e-06
2023-01-23 03:32:35.845155: step: 1644/530, loss: 3.180504063493572e-05
2023-01-23 03:32:36.948389: step: 1648/530, loss: 5.826950291520916e-05
2023-01-23 03:32:38.038989: step: 1652/530, loss: 0.005058264825493097
2023-01-23 03:32:39.157378: step: 1656/530, loss: 0.012596678920090199
2023-01-23 03:32:40.240447: step: 1660/530, loss: 0.0012564659118652344
2023-01-23 03:32:41.353349: step: 1664/530, loss: 0.07707862555980682
2023-01-23 03:32:42.456750: step: 1668/530, loss: 0.04216022416949272
2023-01-23 03:32:43.546564: step: 1672/530, loss: 0.002632999327033758
2023-01-23 03:32:44.647599: step: 1676/530, loss: 0.02209930494427681
2023-01-23 03:32:45.806329: step: 1680/530, loss: 0.03626756742596626
2023-01-23 03:32:46.929328: step: 1684/530, loss: 0.012114906683564186
2023-01-23 03:32:48.022567: step: 1688/530, loss: 0.01845397986471653
2023-01-23 03:32:49.144490: step: 1692/530, loss: 0.005199146457016468
2023-01-23 03:32:50.260677: step: 1696/530, loss: 0.0005088805919513106
2023-01-23 03:32:51.393862: step: 1700/530, loss: 0.006882953457534313
2023-01-23 03:32:52.493256: step: 1704/530, loss: 0.029113102704286575
2023-01-23 03:32:53.651649: step: 1708/530, loss: 0.038135334849357605
2023-01-23 03:32:54.749943: step: 1712/530, loss: 2.784729076665826e-05
2023-01-23 03:32:55.897235: step: 1716/530, loss: 0.04022855684161186
2023-01-23 03:32:56.991769: step: 1720/530, loss: 0.016542483121156693
2023-01-23 03:32:58.096843: step: 1724/530, loss: 0.09811268746852875
2023-01-23 03:32:59.215394: step: 1728/530, loss: 0.003682136768475175
2023-01-23 03:33:00.337887: step: 1732/530, loss: 8.60214204294607e-05
2023-01-23 03:33:01.441783: step: 1736/530, loss: 0.009171867743134499
2023-01-23 03:33:02.551148: step: 1740/530, loss: 0.0441431999206543
2023-01-23 03:33:03.682001: step: 1744/530, loss: 0.007792663760483265
2023-01-23 03:33:04.810875: step: 1748/530, loss: 0.04929351806640625
2023-01-23 03:33:05.922299: step: 1752/530, loss: 0.0033597948495298624
2023-01-23 03:33:07.033789: step: 1756/530, loss: 0.022371673956513405
2023-01-23 03:33:08.191006: step: 1760/530, loss: 0.03011927753686905
2023-01-23 03:33:09.315380: step: 1764/530, loss: 0.005393600556999445
2023-01-23 03:33:10.445659: step: 1768/530, loss: 0.006622409913688898
2023-01-23 03:33:11.522310: step: 1772/530, loss: 3.24249276673072e-06
2023-01-23 03:33:12.624163: step: 1776/530, loss: 0.0022425891365855932
2023-01-23 03:33:13.736871: step: 1780/530, loss: 0.002239704132080078
2023-01-23 03:33:14.854388: step: 1784/530, loss: 0.008510970510542393
2023-01-23 03:33:15.957099: step: 1788/530, loss: -3.814697265625e-06
2023-01-23 03:33:17.054019: step: 1792/530, loss: 9.498596773482859e-05
2023-01-23 03:33:18.156291: step: 1796/530, loss: 0.0006328582530841231
2023-01-23 03:33:19.287723: step: 1800/530, loss: 0.017905235290527344
2023-01-23 03:33:20.422592: step: 1804/530, loss: 0.24385519325733185
2023-01-23 03:33:21.517578: step: 1808/530, loss: 0.0002732276916503906
2023-01-23 03:33:22.612928: step: 1812/530, loss: 2.269744800287299e-05
2023-01-23 03:33:23.697192: step: 1816/530, loss: 0.007462859153747559
2023-01-23 03:33:24.793251: step: 1820/530, loss: 0.011810302734375
2023-01-23 03:33:25.926100: step: 1824/530, loss: 0.00024137497530318797
2023-01-23 03:33:27.027111: step: 1828/530, loss: 0.035941507667303085
2023-01-23 03:33:28.141710: step: 1832/530, loss: 0.00824284553527832
2023-01-23 03:33:29.228443: step: 1836/530, loss: 0.0012829303741455078
2023-01-23 03:33:30.307508: step: 1840/530, loss: 4.9781796406023204e-05
2023-01-23 03:33:31.422064: step: 1844/530, loss: 0.000579833984375
2023-01-23 03:33:32.516990: step: 1848/530, loss: 1.049041748046875e-05
2023-01-23 03:33:33.596403: step: 1852/530, loss: 0.018314171582460403
2023-01-23 03:33:34.731284: step: 1856/530, loss: 0.00010013580322265625
2023-01-23 03:33:35.818474: step: 1860/530, loss: 0.0001957416534423828
2023-01-23 03:33:36.955157: step: 1864/530, loss: 0.012576103210449219
2023-01-23 03:33:38.033426: step: 1868/530, loss: 0.007226563058793545
2023-01-23 03:33:39.131448: step: 1872/530, loss: 0.0015048980712890625
2023-01-23 03:33:40.233802: step: 1876/530, loss: 0.0006517410511150956
2023-01-23 03:33:41.343536: step: 1880/530, loss: 0.0016218186356127262
2023-01-23 03:33:42.424023: step: 1884/530, loss: 0.0010039329063147306
2023-01-23 03:33:43.499963: step: 1888/530, loss: 0.0004635810910258442
2023-01-23 03:33:44.597806: step: 1892/530, loss: 0.005362033843994141
2023-01-23 03:33:45.688970: step: 1896/530, loss: 0.00110712053719908
2023-01-23 03:33:46.794288: step: 1900/530, loss: 0.00048441888066008687
2023-01-23 03:33:47.889485: step: 1904/530, loss: 0.006543636322021484
2023-01-23 03:33:48.970806: step: 1908/530, loss: -1.8119812921213452e-06
2023-01-23 03:33:50.061694: step: 1912/530, loss: 0.007022667210549116
2023-01-23 03:33:51.219881: step: 1916/530, loss: -3.42369094141759e-05
2023-01-23 03:33:52.335186: step: 1920/530, loss: 0.03026561811566353
2023-01-23 03:33:53.441309: step: 1924/530, loss: 0.010492324829101562
2023-01-23 03:33:54.554824: step: 1928/530, loss: 6.008148193359375e-05
2023-01-23 03:33:55.638713: step: 1932/530, loss: 1.4019012269272935e-05
2023-01-23 03:33:56.766011: step: 1936/530, loss: 0.0004623412969522178
2023-01-23 03:33:57.865144: step: 1940/530, loss: 0.0041217803955078125
2023-01-23 03:33:58.945719: step: 1944/530, loss: 2.7179719381820178e-06
2023-01-23 03:34:00.022997: step: 1948/530, loss: 0.000177288064151071
2023-01-23 03:34:01.126568: step: 1952/530, loss: 0.013975572772324085
2023-01-23 03:34:02.246017: step: 1956/530, loss: 0.0005696773296222091
2023-01-23 03:34:03.351106: step: 1960/530, loss: 2.9373170036706142e-05
2023-01-23 03:34:04.454746: step: 1964/530, loss: 0.010573388077318668
2023-01-23 03:34:05.614540: step: 1968/530, loss: 0.005488968454301357
2023-01-23 03:34:06.727423: step: 1972/530, loss: 0.03534388542175293
2023-01-23 03:34:07.824003: step: 1976/530, loss: 0.0025485993828624487
2023-01-23 03:34:08.941833: step: 1980/530, loss: 0.0005553722730837762
2023-01-23 03:34:10.031134: step: 1984/530, loss: 0.0002442359982524067
2023-01-23 03:34:11.127250: step: 1988/530, loss: 0.0011517524253576994
2023-01-23 03:34:12.232839: step: 1992/530, loss: 5.064010838395916e-05
2023-01-23 03:34:13.335799: step: 1996/530, loss: 0.003597450442612171
2023-01-23 03:34:14.432384: step: 2000/530, loss: 0.009614372625946999
2023-01-23 03:34:15.522962: step: 2004/530, loss: 0.003248119493946433
2023-01-23 03:34:16.580269: step: 2008/530, loss: 0.0001390457182424143
2023-01-23 03:34:17.713007: step: 2012/530, loss: 3.0469893317786045e-05
2023-01-23 03:34:18.800887: step: 2016/530, loss: 0.00018959045701194555
2023-01-23 03:34:19.924070: step: 2020/530, loss: 0.014476108364760876
2023-01-23 03:34:21.009169: step: 2024/530, loss: 0.00046114923316054046
2023-01-23 03:34:22.108680: step: 2028/530, loss: 0.030524635687470436
2023-01-23 03:34:23.213191: step: 2032/530, loss: 0.011456107720732689
2023-01-23 03:34:24.344770: step: 2036/530, loss: 0.020128441974520683
2023-01-23 03:34:25.456686: step: 2040/530, loss: 0.07104626297950745
2023-01-23 03:34:26.549397: step: 2044/530, loss: 0.0013711928622797132
2023-01-23 03:34:27.670220: step: 2048/530, loss: 0.028418540954589844
2023-01-23 03:34:28.770336: step: 2052/530, loss: 0.0042282105423510075
2023-01-23 03:34:29.875846: step: 2056/530, loss: 6.0558319091796875e-05
2023-01-23 03:34:30.943371: step: 2060/530, loss: 0.0007425308576785028
2023-01-23 03:34:32.046874: step: 2064/530, loss: 0.017597580328583717
2023-01-23 03:34:33.175421: step: 2068/530, loss: 0.02717743068933487
2023-01-23 03:34:34.292254: step: 2072/530, loss: 0.0004070282157044858
2023-01-23 03:34:35.395542: step: 2076/530, loss: 0.023640252649784088
2023-01-23 03:34:36.498495: step: 2080/530, loss: 0.005477047525346279
2023-01-23 03:34:37.611067: step: 2084/530, loss: 0.009013175964355469
2023-01-23 03:34:38.747683: step: 2088/530, loss: 0.040326882153749466
2023-01-23 03:34:39.849653: step: 2092/530, loss: 0.0025306702591478825
2023-01-23 03:34:40.954037: step: 2096/530, loss: 1.7833710444392636e-05
2023-01-23 03:34:42.074203: step: 2100/530, loss: 0.0012613296275958419
2023-01-23 03:34:43.192408: step: 2104/530, loss: 0.031528472900390625
2023-01-23 03:34:44.308769: step: 2108/530, loss: 6.103515261202119e-05
2023-01-23 03:34:45.401660: step: 2112/530, loss: 0.005725097376853228
2023-01-23 03:34:46.527014: step: 2116/530, loss: 0.004639053251594305
2023-01-23 03:34:47.607387: step: 2120/530, loss: 5.931854320806451e-05
==================================================
Loss: 0.021
--------------------
Dev: {'event': {'p': 0.5826612903225806, 'r': 0.7696404793608522, 'f1': 0.6632243258749283}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Test: {'event': {'p': 0.6385321100917432, 'r': 0.8111888111888111, 'f1': 0.7145790554414785}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Chinese: {'event': {'p': 0.6571428571428571, 'r': 0.8518518518518519, 'f1': 0.7419354838709677}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Korean: {'event': {'p': 0.6551724137931034, 'r': 0.6031746031746031, 'f1': 0.628099173553719}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
Russian: {'event': {'p': 0.5, 'r': 0.5555555555555556, 'f1': 0.5263157894736842}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 23}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6449771689497716, 'r': 0.7523302263648469, 'f1': 0.6945298094652735}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Chinese: {'event': {'p': 0.6692644909887969, 'r': 0.8006993006993007, 'f1': 0.7291058636243036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Chinese: {'event': {'p': 0.6764705882352942, 'r': 0.8518518518518519, 'f1': 0.7540983606557378}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5873340143003064, 'r': 0.7656458055925432, 'f1': 0.6647398843930636}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Eng Test for Korean: {'event': {'p': 0.6496487119437939, 'r': 0.8082750582750583, 'f1': 0.7203323811996885}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Sample Korean: {'event': {'p': 0.6721311475409836, 'r': 0.6507936507936508, 'f1': 0.6612903225806451}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5971370143149284, 'r': 0.7776298268974701, 'f1': 0.6755349913244649}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Russian: {'event': {'p': 0.6401673640167364, 'r': 0.8024475524475524, 'f1': 0.7121799844840963}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Russian: {'event': {'p': 0.5897435897435898, 'r': 0.6388888888888888, 'f1': 0.6133333333333332}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
******************************
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 03:35:26.877762: step: 4/530, loss: 0.0001181602492579259
2023-01-23 03:35:27.972720: step: 8/530, loss: 4.315376281738281e-05
2023-01-23 03:35:29.097992: step: 12/530, loss: 0.007059860043227673
2023-01-23 03:35:30.192399: step: 16/530, loss: 0.00021152498084120452
2023-01-23 03:35:31.324609: step: 20/530, loss: 0.005780410952866077
2023-01-23 03:35:32.423253: step: 24/530, loss: 0.0024755478370934725
2023-01-23 03:35:33.537012: step: 28/530, loss: 0.0013053894508630037
2023-01-23 03:35:34.626759: step: 32/530, loss: 0.0005859375814907253
2023-01-23 03:35:35.711284: step: 36/530, loss: 0.000217437744140625
2023-01-23 03:35:36.843281: step: 40/530, loss: 0.0004322052118368447
2023-01-23 03:35:37.920175: step: 44/530, loss: 0.0024472237564623356
2023-01-23 03:35:39.028643: step: 48/530, loss: 0.0023786069359630346
2023-01-23 03:35:40.195985: step: 52/530, loss: 0.01628742180764675
2023-01-23 03:35:41.309791: step: 56/530, loss: 0.0023448944557458162
2023-01-23 03:35:42.415341: step: 60/530, loss: 0.00939102191478014
2023-01-23 03:35:43.565052: step: 64/530, loss: 0.022030210122466087
2023-01-23 03:35:44.650381: step: 68/530, loss: 0.00042819976806640625
2023-01-23 03:35:45.767463: step: 72/530, loss: 0.004167079925537109
2023-01-23 03:35:46.857898: step: 76/530, loss: 3.5095217754133046e-05
2023-01-23 03:35:47.973324: step: 80/530, loss: 0.023180866613984108
2023-01-23 03:35:49.057081: step: 84/530, loss: 0.001747608301229775
2023-01-23 03:35:50.160315: step: 88/530, loss: 0.0008821488008834422
2023-01-23 03:35:51.262883: step: 92/530, loss: 0.0002480506955180317
2023-01-23 03:35:52.369545: step: 96/530, loss: 0.006002617534250021
2023-01-23 03:35:53.453201: step: 100/530, loss: 1.3828278497385327e-05
2023-01-23 03:35:54.555432: step: 104/530, loss: 0.0005464553833007812
2023-01-23 03:35:55.678913: step: 108/530, loss: 3.051757857974735e-06
2023-01-23 03:35:56.788356: step: 112/530, loss: 0.03663787990808487
2023-01-23 03:35:57.895564: step: 116/530, loss: 0.01664094813168049
2023-01-23 03:35:58.996030: step: 120/530, loss: 0.008404731750488281
2023-01-23 03:36:00.077324: step: 124/530, loss: 0.00017223358736373484
2023-01-23 03:36:01.202398: step: 128/530, loss: 0.01043481845408678
2023-01-23 03:36:02.297716: step: 132/530, loss: 1.3542176020564511e-05
2023-01-23 03:36:03.421241: step: 136/530, loss: 0.004161739256232977
2023-01-23 03:36:04.524676: step: 140/530, loss: 0.0005633354303427041
2023-01-23 03:36:05.630297: step: 144/530, loss: 3.337860107421875e-06
2023-01-23 03:36:06.746208: step: 148/530, loss: 0.00010557174391578883
2023-01-23 03:36:07.854745: step: 152/530, loss: 0.0018682479858398438
2023-01-23 03:36:08.957090: step: 156/530, loss: 0.03556881099939346
2023-01-23 03:36:10.056236: step: 160/530, loss: 0.00486183213070035
2023-01-23 03:36:11.192242: step: 164/530, loss: 0.0003407478507142514
2023-01-23 03:36:12.298256: step: 168/530, loss: 0.0029088975861668587
2023-01-23 03:36:13.409656: step: 172/530, loss: 0.00019893646822310984
2023-01-23 03:36:14.519117: step: 176/530, loss: 0.03455962985754013
2023-01-23 03:36:15.611740: step: 180/530, loss: 0.0019924165681004524
2023-01-23 03:36:16.707763: step: 184/530, loss: 0.05401868745684624
2023-01-23 03:36:17.810174: step: 188/530, loss: 0.0007426262018270791
2023-01-23 03:36:18.900413: step: 192/530, loss: 0.043405912816524506
2023-01-23 03:36:20.037360: step: 196/530, loss: 0.00483021792024374
2023-01-23 03:36:21.134530: step: 200/530, loss: 0.005067634396255016
2023-01-23 03:36:22.241491: step: 204/530, loss: 0.049700167030096054
2023-01-23 03:36:23.380884: step: 208/530, loss: 0.0004032135184388608
2023-01-23 03:36:24.484919: step: 212/530, loss: 0.0001678466796875
2023-01-23 03:36:25.586030: step: 216/530, loss: 0.00030078887357376516
2023-01-23 03:36:26.688393: step: 220/530, loss: 9.450912330066785e-05
2023-01-23 03:36:27.798798: step: 224/530, loss: 0.0022581100929528475
2023-01-23 03:36:28.932752: step: 228/530, loss: 0.0008321762434206903
2023-01-23 03:36:30.029626: step: 232/530, loss: 0.0009102821350097656
2023-01-23 03:36:31.124726: step: 236/530, loss: 0.0002178192080464214
2023-01-23 03:36:32.221114: step: 240/530, loss: 0.3204216957092285
2023-01-23 03:36:33.328586: step: 244/530, loss: 0.01825866848230362
2023-01-23 03:36:34.397702: step: 248/530, loss: 0.0003409385681152344
2023-01-23 03:36:35.523190: step: 252/530, loss: 0.07293710857629776
2023-01-23 03:36:36.625522: step: 256/530, loss: 0.0006601333734579384
2023-01-23 03:36:37.769876: step: 260/530, loss: 4.081726001459174e-05
2023-01-23 03:36:38.873922: step: 264/530, loss: 0.009628105908632278
2023-01-23 03:36:39.978987: step: 268/530, loss: 0.003125953720882535
2023-01-23 03:36:41.095645: step: 272/530, loss: 0.18219681084156036
2023-01-23 03:36:42.179121: step: 276/530, loss: 0.0006276131025515497
2023-01-23 03:36:43.282449: step: 280/530, loss: 0.0007067203987389803
2023-01-23 03:36:44.393214: step: 284/530, loss: 1.945495569088962e-05
2023-01-23 03:36:45.475395: step: 288/530, loss: 0.004003429319709539
2023-01-23 03:36:46.563555: step: 292/530, loss: 0.0003593921719584614
2023-01-23 03:36:47.643814: step: 296/530, loss: 4.358291334938258e-05
2023-01-23 03:36:48.728756: step: 300/530, loss: 0.01516122929751873
2023-01-23 03:36:49.831243: step: 304/530, loss: 0.009535026736557484
2023-01-23 03:36:50.916323: step: 308/530, loss: 0.00018405914306640625
2023-01-23 03:36:52.015377: step: 312/530, loss: 0.018927576020359993
2023-01-23 03:36:53.125172: step: 316/530, loss: 0.00014610291691496968
2023-01-23 03:36:54.240602: step: 320/530, loss: 0.0006084442138671875
2023-01-23 03:36:55.347330: step: 324/530, loss: 0.005340385250747204
2023-01-23 03:36:56.430609: step: 328/530, loss: 0.01884470134973526
2023-01-23 03:36:57.515319: step: 332/530, loss: 6.904602196300402e-05
2023-01-23 03:36:58.615896: step: 336/530, loss: 0.00077991490252316
2023-01-23 03:36:59.731308: step: 340/530, loss: 3.52859501617786e-06
2023-01-23 03:37:00.840131: step: 344/530, loss: 0.00022039414034225047
2023-01-23 03:37:01.919511: step: 348/530, loss: 0.00018386841111350805
2023-01-23 03:37:03.050828: step: 352/530, loss: 0.00035858154296875
2023-01-23 03:37:04.160748: step: 356/530, loss: 0.00054254534188658
2023-01-23 03:37:05.250530: step: 360/530, loss: 0.00017185212345793843
2023-01-23 03:37:06.362516: step: 364/530, loss: 0.0002635955752339214
2023-01-23 03:37:07.498013: step: 368/530, loss: 0.0005266189691610634
2023-01-23 03:37:08.588454: step: 372/530, loss: 0.045053862035274506
2023-01-23 03:37:09.714616: step: 376/530, loss: 0.003920555114746094
2023-01-23 03:37:10.824235: step: 380/530, loss: 0.04845566675066948
2023-01-23 03:37:11.922605: step: 384/530, loss: 6.499290611827746e-05
2023-01-23 03:37:13.017065: step: 388/530, loss: -3.0517576306010596e-06
2023-01-23 03:37:14.137340: step: 392/530, loss: 0.008835315704345703
2023-01-23 03:37:15.238860: step: 396/530, loss: 0.043308451771736145
2023-01-23 03:37:16.337916: step: 400/530, loss: 0.002752399304881692
2023-01-23 03:37:17.460126: step: 404/530, loss: 0.00021276474581100047
2023-01-23 03:37:18.578185: step: 408/530, loss: 0.0014449120499193668
2023-01-23 03:37:19.652658: step: 412/530, loss: 0.00418777484446764
2023-01-23 03:37:20.752863: step: 416/530, loss: 1.6021729607018642e-05
2023-01-23 03:37:21.854883: step: 420/530, loss: 0.002090645022690296
2023-01-23 03:37:22.961399: step: 424/530, loss: 0.014922904781997204
2023-01-23 03:37:24.043272: step: 428/530, loss: 0.006016826257109642
2023-01-23 03:37:25.166210: step: 432/530, loss: 0.0005315780872479081
2023-01-23 03:37:26.257877: step: 436/530, loss: 0.0015379905235022306
2023-01-23 03:37:27.371360: step: 440/530, loss: 0.01862926408648491
2023-01-23 03:37:28.450858: step: 444/530, loss: 0.0006584167713299394
2023-01-23 03:37:29.540878: step: 448/530, loss: 0.00014543533325195312
2023-01-23 03:37:30.637785: step: 452/530, loss: 0.0004741668817587197
2023-01-23 03:37:31.725125: step: 456/530, loss: 0.0010362624889239669
2023-01-23 03:37:32.793977: step: 460/530, loss: 0.0006955146673135459
2023-01-23 03:37:33.930340: step: 464/530, loss: 0.014077950268983841
2023-01-23 03:37:35.010508: step: 468/530, loss: 3.337860107421875e-05
2023-01-23 03:37:36.115987: step: 472/530, loss: 0.00022811889357399195
2023-01-23 03:37:37.208995: step: 476/530, loss: 0.0010173798073083162
2023-01-23 03:37:38.296761: step: 480/530, loss: -1.4781952586417901e-06
2023-01-23 03:37:39.422968: step: 484/530, loss: 0.017048073932528496
2023-01-23 03:37:40.542798: step: 488/530, loss: 0.020419597625732422
2023-01-23 03:37:41.662107: step: 492/530, loss: 0.004304313566535711
2023-01-23 03:37:42.778202: step: 496/530, loss: 0.0002826690615620464
2023-01-23 03:37:43.884812: step: 500/530, loss: 0.00017146169557236135
2023-01-23 03:37:45.012830: step: 504/530, loss: 0.00031719208345748484
2023-01-23 03:37:46.121291: step: 508/530, loss: 8.840560622047633e-05
2023-01-23 03:37:47.226121: step: 512/530, loss: 8.0108642578125e-05
2023-01-23 03:37:48.342502: step: 516/530, loss: 0.008255290798842907
2023-01-23 03:37:49.433573: step: 520/530, loss: 0.005081653594970703
2023-01-23 03:37:50.598828: step: 524/530, loss: 0.0005936622619628906
2023-01-23 03:37:51.696489: step: 528/530, loss: 0.004739189054816961
2023-01-23 03:37:52.794062: step: 532/530, loss: 0.00023932458134368062
2023-01-23 03:37:53.931245: step: 536/530, loss: -2.7179717108083423e-06
2023-01-23 03:37:55.052873: step: 540/530, loss: 0.0025644302368164062
2023-01-23 03:37:56.165572: step: 544/530, loss: 0.002995395800098777
2023-01-23 03:37:57.291784: step: 548/530, loss: 4.673004150390625e-05
2023-01-23 03:37:58.402146: step: 552/530, loss: 0.004652452189475298
2023-01-23 03:37:59.492077: step: 556/530, loss: 0.007967948913574219
2023-01-23 03:38:00.592348: step: 560/530, loss: 2.2411346435546875e-05
2023-01-23 03:38:01.701721: step: 564/530, loss: 0.0012355804210528731
2023-01-23 03:38:02.809348: step: 568/530, loss: 0.020633887499570847
2023-01-23 03:38:03.953966: step: 572/530, loss: 6.961823601159267e-06
2023-01-23 03:38:05.067883: step: 576/530, loss: 0.0017211914528161287
2023-01-23 03:38:06.154972: step: 580/530, loss: 0.06138734892010689
2023-01-23 03:38:07.248397: step: 584/530, loss: 0.0018898011185228825
2023-01-23 03:38:08.336155: step: 588/530, loss: 0.0027740478981286287
2023-01-23 03:38:09.430600: step: 592/530, loss: 0.004668331239372492
2023-01-23 03:38:10.525696: step: 596/530, loss: 7.581711543025449e-06
2023-01-23 03:38:11.607853: step: 600/530, loss: 0.0035331726539880037
2023-01-23 03:38:12.722783: step: 604/530, loss: 0.00034437180147506297
2023-01-23 03:38:13.810026: step: 608/530, loss: 0.0010023117065429688
2023-01-23 03:38:14.908184: step: 612/530, loss: 0.055156707763671875
2023-01-23 03:38:16.012832: step: 616/530, loss: 0.037053827196359634
2023-01-23 03:38:17.110162: step: 620/530, loss: 0.4583573341369629
2023-01-23 03:38:18.236757: step: 624/530, loss: 0.0027387558948248625
2023-01-23 03:38:19.347483: step: 628/530, loss: 0.0004874229780398309
2023-01-23 03:38:20.423350: step: 632/530, loss: 0.0010898590553551912
2023-01-23 03:38:21.528479: step: 636/530, loss: 0.0673213005065918
2023-01-23 03:38:22.637396: step: 640/530, loss: 0.002672863192856312
2023-01-23 03:38:23.723928: step: 644/530, loss: 0.0008506775484420359
2023-01-23 03:38:24.843569: step: 648/530, loss: 0.011867523193359375
2023-01-23 03:38:25.935446: step: 652/530, loss: 0.0004531860467977822
2023-01-23 03:38:27.043184: step: 656/530, loss: 0.004370689857751131
2023-01-23 03:38:28.126585: step: 660/530, loss: 0.024695873260498047
2023-01-23 03:38:29.242909: step: 664/530, loss: 0.009311104193329811
2023-01-23 03:38:30.335446: step: 668/530, loss: 0.0002847671858035028
2023-01-23 03:38:31.429354: step: 672/530, loss: 0.00011577605619095266
2023-01-23 03:38:32.596233: step: 676/530, loss: 0.3177453875541687
2023-01-23 03:38:33.692452: step: 680/530, loss: 0.00013065338134765625
2023-01-23 03:38:34.787882: step: 684/530, loss: 0.0005950927734375
2023-01-23 03:38:35.890877: step: 688/530, loss: 0.03645019605755806
2023-01-23 03:38:36.999078: step: 692/530, loss: 0.00023641585721634328
2023-01-23 03:38:38.104944: step: 696/530, loss: 0.49969181418418884
2023-01-23 03:38:39.211127: step: 700/530, loss: 0.0001312255917582661
2023-01-23 03:38:40.362460: step: 704/530, loss: 0.02437572553753853
2023-01-23 03:38:41.480824: step: 708/530, loss: 4.9591064453125e-05
2023-01-23 03:38:42.578867: step: 712/530, loss: 0.005005550570785999
2023-01-23 03:38:43.702724: step: 716/530, loss: 0.020033836364746094
2023-01-23 03:38:44.809042: step: 720/530, loss: 0.00111817114520818
2023-01-23 03:38:45.910414: step: 724/530, loss: 5.550384594243951e-05
2023-01-23 03:38:47.018357: step: 728/530, loss: 0.024981975555419922
2023-01-23 03:38:48.083818: step: 732/530, loss: 8.893013000488281e-05
2023-01-23 03:38:49.185485: step: 736/530, loss: 0.00029754638671875
2023-01-23 03:38:50.298413: step: 740/530, loss: 0.0016672135097905993
2023-01-23 03:38:51.364949: step: 744/530, loss: 0.031229306012392044
2023-01-23 03:38:52.454414: step: 748/530, loss: 0.009283638559281826
2023-01-23 03:38:53.561556: step: 752/530, loss: 0.03994441032409668
2023-01-23 03:38:54.698312: step: 756/530, loss: 0.00011520386033225805
2023-01-23 03:38:55.835828: step: 760/530, loss: 0.0028385163750499487
2023-01-23 03:38:56.925082: step: 764/530, loss: 0.002548408694565296
2023-01-23 03:38:58.047701: step: 768/530, loss: 0.005142879206687212
2023-01-23 03:38:59.168941: step: 772/530, loss: 0.03744678199291229
2023-01-23 03:39:00.244689: step: 776/530, loss: 0.0002884865098167211
2023-01-23 03:39:01.316862: step: 780/530, loss: 3.738403393072076e-05
2023-01-23 03:39:02.444072: step: 784/530, loss: 6.961822509765625e-05
2023-01-23 03:39:03.567980: step: 788/530, loss: 0.01434869784861803
2023-01-23 03:39:04.687660: step: 792/530, loss: 0.0008829116704873741
2023-01-23 03:39:05.765074: step: 796/530, loss: 6.48498553346144e-06
2023-01-23 03:39:06.908065: step: 800/530, loss: 0.025713825598359108
2023-01-23 03:39:08.017019: step: 804/530, loss: 1.3399124327406753e-05
2023-01-23 03:39:09.104290: step: 808/530, loss: 7.486344111384824e-05
2023-01-23 03:39:10.200117: step: 812/530, loss: 0.018118999898433685
2023-01-23 03:39:11.319394: step: 816/530, loss: 0.03981170803308487
2023-01-23 03:39:12.414769: step: 820/530, loss: 0.07109756767749786
2023-01-23 03:39:13.542340: step: 824/530, loss: 0.00024690627469681203
2023-01-23 03:39:14.629756: step: 828/530, loss: 0.0032117129303514957
2023-01-23 03:39:15.713940: step: 832/530, loss: 2.079009937006049e-05
2023-01-23 03:39:16.797875: step: 836/530, loss: 2.8896331059513614e-05
2023-01-23 03:39:17.925053: step: 840/530, loss: 0.0009204864618368447
2023-01-23 03:39:19.031944: step: 844/530, loss: 0.001543235732242465
2023-01-23 03:39:20.099863: step: 848/530, loss: 5.9604644775390625e-06
2023-01-23 03:39:21.203986: step: 852/530, loss: 0.00014705659123137593
2023-01-23 03:39:22.310033: step: 856/530, loss: 0.10301666706800461
2023-01-23 03:39:23.424430: step: 860/530, loss: 0.0002754211309365928
2023-01-23 03:39:24.503844: step: 864/530, loss: 0.012121295556426048
2023-01-23 03:39:25.578011: step: 868/530, loss: 1.602172778802924e-05
2023-01-23 03:39:26.679086: step: 872/530, loss: 0.0038080215454101562
2023-01-23 03:39:27.760340: step: 876/530, loss: 3.376007225597277e-05
2023-01-23 03:39:28.863803: step: 880/530, loss: 0.0038259506691247225
2023-01-23 03:39:30.004836: step: 884/530, loss: 0.0013064384693279862
2023-01-23 03:39:31.102192: step: 888/530, loss: 0.0045497422106564045
2023-01-23 03:39:32.262117: step: 892/530, loss: 0.009140742011368275
2023-01-23 03:39:33.357072: step: 896/530, loss: 7.400512549793348e-05
2023-01-23 03:39:34.450893: step: 900/530, loss: 0.00025081634521484375
2023-01-23 03:39:35.557581: step: 904/530, loss: 0.0005198478465899825
2023-01-23 03:39:36.684428: step: 908/530, loss: 0.02880859375
2023-01-23 03:39:37.775729: step: 912/530, loss: 0.0015477180713787675
2023-01-23 03:39:38.862099: step: 916/530, loss: 0.5670353174209595
2023-01-23 03:39:39.971875: step: 920/530, loss: 4.301071021473035e-05
2023-01-23 03:39:41.098897: step: 924/530, loss: 0.00040435791015625
2023-01-23 03:39:42.229697: step: 928/530, loss: 0.029523467645049095
2023-01-23 03:39:43.370559: step: 932/530, loss: 0.0002792835293803364
2023-01-23 03:39:44.533160: step: 936/530, loss: 0.0011518478859215975
2023-01-23 03:39:45.650838: step: 940/530, loss: 0.016272639855742455
2023-01-23 03:39:46.768460: step: 944/530, loss: 0.01273798942565918
2023-01-23 03:39:47.887200: step: 948/530, loss: 0.038091469556093216
2023-01-23 03:39:49.026105: step: 952/530, loss: 0.01286239642649889
2023-01-23 03:39:50.121481: step: 956/530, loss: 0.0037246705032885075
2023-01-23 03:39:51.228816: step: 960/530, loss: 0.0008117675897665322
2023-01-23 03:39:52.354681: step: 964/530, loss: 0.0012517928844317794
2023-01-23 03:39:53.483562: step: 968/530, loss: 0.00197181710973382
2023-01-23 03:39:54.596165: step: 972/530, loss: 0.0002876281796488911
2023-01-23 03:39:55.699020: step: 976/530, loss: 2.498626781743951e-05
2023-01-23 03:39:56.831719: step: 980/530, loss: 0.008121490478515625
2023-01-23 03:39:57.959817: step: 984/530, loss: 0.02439708635210991
2023-01-23 03:39:59.075314: step: 988/530, loss: 1.8119826563633978e-06
2023-01-23 03:40:00.159472: step: 992/530, loss: 0.0011347770923748612
2023-01-23 03:40:01.266500: step: 996/530, loss: 6.046295311534777e-05
2023-01-23 03:40:02.367568: step: 1000/530, loss: 0.0009944438934326172
2023-01-23 03:40:03.483466: step: 1004/530, loss: 0.00013828277587890625
2023-01-23 03:40:04.596338: step: 1008/530, loss: 8.258819434558973e-05
2023-01-23 03:40:05.722348: step: 1012/530, loss: 0.028845978900790215
2023-01-23 03:40:06.815937: step: 1016/530, loss: 0.0033416748046875
2023-01-23 03:40:07.938942: step: 1020/530, loss: 0.01681804656982422
2023-01-23 03:40:09.031830: step: 1024/530, loss: 0.04450998455286026
2023-01-23 03:40:10.139771: step: 1028/530, loss: 0.09645596146583557
2023-01-23 03:40:11.241432: step: 1032/530, loss: 0.010912513360381126
2023-01-23 03:40:12.331302: step: 1036/530, loss: 0.0013650894397869706
2023-01-23 03:40:13.432457: step: 1040/530, loss: 6.532669067382812e-05
2023-01-23 03:40:14.554437: step: 1044/530, loss: 0.01375570334494114
2023-01-23 03:40:15.682404: step: 1048/530, loss: 0.0018524170154705644
2023-01-23 03:40:16.812394: step: 1052/530, loss: 0.00483627337962389
2023-01-23 03:40:17.917916: step: 1056/530, loss: 0.0001780033198883757
2023-01-23 03:40:19.002131: step: 1060/530, loss: 0.0001085281401174143
2023-01-23 03:40:20.129254: step: 1064/530, loss: 5.908012462896295e-05
2023-01-23 03:40:21.236900: step: 1068/530, loss: 0.026308298110961914
2023-01-23 03:40:22.335275: step: 1072/530, loss: 0.0011111260391771793
2023-01-23 03:40:23.429708: step: 1076/530, loss: 0.0002441972610540688
2023-01-23 03:40:24.513514: step: 1080/530, loss: 3.814697606685513e-07
2023-01-23 03:40:25.618300: step: 1084/530, loss: 0.0008270263788290322
2023-01-23 03:40:26.736525: step: 1088/530, loss: 0.001354217529296875
2023-01-23 03:40:27.896082: step: 1092/530, loss: 0.0005074500804767013
2023-01-23 03:40:28.980152: step: 1096/530, loss: 0.003538703778758645
2023-01-23 03:40:30.104386: step: 1100/530, loss: 0.014377403073012829
2023-01-23 03:40:31.213458: step: 1104/530, loss: 2.746581958490424e-05
2023-01-23 03:40:32.305091: step: 1108/530, loss: 0.007102012634277344
2023-01-23 03:40:33.444998: step: 1112/530, loss: 0.02230844646692276
2023-01-23 03:40:34.536401: step: 1116/530, loss: 2.1457672119140625e-05
2023-01-23 03:40:35.619316: step: 1120/530, loss: 0.0001049041748046875
2023-01-23 03:40:36.739877: step: 1124/530, loss: 1.9550323486328125e-05
2023-01-23 03:40:37.869385: step: 1128/530, loss: 0.09099344909191132
2023-01-23 03:40:38.978996: step: 1132/530, loss: 0.005656624212861061
2023-01-23 03:40:40.085236: step: 1136/530, loss: 0.004279041197150946
2023-01-23 03:40:41.236362: step: 1140/530, loss: 0.0001928329438669607
2023-01-23 03:40:42.338354: step: 1144/530, loss: 0.015855886042118073
2023-01-23 03:40:43.455341: step: 1148/530, loss: 0.00024585722712799907
2023-01-23 03:40:44.574614: step: 1152/530, loss: 5.6934361055027694e-05
2023-01-23 03:40:45.672334: step: 1156/530, loss: 0.0002584934118203819
2023-01-23 03:40:46.764527: step: 1160/530, loss: 1.9645693100756034e-05
2023-01-23 03:40:47.875423: step: 1164/530, loss: 0.00010290146747138351
2023-01-23 03:40:48.975740: step: 1168/530, loss: 0.09521675109863281
2023-01-23 03:40:50.105664: step: 1172/530, loss: 0.0002265930233988911
2023-01-23 03:40:51.264802: step: 1176/530, loss: 0.0049988748505711555
2023-01-23 03:40:52.398513: step: 1180/530, loss: 0.019220924004912376
2023-01-23 03:40:53.549135: step: 1184/530, loss: 0.000446319580078125
2023-01-23 03:40:54.678132: step: 1188/530, loss: 0.001766967703588307
2023-01-23 03:40:55.843487: step: 1192/530, loss: 0.008145619183778763
2023-01-23 03:40:56.932387: step: 1196/530, loss: 0.0037691115867346525
2023-01-23 03:40:58.020666: step: 1200/530, loss: 0.00022182465181685984
2023-01-23 03:40:59.115458: step: 1204/530, loss: 0.0003319740353617817
2023-01-23 03:41:00.231249: step: 1208/530, loss: 0.0008969306945800781
2023-01-23 03:41:01.358491: step: 1212/530, loss: 3.185272362316027e-05
2023-01-23 03:41:02.451962: step: 1216/530, loss: 0.0006044387700967491
2023-01-23 03:41:03.584680: step: 1220/530, loss: 0.005807018373161554
2023-01-23 03:41:04.688932: step: 1224/530, loss: 0.002032899996265769
2023-01-23 03:41:05.809134: step: 1228/530, loss: 0.003013229463249445
2023-01-23 03:41:06.944895: step: 1232/530, loss: 0.0010243416763842106
2023-01-23 03:41:08.054987: step: 1236/530, loss: 0.0004020213964395225
2023-01-23 03:41:09.167119: step: 1240/530, loss: 0.00019035338482353836
2023-01-23 03:41:10.287806: step: 1244/530, loss: 7.667541649425402e-05
2023-01-23 03:41:11.388272: step: 1248/530, loss: 5.340576535672881e-06
2023-01-23 03:41:12.482718: step: 1252/530, loss: 0.38790231943130493
2023-01-23 03:41:13.609690: step: 1256/530, loss: 0.050110626965761185
2023-01-23 03:41:14.753138: step: 1260/530, loss: 0.023627936840057373
2023-01-23 03:41:15.891890: step: 1264/530, loss: 0.7670993804931641
2023-01-23 03:41:17.043799: step: 1268/530, loss: 0.004557418636977673
2023-01-23 03:41:18.143021: step: 1272/530, loss: 0.0012234688038006425
2023-01-23 03:41:19.258871: step: 1276/530, loss: 0.022089004516601562
2023-01-23 03:41:20.367214: step: 1280/530, loss: 0.003429317381232977
2023-01-23 03:41:21.445627: step: 1284/530, loss: 0.0007022857898846269
2023-01-23 03:41:22.579918: step: 1288/530, loss: 0.009295462630689144
2023-01-23 03:41:23.676967: step: 1292/530, loss: 1.859665098891128e-05
2023-01-23 03:41:24.793413: step: 1296/530, loss: 0.016332531347870827
2023-01-23 03:41:25.895172: step: 1300/530, loss: -1.287460349885805e-06
2023-01-23 03:41:27.010725: step: 1304/530, loss: 0.002175808185711503
2023-01-23 03:41:28.123011: step: 1308/530, loss: 0.0217437744140625
2023-01-23 03:41:29.238364: step: 1312/530, loss: 0.02145233191549778
2023-01-23 03:41:30.336475: step: 1316/530, loss: 0.005115890875458717
2023-01-23 03:41:31.467520: step: 1320/530, loss: 1.220703143189894e-05
2023-01-23 03:41:32.560470: step: 1324/530, loss: 0.00405197124928236
2023-01-23 03:41:33.678310: step: 1328/530, loss: 0.0015566349029541016
2023-01-23 03:41:34.802275: step: 1332/530, loss: 0.0002992630179505795
2023-01-23 03:41:35.924852: step: 1336/530, loss: 0.05089912563562393
2023-01-23 03:41:37.052946: step: 1340/530, loss: 0.0034837722778320312
2023-01-23 03:41:38.193823: step: 1344/530, loss: 0.09760265797376633
2023-01-23 03:41:39.301499: step: 1348/530, loss: 0.0007250786293298006
2023-01-23 03:41:40.403467: step: 1352/530, loss: 0.052616216242313385
2023-01-23 03:41:41.526771: step: 1356/530, loss: 0.015094185248017311
2023-01-23 03:41:42.636805: step: 1360/530, loss: 8.144378807628527e-05
2023-01-23 03:41:43.736140: step: 1364/530, loss: 8.392333984375e-05
2023-01-23 03:41:44.829847: step: 1368/530, loss: 0.22115115821361542
2023-01-23 03:41:45.940005: step: 1372/530, loss: 0.025307562202215195
2023-01-23 03:41:47.044452: step: 1376/530, loss: 0.024248123168945312
2023-01-23 03:41:48.145866: step: 1380/530, loss: 0.02683706395328045
2023-01-23 03:41:49.297014: step: 1384/530, loss: 0.014273738488554955
2023-01-23 03:41:50.398354: step: 1388/530, loss: 0.015970801934599876
2023-01-23 03:41:51.503350: step: 1392/530, loss: 0.021416664123535156
2023-01-23 03:41:52.613803: step: 1396/530, loss: 0.03747883066534996
2023-01-23 03:41:53.739225: step: 1400/530, loss: 2.403259350103326e-05
2023-01-23 03:41:54.838347: step: 1404/530, loss: 0.069361113011837
2023-01-23 03:41:55.916925: step: 1408/530, loss: 0.0010403634514659643
2023-01-23 03:41:57.032210: step: 1412/530, loss: 0.0036463739816099405
2023-01-23 03:41:58.132373: step: 1416/530, loss: 0.00032005307730287313
2023-01-23 03:41:59.238071: step: 1420/530, loss: 0.016077041625976562
2023-01-23 03:42:00.369978: step: 1424/530, loss: 0.06343209743499756
2023-01-23 03:42:01.478511: step: 1428/530, loss: 0.02687687799334526
2023-01-23 03:42:02.567593: step: 1432/530, loss: 0.0008306503877975047
2023-01-23 03:42:03.694237: step: 1436/530, loss: 0.00041537283686921
2023-01-23 03:42:04.844139: step: 1440/530, loss: 0.0008162021404132247
2023-01-23 03:42:05.971245: step: 1444/530, loss: 5.8460234868107364e-05
2023-01-23 03:42:07.066440: step: 1448/530, loss: 0.001305532525293529
2023-01-23 03:42:08.163091: step: 1452/530, loss: 0.008279371075332165
2023-01-23 03:42:09.258646: step: 1456/530, loss: 0.0005608558421954513
2023-01-23 03:42:10.331318: step: 1460/530, loss: 0.0015186310047283769
2023-01-23 03:42:11.420544: step: 1464/530, loss: 0.002937126439064741
2023-01-23 03:42:12.520384: step: 1468/530, loss: 0.008966874331235886
2023-01-23 03:42:13.628840: step: 1472/530, loss: 0.0007056236499920487
2023-01-23 03:42:14.755505: step: 1476/530, loss: 0.03482925891876221
2023-01-23 03:42:15.843123: step: 1480/530, loss: 0.03040785901248455
2023-01-23 03:42:16.943598: step: 1484/530, loss: 0.0003125190851278603
2023-01-23 03:42:18.074479: step: 1488/530, loss: 0.13238820433616638
2023-01-23 03:42:19.192824: step: 1492/530, loss: 0.0005943774594925344
2023-01-23 03:42:20.315984: step: 1496/530, loss: 0.20336304605007172
2023-01-23 03:42:21.447055: step: 1500/530, loss: 0.010007238015532494
2023-01-23 03:42:22.527631: step: 1504/530, loss: 0.0001773834228515625
2023-01-23 03:42:23.636611: step: 1508/530, loss: 0.00023865699768066406
2023-01-23 03:42:24.788237: step: 1512/530, loss: 0.0029567719902843237
2023-01-23 03:42:25.894684: step: 1516/530, loss: 0.2214791178703308
2023-01-23 03:42:27.002451: step: 1520/530, loss: 0.016840552911162376
2023-01-23 03:42:28.099072: step: 1524/530, loss: 0.0015007973415777087
2023-01-23 03:42:29.203579: step: 1528/530, loss: 3.490447852527723e-05
2023-01-23 03:42:30.299718: step: 1532/530, loss: 0.0037677527870982885
2023-01-23 03:42:31.396718: step: 1536/530, loss: 0.005546760745346546
2023-01-23 03:42:32.480910: step: 1540/530, loss: 0.0004440307675395161
2023-01-23 03:42:33.574692: step: 1544/530, loss: 0.0040573119185864925
2023-01-23 03:42:34.685272: step: 1548/530, loss: 0.00013656617375090718
2023-01-23 03:42:35.794910: step: 1552/530, loss: 0.03892365097999573
2023-01-23 03:42:36.935171: step: 1556/530, loss: 3.452301098150201e-05
2023-01-23 03:42:38.013515: step: 1560/530, loss: 9.608268737792969e-05
2023-01-23 03:42:39.136298: step: 1564/530, loss: 0.0007122039678506553
2023-01-23 03:42:40.238460: step: 1568/530, loss: 0.004614353179931641
2023-01-23 03:42:41.367972: step: 1572/530, loss: 0.004091453738510609
2023-01-23 03:42:42.512453: step: 1576/530, loss: 0.003056049346923828
2023-01-23 03:42:43.706986: step: 1580/530, loss: 6.103515261202119e-06
2023-01-23 03:42:44.831618: step: 1584/530, loss: 2.1743775505456142e-05
2023-01-23 03:42:45.933235: step: 1588/530, loss: 0.012013768777251244
2023-01-23 03:42:47.062594: step: 1592/530, loss: 0.0006466865306720138
2023-01-23 03:42:48.157119: step: 1596/530, loss: 0.0014451980823650956
2023-01-23 03:42:49.281363: step: 1600/530, loss: 0.1019367203116417
2023-01-23 03:42:50.446334: step: 1604/530, loss: 0.10819997638463974
2023-01-23 03:42:51.551626: step: 1608/530, loss: 0.00867385882884264
2023-01-23 03:42:52.664075: step: 1612/530, loss: 0.004678917117416859
2023-01-23 03:42:53.732227: step: 1616/530, loss: 1.888275073724799e-05
2023-01-23 03:42:54.863288: step: 1620/530, loss: 0.013427353464066982
2023-01-23 03:42:55.975798: step: 1624/530, loss: 0.010287332348525524
2023-01-23 03:42:57.067752: step: 1628/530, loss: 0.13267642259597778
2023-01-23 03:42:58.191173: step: 1632/530, loss: 0.027617646381258965
2023-01-23 03:42:59.289435: step: 1636/530, loss: 0.00013790131197310984
2023-01-23 03:43:00.403975: step: 1640/530, loss: 0.0011988639598712325
2023-01-23 03:43:01.495246: step: 1644/530, loss: 0.018183326348662376
2023-01-23 03:43:02.611107: step: 1648/530, loss: 0.048110101372003555
2023-01-23 03:43:03.696538: step: 1652/530, loss: 0.000493896019179374
2023-01-23 03:43:04.802719: step: 1656/530, loss: 2.7179718017578125e-05
2023-01-23 03:43:05.923004: step: 1660/530, loss: 2.765655608527595e-06
2023-01-23 03:43:07.017858: step: 1664/530, loss: 5.798339770990424e-05
2023-01-23 03:43:08.096443: step: 1668/530, loss: 0.00041427614632993937
2023-01-23 03:43:09.180312: step: 1672/530, loss: 0.005241870880126953
2023-01-23 03:43:10.269166: step: 1676/530, loss: 0.003254890674725175
2023-01-23 03:43:11.408003: step: 1680/530, loss: 0.006860780529677868
2023-01-23 03:43:12.516656: step: 1684/530, loss: 0.0004207611200399697
2023-01-23 03:43:13.620183: step: 1688/530, loss: 5.440712266135961e-05
2023-01-23 03:43:14.744239: step: 1692/530, loss: 0.0016813278198242188
2023-01-23 03:43:15.807665: step: 1696/530, loss: 0.00386390695348382
2023-01-23 03:43:16.889494: step: 1700/530, loss: 0.0019323349697515368
2023-01-23 03:43:18.005545: step: 1704/530, loss: 0.0003498554287943989
2023-01-23 03:43:19.119974: step: 1708/530, loss: 0.003450918011367321
2023-01-23 03:43:20.215400: step: 1712/530, loss: 0.0006682396051473916
2023-01-23 03:43:21.288138: step: 1716/530, loss: 0.0030312538146972656
2023-01-23 03:43:22.387230: step: 1720/530, loss: 0.004015827085822821
2023-01-23 03:43:23.511084: step: 1724/530, loss: 0.00018043517775367945
2023-01-23 03:43:24.600377: step: 1728/530, loss: 0.0027051924262195826
2023-01-23 03:43:25.699954: step: 1732/530, loss: 0.019979191944003105
2023-01-23 03:43:26.833474: step: 1736/530, loss: 0.0014423370594158769
2023-01-23 03:43:27.970253: step: 1740/530, loss: 0.013526344671845436
2023-01-23 03:43:29.078119: step: 1744/530, loss: 0.020875215530395508
2023-01-23 03:43:30.177373: step: 1748/530, loss: 0.009434891864657402
2023-01-23 03:43:31.289668: step: 1752/530, loss: 0.008918190374970436
2023-01-23 03:43:32.396392: step: 1756/530, loss: 0.0020404814276844263
2023-01-23 03:43:33.500989: step: 1760/530, loss: 0.00026407241239212453
2023-01-23 03:43:34.594449: step: 1764/530, loss: -1.1539459592313506e-05
2023-01-23 03:43:35.668935: step: 1768/530, loss: 0.0017778397304937243
2023-01-23 03:43:36.760823: step: 1772/530, loss: 0.0024145126808434725
2023-01-23 03:43:37.884934: step: 1776/530, loss: 0.017945481464266777
2023-01-23 03:43:38.985814: step: 1780/530, loss: 0.001502609346061945
2023-01-23 03:43:40.093299: step: 1784/530, loss: 0.02790260501205921
2023-01-23 03:43:41.197164: step: 1788/530, loss: 0.00025262832059524953
2023-01-23 03:43:42.292792: step: 1792/530, loss: 0.014989947900176048
2023-01-23 03:43:43.381919: step: 1796/530, loss: 0.0025745390448719263
2023-01-23 03:43:44.490502: step: 1800/530, loss: 0.020673513412475586
2023-01-23 03:43:45.615467: step: 1804/530, loss: -3.862381163344253e-06
2023-01-23 03:43:46.770223: step: 1808/530, loss: 0.010018253698945045
2023-01-23 03:43:47.893865: step: 1812/530, loss: 0.30904483795166016
2023-01-23 03:43:48.997330: step: 1816/530, loss: 0.002582025481387973
2023-01-23 03:43:50.097494: step: 1820/530, loss: 5.896091170143336e-05
2023-01-23 03:43:51.185713: step: 1824/530, loss: 0.007372856140136719
2023-01-23 03:43:52.286240: step: 1828/530, loss: 0.015140152536332607
2023-01-23 03:43:53.381922: step: 1832/530, loss: 0.00011768341209972277
2023-01-23 03:43:54.476276: step: 1836/530, loss: 0.0006092071416787803
2023-01-23 03:43:55.578460: step: 1840/530, loss: 0.003922748379409313
2023-01-23 03:43:56.724676: step: 1844/530, loss: 0.003601646516472101
2023-01-23 03:43:57.808113: step: 1848/530, loss: 0.0008712768321856856
2023-01-23 03:43:58.920264: step: 1852/530, loss: 0.022364426404237747
2023-01-23 03:44:00.041371: step: 1856/530, loss: 0.011196423321962357
2023-01-23 03:44:01.127259: step: 1860/530, loss: 0.005649459548294544
2023-01-23 03:44:02.231579: step: 1864/530, loss: 0.0013299465645104647
2023-01-23 03:44:03.316955: step: 1868/530, loss: 0.008362484164536
2023-01-23 03:44:04.417828: step: 1872/530, loss: 3.24249267578125e-05
2023-01-23 03:44:05.522012: step: 1876/530, loss: 0.0039099217392504215
2023-01-23 03:44:06.630365: step: 1880/530, loss: 0.0012866973411291838
2023-01-23 03:44:07.733651: step: 1884/530, loss: 0.016264427453279495
2023-01-23 03:44:08.841676: step: 1888/530, loss: 0.0229464303702116
2023-01-23 03:44:09.939339: step: 1892/530, loss: 0.005539989564567804
2023-01-23 03:44:11.039741: step: 1896/530, loss: 0.0005311965942382812
2023-01-23 03:44:12.127307: step: 1900/530, loss: 0.02552509307861328
2023-01-23 03:44:13.226604: step: 1904/530, loss: 1.7070769899873994e-05
2023-01-23 03:44:14.356630: step: 1908/530, loss: 6.923676119185984e-05
2023-01-23 03:44:15.434988: step: 1912/530, loss: 0.0014566421741619706
2023-01-23 03:44:16.524964: step: 1916/530, loss: 0.01744053326547146
2023-01-23 03:44:17.618479: step: 1920/530, loss: 0.00016689300537109375
2023-01-23 03:44:18.744484: step: 1924/530, loss: 0.0012124062050133944
2023-01-23 03:44:19.853023: step: 1928/530, loss: -2.1457671550706436e-07
2023-01-23 03:44:20.927228: step: 1932/530, loss: 5.14984139954322e-06
2023-01-23 03:44:22.027096: step: 1936/530, loss: 0.0009291649330407381
2023-01-23 03:44:23.147893: step: 1940/530, loss: 8.559226989746094e-05
2023-01-23 03:44:24.258305: step: 1944/530, loss: 0.010659217834472656
2023-01-23 03:44:25.354187: step: 1948/530, loss: 0.02501850016415119
2023-01-23 03:44:26.432076: step: 1952/530, loss: 0.07284589111804962
2023-01-23 03:44:27.546479: step: 1956/530, loss: 0.04702110216021538
2023-01-23 03:44:28.672856: step: 1960/530, loss: 0.0007806778303347528
2023-01-23 03:44:29.762837: step: 1964/530, loss: 0.0013385772472247481
2023-01-23 03:44:30.879939: step: 1968/530, loss: 0.04651908949017525
2023-01-23 03:44:31.984114: step: 1972/530, loss: 0.017020607367157936
2023-01-23 03:44:33.078191: step: 1976/530, loss: 0.00768203753978014
2023-01-23 03:44:34.169854: step: 1980/530, loss: 1.316070574830519e-05
2023-01-23 03:44:35.273688: step: 1984/530, loss: 0.056861210614442825
2023-01-23 03:44:36.380930: step: 1988/530, loss: 0.012256050482392311
2023-01-23 03:44:37.450747: step: 1992/530, loss: 0.005224514286965132
2023-01-23 03:44:38.569369: step: 1996/530, loss: 4.425048973644152e-05
2023-01-23 03:44:39.695912: step: 2000/530, loss: 0.0013729095226153731
2023-01-23 03:44:40.810802: step: 2004/530, loss: 0.07634048163890839
2023-01-23 03:44:41.937468: step: 2008/530, loss: 0.004924201872199774
2023-01-23 03:44:43.080686: step: 2012/530, loss: 0.001954364823177457
2023-01-23 03:44:44.171829: step: 2016/530, loss: 0.032430462539196014
2023-01-23 03:44:45.278279: step: 2020/530, loss: 0.014415168203413486
2023-01-23 03:44:46.396707: step: 2024/530, loss: 0.00013661386037711054
2023-01-23 03:44:47.493565: step: 2028/530, loss: 0.007250738330185413
2023-01-23 03:44:48.602646: step: 2032/530, loss: 0.007100057788193226
2023-01-23 03:44:49.721267: step: 2036/530, loss: 0.001987457275390625
2023-01-23 03:44:50.810285: step: 2040/530, loss: 0.010371637530624866
2023-01-23 03:44:51.915798: step: 2044/530, loss: 0.0006251335144042969
2023-01-23 03:44:53.048548: step: 2048/530, loss: 0.0031387328635901213
2023-01-23 03:44:54.171602: step: 2052/530, loss: 0.002663898514583707
2023-01-23 03:44:55.265811: step: 2056/530, loss: 0.00012474060349632055
2023-01-23 03:44:56.381671: step: 2060/530, loss: 1.8167496818932705e-05
2023-01-23 03:44:57.495214: step: 2064/530, loss: 0.062425803393125534
2023-01-23 03:44:58.597598: step: 2068/530, loss: 0.0004299640713725239
2023-01-23 03:44:59.737340: step: 2072/530, loss: 0.0001733779936330393
2023-01-23 03:45:00.840674: step: 2076/530, loss: 0.20610304176807404
2023-01-23 03:45:01.916557: step: 2080/530, loss: 0.00035429003764875233
2023-01-23 03:45:03.014582: step: 2084/530, loss: 0.00011205673217773438
2023-01-23 03:45:04.107496: step: 2088/530, loss: 4.38690176451928e-06
2023-01-23 03:45:05.239473: step: 2092/530, loss: 0.006417274475097656
2023-01-23 03:45:06.353017: step: 2096/530, loss: 7.858276512706652e-05
2023-01-23 03:45:07.458084: step: 2100/530, loss: 6.570815457962453e-05
2023-01-23 03:45:08.556472: step: 2104/530, loss: 0.06294260174036026
2023-01-23 03:45:09.644711: step: 2108/530, loss: 0.0017305852379649878
2023-01-23 03:45:10.758047: step: 2112/530, loss: 2.19345088225964e-06
2023-01-23 03:45:11.876212: step: 2116/530, loss: 0.00017070770263671875
2023-01-23 03:45:12.959099: step: 2120/530, loss: 0.0006749153253622353
==================================================
Loss: 0.018
--------------------
Dev: {'event': {'p': 0.5895061728395061, 'r': 0.762982689747004, 'f1': 0.665118978525827}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 24}
Test: {'event': {'p': 0.6339779005524862, 'r': 0.8024475524475524, 'f1': 0.7083333333333333}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 24}
Chinese: {'event': {'p': 0.5866666666666667, 'r': 0.8148148148148148, 'f1': 0.6821705426356589}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 24}
Korean: {'event': {'p': 0.6724137931034483, 'r': 0.6190476190476191, 'f1': 0.6446280991735537}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 24}
Russian: {'event': {'p': 0.48717948717948717, 'r': 0.5277777777777778, 'f1': 0.5066666666666667}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 24}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6449771689497716, 'r': 0.7523302263648469, 'f1': 0.6945298094652735}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Chinese: {'event': {'p': 0.6692644909887969, 'r': 0.8006993006993007, 'f1': 0.7291058636243036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Chinese: {'event': {'p': 0.6764705882352942, 'r': 0.8518518518518519, 'f1': 0.7540983606557378}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5873340143003064, 'r': 0.7656458055925432, 'f1': 0.6647398843930636}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Eng Test for Korean: {'event': {'p': 0.6496487119437939, 'r': 0.8082750582750583, 'f1': 0.7203323811996885}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Sample Korean: {'event': {'p': 0.6721311475409836, 'r': 0.6507936507936508, 'f1': 0.6612903225806451}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5971370143149284, 'r': 0.7776298268974701, 'f1': 0.6755349913244649}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Russian: {'event': {'p': 0.6401673640167364, 'r': 0.8024475524475524, 'f1': 0.7121799844840963}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Russian: {'event': {'p': 0.5897435897435898, 'r': 0.6388888888888888, 'f1': 0.6133333333333332}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
******************************
Epoch: 25
command: python train.py --model_name trg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --event_hidden_num 450 --accumulate_step 4 --max_epoch 30 --p1_data_weight 0.1 --learning_rate 6e-4
2023-01-23 03:45:52.265566: step: 4/530, loss: 0.04722995683550835
2023-01-23 03:45:53.362038: step: 8/530, loss: 0.006507301237434149
2023-01-23 03:45:54.455864: step: 12/530, loss: 0.005153465084731579
2023-01-23 03:45:55.550479: step: 16/530, loss: 7.3432925091765355e-06
2023-01-23 03:45:56.623526: step: 20/530, loss: 0.002524948213249445
2023-01-23 03:45:57.743307: step: 24/530, loss: 0.002706432482227683
2023-01-23 03:45:58.870109: step: 28/530, loss: -1.9073486328125e-06
2023-01-23 03:45:59.975931: step: 32/530, loss: 0.000759983086027205
2023-01-23 03:46:01.107392: step: 36/530, loss: 0.011025046929717064
2023-01-23 03:46:02.256042: step: 40/530, loss: 0.007126999087631702
2023-01-23 03:46:03.320672: step: 44/530, loss: 0.025605248287320137
2023-01-23 03:46:04.411617: step: 48/530, loss: 2.956390380859375e-05
2023-01-23 03:46:05.535017: step: 52/530, loss: 0.00011057854135287926
2023-01-23 03:46:06.650248: step: 56/530, loss: 0.0008554935920983553
2023-01-23 03:46:07.756346: step: 60/530, loss: 0.0004230499325785786
2023-01-23 03:46:08.873344: step: 64/530, loss: 2.4509430659236386e-05
2023-01-23 03:46:09.954683: step: 68/530, loss: 1.9550323486328125e-05
2023-01-23 03:46:11.067651: step: 72/530, loss: 0.0012712478637695312
2023-01-23 03:46:12.161563: step: 76/530, loss: 0.03780489042401314
2023-01-23 03:46:13.270951: step: 80/530, loss: 5.2642819355241954e-05
2023-01-23 03:46:14.380559: step: 84/530, loss: 0.00014801025099586695
2023-01-23 03:46:15.575153: step: 88/530, loss: 1.4686585927847773e-05
2023-01-23 03:46:16.654853: step: 92/530, loss: 0.0014385223621502519
2023-01-23 03:46:17.791048: step: 96/530, loss: 0.1341615617275238
2023-01-23 03:46:18.884832: step: 100/530, loss: 0.004081153776496649
2023-01-23 03:46:20.015678: step: 104/530, loss: 8.831024024402723e-05
2023-01-23 03:46:21.104564: step: 108/530, loss: 1.5544892448815517e-05
2023-01-23 03:46:22.216402: step: 112/530, loss: 0.004470634739845991
2023-01-23 03:46:23.298382: step: 116/530, loss: 4.911422365694307e-06
2023-01-23 03:46:24.398036: step: 120/530, loss: 0.000492095947265625
2023-01-23 03:46:25.514419: step: 124/530, loss: 0.0008932590717449784
2023-01-23 03:46:26.608521: step: 128/530, loss: 0.0006298065418377519
2023-01-23 03:46:27.702399: step: 132/530, loss: 1.0824203855008818e-05
2023-01-23 03:46:28.800858: step: 136/530, loss: 0.00033168791560456157
2023-01-23 03:46:29.893803: step: 140/530, loss: 0.0001293182431254536
2023-01-23 03:46:30.988250: step: 144/530, loss: 0.00031270983163267374
2023-01-23 03:46:32.094855: step: 148/530, loss: 0.0004245758173055947
2023-01-23 03:46:33.215509: step: 152/530, loss: 5.207061622058973e-05
2023-01-23 03:46:34.311246: step: 156/530, loss: 0.004668140783905983
2023-01-23 03:46:35.406409: step: 160/530, loss: 0.0001549005537526682
2023-01-23 03:46:36.502627: step: 164/530, loss: 0.026813507080078125
2023-01-23 03:46:37.632991: step: 168/530, loss: 5.817413330078125e-05
2023-01-23 03:46:38.753376: step: 172/530, loss: 0.004975604824721813
2023-01-23 03:46:39.865722: step: 176/530, loss: 0.010276603512465954
2023-01-23 03:46:40.974132: step: 180/530, loss: 0.0337039977312088
2023-01-23 03:46:42.057723: step: 184/530, loss: 0.007909965701401234
2023-01-23 03:46:43.147720: step: 188/530, loss: 0.013691998086869717
2023-01-23 03:46:44.252516: step: 192/530, loss: 0.046692658215761185
2023-01-23 03:46:45.362179: step: 196/530, loss: 4.39643845311366e-05
2023-01-23 03:46:46.450111: step: 200/530, loss: 0.0009597778553143144
2023-01-23 03:46:47.564003: step: 204/530, loss: 0.08455977588891983
2023-01-23 03:46:48.640533: step: 208/530, loss: 0.007660388946533203
2023-01-23 03:46:49.741205: step: 212/530, loss: 0.0005658150184899569
2023-01-23 03:46:50.822987: step: 216/530, loss: 0.0011463165283203125
2023-01-23 03:46:51.927031: step: 220/530, loss: 0.02997284010052681
2023-01-23 03:46:53.026191: step: 224/530, loss: 7.772445314913057e-06
2023-01-23 03:46:54.133970: step: 228/530, loss: 0.023921657353639603
2023-01-23 03:46:55.260616: step: 232/530, loss: 0.0005196809652261436
2023-01-23 03:46:56.348686: step: 236/530, loss: 0.0006315231439657509
2023-01-23 03:46:57.442584: step: 240/530, loss: 0.016075754538178444
2023-01-23 03:46:58.533517: step: 244/530, loss: 0.0009379386901855469
2023-01-23 03:46:59.608027: step: 248/530, loss: 0.008540726266801357
2023-01-23 03:47:00.710430: step: 252/530, loss: 0.00045261383638717234
2023-01-23 03:47:01.833234: step: 256/530, loss: 0.01786184310913086
2023-01-23 03:47:02.943648: step: 260/530, loss: 0.003457355545833707
2023-01-23 03:47:04.027430: step: 264/530, loss: 0.00020170211791992188
2023-01-23 03:47:05.102530: step: 268/530, loss: 0.0003158569452352822
2023-01-23 03:47:06.216327: step: 272/530, loss: 0.006680727005004883
2023-01-23 03:47:07.326889: step: 276/530, loss: 0.0005456925136968493
2023-01-23 03:47:08.433696: step: 280/530, loss: 0.00037136077298782766
2023-01-23 03:47:09.568843: step: 284/530, loss: 0.01712055318057537
2023-01-23 03:47:10.658044: step: 288/530, loss: 0.0004516601620707661
2023-01-23 03:47:11.740434: step: 292/530, loss: 0.0009038925636559725
2023-01-23 03:47:12.836264: step: 296/530, loss: 0.018912507221102715
2023-01-23 03:47:13.937081: step: 300/530, loss: 0.001996851060539484
2023-01-23 03:47:15.059524: step: 304/530, loss: 0.0004201889387331903
2023-01-23 03:47:16.154020: step: 308/530, loss: 0.00010566711716819555
2023-01-23 03:47:17.266740: step: 312/530, loss: 2.0503997802734375e-05
2023-01-23 03:47:18.393994: step: 316/530, loss: 0.0006224632379598916
2023-01-23 03:47:19.550863: step: 320/530, loss: 0.00022068023099564016
2023-01-23 03:47:20.648847: step: 324/530, loss: 0.07869367301464081
2023-01-23 03:47:21.750564: step: 328/530, loss: 0.004807138349860907
2023-01-23 03:47:22.826740: step: 332/530, loss: 0.0005497932434082031
2023-01-23 03:47:23.925143: step: 336/530, loss: 0.0018842697609215975
2023-01-23 03:47:25.029095: step: 340/530, loss: 0.0012351989280432463
2023-01-23 03:47:26.150725: step: 344/530, loss: 0.01212768629193306
2023-01-23 03:47:27.281697: step: 348/530, loss: 0.00291271205060184
2023-01-23 03:47:28.393925: step: 352/530, loss: 0.0009590148692950606
2023-01-23 03:47:29.515137: step: 356/530, loss: 0.0005356550100259483
2023-01-23 03:47:30.628808: step: 360/530, loss: 0.00011124611046398059
2023-01-23 03:47:31.716375: step: 364/530, loss: 0.0003190040588378906
2023-01-23 03:47:32.828578: step: 368/530, loss: 0.0028252601623535156
2023-01-23 03:47:33.956693: step: 372/530, loss: 7.576942152809352e-05
2023-01-23 03:47:35.076461: step: 376/530, loss: 0.0014024734264239669
2023-01-23 03:47:36.189971: step: 380/530, loss: 0.0031455992721021175
2023-01-23 03:47:37.289458: step: 384/530, loss: 0.00014061927504371852
2023-01-23 03:47:38.403478: step: 388/530, loss: 0.013525962829589844
2023-01-23 03:47:39.516710: step: 392/530, loss: -1.0490416570974048e-06
2023-01-23 03:47:40.619130: step: 396/530, loss: 0.554465115070343
2023-01-23 03:47:41.724063: step: 400/530, loss: 0.0021772384643554688
2023-01-23 03:47:42.871437: step: 404/530, loss: 5.807876732433215e-05
2023-01-23 03:47:43.989156: step: 408/530, loss: 0.0012197494506835938
2023-01-23 03:47:45.086415: step: 412/530, loss: 0.003692054655402899
2023-01-23 03:47:46.179760: step: 416/530, loss: -1.9073468138230965e-07
2023-01-23 03:47:47.254267: step: 420/530, loss: 0.01598997227847576
2023-01-23 03:47:48.341914: step: 424/530, loss: 0.0017528533935546875
2023-01-23 03:47:49.453637: step: 428/530, loss: 0.004490375518798828
2023-01-23 03:47:50.558506: step: 432/530, loss: 0.005492687691003084
2023-01-23 03:47:51.665923: step: 436/530, loss: 0.05463390424847603
2023-01-23 03:47:52.767376: step: 440/530, loss: 0.0016963958041742444
2023-01-23 03:47:53.843676: step: 444/530, loss: 0.0006232261657714844
2023-01-23 03:47:54.955097: step: 448/530, loss: 0.0022510529961436987
2023-01-23 03:47:56.046924: step: 452/530, loss: 0.025351429358124733
2023-01-23 03:47:57.126154: step: 456/530, loss: 0.00013446807861328125
2023-01-23 03:47:58.270450: step: 460/530, loss: 0.013764476403594017
2023-01-23 03:47:59.361389: step: 464/530, loss: 0.00011339187767589465
2023-01-23 03:48:00.470428: step: 468/530, loss: 0.0009132385021075606
2023-01-23 03:48:01.574776: step: 472/530, loss: 0.00017576217942405492
2023-01-23 03:48:02.687534: step: 476/530, loss: 0.04987630620598793
2023-01-23 03:48:03.776271: step: 480/530, loss: 0.02460164949297905
2023-01-23 03:48:04.847843: step: 484/530, loss: 1.6355514162569307e-05
2023-01-23 03:48:05.947783: step: 488/530, loss: 0.02014312706887722
2023-01-23 03:48:07.060998: step: 492/530, loss: 0.0007257461547851562
2023-01-23 03:48:08.175718: step: 496/530, loss: 0.00020144581503700465
2023-01-23 03:48:09.288430: step: 500/530, loss: 0.0008329391130246222
2023-01-23 03:48:10.342436: step: 504/530, loss: 0.00021848677715752274
2023-01-23 03:48:11.464755: step: 508/530, loss: 0.0016999244689941406
2023-01-23 03:48:12.563138: step: 512/530, loss: 0.0022586823906749487
2023-01-23 03:48:13.644085: step: 516/530, loss: 2.8038026357535273e-05
2023-01-23 03:48:14.729961: step: 520/530, loss: 5.998611595714465e-05
2023-01-23 03:48:15.836117: step: 524/530, loss: 0.0001143455519923009
2023-01-23 03:48:16.983022: step: 528/530, loss: 0.004932880867272615
2023-01-23 03:48:18.129758: step: 532/530, loss: 0.020798780024051666
2023-01-23 03:48:19.251092: step: 536/530, loss: 0.009405707940459251
2023-01-23 03:48:20.353103: step: 540/530, loss: 0.010867644101381302
2023-01-23 03:48:21.481022: step: 544/530, loss: 0.007351684849709272
2023-01-23 03:48:22.607133: step: 548/530, loss: 0.0003692626778502017
2023-01-23 03:48:23.761329: step: 552/530, loss: 0.014289951883256435
2023-01-23 03:48:24.854737: step: 556/530, loss: 0.0012221335200592875
2023-01-23 03:48:25.971215: step: 560/530, loss: 0.004057884216308594
2023-01-23 03:48:27.098815: step: 564/530, loss: 0.02413156069815159
2023-01-23 03:48:28.213719: step: 568/530, loss: 0.0004905700916424394
2023-01-23 03:48:29.303082: step: 572/530, loss: 0.0001739501894917339
2023-01-23 03:48:30.390469: step: 576/530, loss: 0.002389621688053012
2023-01-23 03:48:31.474533: step: 580/530, loss: 0.0016176224453374743
2023-01-23 03:48:32.574221: step: 584/530, loss: 0.03457632288336754
2023-01-23 03:48:33.698801: step: 588/530, loss: 0.0020925523713231087
2023-01-23 03:48:34.777441: step: 592/530, loss: 3.337860107421875e-06
2023-01-23 03:48:35.881350: step: 596/530, loss: 7.638931856490672e-05
2023-01-23 03:48:36.977821: step: 600/530, loss: 0.037329718470573425
2023-01-23 03:48:38.086277: step: 604/530, loss: 0.0004299640713725239
2023-01-23 03:48:39.205916: step: 608/530, loss: 0.0006592273712158203
2023-01-23 03:48:40.323306: step: 612/530, loss: 0.0005601883167400956
2023-01-23 03:48:41.413863: step: 616/530, loss: 0.035027313977479935
2023-01-23 03:48:42.577918: step: 620/530, loss: 0.0012137056328356266
2023-01-23 03:48:43.687534: step: 624/530, loss: 2.880096508306451e-05
2023-01-23 03:48:44.786349: step: 628/530, loss: 8.668899681651965e-05
2023-01-23 03:48:45.900926: step: 632/530, loss: 0.027423381805419922
2023-01-23 03:48:47.022269: step: 636/530, loss: 0.0077041625045239925
2023-01-23 03:48:48.120037: step: 640/530, loss: 8.535385859431699e-06
2023-01-23 03:48:49.228601: step: 644/530, loss: 0.0006603241199627519
2023-01-23 03:48:50.320439: step: 648/530, loss: 0.009639739990234375
2023-01-23 03:48:51.435619: step: 652/530, loss: 0.0016557216877117753
2023-01-23 03:48:52.514318: step: 656/530, loss: 0.02028980292379856
2023-01-23 03:48:53.591167: step: 660/530, loss: 0.0034016608260571957
2023-01-23 03:48:54.675825: step: 664/530, loss: 0.003178215119987726
2023-01-23 03:48:55.791132: step: 668/530, loss: 0.02085561864078045
2023-01-23 03:48:56.892955: step: 672/530, loss: 0.00034213069011457264
2023-01-23 03:48:58.001422: step: 676/530, loss: 0.0011877060169354081
2023-01-23 03:48:59.081087: step: 680/530, loss: 2.0408631826285273e-05
2023-01-23 03:49:00.191746: step: 684/530, loss: 0.00039143560570664704
2023-01-23 03:49:01.327585: step: 688/530, loss: 0.0184478759765625
2023-01-23 03:49:02.426087: step: 692/530, loss: 0.0019886016380041838
2023-01-23 03:49:03.536085: step: 696/530, loss: 0.002204513642936945
2023-01-23 03:49:04.649415: step: 700/530, loss: 0.02226715162396431
2023-01-23 03:49:05.769802: step: 704/530, loss: 0.0016760826110839844
2023-01-23 03:49:06.905455: step: 708/530, loss: 0.0001087188720703125
2023-01-23 03:49:08.033894: step: 712/530, loss: 0.007320213597267866
2023-01-23 03:49:09.120572: step: 716/530, loss: 0.0002645254135131836
2023-01-23 03:49:10.211345: step: 720/530, loss: 2.86102294921875e-06
2023-01-23 03:49:11.284968: step: 724/530, loss: 0.000305366498650983
2023-01-23 03:49:12.390490: step: 728/530, loss: 0.0002894401550292969
2023-01-23 03:49:13.464946: step: 732/530, loss: 0.0028312685899436474
2023-01-23 03:49:14.551129: step: 736/530, loss: 0.009303283877670765
2023-01-23 03:49:15.648131: step: 740/530, loss: 0.0020860673394054174
2023-01-23 03:49:16.754128: step: 744/530, loss: 0.004052543547004461
2023-01-23 03:49:17.869490: step: 748/530, loss: 0.09322519600391388
2023-01-23 03:49:18.958246: step: 752/530, loss: 0.0005322456709109247
2023-01-23 03:49:20.085132: step: 756/530, loss: 0.015447044745087624
2023-01-23 03:49:21.161319: step: 760/530, loss: 0.00033173561678268015
2023-01-23 03:49:22.316451: step: 764/530, loss: 0.06259326636791229
2023-01-23 03:49:23.413497: step: 768/530, loss: 0.011116600595414639
2023-01-23 03:49:24.515324: step: 772/530, loss: 0.041582491248846054
2023-01-23 03:49:25.600249: step: 776/530, loss: 0.4507943391799927
2023-01-23 03:49:26.712179: step: 780/530, loss: 0.0004926681285724044
2023-01-23 03:49:27.814896: step: 784/530, loss: 5.4359438763640355e-06
2023-01-23 03:49:28.925871: step: 788/530, loss: 0.014278173446655273
2023-01-23 03:49:30.062896: step: 792/530, loss: 0.004047298338264227
2023-01-23 03:49:31.174074: step: 796/530, loss: 0.0006560325855389237
2023-01-23 03:49:32.285475: step: 800/530, loss: 0.005858230870217085
2023-01-23 03:49:33.401739: step: 804/530, loss: 0.0016461373306810856
2023-01-23 03:49:34.500013: step: 808/530, loss: 0.025136232376098633
2023-01-23 03:49:35.629260: step: 812/530, loss: 2.6035308110294864e-05
2023-01-23 03:49:36.735579: step: 816/530, loss: 0.007239818572998047
2023-01-23 03:49:37.871581: step: 820/530, loss: 0.0034332750365138054
2023-01-23 03:49:39.008136: step: 824/530, loss: 2.727508581301663e-05
2023-01-23 03:49:40.091663: step: 828/530, loss: 4.8923491704044864e-05
2023-01-23 03:49:41.190973: step: 832/530, loss: 0.0041336058638989925
2023-01-23 03:49:42.303650: step: 836/530, loss: 0.027501869946718216
2023-01-23 03:49:43.420499: step: 840/530, loss: 0.06568918377161026
2023-01-23 03:49:44.522344: step: 844/530, loss: 0.014821053482592106
2023-01-23 03:49:45.641350: step: 848/530, loss: 0.019756508991122246
2023-01-23 03:49:46.760494: step: 852/530, loss: 1.220703143189894e-05
2023-01-23 03:49:47.865360: step: 856/530, loss: 0.0004754066758323461
2023-01-23 03:49:48.971495: step: 860/530, loss: 0.0005312919383868575
2023-01-23 03:49:50.091484: step: 864/530, loss: 1.888275073724799e-05
2023-01-23 03:49:51.191797: step: 868/530, loss: 3.99589553126134e-05
2023-01-23 03:49:52.314184: step: 872/530, loss: 0.0025051117409020662
2023-01-23 03:49:53.397547: step: 876/530, loss: 0.0011125088203698397
2023-01-23 03:49:54.505567: step: 880/530, loss: 0.016980934888124466
2023-01-23 03:49:55.642970: step: 884/530, loss: 0.030041933059692383
2023-01-23 03:49:56.708686: step: 888/530, loss: 0.0027034759987145662
2023-01-23 03:49:57.808490: step: 892/530, loss: 0.0003354072687216103
2023-01-23 03:49:58.894780: step: 896/530, loss: 0.003802680876106024
2023-01-23 03:49:59.998245: step: 900/530, loss: 0.0007093430031090975
2023-01-23 03:50:01.130913: step: 904/530, loss: 0.0005811214214190841
2023-01-23 03:50:02.242698: step: 908/530, loss: 8.449554297840223e-05
2023-01-23 03:50:03.432139: step: 912/530, loss: 0.001377964043058455
2023-01-23 03:50:04.524243: step: 916/530, loss: 0.04289431497454643
2023-01-23 03:50:05.617038: step: 920/530, loss: 4.0817263652570546e-05
2023-01-23 03:50:06.744517: step: 924/530, loss: 0.040535736829042435
2023-01-23 03:50:07.854948: step: 928/530, loss: 0.008727455511689186
2023-01-23 03:50:08.940368: step: 932/530, loss: 0.003745126770809293
2023-01-23 03:50:10.069579: step: 936/530, loss: -2.956390289909905e-06
2023-01-23 03:50:11.160864: step: 940/530, loss: 0.0005401611560955644
2023-01-23 03:50:12.249049: step: 944/530, loss: 0.0032356262672692537
2023-01-23 03:50:13.344522: step: 948/530, loss: 0.00028362273587845266
2023-01-23 03:50:14.440873: step: 952/530, loss: 0.0003520965401548892
2023-01-23 03:50:15.511415: step: 956/530, loss: 0.036427877843379974
2023-01-23 03:50:16.602539: step: 960/530, loss: 3.075599670410156e-05
2023-01-23 03:50:17.697771: step: 964/530, loss: 0.03636689484119415
2023-01-23 03:50:18.774580: step: 968/530, loss: 0.0015252113807946444
2023-01-23 03:50:19.838630: step: 972/530, loss: 0.0008503437275066972
2023-01-23 03:50:20.940369: step: 976/530, loss: 0.026938581839203835
2023-01-23 03:50:22.064842: step: 980/530, loss: 0.05759334936738014
2023-01-23 03:50:23.164060: step: 984/530, loss: 0.0029325485229492188
2023-01-23 03:50:24.259567: step: 988/530, loss: 0.004162514582276344
2023-01-23 03:50:25.322331: step: 992/530, loss: 0.0004974007606506348
2023-01-23 03:50:26.430816: step: 996/530, loss: 0.0006010055658407509
2023-01-23 03:50:27.544976: step: 1000/530, loss: 0.0006549835088662803
2023-01-23 03:50:28.667373: step: 1004/530, loss: 0.04351158067584038
2023-01-23 03:50:29.788279: step: 1008/530, loss: 0.00028524399385787547
2023-01-23 03:50:30.891404: step: 1012/530, loss: 0.010936069302260876
2023-01-23 03:50:31.996222: step: 1016/530, loss: 0.003226327942684293
2023-01-23 03:50:33.084046: step: 1020/530, loss: 0.00013589859008789062
2023-01-23 03:50:34.207423: step: 1024/530, loss: 0.004448986146599054
2023-01-23 03:50:35.320942: step: 1028/530, loss: 0.0035955430939793587
2023-01-23 03:50:36.427086: step: 1032/530, loss: 4.854202416026965e-05
2023-01-23 03:50:37.516839: step: 1036/530, loss: 0.00025935174198821187
2023-01-23 03:50:38.619470: step: 1040/530, loss: 0.0266131404787302
2023-01-23 03:50:39.738140: step: 1044/530, loss: 3.0851362680550665e-05
2023-01-23 03:50:40.857228: step: 1048/530, loss: 5.092620995128527e-05
2023-01-23 03:50:41.941739: step: 1052/530, loss: 0.0040611266158521175
2023-01-23 03:50:43.059514: step: 1056/530, loss: 1.354217511106981e-05
2023-01-23 03:50:44.170679: step: 1060/530, loss: 3.981590270996094e-05
2023-01-23 03:50:45.289606: step: 1064/530, loss: 0.20756812393665314
2023-01-23 03:50:46.405987: step: 1068/530, loss: 0.0017080307006835938
2023-01-23 03:50:47.499013: step: 1072/530, loss: 0.0060065267607569695
2023-01-23 03:50:48.610997: step: 1076/530, loss: 3.471374657237902e-05
2023-01-23 03:50:49.731164: step: 1080/530, loss: 7.629394076502649e-07
2023-01-23 03:50:50.839882: step: 1084/530, loss: 0.062209080904722214
2023-01-23 03:50:51.976584: step: 1088/530, loss: 0.07628345489501953
2023-01-23 03:50:53.077939: step: 1092/530, loss: 9.231567673850805e-05
2023-01-23 03:50:54.156912: step: 1096/530, loss: 0.004822445102035999
2023-01-23 03:50:55.263996: step: 1100/530, loss: 0.0013984680408611894
2023-01-23 03:50:56.391296: step: 1104/530, loss: 0.0018266676925122738
2023-01-23 03:50:57.482956: step: 1108/530, loss: 4.882812572759576e-05
2023-01-23 03:50:58.609662: step: 1112/530, loss: 0.004096985328942537
2023-01-23 03:50:59.688053: step: 1116/530, loss: 0.006518650334328413
2023-01-23 03:51:00.799784: step: 1120/530, loss: 0.0011026383144780993
2023-01-23 03:51:01.928863: step: 1124/530, loss: 8.440018427791074e-05
2023-01-23 03:51:03.036667: step: 1128/530, loss: 8.283853821922094e-05
2023-01-23 03:51:04.174073: step: 1132/530, loss: 4.343986802268773e-05
2023-01-23 03:51:05.279356: step: 1136/530, loss: 0.0021999359596520662
2023-01-23 03:51:06.388456: step: 1140/530, loss: 0.019924068823456764
2023-01-23 03:51:07.466262: step: 1144/530, loss: 0.042476460337638855
2023-01-23 03:51:08.574201: step: 1148/530, loss: 0.00019769668870139867
2023-01-23 03:51:09.666549: step: 1152/530, loss: 0.0004432678106240928
2023-01-23 03:51:10.785556: step: 1156/530, loss: 0.062159352004528046
2023-01-23 03:51:11.902738: step: 1160/530, loss: 0.011827182956039906
2023-01-23 03:51:13.000242: step: 1164/530, loss: 0.0022527696564793587
2023-01-23 03:51:14.135876: step: 1168/530, loss: 1.9073486612342094e-07
2023-01-23 03:51:15.245940: step: 1172/530, loss: 0.0011508942116051912
2023-01-23 03:51:16.369150: step: 1176/530, loss: 0.003374099964275956
2023-01-23 03:51:17.452864: step: 1180/530, loss: 9.117126319324598e-05
2023-01-23 03:51:18.539774: step: 1184/530, loss: 0.6503921151161194
2023-01-23 03:51:19.657629: step: 1188/530, loss: 0.0009100913885049522
2023-01-23 03:51:20.740233: step: 1192/530, loss: 0.0002119064301950857
2023-01-23 03:51:21.832840: step: 1196/530, loss: 0.008825588971376419
2023-01-23 03:51:22.943666: step: 1200/530, loss: 0.08517579734325409
2023-01-23 03:51:24.047622: step: 1204/530, loss: 6.4373016357421875e-06
2023-01-23 03:51:25.144548: step: 1208/530, loss: 0.0017513275379315019
2023-01-23 03:51:26.230887: step: 1212/530, loss: 0.5070964694023132
2023-01-23 03:51:27.327631: step: 1216/530, loss: 0.0010450363624840975
2023-01-23 03:51:28.412126: step: 1220/530, loss: 0.0002019882231252268
2023-01-23 03:51:29.533952: step: 1224/530, loss: 0.0003076791763305664
2023-01-23 03:51:30.633222: step: 1228/530, loss: 0.002882242202758789
2023-01-23 03:51:31.735718: step: 1232/530, loss: 2.250671423098538e-05
2023-01-23 03:51:32.827778: step: 1236/530, loss: 3.9577484130859375e-05
2023-01-23 03:51:33.979857: step: 1240/530, loss: 0.00012664795212913305
2023-01-23 03:51:35.085312: step: 1244/530, loss: 0.002530813217163086
2023-01-23 03:51:36.176367: step: 1248/530, loss: 0.0033914565574377775
2023-01-23 03:51:37.291244: step: 1252/530, loss: 0.020035266876220703
2023-01-23 03:51:38.393887: step: 1256/530, loss: 1.5354156857938506e-05
2023-01-23 03:51:39.537595: step: 1260/530, loss: 3.814697322468419e-07
2023-01-23 03:51:40.666957: step: 1264/530, loss: 0.0004520416259765625
2023-01-23 03:51:41.794137: step: 1268/530, loss: 0.030242253094911575
2023-01-23 03:51:42.904980: step: 1272/530, loss: 0.0007990360027179122
2023-01-23 03:51:44.022605: step: 1276/530, loss: 0.00014200209989212453
2023-01-23 03:51:45.152321: step: 1280/530, loss: 0.006500435061752796
2023-01-23 03:51:46.249897: step: 1284/530, loss: 0.0013354301918298006
2023-01-23 03:51:47.340001: step: 1288/530, loss: 0.00023145676823332906
2023-01-23 03:51:48.440101: step: 1292/530, loss: 0.0027272223960608244
2023-01-23 03:51:49.521817: step: 1296/530, loss: 0.0027792933396995068
2023-01-23 03:51:50.613206: step: 1300/530, loss: 0.0002803802490234375
2023-01-23 03:51:51.730542: step: 1304/530, loss: 0.00017542838759254664
2023-01-23 03:51:52.836541: step: 1308/530, loss: 0.011533738113939762
2023-01-23 03:51:53.968754: step: 1312/530, loss: 3.5048744678497314
2023-01-23 03:51:55.093648: step: 1316/530, loss: 0.0529085174202919
2023-01-23 03:51:56.232572: step: 1320/530, loss: 0.0029927254654467106
2023-01-23 03:51:57.375293: step: 1324/530, loss: 0.0325622595846653
2023-01-23 03:51:58.502255: step: 1328/530, loss: 0.015258599072694778
2023-01-23 03:51:59.640090: step: 1332/530, loss: 0.01711559295654297
2023-01-23 03:52:00.770576: step: 1336/530, loss: 0.0004385948122944683
2023-01-23 03:52:01.886017: step: 1340/530, loss: 0.39757195115089417
2023-01-23 03:52:03.001548: step: 1344/530, loss: 0.001965141389518976
2023-01-23 03:52:04.102917: step: 1348/530, loss: 0.0014477253425866365
2023-01-23 03:52:05.236426: step: 1352/530, loss: 0.0031809809152036905
2023-01-23 03:52:06.336665: step: 1356/530, loss: 0.0006017684936523438
2023-01-23 03:52:07.467665: step: 1360/530, loss: 0.0034381865989416838
2023-01-23 03:52:08.577556: step: 1364/530, loss: 2.441406286379788e-05
2023-01-23 03:52:09.692289: step: 1368/530, loss: 0.007786208298057318
2023-01-23 03:52:10.816488: step: 1372/530, loss: 0.00016717911057639867
2023-01-23 03:52:11.924563: step: 1376/530, loss: 0.0016846656799316406
2023-01-23 03:52:13.025138: step: 1380/530, loss: 0.004592704586684704
2023-01-23 03:52:14.142328: step: 1384/530, loss: 0.0014440537197515368
2023-01-23 03:52:15.265120: step: 1388/530, loss: 0.0017663001781329513
2023-01-23 03:52:16.347829: step: 1392/530, loss: 0.00453681917861104
2023-01-23 03:52:17.462084: step: 1396/530, loss: 0.0002994537353515625
2023-01-23 03:52:18.548609: step: 1400/530, loss: 0.000209808349609375
2023-01-23 03:52:19.626068: step: 1404/530, loss: 0.0002300739288330078
2023-01-23 03:52:20.761129: step: 1408/530, loss: 0.09959588199853897
2023-01-23 03:52:21.879617: step: 1412/530, loss: 0.005264949519187212
2023-01-23 03:52:23.046323: step: 1416/530, loss: 0.002631664276123047
2023-01-23 03:52:24.199968: step: 1420/530, loss: 0.02011279948055744
2023-01-23 03:52:25.303748: step: 1424/530, loss: 0.0006235599867068231
2023-01-23 03:52:26.410255: step: 1428/530, loss: 0.00156660086940974
2023-01-23 03:52:27.506088: step: 1432/530, loss: 0.018874311819672585
2023-01-23 03:52:28.616137: step: 1436/530, loss: 1.5544890629826114e-05
2023-01-23 03:52:29.744681: step: 1440/530, loss: 0.0019668578170239925
2023-01-23 03:52:30.870545: step: 1444/530, loss: 0.0003955840948037803
2023-01-23 03:52:31.974956: step: 1448/530, loss: 0.0004201889387331903
2023-01-23 03:52:33.084206: step: 1452/530, loss: 0.022609233856201172
2023-01-23 03:52:34.165421: step: 1456/530, loss: 0.019643783569335938
2023-01-23 03:52:35.272993: step: 1460/530, loss: 0.015396405011415482
2023-01-23 03:52:36.400809: step: 1464/530, loss: 0.004237174987792969
2023-01-23 03:52:37.507799: step: 1468/530, loss: 2.899169885495212e-05
2023-01-23 03:52:38.590354: step: 1472/530, loss: 0.08381299674510956
2023-01-23 03:52:39.744901: step: 1476/530, loss: 0.041929055005311966
2023-01-23 03:52:40.870539: step: 1480/530, loss: 0.061078548431396484
2023-01-23 03:52:41.973269: step: 1484/530, loss: 0.009345054626464844
2023-01-23 03:52:43.068377: step: 1488/530, loss: 0.030644893646240234
2023-01-23 03:52:44.171824: step: 1492/530, loss: 0.004668998531997204
2023-01-23 03:52:45.289763: step: 1496/530, loss: 0.0002442359982524067
2023-01-23 03:52:46.374886: step: 1500/530, loss: 0.0003310203901492059
2023-01-23 03:52:47.485307: step: 1504/530, loss: 0.0008363723754882812
2023-01-23 03:52:48.575421: step: 1508/530, loss: 0.029625702649354935
2023-01-23 03:52:49.658093: step: 1512/530, loss: 0.0017625123728066683
2023-01-23 03:52:50.760379: step: 1516/530, loss: 0.005372428800910711
2023-01-23 03:52:51.877431: step: 1520/530, loss: 0.3130576014518738
2023-01-23 03:52:52.977345: step: 1524/530, loss: 0.00015444755263160914
2023-01-23 03:52:54.086798: step: 1528/530, loss: 0.024785803630948067
2023-01-23 03:52:55.212202: step: 1532/530, loss: 0.0010930061107501388
2023-01-23 03:52:56.290347: step: 1536/530, loss: 0.002026176545768976
2023-01-23 03:52:57.405597: step: 1540/530, loss: 0.001341152237728238
2023-01-23 03:52:58.503183: step: 1544/530, loss: 0.0007477760664187372
2023-01-23 03:52:59.617653: step: 1548/530, loss: 0.0006202697986736894
2023-01-23 03:53:00.729913: step: 1552/530, loss: 0.0037949562538415194
2023-01-23 03:53:01.841536: step: 1556/530, loss: 0.01739645004272461
2023-01-23 03:53:02.999237: step: 1560/530, loss: 0.0024330138694494963
2023-01-23 03:53:04.089360: step: 1564/530, loss: 0.00013990403385832906
2023-01-23 03:53:05.222296: step: 1568/530, loss: 0.0007499695057049394
2023-01-23 03:53:06.332122: step: 1572/530, loss: 0.03244819492101669
2023-01-23 03:53:07.466077: step: 1576/530, loss: 0.00025138852652162313
2023-01-23 03:53:08.559980: step: 1580/530, loss: -7.152561920520384e-08
2023-01-23 03:53:09.672285: step: 1584/530, loss: 0.0012388229370117188
2023-01-23 03:53:10.798108: step: 1588/530, loss: 0.031202031299471855
2023-01-23 03:53:11.892718: step: 1592/530, loss: 0.0011800766224041581
2023-01-23 03:53:13.011915: step: 1596/530, loss: 0.0004047393740620464
2023-01-23 03:53:14.104596: step: 1600/530, loss: 0.011413288302719593
2023-01-23 03:53:15.203906: step: 1604/530, loss: 0.0024421692360192537
2023-01-23 03:53:16.319133: step: 1608/530, loss: 0.00242195138707757
2023-01-23 03:53:17.420854: step: 1612/530, loss: 0.0018444061279296875
2023-01-23 03:53:18.534626: step: 1616/530, loss: 1.621246337890625e-05
2023-01-23 03:53:19.620703: step: 1620/530, loss: 0.024398326873779297
2023-01-23 03:53:20.726812: step: 1624/530, loss: 0.00043334963265806437
2023-01-23 03:53:21.817683: step: 1628/530, loss: 0.00022420883760787547
2023-01-23 03:53:22.948756: step: 1632/530, loss: 0.00014038085646461695
2023-01-23 03:53:24.059014: step: 1636/530, loss: 0.016608715057373047
2023-01-23 03:53:25.189665: step: 1640/530, loss: 0.012693596072494984
2023-01-23 03:53:26.274755: step: 1644/530, loss: 0.00014200209989212453
2023-01-23 03:53:27.361252: step: 1648/530, loss: 0.0008685112115927041
2023-01-23 03:53:28.437114: step: 1652/530, loss: 0.012342739850282669
2023-01-23 03:53:29.556437: step: 1656/530, loss: 0.011956882663071156
2023-01-23 03:53:30.676881: step: 1660/530, loss: 0.004529762081801891
2023-01-23 03:53:31.792507: step: 1664/530, loss: 0.005699109751731157
2023-01-23 03:53:32.887026: step: 1668/530, loss: 0.0001790046808309853
2023-01-23 03:53:33.993646: step: 1672/530, loss: 0.06953687220811844
2023-01-23 03:53:35.086575: step: 1676/530, loss: 0.0008713722345419228
2023-01-23 03:53:36.183183: step: 1680/530, loss: 0.031763460487127304
2023-01-23 03:53:37.317884: step: 1684/530, loss: 8.0108642578125e-05
2023-01-23 03:53:38.417739: step: 1688/530, loss: 0.004968118853867054
2023-01-23 03:53:39.505028: step: 1692/530, loss: 0.00033550261287018657
2023-01-23 03:53:40.607747: step: 1696/530, loss: 3.566742088878527e-05
2023-01-23 03:53:41.707266: step: 1700/530, loss: 0.003076171735301614
2023-01-23 03:53:42.793063: step: 1704/530, loss: 0.0001276016264455393
2023-01-23 03:53:43.906580: step: 1708/530, loss: 9.880065772449598e-05
2023-01-23 03:53:45.018908: step: 1712/530, loss: 0.00235672015696764
2023-01-23 03:53:46.127802: step: 1716/530, loss: 0.0002490997430868447
2023-01-23 03:53:47.258259: step: 1720/530, loss: 6.103516170696821e-06
2023-01-23 03:53:48.349108: step: 1724/530, loss: 2.613067590573337e-05
2023-01-23 03:53:49.450847: step: 1728/530, loss: 0.0014015198685228825
2023-01-23 03:53:50.598112: step: 1732/530, loss: 4.928111957269721e-05
2023-01-23 03:53:51.690838: step: 1736/530, loss: 0.055178169161081314
2023-01-23 03:53:52.823273: step: 1740/530, loss: 2.2792817617300898e-05
2023-01-23 03:53:53.906500: step: 1744/530, loss: 0.000164031982421875
2023-01-23 03:53:55.025189: step: 1748/530, loss: 0.0009350776672363281
2023-01-23 03:53:56.113159: step: 1752/530, loss: 0.00012502670870162547
2023-01-23 03:53:57.202612: step: 1756/530, loss: 0.00087738037109375
2023-01-23 03:53:58.297573: step: 1760/530, loss: 0.0022929192055016756
2023-01-23 03:53:59.389206: step: 1764/530, loss: 0.016465187072753906
2023-01-23 03:54:00.511521: step: 1768/530, loss: 0.0002925872977357358
2023-01-23 03:54:01.648375: step: 1772/530, loss: 0.03180332109332085
2023-01-23 03:54:02.730683: step: 1776/530, loss: 1.7309188478975557e-05
2023-01-23 03:54:03.850393: step: 1780/530, loss: 0.00043048858060501516
2023-01-23 03:54:04.934204: step: 1784/530, loss: 0.014838123694062233
2023-01-23 03:54:06.023502: step: 1788/530, loss: 5.73158249608241e-05
2023-01-23 03:54:07.097448: step: 1792/530, loss: 0.00015754700871184468
2023-01-23 03:54:08.217238: step: 1796/530, loss: 0.02205810695886612
2023-01-23 03:54:09.336506: step: 1800/530, loss: 0.002079200930893421
2023-01-23 03:54:10.443313: step: 1804/530, loss: 0.04273023456335068
2023-01-23 03:54:11.527672: step: 1808/530, loss: 0.0004676103708334267
2023-01-23 03:54:12.650525: step: 1812/530, loss: 0.006861209869384766
2023-01-23 03:54:13.750147: step: 1816/530, loss: 8.516311936546117e-05
2023-01-23 03:54:14.847930: step: 1820/530, loss: 0.0067656515166163445
2023-01-23 03:54:15.971510: step: 1824/530, loss: 0.028238391503691673
2023-01-23 03:54:17.102026: step: 1828/530, loss: 0.11601724475622177
2023-01-23 03:54:18.213513: step: 1832/530, loss: 0.0003273964102845639
2023-01-23 03:54:19.320321: step: 1836/530, loss: 0.018491197377443314
2023-01-23 03:54:20.438786: step: 1840/530, loss: 5.6838991440599784e-05
2023-01-23 03:54:21.524619: step: 1844/530, loss: 0.0017460347153246403
2023-01-23 03:54:22.633813: step: 1848/530, loss: 0.009456252679228783
2023-01-23 03:54:23.779661: step: 1852/530, loss: 1.980755090713501
2023-01-23 03:54:24.912277: step: 1856/530, loss: 0.00031957626924850047
2023-01-23 03:54:26.015018: step: 1860/530, loss: 3.223419116693549e-05
2023-01-23 03:54:27.132777: step: 1864/530, loss: 0.01775188557803631
2023-01-23 03:54:28.268174: step: 1868/530, loss: 0.0002731323183979839
2023-01-23 03:54:29.397342: step: 1872/530, loss: 0.029294587671756744
2023-01-23 03:54:30.503304: step: 1876/530, loss: 0.0009731292957440019
2023-01-23 03:54:31.673514: step: 1880/530, loss: 0.0014904976123943925
2023-01-23 03:54:32.781618: step: 1884/530, loss: 0.0049987793900072575
2023-01-23 03:54:33.918953: step: 1888/530, loss: 0.0008016586070880294
2023-01-23 03:54:35.012746: step: 1892/530, loss: 0.00014181138249114156
2023-01-23 03:54:36.121668: step: 1896/530, loss: 0.005658340640366077
2023-01-23 03:54:37.223694: step: 1900/530, loss: 9.5367431640625e-06
2023-01-23 03:54:38.351558: step: 1904/530, loss: 0.0009243011591024697
2023-01-23 03:54:39.473245: step: 1908/530, loss: 0.004503107164055109
2023-01-23 03:54:40.600503: step: 1912/530, loss: 0.017327118664979935
2023-01-23 03:54:41.707031: step: 1916/530, loss: 4.4155120122013614e-05
2023-01-23 03:54:42.793087: step: 1920/530, loss: 0.0004862785281147808
2023-01-23 03:54:43.888321: step: 1924/530, loss: 0.0007985115516930819
2023-01-23 03:54:44.983818: step: 1928/530, loss: 0.0027611732948571444
2023-01-23 03:54:46.100467: step: 1932/530, loss: 0.013783550821244717
2023-01-23 03:54:47.174520: step: 1936/530, loss: 0.0010929107666015625
2023-01-23 03:54:48.280252: step: 1940/530, loss: 0.052123069763183594
2023-01-23 03:54:49.365576: step: 1944/530, loss: 0.011940956115722656
2023-01-23 03:54:50.471348: step: 1948/530, loss: 0.000888824462890625
2023-01-23 03:54:51.580731: step: 1952/530, loss: 0.03435344994068146
2023-01-23 03:54:52.720360: step: 1956/530, loss: 0.025199031457304955
2023-01-23 03:54:53.831924: step: 1960/530, loss: 7.972717139637098e-05
2023-01-23 03:54:54.927418: step: 1964/530, loss: 3.4904482163256034e-05
2023-01-23 03:54:56.003248: step: 1968/530, loss: 0.0027645111549645662
2023-01-23 03:54:57.118161: step: 1972/530, loss: 0.0034851073287427425
2023-01-23 03:54:58.235187: step: 1976/530, loss: 0.0005037784576416016
2023-01-23 03:54:59.363740: step: 1980/530, loss: 9.13620024221018e-05
2023-01-23 03:55:00.488476: step: 1984/530, loss: 0.04556474834680557
2023-01-23 03:55:01.603675: step: 1988/530, loss: 7.667540921829641e-05
2023-01-23 03:55:02.770618: step: 1992/530, loss: 0.0006044387700967491
2023-01-23 03:55:03.884486: step: 1996/530, loss: 0.006947183515876532
2023-01-23 03:55:04.953359: step: 2000/530, loss: 0.0038581849075853825
2023-01-23 03:55:06.058223: step: 2004/530, loss: 1.106262243411038e-05
2023-01-23 03:55:07.156868: step: 2008/530, loss: 0.12032680958509445
2023-01-23 03:55:08.271966: step: 2012/530, loss: 5.731582859880291e-05
2023-01-23 03:55:09.379392: step: 2016/530, loss: 2.0027162008773303e-06
2023-01-23 03:55:10.469713: step: 2020/530, loss: 0.24131107330322266
2023-01-23 03:55:11.583622: step: 2024/530, loss: 0.030902672559022903
2023-01-23 03:55:12.678355: step: 2028/530, loss: 0.009600449353456497
2023-01-23 03:55:13.801198: step: 2032/530, loss: 0.0019876479636877775
2023-01-23 03:55:14.900252: step: 2036/530, loss: 0.03327293321490288
2023-01-23 03:55:16.014173: step: 2040/530, loss: 0.0004704475577455014
2023-01-23 03:55:17.103430: step: 2044/530, loss: 0.05720863491296768
2023-01-23 03:55:18.188753: step: 2048/530, loss: 6.628036499023438e-05
2023-01-23 03:55:19.268815: step: 2052/530, loss: 0.011372094973921776
2023-01-23 03:55:20.392989: step: 2056/530, loss: 0.02214241214096546
2023-01-23 03:55:21.468509: step: 2060/530, loss: 0.006056881044059992
2023-01-23 03:55:22.592819: step: 2064/530, loss: 0.0035987854935228825
2023-01-23 03:55:23.707146: step: 2068/530, loss: 6.542205665027723e-05
2023-01-23 03:55:24.802655: step: 2072/530, loss: 2.689361645025201e-05
2023-01-23 03:55:25.942095: step: 2076/530, loss: 3.156661841785535e-05
2023-01-23 03:55:27.082936: step: 2080/530, loss: 0.0016698838444426656
2023-01-23 03:55:28.185534: step: 2084/530, loss: 0.0003034591500181705
2023-01-23 03:55:29.306186: step: 2088/530, loss: 0.06633710861206055
2023-01-23 03:55:30.408160: step: 2092/530, loss: 0.02072906494140625
2023-01-23 03:55:31.511269: step: 2096/530, loss: 0.005288505461066961
2023-01-23 03:55:32.613628: step: 2100/530, loss: 0.000419425981817767
2023-01-23 03:55:33.694862: step: 2104/530, loss: 0.007842540740966797
2023-01-23 03:55:34.787565: step: 2108/530, loss: 0.0012838364345952868
2023-01-23 03:55:35.869182: step: 2112/530, loss: 4.9209596909349784e-05
2023-01-23 03:55:36.975872: step: 2116/530, loss: 0.021673966199159622
2023-01-23 03:55:38.105464: step: 2120/530, loss: 0.0042476654052734375
==================================================
Loss: 0.026
--------------------
Dev: {'event': {'p': 0.593167701863354, 'r': 0.762982689747004, 'f1': 0.6674432149097262}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 25}
Test: {'event': {'p': 0.6428241808952468, 'r': 0.8117715617715617, 'f1': 0.7174864795261395}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 25}
Chinese: {'event': {'p': 0.581081081081081, 'r': 0.7962962962962963, 'f1': 0.6718749999999999}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 25}
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': 25}
Russian: {'event': {'p': 0.4864864864864865, 'r': 0.5, 'f1': 0.4931506849315069}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 25}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6449771689497716, 'r': 0.7523302263648469, 'f1': 0.6945298094652735}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Chinese: {'event': {'p': 0.6692644909887969, 'r': 0.8006993006993007, 'f1': 0.7291058636243036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Chinese: {'event': {'p': 0.6764705882352942, 'r': 0.8518518518518519, 'f1': 0.7540983606557378}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5873340143003064, 'r': 0.7656458055925432, 'f1': 0.6647398843930636}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Eng Test for Korean: {'event': {'p': 0.6496487119437939, 'r': 0.8082750582750583, 'f1': 0.7203323811996885}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Sample Korean: {'event': {'p': 0.6721311475409836, 'r': 0.6507936507936508, 'f1': 0.6612903225806451}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5971370143149284, 'r': 0.7776298268974701, 'f1': 0.6755349913244649}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Russian: {'event': {'p': 0.6401673640167364, 'r': 0.8024475524475524, 'f1': 0.7121799844840963}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Russian: {'event': {'p': 0.5897435897435898, 'r': 0.6388888888888888, 'f1': 0.6133333333333332}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
******************************
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 03:56:17.541437: step: 4/530, loss: 1.1157990229548886e-05
2023-01-23 03:56:18.684067: step: 8/530, loss: 9.860992577159777e-05
2023-01-23 03:56:19.794870: step: 12/530, loss: 0.029435252770781517
2023-01-23 03:56:20.903938: step: 16/530, loss: 0.0015669644344598055
2023-01-23 03:56:22.012669: step: 20/530, loss: 0.0034360885620117188
2023-01-23 03:56:23.128722: step: 24/530, loss: 0.005712271202355623
2023-01-23 03:56:24.228684: step: 28/530, loss: 0.04923725500702858
2023-01-23 03:56:25.352565: step: 32/530, loss: 3.280639793956652e-05
2023-01-23 03:56:26.457828: step: 36/530, loss: 0.001529693603515625
2023-01-23 03:56:27.528794: step: 40/530, loss: 0.0001638412504689768
2023-01-23 03:56:28.600042: step: 44/530, loss: 0.0005210876697674394
2023-01-23 03:56:29.682597: step: 48/530, loss: 0.0004524230898823589
2023-01-23 03:56:30.787966: step: 52/530, loss: 0.00015468598576262593
2023-01-23 03:56:31.886157: step: 56/530, loss: 0.0006010055658407509
2023-01-23 03:56:33.012947: step: 60/530, loss: 7.724761962890625e-05
2023-01-23 03:56:34.111406: step: 64/530, loss: 0.0005258560413494706
2023-01-23 03:56:35.182197: step: 68/530, loss: 0.03582150861620903
2023-01-23 03:56:36.290512: step: 72/530, loss: 0.00010957718041026965
2023-01-23 03:56:37.401554: step: 76/530, loss: 0.002403736114501953
2023-01-23 03:56:38.531749: step: 80/530, loss: 7.724762326688506e-06
2023-01-23 03:56:39.627681: step: 84/530, loss: 0.00015163421630859375
2023-01-23 03:56:40.713210: step: 88/530, loss: 0.00011005401756847277
2023-01-23 03:56:41.815996: step: 92/530, loss: 0.010606384836137295
2023-01-23 03:56:42.910704: step: 96/530, loss: 0.0002722263161558658
2023-01-23 03:56:44.019799: step: 100/530, loss: 0.0005909919855184853
2023-01-23 03:56:45.142035: step: 104/530, loss: 0.02245931699872017
2023-01-23 03:56:46.228090: step: 108/530, loss: 0.001161321997642517
2023-01-23 03:56:47.333465: step: 112/530, loss: 0.012830877676606178
2023-01-23 03:56:48.425805: step: 116/530, loss: 0.0008175074472092092
2023-01-23 03:56:49.517128: step: 120/530, loss: 4.1484832763671875e-05
2023-01-23 03:56:50.629142: step: 124/530, loss: 0.0493658073246479
2023-01-23 03:56:51.731264: step: 128/530, loss: 0.013104820623993874
2023-01-23 03:56:52.809433: step: 132/530, loss: 8.096695091808215e-05
2023-01-23 03:56:53.924045: step: 136/530, loss: 0.00013017654418945312
2023-01-23 03:56:55.026849: step: 140/530, loss: 0.00047397613525390625
2023-01-23 03:56:56.126144: step: 144/530, loss: 6.8664553509734105e-06
2023-01-23 03:56:57.219583: step: 148/530, loss: 0.00032329559326171875
2023-01-23 03:56:58.332597: step: 152/530, loss: 0.00010070800635730848
2023-01-23 03:56:59.442488: step: 156/530, loss: 0.0018201827770099044
2023-01-23 03:57:00.558012: step: 160/530, loss: 0.046710968017578125
2023-01-23 03:57:01.646044: step: 164/530, loss: 0.0021920683793723583
2023-01-23 03:57:02.741353: step: 168/530, loss: 0.019598007202148438
2023-01-23 03:57:03.857819: step: 172/530, loss: 0.004548835568130016
2023-01-23 03:57:04.959183: step: 176/530, loss: 0.001579380128532648
2023-01-23 03:57:06.053729: step: 180/530, loss: 0.002179431961849332
2023-01-23 03:57:07.228708: step: 184/530, loss: 0.000134265428641811
2023-01-23 03:57:08.352081: step: 188/530, loss: 2.307891918462701e-05
2023-01-23 03:57:09.436116: step: 192/530, loss: -2.098083541568485e-06
2023-01-23 03:57:10.584160: step: 196/530, loss: 0.0005447388393804431
2023-01-23 03:57:11.674313: step: 200/530, loss: 0.17504529654979706
2023-01-23 03:57:12.783316: step: 204/530, loss: 0.009723090566694736
2023-01-23 03:57:13.850861: step: 208/530, loss: 0.005770397372543812
2023-01-23 03:57:14.971223: step: 212/530, loss: 4.138946678722277e-05
2023-01-23 03:57:16.055164: step: 216/530, loss: 0.01642761379480362
2023-01-23 03:57:17.176577: step: 220/530, loss: 0.0005374908214434981
2023-01-23 03:57:18.296901: step: 224/530, loss: 0.03251204267144203
2023-01-23 03:57:19.425563: step: 228/530, loss: 0.0005940437549725175
2023-01-23 03:57:20.533955: step: 232/530, loss: 4.863739013671875e-05
2023-01-23 03:57:21.662986: step: 236/530, loss: 0.017530251294374466
2023-01-23 03:57:22.758887: step: 240/530, loss: 0.00012540817260742188
2023-01-23 03:57:23.871195: step: 244/530, loss: 0.1345689743757248
2023-01-23 03:57:24.960179: step: 248/530, loss: 2.651214526849799e-05
2023-01-23 03:57:26.080582: step: 252/530, loss: 0.0005752563592977822
2023-01-23 03:57:27.191410: step: 256/530, loss: 0.003058910369873047
2023-01-23 03:57:28.267930: step: 260/530, loss: 0.02488093450665474
2023-01-23 03:57:29.425677: step: 264/530, loss: 0.0002075195370707661
2023-01-23 03:57:30.521245: step: 268/530, loss: 1.6403197150793858e-05
2023-01-23 03:57:31.621305: step: 272/530, loss: 0.004748344421386719
2023-01-23 03:57:32.716103: step: 276/530, loss: 0.0008715391159057617
2023-01-23 03:57:33.806419: step: 280/530, loss: 8.621215965831652e-05
2023-01-23 03:57:34.912984: step: 284/530, loss: 0.003278541611507535
2023-01-23 03:57:36.006162: step: 288/530, loss: 0.0012996196746826172
2023-01-23 03:57:37.100836: step: 292/530, loss: 0.004025363828986883
2023-01-23 03:57:38.218781: step: 296/530, loss: 0.0002639770682435483
2023-01-23 03:57:39.331661: step: 300/530, loss: 0.06756363064050674
2023-01-23 03:57:40.434330: step: 304/530, loss: 0.00033130645169876516
2023-01-23 03:57:41.536520: step: 308/530, loss: 1.8119812921213452e-06
2023-01-23 03:57:42.631693: step: 312/530, loss: 0.005310869310051203
2023-01-23 03:57:43.755954: step: 316/530, loss: 0.00027751922607421875
2023-01-23 03:57:44.861639: step: 320/530, loss: 4.549026198219508e-05
2023-01-23 03:57:45.979429: step: 324/530, loss: 0.0003276825009379536
2023-01-23 03:57:47.085843: step: 328/530, loss: 0.0001377105654682964
2023-01-23 03:57:48.206480: step: 332/530, loss: 0.034422874450683594
2023-01-23 03:57:49.300912: step: 336/530, loss: 0.004054450895637274
2023-01-23 03:57:50.405460: step: 340/530, loss: 0.04195096716284752
2023-01-23 03:57:51.498276: step: 344/530, loss: 0.01164169330149889
2023-01-23 03:57:52.645623: step: 348/530, loss: 6.008148375258315e-06
2023-01-23 03:57:53.743352: step: 352/530, loss: 0.003418350126594305
2023-01-23 03:57:54.851528: step: 356/530, loss: -3.957748049288057e-06
2023-01-23 03:57:55.952290: step: 360/530, loss: 0.0015730857849121094
2023-01-23 03:57:57.059010: step: 364/530, loss: 0.0019794225227087736
2023-01-23 03:57:58.160051: step: 368/530, loss: 5.474090721691027e-05
2023-01-23 03:57:59.232770: step: 372/530, loss: 0.000142955788760446
2023-01-23 03:58:00.328318: step: 376/530, loss: 0.014256859198212624
2023-01-23 03:58:01.432150: step: 380/530, loss: 0.013043498620390892
2023-01-23 03:58:02.533646: step: 384/530, loss: 0.015285111032426357
2023-01-23 03:58:03.660205: step: 388/530, loss: 0.00013070108252577484
2023-01-23 03:58:04.767774: step: 392/530, loss: 0.01378779485821724
2023-01-23 03:58:05.868574: step: 396/530, loss: 0.006086444947868586
2023-01-23 03:58:06.984028: step: 400/530, loss: 0.004956245422363281
2023-01-23 03:58:08.072253: step: 404/530, loss: 0.0001424789516022429
2023-01-23 03:58:09.201569: step: 408/530, loss: 0.00032224657479673624
2023-01-23 03:58:10.350547: step: 412/530, loss: 0.0006439209100790322
2023-01-23 03:58:11.437267: step: 416/530, loss: 0.006103229243308306
2023-01-23 03:58:12.548533: step: 420/530, loss: 0.00018939973961096257
2023-01-23 03:58:13.678201: step: 424/530, loss: 0.018399430438876152
2023-01-23 03:58:14.758283: step: 428/530, loss: 0.00026426315889693797
2023-01-23 03:58:15.839637: step: 432/530, loss: 0.034485433250665665
2023-01-23 03:58:16.968921: step: 436/530, loss: 0.00123853690456599
2023-01-23 03:58:18.090780: step: 440/530, loss: 0.0002925872977357358
2023-01-23 03:58:19.227631: step: 444/530, loss: 0.0002666473446879536
2023-01-23 03:58:20.324429: step: 448/530, loss: 0.0008953094366006553
2023-01-23 03:58:21.441000: step: 452/530, loss: 0.00030794143094681203
2023-01-23 03:58:22.548187: step: 456/530, loss: 6.532669431180693e-06
2023-01-23 03:58:23.647997: step: 460/530, loss: -1.0824202036019415e-05
2023-01-23 03:58:24.735531: step: 464/530, loss: 8.583068620282575e-07
2023-01-23 03:58:25.842960: step: 468/530, loss: 0.03253975138068199
2023-01-23 03:58:26.926100: step: 472/530, loss: 2.136230432370212e-05
2023-01-23 03:58:28.021976: step: 476/530, loss: 8.306503150379285e-05
2023-01-23 03:58:29.109142: step: 480/530, loss: 2.2506712411995977e-05
2023-01-23 03:58:30.188383: step: 484/530, loss: 0.012070560827851295
2023-01-23 03:58:31.293166: step: 488/530, loss: 0.00019397735013626516
2023-01-23 03:58:32.405853: step: 492/530, loss: 0.12563222646713257
2023-01-23 03:58:33.502695: step: 496/530, loss: 0.000109624867036473
2023-01-23 03:58:34.585652: step: 500/530, loss: -9.536688594380394e-08
2023-01-23 03:58:35.714186: step: 504/530, loss: 0.01101923082023859
2023-01-23 03:58:36.813742: step: 508/530, loss: 0.0004941940424032509
2023-01-23 03:58:37.925996: step: 512/530, loss: 0.00046367646427825093
2023-01-23 03:58:39.026200: step: 516/530, loss: 0.0035005570389330387
2023-01-23 03:58:40.118419: step: 520/530, loss: 0.06160468980669975
2023-01-23 03:58:41.235434: step: 524/530, loss: 0.08625183254480362
2023-01-23 03:58:42.338099: step: 528/530, loss: 0.006708526983857155
2023-01-23 03:58:43.480232: step: 532/530, loss: 0.008047866635024548
2023-01-23 03:58:44.626147: step: 536/530, loss: 0.0011442184913903475
2023-01-23 03:58:45.720074: step: 540/530, loss: 0.001378822373226285
2023-01-23 03:58:46.799183: step: 544/530, loss: 0.005866670981049538
2023-01-23 03:58:47.895440: step: 548/530, loss: 0.017339278012514114
2023-01-23 03:58:48.997289: step: 552/530, loss: 0.0013941765064373612
2023-01-23 03:58:50.087595: step: 556/530, loss: 0.04866056516766548
2023-01-23 03:58:51.178866: step: 560/530, loss: 0.12443151324987411
2023-01-23 03:58:52.314225: step: 564/530, loss: 0.0091705322265625
2023-01-23 03:58:53.451371: step: 568/530, loss: 0.015758037567138672
2023-01-23 03:58:54.551101: step: 572/530, loss: 0.004190015606582165
2023-01-23 03:58:55.646190: step: 576/530, loss: 0.0022509575355798006
2023-01-23 03:58:56.734613: step: 580/530, loss: 0.00527381943538785
2023-01-23 03:58:57.828870: step: 584/530, loss: 6.437301635742188e-05
2023-01-23 03:58:58.928325: step: 588/530, loss: 0.015719985589385033
2023-01-23 03:59:00.031932: step: 592/530, loss: 0.0040496825240552425
2023-01-23 03:59:01.144712: step: 596/530, loss: 0.00021363497944548726
2023-01-23 03:59:02.270279: step: 600/530, loss: 0.003868484403938055
2023-01-23 03:59:03.347138: step: 604/530, loss: 3.223419116693549e-05
2023-01-23 03:59:04.465670: step: 608/530, loss: 0.008206367492675781
2023-01-23 03:59:05.560739: step: 612/530, loss: 0.00392074603587389
2023-01-23 03:59:06.689929: step: 616/530, loss: 0.0008504867437295616
2023-01-23 03:59:07.788889: step: 620/530, loss: 6.809234764659777e-05
2023-01-23 03:59:08.879546: step: 624/530, loss: 0.0011110305786132812
2023-01-23 03:59:09.950293: step: 628/530, loss: -3.14712519866589e-06
2023-01-23 03:59:11.039341: step: 632/530, loss: 0.011076497845351696
2023-01-23 03:59:12.150486: step: 636/530, loss: 8.635521226096898e-05
2023-01-23 03:59:13.252978: step: 640/530, loss: 0.00038051605224609375
2023-01-23 03:59:14.366204: step: 644/530, loss: 0.0009580135811120272
2023-01-23 03:59:15.459049: step: 648/530, loss: 0.000466763973236084
2023-01-23 03:59:16.551036: step: 652/530, loss: 0.014777708798646927
2023-01-23 03:59:17.673473: step: 656/530, loss: 0.003245115280151367
2023-01-23 03:59:18.763238: step: 660/530, loss: 2.0885467165498994e-05
2023-01-23 03:59:19.865396: step: 664/530, loss: 3.8695336115779355e-05
2023-01-23 03:59:21.007766: step: 668/530, loss: 0.007199478335678577
2023-01-23 03:59:22.104544: step: 672/530, loss: 0.0011286735534667969
2023-01-23 03:59:23.203270: step: 676/530, loss: 0.00013570785813499242
2023-01-23 03:59:24.314320: step: 680/530, loss: 0.02729034423828125
2023-01-23 03:59:25.419971: step: 684/530, loss: 0.0005313873407430947
2023-01-23 03:59:26.522158: step: 688/530, loss: 0.004558372311294079
2023-01-23 03:59:27.627845: step: 692/530, loss: 0.0023105619475245476
2023-01-23 03:59:28.747206: step: 696/530, loss: 0.0005208969232626259
2023-01-23 03:59:29.837038: step: 700/530, loss: 0.007081508636474609
2023-01-23 03:59:30.920148: step: 704/530, loss: 6.923676119185984e-05
2023-01-23 03:59:32.022106: step: 708/530, loss: 0.0021877288818359375
2023-01-23 03:59:33.164619: step: 712/530, loss: 5.14984139954322e-06
2023-01-23 03:59:34.268954: step: 716/530, loss: 0.06427783519029617
2023-01-23 03:59:35.374660: step: 720/530, loss: 0.006396484561264515
2023-01-23 03:59:36.478479: step: 724/530, loss: 0.0006708145374432206
2023-01-23 03:59:37.588010: step: 728/530, loss: 0.0008666992071084678
2023-01-23 03:59:38.679692: step: 732/530, loss: 0.00407829275354743
2023-01-23 03:59:39.789543: step: 736/530, loss: 0.0016889572143554688
2023-01-23 03:59:40.874818: step: 740/530, loss: 6.0653688706224784e-05
2023-01-23 03:59:41.959488: step: 744/530, loss: 0.0006469726795330644
2023-01-23 03:59:43.064052: step: 748/530, loss: 5.507469177246094e-05
2023-01-23 03:59:44.157468: step: 752/530, loss: 0.025494765490293503
2023-01-23 03:59:45.265854: step: 756/530, loss: 0.0001260757417185232
2023-01-23 03:59:46.355043: step: 760/530, loss: 0.0004618644597940147
2023-01-23 03:59:47.449491: step: 764/530, loss: 4.38690176451928e-06
2023-01-23 03:59:48.565401: step: 768/530, loss: 0.037951089441776276
2023-01-23 03:59:49.689163: step: 772/530, loss: 0.011043357662856579
2023-01-23 03:59:50.844411: step: 776/530, loss: 0.002699947450309992
2023-01-23 03:59:51.985321: step: 780/530, loss: 0.0010293960804119706
2023-01-23 03:59:53.086300: step: 784/530, loss: 0.03637123107910156
2023-01-23 03:59:54.195046: step: 788/530, loss: 0.000865936279296875
2023-01-23 03:59:55.301855: step: 792/530, loss: 0.0012589097023010254
2023-01-23 03:59:56.403649: step: 796/530, loss: 9.331703040516004e-05
2023-01-23 03:59:57.522712: step: 800/530, loss: 0.01222838182002306
2023-01-23 03:59:58.597675: step: 804/530, loss: 0.0003603935183491558
2023-01-23 03:59:59.716415: step: 808/530, loss: 0.0033665657974779606
2023-01-23 04:00:00.829656: step: 812/530, loss: 0.04898262023925781
2023-01-23 04:00:01.912004: step: 816/530, loss: 0.0007745742332190275
2023-01-23 04:00:03.019859: step: 820/530, loss: 0.0017484665149822831
2023-01-23 04:00:04.091810: step: 824/530, loss: 1.5594067008350976e-05
2023-01-23 04:00:05.213432: step: 828/530, loss: 0.011928940191864967
2023-01-23 04:00:06.287406: step: 832/530, loss: 0.0004944801330566406
2023-01-23 04:00:07.383219: step: 836/530, loss: 0.08316879719495773
2023-01-23 04:00:08.477154: step: 840/530, loss: 0.00011520386033225805
2023-01-23 04:00:09.570443: step: 844/530, loss: 0.0023003576789051294
2023-01-23 04:00:10.714258: step: 848/530, loss: 0.0009042262681759894
2023-01-23 04:00:11.819458: step: 852/530, loss: 0.02319011092185974
2023-01-23 04:00:12.906327: step: 856/530, loss: 2.307891918462701e-05
2023-01-23 04:00:14.001482: step: 860/530, loss: 0.009898853488266468
2023-01-23 04:00:15.109964: step: 864/530, loss: 0.007693099789321423
2023-01-23 04:00:16.191650: step: 868/530, loss: 0.08891773223876953
2023-01-23 04:00:17.304260: step: 872/530, loss: 0.0014736176235601306
2023-01-23 04:00:18.405608: step: 876/530, loss: 0.0031101228669285774
2023-01-23 04:00:19.499453: step: 880/530, loss: 0.06769299507141113
2023-01-23 04:00:20.593012: step: 884/530, loss: 0.00031795501126907766
2023-01-23 04:00:21.702647: step: 888/530, loss: 1.144409225162235e-06
2023-01-23 04:00:22.784415: step: 892/530, loss: 0.0024682998191565275
2023-01-23 04:00:23.912930: step: 896/530, loss: 0.005889797117561102
2023-01-23 04:00:25.048640: step: 900/530, loss: 0.00019111634173896164
2023-01-23 04:00:26.161672: step: 904/530, loss: 2.19345088225964e-06
2023-01-23 04:00:27.262624: step: 908/530, loss: 9.51766996877268e-05
2023-01-23 04:00:28.359731: step: 912/530, loss: 0.0017923356499522924
2023-01-23 04:00:29.458502: step: 916/530, loss: 0.00038485525874421
2023-01-23 04:00:30.588480: step: 920/530, loss: 0.007113933563232422
2023-01-23 04:00:31.667874: step: 924/530, loss: 0.00019497872563079
2023-01-23 04:00:32.774089: step: 928/530, loss: -2.6702882678364404e-06
2023-01-23 04:00:33.921565: step: 932/530, loss: 0.008819389156997204
2023-01-23 04:00:35.030195: step: 936/530, loss: 8.907318260753527e-05
2023-01-23 04:00:36.109251: step: 940/530, loss: 0.0006539822206832469
2023-01-23 04:00:37.205397: step: 944/530, loss: 0.017255211248993874
2023-01-23 04:00:38.315744: step: 948/530, loss: 0.0143890380859375
2023-01-23 04:00:39.404172: step: 952/530, loss: 0.008497429080307484
2023-01-23 04:00:40.487374: step: 956/530, loss: 0.01560201682150364
2023-01-23 04:00:41.572236: step: 960/530, loss: 0.00018668174743652344
2023-01-23 04:00:42.659344: step: 964/530, loss: 0.0010456085437908769
2023-01-23 04:00:43.758079: step: 968/530, loss: 1.5258789289873675e-06
2023-01-23 04:00:44.868177: step: 972/530, loss: 0.00011358261690475047
2023-01-23 04:00:45.960094: step: 976/530, loss: 0.0005155563121661544
2023-01-23 04:00:47.033879: step: 980/530, loss: 0.0016478538746014237
2023-01-23 04:00:48.138412: step: 984/530, loss: 0.001124572823755443
2023-01-23 04:00:49.299757: step: 988/530, loss: 0.03444557264447212
2023-01-23 04:00:50.399071: step: 992/530, loss: 0.0025963785592466593
2023-01-23 04:00:51.525414: step: 996/530, loss: 0.0007981777307577431
2023-01-23 04:00:52.656117: step: 1000/530, loss: 2.28881845032447e-06
2023-01-23 04:00:53.789967: step: 1004/530, loss: 0.00042552949162200093
2023-01-23 04:00:54.882609: step: 1008/530, loss: 0.0015125274658203125
2023-01-23 04:00:55.993640: step: 1012/530, loss: 3.256797936046496e-05
2023-01-23 04:00:57.112693: step: 1016/530, loss: 0.0007802963373251259
2023-01-23 04:00:58.197219: step: 1020/530, loss: 0.037128545343875885
2023-01-23 04:00:59.310335: step: 1024/530, loss: 0.00014419556828215718
2023-01-23 04:01:00.400422: step: 1028/530, loss: 0.0001985549897653982
2023-01-23 04:01:01.507564: step: 1032/530, loss: 0.018280314281582832
2023-01-23 04:01:02.611807: step: 1036/530, loss: 0.005886650178581476
2023-01-23 04:01:03.717674: step: 1040/530, loss: 0.037924766540527344
2023-01-23 04:01:04.805270: step: 1044/530, loss: 1.1444091796875e-05
2023-01-23 04:01:05.905656: step: 1048/530, loss: 0.020010853186249733
2023-01-23 04:01:06.991119: step: 1052/530, loss: 0.0058193206787109375
2023-01-23 04:01:08.085428: step: 1056/530, loss: 0.018397904932498932
2023-01-23 04:01:09.271745: step: 1060/530, loss: 0.0002628326474223286
2023-01-23 04:01:10.380511: step: 1064/530, loss: 0.0003414154052734375
2023-01-23 04:01:11.470558: step: 1068/530, loss: 0.002363014267757535
2023-01-23 04:01:12.560573: step: 1072/530, loss: 6.923675391590223e-05
2023-01-23 04:01:13.659452: step: 1076/530, loss: 3.070831371587701e-05
2023-01-23 04:01:14.757546: step: 1080/530, loss: 0.0001294136163778603
2023-01-23 04:01:15.863488: step: 1084/530, loss: 3.3903121220646426e-05
2023-01-23 04:01:16.942077: step: 1088/530, loss: 0.0008142471197061241
2023-01-23 04:01:18.027627: step: 1092/530, loss: 0.0005998611450195312
2023-01-23 04:01:19.121476: step: 1096/530, loss: -1.6689301673977752e-07
2023-01-23 04:01:20.218776: step: 1100/530, loss: 0.02089834213256836
2023-01-23 04:01:21.328256: step: 1104/530, loss: 0.0013528346316888928
2023-01-23 04:01:22.421762: step: 1108/530, loss: 0.013146591372787952
2023-01-23 04:01:23.535486: step: 1112/530, loss: 0.014933396130800247
2023-01-23 04:01:24.643608: step: 1116/530, loss: 0.004085540771484375
2023-01-23 04:01:25.726307: step: 1120/530, loss: 0.00102148053701967
2023-01-23 04:01:26.830444: step: 1124/530, loss: 4.625320343620842e-06
2023-01-23 04:01:27.943304: step: 1128/530, loss: 1.544952465337701e-05
2023-01-23 04:01:29.036016: step: 1132/530, loss: 0.013423156924545765
2023-01-23 04:01:30.155625: step: 1136/530, loss: 0.02184591442346573
2023-01-23 04:01:31.249715: step: 1140/530, loss: 0.03049163706600666
2023-01-23 04:01:32.362723: step: 1144/530, loss: 0.0017245293129235506
2023-01-23 04:01:33.486081: step: 1148/530, loss: 0.019046783447265625
2023-01-23 04:01:34.616705: step: 1152/530, loss: 0.013104438781738281
2023-01-23 04:01:35.727194: step: 1156/530, loss: 1.7166138377433526e-06
2023-01-23 04:01:36.842768: step: 1160/530, loss: 0.07359505444765091
2023-01-23 04:01:37.983146: step: 1164/530, loss: 0.002857208251953125
2023-01-23 04:01:39.075571: step: 1168/530, loss: 0.01428766269236803
2023-01-23 04:01:40.191037: step: 1172/530, loss: 0.0001465797540731728
2023-01-23 04:01:41.335033: step: 1176/530, loss: 0.0024166107177734375
2023-01-23 04:01:42.437022: step: 1180/530, loss: 2.422332727292087e-05
2023-01-23 04:01:43.543232: step: 1184/530, loss: 0.0417386032640934
2023-01-23 04:01:44.654646: step: 1188/530, loss: 0.002197265625
2023-01-23 04:01:45.759147: step: 1192/530, loss: 0.006925869267433882
2023-01-23 04:01:46.857755: step: 1196/530, loss: 0.0008164405589923263
2023-01-23 04:01:47.983101: step: 1200/530, loss: 3.814697265625e-06
2023-01-23 04:01:49.141081: step: 1204/530, loss: 0.12293558567762375
2023-01-23 04:01:50.264058: step: 1208/530, loss: 0.021139884367585182
2023-01-23 04:01:51.377816: step: 1212/530, loss: 0.00037450791569426656
2023-01-23 04:01:52.464302: step: 1216/530, loss: 0.0002123355952790007
2023-01-23 04:01:53.545133: step: 1220/530, loss: 0.0006303787231445312
2023-01-23 04:01:54.645635: step: 1224/530, loss: 9.460449655307457e-05
2023-01-23 04:01:55.736081: step: 1228/530, loss: 0.005875611677765846
2023-01-23 04:01:56.822467: step: 1232/530, loss: 0.0003562927304301411
2023-01-23 04:01:57.950399: step: 1236/530, loss: 0.0016563415993005037
2023-01-23 04:01:59.067080: step: 1240/530, loss: 0.0020252226386219263
2023-01-23 04:02:00.188506: step: 1244/530, loss: 0.003129387041553855
2023-01-23 04:02:01.294968: step: 1248/530, loss: 2.6607514882925898e-05
2023-01-23 04:02:02.383737: step: 1252/530, loss: 8.678436279296875e-05
2023-01-23 04:02:03.496268: step: 1256/530, loss: 4.08649466407951e-05
2023-01-23 04:02:04.581146: step: 1260/530, loss: 0.00042705534724518657
2023-01-23 04:02:05.681730: step: 1264/530, loss: 0.00036196707515046
2023-01-23 04:02:06.800518: step: 1268/530, loss: 0.002379512647166848
2023-01-23 04:02:07.885588: step: 1272/530, loss: 0.00021018982806708664
2023-01-23 04:02:08.983104: step: 1276/530, loss: 0.00013656615919899195
2023-01-23 04:02:10.110810: step: 1280/530, loss: 0.08921489864587784
2023-01-23 04:02:11.189406: step: 1284/530, loss: 0.5422126650810242
2023-01-23 04:02:12.284683: step: 1288/530, loss: 0.002125644823536277
2023-01-23 04:02:13.385107: step: 1292/530, loss: 0.0005640030140057206
2023-01-23 04:02:14.482343: step: 1296/530, loss: 5.7888031733455136e-05
2023-01-23 04:02:15.612444: step: 1300/530, loss: 0.0030906680040061474
2023-01-23 04:02:16.686511: step: 1304/530, loss: 0.0002229690580861643
2023-01-23 04:02:17.752154: step: 1308/530, loss: 0.022458650171756744
2023-01-23 04:02:18.868886: step: 1312/530, loss: 0.07224559783935547
2023-01-23 04:02:19.977062: step: 1316/530, loss: 0.002983188722282648
2023-01-23 04:02:21.077926: step: 1320/530, loss: 0.0032672882080078125
2023-01-23 04:02:22.178729: step: 1324/530, loss: 7.42912307032384e-05
2023-01-23 04:02:23.285410: step: 1328/530, loss: -1.277923547604587e-05
2023-01-23 04:02:24.371063: step: 1332/530, loss: 9.250640869140625e-05
2023-01-23 04:02:25.475224: step: 1336/530, loss: 0.0002472877677064389
2023-01-23 04:02:26.585776: step: 1340/530, loss: 0.0001846313534770161
2023-01-23 04:02:27.689953: step: 1344/530, loss: 0.0018259048229083419
2023-01-23 04:02:28.800020: step: 1348/530, loss: 0.015125465579330921
2023-01-23 04:02:29.920038: step: 1352/530, loss: 0.00010552406456554309
2023-01-23 04:02:31.005050: step: 1356/530, loss: 0.029802896082401276
2023-01-23 04:02:32.099547: step: 1360/530, loss: 0.009287071414291859
2023-01-23 04:02:33.229338: step: 1364/530, loss: 0.0016962051158770919
2023-01-23 04:02:34.351489: step: 1368/530, loss: 0.05070772022008896
2023-01-23 04:02:35.475216: step: 1372/530, loss: 0.0001220703125
2023-01-23 04:02:36.602612: step: 1376/530, loss: 0.0008016586070880294
2023-01-23 04:02:37.735641: step: 1380/530, loss: 0.12225323170423508
2023-01-23 04:02:38.846648: step: 1384/530, loss: 0.0001961708185262978
2023-01-23 04:02:39.953160: step: 1388/530, loss: 0.0018245697719976306
2023-01-23 04:02:41.056281: step: 1392/530, loss: 5.493163916980848e-05
2023-01-23 04:02:42.164480: step: 1396/530, loss: 3.62396240234375e-05
2023-01-23 04:02:43.265461: step: 1400/530, loss: 0.0017461300594732165
2023-01-23 04:02:44.369260: step: 1404/530, loss: 0.001063442206941545
2023-01-23 04:02:45.455030: step: 1408/530, loss: -2.6702882678364404e-06
2023-01-23 04:02:46.559500: step: 1412/530, loss: 2.2315980459097773e-05
2023-01-23 04:02:47.689425: step: 1416/530, loss: 0.15167808532714844
2023-01-23 04:02:48.799367: step: 1420/530, loss: 0.011538887396454811
2023-01-23 04:02:49.875589: step: 1424/530, loss: 0.02946019172668457
2023-01-23 04:02:51.018952: step: 1428/530, loss: 0.0005007744184695184
2023-01-23 04:02:52.149438: step: 1432/530, loss: 8.74519391800277e-05
2023-01-23 04:02:53.264147: step: 1436/530, loss: 0.007039070129394531
2023-01-23 04:02:54.373415: step: 1440/530, loss: 0.002211666200309992
2023-01-23 04:02:55.493751: step: 1444/530, loss: 0.002252769423648715
2023-01-23 04:02:56.611913: step: 1448/530, loss: 0.017626095563173294
2023-01-23 04:02:57.720293: step: 1452/530, loss: 0.04771079868078232
2023-01-23 04:02:58.817133: step: 1456/530, loss: 0.00021529197692871094
2023-01-23 04:02:59.893754: step: 1460/530, loss: 0.021303797140717506
2023-01-23 04:03:01.009620: step: 1464/530, loss: 0.021502112969756126
2023-01-23 04:03:02.106930: step: 1468/530, loss: 0.00021286010451149195
2023-01-23 04:03:03.186594: step: 1472/530, loss: 0.026974869892001152
2023-01-23 04:03:04.254465: step: 1476/530, loss: 0.03495273366570473
2023-01-23 04:03:05.386592: step: 1480/530, loss: 0.0011823654640465975
2023-01-23 04:03:06.514101: step: 1484/530, loss: 0.004939174745231867
2023-01-23 04:03:07.649282: step: 1488/530, loss: 0.035330772399902344
2023-01-23 04:03:08.743101: step: 1492/530, loss: 3.0231476557673886e-05
2023-01-23 04:03:09.866800: step: 1496/530, loss: 0.00087060930673033
2023-01-23 04:03:11.028133: step: 1500/530, loss: 0.001101589179597795
2023-01-23 04:03:12.183290: step: 1504/530, loss: 0.029007529839873314
2023-01-23 04:03:13.298949: step: 1508/530, loss: 4.138946678722277e-05
2023-01-23 04:03:14.402814: step: 1512/530, loss: 3.252029637224041e-05
2023-01-23 04:03:15.488394: step: 1516/530, loss: 0.005960798356682062
2023-01-23 04:03:16.609725: step: 1520/530, loss: 0.0016349792713299394
2023-01-23 04:03:17.738736: step: 1524/530, loss: 0.0010149001609534025
2023-01-23 04:03:18.827717: step: 1528/530, loss: 0.014621496200561523
2023-01-23 04:03:19.972011: step: 1532/530, loss: 6.217956251930445e-05
2023-01-23 04:03:21.068860: step: 1536/530, loss: 0.023708727210760117
2023-01-23 04:03:22.208926: step: 1540/530, loss: 0.009775924496352673
2023-01-23 04:03:23.324698: step: 1544/530, loss: 0.05845604091882706
2023-01-23 04:03:24.439212: step: 1548/530, loss: 0.0002932548522949219
2023-01-23 04:03:25.577097: step: 1552/530, loss: 0.0006668090936727822
2023-01-23 04:03:26.656713: step: 1556/530, loss: 0.004498577211052179
2023-01-23 04:03:27.781794: step: 1560/530, loss: 0.0006767273298464715
2023-01-23 04:03:28.914093: step: 1564/530, loss: 0.0002667427179403603
2023-01-23 04:03:30.026402: step: 1568/530, loss: 0.07163677364587784
2023-01-23 04:03:31.155034: step: 1572/530, loss: 0.0012791634071618319
2023-01-23 04:03:32.265017: step: 1576/530, loss: 0.01545562781393528
2023-01-23 04:03:33.361324: step: 1580/530, loss: 0.052401352673769
2023-01-23 04:03:34.443892: step: 1584/530, loss: 0.0019769668579101562
2023-01-23 04:03:35.547118: step: 1588/530, loss: 8.58306884765625e-06
2023-01-23 04:03:36.626403: step: 1592/530, loss: 0.07593629509210587
2023-01-23 04:03:37.729086: step: 1596/530, loss: 0.0024896622635424137
2023-01-23 04:03:38.848545: step: 1600/530, loss: 0.02565021626651287
2023-01-23 04:03:39.969443: step: 1604/530, loss: 0.04879875108599663
2023-01-23 04:03:41.058473: step: 1608/530, loss: 0.02191152609884739
2023-01-23 04:03:42.156404: step: 1612/530, loss: 0.0007493972661904991
2023-01-23 04:03:43.232338: step: 1616/530, loss: 6.86645489622606e-06
2023-01-23 04:03:44.336702: step: 1620/530, loss: 1.4066696166992188e-05
2023-01-23 04:03:45.462821: step: 1624/530, loss: 0.001956462860107422
2023-01-23 04:03:46.607077: step: 1628/530, loss: 0.0011052131885662675
2023-01-23 04:03:47.722700: step: 1632/530, loss: 3.008842577401083e-05
2023-01-23 04:03:48.846058: step: 1636/530, loss: 0.06111621856689453
2023-01-23 04:03:49.967122: step: 1640/530, loss: 0.0961918830871582
2023-01-23 04:03:51.041781: step: 1644/530, loss: 0.0366147980093956
2023-01-23 04:03:52.158458: step: 1648/530, loss: 0.00013875961303710938
2023-01-23 04:03:53.254087: step: 1652/530, loss: 0.00020456314086914062
2023-01-23 04:03:54.327294: step: 1656/530, loss: 0.00014743805513717234
2023-01-23 04:03:55.460649: step: 1660/530, loss: 0.026435280218720436
2023-01-23 04:03:56.578938: step: 1664/530, loss: 0.013074684888124466
2023-01-23 04:03:57.709994: step: 1668/530, loss: 0.0015708922874182463
2023-01-23 04:03:58.777367: step: 1672/530, loss: 7.028579420875758e-05
2023-01-23 04:03:59.878323: step: 1676/530, loss: 0.02171039581298828
2023-01-23 04:04:00.981229: step: 1680/530, loss: 0.00040426256600767374
2023-01-23 04:04:02.074272: step: 1684/530, loss: 0.0002588272327557206
2023-01-23 04:04:03.181115: step: 1688/530, loss: 0.016860390082001686
2023-01-23 04:04:04.304254: step: 1692/530, loss: 0.000698089599609375
2023-01-23 04:04:05.382281: step: 1696/530, loss: 0.00045871734619140625
2023-01-23 04:04:06.463165: step: 1700/530, loss: 0.010169411078095436
2023-01-23 04:04:07.583646: step: 1704/530, loss: 0.0022070587147027254
2023-01-23 04:04:08.670501: step: 1708/530, loss: 3.0040741876291577e-06
2023-01-23 04:04:09.773547: step: 1712/530, loss: 0.003843927290290594
2023-01-23 04:04:10.897015: step: 1716/530, loss: 0.027553748339414597
2023-01-23 04:04:11.997761: step: 1720/530, loss: 0.00010032654245151207
2023-01-23 04:04:13.098641: step: 1724/530, loss: 6.471872620750219e-05
2023-01-23 04:04:14.214990: step: 1728/530, loss: 0.012194443494081497
2023-01-23 04:04:15.333020: step: 1732/530, loss: 0.0004935264587402344
2023-01-23 04:04:16.429054: step: 1736/530, loss: 0.0001237869291799143
2023-01-23 04:04:17.509386: step: 1740/530, loss: 0.0044682505540549755
2023-01-23 04:04:18.616143: step: 1744/530, loss: 0.009037971496582031
2023-01-23 04:04:19.713481: step: 1748/530, loss: 0.0004528045537881553
2023-01-23 04:04:20.812124: step: 1752/530, loss: 0.008081579580903053
2023-01-23 04:04:21.896153: step: 1756/530, loss: 0.09083328396081924
2023-01-23 04:04:23.040256: step: 1760/530, loss: 9.212493750965223e-05
2023-01-23 04:04:24.135592: step: 1764/530, loss: 0.019496917724609375
2023-01-23 04:04:25.216522: step: 1768/530, loss: 0.06898327171802521
2023-01-23 04:04:26.326902: step: 1772/530, loss: 0.00013227462477516383
2023-01-23 04:04:27.438958: step: 1776/530, loss: 0.0004791736719198525
2023-01-23 04:04:28.547828: step: 1780/530, loss: 0.0001474380405852571
2023-01-23 04:04:29.643647: step: 1784/530, loss: 2.0122528439969756e-05
2023-01-23 04:04:30.732329: step: 1788/530, loss: 2.2888182229507947e-06
2023-01-23 04:04:31.847133: step: 1792/530, loss: 0.0007535934564657509
2023-01-23 04:04:32.942639: step: 1796/530, loss: 0.0009433747036382556
2023-01-23 04:04:34.055677: step: 1800/530, loss: 0.0003368377801962197
2023-01-23 04:04:35.172221: step: 1804/530, loss: 0.0006818771944381297
2023-01-23 04:04:36.251675: step: 1808/530, loss: 0.014892674051225185
2023-01-23 04:04:37.349817: step: 1812/530, loss: 1.8644332158146426e-05
2023-01-23 04:04:38.466404: step: 1816/530, loss: 0.01797199249267578
2023-01-23 04:04:39.593497: step: 1820/530, loss: 0.007116890046745539
2023-01-23 04:04:40.665257: step: 1824/530, loss: 0.00049591064453125
2023-01-23 04:04:41.790361: step: 1828/530, loss: 0.01926250569522381
2023-01-23 04:04:42.871231: step: 1832/530, loss: 0.002722835401073098
2023-01-23 04:04:43.973114: step: 1836/530, loss: 0.00034370424691587687
2023-01-23 04:04:45.058664: step: 1840/530, loss: 0.0001274108944926411
2023-01-23 04:04:46.182376: step: 1844/530, loss: 2.307891918462701e-05
2023-01-23 04:04:47.284005: step: 1848/530, loss: -5.722044988942798e-07
2023-01-23 04:04:48.390351: step: 1852/530, loss: 0.0025342940352857113
2023-01-23 04:04:49.473680: step: 1856/530, loss: 4.8446658183820546e-05
2023-01-23 04:04:50.573662: step: 1860/530, loss: 8.716583397472277e-05
2023-01-23 04:04:51.669367: step: 1864/530, loss: 0.018255997449159622
2023-01-23 04:04:52.763695: step: 1868/530, loss: 0.024232864379882812
2023-01-23 04:04:53.895171: step: 1872/530, loss: 0.0029203416779637337
2023-01-23 04:04:55.004855: step: 1876/530, loss: 8.077621896518394e-05
2023-01-23 04:04:56.122488: step: 1880/530, loss: 0.0002073288051178679
2023-01-23 04:04:57.217806: step: 1884/530, loss: 0.003910255618393421
2023-01-23 04:04:58.352323: step: 1888/530, loss: 0.00177345285192132
2023-01-23 04:04:59.476399: step: 1892/530, loss: 0.023700904101133347
2023-01-23 04:05:00.586348: step: 1896/530, loss: 0.008883285336196423
2023-01-23 04:05:01.703916: step: 1900/530, loss: 1.6689300537109375e-05
2023-01-23 04:05:02.808630: step: 1904/530, loss: 0.0009330749744549394
2023-01-23 04:05:03.928506: step: 1908/530, loss: 0.0004020690976176411
2023-01-23 04:05:05.053326: step: 1912/530, loss: 0.00103168492205441
2023-01-23 04:05:06.149790: step: 1916/530, loss: 2.288818359375e-05
2023-01-23 04:05:07.270056: step: 1920/530, loss: 0.0003933906555175781
2023-01-23 04:05:08.411734: step: 1924/530, loss: 0.008941269479691982
2023-01-23 04:05:09.519183: step: 1928/530, loss: 0.0024581910111010075
2023-01-23 04:05:10.602040: step: 1932/530, loss: 2.4890900022001006e-05
2023-01-23 04:05:11.710588: step: 1936/530, loss: 0.004462289623916149
2023-01-23 04:05:12.821378: step: 1940/530, loss: 0.01343617495149374
2023-01-23 04:05:13.910772: step: 1944/530, loss: 0.005720329470932484
2023-01-23 04:05:14.991534: step: 1948/530, loss: 2.19345088225964e-06
2023-01-23 04:05:16.084109: step: 1952/530, loss: 0.006926346104592085
2023-01-23 04:05:17.205135: step: 1956/530, loss: 0.049279119819402695
2023-01-23 04:05:18.329559: step: 1960/530, loss: 5.493163916980848e-05
2023-01-23 04:05:19.420255: step: 1964/530, loss: 0.0014108658069744706
2023-01-23 04:05:20.525620: step: 1968/530, loss: 0.012261772528290749
2023-01-23 04:05:21.648453: step: 1972/530, loss: 0.08735714107751846
2023-01-23 04:05:22.751573: step: 1976/530, loss: 0.0006707191932946444
2023-01-23 04:05:23.834529: step: 1980/530, loss: 0.00034465789212845266
2023-01-23 04:05:24.918884: step: 1984/530, loss: 0.00010528564598644152
2023-01-23 04:05:26.016246: step: 1988/530, loss: 0.007911848835647106
2023-01-23 04:05:27.096092: step: 1992/530, loss: 0.0011487960582599044
2023-01-23 04:05:28.193609: step: 1996/530, loss: 0.00415878277271986
2023-01-23 04:05:29.295486: step: 2000/530, loss: 0.000102996826171875
2023-01-23 04:05:30.396599: step: 2004/530, loss: 0.010316086001694202
2023-01-23 04:05:31.534515: step: 2008/530, loss: 0.0009088516235351562
2023-01-23 04:05:32.642370: step: 2012/530, loss: 0.03199787437915802
2023-01-23 04:05:33.778853: step: 2016/530, loss: 0.008266925811767578
2023-01-23 04:05:34.898653: step: 2020/530, loss: 0.0008687973022460938
2023-01-23 04:05:35.981944: step: 2024/530, loss: 0.007015037350356579
2023-01-23 04:05:37.093604: step: 2028/530, loss: 1.9073468138230965e-07
2023-01-23 04:05:38.219349: step: 2032/530, loss: 0.0005262374761514366
2023-01-23 04:05:39.344285: step: 2036/530, loss: 0.0008533478248864412
2023-01-23 04:05:40.459604: step: 2040/530, loss: 3.719329833984375e-05
2023-01-23 04:05:41.570195: step: 2044/530, loss: 0.020283222198486328
2023-01-23 04:05:42.678598: step: 2048/530, loss: 0.05246772617101669
2023-01-23 04:05:43.778473: step: 2052/530, loss: 9.72747784544481e-06
2023-01-23 04:05:44.888938: step: 2056/530, loss: 0.002403640653938055
2023-01-23 04:05:45.979747: step: 2060/530, loss: 0.007567406166344881
2023-01-23 04:05:47.079488: step: 2064/530, loss: 0.09182777255773544
2023-01-23 04:05:48.199071: step: 2068/530, loss: 4.158019874012098e-05
2023-01-23 04:05:49.304528: step: 2072/530, loss: 0.0003243446408305317
2023-01-23 04:05:50.410290: step: 2076/530, loss: 0.035164546221494675
2023-01-23 04:05:51.504628: step: 2080/530, loss: 0.001502227853052318
2023-01-23 04:05:52.623590: step: 2084/530, loss: 0.02115955390036106
2023-01-23 04:05:53.739340: step: 2088/530, loss: 1.144409225162235e-06
2023-01-23 04:05:54.849532: step: 2092/530, loss: 0.0027053833473473787
2023-01-23 04:05:55.973177: step: 2096/530, loss: 0.0006269455188885331
2023-01-23 04:05:57.061172: step: 2100/530, loss: 0.0007406235090456903
2023-01-23 04:05:58.171080: step: 2104/530, loss: 0.004179859068244696
2023-01-23 04:05:59.287944: step: 2108/530, loss: 0.012934589758515358
2023-01-23 04:06:00.399673: step: 2112/530, loss: 0.14338044822216034
2023-01-23 04:06:01.489685: step: 2116/530, loss: 9.632110959501006e-06
2023-01-23 04:06:02.623374: step: 2120/530, loss: 3.032684253412299e-05
==================================================
Loss: 0.012
--------------------
Dev: {'event': {'p': 0.5743639921722113, 'r': 0.7816245006657789, 'f1': 0.6621545403271291}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
Test: {'event': {'p': 0.6367774237596723, 'r': 0.8152680652680653, 'f1': 0.7150523894709941}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
Chinese: {'event': {'p': 0.5974025974025974, 'r': 0.8518518518518519, 'f1': 0.7022900763358778}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
Korean: {'event': {'p': 0.6101694915254238, 'r': 0.5714285714285714, 'f1': 0.5901639344262296}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
Russian: {'event': {'p': 0.4878048780487805, 'r': 0.5555555555555556, 'f1': 0.5194805194805195}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 26}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6449771689497716, 'r': 0.7523302263648469, 'f1': 0.6945298094652735}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Chinese: {'event': {'p': 0.6692644909887969, 'r': 0.8006993006993007, 'f1': 0.7291058636243036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Chinese: {'event': {'p': 0.6764705882352942, 'r': 0.8518518518518519, 'f1': 0.7540983606557378}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5873340143003064, 'r': 0.7656458055925432, 'f1': 0.6647398843930636}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Eng Test for Korean: {'event': {'p': 0.6496487119437939, 'r': 0.8082750582750583, 'f1': 0.7203323811996885}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Sample Korean: {'event': {'p': 0.6721311475409836, 'r': 0.6507936507936508, 'f1': 0.6612903225806451}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5971370143149284, 'r': 0.7776298268974701, 'f1': 0.6755349913244649}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Russian: {'event': {'p': 0.6401673640167364, 'r': 0.8024475524475524, 'f1': 0.7121799844840963}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Russian: {'event': {'p': 0.5897435897435898, 'r': 0.6388888888888888, 'f1': 0.6133333333333332}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
******************************
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 04:06:42.020726: step: 4/530, loss: 0.0010096549522131681
2023-01-23 04:06:43.145732: step: 8/530, loss: 0.00012464524479582906
2023-01-23 04:06:44.230864: step: 12/530, loss: 0.0027126313652843237
2023-01-23 04:06:45.355307: step: 16/530, loss: 0.0016362189780920744
2023-01-23 04:06:46.461944: step: 20/530, loss: 0.0075286864303052425
2023-01-23 04:06:47.562520: step: 24/530, loss: 0.002128791995346546
2023-01-23 04:06:48.695092: step: 28/530, loss: 0.021907806396484375
2023-01-23 04:06:49.797764: step: 32/530, loss: 2.870559910661541e-05
2023-01-23 04:06:50.903367: step: 36/530, loss: 0.0001319885195698589
2023-01-23 04:06:51.989621: step: 40/530, loss: 0.035663798451423645
2023-01-23 04:06:53.104705: step: 44/530, loss: 0.0008243561023846269
2023-01-23 04:06:54.225557: step: 48/530, loss: 1.220703143189894e-05
2023-01-23 04:06:55.312921: step: 52/530, loss: 6.389617919921875e-05
2023-01-23 04:06:56.409137: step: 56/530, loss: 0.0003759383980650455
2023-01-23 04:06:57.507733: step: 60/530, loss: 0.004250288475304842
2023-01-23 04:06:58.615096: step: 64/530, loss: 0.0003361701965332031
2023-01-23 04:06:59.730883: step: 68/530, loss: 8.487702143611386e-05
2023-01-23 04:07:00.841981: step: 72/530, loss: 0.00279064173810184
2023-01-23 04:07:01.957487: step: 76/530, loss: 2.212524486822076e-05
2023-01-23 04:07:03.112190: step: 80/530, loss: 0.00035953521728515625
2023-01-23 04:07:04.217532: step: 84/530, loss: 0.00030746462289243937
2023-01-23 04:07:05.307877: step: 88/530, loss: 7.82012921263231e-06
2023-01-23 04:07:06.391347: step: 92/530, loss: 0.0002442359982524067
2023-01-23 04:07:07.497346: step: 96/530, loss: -1.5258790426742053e-06
2023-01-23 04:07:08.594388: step: 100/530, loss: 0.0008955001831054688
2023-01-23 04:07:09.685260: step: 104/530, loss: 0.0049835206009447575
2023-01-23 04:07:10.776474: step: 108/530, loss: 0.003570556640625
2023-01-23 04:07:11.866054: step: 112/530, loss: 5.435943421616685e-06
2023-01-23 04:07:12.998831: step: 116/530, loss: 0.005488777533173561
2023-01-23 04:07:14.128439: step: 120/530, loss: 0.7814303040504456
2023-01-23 04:07:15.244949: step: 124/530, loss: 0.012199878692626953
2023-01-23 04:07:16.311043: step: 128/530, loss: 0.0003070831298828125
2023-01-23 04:07:17.419729: step: 132/530, loss: 0.0020907402504235506
2023-01-23 04:07:18.547239: step: 136/530, loss: 0.008513259701430798
2023-01-23 04:07:19.650656: step: 140/530, loss: 0.00013484954251907766
2023-01-23 04:07:20.730330: step: 144/530, loss: 5.340576535672881e-05
2023-01-23 04:07:21.820680: step: 148/530, loss: 0.00028133392333984375
2023-01-23 04:07:22.905329: step: 152/530, loss: 0.0003326416190247983
2023-01-23 04:07:24.020336: step: 156/530, loss: 0.0008787155384197831
2023-01-23 04:07:25.156915: step: 160/530, loss: 2.4175644284696318e-05
2023-01-23 04:07:26.272206: step: 164/530, loss: 0.0069141392596066
2023-01-23 04:07:27.376892: step: 168/530, loss: 0.0025159837678074837
2023-01-23 04:07:28.474781: step: 172/530, loss: 1.564025842526462e-05
2023-01-23 04:07:29.599594: step: 176/530, loss: 2.8610230629055877e-07
2023-01-23 04:07:30.761511: step: 180/530, loss: 7.896422903286293e-05
2023-01-23 04:07:31.897458: step: 184/530, loss: 3.051757857974735e-06
2023-01-23 04:07:33.006626: step: 188/530, loss: 5.7983401347883046e-05
2023-01-23 04:07:34.117522: step: 192/530, loss: 0.0006700515514239669
2023-01-23 04:07:35.225503: step: 196/530, loss: -6.3896181927702855e-06
2023-01-23 04:07:36.354256: step: 200/530, loss: 3.280639793956652e-05
2023-01-23 04:07:37.489714: step: 204/530, loss: 1.1444094525359105e-06
2023-01-23 04:07:38.574516: step: 208/530, loss: 0.018450547009706497
2023-01-23 04:07:39.677932: step: 212/530, loss: 0.004146575927734375
2023-01-23 04:07:40.776414: step: 216/530, loss: 1.049041748046875e-05
2023-01-23 04:07:41.869108: step: 220/530, loss: 0.0004729270876850933
2023-01-23 04:07:42.976604: step: 224/530, loss: 0.02790956385433674
2023-01-23 04:07:44.071201: step: 228/530, loss: 0.07359971106052399
2023-01-23 04:07:45.150159: step: 232/530, loss: 0.008219147101044655
2023-01-23 04:07:46.241889: step: 236/530, loss: 9.632110959501006e-06
2023-01-23 04:07:47.360613: step: 240/530, loss: 0.0003383636649232358
2023-01-23 04:07:48.480770: step: 244/530, loss: 0.00019979476928710938
2023-01-23 04:07:49.587846: step: 248/530, loss: 0.000308799761114642
2023-01-23 04:07:50.712986: step: 252/530, loss: 0.0016082765068858862
2023-01-23 04:07:51.786735: step: 256/530, loss: 0.05128088220953941
2023-01-23 04:07:52.896837: step: 260/530, loss: 0.004553794860839844
2023-01-23 04:07:54.015122: step: 264/530, loss: 0.003433799836784601
2023-01-23 04:07:55.118028: step: 268/530, loss: 1.4209746950655244e-05
2023-01-23 04:07:56.196971: step: 272/530, loss: 0.00014991761418059468
2023-01-23 04:07:57.299708: step: 276/530, loss: 0.022023772820830345
2023-01-23 04:07:58.423611: step: 280/530, loss: 0.0008543014409951866
2023-01-23 04:07:59.534269: step: 284/530, loss: 0.007998799905180931
2023-01-23 04:08:00.631216: step: 288/530, loss: 1.3256072634248994e-05
2023-01-23 04:08:01.724714: step: 292/530, loss: 0.01682457886636257
2023-01-23 04:08:02.846755: step: 296/530, loss: 0.019149303436279297
2023-01-23 04:08:03.955033: step: 300/530, loss: 0.00010976791236316785
2023-01-23 04:08:05.042276: step: 304/530, loss: 0.0038158418610692024
2023-01-23 04:08:06.188183: step: 308/530, loss: 0.0002145290345652029
2023-01-23 04:08:07.313522: step: 312/530, loss: 0.00022230147442314774
2023-01-23 04:08:08.409928: step: 316/530, loss: 0.015474510379135609
2023-01-23 04:08:09.502183: step: 320/530, loss: 0.0010788918007165194
2023-01-23 04:08:10.596662: step: 324/530, loss: 0.00108509068377316
2023-01-23 04:08:11.742345: step: 328/530, loss: 0.015140295028686523
2023-01-23 04:08:12.871833: step: 332/530, loss: 0.001922607421875
2023-01-23 04:08:13.989874: step: 336/530, loss: 0.0005485534784384072
2023-01-23 04:08:15.138303: step: 340/530, loss: 0.0006781578413210809
2023-01-23 04:08:16.225177: step: 344/530, loss: -1.1157990229548886e-05
2023-01-23 04:08:17.311397: step: 348/530, loss: 0.0023775100708007812
2023-01-23 04:08:18.421329: step: 352/530, loss: 0.03296509012579918
2023-01-23 04:08:19.490228: step: 356/530, loss: 0.021395349875092506
2023-01-23 04:08:20.584785: step: 360/530, loss: 2.6798248654813506e-05
2023-01-23 04:08:21.675860: step: 364/530, loss: 0.005473041906952858
2023-01-23 04:08:22.762670: step: 368/530, loss: 0.002603721572086215
2023-01-23 04:08:23.891137: step: 372/530, loss: 0.005002403166145086
2023-01-23 04:08:24.972928: step: 376/530, loss: 0.00012664793757721782
2023-01-23 04:08:26.045881: step: 380/530, loss: 2.0408631826285273e-05
2023-01-23 04:08:27.135159: step: 384/530, loss: 3.051757857974735e-06
2023-01-23 04:08:28.228744: step: 388/530, loss: 0.0010314941173419356
2023-01-23 04:08:29.408400: step: 392/530, loss: 0.007472324185073376
2023-01-23 04:08:30.521036: step: 396/530, loss: 0.00023345947556663305
2023-01-23 04:08:31.612917: step: 400/530, loss: 0.008788490667939186
2023-01-23 04:08:32.713674: step: 404/530, loss: 1.9073486328125e-06
2023-01-23 04:08:33.840429: step: 408/530, loss: 0.012767791748046875
2023-01-23 04:08:34.950727: step: 412/530, loss: 0.0020271302200853825
2023-01-23 04:08:36.033388: step: 416/530, loss: 5.073547436040826e-05
2023-01-23 04:08:37.125674: step: 420/530, loss: 0.0002856254577636719
2023-01-23 04:08:38.214286: step: 424/530, loss: 0.016585826873779297
2023-01-23 04:08:39.325698: step: 428/530, loss: 0.06579236686229706
2023-01-23 04:08:40.452192: step: 432/530, loss: 0.00033884047297760844
2023-01-23 04:08:41.547392: step: 436/530, loss: 5.3882598876953125e-05
2023-01-23 04:08:42.643144: step: 440/530, loss: 5.340576535672881e-06
2023-01-23 04:08:43.741178: step: 444/530, loss: 0.01808910444378853
2023-01-23 04:08:44.851928: step: 448/530, loss: 0.0004714965762104839
2023-01-23 04:08:45.935969: step: 452/530, loss: 3.566742088878527e-05
2023-01-23 04:08:47.036762: step: 456/530, loss: 0.000152587890625
2023-01-23 04:08:48.116895: step: 460/530, loss: 0.0021878243423998356
2023-01-23 04:08:49.227008: step: 464/530, loss: 9.5367431640625e-05
2023-01-23 04:08:50.347380: step: 468/530, loss: 6.446838960982859e-05
2023-01-23 04:08:51.455358: step: 472/530, loss: 0.011886215768754482
2023-01-23 04:08:52.529774: step: 476/530, loss: 9.579658217262477e-05
2023-01-23 04:08:53.642663: step: 480/530, loss: 0.0019781114533543587
2023-01-23 04:08:54.752186: step: 484/530, loss: 2.6512147087487392e-05
2023-01-23 04:08:55.839789: step: 488/530, loss: 0.00591201800853014
2023-01-23 04:08:56.967530: step: 492/530, loss: 0.0002845764101948589
2023-01-23 04:08:58.049950: step: 496/530, loss: -2.6702878130890895e-06
2023-01-23 04:08:59.180127: step: 500/530, loss: 6.580352783203125e-05
2023-01-23 04:09:00.306107: step: 504/530, loss: 3.271103196311742e-05
2023-01-23 04:09:01.395466: step: 508/530, loss: 0.000152587890625
2023-01-23 04:09:02.487194: step: 512/530, loss: 0.002174949739128351
2023-01-23 04:09:03.586078: step: 516/530, loss: 0.2822275161743164
2023-01-23 04:09:04.710705: step: 520/530, loss: 0.0025876997970044613
2023-01-23 04:09:05.786285: step: 524/530, loss: 0.0001642227143747732
2023-01-23 04:09:06.879718: step: 528/530, loss: 0.023834228515625
2023-01-23 04:09:07.985415: step: 532/530, loss: 0.003063678741455078
2023-01-23 04:09:09.088293: step: 536/530, loss: 0.008183956146240234
2023-01-23 04:09:10.211825: step: 540/530, loss: 5.912781489314511e-06
2023-01-23 04:09:11.288728: step: 544/530, loss: 0.0005004882696084678
2023-01-23 04:09:12.387332: step: 548/530, loss: 1.029968279908644e-05
2023-01-23 04:09:13.479613: step: 552/530, loss: 0.007947539910674095
2023-01-23 04:09:14.594941: step: 556/530, loss: 0.0004594803031068295
2023-01-23 04:09:15.674390: step: 560/530, loss: 5.722044988942798e-07
2023-01-23 04:09:16.781625: step: 564/530, loss: 7.915496826171875e-05
2023-01-23 04:09:17.833150: step: 568/530, loss: 0.004147338680922985
2023-01-23 04:09:18.957352: step: 572/530, loss: 0.00020313262939453125
2023-01-23 04:09:20.045598: step: 576/530, loss: 0.0012911796802654862
2023-01-23 04:09:21.139280: step: 580/530, loss: 0.03221764788031578
2023-01-23 04:09:22.249723: step: 584/530, loss: 0.0023469924926757812
2023-01-23 04:09:23.321106: step: 588/530, loss: 0.0006121456390246749
2023-01-23 04:09:24.470226: step: 592/530, loss: -9.632110959501006e-06
2023-01-23 04:09:25.570129: step: 596/530, loss: 1.926422191900201e-05
2023-01-23 04:09:26.669149: step: 600/530, loss: 2.1362306142691523e-05
2023-01-23 04:09:27.738775: step: 604/530, loss: 0.000508213066495955
2023-01-23 04:09:28.876359: step: 608/530, loss: 8.96453857421875e-05
2023-01-23 04:09:29.963614: step: 612/530, loss: 5.292892637953628e-06
2023-01-23 04:09:31.061075: step: 616/530, loss: 0.003673267550766468
2023-01-23 04:09:32.165267: step: 620/530, loss: 0.01336822472512722
2023-01-23 04:09:33.274042: step: 624/530, loss: 0.0013370513916015625
2023-01-23 04:09:34.412041: step: 628/530, loss: 0.0011447906726971269
2023-01-23 04:09:35.558361: step: 632/530, loss: 5.14984139954322e-06
2023-01-23 04:09:36.705638: step: 636/530, loss: 0.00775146484375
2023-01-23 04:09:37.796883: step: 640/530, loss: 0.00015583037748001516
2023-01-23 04:09:38.916757: step: 644/530, loss: 0.0515630729496479
2023-01-23 04:09:40.014706: step: 648/530, loss: 0.00110034947283566
2023-01-23 04:09:41.116033: step: 652/530, loss: 0.0018465042812749743
2023-01-23 04:09:42.214564: step: 656/530, loss: 0.00016059876361396164
2023-01-23 04:09:43.315465: step: 660/530, loss: 0.007879448123276234
2023-01-23 04:09:44.434373: step: 664/530, loss: 9.965896606445312e-05
2023-01-23 04:09:45.535322: step: 668/530, loss: 3.4046173823298886e-05
2023-01-23 04:09:46.608167: step: 672/530, loss: 0.0016366958152502775
2023-01-23 04:09:47.705474: step: 676/530, loss: 1.0490417707842425e-06
2023-01-23 04:09:48.825367: step: 680/530, loss: 4.8351288569392636e-05
2023-01-23 04:09:49.909974: step: 684/530, loss: 2.4366378056583926e-05
2023-01-23 04:09:51.014631: step: 688/530, loss: 2.0122528439969756e-05
2023-01-23 04:09:52.109236: step: 692/530, loss: 0.02140960842370987
2023-01-23 04:09:53.220959: step: 696/530, loss: 1.9550323486328125e-05
2023-01-23 04:09:54.313676: step: 700/530, loss: 2.2411346435546875e-05
2023-01-23 04:09:55.392211: step: 704/530, loss: 0.004517364781349897
2023-01-23 04:09:56.475915: step: 708/530, loss: 0.004183006472885609
2023-01-23 04:09:57.549787: step: 712/530, loss: 0.00036644935607910156
2023-01-23 04:09:58.649168: step: 716/530, loss: 0.00021810532780364156
2023-01-23 04:09:59.744539: step: 720/530, loss: 3.643035961431451e-05
2023-01-23 04:10:00.854229: step: 724/530, loss: 0.00020451545424293727
2023-01-23 04:10:01.980442: step: 728/530, loss: 0.022845841944217682
2023-01-23 04:10:03.095245: step: 732/530, loss: 7.963180905790068e-06
2023-01-23 04:10:04.202624: step: 736/530, loss: 0.1205991730093956
2023-01-23 04:10:05.294155: step: 740/530, loss: 0.0001256942778127268
2023-01-23 04:10:06.407831: step: 744/530, loss: 0.0001307010679738596
2023-01-23 04:10:07.502287: step: 748/530, loss: 7.534027099609375e-05
2023-01-23 04:10:08.622310: step: 752/530, loss: 2.2888179955771193e-06
2023-01-23 04:10:09.716806: step: 756/530, loss: 0.0009071350214071572
2023-01-23 04:10:10.829982: step: 760/530, loss: 3.728866431629285e-05
2023-01-23 04:10:11.942639: step: 764/530, loss: 2.346038854739163e-05
2023-01-23 04:10:13.046770: step: 768/530, loss: 5.416870044427924e-05
2023-01-23 04:10:14.147615: step: 772/530, loss: 0.0007337570423260331
2023-01-23 04:10:15.240624: step: 776/530, loss: 0.0025575635954737663
2023-01-23 04:10:16.359834: step: 780/530, loss: 0.00017578601546119899
2023-01-23 04:10:17.445106: step: 784/530, loss: 0.0004924774402752519
2023-01-23 04:10:18.539321: step: 788/530, loss: 0.0032939910888671875
2023-01-23 04:10:19.646603: step: 792/530, loss: 0.0022895813453942537
2023-01-23 04:10:20.734426: step: 796/530, loss: 0.0001958847133209929
2023-01-23 04:10:21.834976: step: 800/530, loss: 4.10556785936933e-05
2023-01-23 04:10:22.960716: step: 804/530, loss: 0.019309282302856445
2023-01-23 04:10:24.077754: step: 808/530, loss: 0.03515605628490448
2023-01-23 04:10:25.192396: step: 812/530, loss: 0.0006406784523278475
2023-01-23 04:10:26.296733: step: 816/530, loss: 0.0013569355942308903
2023-01-23 04:10:27.438476: step: 820/530, loss: 0.019174957647919655
2023-01-23 04:10:28.537215: step: 824/530, loss: 9.5367431640625e-07
2023-01-23 04:10:29.631008: step: 828/530, loss: 0.0001541137753520161
2023-01-23 04:10:30.751341: step: 832/530, loss: 0.0008588791242800653
2023-01-23 04:10:31.850661: step: 836/530, loss: 0.00534133892506361
2023-01-23 04:10:32.942349: step: 840/530, loss: 0.0001928329438669607
2023-01-23 04:10:34.015950: step: 844/530, loss: 0.00010194779315497726
2023-01-23 04:10:35.164365: step: 848/530, loss: 2.57015235547442e-05
2023-01-23 04:10:36.292624: step: 852/530, loss: 0.0002609252987895161
2023-01-23 04:10:37.370673: step: 856/530, loss: 3.42369094141759e-05
2023-01-23 04:10:38.462316: step: 860/530, loss: 4.100799560546875e-05
2023-01-23 04:10:39.574792: step: 864/530, loss: 0.0002229690580861643
2023-01-23 04:10:40.684720: step: 868/530, loss: 0.001729011652059853
2023-01-23 04:10:41.790464: step: 872/530, loss: 0.0005086899036541581
2023-01-23 04:10:42.887460: step: 876/530, loss: 7.62939453125e-06
2023-01-23 04:10:43.977048: step: 880/530, loss: 0.00961842481046915
2023-01-23 04:10:45.083655: step: 884/530, loss: 0.00019292833167128265
2023-01-23 04:10:46.184037: step: 888/530, loss: 0.0027963637840002775
2023-01-23 04:10:47.277612: step: 892/530, loss: 0.0016664504073560238
2023-01-23 04:10:48.387567: step: 896/530, loss: 0.18164244294166565
2023-01-23 04:10:49.509755: step: 900/530, loss: 9.784698340808973e-05
2023-01-23 04:10:50.597263: step: 904/530, loss: 0.009173869155347347
2023-01-23 04:10:51.693949: step: 908/530, loss: 0.0009234428871423006
2023-01-23 04:10:52.811020: step: 912/530, loss: 0.0015529155498370528
2023-01-23 04:10:53.901357: step: 916/530, loss: 0.0032547474838793278
2023-01-23 04:10:55.021964: step: 920/530, loss: 0.004950427915900946
2023-01-23 04:10:56.106893: step: 924/530, loss: 0.00021562576876021922
2023-01-23 04:10:57.225683: step: 928/530, loss: 1.678466833254788e-05
2023-01-23 04:10:58.300305: step: 932/530, loss: 0.008465195074677467
2023-01-23 04:10:59.434767: step: 936/530, loss: 1.506805438111769e-05
2023-01-23 04:11:00.542179: step: 940/530, loss: 0.04710598289966583
2023-01-23 04:11:01.654214: step: 944/530, loss: 0.01031026802957058
2023-01-23 04:11:02.749498: step: 948/530, loss: 0.00243034353479743
2023-01-23 04:11:03.839364: step: 952/530, loss: 8.106232598947827e-06
2023-01-23 04:11:04.972445: step: 956/530, loss: 0.000247955322265625
2023-01-23 04:11:06.075503: step: 960/530, loss: 0.003259849501773715
2023-01-23 04:11:07.174585: step: 964/530, loss: 0.00048675539437681437
2023-01-23 04:11:08.265350: step: 968/530, loss: 9.422301809536293e-05
2023-01-23 04:11:09.343026: step: 972/530, loss: 3.814697265625e-05
2023-01-23 04:11:10.461240: step: 976/530, loss: 1.7452241081628017e-05
2023-01-23 04:11:11.566987: step: 980/530, loss: 0.02725839801132679
2023-01-23 04:11:12.679073: step: 984/530, loss: 0.0006204128148965538
2023-01-23 04:11:13.777076: step: 988/530, loss: 0.0010396003490313888
2023-01-23 04:11:14.893400: step: 992/530, loss: 0.0016298294067382812
2023-01-23 04:11:15.985818: step: 996/530, loss: 0.00018310546875
2023-01-23 04:11:17.123495: step: 1000/530, loss: 0.0004096984921488911
2023-01-23 04:11:18.242868: step: 1004/530, loss: 0.007838249206542969
2023-01-23 04:11:19.349306: step: 1008/530, loss: 9.059906005859375e-05
2023-01-23 04:11:20.451561: step: 1012/530, loss: 6.31332368357107e-05
2023-01-23 04:11:21.542162: step: 1016/530, loss: 0.004192305263131857
2023-01-23 04:11:22.636424: step: 1020/530, loss: 0.0005960464477539062
2023-01-23 04:11:23.771062: step: 1024/530, loss: 0.003124237060546875
2023-01-23 04:11:24.875823: step: 1028/530, loss: 0.035961344838142395
2023-01-23 04:11:25.981070: step: 1032/530, loss: 0.04003048315644264
2023-01-23 04:11:27.070555: step: 1036/530, loss: 0.01762714423239231
2023-01-23 04:11:28.179285: step: 1040/530, loss: 0.00048313141451217234
2023-01-23 04:11:29.290874: step: 1044/530, loss: 0.40052005648612976
2023-01-23 04:11:30.413185: step: 1048/530, loss: 0.0035814286675304174
2023-01-23 04:11:31.539896: step: 1052/530, loss: 0.09833412617444992
2023-01-23 04:11:32.637179: step: 1056/530, loss: 0.12969213724136353
2023-01-23 04:11:33.758880: step: 1060/530, loss: 0.00010242462303722277
2023-01-23 04:11:34.859420: step: 1064/530, loss: 4.944801185047254e-05
2023-01-23 04:11:35.967002: step: 1068/530, loss: 9.117127046920359e-05
2023-01-23 04:11:37.068123: step: 1072/530, loss: 0.0005752563010901213
2023-01-23 04:11:38.205853: step: 1076/530, loss: 0.00030269622220657766
2023-01-23 04:11:39.298181: step: 1080/530, loss: 4.100799560546875e-05
2023-01-23 04:11:40.398234: step: 1084/530, loss: 0.00019750595674850047
2023-01-23 04:11:41.509998: step: 1088/530, loss: 0.0004329681396484375
2023-01-23 04:11:42.616756: step: 1092/530, loss: 0.0002244949428131804
2023-01-23 04:11:43.714999: step: 1096/530, loss: 0.006389522459357977
2023-01-23 04:11:44.861698: step: 1100/530, loss: 0.06389942765235901
2023-01-23 04:11:45.968841: step: 1104/530, loss: 7.367134094238281e-05
2023-01-23 04:11:47.111409: step: 1108/530, loss: 5.836487252963707e-05
2023-01-23 04:11:48.205956: step: 1112/530, loss: 0.0010914802551269531
2023-01-23 04:11:49.280982: step: 1116/530, loss: 0.0007221222040243447
2023-01-23 04:11:50.383956: step: 1120/530, loss: 0.0002206802455475554
2023-01-23 04:11:51.478847: step: 1124/530, loss: 4.825591895496473e-05
2023-01-23 04:11:52.576906: step: 1128/530, loss: 0.004268741700798273
2023-01-23 04:11:53.646013: step: 1132/530, loss: 4.6253204345703125e-05
2023-01-23 04:11:54.733110: step: 1136/530, loss: 0.5552914142608643
2023-01-23 04:11:55.886355: step: 1140/530, loss: 0.0036377906799316406
2023-01-23 04:11:56.980145: step: 1144/530, loss: 5.0163271225756034e-05
2023-01-23 04:11:58.109518: step: 1148/530, loss: 0.0003183365042787045
2023-01-23 04:11:59.202455: step: 1152/530, loss: 0.0018349647289142013
2023-01-23 04:12:00.319105: step: 1156/530, loss: 2.9087066195643274e-06
2023-01-23 04:12:01.418338: step: 1160/530, loss: 0.009746838361024857
2023-01-23 04:12:02.521302: step: 1164/530, loss: 5.14984130859375e-05
2023-01-23 04:12:03.625030: step: 1168/530, loss: 0.0021588325034826994
2023-01-23 04:12:04.718121: step: 1172/530, loss: 0.018843458965420723
2023-01-23 04:12:05.805138: step: 1176/530, loss: 0.0001731872616801411
2023-01-23 04:12:06.949698: step: 1180/530, loss: 0.03321237489581108
2023-01-23 04:12:08.054917: step: 1184/530, loss: 3.3736228942871094e-05
2023-01-23 04:12:09.171764: step: 1188/530, loss: 0.06683731079101562
2023-01-23 04:12:10.261434: step: 1192/530, loss: 1.6498564946232364e-05
2023-01-23 04:12:11.364947: step: 1196/530, loss: 0.002348232315853238
2023-01-23 04:12:12.439107: step: 1200/530, loss: 0.003155350685119629
2023-01-23 04:12:13.538971: step: 1204/530, loss: 0.00011310577974654734
2023-01-23 04:12:14.631170: step: 1208/530, loss: 0.011898803524672985
2023-01-23 04:12:15.758739: step: 1212/530, loss: 0.00017099380784202367
2023-01-23 04:12:16.868198: step: 1216/530, loss: 9.078979201149195e-05
2023-01-23 04:12:17.972494: step: 1220/530, loss: 0.012598324567079544
2023-01-23 04:12:19.082495: step: 1224/530, loss: 4.272460864740424e-05
2023-01-23 04:12:20.177826: step: 1228/530, loss: 0.008247184567153454
2023-01-23 04:12:21.262607: step: 1232/530, loss: 2.3937225705594756e-05
2023-01-23 04:12:22.349340: step: 1236/530, loss: 8.344650268554688e-06
2023-01-23 04:12:23.437412: step: 1240/530, loss: 0.05277138203382492
2023-01-23 04:12:24.529124: step: 1244/530, loss: 0.024059487506747246
2023-01-23 04:12:25.605104: step: 1248/530, loss: 2.57492069977161e-06
2023-01-23 04:12:26.704940: step: 1252/530, loss: 0.03417501226067543
2023-01-23 04:12:27.794049: step: 1256/530, loss: 0.00791635550558567
2023-01-23 04:12:28.916213: step: 1260/530, loss: 0.0004467964172363281
2023-01-23 04:12:30.052506: step: 1264/530, loss: 0.00011672973778331652
2023-01-23 04:12:31.112664: step: 1268/530, loss: -1.754760705807712e-05
2023-01-23 04:12:32.200486: step: 1272/530, loss: 0.027198314666748047
2023-01-23 04:12:33.329866: step: 1276/530, loss: -3.986358569818549e-05
2023-01-23 04:12:34.433702: step: 1280/530, loss: 0.0018262863159179688
2023-01-23 04:12:35.556258: step: 1284/530, loss: 0.01218109205365181
2023-01-23 04:12:36.698833: step: 1288/530, loss: 0.015147591009736061
2023-01-23 04:12:37.805401: step: 1292/530, loss: 0.0001583099365234375
2023-01-23 04:12:38.889410: step: 1296/530, loss: 0.008032942190766335
2023-01-23 04:12:39.973151: step: 1300/530, loss: 0.03481235355138779
2023-01-23 04:12:41.053426: step: 1304/530, loss: 1.8787384760798886e-05
2023-01-23 04:12:42.172223: step: 1308/530, loss: 0.028191566467285156
2023-01-23 04:12:43.279562: step: 1312/530, loss: 3.4952165151480585e-05
2023-01-23 04:12:44.394560: step: 1316/530, loss: 0.002737045520916581
2023-01-23 04:12:45.497102: step: 1320/530, loss: 0.002050376031547785
2023-01-23 04:12:46.608447: step: 1324/530, loss: 0.04877433925867081
2023-01-23 04:12:47.683207: step: 1328/530, loss: 0.0007799148443154991
2023-01-23 04:12:48.806898: step: 1332/530, loss: 7.009506134636467e-06
2023-01-23 04:12:49.962677: step: 1336/530, loss: 0.007594585418701172
2023-01-23 04:12:51.060798: step: 1340/530, loss: 0.012871837243437767
2023-01-23 04:12:52.154107: step: 1344/530, loss: 0.0014665602939203382
2023-01-23 04:12:53.263136: step: 1348/530, loss: 0.0005381584051065147
2023-01-23 04:12:54.364239: step: 1352/530, loss: 0.000457763671875
2023-01-23 04:12:55.462481: step: 1356/530, loss: 0.0007632255437783897
2023-01-23 04:12:56.541729: step: 1360/530, loss: 0.0016248227329924703
2023-01-23 04:12:57.631218: step: 1364/530, loss: 0.024770306423306465
2023-01-23 04:12:58.735242: step: 1368/530, loss: 0.0315372459590435
2023-01-23 04:12:59.839965: step: 1372/530, loss: 0.01925830915570259
2023-01-23 04:13:00.943490: step: 1376/530, loss: 0.0003323554992675781
2023-01-23 04:13:02.034269: step: 1380/530, loss: 0.0029994964133948088
2023-01-23 04:13:03.171478: step: 1384/530, loss: 0.0006886005285196006
2023-01-23 04:13:04.284255: step: 1388/530, loss: 0.005381774622946978
2023-01-23 04:13:05.397132: step: 1392/530, loss: 0.004721260163933039
2023-01-23 04:13:06.499104: step: 1396/530, loss: 0.009737777523696423
2023-01-23 04:13:07.592822: step: 1400/530, loss: 0.0003829956112895161
2023-01-23 04:13:08.677299: step: 1404/530, loss: 0.00012092590623069555
2023-01-23 04:13:09.753181: step: 1408/530, loss: 1.602172778802924e-05
2023-01-23 04:13:10.857933: step: 1412/530, loss: 0.008525085635483265
2023-01-23 04:13:11.997308: step: 1416/530, loss: 0.0013958930503576994
2023-01-23 04:13:13.095411: step: 1420/530, loss: 0.014683819375932217
2023-01-23 04:13:14.175373: step: 1424/530, loss: 2.956390289909905e-06
2023-01-23 04:13:15.254992: step: 1428/530, loss: -2.86102294921875e-06
2023-01-23 04:13:16.331090: step: 1432/530, loss: 0.00031223296537064016
2023-01-23 04:13:17.423932: step: 1436/530, loss: 0.0008543968433514237
2023-01-23 04:13:18.519746: step: 1440/530, loss: 6.246566772460938e-05
2023-01-23 04:13:19.637896: step: 1444/530, loss: 2.467632293701172e-05
2023-01-23 04:13:20.756511: step: 1448/530, loss: 0.0001371383696096018
2023-01-23 04:13:21.843459: step: 1452/530, loss: 1.4305115314527939e-07
2023-01-23 04:13:22.943368: step: 1456/530, loss: 0.005004500970244408
2023-01-23 04:13:24.078024: step: 1460/530, loss: 2.470016261213459e-05
2023-01-23 04:13:25.197793: step: 1464/530, loss: 0.002196884248405695
2023-01-23 04:13:26.278429: step: 1468/530, loss: 0.00021629333787132055
2023-01-23 04:13:27.379949: step: 1472/530, loss: 6.713867333019152e-05
2023-01-23 04:13:28.468713: step: 1476/530, loss: 4.992485264665447e-05
2023-01-23 04:13:29.593826: step: 1480/530, loss: 1.4257431757869199e-05
2023-01-23 04:13:30.704527: step: 1484/530, loss: 5.5313107623078395e-06
2023-01-23 04:13:31.815301: step: 1488/530, loss: 0.005343055818229914
2023-01-23 04:13:32.933445: step: 1492/530, loss: 3.597736213123426e-05
2023-01-23 04:13:34.050527: step: 1496/530, loss: 0.023518182337284088
2023-01-23 04:13:35.125269: step: 1500/530, loss: 0.00028247834416106343
2023-01-23 04:13:36.238518: step: 1504/530, loss: 0.0004214286745991558
2023-01-23 04:13:37.340909: step: 1508/530, loss: 0.0031370639335364103
2023-01-23 04:13:38.448691: step: 1512/530, loss: 0.004721451085060835
2023-01-23 04:13:39.548733: step: 1516/530, loss: 0.0005359649658203125
2023-01-23 04:13:40.663038: step: 1520/530, loss: 0.004294776823371649
2023-01-23 04:13:41.754304: step: 1524/530, loss: 0.004687500651925802
2023-01-23 04:13:42.849962: step: 1528/530, loss: 0.00979461707174778
2023-01-23 04:13:43.980141: step: 1532/530, loss: 2.2411346435546875e-05
2023-01-23 04:13:45.067905: step: 1536/530, loss: 4.0531158447265625e-05
2023-01-23 04:13:46.207368: step: 1540/530, loss: 0.034278105944395065
2023-01-23 04:13:47.313289: step: 1544/530, loss: 0.06323222815990448
2023-01-23 04:13:48.454413: step: 1548/530, loss: 0.002895546145737171
2023-01-23 04:13:49.579597: step: 1552/530, loss: 0.0006244659307412803
2023-01-23 04:13:50.662932: step: 1556/530, loss: 0.005742931272834539
2023-01-23 04:13:51.785810: step: 1560/530, loss: 0.06888294219970703
2023-01-23 04:13:52.892106: step: 1564/530, loss: 0.0837133377790451
2023-01-23 04:13:54.009185: step: 1568/530, loss: 0.0010878562461584806
2023-01-23 04:13:55.135311: step: 1572/530, loss: 0.015175819396972656
2023-01-23 04:13:56.270463: step: 1576/530, loss: 0.0026901247911155224
2023-01-23 04:13:57.384563: step: 1580/530, loss: 2.6893614631262608e-05
2023-01-23 04:13:58.484397: step: 1584/530, loss: 0.010282636620104313
2023-01-23 04:13:59.607978: step: 1588/530, loss: 0.0028836249839514494
2023-01-23 04:14:00.697214: step: 1592/530, loss: 0.0038822172209620476
2023-01-23 04:14:01.790312: step: 1596/530, loss: 3.638267298811115e-05
2023-01-23 04:14:02.888329: step: 1600/530, loss: 0.0006497383001260459
2023-01-23 04:14:04.008767: step: 1604/530, loss: 0.0014176368713378906
2023-01-23 04:14:05.145584: step: 1608/530, loss: 0.013205445371568203
2023-01-23 04:14:06.250610: step: 1612/530, loss: 4.76837158203125e-06
2023-01-23 04:14:07.330127: step: 1616/530, loss: 0.00020632744417525828
2023-01-23 04:14:08.406507: step: 1620/530, loss: 0.00438957242295146
2023-01-23 04:14:09.498632: step: 1624/530, loss: 3.900527735822834e-05
2023-01-23 04:14:10.599165: step: 1628/530, loss: 0.008436108008027077
2023-01-23 04:14:11.726875: step: 1632/530, loss: 0.004226303193718195
2023-01-23 04:14:12.831285: step: 1636/530, loss: 0.001207637833431363
2023-01-23 04:14:13.971941: step: 1640/530, loss: 5.741119457525201e-05
2023-01-23 04:14:15.075117: step: 1644/530, loss: 0.0001947641430888325
2023-01-23 04:14:16.170368: step: 1648/530, loss: 0.0005242347833700478
2023-01-23 04:14:17.255772: step: 1652/530, loss: 8.106231689453125e-06
2023-01-23 04:14:18.383718: step: 1656/530, loss: 0.25929784774780273
2023-01-23 04:14:19.479051: step: 1660/530, loss: 0.0014763831859454513
2023-01-23 04:14:20.566724: step: 1664/530, loss: 0.010774183087050915
2023-01-23 04:14:21.664898: step: 1668/530, loss: 0.0017530441982671618
2023-01-23 04:14:22.796420: step: 1672/530, loss: 0.0024311065208166838
2023-01-23 04:14:23.924213: step: 1676/530, loss: 0.003326416015625
2023-01-23 04:14:25.007824: step: 1680/530, loss: 0.0018481732113286853
2023-01-23 04:14:26.100576: step: 1684/530, loss: 1.3542176020564511e-05
2023-01-23 04:14:27.180034: step: 1688/530, loss: 0.0009551048860885203
2023-01-23 04:14:28.276638: step: 1692/530, loss: 0.006049538031220436
2023-01-23 04:14:29.379917: step: 1696/530, loss: 2.212524486822076e-05
2023-01-23 04:14:30.493177: step: 1700/530, loss: 0.0004325866757426411
2023-01-23 04:14:31.595318: step: 1704/530, loss: 0.009316349402070045
2023-01-23 04:14:32.760534: step: 1708/530, loss: 0.039919376373291016
2023-01-23 04:14:33.854079: step: 1712/530, loss: 0.0015592575073242188
2023-01-23 04:14:34.972475: step: 1716/530, loss: 0.0003067016659770161
2023-01-23 04:14:36.080851: step: 1720/530, loss: 1.0776520866784267e-05
2023-01-23 04:14:37.204867: step: 1724/530, loss: 0.0004425048828125
2023-01-23 04:14:38.304039: step: 1728/530, loss: 0.00282115931622684
2023-01-23 04:14:39.402075: step: 1732/530, loss: 0.0003891944943461567
2023-01-23 04:14:40.520557: step: 1736/530, loss: 0.00961227435618639
2023-01-23 04:14:41.643406: step: 1740/530, loss: 0.0005256652948446572
2023-01-23 04:14:42.762038: step: 1744/530, loss: 0.0030451775528490543
2023-01-23 04:14:43.862639: step: 1748/530, loss: 0.0014260768657550216
2023-01-23 04:14:44.977525: step: 1752/530, loss: 8.821487426757812e-05
2023-01-23 04:14:46.099048: step: 1756/530, loss: 0.005660820286720991
2023-01-23 04:14:47.221909: step: 1760/530, loss: 0.0007322311867028475
2023-01-23 04:14:48.319580: step: 1764/530, loss: 0.030092239379882812
2023-01-23 04:14:49.429535: step: 1768/530, loss: 0.04018134996294975
2023-01-23 04:14:50.542393: step: 1772/530, loss: 0.0006579876062460244
2023-01-23 04:14:51.655423: step: 1776/530, loss: 2.1839141481905244e-05
2023-01-23 04:14:52.778972: step: 1780/530, loss: 1.6117095583467744e-05
2023-01-23 04:14:53.868653: step: 1784/530, loss: 0.0028345107566565275
2023-01-23 04:14:54.945040: step: 1788/530, loss: 0.0024671554565429688
2023-01-23 04:14:56.018290: step: 1792/530, loss: 0.00020122528076171875
2023-01-23 04:14:57.118168: step: 1796/530, loss: 0.0018091201782226562
2023-01-23 04:14:58.192860: step: 1800/530, loss: 0.004432964604347944
2023-01-23 04:14:59.298050: step: 1804/530, loss: 0.0003448486386332661
2023-01-23 04:15:00.418345: step: 1808/530, loss: 7.400513277389109e-05
2023-01-23 04:15:01.546627: step: 1812/530, loss: 0.011529112234711647
2023-01-23 04:15:02.627893: step: 1816/530, loss: 0.00010013580322265625
2023-01-23 04:15:03.732754: step: 1820/530, loss: 0.0007772445678710938
2023-01-23 04:15:04.849204: step: 1824/530, loss: 0.00011100769188487902
2023-01-23 04:15:05.970680: step: 1828/530, loss: 0.010199164971709251
2023-01-23 04:15:07.083632: step: 1832/530, loss: 0.0003094673447776586
2023-01-23 04:15:08.175044: step: 1836/530, loss: 0.016125153750181198
2023-01-23 04:15:09.289438: step: 1840/530, loss: 9.727478754939511e-06
2023-01-23 04:15:10.380109: step: 1844/530, loss: 3.280639793956652e-05
2023-01-23 04:15:11.529064: step: 1848/530, loss: 0.014998816885054111
2023-01-23 04:15:12.644557: step: 1852/530, loss: 0.02959260903298855
2023-01-23 04:15:13.785771: step: 1856/530, loss: 0.04317960888147354
2023-01-23 04:15:14.887477: step: 1860/530, loss: 2.422332727292087e-05
2023-01-23 04:15:15.995483: step: 1864/530, loss: 5.826950291520916e-05
2023-01-23 04:15:17.090721: step: 1868/530, loss: 0.02931070514023304
2023-01-23 04:15:18.171732: step: 1872/530, loss: 6.27517729299143e-05
2023-01-23 04:15:19.290929: step: 1876/530, loss: 5.841255187988281e-05
2023-01-23 04:15:20.404363: step: 1880/530, loss: 0.0016360284062102437
2023-01-23 04:15:21.518326: step: 1884/530, loss: 0.07107105106115341
2023-01-23 04:15:22.629547: step: 1888/530, loss: 0.007952404208481312
2023-01-23 04:15:23.724483: step: 1892/530, loss: 6.489753286587074e-05
2023-01-23 04:15:24.816719: step: 1896/530, loss: 9.722710092319176e-05
2023-01-23 04:15:25.901951: step: 1900/530, loss: 0.017777537927031517
2023-01-23 04:15:26.960445: step: 1904/530, loss: 0.00012693405733443797
2023-01-23 04:15:28.035294: step: 1908/530, loss: 0.00017786027456168085
2023-01-23 04:15:29.127063: step: 1912/530, loss: 0.0009184837690554559
2023-01-23 04:15:30.211982: step: 1916/530, loss: 0.0005043029668740928
2023-01-23 04:15:31.302560: step: 1920/530, loss: 0.0010626792209222913
2023-01-23 04:15:32.363252: step: 1924/530, loss: 0.0005792140727862716
2023-01-23 04:15:33.447231: step: 1928/530, loss: 0.0005459785461425781
2023-01-23 04:15:34.559353: step: 1932/530, loss: 0.00039095879765227437
2023-01-23 04:15:35.654362: step: 1936/530, loss: 6.718635268043727e-05
2023-01-23 04:15:36.746841: step: 1940/530, loss: 0.0009237289777956903
2023-01-23 04:15:37.865295: step: 1944/530, loss: 0.002246761228889227
2023-01-23 04:15:38.991094: step: 1948/530, loss: 0.0007325172773562372
2023-01-23 04:15:40.116210: step: 1952/530, loss: 0.051781561225652695
2023-01-23 04:15:41.193288: step: 1956/530, loss: 7.905960228526965e-05
2023-01-23 04:15:42.333324: step: 1960/530, loss: 0.08850985020399094
2023-01-23 04:15:43.459921: step: 1964/530, loss: 0.016207123175263405
2023-01-23 04:15:44.585521: step: 1968/530, loss: 0.0004255295207258314
2023-01-23 04:15:45.700233: step: 1972/530, loss: 3.719329833984375e-05
2023-01-23 04:15:46.766930: step: 1976/530, loss: 0.0003643989621195942
2023-01-23 04:15:47.877112: step: 1980/530, loss: 0.00019464493379928172
2023-01-23 04:15:48.989895: step: 1984/530, loss: 9.93728608591482e-05
2023-01-23 04:15:50.108523: step: 1988/530, loss: 0.027887536212801933
2023-01-23 04:15:51.218791: step: 1992/530, loss: 3.709793236339465e-05
2023-01-23 04:15:52.326016: step: 1996/530, loss: 0.2826540768146515
2023-01-23 04:15:53.418376: step: 2000/530, loss: 0.013715744018554688
2023-01-23 04:15:54.523690: step: 2004/530, loss: 0.0035851476714015007
2023-01-23 04:15:55.618140: step: 2008/530, loss: 0.03893556445837021
2023-01-23 04:15:56.703010: step: 2012/530, loss: 0.010373878292739391
2023-01-23 04:15:57.798454: step: 2016/530, loss: 0.3003626763820648
2023-01-23 04:15:58.900739: step: 2020/530, loss: 0.03634843975305557
2023-01-23 04:16:00.000296: step: 2024/530, loss: 0.00016622543625999242
2023-01-23 04:16:01.080458: step: 2028/530, loss: 0.0023660659790039062
2023-01-23 04:16:02.185661: step: 2032/530, loss: 8.945464651333168e-05
2023-01-23 04:16:03.286827: step: 2036/530, loss: 0.09421481937170029
2023-01-23 04:16:04.391278: step: 2040/530, loss: 0.006899738218635321
2023-01-23 04:16:05.516274: step: 2044/530, loss: 9.841918654274195e-05
2023-01-23 04:16:06.674681: step: 2048/530, loss: 0.00013942719670012593
2023-01-23 04:16:07.758663: step: 2052/530, loss: 0.020216751843690872
2023-01-23 04:16:08.840121: step: 2056/530, loss: 3.681182715808973e-05
2023-01-23 04:16:09.956191: step: 2060/530, loss: 0.03598308563232422
2023-01-23 04:16:11.070172: step: 2064/530, loss: 0.04095497354865074
2023-01-23 04:16:12.164200: step: 2068/530, loss: 2.593994213384576e-05
2023-01-23 04:16:13.278428: step: 2072/530, loss: 0.0004803657648153603
2023-01-23 04:16:14.389874: step: 2076/530, loss: 0.00043506623478606343
2023-01-23 04:16:15.473066: step: 2080/530, loss: 1.62124638336536e-06
2023-01-23 04:16:16.568730: step: 2084/530, loss: 0.0028630257584154606
2023-01-23 04:16:17.689671: step: 2088/530, loss: 0.007358551025390625
2023-01-23 04:16:18.806901: step: 2092/530, loss: 0.00019612311734817922
2023-01-23 04:16:19.910382: step: 2096/530, loss: 0.0027858735993504524
2023-01-23 04:16:21.032085: step: 2100/530, loss: 0.059932902455329895
2023-01-23 04:16:22.134615: step: 2104/530, loss: 0.016859544441103935
2023-01-23 04:16:23.259222: step: 2108/530, loss: 8.659363084007055e-05
2023-01-23 04:16:24.387365: step: 2112/530, loss: 3.728866431629285e-05
2023-01-23 04:16:25.495876: step: 2116/530, loss: 0.0197543166577816
2023-01-23 04:16:26.573047: step: 2120/530, loss: 0.0003839731216430664
==================================================
Loss: 0.013
--------------------
Dev: {'event': {'p': 0.5972369819341127, 'r': 0.748335552596538, 'f1': 0.6643026004728132}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
Test: {'event': {'p': 0.6417633410672854, 'r': 0.8059440559440559, 'f1': 0.7145440454662877}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
Chinese: {'event': {'p': 0.5694444444444444, 'r': 0.7592592592592593, 'f1': 0.6507936507936508}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
Korean: {'event': {'p': 0.8, 'r': 0.5079365079365079, 'f1': 0.6213592233009708}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
Russian: {'event': {'p': 0.4146341463414634, 'r': 0.4722222222222222, 'f1': 0.4415584415584415}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 27}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6449771689497716, 'r': 0.7523302263648469, 'f1': 0.6945298094652735}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Chinese: {'event': {'p': 0.6692644909887969, 'r': 0.8006993006993007, 'f1': 0.7291058636243036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Chinese: {'event': {'p': 0.6764705882352942, 'r': 0.8518518518518519, 'f1': 0.7540983606557378}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5873340143003064, 'r': 0.7656458055925432, 'f1': 0.6647398843930636}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Eng Test for Korean: {'event': {'p': 0.6496487119437939, 'r': 0.8082750582750583, 'f1': 0.7203323811996885}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Sample Korean: {'event': {'p': 0.6721311475409836, 'r': 0.6507936507936508, 'f1': 0.6612903225806451}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5971370143149284, 'r': 0.7776298268974701, 'f1': 0.6755349913244649}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Russian: {'event': {'p': 0.6401673640167364, 'r': 0.8024475524475524, 'f1': 0.7121799844840963}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Russian: {'event': {'p': 0.5897435897435898, 'r': 0.6388888888888888, 'f1': 0.6133333333333332}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
******************************
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 04:17:05.918280: step: 4/530, loss: 0.0009229659917764366
2023-01-23 04:17:07.011824: step: 8/530, loss: 2.098083541568485e-06
2023-01-23 04:17:08.118114: step: 12/530, loss: 0.03904075548052788
2023-01-23 04:17:09.230167: step: 16/530, loss: 5.054474058852065e-06
2023-01-23 04:17:10.350153: step: 20/530, loss: 0.0012743950355798006
2023-01-23 04:17:11.475315: step: 24/530, loss: 0.0008071899646893144
2023-01-23 04:17:12.597966: step: 28/530, loss: 0.06114683300256729
2023-01-23 04:17:13.686785: step: 32/530, loss: 0.003858423326164484
2023-01-23 04:17:14.777956: step: 36/530, loss: 5.24044044141192e-05
2023-01-23 04:17:15.909157: step: 40/530, loss: 2.6702882678364404e-06
2023-01-23 04:17:17.017524: step: 44/530, loss: 0.0011781692737713456
2023-01-23 04:17:18.123800: step: 48/530, loss: 0.012569714337587357
2023-01-23 04:17:19.220504: step: 52/530, loss: 2.1743775505456142e-05
2023-01-23 04:17:20.303184: step: 56/530, loss: 0.0006578445318154991
2023-01-23 04:17:21.422436: step: 60/530, loss: 9.424686868442222e-05
2023-01-23 04:17:22.505518: step: 64/530, loss: 0.016581345349550247
2023-01-23 04:17:23.599659: step: 68/530, loss: 0.0005012512556277215
2023-01-23 04:17:24.708306: step: 72/530, loss: 0.004143428988754749
2023-01-23 04:17:25.805763: step: 76/530, loss: 0.003126526018604636
2023-01-23 04:17:26.903882: step: 80/530, loss: 0.0007184982532635331
2023-01-23 04:17:28.017212: step: 84/530, loss: 0.02431163750588894
2023-01-23 04:17:29.111044: step: 88/530, loss: 4.768372036778601e-06
2023-01-23 04:17:30.202526: step: 92/530, loss: 0.00013790131197310984
2023-01-23 04:17:31.354063: step: 96/530, loss: 4.47750098828692e-05
2023-01-23 04:17:32.472712: step: 100/530, loss: 0.0005819320795126259
2023-01-23 04:17:33.587269: step: 104/530, loss: 1.9359587895451114e-05
2023-01-23 04:17:34.705587: step: 108/530, loss: 0.002309608506038785
2023-01-23 04:17:35.806141: step: 112/530, loss: 0.0016008376842364669
2023-01-23 04:17:36.939006: step: 116/530, loss: 7.724761417193804e-06
2023-01-23 04:17:38.038915: step: 120/530, loss: 1.2302398317842744e-05
2023-01-23 04:17:39.158489: step: 124/530, loss: 0.006310272496193647
2023-01-23 04:17:40.266703: step: 128/530, loss: 6.237030174816027e-05
2023-01-23 04:17:41.364041: step: 132/530, loss: 0.03372449800372124
2023-01-23 04:17:42.488905: step: 136/530, loss: 0.027324484661221504
2023-01-23 04:17:43.587421: step: 140/530, loss: 0.000988864921964705
2023-01-23 04:17:44.711135: step: 144/530, loss: 0.01523289643228054
2023-01-23 04:17:45.834288: step: 148/530, loss: 0.04396963119506836
2023-01-23 04:17:46.898920: step: 152/530, loss: 0.00046916009159758687
2023-01-23 04:17:48.013831: step: 156/530, loss: 0.0020969391334801912
2023-01-23 04:17:49.080248: step: 160/530, loss: 0.00043907167855650187
2023-01-23 04:17:50.174426: step: 164/530, loss: 0.015908576548099518
2023-01-23 04:17:51.293891: step: 168/530, loss: 0.00022373201500158757
2023-01-23 04:17:52.366250: step: 172/530, loss: 1.4019013178767636e-05
2023-01-23 04:17:53.487766: step: 176/530, loss: 0.05156669765710831
2023-01-23 04:17:54.565334: step: 180/530, loss: 0.0002509593905415386
2023-01-23 04:17:55.662810: step: 184/530, loss: 0.0355280376970768
2023-01-23 04:17:56.774249: step: 188/530, loss: 2.517700158932712e-05
2023-01-23 04:17:57.917348: step: 192/530, loss: 0.006950664333999157
2023-01-23 04:17:59.021891: step: 196/530, loss: 0.0006632328731939197
2023-01-23 04:18:00.127750: step: 200/530, loss: 0.0006520271417684853
2023-01-23 04:18:01.223442: step: 204/530, loss: 0.0001260757417185232
2023-01-23 04:18:02.328099: step: 208/530, loss: 0.0016664505237713456
2023-01-23 04:18:03.427524: step: 212/530, loss: 0.0012594223953783512
2023-01-23 04:18:04.563328: step: 216/530, loss: 0.00030007361783646047
2023-01-23 04:18:05.654680: step: 220/530, loss: 0.02172260358929634
2023-01-23 04:18:06.754202: step: 224/530, loss: 0.00016040803166106343
2023-01-23 04:18:07.855633: step: 228/530, loss: 0.06179637834429741
2023-01-23 04:18:08.924005: step: 232/530, loss: 0.00010242462303722277
2023-01-23 04:18:10.014929: step: 236/530, loss: 3.3950807846849784e-05
2023-01-23 04:18:11.097693: step: 240/530, loss: 3.070831371587701e-05
2023-01-23 04:18:12.173974: step: 244/530, loss: 0.0029663562308996916
2023-01-23 04:18:13.267266: step: 248/530, loss: 0.005881762597709894
2023-01-23 04:18:14.362393: step: 252/530, loss: 0.006851959507912397
2023-01-23 04:18:15.460170: step: 256/530, loss: 0.001330566476099193
2023-01-23 04:18:16.549141: step: 260/530, loss: 0.00039005279541015625
2023-01-23 04:18:17.663787: step: 264/530, loss: 5.283355858409777e-05
2023-01-23 04:18:18.760891: step: 268/530, loss: 0.0006299972883425653
2023-01-23 04:18:19.847179: step: 272/530, loss: 9.918213436321821e-06
2023-01-23 04:18:20.943137: step: 276/530, loss: 0.017178155481815338
2023-01-23 04:18:22.051146: step: 280/530, loss: 0.00013809204392600805
2023-01-23 04:18:23.181967: step: 284/530, loss: 0.03849988058209419
2023-01-23 04:18:24.313508: step: 288/530, loss: 0.0422937385737896
2023-01-23 04:18:25.444964: step: 292/530, loss: 0.0005568981287069619
2023-01-23 04:18:26.574288: step: 296/530, loss: 0.000295531761366874
2023-01-23 04:18:27.700568: step: 300/530, loss: 0.002651310060173273
2023-01-23 04:18:28.777599: step: 304/530, loss: 0.0001181602492579259
2023-01-23 04:18:29.879737: step: 308/530, loss: 0.005441808607429266
2023-01-23 04:18:30.998005: step: 312/530, loss: 0.061397455632686615
2023-01-23 04:18:32.097843: step: 316/530, loss: 2.193450927734375e-05
2023-01-23 04:18:33.194128: step: 320/530, loss: 2.9563905172835803e-06
2023-01-23 04:18:34.299062: step: 324/530, loss: 1.1444091796875e-05
2023-01-23 04:18:35.397311: step: 328/530, loss: 0.0008769988780841231
2023-01-23 04:18:36.509220: step: 332/530, loss: 0.011965751647949219
2023-01-23 04:18:37.605453: step: 336/530, loss: 0.0050147054716944695
2023-01-23 04:18:38.700521: step: 340/530, loss: 0.001248478889465332
2023-01-23 04:18:39.807704: step: 344/530, loss: 2.937316821771674e-05
2023-01-23 04:18:40.923773: step: 348/530, loss: 0.23125873506069183
2023-01-23 04:18:42.043184: step: 352/530, loss: 0.0008073807111941278
2023-01-23 04:18:43.121048: step: 356/530, loss: 5.569458153331652e-05
2023-01-23 04:18:44.252664: step: 360/530, loss: 0.00013837814913131297
2023-01-23 04:18:45.371315: step: 364/530, loss: 6.341934295051033e-06
2023-01-23 04:18:46.459670: step: 368/530, loss: 0.005256843753159046
2023-01-23 04:18:47.538220: step: 372/530, loss: 3.1757354008732364e-05
2023-01-23 04:18:48.675213: step: 376/530, loss: 0.10189895331859589
2023-01-23 04:18:49.768805: step: 380/530, loss: 0.0039685252122581005
2023-01-23 04:18:50.866119: step: 384/530, loss: 0.03534860908985138
2023-01-23 04:18:51.944948: step: 388/530, loss: 0.0003299713134765625
2023-01-23 04:18:53.030727: step: 392/530, loss: 0.018732406198978424
2023-01-23 04:18:54.138872: step: 396/530, loss: 0.017844010144472122
2023-01-23 04:18:55.254570: step: 400/530, loss: 0.0007582188118249178
2023-01-23 04:18:56.355839: step: 404/530, loss: 4.1770937968976796e-05
2023-01-23 04:18:57.469176: step: 408/530, loss: 0.00011596680269576609
2023-01-23 04:18:58.578856: step: 412/530, loss: 0.006153678987175226
2023-01-23 04:18:59.666923: step: 416/530, loss: 0.00026865003746934235
2023-01-23 04:19:00.806453: step: 420/530, loss: 0.0002304077206645161
2023-01-23 04:19:01.871500: step: 424/530, loss: 5.435943421616685e-06
2023-01-23 04:19:02.942711: step: 428/530, loss: 3.0422212148550898e-05
2023-01-23 04:19:04.053565: step: 432/530, loss: 2.050399962172378e-05
2023-01-23 04:19:05.135147: step: 436/530, loss: 0.0001386642543366179
2023-01-23 04:19:06.267690: step: 440/530, loss: 1.7833710444392636e-05
2023-01-23 04:19:07.372932: step: 444/530, loss: 0.0001127243012888357
2023-01-23 04:19:08.464704: step: 448/530, loss: 0.0015014648670330644
2023-01-23 04:19:09.575310: step: 452/530, loss: 0.0003955840948037803
2023-01-23 04:19:10.669347: step: 456/530, loss: 0.04159178584814072
2023-01-23 04:19:11.791294: step: 460/530, loss: 0.0026561259292066097
2023-01-23 04:19:12.931966: step: 464/530, loss: 4.6253204345703125e-05
2023-01-23 04:19:14.039669: step: 468/530, loss: 0.01020207442343235
2023-01-23 04:19:15.119853: step: 472/530, loss: 0.0003520488680806011
2023-01-23 04:19:16.246376: step: 476/530, loss: 0.03383493423461914
2023-01-23 04:19:17.335946: step: 480/530, loss: 4.5108794438419864e-05
2023-01-23 04:19:18.448796: step: 484/530, loss: 0.007518577855080366
2023-01-23 04:19:19.559974: step: 488/530, loss: 7.553101022494957e-05
2023-01-23 04:19:20.643556: step: 492/530, loss: 1.5163422176556196e-05
2023-01-23 04:19:21.752333: step: 496/530, loss: 1.5258788153005298e-06
2023-01-23 04:19:22.908964: step: 500/530, loss: 0.00019874573627021164
2023-01-23 04:19:24.017542: step: 504/530, loss: 0.0003895759582519531
2023-01-23 04:19:25.135231: step: 508/530, loss: 0.00015597343735862523
2023-01-23 04:19:26.222329: step: 512/530, loss: -1.296997106692288e-05
2023-01-23 04:19:27.336440: step: 516/530, loss: 4.510879807639867e-05
2023-01-23 04:19:28.433167: step: 520/530, loss: 0.0001903533993754536
2023-01-23 04:19:29.546793: step: 524/530, loss: 0.00045723916264250875
2023-01-23 04:19:30.623188: step: 528/530, loss: 9.140968177234754e-05
2023-01-23 04:19:31.749598: step: 532/530, loss: 0.0018447876209393144
2023-01-23 04:19:32.871175: step: 536/530, loss: 0.0031841278541833162
2023-01-23 04:19:33.973183: step: 540/530, loss: 0.0012926101917400956
2023-01-23 04:19:35.085919: step: 544/530, loss: 1.239776611328125e-05
2023-01-23 04:19:36.182119: step: 548/530, loss: 0.0030548095237463713
2023-01-23 04:19:37.262129: step: 552/530, loss: 0.013393307104706764
2023-01-23 04:19:38.336258: step: 556/530, loss: 6.28471389063634e-05
2023-01-23 04:19:39.434452: step: 560/530, loss: 0.00019445418729446828
2023-01-23 04:19:40.539978: step: 564/530, loss: 4.510879807639867e-05
2023-01-23 04:19:41.688867: step: 568/530, loss: 0.0006181717035360634
2023-01-23 04:19:42.790897: step: 572/530, loss: 0.056319236755371094
2023-01-23 04:19:43.908785: step: 576/530, loss: 4.382133556646295e-05
2023-01-23 04:19:44.993455: step: 580/530, loss: 5.2165985835017636e-05
2023-01-23 04:19:46.092044: step: 584/530, loss: 0.008712291717529297
2023-01-23 04:19:47.195361: step: 588/530, loss: 8.325577073264867e-05
2023-01-23 04:19:48.312296: step: 592/530, loss: 4.110336521989666e-05
2023-01-23 04:19:49.456268: step: 596/530, loss: 0.0010107040870934725
2023-01-23 04:19:50.547161: step: 600/530, loss: 0.0013206482399255037
2023-01-23 04:19:51.652619: step: 604/530, loss: 1.888275073724799e-05
2023-01-23 04:19:52.742183: step: 608/530, loss: 0.04675489291548729
2023-01-23 04:19:53.836193: step: 612/530, loss: 0.00010929107520496473
2023-01-23 04:19:54.935708: step: 616/530, loss: 0.00014934541832190007
2023-01-23 04:19:56.033125: step: 620/530, loss: 2.0313262211857364e-05
2023-01-23 04:19:57.142284: step: 624/530, loss: 0.00318737025372684
2023-01-23 04:19:58.218580: step: 628/530, loss: 8.39233416627394e-06
2023-01-23 04:19:59.305310: step: 632/530, loss: 0.00022768972849007696
2023-01-23 04:20:00.426060: step: 636/530, loss: 0.005745220463722944
2023-01-23 04:20:01.516415: step: 640/530, loss: 0.025087738409638405
2023-01-23 04:20:02.624231: step: 644/530, loss: 4.792213439941406e-05
2023-01-23 04:20:03.729363: step: 648/530, loss: 0.0017478943336755037
2023-01-23 04:20:04.865657: step: 652/530, loss: 0.03402920067310333
2023-01-23 04:20:05.949842: step: 656/530, loss: 0.0003834724484477192
2023-01-23 04:20:07.106570: step: 660/530, loss: 0.0030072215013206005
2023-01-23 04:20:08.225335: step: 664/530, loss: 0.003998184110969305
2023-01-23 04:20:09.336092: step: 668/530, loss: 0.0004158973752055317
2023-01-23 04:20:10.440228: step: 672/530, loss: 9.536779543850571e-08
2023-01-23 04:20:11.566360: step: 676/530, loss: 0.035379983484745026
2023-01-23 04:20:12.655206: step: 680/530, loss: 9.393692016601562e-05
2023-01-23 04:20:13.773847: step: 684/530, loss: 0.000135326394229196
2023-01-23 04:20:14.907977: step: 688/530, loss: 0.0006980896578170359
2023-01-23 04:20:15.992402: step: 692/530, loss: -5.292892183206277e-06
2023-01-23 04:20:17.090321: step: 696/530, loss: 2.341270555916708e-05
2023-01-23 04:20:18.206529: step: 700/530, loss: 0.07872925698757172
2023-01-23 04:20:19.318147: step: 704/530, loss: 4.615783836925402e-05
2023-01-23 04:20:20.428123: step: 708/530, loss: 0.0009909630753099918
2023-01-23 04:20:21.543755: step: 712/530, loss: 0.0011909485328942537
2023-01-23 04:20:22.642949: step: 716/530, loss: 0.00013618468074128032
2023-01-23 04:20:23.815492: step: 720/530, loss: 0.008033180609345436
2023-01-23 04:20:24.906423: step: 724/530, loss: 0.0009420395363122225
2023-01-23 04:20:26.007797: step: 728/530, loss: 0.0007971763843670487
2023-01-23 04:20:27.094764: step: 732/530, loss: 0.00034179689828306437
2023-01-23 04:20:28.206923: step: 736/530, loss: 0.0026996613014489412
2023-01-23 04:20:29.296651: step: 740/530, loss: 9.212494478560984e-05
2023-01-23 04:20:30.414787: step: 744/530, loss: 5.2738188969669864e-05
2023-01-23 04:20:31.548533: step: 748/530, loss: 0.017889022827148438
2023-01-23 04:20:32.667882: step: 752/530, loss: 0.004961967468261719
2023-01-23 04:20:33.759166: step: 756/530, loss: 0.05314483866095543
2023-01-23 04:20:34.819775: step: 760/530, loss: 2.574920654296875e-05
2023-01-23 04:20:35.917812: step: 764/530, loss: -3.2424923119833693e-06
2023-01-23 04:20:37.015332: step: 768/530, loss: 1.1730194273695815e-05
2023-01-23 04:20:38.104252: step: 772/530, loss: 5.8364865253679454e-05
2023-01-23 04:20:39.227995: step: 776/530, loss: 0.0005382538074627519
2023-01-23 04:20:40.325901: step: 780/530, loss: 0.005088138394057751
2023-01-23 04:20:41.398885: step: 784/530, loss: 0.0001968383730854839
2023-01-23 04:20:42.492214: step: 788/530, loss: 2.8944017685716972e-05
2023-01-23 04:20:43.566414: step: 792/530, loss: 0.004815292544662952
2023-01-23 04:20:44.650832: step: 796/530, loss: 0.015410042367875576
2023-01-23 04:20:45.771033: step: 800/530, loss: 0.026335623115301132
2023-01-23 04:20:46.892241: step: 804/530, loss: 0.017641641199588776
2023-01-23 04:20:48.003611: step: 808/530, loss: 0.041811753064394
2023-01-23 04:20:49.123164: step: 812/530, loss: 0.000521755195222795
2023-01-23 04:20:50.231877: step: 816/530, loss: 4.167556471657008e-05
2023-01-23 04:20:51.349291: step: 820/530, loss: 2.7084352041129023e-05
2023-01-23 04:20:52.487680: step: 824/530, loss: 7.133484905352816e-05
2023-01-23 04:20:53.592026: step: 828/530, loss: 0.15551558136940002
2023-01-23 04:20:54.688247: step: 832/530, loss: 0.0006693362956866622
2023-01-23 04:20:55.811868: step: 836/530, loss: 0.0013718605041503906
2023-01-23 04:20:56.952508: step: 840/530, loss: 0.026207733899354935
2023-01-23 04:20:58.033331: step: 844/530, loss: 0.00010585785639705136
2023-01-23 04:20:59.112481: step: 848/530, loss: 0.0015985966892912984
2023-01-23 04:21:00.212882: step: 852/530, loss: 4.95910626341356e-06
2023-01-23 04:21:01.360678: step: 856/530, loss: 1.9073486328125e-06
2023-01-23 04:21:02.451944: step: 860/530, loss: 0.047466181218624115
2023-01-23 04:21:03.541497: step: 864/530, loss: 0.006888008210808039
2023-01-23 04:21:04.631852: step: 868/530, loss: 0.00038075449992902577
2023-01-23 04:21:05.729836: step: 872/530, loss: 0.015539360232651234
2023-01-23 04:21:06.838019: step: 876/530, loss: 3.585815284168348e-05
2023-01-23 04:21:07.924538: step: 880/530, loss: 0.00989522971212864
2023-01-23 04:21:09.049793: step: 884/530, loss: 0.03495483472943306
2023-01-23 04:21:10.136959: step: 888/530, loss: 0.0013396263821050525
2023-01-23 04:21:11.235570: step: 892/530, loss: 0.0007195472717285156
2023-01-23 04:21:12.363342: step: 896/530, loss: 0.0053039551712572575
2023-01-23 04:21:13.453573: step: 900/530, loss: 4.4631960918195546e-05
2023-01-23 04:21:14.561932: step: 904/530, loss: 0.005351925268769264
2023-01-23 04:21:15.663714: step: 908/530, loss: 0.00018386841111350805
2023-01-23 04:21:16.812507: step: 912/530, loss: 0.003766822861507535
2023-01-23 04:21:17.904452: step: 916/530, loss: 0.0004925489192828536
2023-01-23 04:21:19.022326: step: 920/530, loss: 5.5789947509765625e-05
2023-01-23 04:21:20.160585: step: 924/530, loss: -1.0204315003647935e-05
2023-01-23 04:21:21.237009: step: 928/530, loss: 0.00013952255540061742
2023-01-23 04:21:22.377192: step: 932/530, loss: 2.708435022213962e-05
2023-01-23 04:21:23.481143: step: 936/530, loss: 0.0013339996803551912
2023-01-23 04:21:24.574282: step: 940/530, loss: 0.0017431259620934725
2023-01-23 04:21:25.672472: step: 944/530, loss: 0.00021848679170943797
2023-01-23 04:21:26.780019: step: 948/530, loss: 0.005098819732666016
2023-01-23 04:21:27.874068: step: 952/530, loss: 0.006736421957612038
2023-01-23 04:21:28.970375: step: 956/530, loss: 0.0012333870399743319
2023-01-23 04:21:30.116940: step: 960/530, loss: 0.0004223823780193925
2023-01-23 04:21:31.222020: step: 964/530, loss: 0.10441255569458008
2023-01-23 04:21:32.313744: step: 968/530, loss: 0.028757857158780098
2023-01-23 04:21:33.439930: step: 972/530, loss: 9.202957880916074e-05
2023-01-23 04:21:34.571956: step: 976/530, loss: 0.00014858247595839202
2023-01-23 04:21:35.698326: step: 980/530, loss: 0.002829647157341242
2023-01-23 04:21:36.807066: step: 984/530, loss: 0.0016164302360266447
2023-01-23 04:21:37.894621: step: 988/530, loss: 0.009170341305434704
2023-01-23 04:21:39.008118: step: 992/530, loss: 0.006107521243393421
2023-01-23 04:21:40.128112: step: 996/530, loss: 0.0030161382164806128
2023-01-23 04:21:41.205387: step: 1000/530, loss: 2.1696090698242188e-05
2023-01-23 04:21:42.296032: step: 1004/530, loss: 0.0031592370942234993
2023-01-23 04:21:43.387196: step: 1008/530, loss: 0.00019578934006858617
2023-01-23 04:21:44.496969: step: 1012/530, loss: 0.021430397406220436
2023-01-23 04:21:45.625232: step: 1016/530, loss: 0.00037174223689362407
2023-01-23 04:21:46.713838: step: 1020/530, loss: 0.00047388076200149953
2023-01-23 04:21:47.789558: step: 1024/530, loss: 0.0002367019624216482
2023-01-23 04:21:48.892042: step: 1028/530, loss: 1.1062621524615679e-05
2023-01-23 04:21:49.985208: step: 1032/530, loss: 0.025748252868652344
2023-01-23 04:21:51.088147: step: 1036/530, loss: 1.6355514162569307e-05
2023-01-23 04:21:52.193693: step: 1040/530, loss: 0.0006443976890295744
2023-01-23 04:21:53.327658: step: 1044/530, loss: 0.006474304012954235
2023-01-23 04:21:54.424144: step: 1048/530, loss: 0.00276012415997684
2023-01-23 04:21:55.524587: step: 1052/530, loss: 4.200935291009955e-05
2023-01-23 04:21:56.641347: step: 1056/530, loss: 0.5726009607315063
2023-01-23 04:21:57.722757: step: 1060/530, loss: 2.4366378056583926e-05
2023-01-23 04:21:58.823222: step: 1064/530, loss: 2.975463939947076e-05
2023-01-23 04:21:59.949208: step: 1068/530, loss: 0.04387016221880913
2023-01-23 04:22:01.063433: step: 1072/530, loss: 0.008613396435976028
2023-01-23 04:22:02.164701: step: 1076/530, loss: 0.001984023954719305
2023-01-23 04:22:03.286927: step: 1080/530, loss: 0.0034473419655114412
2023-01-23 04:22:04.386548: step: 1084/530, loss: 1.2969970157428179e-05
2023-01-23 04:22:05.484297: step: 1088/530, loss: 4.0626528061693534e-05
2023-01-23 04:22:06.591588: step: 1092/530, loss: 3.604888843256049e-05
2023-01-23 04:22:07.693196: step: 1096/530, loss: 0.0010149956215173006
2023-01-23 04:22:08.798876: step: 1100/530, loss: 0.0002774238819256425
2023-01-23 04:22:09.906727: step: 1104/530, loss: 9.346007573185489e-06
2023-01-23 04:22:11.029133: step: 1108/530, loss: 0.00012211799912620336
2023-01-23 04:22:12.153651: step: 1112/530, loss: 0.004173374269157648
2023-01-23 04:22:13.285746: step: 1116/530, loss: 0.0025569917634129524
2023-01-23 04:22:14.399319: step: 1120/530, loss: 0.008492469787597656
2023-01-23 04:22:15.475161: step: 1124/530, loss: 0.0019285203889012337
2023-01-23 04:22:16.571267: step: 1128/530, loss: 0.0002206802455475554
2023-01-23 04:22:17.676382: step: 1132/530, loss: 0.0005338669288903475
2023-01-23 04:22:18.764354: step: 1136/530, loss: 6.065368506824598e-05
2023-01-23 04:22:19.882146: step: 1140/530, loss: 5.1784514653263614e-05
2023-01-23 04:22:20.965045: step: 1144/530, loss: 0.00017032623873092234
2023-01-23 04:22:22.056792: step: 1148/530, loss: -1.1444091796875e-05
2023-01-23 04:22:23.162576: step: 1152/530, loss: 0.0009275436750613153
2023-01-23 04:22:24.274444: step: 1156/530, loss: 9.15527380129788e-06
2023-01-23 04:22:25.367982: step: 1160/530, loss: 5.6743621826171875e-05
2023-01-23 04:22:26.482112: step: 1164/530, loss: 0.08822441101074219
2023-01-23 04:22:27.605496: step: 1168/530, loss: 0.0014806747203692794
2023-01-23 04:22:28.731348: step: 1172/530, loss: -4.1770188545342535e-05
2023-01-23 04:22:29.871785: step: 1176/530, loss: 5.455017162603326e-05
2023-01-23 04:22:30.987812: step: 1180/530, loss: 0.005130958743393421
2023-01-23 04:22:32.057306: step: 1184/530, loss: 0.0002884388086386025
2023-01-23 04:22:33.150999: step: 1188/530, loss: 0.0047550201416015625
2023-01-23 04:22:34.255473: step: 1192/530, loss: 0.03452110290527344
2023-01-23 04:22:35.359501: step: 1196/530, loss: 0.008860398083925247
2023-01-23 04:22:36.453533: step: 1200/530, loss: 7.090569124557078e-05
2023-01-23 04:22:37.547815: step: 1204/530, loss: 1.0585785275907256e-05
2023-01-23 04:22:38.665861: step: 1208/530, loss: 0.0445004478096962
2023-01-23 04:22:39.759768: step: 1212/530, loss: 2.6226043701171875e-06
2023-01-23 04:22:40.937525: step: 1216/530, loss: 0.002046013018116355
2023-01-23 04:22:42.039924: step: 1220/530, loss: 0.01266031339764595
2023-01-23 04:22:43.117997: step: 1224/530, loss: 6.246566954359878e-06
2023-01-23 04:22:44.230633: step: 1228/530, loss: 0.00030889513436704874
2023-01-23 04:22:45.317111: step: 1232/530, loss: 3.967285010730848e-05
2023-01-23 04:22:46.406387: step: 1236/530, loss: 0.0002111435023834929
2023-01-23 04:22:47.530175: step: 1240/530, loss: 0.000312614458380267
2023-01-23 04:22:48.640567: step: 1244/530, loss: 0.0019449711544439197
2023-01-23 04:22:49.751415: step: 1248/530, loss: 0.005079841706901789
2023-01-23 04:22:50.842444: step: 1252/530, loss: 0.00550689734518528
2023-01-23 04:22:51.929691: step: 1256/530, loss: 0.001361846923828125
2023-01-23 04:22:53.041621: step: 1260/530, loss: 0.0181577205657959
2023-01-23 04:22:54.142168: step: 1264/530, loss: 0.0506596565246582
2023-01-23 04:22:55.202322: step: 1268/530, loss: 2.3365021206700476e-06
2023-01-23 04:22:56.315732: step: 1272/530, loss: 4.19616708313697e-06
2023-01-23 04:22:57.428394: step: 1276/530, loss: 0.4252834618091583
2023-01-23 04:22:58.495159: step: 1280/530, loss: 9.870529902400449e-05
2023-01-23 04:22:59.587359: step: 1284/530, loss: 0.0007711410289630294
2023-01-23 04:23:00.684578: step: 1288/530, loss: 7.772445678710938e-05
2023-01-23 04:23:01.787944: step: 1292/530, loss: 0.006256484892219305
2023-01-23 04:23:02.929788: step: 1296/530, loss: 0.00016078949556685984
2023-01-23 04:23:04.030032: step: 1300/530, loss: 2.307891918462701e-05
2023-01-23 04:23:05.116429: step: 1304/530, loss: 0.00018558502779342234
2023-01-23 04:23:06.188380: step: 1308/530, loss: 0.0006884575122967362
2023-01-23 04:23:07.286348: step: 1312/530, loss: -7.4386593951203395e-06
2023-01-23 04:23:08.388179: step: 1316/530, loss: 0.0002462386910337955
2023-01-23 04:23:09.502026: step: 1320/530, loss: 0.006736373994499445
2023-01-23 04:23:10.616806: step: 1324/530, loss: 2.555847095209174e-05
2023-01-23 04:23:11.708194: step: 1328/530, loss: 0.0010400773026049137
2023-01-23 04:23:12.840267: step: 1332/530, loss: 0.0006032944074831903
2023-01-23 04:23:13.968680: step: 1336/530, loss: 0.001121139619499445
2023-01-23 04:23:15.075163: step: 1340/530, loss: 2.822876012942288e-05
2023-01-23 04:23:16.168358: step: 1344/530, loss: 8.087158494163305e-05
2023-01-23 04:23:17.284573: step: 1348/530, loss: -1.8215179807157256e-05
2023-01-23 04:23:18.379813: step: 1352/530, loss: 0.00023841859365347773
2023-01-23 04:23:19.484440: step: 1356/530, loss: -4.863738467975054e-06
2023-01-23 04:23:20.592669: step: 1360/530, loss: 0.011794280260801315
2023-01-23 04:23:21.728720: step: 1364/530, loss: 0.0020538331009447575
2023-01-23 04:23:22.833873: step: 1368/530, loss: 0.00014352798461914062
2023-01-23 04:23:23.963438: step: 1372/530, loss: 0.0250486359000206
2023-01-23 04:23:25.063604: step: 1376/530, loss: 0.010883426293730736
2023-01-23 04:23:26.181472: step: 1380/530, loss: 0.016922378912568092
2023-01-23 04:23:27.293098: step: 1384/530, loss: 0.0009827613830566406
2023-01-23 04:23:28.401850: step: 1388/530, loss: 0.017726421356201172
2023-01-23 04:23:29.491031: step: 1392/530, loss: 0.0227032657712698
2023-01-23 04:23:30.606142: step: 1396/530, loss: 1.773834264895413e-05
2023-01-23 04:23:31.690077: step: 1400/530, loss: 0.004320716951042414
2023-01-23 04:23:32.801696: step: 1404/530, loss: 0.052590563893318176
2023-01-23 04:23:33.947393: step: 1408/530, loss: 0.00010766983177745715
2023-01-23 04:23:35.031864: step: 1412/530, loss: 0.02021484635770321
2023-01-23 04:23:36.131463: step: 1416/530, loss: 1.201629675051663e-05
2023-01-23 04:23:37.214231: step: 1420/530, loss: 0.00013103484525345266
2023-01-23 04:23:38.305503: step: 1424/530, loss: 0.0021976472344249487
2023-01-23 04:23:39.421317: step: 1428/530, loss: 0.0019039154285565019
2023-01-23 04:23:40.543190: step: 1432/530, loss: 0.0010318756103515625
2023-01-23 04:23:41.638735: step: 1436/530, loss: -3.910064606316155e-06
2023-01-23 04:23:42.734206: step: 1440/530, loss: 4.94956984766759e-05
2023-01-23 04:23:43.848112: step: 1444/530, loss: 7.867813110351562e-06
2023-01-23 04:23:44.914869: step: 1448/530, loss: 3.0183793569449335e-05
2023-01-23 04:23:46.029628: step: 1452/530, loss: 0.012162781320512295
2023-01-23 04:23:47.132575: step: 1456/530, loss: -1.5258789289873675e-06
2023-01-23 04:23:48.216358: step: 1460/530, loss: 0.0005529403570108116
2023-01-23 04:23:49.326373: step: 1464/530, loss: 0.01263351459056139
2023-01-23 04:23:50.400820: step: 1468/530, loss: 0.04742584377527237
2023-01-23 04:23:51.527631: step: 1472/530, loss: 0.00010356903658248484
2023-01-23 04:23:52.617256: step: 1476/530, loss: 0.010910892859101295
2023-01-23 04:23:53.739439: step: 1480/530, loss: 0.0010728836059570312
2023-01-23 04:23:54.832646: step: 1484/530, loss: 2.28881845032447e-06
2023-01-23 04:23:55.918844: step: 1488/530, loss: 0.02781372144818306
2023-01-23 04:23:57.003783: step: 1492/530, loss: -1.3351440202313825e-06
2023-01-23 04:23:58.122646: step: 1496/530, loss: 3.619194103521295e-05
2023-01-23 04:23:59.213122: step: 1500/530, loss: 0.00023479462834075093
2023-01-23 04:24:00.330138: step: 1504/530, loss: 0.0010267258621752262
2023-01-23 04:24:01.462610: step: 1508/530, loss: 4.95910626341356e-06
2023-01-23 04:24:02.560612: step: 1512/530, loss: 5.464554124046117e-05
2023-01-23 04:24:03.682850: step: 1516/530, loss: 5.53131103515625e-05
2023-01-23 04:24:04.772784: step: 1520/530, loss: 0.0007488250848837197
2023-01-23 04:24:05.862434: step: 1524/530, loss: 0.010063553228974342
2023-01-23 04:24:06.978089: step: 1528/530, loss: 5.035400317865424e-05
2023-01-23 04:24:08.091074: step: 1532/530, loss: 0.001187992049381137
2023-01-23 04:24:09.205858: step: 1536/530, loss: 7.343292054429185e-06
2023-01-23 04:24:10.299774: step: 1540/530, loss: 0.0012093543773517013
2023-01-23 04:24:11.411026: step: 1544/530, loss: 1.869201696536038e-05
2023-01-23 04:24:12.536299: step: 1548/530, loss: 0.00020904542179778218
2023-01-23 04:24:13.638211: step: 1552/530, loss: 0.0028181076049804688
2023-01-23 04:24:14.777921: step: 1556/530, loss: 0.0262451171875
2023-01-23 04:24:15.881199: step: 1560/530, loss: 0.03380327299237251
2023-01-23 04:24:16.988515: step: 1564/530, loss: 0.12318307161331177
2023-01-23 04:24:18.087454: step: 1568/530, loss: 0.24842096865177155
2023-01-23 04:24:19.188862: step: 1572/530, loss: 0.0003291606844868511
2023-01-23 04:24:20.322121: step: 1576/530, loss: 0.0035772323608398438
2023-01-23 04:24:21.427504: step: 1580/530, loss: -1.3351436791708693e-06
2023-01-23 04:24:22.534542: step: 1584/530, loss: 2.1266938347253017e-05
2023-01-23 04:24:23.616457: step: 1588/530, loss: 1.0776519957289565e-05
2023-01-23 04:24:24.705592: step: 1592/530, loss: 0.00022430421086028218
2023-01-23 04:24:25.788090: step: 1596/530, loss: 6.675720669591101e-07
2023-01-23 04:24:26.905879: step: 1600/530, loss: 1.7833710444392636e-05
2023-01-23 04:24:28.063917: step: 1604/530, loss: 0.00043020248995162547
2023-01-23 04:24:29.193234: step: 1608/530, loss: 0.0005462646367959678
2023-01-23 04:24:30.355087: step: 1612/530, loss: 0.0023721696343272924
2023-01-23 04:24:31.476930: step: 1616/530, loss: 8.106231689453125e-06
2023-01-23 04:24:32.577021: step: 1620/530, loss: 0.009445000439882278
2023-01-23 04:24:33.690195: step: 1624/530, loss: 0.00015916823758743703
2023-01-23 04:24:34.796236: step: 1628/530, loss: 0.002831840654835105
2023-01-23 04:24:35.869664: step: 1632/530, loss: 2.19345088225964e-06
2023-01-23 04:24:36.976734: step: 1636/530, loss: 2.632141149661038e-05
2023-01-23 04:24:38.065754: step: 1640/530, loss: 2.918243444582913e-05
2023-01-23 04:24:39.164961: step: 1644/530, loss: 0.0029728414956480265
2023-01-23 04:24:40.286584: step: 1648/530, loss: 0.00014982224092818797
2023-01-23 04:24:41.374961: step: 1652/530, loss: 0.0015291214222088456
2023-01-23 04:24:42.466345: step: 1656/530, loss: 0.004897594451904297
2023-01-23 04:24:43.576981: step: 1660/530, loss: 2.784729076665826e-05
2023-01-23 04:24:44.700454: step: 1664/530, loss: 0.1471010148525238
2023-01-23 04:24:45.778203: step: 1668/530, loss: 1.0395049685030244e-05
2023-01-23 04:24:46.881319: step: 1672/530, loss: 0.0003562927304301411
2023-01-23 04:24:47.985461: step: 1676/530, loss: 5.4931642807787284e-05
2023-01-23 04:24:49.092568: step: 1680/530, loss: 0.0004313468816690147
2023-01-23 04:24:50.219331: step: 1684/530, loss: 0.023760128766298294
2023-01-23 04:24:51.336494: step: 1688/530, loss: 0.0010833740234375
2023-01-23 04:24:52.437333: step: 1692/530, loss: 5.111694190418348e-05
2023-01-23 04:24:53.561780: step: 1696/530, loss: 4.305839684093371e-05
2023-01-23 04:24:54.676976: step: 1700/530, loss: 2.5749204723979346e-06
2023-01-23 04:24:55.769169: step: 1704/530, loss: 4.301071021473035e-05
2023-01-23 04:24:56.902665: step: 1708/530, loss: 9.5367431640625e-06
2023-01-23 04:24:58.016069: step: 1712/530, loss: 0.00021529197692871094
2023-01-23 04:24:59.151476: step: 1716/530, loss: 0.0006444930913858116
2023-01-23 04:25:00.281685: step: 1720/530, loss: 6.65664701955393e-05
2023-01-23 04:25:01.358597: step: 1724/530, loss: 0.0013866424560546875
2023-01-23 04:25:02.488998: step: 1728/530, loss: 0.030509136617183685
2023-01-23 04:25:03.591144: step: 1732/530, loss: 0.00017833711171988398
2023-01-23 04:25:04.669274: step: 1736/530, loss: 0.00022220611572265625
2023-01-23 04:25:05.767212: step: 1740/530, loss: 1.6117095583467744e-05
2023-01-23 04:25:06.892791: step: 1744/530, loss: 4.305839684093371e-05
2023-01-23 04:25:08.001565: step: 1748/530, loss: 0.010710716247558594
2023-01-23 04:25:09.112761: step: 1752/530, loss: 0.00498700188472867
2023-01-23 04:25:10.225452: step: 1756/530, loss: 0.0033548830542713404
2023-01-23 04:25:11.329316: step: 1760/530, loss: 0.004049873445183039
2023-01-23 04:25:12.416537: step: 1764/530, loss: 0.013058949261903763
2023-01-23 04:25:13.521450: step: 1768/530, loss: 0.0026417733170092106
2023-01-23 04:25:14.632384: step: 1772/530, loss: 2.1934511096333154e-05
2023-01-23 04:25:15.787698: step: 1776/530, loss: 0.0008058547973632812
2023-01-23 04:25:16.901728: step: 1780/530, loss: 0.0002092361537506804
2023-01-23 04:25:18.031134: step: 1784/530, loss: 0.11256122589111328
2023-01-23 04:25:19.139262: step: 1788/530, loss: 0.004712057299911976
2023-01-23 04:25:20.273039: step: 1792/530, loss: 0.03334465250372887
2023-01-23 04:25:21.382714: step: 1796/530, loss: 0.0004414081631693989
2023-01-23 04:25:22.483360: step: 1800/530, loss: 1.506805438111769e-05
2023-01-23 04:25:23.595233: step: 1804/530, loss: 0.06063595041632652
2023-01-23 04:25:24.704144: step: 1808/530, loss: 0.0013854980934411287
2023-01-23 04:25:25.806881: step: 1812/530, loss: 9.622574725653976e-05
2023-01-23 04:25:26.941142: step: 1816/530, loss: 0.023438835516572
2023-01-23 04:25:28.045964: step: 1820/530, loss: 0.004013252444565296
2023-01-23 04:25:29.157323: step: 1824/530, loss: 0.0030981062445789576
2023-01-23 04:25:30.257867: step: 1828/530, loss: 0.12134285271167755
2023-01-23 04:25:31.360932: step: 1832/530, loss: 0.00010433197167003527
2023-01-23 04:25:32.503267: step: 1836/530, loss: 0.00027232171851210296
2023-01-23 04:25:33.599792: step: 1840/530, loss: 0.004335212986916304
2023-01-23 04:25:34.664739: step: 1844/530, loss: 0.000164031982421875
2023-01-23 04:25:35.789367: step: 1848/530, loss: 0.035561371594667435
2023-01-23 04:25:36.904476: step: 1852/530, loss: 0.14002734422683716
2023-01-23 04:25:38.037471: step: 1856/530, loss: 1.8787384760798886e-05
2023-01-23 04:25:39.183180: step: 1860/530, loss: 0.01986560970544815
2023-01-23 04:25:40.298246: step: 1864/530, loss: 0.002645397325977683
2023-01-23 04:25:41.421359: step: 1868/530, loss: 0.0004326820489950478
2023-01-23 04:25:42.550445: step: 1872/530, loss: 0.07766446471214294
2023-01-23 04:25:43.700927: step: 1876/530, loss: 0.00013055800809524953
2023-01-23 04:25:44.794678: step: 1880/530, loss: 3.5858156479662284e-05
2023-01-23 04:25:45.906654: step: 1884/530, loss: 0.04719515144824982
2023-01-23 04:25:47.048875: step: 1888/530, loss: 3.1948089599609375e-05
2023-01-23 04:25:48.146526: step: 1892/530, loss: 0.0010848998790606856
2023-01-23 04:25:49.255191: step: 1896/530, loss: 0.00013999939255882055
2023-01-23 04:25:50.364024: step: 1900/530, loss: 0.05254707485437393
2023-01-23 04:25:51.486174: step: 1904/530, loss: 0.00010523795936023816
2023-01-23 04:25:52.607318: step: 1908/530, loss: 2.2554397219209932e-05
2023-01-23 04:25:53.720882: step: 1912/530, loss: 6.8664553509734105e-06
2023-01-23 04:25:54.820741: step: 1916/530, loss: 0.00041790009709075093
2023-01-23 04:25:55.914052: step: 1920/530, loss: 0.0242767333984375
2023-01-23 04:25:57.039232: step: 1924/530, loss: 0.008136939257383347
2023-01-23 04:25:58.130772: step: 1928/530, loss: 0.0008774757734499872
2023-01-23 04:25:59.203216: step: 1932/530, loss: 2.9277802241267636e-05
2023-01-23 04:26:00.303297: step: 1936/530, loss: -4.196166628389619e-06
2023-01-23 04:26:01.399331: step: 1940/530, loss: 0.005142879206687212
2023-01-23 04:26:02.501523: step: 1944/530, loss: 0.0016587257850915194
2023-01-23 04:26:03.603083: step: 1948/530, loss: 0.019158076494932175
2023-01-23 04:26:04.704992: step: 1952/530, loss: 0.005306816194206476
2023-01-23 04:26:05.828432: step: 1956/530, loss: 0.001859426498413086
2023-01-23 04:26:06.932037: step: 1960/530, loss: 4.501342846197076e-05
2023-01-23 04:26:08.018872: step: 1964/530, loss: 0.0017673493130132556
2023-01-23 04:26:09.121208: step: 1968/530, loss: 0.021413613110780716
2023-01-23 04:26:10.234359: step: 1972/530, loss: 0.011100483126938343
2023-01-23 04:26:11.333271: step: 1976/530, loss: 0.03028392791748047
2023-01-23 04:26:12.412857: step: 1980/530, loss: 0.0007142543909139931
2023-01-23 04:26:13.559059: step: 1984/530, loss: 0.00026192667428404093
2023-01-23 04:26:14.715126: step: 1988/530, loss: 3.452301098150201e-05
2023-01-23 04:26:15.809509: step: 1992/530, loss: 0.0020510198082774878
2023-01-23 04:26:16.956098: step: 1996/530, loss: 0.0008483887067995965
2023-01-23 04:26:18.033527: step: 2000/530, loss: 0.0001583099365234375
2023-01-23 04:26:19.119281: step: 2004/530, loss: 0.00597991980612278
2023-01-23 04:26:20.218162: step: 2008/530, loss: 0.0006293297046795487
2023-01-23 04:26:21.364189: step: 2012/530, loss: 0.0004289627249818295
2023-01-23 04:26:22.497186: step: 2016/530, loss: -1.1920928955078125e-06
2023-01-23 04:26:23.589041: step: 2020/530, loss: 0.028151322156190872
2023-01-23 04:26:24.701383: step: 2024/530, loss: 4.749298022943549e-05
2023-01-23 04:26:25.798795: step: 2028/530, loss: 0.0016389847733080387
2023-01-23 04:26:26.888078: step: 2032/530, loss: 0.0014969349140301347
2023-01-23 04:26:27.949031: step: 2036/530, loss: 0.0001476764737162739
2023-01-23 04:26:29.057615: step: 2040/530, loss: 0.008602429181337357
2023-01-23 04:26:30.168156: step: 2044/530, loss: 0.004796028137207031
2023-01-23 04:26:31.264267: step: 2048/530, loss: 0.08157216012477875
2023-01-23 04:26:32.380170: step: 2052/530, loss: 0.00031261442927643657
2023-01-23 04:26:33.480434: step: 2056/530, loss: 3.814697322468419e-07
2023-01-23 04:26:34.606359: step: 2060/530, loss: 0.002353382296860218
2023-01-23 04:26:35.691027: step: 2064/530, loss: 9.34600848268019e-06
2023-01-23 04:26:36.798276: step: 2068/530, loss: 2.6226043701171875e-05
2023-01-23 04:26:37.914772: step: 2072/530, loss: 0.00015964507474564016
2023-01-23 04:26:39.022766: step: 2076/530, loss: 0.009865951724350452
2023-01-23 04:26:40.132408: step: 2080/530, loss: 1.0277678966522217
2023-01-23 04:26:41.265632: step: 2084/530, loss: 0.007714462466537952
2023-01-23 04:26:42.372575: step: 2088/530, loss: 0.0003246307314839214
2023-01-23 04:26:43.505883: step: 2092/530, loss: 0.0042854310013353825
2023-01-23 04:26:44.607454: step: 2096/530, loss: 0.0031880377791821957
2023-01-23 04:26:45.755120: step: 2100/530, loss: 0.0009963989723473787
2023-01-23 04:26:46.892064: step: 2104/530, loss: 0.002493238542228937
2023-01-23 04:26:47.987542: step: 2108/530, loss: 0.004219150636345148
2023-01-23 04:26:49.086889: step: 2112/530, loss: 0.005974722094833851
2023-01-23 04:26:50.181294: step: 2116/530, loss: 0.00011444091796875
2023-01-23 04:26:51.298576: step: 2120/530, loss: 0.03793644905090332
==================================================
Loss: 0.013
--------------------
Dev: {'event': {'p': 0.6045548654244306, 'r': 0.7776298268974701, 'f1': 0.6802562609202096}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 28}
Test: {'event': {'p': 0.6389016018306636, 'r': 0.8135198135198135, 'f1': 0.7157139195078185}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 28}
Chinese: {'event': {'p': 0.6164383561643836, 'r': 0.8333333333333334, 'f1': 0.7086614173228347}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 28}
Korean: {'event': {'p': 0.7619047619047619, 'r': 0.5079365079365079, 'f1': 0.6095238095238095}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 28}
Russian: {'event': {'p': 0.46153846153846156, 'r': 0.5, 'f1': 0.48000000000000004}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 28}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6449771689497716, 'r': 0.7523302263648469, 'f1': 0.6945298094652735}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Chinese: {'event': {'p': 0.6692644909887969, 'r': 0.8006993006993007, 'f1': 0.7291058636243036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Chinese: {'event': {'p': 0.6764705882352942, 'r': 0.8518518518518519, 'f1': 0.7540983606557378}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5873340143003064, 'r': 0.7656458055925432, 'f1': 0.6647398843930636}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Eng Test for Korean: {'event': {'p': 0.6496487119437939, 'r': 0.8082750582750583, 'f1': 0.7203323811996885}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Sample Korean: {'event': {'p': 0.6721311475409836, 'r': 0.6507936507936508, 'f1': 0.6612903225806451}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5971370143149284, 'r': 0.7776298268974701, 'f1': 0.6755349913244649}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Russian: {'event': {'p': 0.6401673640167364, 'r': 0.8024475524475524, 'f1': 0.7121799844840963}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Russian: {'event': {'p': 0.5897435897435898, 'r': 0.6388888888888888, 'f1': 0.6133333333333332}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
******************************
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 04:27:30.852704: step: 4/530, loss: 3.890991138177924e-05
2023-01-23 04:27:31.935997: step: 8/530, loss: 6.198883511387976e-06
2023-01-23 04:27:33.032457: step: 12/530, loss: 0.000780296279117465
2023-01-23 04:27:34.136376: step: 16/530, loss: 1.8978118532686494e-05
2023-01-23 04:27:35.257255: step: 20/530, loss: 0.005344391334801912
2023-01-23 04:27:36.363658: step: 24/530, loss: 0.0016595841152593493
2023-01-23 04:27:37.471506: step: 28/530, loss: 0.0007118225912563503
2023-01-23 04:27:38.634750: step: 32/530, loss: 0.00027694704476743937
2023-01-23 04:27:39.758025: step: 36/530, loss: 0.03676815330982208
2023-01-23 04:27:40.850271: step: 40/530, loss: 3.347396705066785e-05
2023-01-23 04:27:41.938547: step: 44/530, loss: 0.0037827491760253906
2023-01-23 04:27:43.037496: step: 48/530, loss: 0.011240005493164062
2023-01-23 04:27:44.148493: step: 52/530, loss: 0.017479324713349342
2023-01-23 04:27:45.246797: step: 56/530, loss: 4.9591067181609105e-06
2023-01-23 04:27:46.353005: step: 60/530, loss: 0.010850906372070312
2023-01-23 04:27:47.438412: step: 64/530, loss: 3.633499363786541e-05
2023-01-23 04:27:48.533617: step: 68/530, loss: 0.006569766905158758
2023-01-23 04:27:49.617414: step: 72/530, loss: 0.020728018134832382
2023-01-23 04:27:50.682595: step: 76/530, loss: 7.152557373046875e-05
2023-01-23 04:27:51.758942: step: 80/530, loss: 0.0005804061656817794
2023-01-23 04:27:52.854226: step: 84/530, loss: 0.014216899871826172
2023-01-23 04:27:53.979316: step: 88/530, loss: 0.0013484955998137593
2023-01-23 04:27:55.093222: step: 92/530, loss: 0.0015741349197924137
2023-01-23 04:27:56.216302: step: 96/530, loss: -1.392364538332913e-05
2023-01-23 04:27:57.302754: step: 100/530, loss: 9.193419828079641e-05
2023-01-23 04:27:58.413028: step: 104/530, loss: 0.0001548767031636089
2023-01-23 04:27:59.496315: step: 108/530, loss: -1.8215179807157256e-05
2023-01-23 04:28:00.570843: step: 112/530, loss: 1.583099401614163e-05
2023-01-23 04:28:01.639664: step: 116/530, loss: 4.272460864740424e-05
2023-01-23 04:28:02.758031: step: 120/530, loss: 0.0004975319025106728
2023-01-23 04:28:03.883287: step: 124/530, loss: 1.449584942747606e-05
2023-01-23 04:28:04.979143: step: 128/530, loss: -1.1205673217773438e-05
2023-01-23 04:28:06.082586: step: 132/530, loss: 2.09808349609375e-05
2023-01-23 04:28:07.174041: step: 136/530, loss: 0.010014343075454235
2023-01-23 04:28:08.277289: step: 140/530, loss: 6.370544724632055e-05
2023-01-23 04:28:09.400996: step: 144/530, loss: 0.00011339187767589465
2023-01-23 04:28:10.525438: step: 148/530, loss: 0.00023927689471747726
2023-01-23 04:28:11.619104: step: 152/530, loss: 0.00033359526423737407
2023-01-23 04:28:12.700055: step: 156/530, loss: 2.708435022213962e-05
2023-01-23 04:28:13.793851: step: 160/530, loss: 0.0004328727663960308
2023-01-23 04:28:14.888662: step: 164/530, loss: 0.0005460739484988153
2023-01-23 04:28:16.012493: step: 168/530, loss: 0.00011358260962879285
2023-01-23 04:28:17.135543: step: 172/530, loss: 0.00025196076603606343
2023-01-23 04:28:18.253297: step: 176/530, loss: 7.05719003235572e-06
2023-01-23 04:28:19.334969: step: 180/530, loss: 0.0013875007862225175
2023-01-23 04:28:20.446004: step: 184/530, loss: 0.00039091112557798624
2023-01-23 04:28:21.549144: step: 188/530, loss: 0.01099462527781725
2023-01-23 04:28:22.635327: step: 192/530, loss: 0.0025278092361986637
2023-01-23 04:28:23.727823: step: 196/530, loss: 1.907349087559851e-07
2023-01-23 04:28:24.817684: step: 200/530, loss: -1.0490417707842425e-06
2023-01-23 04:28:25.919861: step: 204/530, loss: 0.0064601898193359375
2023-01-23 04:28:27.022435: step: 208/530, loss: 3.0183793569449335e-05
2023-01-23 04:28:28.159085: step: 212/530, loss: 0.00010929107520496473
2023-01-23 04:28:29.278983: step: 216/530, loss: 1.3494491213350557e-05
2023-01-23 04:28:30.377890: step: 220/530, loss: 0.005573845002800226
2023-01-23 04:28:31.495950: step: 224/530, loss: 0.00548477191478014
2023-01-23 04:28:32.575586: step: 228/530, loss: 0.00038375856820493937
2023-01-23 04:28:33.690362: step: 232/530, loss: 4.6443939936580136e-05
2023-01-23 04:28:34.797937: step: 236/530, loss: 8.0108642578125e-05
2023-01-23 04:28:35.886159: step: 240/530, loss: 0.008176421746611595
2023-01-23 04:28:37.005491: step: 244/530, loss: 0.034354403614997864
2023-01-23 04:28:38.078723: step: 248/530, loss: 1.0961294719891157e-05
2023-01-23 04:28:39.209325: step: 252/530, loss: 0.011131287552416325
2023-01-23 04:28:40.311331: step: 256/530, loss: 0.00012502670870162547
2023-01-23 04:28:41.459898: step: 260/530, loss: 7.02858014847152e-05
2023-01-23 04:28:42.564742: step: 264/530, loss: 2.28881845032447e-06
2023-01-23 04:28:43.671578: step: 268/530, loss: 0.012936783023178577
2023-01-23 04:28:44.751145: step: 272/530, loss: 5.5265431001316756e-05
2023-01-23 04:28:45.849480: step: 276/530, loss: 2.8610247682081535e-07
2023-01-23 04:28:46.956211: step: 280/530, loss: 0.00015001297288108617
2023-01-23 04:28:48.037932: step: 284/530, loss: 1.9168854123563506e-05
2023-01-23 04:28:49.181580: step: 288/530, loss: 0.0020424844697117805
2023-01-23 04:28:50.334062: step: 292/530, loss: 2.5844574338407256e-05
2023-01-23 04:28:51.446378: step: 296/530, loss: 0.0004562377871479839
2023-01-23 04:28:52.562088: step: 300/530, loss: 0.03921656310558319
2023-01-23 04:28:53.687724: step: 304/530, loss: 0.029955388978123665
2023-01-23 04:28:54.814693: step: 308/530, loss: 0.0005227088695392013
2023-01-23 04:28:55.911239: step: 312/530, loss: 1.716613724056515e-06
2023-01-23 04:28:57.031693: step: 316/530, loss: 1.239776611328125e-05
2023-01-23 04:28:58.101955: step: 320/530, loss: 0.003644275479018688
2023-01-23 04:28:59.214474: step: 324/530, loss: 0.00013256072998046875
2023-01-23 04:29:00.288144: step: 328/530, loss: 4.94956984766759e-05
2023-01-23 04:29:01.360274: step: 332/530, loss: 0.0006685256958007812
2023-01-23 04:29:02.461358: step: 336/530, loss: 0.00012159347534179688
2023-01-23 04:29:03.564251: step: 340/530, loss: 0.01426792237907648
2023-01-23 04:29:04.640033: step: 344/530, loss: 0.0007764339097775519
2023-01-23 04:29:05.764033: step: 348/530, loss: 1.6498566765221767e-05
2023-01-23 04:29:06.864864: step: 352/530, loss: 8.0108642578125e-05
2023-01-23 04:29:07.943613: step: 356/530, loss: 0.01762542687356472
2023-01-23 04:29:09.050664: step: 360/530, loss: 0.008090591058135033
2023-01-23 04:29:10.133938: step: 364/530, loss: 0.00021429063053801656
2023-01-23 04:29:11.232157: step: 368/530, loss: 0.0017854692414402962
2023-01-23 04:29:12.327380: step: 372/530, loss: 0.0031813145615160465
2023-01-23 04:29:13.405839: step: 376/530, loss: 8.822679956210777e-05
2023-01-23 04:29:14.485490: step: 380/530, loss: 5.222559047979303e-05
2023-01-23 04:29:15.595225: step: 384/530, loss: 0.0020753622520715
2023-01-23 04:29:16.682448: step: 388/530, loss: 0.00017557146202307194
2023-01-23 04:29:17.778635: step: 392/530, loss: 0.0038789750542491674
2023-01-23 04:29:18.905871: step: 396/530, loss: 0.0021792410407215357
2023-01-23 04:29:20.015693: step: 400/530, loss: 0.03272876888513565
2023-01-23 04:29:21.113298: step: 404/530, loss: 5.0926206313306466e-05
2023-01-23 04:29:22.205836: step: 408/530, loss: 1.182556115963962e-05
2023-01-23 04:29:23.297880: step: 412/530, loss: 0.0017423630924895406
2023-01-23 04:29:24.401873: step: 416/530, loss: 0.00044622423592954874
2023-01-23 04:29:25.513723: step: 420/530, loss: -1.1420250302762724e-05
2023-01-23 04:29:26.626441: step: 424/530, loss: 0.0032587051391601562
2023-01-23 04:29:27.709916: step: 428/530, loss: -1.8119811784345075e-06
2023-01-23 04:29:28.824303: step: 432/530, loss: 0.010600185953080654
2023-01-23 04:29:29.926936: step: 436/530, loss: 0.00033550261287018657
2023-01-23 04:29:31.028524: step: 440/530, loss: 0.5257606506347656
2023-01-23 04:29:32.124686: step: 444/530, loss: 0.0025041578337550163
2023-01-23 04:29:33.240667: step: 448/530, loss: 0.03446917608380318
2023-01-23 04:29:34.331943: step: 452/530, loss: 0.03645334392786026
2023-01-23 04:29:35.449419: step: 456/530, loss: 0.0035427093971520662
2023-01-23 04:29:36.541601: step: 460/530, loss: 2.307891918462701e-05
2023-01-23 04:29:37.668678: step: 464/530, loss: 1.9073486328125e-06
2023-01-23 04:29:38.751283: step: 468/530, loss: 7.24792471373803e-06
2023-01-23 04:29:39.892640: step: 472/530, loss: 7.057190487103071e-06
2023-01-23 04:29:40.984770: step: 476/530, loss: 0.0004782676696777344
2023-01-23 04:29:42.095039: step: 480/530, loss: 0.0024044038727879524
2023-01-23 04:29:43.188236: step: 484/530, loss: 5.884170241188258e-05
2023-01-23 04:29:44.293639: step: 488/530, loss: 0.0033718112390488386
2023-01-23 04:29:45.392632: step: 492/530, loss: 0.02174835279583931
2023-01-23 04:29:46.501949: step: 496/530, loss: 0.0005529403570108116
2023-01-23 04:29:47.595913: step: 500/530, loss: 0.00074005126953125
2023-01-23 04:29:48.745195: step: 504/530, loss: 0.001361084054224193
2023-01-23 04:29:49.859888: step: 508/530, loss: 0.05779757350683212
2023-01-23 04:29:50.959642: step: 512/530, loss: 0.00034122465876862407
2023-01-23 04:29:52.063092: step: 516/530, loss: 0.015423583798110485
2023-01-23 04:29:53.171958: step: 520/530, loss: 0.01027526892721653
2023-01-23 04:29:54.263839: step: 524/530, loss: 0.008314036764204502
2023-01-23 04:29:55.386154: step: 528/530, loss: 0.003544759703800082
2023-01-23 04:29:56.460744: step: 532/530, loss: 0.0021855831146240234
2023-01-23 04:29:57.580917: step: 536/530, loss: -4.539489600574598e-05
2023-01-23 04:29:58.638381: step: 540/530, loss: 0.0004616737423930317
2023-01-23 04:29:59.770268: step: 544/530, loss: 0.044037818908691406
2023-01-23 04:30:00.841817: step: 548/530, loss: 5.3215029765851796e-05
2023-01-23 04:30:01.908146: step: 552/530, loss: 0.0035499571822583675
2023-01-23 04:30:03.016694: step: 556/530, loss: 0.001546621322631836
2023-01-23 04:30:04.140685: step: 560/530, loss: 1.411438006471144e-05
2023-01-23 04:30:05.249034: step: 564/530, loss: 8.487701052217744e-06
2023-01-23 04:30:06.316548: step: 568/530, loss: 1.8024444216280244e-05
2023-01-23 04:30:07.421452: step: 572/530, loss: -5.722046125811175e-07
2023-01-23 04:30:08.550994: step: 576/530, loss: 0.31961217522621155
2023-01-23 04:30:09.638751: step: 580/530, loss: 0.04861736297607422
2023-01-23 04:30:10.746984: step: 584/530, loss: 1.3351441339182202e-06
2023-01-23 04:30:11.851771: step: 588/530, loss: 9.212493750965223e-05
2023-01-23 04:30:12.995766: step: 592/530, loss: 3.337860107421875e-05
2023-01-23 04:30:14.074148: step: 596/530, loss: 0.011237908154726028
2023-01-23 04:30:15.184203: step: 600/530, loss: 0.0005907058366574347
2023-01-23 04:30:16.317528: step: 604/530, loss: 0.04331379383802414
2023-01-23 04:30:17.402200: step: 608/530, loss: 6.146430678199977e-05
2023-01-23 04:30:18.502402: step: 612/530, loss: 0.008853530511260033
2023-01-23 04:30:19.628992: step: 616/530, loss: 7.305145845748484e-05
2023-01-23 04:30:20.732160: step: 620/530, loss: 4.501342846197076e-05
2023-01-23 04:30:21.862866: step: 624/530, loss: 3.137588646495715e-05
2023-01-23 04:30:22.949806: step: 628/530, loss: 7.467270188499242e-05
2023-01-23 04:30:24.053654: step: 632/530, loss: 3.719329924933845e-06
2023-01-23 04:30:25.168084: step: 636/530, loss: 0.0016036510933190584
2023-01-23 04:30:26.296777: step: 640/530, loss: 6.103515625e-05
2023-01-23 04:30:27.406363: step: 644/530, loss: 0.0002863883855752647
2023-01-23 04:30:28.522474: step: 648/530, loss: 0.04936389997601509
2023-01-23 04:30:29.655188: step: 652/530, loss: 0.0014019012451171875
2023-01-23 04:30:30.760044: step: 656/530, loss: 0.011093712411820889
2023-01-23 04:30:31.855231: step: 660/530, loss: 1.430511474609375e-06
2023-01-23 04:30:32.942414: step: 664/530, loss: 9.34600848268019e-06
2023-01-23 04:30:34.027122: step: 668/530, loss: 2.2125243049231358e-05
2023-01-23 04:30:35.146786: step: 672/530, loss: 0.04928307607769966
2023-01-23 04:30:36.269853: step: 676/530, loss: 0.00010032653517555445
2023-01-23 04:30:37.362507: step: 680/530, loss: 0.043377067893743515
2023-01-23 04:30:38.477544: step: 684/530, loss: 0.0004592895566020161
2023-01-23 04:30:39.567218: step: 688/530, loss: 0.0006210327264852822
2023-01-23 04:30:40.691758: step: 692/530, loss: 4.0531158447265625e-05
2023-01-23 04:30:41.783608: step: 696/530, loss: 0.019286155700683594
2023-01-23 04:30:42.862228: step: 700/530, loss: 0.0013612746261060238
2023-01-23 04:30:43.975386: step: 704/530, loss: 0.00032186511089093983
2023-01-23 04:30:45.083641: step: 708/530, loss: 5.7744979130802676e-05
2023-01-23 04:30:46.159164: step: 712/530, loss: 0.0013157606590539217
2023-01-23 04:30:47.245781: step: 716/530, loss: 6.341934204101562e-05
2023-01-23 04:30:48.348995: step: 720/530, loss: 4.615783836925402e-05
2023-01-23 04:30:49.480174: step: 724/530, loss: 1.7976761228055693e-05
2023-01-23 04:30:50.585323: step: 728/530, loss: 2.231597864010837e-05
2023-01-23 04:30:51.685457: step: 732/530, loss: 0.017851924523711205
2023-01-23 04:30:52.813577: step: 736/530, loss: 0.00011787414405262098
2023-01-23 04:30:53.951869: step: 740/530, loss: 0.006387901492416859
2023-01-23 04:30:55.055017: step: 744/530, loss: 0.0002860069216694683
2023-01-23 04:30:56.216412: step: 748/530, loss: 0.00010623932030284777
2023-01-23 04:30:57.314726: step: 752/530, loss: 0.006388283334672451
2023-01-23 04:30:58.427120: step: 756/530, loss: 0.00021567344083450735
2023-01-23 04:30:59.509759: step: 760/530, loss: 0.00027551653329283
2023-01-23 04:31:00.625475: step: 764/530, loss: 2.3746490114717744e-05
2023-01-23 04:31:01.755158: step: 768/530, loss: -5.507469268195564e-06
2023-01-23 04:31:02.887888: step: 772/530, loss: 0.0010121345985680819
2023-01-23 04:31:04.009620: step: 776/530, loss: 1.6021729607018642e-05
2023-01-23 04:31:05.115236: step: 780/530, loss: 8.39233416627394e-06
2023-01-23 04:31:06.236804: step: 784/530, loss: 0.0015523910988122225
2023-01-23 04:31:07.360915: step: 788/530, loss: 0.020052339881658554
2023-01-23 04:31:08.488039: step: 792/530, loss: 0.02536621317267418
2023-01-23 04:31:09.592243: step: 796/530, loss: 0.0010267257457599044
2023-01-23 04:31:10.683678: step: 800/530, loss: 6.866455805720761e-05
2023-01-23 04:31:11.823835: step: 804/530, loss: 0.10678310692310333
2023-01-23 04:31:12.912081: step: 808/530, loss: 0.0006478309514932334
2023-01-23 04:31:14.006371: step: 812/530, loss: 0.00012464524479582906
2023-01-23 04:31:15.129655: step: 816/530, loss: 0.0003482818719930947
2023-01-23 04:31:16.250620: step: 820/530, loss: 0.005203056614845991
2023-01-23 04:31:17.355372: step: 824/530, loss: 0.00028162001399323344
2023-01-23 04:31:18.467801: step: 828/530, loss: 0.004108619876205921
2023-01-23 04:31:19.585517: step: 832/530, loss: 0.0001050949067575857
2023-01-23 04:31:20.708564: step: 836/530, loss: 0.03114309348165989
2023-01-23 04:31:21.813232: step: 840/530, loss: 0.0004096984921488911
2023-01-23 04:31:22.937713: step: 844/530, loss: -2.86102294921875e-06
2023-01-23 04:31:24.010589: step: 848/530, loss: 0.00025815964909270406
2023-01-23 04:31:25.124441: step: 852/530, loss: 0.00041675567626953125
2023-01-23 04:31:26.228780: step: 856/530, loss: 0.0006967544904910028
2023-01-23 04:31:27.344481: step: 860/530, loss: 1.5354156857938506e-05
2023-01-23 04:31:28.433965: step: 864/530, loss: 0.002492713974788785
2023-01-23 04:31:29.522329: step: 868/530, loss: 0.0003426551993470639
2023-01-23 04:31:30.622976: step: 872/530, loss: 5.7220458984375e-06
2023-01-23 04:31:31.732858: step: 876/530, loss: 0.011728096753358841
2023-01-23 04:31:32.834685: step: 880/530, loss: 0.0033672333229333162
2023-01-23 04:31:33.942603: step: 884/530, loss: 1.4162063962430693e-05
2023-01-23 04:31:35.040527: step: 888/530, loss: 0.0014015198685228825
2023-01-23 04:31:36.146648: step: 892/530, loss: 0.003694724990054965
2023-01-23 04:31:37.289736: step: 896/530, loss: 0.0001392364501953125
2023-01-23 04:31:38.367463: step: 900/530, loss: 1.8501283193472773e-05
2023-01-23 04:31:39.494515: step: 904/530, loss: 0.02150108851492405
2023-01-23 04:31:40.609281: step: 908/530, loss: 0.003271674970164895
2023-01-23 04:31:41.708230: step: 912/530, loss: 8.821487426757812e-05
2023-01-23 04:31:42.842974: step: 916/530, loss: 0.00021638871112372726
2023-01-23 04:31:43.944488: step: 920/530, loss: 0.00019130708824377507
2023-01-23 04:31:45.043821: step: 924/530, loss: 0.0004391670227050781
2023-01-23 04:31:46.137834: step: 928/530, loss: 0.001921844552271068
2023-01-23 04:31:47.207591: step: 932/530, loss: 3.643035961431451e-05
2023-01-23 04:31:48.283356: step: 936/530, loss: 0.01632533222436905
2023-01-23 04:31:49.382432: step: 940/530, loss: 8.850097947288305e-05
2023-01-23 04:31:50.458869: step: 944/530, loss: 3.24249276673072e-06
2023-01-23 04:31:51.577206: step: 948/530, loss: 0.007223653607070446
2023-01-23 04:31:52.663599: step: 952/530, loss: 0.013106775470077991
2023-01-23 04:31:53.752891: step: 956/530, loss: 0.0002998829004354775
2023-01-23 04:31:54.870517: step: 960/530, loss: 0.00030956268892623484
2023-01-23 04:31:55.965352: step: 964/530, loss: 0.04158134385943413
2023-01-23 04:31:57.079874: step: 968/530, loss: 0.00016536712064407766
2023-01-23 04:31:58.178646: step: 972/530, loss: 0.01878223568201065
2023-01-23 04:31:59.282439: step: 976/530, loss: 2.9325485229492188e-05
2023-01-23 04:32:00.382898: step: 980/530, loss: 0.004874419886618853
2023-01-23 04:32:01.478044: step: 984/530, loss: 0.00011215209815418348
2023-01-23 04:32:02.598072: step: 988/530, loss: 0.008832740597426891
2023-01-23 04:32:03.678075: step: 992/530, loss: 0.00017585755267646164
2023-01-23 04:32:04.813923: step: 996/530, loss: 0.00022811890812590718
2023-01-23 04:32:05.912519: step: 1000/530, loss: 0.053105734288692474
2023-01-23 04:32:07.039285: step: 1004/530, loss: 0.00018310546875
2023-01-23 04:32:08.149720: step: 1008/530, loss: 2.2029877072782256e-05
2023-01-23 04:32:09.229476: step: 1012/530, loss: 0.0010477066971361637
2023-01-23 04:32:10.376785: step: 1016/530, loss: 0.017580414190888405
2023-01-23 04:32:11.467697: step: 1020/530, loss: 4.434585662238533e-06
2023-01-23 04:32:12.558927: step: 1024/530, loss: 0.014266586862504482
2023-01-23 04:32:13.737292: step: 1028/530, loss: 0.0001199722319142893
2023-01-23 04:32:14.838027: step: 1032/530, loss: 3.6811830796068534e-05
2023-01-23 04:32:15.932215: step: 1036/530, loss: 0.000347375898854807
2023-01-23 04:32:17.031038: step: 1040/530, loss: 0.000927352870348841
2023-01-23 04:32:18.173294: step: 1044/530, loss: 0.0008510589832440019
2023-01-23 04:32:19.311134: step: 1048/530, loss: 0.0007715702522546053
2023-01-23 04:32:20.433268: step: 1052/530, loss: 0.0011595726246014237
2023-01-23 04:32:21.578776: step: 1056/530, loss: 0.0020853043533861637
2023-01-23 04:32:22.689704: step: 1060/530, loss: 1.8024444216280244e-05
2023-01-23 04:32:23.800010: step: 1064/530, loss: 0.0004734992980957031
2023-01-23 04:32:24.944150: step: 1068/530, loss: 0.00264568324200809
2023-01-23 04:32:26.069218: step: 1072/530, loss: 0.0012210846180096269
2023-01-23 04:32:27.166425: step: 1076/530, loss: -4.76837158203125e-06
2023-01-23 04:32:28.284316: step: 1080/530, loss: 0.0407983772456646
2023-01-23 04:32:29.403612: step: 1084/530, loss: 0.13124600052833557
2023-01-23 04:32:30.502535: step: 1088/530, loss: -1.907349087559851e-07
2023-01-23 04:32:31.615146: step: 1092/530, loss: 0.04686775431036949
2023-01-23 04:32:32.707346: step: 1096/530, loss: 5.35011276951991e-05
2023-01-23 04:32:33.817553: step: 1100/530, loss: -4.95910626341356e-06
2023-01-23 04:32:34.906077: step: 1104/530, loss: 0.00028285980806685984
2023-01-23 04:32:36.013030: step: 1108/530, loss: -1.5258790426742053e-06
2023-01-23 04:32:37.108856: step: 1112/530, loss: -1.2777745723724365e-05
2023-01-23 04:32:38.200084: step: 1116/530, loss: 0.0007844925276003778
2023-01-23 04:32:39.298167: step: 1120/530, loss: 2.47955313170678e-06
2023-01-23 04:32:40.409576: step: 1124/530, loss: 4.181861731922254e-05
2023-01-23 04:32:41.520506: step: 1128/530, loss: 5.493163916980848e-05
2023-01-23 04:32:42.627600: step: 1132/530, loss: 0.0004955291515216231
2023-01-23 04:32:43.745844: step: 1136/530, loss: 0.0035698891151696444
2023-01-23 04:32:44.865597: step: 1140/530, loss: 0.0011486053699627519
2023-01-23 04:32:45.959898: step: 1144/530, loss: 0.05339193716645241
2023-01-23 04:32:47.069554: step: 1148/530, loss: 2.098083541568485e-06
2023-01-23 04:32:48.187276: step: 1152/530, loss: -5.34057608092553e-06
2023-01-23 04:32:49.278261: step: 1156/530, loss: 0.00012464523024391383
2023-01-23 04:32:50.418452: step: 1160/530, loss: -1.2302398317842744e-05
2023-01-23 04:32:51.501404: step: 1164/530, loss: 7.247925168485381e-06
2023-01-23 04:32:52.601216: step: 1168/530, loss: 0.000994873116724193
2023-01-23 04:32:53.694691: step: 1172/530, loss: 1.716613724056515e-06
2023-01-23 04:32:54.778313: step: 1176/530, loss: 0.0005027770530432463
2023-01-23 04:32:55.915758: step: 1180/530, loss: 5.0067901611328125e-05
2023-01-23 04:32:57.032062: step: 1184/530, loss: 5.817413693876006e-06
2023-01-23 04:32:58.111743: step: 1188/530, loss: 0.0020944594871252775
2023-01-23 04:32:59.208519: step: 1192/530, loss: 0.00014090538024902344
2023-01-23 04:33:00.331648: step: 1196/530, loss: 0.0024373054038733244
2023-01-23 04:33:01.427064: step: 1200/530, loss: 0.008447266183793545
2023-01-23 04:33:02.545122: step: 1204/530, loss: 0.03229274973273277
2023-01-23 04:33:03.639899: step: 1208/530, loss: 1.5354156857938506e-05
2023-01-23 04:33:04.734292: step: 1212/530, loss: 0.002697324613109231
2023-01-23 04:33:05.830174: step: 1216/530, loss: 0.0002155303955078125
2023-01-23 04:33:06.928776: step: 1220/530, loss: 0.013344001956284046
2023-01-23 04:33:08.038679: step: 1224/530, loss: 0.000156402587890625
2023-01-23 04:33:09.156042: step: 1228/530, loss: 0.00023918152146507055
2023-01-23 04:33:10.281261: step: 1232/530, loss: 0.017763758078217506
2023-01-23 04:33:11.388108: step: 1236/530, loss: 0.0007492065196856856
2023-01-23 04:33:12.507383: step: 1240/530, loss: 0.030246257781982422
2023-01-23 04:33:13.616481: step: 1244/530, loss: 0.007139683235436678
2023-01-23 04:33:14.724610: step: 1248/530, loss: 0.0008123397710733116
2023-01-23 04:33:15.815824: step: 1252/530, loss: 0.0007519721984863281
2023-01-23 04:33:16.943804: step: 1256/530, loss: 0.04609966278076172
2023-01-23 04:33:18.024134: step: 1260/530, loss: 0.002103185746818781
2023-01-23 04:33:19.183015: step: 1264/530, loss: 5.416870044427924e-05
2023-01-23 04:33:20.310440: step: 1268/530, loss: 0.003810882568359375
2023-01-23 04:33:21.404414: step: 1272/530, loss: 0.007046985439956188
2023-01-23 04:33:22.568908: step: 1276/530, loss: 2.6130677724722773e-05
2023-01-23 04:33:23.699580: step: 1280/530, loss: 0.0003641128714662045
2023-01-23 04:33:24.776959: step: 1284/530, loss: 0.004894828889518976
2023-01-23 04:33:25.851859: step: 1288/530, loss: 0.08625183254480362
2023-01-23 04:33:26.963462: step: 1292/530, loss: 6.284713163040578e-05
2023-01-23 04:33:28.057973: step: 1296/530, loss: 0.03153266757726669
2023-01-23 04:33:29.143564: step: 1300/530, loss: 0.0030193328857421875
2023-01-23 04:33:30.230972: step: 1304/530, loss: 2.002716064453125e-05
2023-01-23 04:33:31.356057: step: 1308/530, loss: 0.016692256554961205
2023-01-23 04:33:32.436467: step: 1312/530, loss: 0.0019135475158691406
2023-01-23 04:33:33.549316: step: 1316/530, loss: 0.0013895034790039062
2023-01-23 04:33:34.700004: step: 1320/530, loss: 0.02096405066549778
2023-01-23 04:33:35.800210: step: 1324/530, loss: 0.001596736954525113
2023-01-23 04:33:36.895906: step: 1328/530, loss: 0.0001398086460540071
2023-01-23 04:33:38.011710: step: 1332/530, loss: 4.978180004400201e-05
2023-01-23 04:33:39.102020: step: 1336/530, loss: 0.00035411419230513275
2023-01-23 04:33:40.196238: step: 1340/530, loss: 7.052422006381676e-05
2023-01-23 04:33:41.312939: step: 1344/530, loss: 7.719993300270289e-05
2023-01-23 04:33:42.397613: step: 1348/530, loss: 0.05265455320477486
2023-01-23 04:33:43.493773: step: 1352/530, loss: 1.1539459592313506e-05
2023-01-23 04:33:44.594899: step: 1356/530, loss: 0.00043845176696777344
2023-01-23 04:33:45.704717: step: 1360/530, loss: 0.0018323898548260331
2023-01-23 04:33:46.804132: step: 1364/530, loss: 7.05719003235572e-06
2023-01-23 04:33:47.902788: step: 1368/530, loss: 0.00014791489229537547
2023-01-23 04:33:48.992363: step: 1372/530, loss: 0.00033206940861418843
2023-01-23 04:33:50.108693: step: 1376/530, loss: 0.0012651443248614669
2023-01-23 04:33:51.190501: step: 1380/530, loss: 0.006691169925034046
2023-01-23 04:33:52.309489: step: 1384/530, loss: 0.00017976760864257812
2023-01-23 04:33:53.381920: step: 1388/530, loss: 0.0006376266246661544
2023-01-23 04:33:54.501286: step: 1392/530, loss: 3.43322744811303e-06
2023-01-23 04:33:55.595233: step: 1396/530, loss: 0.0034801482688635588
2023-01-23 04:33:56.669258: step: 1400/530, loss: 0.00205574044957757
2023-01-23 04:33:57.778543: step: 1404/530, loss: 4.57763671875e-05
2023-01-23 04:33:58.860190: step: 1408/530, loss: 0.03355369344353676
2023-01-23 04:33:59.975997: step: 1412/530, loss: 5.7697296142578125e-05
2023-01-23 04:34:01.088546: step: 1416/530, loss: 0.0007795334095135331
2023-01-23 04:34:02.184064: step: 1420/530, loss: 3.814697265625e-06
2023-01-23 04:34:03.312982: step: 1424/530, loss: -6.389617738022935e-06
2023-01-23 04:34:04.408510: step: 1428/530, loss: 0.00022048951359465718
2023-01-23 04:34:05.492835: step: 1432/530, loss: 0.0369873046875
2023-01-23 04:34:06.586302: step: 1436/530, loss: 0.0006166458479128778
2023-01-23 04:34:07.681568: step: 1440/530, loss: 0.0008240699535235763
2023-01-23 04:34:08.804225: step: 1444/530, loss: 0.02875046618282795
2023-01-23 04:34:09.892815: step: 1448/530, loss: 9.012222108140122e-06
2023-01-23 04:34:10.988951: step: 1452/530, loss: 0.00011897087097167969
2023-01-23 04:34:12.091316: step: 1456/530, loss: 6.198883056640625e-06
2023-01-23 04:34:13.177765: step: 1460/530, loss: 0.0026089190505445004
2023-01-23 04:34:14.276191: step: 1464/530, loss: 0.0026412964798510075
2023-01-23 04:34:15.409061: step: 1468/530, loss: 0.013840675354003906
2023-01-23 04:34:16.519611: step: 1472/530, loss: 0.01151733472943306
2023-01-23 04:34:17.609795: step: 1476/530, loss: 4.00543194700731e-06
2023-01-23 04:34:18.714983: step: 1480/530, loss: 0.0010827063815668225
2023-01-23 04:34:19.833325: step: 1484/530, loss: 6.427765038097277e-05
2023-01-23 04:34:20.947124: step: 1488/530, loss: 3.776550147449598e-05
2023-01-23 04:34:22.009769: step: 1492/530, loss: 0.0004416942538227886
2023-01-23 04:34:23.127479: step: 1496/530, loss: -2.269744800287299e-05
2023-01-23 04:34:24.217394: step: 1500/530, loss: 1.029968279908644e-05
2023-01-23 04:34:25.340591: step: 1504/530, loss: 8.106231689453125e-05
2023-01-23 04:34:26.444800: step: 1508/530, loss: 0.0003513336123432964
2023-01-23 04:34:27.536646: step: 1512/530, loss: 3.385544005141128e-06
2023-01-23 04:34:28.649444: step: 1516/530, loss: 0.0001958847133209929
2023-01-23 04:34:29.754218: step: 1520/530, loss: 6.322861008811742e-05
2023-01-23 04:34:30.838548: step: 1524/530, loss: 3.5762786865234375e-05
2023-01-23 04:34:31.930558: step: 1528/530, loss: 0.0002197265566792339
2023-01-23 04:34:33.051781: step: 1532/530, loss: 0.023019982501864433
2023-01-23 04:34:34.146951: step: 1536/530, loss: 3.7765505112474784e-05
2023-01-23 04:34:35.261355: step: 1540/530, loss: 0.002713489579036832
2023-01-23 04:34:36.360949: step: 1544/530, loss: 8.878708467818797e-05
2023-01-23 04:34:37.473615: step: 1548/530, loss: 0.0007563590770587325
2023-01-23 04:34:38.608906: step: 1552/530, loss: 2.689361645025201e-05
2023-01-23 04:34:39.715111: step: 1556/530, loss: 0.004341316409409046
2023-01-23 04:34:40.827787: step: 1560/530, loss: -7.43865984986769e-06
2023-01-23 04:34:41.981796: step: 1564/530, loss: 0.000636196113191545
2023-01-23 04:34:43.099710: step: 1568/530, loss: 0.0011468887096270919
2023-01-23 04:34:44.225765: step: 1572/530, loss: 0.024539949372410774
2023-01-23 04:34:45.336290: step: 1576/530, loss: 0.003494834993034601
2023-01-23 04:34:46.471897: step: 1580/530, loss: 0.0003715515194926411
2023-01-23 04:34:47.596547: step: 1584/530, loss: 7.085800461936742e-05
2023-01-23 04:34:48.721139: step: 1588/530, loss: 9.52720656641759e-05
2023-01-23 04:34:49.818086: step: 1592/530, loss: 0.1194818913936615
2023-01-23 04:34:50.909512: step: 1596/530, loss: 0.006272125523537397
2023-01-23 04:34:52.044900: step: 1600/530, loss: 0.007403469178825617
2023-01-23 04:34:53.169524: step: 1604/530, loss: 0.0004604339774232358
2023-01-23 04:34:54.266086: step: 1608/530, loss: 0.6316318511962891
2023-01-23 04:34:55.382026: step: 1612/530, loss: 0.0007030487176962197
2023-01-23 04:34:56.498711: step: 1616/530, loss: 7.553100294899195e-05
2023-01-23 04:34:57.599006: step: 1620/530, loss: 0.00012130737013649195
2023-01-23 04:34:58.671360: step: 1624/530, loss: 4.310607982915826e-05
2023-01-23 04:34:59.771787: step: 1628/530, loss: 1.5783309208927676e-05
2023-01-23 04:35:00.862138: step: 1632/530, loss: 0.051241107285022736
2023-01-23 04:35:01.987181: step: 1636/530, loss: 2.155303991457913e-05
2023-01-23 04:35:03.089865: step: 1640/530, loss: 0.0011890887981280684
2023-01-23 04:35:04.200020: step: 1644/530, loss: 0.0010676385136321187
2023-01-23 04:35:05.314608: step: 1648/530, loss: 0.007977867498993874
2023-01-23 04:35:06.407353: step: 1652/530, loss: 0.0008755684248171747
2023-01-23 04:35:07.489056: step: 1656/530, loss: 0.02317504957318306
2023-01-23 04:35:08.603648: step: 1660/530, loss: 0.006262397859245539
2023-01-23 04:35:09.702050: step: 1664/530, loss: 0.0007551193120889366
2023-01-23 04:35:10.785503: step: 1668/530, loss: 4.425048973644152e-05
2023-01-23 04:35:11.879944: step: 1672/530, loss: 0.001087188720703125
2023-01-23 04:35:12.989083: step: 1676/530, loss: -1.411438006471144e-05
2023-01-23 04:35:14.096718: step: 1680/530, loss: 0.0006421089055947959
2023-01-23 04:35:15.223759: step: 1684/530, loss: 5.0354006816633046e-05
2023-01-23 04:35:16.318851: step: 1688/530, loss: 0.017382431775331497
2023-01-23 04:35:17.407267: step: 1692/530, loss: 3.814698175119702e-06
2023-01-23 04:35:18.515284: step: 1696/530, loss: 0.009712029248476028
2023-01-23 04:35:19.588580: step: 1700/530, loss: 0.0010938644409179688
2023-01-23 04:35:20.675992: step: 1704/530, loss: 3.1757354008732364e-05
2023-01-23 04:35:21.761289: step: 1708/530, loss: 0.0444524809718132
2023-01-23 04:35:22.858391: step: 1712/530, loss: 0.0024413110222667456
2023-01-23 04:35:23.963378: step: 1716/530, loss: 0.0006350517505779862
2023-01-23 04:35:25.063965: step: 1720/530, loss: 0.01232757605612278
2023-01-23 04:35:26.211204: step: 1724/530, loss: 0.03368110954761505
2023-01-23 04:35:27.325848: step: 1728/530, loss: 0.00010776519775390625
2023-01-23 04:35:28.441882: step: 1732/530, loss: 0.00019168853759765625
2023-01-23 04:35:29.559837: step: 1736/530, loss: 0.01845264434814453
2023-01-23 04:35:30.672576: step: 1740/530, loss: -2.6893614631262608e-05
2023-01-23 04:35:31.737652: step: 1744/530, loss: 1.9454957509879023e-05
2023-01-23 04:35:32.850146: step: 1748/530, loss: 0.0001947402924997732
2023-01-23 04:35:33.947839: step: 1752/530, loss: 0.08016948401927948
2023-01-23 04:35:35.031021: step: 1756/530, loss: 0.029342079535126686
2023-01-23 04:35:36.115688: step: 1760/530, loss: 0.07217636704444885
2023-01-23 04:35:37.224502: step: 1764/530, loss: 8.010864803509321e-06
2023-01-23 04:35:38.356312: step: 1768/530, loss: 7.410049147438258e-05
2023-01-23 04:35:39.450776: step: 1772/530, loss: 0.04358520731329918
2023-01-23 04:35:40.551961: step: 1776/530, loss: 0.02006387710571289
2023-01-23 04:35:41.650050: step: 1780/530, loss: 7.710456702625379e-05
2023-01-23 04:35:42.755395: step: 1784/530, loss: 0.0009565353393554688
2023-01-23 04:35:43.873748: step: 1788/530, loss: 0.0006052971002645791
2023-01-23 04:35:44.992700: step: 1792/530, loss: 9.059906005859375e-05
2023-01-23 04:35:46.080492: step: 1796/530, loss: 0.02305593527853489
2023-01-23 04:35:47.204162: step: 1800/530, loss: 7.104873657226562e-05
2023-01-23 04:35:48.304265: step: 1804/530, loss: 0.02657165564596653
2023-01-23 04:35:49.410440: step: 1808/530, loss: 0.04848675802350044
2023-01-23 04:35:50.532139: step: 1812/530, loss: 0.0006486892816610634
2023-01-23 04:35:51.635463: step: 1816/530, loss: 1.5163422176556196e-05
2023-01-23 04:35:52.728128: step: 1820/530, loss: 3.0934810638427734e-05
2023-01-23 04:35:53.866734: step: 1824/530, loss: 0.002617454621940851
2023-01-23 04:35:54.969164: step: 1828/530, loss: 0.0002020835963776335
2023-01-23 04:35:56.055554: step: 1832/530, loss: 0.00014572143845725805
2023-01-23 04:35:57.173556: step: 1836/530, loss: 3.070831371587701e-05
2023-01-23 04:35:58.274210: step: 1840/530, loss: 0.006595039740204811
2023-01-23 04:35:59.369246: step: 1844/530, loss: 3.24249276673072e-06
2023-01-23 04:36:00.457088: step: 1848/530, loss: 0.38332873582839966
2023-01-23 04:36:01.587900: step: 1852/530, loss: 8.754729788051918e-05
2023-01-23 04:36:02.676994: step: 1856/530, loss: 0.0014815331669524312
2023-01-23 04:36:03.753478: step: 1860/530, loss: 5.91278076171875e-05
2023-01-23 04:36:04.853960: step: 1864/530, loss: 1.220703143189894e-05
2023-01-23 04:36:05.940364: step: 1868/530, loss: 0.0001296043483307585
2023-01-23 04:36:07.049017: step: 1872/530, loss: 0.002555465791374445
2023-01-23 04:36:08.160768: step: 1876/530, loss: 0.12273406982421875
2023-01-23 04:36:09.280346: step: 1880/530, loss: 0.0011685371864587069
2023-01-23 04:36:10.405879: step: 1884/530, loss: 0.000613355659879744
2023-01-23 04:36:11.527152: step: 1888/530, loss: 1.2969970157428179e-05
2023-01-23 04:36:12.613564: step: 1892/530, loss: 2.6035308110294864e-05
2023-01-23 04:36:13.728362: step: 1896/530, loss: 0.00016312600928358734
2023-01-23 04:36:14.834903: step: 1900/530, loss: 0.0007160186651162803
2023-01-23 04:36:15.927925: step: 1904/530, loss: 0.000484657270135358
2023-01-23 04:36:17.059442: step: 1908/530, loss: 3.108978125965223e-05
2023-01-23 04:36:18.145542: step: 1912/530, loss: 0.0006547927623614669
2023-01-23 04:36:19.247876: step: 1916/530, loss: 0.0013147353893145919
2023-01-23 04:36:20.340807: step: 1920/530, loss: 0.00020065308490302414
2023-01-23 04:36:21.443963: step: 1924/530, loss: 0.0026014328468590975
2023-01-23 04:36:22.594352: step: 1928/530, loss: 0.0006048202631063759
2023-01-23 04:36:23.703338: step: 1932/530, loss: 0.0004174232599325478
2023-01-23 04:36:24.831849: step: 1936/530, loss: 0.009001731872558594
2023-01-23 04:36:25.940603: step: 1940/530, loss: 8.096695091808215e-05
2023-01-23 04:36:27.043689: step: 1944/530, loss: -2.002716064453125e-05
2023-01-23 04:36:28.140760: step: 1948/530, loss: 4.00543194700731e-06
2023-01-23 04:36:29.246781: step: 1952/530, loss: 3.948211815441027e-05
2023-01-23 04:36:30.334804: step: 1956/530, loss: 0.0002763748343568295
2023-01-23 04:36:31.438304: step: 1960/530, loss: 0.0001084327741409652
2023-01-23 04:36:32.529122: step: 1964/530, loss: 2.174377368646674e-05
2023-01-23 04:36:33.649634: step: 1968/530, loss: 4.76837158203125e-06
2023-01-23 04:36:34.742531: step: 1972/530, loss: 0.02414684370160103
2023-01-23 04:36:35.859748: step: 1976/530, loss: 0.00010356903658248484
2023-01-23 04:36:37.004108: step: 1980/530, loss: 4.711151268566027e-05
2023-01-23 04:36:38.132272: step: 1984/530, loss: 0.0009056091657839715
2023-01-23 04:36:39.271689: step: 1988/530, loss: -4.196166628389619e-06
2023-01-23 04:36:40.402410: step: 1992/530, loss: 0.0012894630199298263
2023-01-23 04:36:41.505336: step: 1996/530, loss: 0.00011959076800849289
2023-01-23 04:36:42.605456: step: 2000/530, loss: 0.004378605168312788
2023-01-23 04:36:43.718339: step: 2004/530, loss: 0.03665943443775177
2023-01-23 04:36:44.851900: step: 2008/530, loss: -8.01086389401462e-06
2023-01-23 04:36:45.968128: step: 2012/530, loss: -1.087188684323337e-05
2023-01-23 04:36:47.088793: step: 2016/530, loss: 0.02641754224896431
2023-01-23 04:36:48.211741: step: 2020/530, loss: 0.000179290771484375
2023-01-23 04:36:49.316153: step: 2024/530, loss: 0.00010614395432639867
2023-01-23 04:36:50.451957: step: 2028/530, loss: 1.00374218163779e-05
2023-01-23 04:36:51.585668: step: 2032/530, loss: 0.0001964569091796875
2023-01-23 04:36:52.743122: step: 2036/530, loss: 0.0001243591250386089
2023-01-23 04:36:53.845959: step: 2040/530, loss: 0.009293843060731888
2023-01-23 04:36:54.974451: step: 2044/530, loss: 0.0001361370086669922
2023-01-23 04:36:56.098272: step: 2048/530, loss: 0.0009220839128829539
2023-01-23 04:36:57.193653: step: 2052/530, loss: 6.0367583500919864e-05
2023-01-23 04:36:58.293277: step: 2056/530, loss: 0.03232908248901367
2023-01-23 04:36:59.379606: step: 2060/530, loss: 0.0002918243408203125
2023-01-23 04:37:00.497666: step: 2064/530, loss: 0.00020189284987282008
2023-01-23 04:37:01.608816: step: 2068/530, loss: 0.001088047050870955
2023-01-23 04:37:02.713720: step: 2072/530, loss: 0.0007814407581463456
2023-01-23 04:37:03.837998: step: 2076/530, loss: 0.003830432891845703
2023-01-23 04:37:04.936976: step: 2080/530, loss: 0.014248276129364967
2023-01-23 04:37:06.016800: step: 2084/530, loss: 0.0001605033758096397
2023-01-23 04:37:07.126284: step: 2088/530, loss: 0.0002109050692524761
2023-01-23 04:37:08.229396: step: 2092/530, loss: 0.002663230989128351
2023-01-23 04:37:09.406947: step: 2096/530, loss: 0.00017042159743141383
2023-01-23 04:37:10.508431: step: 2100/530, loss: 0.019017985090613365
2023-01-23 04:37:11.604010: step: 2104/530, loss: 0.057625580579042435
2023-01-23 04:37:12.732897: step: 2108/530, loss: 0.00010948180715786293
2023-01-23 04:37:13.857271: step: 2112/530, loss: 4.768372718899627e-08
2023-01-23 04:37:14.958496: step: 2116/530, loss: 0.00043277739314362407
2023-01-23 04:37:16.083559: step: 2120/530, loss: 3.4141543437726796e-05
==================================================
Loss: 0.010
--------------------
Dev: {'event': {'p': 0.6085594989561587, 'r': 0.7762982689747004, 'f1': 0.6822703335283792}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 29}
Test: {'event': {'p': 0.6420269642026964, 'r': 0.8047785547785548, 'f1': 0.7142487716576158}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 29}
Chinese: {'event': {'p': 0.5769230769230769, 'r': 0.8333333333333334, 'f1': 0.6818181818181818}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 29}
Korean: {'event': {'p': 0.6111111111111112, 'r': 0.5238095238095238, 'f1': 0.5641025641025642}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 29}
Russian: {'event': {'p': 0.475, 'r': 0.5277777777777778, 'f1': 0.5}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 29}
==================================================
Current best result:
--------------------
Eng Dev for Chinese: {'event': {'p': 0.6449771689497716, 'r': 0.7523302263648469, 'f1': 0.6945298094652735}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Eng Test for Chinese: {'event': {'p': 0.6692644909887969, 'r': 0.8006993006993007, 'f1': 0.7291058636243036}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
Sample Chinese: {'event': {'p': 0.6764705882352942, 'r': 0.8518518518518519, 'f1': 0.7540983606557378}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 12}
--------------------
Eng Dev for Korean: {'event': {'p': 0.5873340143003064, 'r': 0.7656458055925432, 'f1': 0.6647398843930636}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Eng Test for Korean: {'event': {'p': 0.6496487119437939, 'r': 0.8082750582750583, 'f1': 0.7203323811996885}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
Sample Korean: {'event': {'p': 0.6721311475409836, 'r': 0.6507936507936508, 'f1': 0.6612903225806451}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 22}
--------------------
Eng Dev for Russian: {'event': {'p': 0.5971370143149284, 'r': 0.7776298268974701, 'f1': 0.6755349913244649}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Eng Test for Russian: {'event': {'p': 0.6401673640167364, 'r': 0.8024475524475524, 'f1': 0.7121799844840963}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}
Sample Russian: {'event': {'p': 0.5897435897435898, 'r': 0.6388888888888888, 'f1': 0.6133333333333332}, 'argument': {'p': 0.0, 'r': 0.0, 'f1': 0.0}, 'combined': 0.0, 'epoch': 9}